switch block layer polling to a bio based model v4

switch block layer polling to a bio based model v4

[Christoph Hellwig]

Hi all,

This series clean up the block polling code a bit and changes the interface
to poll for a specific bio instead of a request_queue and cookie pair.

Polling for the bio itself leads to a few advantages:

  - the cookie construction can made entirely private in blk-mq.c
  - the caller does not need to remember the request_queue and cookie
    separately and thus sidesteps their lifetime issues
  - keeping the device and the cookie inside the bio allows to trivially
    support polling BIOs remapping by stacking drivers
  - a lot of code to propagate the cookie back up the submission path can
    removed entirely

The one major caveat is that this requires RCU freeing polled BIOs to make
sure the bio that contains the polling information is still alive when
io_uring tries to poll it through the iocb. For synchronous polling all the
callers have a bio reference anyway, so this is not an issue.

Git tree:

   git://git.infradead.org/users/hch/block.git bio-poll

Gitweb:

    http://git.infradead.org/users/hch/block.git/shortlog/refs/heads/bio-poll

Chances since v3:
 - rebased to the latests for-5.14/block tree
 - fix the refcount logic in __blkdev_direct_IO
 - split up a patch to make it easier to review
 - grab a queue reference in bio_poll
 - better document the RCU assumptions in bio_poll

Chances since v2:
 - remove support for writing to the poll attribute
 - better document the block_device life time assumptions in bio_poll
 - only set QUEUE_FLAG_POLL on nvme-multipath queues where it makes sense

Chances since v1:
 - use SLAB_TYPESAFE_BY_RCU to only free the pages backing the bio
   slabs bio RCU
 - split the spin argument to bio_poll to avoid sleeping under RCU from
   io_uring
 - add support for polling nvme multipath devices

Diffstat:
 arch/m68k/emu/nfblock.c             |    3 
 arch/xtensa/platforms/iss/simdisk.c |    3 
 block/bio.c                         |    4 
 block/blk-core.c                    |  129 ++++++++++++++++++++------
 block/blk-merge.c                   |    2 
 block/blk-mq-debugfs.c              |    2 
 block/blk-mq.c                      |  173 ++++++++++++++----------------------
 block/blk-mq.h                      |    6 -
 block/blk-sysfs.c                   |   23 ----
 drivers/block/brd.c                 |   12 +-
 drivers/block/drbd/drbd_int.h       |    2 
 drivers/block/drbd/drbd_req.c       |    3 
 drivers/block/n64cart.c             |   12 +-
 drivers/block/null_blk/main.c       |    3 
 drivers/block/pktcdvd.c             |    7 -
 drivers/block/ps3vram.c             |    6 -
 drivers/block/rsxx/dev.c            |    7 -
 drivers/block/zram/zram_drv.c       |   10 --
 drivers/lightnvm/pblk-init.c        |    6 -
 drivers/md/bcache/request.c         |   13 +-
 drivers/md/bcache/request.h         |    4 
 drivers/md/dm.c                     |   28 ++---
 drivers/md/md.c                     |   10 --
 drivers/nvdimm/blk.c                |    5 -
 drivers/nvdimm/btt.c                |    5 -
 drivers/nvdimm/pmem.c               |    3 
 drivers/nvme/host/core.c            |    4 
 drivers/nvme/host/multipath.c       |   17 ++-
 drivers/s390/block/dcssblk.c        |    7 -
 drivers/s390/block/xpram.c          |    5 -
 drivers/scsi/scsi_debug.c           |   10 +-
 fs/block_dev.c                      |   44 ++-------
 fs/btrfs/inode.c                    |    8 -
 fs/direct-io.c                      |   14 --
 fs/ext4/file.c                      |    2 
 fs/gfs2/file.c                      |    4 
 fs/io_uring.c                       |   14 +-
 fs/iomap/direct-io.c                |   56 ++++++-----
 fs/xfs/xfs_file.c                   |    2 
 fs/zonefs/super.c                   |    2 
 include/linux/bio.h                 |    4 
 include/linux/blk-mq.h              |   15 ---
 include/linux/blk_types.h           |   34 +------
 include/linux/blkdev.h              |   12 +-
 include/linux/bvec.h                |    2 
 include/linux/fs.h                  |    8 -
 include/linux/iomap.h               |    3 
 mm/page_io.c                        |   10 --
 48 files changed, 350 insertions(+), 408 deletions(-)

[PATCH 01/16] direct-io: remove blk_poll support

[Christoph Hellwig]

The polling support in the legacy direct-io support is a little crufty.
It already doesn't support the asynchronous polling needed for io_uring
polling, and is hard to adopt to upcoming changes in the polling
interfaces.  Given that all the major file systems already use the iomap
direct I/O code, just drop the polling support.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Mark Wunderlich <mark.wunderlich@intel.com>
---
 fs/direct-io.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/fs/direct-io.c b/fs/direct-io.c
index b2e86e739d7a..453dcff0e7f5 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -119,7 +119,6 @@ struct dio {
 	int flags;			/* doesn't change */
 	int op;
 	int op_flags;
-	blk_qc_t bio_cookie;
 	struct gendisk *bio_disk;
 	struct inode *inode;
 	loff_t i_size;			/* i_size when submitted */
@@ -438,11 +437,10 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio)
 
 	dio->bio_disk = bio->bi_bdev->bd_disk;
 
-	if (sdio->submit_io) {
+	if (sdio->submit_io)
 		sdio->submit_io(bio, dio->inode, sdio->logical_offset_in_bio);
-		dio->bio_cookie = BLK_QC_T_NONE;
-	} else
-		dio->bio_cookie = submit_bio(bio);
+	else
+		submit_bio(bio);
 
 	sdio->bio = NULL;
 	sdio->boundary = 0;
@@ -481,9 +479,7 @@ static struct bio *dio_await_one(struct dio *dio)
 		__set_current_state(TASK_UNINTERRUPTIBLE);
 		dio->waiter = current;
 		spin_unlock_irqrestore(&dio->bio_lock, flags);
-		if (!(dio->iocb->ki_flags & IOCB_HIPRI) ||
-		    !blk_poll(dio->bio_disk->queue, dio->bio_cookie, true))
-			blk_io_schedule();
+		blk_io_schedule();
 		/* wake up sets us TASK_RUNNING */
 		spin_lock_irqsave(&dio->bio_lock, flags);
 		dio->waiter = NULL;
@@ -1214,8 +1210,6 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 	} else {
 		dio->op = REQ_OP_READ;
 	}
-	if (iocb->ki_flags & IOCB_HIPRI)
-		dio->op_flags |= REQ_HIPRI;
 
 	/*
 	 * For AIO O_(D)SYNC writes we need to defer completions to a workqueue
-- 
2.30.2

[PATCH 02/16] block: don't try to poll multi-bio I/Os in __blkdev_direct_IO

[Christoph Hellwig]

If an iocb is split into multiple bios we can't poll for both.  So don't
bother to even try to poll in that case.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/block_dev.c | 21 +++++++--------------
 1 file changed, 7 insertions(+), 14 deletions(-)

diff --git a/fs/block_dev.c b/fs/block_dev.c
index ac9b3c158a77..8600c651b0b0 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -375,7 +375,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	struct blk_plug plug;
 	struct blkdev_dio *dio;
 	struct bio *bio;
-	bool is_poll = (iocb->ki_flags & IOCB_HIPRI) != 0;
+	bool do_poll = (iocb->ki_flags & IOCB_HIPRI);
 	bool is_read = (iov_iter_rw(iter) == READ), is_sync;
 	loff_t pos = iocb->ki_pos;
 	blk_qc_t qc = BLK_QC_T_NONE;
@@ -404,7 +404,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	 * Don't plug for HIPRI/polled IO, as those should go straight
 	 * to issue
 	 */
-	if (!is_poll)
+	if (!(iocb->ki_flags & IOCB_HIPRI))
 		blk_start_plug(&plug);
 
 	for (;;) {
@@ -438,20 +438,13 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 
 		nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS);
 		if (!nr_pages) {
-			bool polled = false;
-
-			if (iocb->ki_flags & IOCB_HIPRI) {
+			if (do_poll)
 				bio_set_polled(bio, iocb);
-				polled = true;
-			}
-
 			qc = submit_bio(bio);
-
-			if (polled)
+			if (do_poll)
 				WRITE_ONCE(iocb->ki_cookie, qc);
 			break;
 		}
-
 		if (!dio->multi_bio) {
 			/*
 			 * AIO needs an extra reference to ensure the dio
@@ -462,6 +455,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 				bio_get(bio);
 			dio->multi_bio = true;
 			atomic_set(&dio->ref, 2);
+			do_poll = false;
 		} else {
 			atomic_inc(&dio->ref);
 		}
@@ -470,7 +464,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 		bio = bio_alloc(GFP_KERNEL, nr_pages);
 	}
 
-	if (!is_poll)
+	if (!(iocb->ki_flags & IOCB_HIPRI))
 		blk_finish_plug(&plug);
 
 	if (!is_sync)
@@ -481,8 +475,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 		if (!READ_ONCE(dio->waiter))
 			break;
 
-		if (!(iocb->ki_flags & IOCB_HIPRI) ||
-		    !blk_poll(bdev_get_queue(bdev), qc, true))
+		if (!do_poll || !blk_poll(bdev_get_queue(bdev), qc, true))
 			blk_io_schedule();
 	}
 	__set_current_state(TASK_RUNNING);
-- 
2.30.2

[PATCH 03/16] iomap: don't try to poll multi-bio I/Os in __iomap_dio_rw

[Christoph Hellwig]

If an iocb is split into multiple bios we can't poll for both.  So don't
bother to even try to poll in that case.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Mark Wunderlich <mark.wunderlich@intel.com>
---
 fs/iomap/direct-io.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 9398b8c31323..d5637f467109 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -282,6 +282,13 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 	if (!iov_iter_count(dio->submit.iter))
 		goto out;
 
+	/*
+	 * We can only poll for single bio I/Os.
+	 */
+	if (need_zeroout ||
+	    ((dio->flags & IOMAP_DIO_WRITE) && pos >= i_size_read(inode)))
+		dio->iocb->ki_flags &= ~IOCB_HIPRI;
+
 	if (need_zeroout) {
 		/* zero out from the start of the block to the write offset */
 		pad = pos & (fs_block_size - 1);
@@ -339,6 +346,11 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 
 		nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter,
 						 BIO_MAX_VECS);
+		/*
+		 * We can only poll for single bio I/Os.
+		 */
+		if (nr_pages)
+			dio->iocb->ki_flags &= ~IOCB_HIPRI;
 		iomap_dio_submit_bio(dio, iomap, bio, pos);
 		pos += n;
 	} while (nr_pages);
@@ -579,6 +591,11 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 			iov_iter_revert(iter, pos - dio->i_size);
 			break;
 		}
+
+		/*
+		 * We can only poll for single bio I/Os.
+		 */
+		iocb->ki_flags &= ~IOCB_HIPRI;
 	} while ((count = iov_iter_count(iter)) > 0);
 	blk_finish_plug(&plug);
 
-- 
2.30.2

[PATCH 04/16] blk-mq: factor out a blk_qc_to_hctx helper

[Christoph Hellwig]

Add a helper to get the hctx from a request_queue and cookie, and fold
the blk_qc_t_to_queue_num helper into it as no other callers are left.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Tested-by: Mark Wunderlich <mark.wunderlich@intel.com>
---
 block/blk-mq.c            | 8 +++++++-
 include/linux/blk_types.h | 5 -----
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 3115ea2d0990..9b3fe1062061 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -63,6 +63,12 @@ static int blk_mq_poll_stats_bkt(const struct request *rq)
 	return bucket;
 }
 
+static inline struct blk_mq_hw_ctx *blk_qc_to_hctx(struct request_queue *q,
+		blk_qc_t qc)
+{
+	return q->queue_hw_ctx[(qc & ~BLK_QC_T_INTERNAL) >> BLK_QC_T_SHIFT];
+}
+
 /*
  * Check if any of the ctx, dispatch list or elevator
  * have pending work in this hardware queue.
@@ -3970,7 +3976,7 @@ int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin)
 	if (current->plug)
 		blk_flush_plug_list(current->plug, false);
 
-	hctx = q->queue_hw_ctx[blk_qc_t_to_queue_num(cookie)];
+	hctx = blk_qc_to_hctx(q, cookie);
 
 	/*
 	 * If we sleep, have the caller restart the poll loop to reset
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index fd3860d18d7e..e2c4a7d5de05 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -511,11 +511,6 @@ static inline bool blk_qc_t_valid(blk_qc_t cookie)
 	return cookie != BLK_QC_T_NONE;
 }
 
-static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie)
-{
-	return (cookie & ~BLK_QC_T_INTERNAL) >> BLK_QC_T_SHIFT;
-}
-
 static inline unsigned int blk_qc_t_to_tag(blk_qc_t cookie)
 {
 	return cookie & ((1u << BLK_QC_T_SHIFT) - 1);
-- 
2.30.2

[PATCH 05/16] blk-mq: factor out a "classic" poll helper

[Christoph Hellwig]

Factor the code to do the classic full metal polling out of blk_poll into
a separate blk_mq_poll_classic helper.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Tested-by: Mark Wunderlich <mark.wunderlich@intel.com>
---
 block/blk-mq.c | 120 +++++++++++++++++++++++--------------------------
 1 file changed, 56 insertions(+), 64 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 9b3fe1062061..f4bb6e1db36a 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -69,6 +69,14 @@ static inline struct blk_mq_hw_ctx *blk_qc_to_hctx(struct request_queue *q,
 	return q->queue_hw_ctx[(qc & ~BLK_QC_T_INTERNAL) >> BLK_QC_T_SHIFT];
 }
 
+static inline struct request *blk_qc_to_rq(struct blk_mq_hw_ctx *hctx,
+		blk_qc_t qc)
+{
+	if (blk_qc_t_is_internal(qc))
+		return blk_mq_tag_to_rq(hctx->sched_tags, blk_qc_t_to_tag(qc));
+	return blk_mq_tag_to_rq(hctx->tags, blk_qc_t_to_tag(qc));
+}
+
 /*
  * Check if any of the ctx, dispatch list or elevator
  * have pending work in this hardware queue.
@@ -3874,15 +3882,20 @@ static unsigned long blk_mq_poll_nsecs(struct request_queue *q,
 	return ret;
 }
 
-static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
-				     struct request *rq)
+static bool blk_mq_poll_hybrid(struct request_queue *q, blk_qc_t qc)
 {
+	struct blk_mq_hw_ctx *hctx = blk_qc_to_hctx(q, qc);
+	struct request *rq = blk_qc_to_rq(hctx, qc);
 	struct hrtimer_sleeper hs;
 	enum hrtimer_mode mode;
 	unsigned int nsecs;
 	ktime_t kt;
 
-	if (rq->rq_flags & RQF_MQ_POLL_SLEPT)
+	/*
+	 * If a request has completed on queue that uses an I/O scheduler, we
+	 * won't get back a request from blk_qc_to_rq.
+	 */
+	if (!rq || (rq->rq_flags & RQF_MQ_POLL_SLEPT))
 		return false;
 
 	/*
@@ -3924,32 +3937,48 @@ static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
 
 	__set_current_state(TASK_RUNNING);
 	destroy_hrtimer_on_stack(&hs.timer);
+
+	/*
+	 * If we sleep, have the caller restart the poll loop to reset the
+	 * state.  Like for the other success return cases, the caller is
+	 * responsible for checking if the IO completed.  If the IO isn't
+	 * complete, we'll get called again and will go straight to the busy
+	 * poll loop.
+	 */
 	return true;
 }
 
-static bool blk_mq_poll_hybrid(struct request_queue *q,
-			       struct blk_mq_hw_ctx *hctx, blk_qc_t cookie)
+static int blk_mq_poll_classic(struct request_queue *q, blk_qc_t cookie,
+		bool spin)
 {
-	struct request *rq;
+	struct blk_mq_hw_ctx *hctx = blk_qc_to_hctx(q, cookie);
+	long state = current->state;
+	int ret;
 
-	if (q->poll_nsec == BLK_MQ_POLL_CLASSIC)
-		return false;
+	hctx->poll_considered++;
 
-	if (!blk_qc_t_is_internal(cookie))
-		rq = blk_mq_tag_to_rq(hctx->tags, blk_qc_t_to_tag(cookie));
-	else {
-		rq = blk_mq_tag_to_rq(hctx->sched_tags, blk_qc_t_to_tag(cookie));
-		/*
-		 * With scheduling, if the request has completed, we'll
-		 * get a NULL return here, as we clear the sched tag when
-		 * that happens. The request still remains valid, like always,
-		 * so we should be safe with just the NULL check.
-		 */
-		if (!rq)
-			return false;
-	}
+	do {
+		hctx->poll_invoked++;
 
-	return blk_mq_poll_hybrid_sleep(q, rq);
+		ret = q->mq_ops->poll(hctx);
+		if (ret > 0) {
+			hctx->poll_success++;
+			__set_current_state(TASK_RUNNING);
+			return ret;
+		}
+
+		if (signal_pending_state(state, current))
+			__set_current_state(TASK_RUNNING);
+		if (current->state == TASK_RUNNING)
+			return 1;
+
+		if (ret < 0 || !spin)
+			break;
+		cpu_relax();
+	} while (!need_resched());
+
+	__set_current_state(TASK_RUNNING);
+	return 0;
 }
 
 /**
@@ -3966,9 +3995,6 @@ static bool blk_mq_poll_hybrid(struct request_queue *q,
  */
 int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin)
 {
-	struct blk_mq_hw_ctx *hctx;
-	long state;
-
 	if (!blk_qc_t_valid(cookie) ||
 	    !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
 		return 0;
@@ -3976,46 +4002,12 @@ int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin)
 	if (current->plug)
 		blk_flush_plug_list(current->plug, false);
 
-	hctx = blk_qc_to_hctx(q, cookie);
-
-	/*
-	 * If we sleep, have the caller restart the poll loop to reset
-	 * the state. Like for the other success return cases, the
-	 * caller is responsible for checking if the IO completed. If
-	 * the IO isn't complete, we'll get called again and will go
-	 * straight to the busy poll loop. If specified not to spin,
-	 * we also should not sleep.
-	 */
-	if (spin && blk_mq_poll_hybrid(q, hctx, cookie))
-		return 1;
-
-	hctx->poll_considered++;
-
-	state = current->state;
-	do {
-		int ret;
-
-		hctx->poll_invoked++;
-
-		ret = q->mq_ops->poll(hctx);
-		if (ret > 0) {
-			hctx->poll_success++;
-			__set_current_state(TASK_RUNNING);
-			return ret;
-		}
-
-		if (signal_pending_state(state, current))
-			__set_current_state(TASK_RUNNING);
-
-		if (current->state == TASK_RUNNING)
+	/* If specified not to spin, we also should not sleep. */
+	if (spin && q->poll_nsec != BLK_MQ_POLL_CLASSIC) {
+		if (blk_mq_poll_hybrid(q, cookie))
 			return 1;
-		if (ret < 0 || !spin)
-			break;
-		cpu_relax();
-	} while (!need_resched());
-
-	__set_current_state(TASK_RUNNING);
-	return 0;
+	}
+	return blk_mq_poll_classic(q, cookie, spin);
 }
 EXPORT_SYMBOL_GPL(blk_poll);
 
-- 
2.30.2

[PATCH 06/16] blk-mq: remove blk_qc_t_to_tag and blk_qc_t_is_internal

[Christoph Hellwig]

Merge both functions into their only caller to keep the blk-mq tag to
blk_qc_t mapping as private as possible in blk-mq.c.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Tested-by: Mark Wunderlich <mark.wunderlich@intel.com>
---
 block/blk-mq.c            |  8 +++++---
 include/linux/blk_types.h | 10 ----------
 2 files changed, 5 insertions(+), 13 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index f4bb6e1db36a..eb861839ff49 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -72,9 +72,11 @@ static inline struct blk_mq_hw_ctx *blk_qc_to_hctx(struct request_queue *q,
 static inline struct request *blk_qc_to_rq(struct blk_mq_hw_ctx *hctx,
 		blk_qc_t qc)
 {
-	if (blk_qc_t_is_internal(qc))
-		return blk_mq_tag_to_rq(hctx->sched_tags, blk_qc_t_to_tag(qc));
-	return blk_mq_tag_to_rq(hctx->tags, blk_qc_t_to_tag(qc));
+	unsigned int tag = qc & ((1U << BLK_QC_T_SHIFT) - 1);
+
+	if (qc & BLK_QC_T_INTERNAL)
+		return blk_mq_tag_to_rq(hctx->sched_tags, tag);
+	return blk_mq_tag_to_rq(hctx->tags, tag);
 }
 
 /*
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index e2c4a7d5de05..abe00ac81b2e 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -511,16 +511,6 @@ static inline bool blk_qc_t_valid(blk_qc_t cookie)
 	return cookie != BLK_QC_T_NONE;
 }
 
-static inline unsigned int blk_qc_t_to_tag(blk_qc_t cookie)
-{
-	return cookie & ((1u << BLK_QC_T_SHIFT) - 1);
-}
-
-static inline bool blk_qc_t_is_internal(blk_qc_t cookie)
-{
-	return (cookie & BLK_QC_T_INTERNAL) != 0;
-}
-
 struct blk_rq_stat {
 	u64 mean;
 	u64 min;
-- 
2.30.2

[PATCH 07/16] blk-mq: remove blk_qc_t_valid

[Christoph Hellwig]

Move the trivial check into the only caller.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Tested-by: Mark Wunderlich <mark.wunderlich@intel.com>
---
 block/blk-mq.c            | 2 +-
 include/linux/blk_types.h | 5 -----
 2 files changed, 1 insertion(+), 6 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index eb861839ff49..cb94cf9bcf99 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -3997,7 +3997,7 @@ static int blk_mq_poll_classic(struct request_queue *q, blk_qc_t cookie,
  */
 int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin)
 {
-	if (!blk_qc_t_valid(cookie) ||
+	if (cookie == BLK_QC_T_NONE ||
 	    !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
 		return 0;
 
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index abe00ac81b2e..295addd38390 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -506,11 +506,6 @@ typedef unsigned int blk_qc_t;
 #define BLK_QC_T_SHIFT		16
 #define BLK_QC_T_INTERNAL	(1U << 31)
 
-static inline bool blk_qc_t_valid(blk_qc_t cookie)
-{
-	return cookie != BLK_QC_T_NONE;
-}
-
 struct blk_rq_stat {
 	u64 mean;
 	u64 min;
-- 
2.30.2

[PATCH 08/16] block: replace the spin argument to blk_iopoll with a flags argument

[Christoph Hellwig]

Switch the boolean spin argument to blk_poll to passing a set of flags
instead.  This will allow to control polling behavior in a more fine
grained way.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Mark Wunderlich <mark.wunderlich@intel.com>
---
 block/blk-mq.c           | 17 +++++++----------
 drivers/nvme/host/core.c |  2 +-
 fs/block_dev.c           |  8 ++++----
 fs/io_uring.c            | 14 +++++++-------
 fs/iomap/direct-io.c     |  6 +++---
 include/linux/blkdev.h   |  4 +++-
 include/linux/fs.h       |  2 +-
 include/linux/iomap.h    |  2 +-
 mm/page_io.c             |  2 +-
 9 files changed, 28 insertions(+), 29 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index cb94cf9bcf99..c2b2c7abd712 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -3951,7 +3951,7 @@ static bool blk_mq_poll_hybrid(struct request_queue *q, blk_qc_t qc)
 }
 
 static int blk_mq_poll_classic(struct request_queue *q, blk_qc_t cookie,
-		bool spin)
+		unsigned int flags)
 {
 	struct blk_mq_hw_ctx *hctx = blk_qc_to_hctx(q, cookie);
 	long state = current->state;
@@ -3974,7 +3974,7 @@ static int blk_mq_poll_classic(struct request_queue *q, blk_qc_t cookie,
 		if (current->state == TASK_RUNNING)
 			return 1;
 
-		if (ret < 0 || !spin)
+		if (ret < 0 || (flags & BLK_POLL_ONESHOT))
 			break;
 		cpu_relax();
 	} while (!need_resched());
@@ -3987,15 +3987,13 @@ static int blk_mq_poll_classic(struct request_queue *q, blk_qc_t cookie,
  * blk_poll - poll for IO completions
  * @q:  the queue
  * @cookie: cookie passed back at IO submission time
- * @spin: whether to spin for completions
+ * @flags: BLK_POLL_* flags that control the behavior
  *
  * Description:
  *    Poll for completions on the passed in queue. Returns number of
- *    completed entries found. If @spin is true, then blk_poll will continue
- *    looping until at least one completion is found, unless the task is
- *    otherwise marked running (or we need to reschedule).
+ *    completed entries found.
  */
-int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin)
+int blk_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags)
 {
 	if (cookie == BLK_QC_T_NONE ||
 	    !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
@@ -4004,12 +4002,11 @@ int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin)
 	if (current->plug)
 		blk_flush_plug_list(current->plug, false);
 
-	/* If specified not to spin, we also should not sleep. */
-	if (spin && q->poll_nsec != BLK_MQ_POLL_CLASSIC) {
+	if (q->poll_nsec != BLK_MQ_POLL_CLASSIC) {
 		if (blk_mq_poll_hybrid(q, cookie))
 			return 1;
 	}
-	return blk_mq_poll_classic(q, cookie, spin);
+	return blk_mq_poll_classic(q, cookie, flags);
 }
 EXPORT_SYMBOL_GPL(blk_poll);
 
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 24bcae88587a..115c8d90530a 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1032,7 +1032,7 @@ static void nvme_execute_rq_polled(struct request_queue *q,
 	blk_execute_rq_nowait(bd_disk, rq, at_head, nvme_end_sync_rq);
 
 	while (!completion_done(&wait)) {
-		blk_poll(q, request_to_qc_t(rq->mq_hctx, rq), true);
+		blk_poll(q, request_to_qc_t(rq->mq_hctx, rq), 0);
 		cond_resched();
 	}
 }
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 8600c651b0b0..c9bdaa138909 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -286,7 +286,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 		if (!READ_ONCE(bio.bi_private))
 			break;
 		if (!(iocb->ki_flags & IOCB_HIPRI) ||
-		    !blk_poll(bdev_get_queue(bdev), qc, true))
+		    !blk_poll(bdev_get_queue(bdev), qc, 0))
 			blk_io_schedule();
 	}
 	__set_current_state(TASK_RUNNING);
@@ -319,12 +319,12 @@ struct blkdev_dio {
 
 static struct bio_set blkdev_dio_pool;
 
-static int blkdev_iopoll(struct kiocb *kiocb, bool wait)
+static int blkdev_iopoll(struct kiocb *kiocb, unsigned int flags)
 {
 	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);
+	return blk_poll(q, READ_ONCE(kiocb->ki_cookie), flags);
 }
 
 static void blkdev_bio_end_io(struct bio *bio)
@@ -475,7 +475,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 		if (!READ_ONCE(dio->waiter))
 			break;
 
-		if (!do_poll || !blk_poll(bdev_get_queue(bdev), qc, true))
+		if (!do_poll || !blk_poll(bdev_get_queue(bdev), qc, 0))
 			blk_io_schedule();
 	}
 	__set_current_state(TASK_RUNNING);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 5f82954004f6..de8d39e9a154 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2290,18 +2290,18 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
 static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
 			long min)
 {
+	unsigned int poll_flags = 0;
 	struct io_kiocb *req, *tmp;
 	LIST_HEAD(done);
-	bool spin;
-	int ret;
+	int ret = 0;
 
 	/*
 	 * Only spin for completions if we don't have multiple devices hanging
 	 * off our complete list, and we're under the requested amount.
 	 */
-	spin = !ctx->poll_multi_file && *nr_events < min;
+	if (ctx->poll_multi_file || *nr_events >= min)
+		poll_flags |= BLK_POLL_ONESHOT;
 
-	ret = 0;
 	list_for_each_entry_safe(req, tmp, &ctx->iopoll_list, inflight_entry) {
 		struct kiocb *kiocb = &req->rw.kiocb;
 
@@ -2317,7 +2317,7 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
 		if (!list_empty(&done))
 			break;
 
-		ret = kiocb->ki_filp->f_op->iopoll(kiocb, spin);
+		ret = kiocb->ki_filp->f_op->iopoll(kiocb, poll_flags);
 		if (ret < 0)
 			break;
 
@@ -2325,8 +2325,8 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
 		if (READ_ONCE(req->iopoll_completed))
 			list_move_tail(&req->inflight_entry, &done);
 
-		if (ret && spin)
-			spin = false;
+		if (ret)
+			poll_flags |= BLK_POLL_ONESHOT;
 		ret = 0;
 	}
 
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index d5637f467109..9b6c26da3a2d 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -49,13 +49,13 @@ struct iomap_dio {
 	};
 };
 
-int iomap_dio_iopoll(struct kiocb *kiocb, bool spin)
+int iomap_dio_iopoll(struct kiocb *kiocb, unsigned int flags)
 {
 	struct request_queue *q = READ_ONCE(kiocb->private);
 
 	if (!q)
 		return 0;
-	return blk_poll(q, READ_ONCE(kiocb->ki_cookie), spin);
+	return blk_poll(q, READ_ONCE(kiocb->ki_cookie), flags);
 }
 EXPORT_SYMBOL_GPL(iomap_dio_iopoll);
 
@@ -640,7 +640,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 			if (!(iocb->ki_flags & IOCB_HIPRI) ||
 			    !dio->submit.last_queue ||
 			    !blk_poll(dio->submit.last_queue,
-					 dio->submit.cookie, true))
+					 dio->submit.cookie, 0))
 				blk_io_schedule();
 		}
 		__set_current_state(TASK_RUNNING);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d66d0da72529..c7061f25ee5f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -946,7 +946,9 @@ extern const char *blk_op_str(unsigned int op);
 int blk_status_to_errno(blk_status_t status);
 blk_status_t errno_to_blk_status(int errno);
 
-int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin);
+/* only poll the hardware once, don't continue until a completion was found */
+#define BLK_POLL_ONESHOT		(1 << 0)
+int blk_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags);
 
 static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
 {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index c3c88fdb9b2a..483fb557d92f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2026,7 +2026,7 @@ struct file_operations {
 	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
 	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
 	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
-	int (*iopoll)(struct kiocb *kiocb, bool spin);
+	int (*iopoll)(struct kiocb *kiocb, unsigned int flags);
 	int (*iterate) (struct file *, struct dir_context *);
 	int (*iterate_shared) (struct file *, struct dir_context *);
 	__poll_t (*poll) (struct file *, struct poll_table_struct *);
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index c87d0cb0de6d..56e5949ccb60 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -275,7 +275,7 @@ struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
 		unsigned int dio_flags);
 ssize_t iomap_dio_complete(struct iomap_dio *dio);
-int iomap_dio_iopoll(struct kiocb *kiocb, bool spin);
+int iomap_dio_iopoll(struct kiocb *kiocb, unsigned int flags);
 
 #ifdef CONFIG_SWAP
 struct file;
diff --git a/mm/page_io.c b/mm/page_io.c
index c493ce9ebcf5..5d5543fcefa4 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -428,7 +428,7 @@ int swap_readpage(struct page *page, bool synchronous)
 		if (!READ_ONCE(bio->bi_private))
 			break;
 
-		if (!blk_poll(disk->queue, qc, true))
+		if (!blk_poll(disk->queue, qc, 0))
 			blk_io_schedule();
 	}
 	__set_current_state(TASK_RUNNING);
-- 
2.30.2

[PATCH 09/16] io_uring: don't sleep when polling for I/O

[Christoph Hellwig]

There is no point in sleeping for the expected I/O completion timeout
in the io_uring async polling model as we never poll for a specific
I/O.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Mark Wunderlich <mark.wunderlich@intel.com>
---
 block/blk-mq.c         | 3 ++-
 fs/io_uring.c          | 2 +-
 include/linux/blkdev.h | 2 ++
 3 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index c2b2c7abd712..86e59ffcca44 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -4002,7 +4002,8 @@ int blk_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags)
 	if (current->plug)
 		blk_flush_plug_list(current->plug, false);
 
-	if (q->poll_nsec != BLK_MQ_POLL_CLASSIC) {
+	if (!(flags & BLK_POLL_NOSLEEP) &&
+	    q->poll_nsec != BLK_MQ_POLL_CLASSIC) {
 		if (blk_mq_poll_hybrid(q, cookie))
 			return 1;
 	}
diff --git a/fs/io_uring.c b/fs/io_uring.c
index de8d39e9a154..6ce1e5b60725 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2290,7 +2290,7 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
 static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
 			long min)
 {
-	unsigned int poll_flags = 0;
+	unsigned int poll_flags = BLK_POLL_NOSLEEP;
 	struct io_kiocb *req, *tmp;
 	LIST_HEAD(done);
 	int ret = 0;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c7061f25ee5f..821d721f78e7 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -948,6 +948,8 @@ blk_status_t errno_to_blk_status(int errno);
 
 /* only poll the hardware once, don't continue until a completion was found */
 #define BLK_POLL_ONESHOT		(1 << 0)
+/* do not sleep to wait for the expected completion time */
+#define BLK_POLL_NOSLEEP		(1 << 1)
 int blk_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags);
 
 static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
-- 
2.30.2

[PATCH 10/16] block: rename REQ_HIPRI to REQ_POLLED

[Christoph Hellwig]

Unlike the RWF_HIPRI userspace ABI which is intentionally kept vague,
the bio flag is specific to the polling implementation, so rename and
document it properly.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Tested-by: Mark Wunderlich <mark.wunderlich@intel.com>
---
 block/blk-core.c          |  2 +-
 block/blk-merge.c         |  2 +-
 block/blk-mq-debugfs.c    |  2 +-
 block/blk-mq.c            |  4 ++--
 block/blk-mq.h            |  4 ++--
 drivers/nvme/host/core.c  |  2 +-
 drivers/scsi/scsi_debug.c | 10 +++++-----
 include/linux/bio.h       |  2 +-
 include/linux/blk_types.h |  4 ++--
 mm/page_io.c              |  2 +-
 10 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index 514838ccab2d..858a76858cb0 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -836,7 +836,7 @@ static noinline_for_stack bool submit_bio_checks(struct bio *bio)
 	}
 
 	if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
-		bio->bi_opf &= ~REQ_HIPRI;
+		bio->bi_opf &= ~REQ_POLLED;
 
 	switch (bio_op(bio)) {
 	case REQ_OP_DISCARD:
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 4d97fb6dd226..5c9d2a4ece86 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -285,7 +285,7 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 	 * iopoll in direct IO routine. Given performance gain of iopoll for
 	 * big IO can be trival, disable iopoll when split needed.
 	 */
-	bio->bi_opf &= ~REQ_HIPRI;
+	bio->bi_opf &= ~REQ_POLLED;
 
 	return bio_split(bio, sectors, GFP_NOIO, bs);
 }
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 2a75bc7401df..0b821b369ffd 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -286,7 +286,7 @@ static const char *const cmd_flag_name[] = {
 	CMD_FLAG_NAME(BACKGROUND),
 	CMD_FLAG_NAME(NOWAIT),
 	CMD_FLAG_NAME(NOUNMAP),
-	CMD_FLAG_NAME(HIPRI),
+	CMD_FLAG_NAME(POLLED),
 };
 #undef CMD_FLAG_NAME
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 86e59ffcca44..a0cc1eedc15a 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -667,7 +667,7 @@ bool blk_mq_complete_request_remote(struct request *rq)
 	 * For a polled request, always complete locallly, it's pointless
 	 * to redirect the completion.
 	 */
-	if (rq->cmd_flags & REQ_HIPRI)
+	if (rq->cmd_flags & REQ_POLLED)
 		return false;
 
 	if (blk_mq_complete_need_ipi(rq)) {
@@ -2220,7 +2220,7 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
 
 	rq_qos_throttle(q, bio);
 
-	hipri = bio->bi_opf & REQ_HIPRI;
+	hipri = bio->bi_opf & REQ_POLLED;
 
 	data.cmd_flags = bio->bi_opf;
 	rq = __blk_mq_alloc_request(&data);
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 4b1ca7b7bbeb..8444e00e8d25 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -109,9 +109,9 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
 	enum hctx_type type = HCTX_TYPE_DEFAULT;
 
 	/*
-	 * The caller ensure that if REQ_HIPRI, poll must be enabled.
+	 * The caller ensure that if REQ_POLLED, poll must be enabled.
 	 */
-	if (flags & REQ_HIPRI)
+	if (flags & REQ_POLLED)
 		type = HCTX_TYPE_POLL;
 	else if ((flags & REQ_OP_MASK) == REQ_OP_READ)
 		type = HCTX_TYPE_READ;
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 115c8d90530a..1f2ecb2fe9b1 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1027,7 +1027,7 @@ static void nvme_execute_rq_polled(struct request_queue *q,
 
 	WARN_ON_ONCE(!test_bit(QUEUE_FLAG_POLL, &q->queue_flags));
 
-	rq->cmd_flags |= REQ_HIPRI;
+	rq->cmd_flags |= REQ_POLLED;
 	rq->end_io_data = &wait;
 	blk_execute_rq_nowait(bd_disk, rq, at_head, nvme_end_sync_rq);
 
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index a5d1633b5bd8..81384d28ff90 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -5367,7 +5367,7 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip,
 {
 	bool new_sd_dp;
 	bool inject = false;
-	bool hipri = (cmnd->request->cmd_flags & REQ_HIPRI);
+	bool polled = (cmnd->request->cmd_flags & REQ_POLLED);
 	int k, num_in_q, qdepth;
 	unsigned long iflags;
 	u64 ns_from_boot = 0;
@@ -5454,7 +5454,7 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip,
 	if (sdebug_host_max_queue)
 		sd_dp->hc_idx = get_tag(cmnd);
 
-	if (hipri)
+	if (polled)
 		ns_from_boot = ktime_get_boottime_ns();
 
 	/* one of the resp_*() response functions is called here */
@@ -5514,7 +5514,7 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip,
 				kt -= d;
 			}
 		}
-		if (hipri) {
+		if (polled) {
 			sd_dp->cmpl_ts = ktime_add(ns_to_ktime(ns_from_boot), kt);
 			spin_lock_irqsave(&sqp->qc_lock, iflags);
 			if (!sd_dp->init_poll) {
@@ -5545,7 +5545,7 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip,
 		if (unlikely((sdebug_opts & SDEBUG_OPT_CMD_ABORT) &&
 			     atomic_read(&sdeb_inject_pending)))
 			sd_dp->aborted = true;
-		if (hipri) {
+		if (polled) {
 			sd_dp->cmpl_ts = ns_to_ktime(ns_from_boot);
 			spin_lock_irqsave(&sqp->qc_lock, iflags);
 			if (!sd_dp->init_poll) {
@@ -7313,7 +7313,7 @@ static int sdebug_blk_mq_poll(struct Scsi_Host *shost, unsigned int queue_num)
 			if (kt_from_boot < sd_dp->cmpl_ts)
 				continue;
 
-		} else		/* ignoring non REQ_HIPRI requests */
+		} else		/* ignoring non REQ_POLLED requests */
 			continue;
 		devip = (struct sdebug_dev_info *)scp->device->hostdata;
 		if (likely(devip))
diff --git a/include/linux/bio.h b/include/linux/bio.h
index d2b98efb5cc5..feaebd2367a0 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -813,7 +813,7 @@ static inline int bio_integrity_add_page(struct bio *bio, struct page *page,
  */
 static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb)
 {
-	bio->bi_opf |= REQ_HIPRI;
+	bio->bi_opf |= REQ_POLLED;
 	if (!is_sync_kiocb(kiocb))
 		bio->bi_opf |= REQ_NOWAIT;
 }
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 295addd38390..bb53aaa36caf 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -388,7 +388,7 @@ enum req_flag_bits {
 	/* command specific flags for REQ_OP_WRITE_ZEROES: */
 	__REQ_NOUNMAP,		/* do not free blocks when zeroing */
 
-	__REQ_HIPRI,
+	__REQ_POLLED,		/* caller polls for completion using blk_poll */
 
 	/* for driver use */
 	__REQ_DRV,
@@ -413,7 +413,7 @@ enum req_flag_bits {
 #define REQ_CGROUP_PUNT		(1ULL << __REQ_CGROUP_PUNT)
 
 #define REQ_NOUNMAP		(1ULL << __REQ_NOUNMAP)
-#define REQ_HIPRI		(1ULL << __REQ_HIPRI)
+#define REQ_POLLED		(1ULL << __REQ_POLLED)
 
 #define REQ_DRV			(1ULL << __REQ_DRV)
 #define REQ_SWAP		(1ULL << __REQ_SWAP)
diff --git a/mm/page_io.c b/mm/page_io.c
index 5d5543fcefa4..ed2eded74f3a 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -416,7 +416,7 @@ int swap_readpage(struct page *page, bool synchronous)
 	 * attempt to access it in the page fault retry time check.
 	 */
 	if (synchronous) {
-		bio->bi_opf |= REQ_HIPRI;
+		bio->bi_opf |= REQ_POLLED;
 		get_task_struct(current);
 		bio->bi_private = current;
 	}
-- 
2.30.2

[PATCH 11/16] block: use SLAB_TYPESAFE_BY_RCU for the bio slab

[Christoph Hellwig]

This flags ensures that the pages will not be reused for non-bio
allocations before the end of an RCU grace period.  With that we can
safely use a RCU lookup for bio polling as long as we are fine with
occasionally polling the wrong device.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Mark Wunderlich <mark.wunderlich@intel.com>
---
 block/bio.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/block/bio.c b/block/bio.c
index 44205dfb6b60..de5505d7018e 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -82,7 +82,8 @@ static struct bio_slab *create_bio_slab(unsigned int size)
 
 	snprintf(bslab->name, sizeof(bslab->name), "bio-%d", size);
 	bslab->slab = kmem_cache_create(bslab->name, size,
-			ARCH_KMALLOC_MINALIGN, SLAB_HWCACHE_ALIGN, NULL);
+			ARCH_KMALLOC_MINALIGN,
+			SLAB_HWCACHE_ALIGN | SLAB_TYPESAFE_BY_RCU, NULL);
 	if (!bslab->slab)
 		goto fail_alloc_slab;
 
-- 
2.30.2

[PATCH 12/16] block: define 'struct bvec_iter' as packed

[Christoph Hellwig]

From: Ming Lei <ming.lei@redhat.com>

'struct bvec_iter' is embedded into 'struct bio', define it as packed
so that we can get one extra 4bytes for other uses without expanding
bio.

'struct bvec_iter' is often allocated on stack, so making it packed
doesn't affect performance. Also I have run io_uring on both
nvme/null_blk, and not observe performance effect in this way.

Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Mark Wunderlich <mark.wunderlich@intel.com>
---
 include/linux/bvec.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index ff832e698efb..a0c4f41dfc83 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -43,7 +43,7 @@ struct bvec_iter {
 
 	unsigned int            bi_bvec_done;	/* number of bytes completed in
 						   current bvec */
-};
+} __packed;
 
 struct bvec_iter_all {
 	struct bio_vec	bv;
-- 
2.30.2

[PATCH 13/16] block: switch polling to be bio based

[Christoph Hellwig]

Replace the blk_poll interface that requires the caller to keep a queue
and cookie from the submissions with polling based on the bio.

Polling for the bio itself leads to a few advantages:

 - the cookie construction can made entirely private in blk-mq.c
 - the caller does not need to remember the request_queue and cookie
   separately and thus sidesteps their lifetime issues
 - keeping the device and the cookie inside the bio allows to trivially
   support polling BIOs remapping by stacking drivers
 - a lot of code to propagate the cookie back up the submission path can
   be removed entirely.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Mark Wunderlich <mark.wunderlich@intel.com>
---
 arch/m68k/emu/nfblock.c             |   3 +-
 arch/xtensa/platforms/iss/simdisk.c |   3 +-
 block/bio.c                         |   1 +
 block/blk-core.c                    | 127 +++++++++++++++++++++-------
 block/blk-mq.c                      |  73 +++++-----------
 block/blk-mq.h                      |   2 +
 drivers/block/brd.c                 |  12 ++-
 drivers/block/drbd/drbd_int.h       |   2 +-
 drivers/block/drbd/drbd_req.c       |   3 +-
 drivers/block/n64cart.c             |  12 ++-
 drivers/block/null_blk/main.c       |   3 +-
 drivers/block/pktcdvd.c             |   7 +-
 drivers/block/ps3vram.c             |   6 +-
 drivers/block/rsxx/dev.c            |   7 +-
 drivers/block/zram/zram_drv.c       |  10 +--
 drivers/lightnvm/pblk-init.c        |   6 +-
 drivers/md/bcache/request.c         |  13 ++-
 drivers/md/bcache/request.h         |   4 +-
 drivers/md/dm.c                     |  28 +++---
 drivers/md/md.c                     |  10 +--
 drivers/nvdimm/blk.c                |   5 +-
 drivers/nvdimm/btt.c                |   5 +-
 drivers/nvdimm/pmem.c               |   3 +-
 drivers/nvme/host/core.c            |   2 +-
 drivers/nvme/host/multipath.c       |   6 +-
 drivers/s390/block/dcssblk.c        |   7 +-
 drivers/s390/block/xpram.c          |   5 +-
 fs/block_dev.c                      |  25 ++----
 fs/btrfs/inode.c                    |   8 +-
 fs/ext4/file.c                      |   2 +-
 fs/gfs2/file.c                      |   4 +-
 fs/iomap/direct-io.c                |  39 +++------
 fs/xfs/xfs_file.c                   |   2 +-
 fs/zonefs/super.c                   |   2 +-
 include/linux/bio.h                 |   2 +-
 include/linux/blk-mq.h              |  15 +---
 include/linux/blk_types.h           |  12 ++-
 include/linux/blkdev.h              |   8 +-
 include/linux/fs.h                  |   6 +-
 include/linux/iomap.h               |   3 +-
 mm/page_io.c                        |   8 +-
 41 files changed, 230 insertions(+), 271 deletions(-)

diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c
index 9a8394e96388..4ef457ba5220 100644
--- a/arch/m68k/emu/nfblock.c
+++ b/arch/m68k/emu/nfblock.c
@@ -58,7 +58,7 @@ struct nfhd_device {
 	struct gendisk *disk;
 };
 
-static blk_qc_t nfhd_submit_bio(struct bio *bio)
+static void nfhd_submit_bio(struct bio *bio)
 {
 	struct nfhd_device *dev = bio->bi_bdev->bd_disk->private_data;
 	struct bio_vec bvec;
@@ -76,7 +76,6 @@ static blk_qc_t nfhd_submit_bio(struct bio *bio)
 		sec += len;
 	}
 	bio_endio(bio);
-	return BLK_QC_T_NONE;
 }
 
 static int nfhd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c
index 3cdfa00738e0..ddd1fe3db474 100644
--- a/arch/xtensa/platforms/iss/simdisk.c
+++ b/arch/xtensa/platforms/iss/simdisk.c
@@ -100,7 +100,7 @@ static void simdisk_transfer(struct simdisk *dev, unsigned long sector,
 	spin_unlock(&dev->lock);
 }
 
-static blk_qc_t simdisk_submit_bio(struct bio *bio)
+static void simdisk_submit_bio(struct bio *bio)
 {
 	struct simdisk *dev = bio->bi_bdev->bd_disk->private_data;
 	struct bio_vec bvec;
@@ -118,7 +118,6 @@ static blk_qc_t simdisk_submit_bio(struct bio *bio)
 	}
 
 	bio_endio(bio);
-	return BLK_QC_T_NONE;
 }
 
 static int simdisk_open(struct block_device *bdev, fmode_t mode)
diff --git a/block/bio.c b/block/bio.c
index de5505d7018e..986908cc99d4 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -250,6 +250,7 @@ void bio_init(struct bio *bio, struct bio_vec *table,
 	memset(bio, 0, sizeof(*bio));
 	atomic_set(&bio->__bi_remaining, 1);
 	atomic_set(&bio->__bi_cnt, 1);
+	bio->bi_cookie = BLK_QC_T_NONE;
 
 	bio->bi_io_vec = table;
 	bio->bi_max_vecs = max_vecs;
diff --git a/block/blk-core.c b/block/blk-core.c
index 858a76858cb0..531176578221 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -909,18 +909,18 @@ static noinline_for_stack bool submit_bio_checks(struct bio *bio)
 	return false;
 }
 
-static blk_qc_t __submit_bio(struct bio *bio)
+static void __submit_bio(struct bio *bio)
 {
 	struct gendisk *disk = bio->bi_bdev->bd_disk;
-	blk_qc_t ret = BLK_QC_T_NONE;
 
 	if (blk_crypto_bio_prep(&bio)) {
-		if (!disk->fops->submit_bio)
-			return blk_mq_submit_bio(bio);
-		ret = disk->fops->submit_bio(bio);
+		if (!disk->fops->submit_bio) {
+			blk_mq_submit_bio(bio);
+			return;
+		}
+		disk->fops->submit_bio(bio);
 	}
 	blk_queue_exit(disk->queue);
-	return ret;
 }
 
 /*
@@ -942,10 +942,9 @@ static blk_qc_t __submit_bio(struct bio *bio)
  * bio_list_on_stack[1] contains bios that were submitted before the current
  *	->submit_bio_bio, but that haven't been processed yet.
  */
-static blk_qc_t __submit_bio_noacct(struct bio *bio)
+static void __submit_bio_noacct(struct bio *bio)
 {
 	struct bio_list bio_list_on_stack[2];
-	blk_qc_t ret = BLK_QC_T_NONE;
 
 	BUG_ON(bio->bi_next);
 
@@ -965,7 +964,7 @@ static blk_qc_t __submit_bio_noacct(struct bio *bio)
 		bio_list_on_stack[1] = bio_list_on_stack[0];
 		bio_list_init(&bio_list_on_stack[0]);
 
-		ret = __submit_bio(bio);
+		__submit_bio(bio);
 
 		/*
 		 * Sort new bios into those for a lower level and those for the
@@ -988,13 +987,11 @@ static blk_qc_t __submit_bio_noacct(struct bio *bio)
 	} while ((bio = bio_list_pop(&bio_list_on_stack[0])));
 
 	current->bio_list = NULL;
-	return ret;
 }
 
-static blk_qc_t __submit_bio_noacct_mq(struct bio *bio)
+static void __submit_bio_noacct_mq(struct bio *bio)
 {
 	struct bio_list bio_list[2] = { };
-	blk_qc_t ret = BLK_QC_T_NONE;
 
 	current->bio_list = bio_list;
 
@@ -1006,15 +1003,13 @@ static blk_qc_t __submit_bio_noacct_mq(struct bio *bio)
 
 		if (!blk_crypto_bio_prep(&bio)) {
 			blk_queue_exit(disk->queue);
-			ret = BLK_QC_T_NONE;
 			continue;
 		}
 
-		ret = blk_mq_submit_bio(bio);
+		blk_mq_submit_bio(bio);
 	} while ((bio = bio_list_pop(&bio_list[0])));
 
 	current->bio_list = NULL;
-	return ret;
 }
 
 /**
@@ -1026,10 +1021,10 @@ static blk_qc_t __submit_bio_noacct_mq(struct bio *bio)
  * systems and other upper level users of the block layer should use
  * submit_bio() instead.
  */
-blk_qc_t submit_bio_noacct(struct bio *bio)
+void submit_bio_noacct(struct bio *bio)
 {
 	if (!submit_bio_checks(bio))
-		return BLK_QC_T_NONE;
+		return;
 
 	/*
 	 * We only want one ->submit_bio to be active at a time, else stack
@@ -1037,14 +1032,12 @@ blk_qc_t submit_bio_noacct(struct bio *bio)
 	 * to collect a list of requests submited by a ->submit_bio method while
 	 * it is active, and then process them after it returned.
 	 */
-	if (current->bio_list) {
+	if (current->bio_list)
 		bio_list_add(&current->bio_list[0], bio);
-		return BLK_QC_T_NONE;
-	}
-
-	if (!bio->bi_bdev->bd_disk->fops->submit_bio)
-		return __submit_bio_noacct_mq(bio);
-	return __submit_bio_noacct(bio);
+	else if (!bio->bi_bdev->bd_disk->fops->submit_bio)
+		__submit_bio_noacct_mq(bio);
+	else
+		__submit_bio_noacct(bio);
 }
 EXPORT_SYMBOL(submit_bio_noacct);
 
@@ -1061,10 +1054,10 @@ EXPORT_SYMBOL(submit_bio_noacct);
  * in @bio.  The bio must NOT be touched by thecaller until ->bi_end_io() has
  * been called.
  */
-blk_qc_t submit_bio(struct bio *bio)
+void submit_bio(struct bio *bio)
 {
 	if (blkcg_punt_bio_submit(bio))
-		return BLK_QC_T_NONE;
+		return;
 
 	/*
 	 * If it's a regular read/write or a barrier with data attached,
@@ -1096,19 +1089,91 @@ blk_qc_t submit_bio(struct bio *bio)
 	if (unlikely(bio_op(bio) == REQ_OP_READ &&
 	    bio_flagged(bio, BIO_WORKINGSET))) {
 		unsigned long pflags;
-		blk_qc_t ret;
 
 		psi_memstall_enter(&pflags);
-		ret = submit_bio_noacct(bio);
+		submit_bio_noacct(bio);
 		psi_memstall_leave(&pflags);
-
-		return ret;
+		return;
 	}
 
-	return submit_bio_noacct(bio);
+	submit_bio_noacct(bio);
 }
 EXPORT_SYMBOL(submit_bio);
 
+/**
+ * bio_poll - poll for BIO completions
+ * @bio: bio to poll for
+ * @flags: BLK_POLL_* flags that control the behavior
+ *
+ * Poll for completions on queue associated with the bio. Returns number of
+ * completed entries found.
+ *
+ * Note: the caller must either be the context that submitted @bio, or
+ * be in a RCU critical section to prevent freeing of @bio.
+ */
+int bio_poll(struct bio *bio, unsigned int flags)
+{
+	struct request_queue *q = bio->bi_bdev->bd_disk->queue;
+	blk_qc_t cookie = READ_ONCE(bio->bi_cookie);
+	int ret;
+
+	if (cookie == BLK_QC_T_NONE ||
+	    !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
+		return 0;
+
+	if (current->plug)
+		blk_flush_plug_list(current->plug, false);
+
+	if (blk_queue_enter(q, BLK_MQ_REQ_NOWAIT))
+		return 0;
+	if (WARN_ON_ONCE(!queue_is_mq(q)))
+		ret = 0;	/* not yet implemented, should not happen */
+	else
+		ret = blk_mq_poll(q, cookie, flags);
+	blk_queue_exit(q);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(bio_poll);
+
+/*
+ * Helper to implement file_operations.iopoll.  Requires the bio to be stored
+ * in iocb->private, and cleared before freeing the bio.
+ */
+int iocb_bio_iopoll(struct kiocb *kiocb, unsigned int flags)
+{
+	struct bio *bio;
+	int ret = 0;
+
+	/*
+	 * Note: the bio cache only uses SLAB_TYPESAFE_BY_RCU, so bio can
+	 * point to a freshly allocated bio at this point.  If that happens
+	 * we have a few cases to consider:
+	 *
+	 *  1) the bio is beeing initialized and bi_bdev is NULL.  We can just
+	 *     simply nothing in this case
+	 *  2) the bio points to a not poll enabled device.  bio_poll will catch
+	 *     this and return 0
+	 *  3) the bio points to a poll capable device, including but not
+	 *     limited to the one that the original bio pointed to.  In this
+	 *     case we will call into the actual poll method and poll for I/O,
+	 *     even if we don't need to, but it won't cause harm either.
+	 *
+	 * For cases 2) and 3) above the RCU grace period ensures that bi_bdev
+	 * is still allocated. Because partitions hold a reference to the whole
+	 * device bdev and thus disk, the disk is also still valid.  Grabbing
+	 * a reference to the queue in bio_poll() ensures the hctxs and requests
+	 * are still valid as well.
+	 */
+	rcu_read_lock();
+	bio = READ_ONCE(kiocb->private);
+	if (bio && bio->bi_bdev)
+		ret = bio_poll(bio, flags);
+	rcu_read_unlock();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iocb_bio_iopoll);
+
 /**
  * blk_cloned_rq_check_limits - Helper function to check a cloned request
  *                              for the new queue limits
diff --git a/block/blk-mq.c b/block/blk-mq.c
index a0cc1eedc15a..df5dc3b756f5 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -63,6 +63,9 @@ static int blk_mq_poll_stats_bkt(const struct request *rq)
 	return bucket;
 }
 
+#define BLK_QC_T_SHIFT		16
+#define BLK_QC_T_INTERNAL	(1U << 31)
+
 static inline struct blk_mq_hw_ctx *blk_qc_to_hctx(struct request_queue *q,
 		blk_qc_t qc)
 {
@@ -79,6 +82,13 @@ static inline struct request *blk_qc_to_rq(struct blk_mq_hw_ctx *hctx,
 	return blk_mq_tag_to_rq(hctx->tags, tag);
 }
 
+static inline blk_qc_t blk_rq_to_qc(struct request *rq)
+{
+	return (rq->mq_hctx->queue_num << BLK_QC_T_SHIFT) |
+		(rq->tag != -1 ?
+		 rq->tag : (rq->internal_tag | BLK_QC_T_INTERNAL));
+}
+
 /*
  * Check if any of the ctx, dispatch list or elevator
  * have pending work in this hardware queue.
@@ -747,6 +757,8 @@ void blk_mq_start_request(struct request *rq)
 	if (blk_integrity_rq(rq) && req_op(rq) == REQ_OP_WRITE)
 		q->integrity.profile->prepare_fn(rq);
 #endif
+	if (rq->bio && rq->bio->bi_opf & REQ_POLLED)
+	        WRITE_ONCE(rq->bio->bi_cookie, blk_rq_to_qc(rq));
 }
 EXPORT_SYMBOL(blk_mq_start_request);
 
@@ -1996,19 +2008,15 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio,
 }
 
 static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
-					    struct request *rq,
-					    blk_qc_t *cookie, bool last)
+					    struct request *rq, bool last)
 {
 	struct request_queue *q = rq->q;
 	struct blk_mq_queue_data bd = {
 		.rq = rq,
 		.last = last,
 	};
-	blk_qc_t new_cookie;
 	blk_status_t ret;
 
-	new_cookie = request_to_qc_t(hctx, rq);
-
 	/*
 	 * For OK queue, we are done. For error, caller may kill it.
 	 * Any other error (busy), just add it to our list as we
@@ -2018,7 +2026,6 @@ static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
 	switch (ret) {
 	case BLK_STS_OK:
 		blk_mq_update_dispatch_busy(hctx, false);
-		*cookie = new_cookie;
 		break;
 	case BLK_STS_RESOURCE:
 	case BLK_STS_DEV_RESOURCE:
@@ -2027,7 +2034,6 @@ static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
 		break;
 	default:
 		blk_mq_update_dispatch_busy(hctx, false);
-		*cookie = BLK_QC_T_NONE;
 		break;
 	}
 
@@ -2036,7 +2042,6 @@ static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
 
 static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 						struct request *rq,
-						blk_qc_t *cookie,
 						bool bypass_insert, bool last)
 {
 	struct request_queue *q = rq->q;
@@ -2070,7 +2075,7 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 		goto insert;
 	}
 
-	return __blk_mq_issue_directly(hctx, rq, cookie, last);
+	return __blk_mq_issue_directly(hctx, rq, last);
 insert:
 	if (bypass_insert)
 		return BLK_STS_RESOURCE;
@@ -2084,7 +2089,6 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
  * blk_mq_try_issue_directly - Try to send a request directly to device driver.
  * @hctx: Pointer of the associated hardware queue.
  * @rq: Pointer to request to be sent.
- * @cookie: Request queue cookie.
  *
  * If the device has enough resources to accept a new request now, send the
  * request directly to device driver. Else, insert at hctx->dispatch queue, so
@@ -2092,7 +2096,7 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
  * queue have higher priority.
  */
 static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
-		struct request *rq, blk_qc_t *cookie)
+		struct request *rq)
 {
 	blk_status_t ret;
 	int srcu_idx;
@@ -2101,7 +2105,7 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 
 	hctx_lock(hctx, &srcu_idx);
 
-	ret = __blk_mq_try_issue_directly(hctx, rq, cookie, false, true);
+	ret = __blk_mq_try_issue_directly(hctx, rq, false, true);
 	if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE)
 		blk_mq_request_bypass_insert(rq, false, true);
 	else if (ret != BLK_STS_OK)
@@ -2114,11 +2118,10 @@ blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last)
 {
 	blk_status_t ret;
 	int srcu_idx;
-	blk_qc_t unused_cookie;
 	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
 
 	hctx_lock(hctx, &srcu_idx);
-	ret = __blk_mq_try_issue_directly(hctx, rq, &unused_cookie, true, last);
+	ret = __blk_mq_try_issue_directly(hctx, rq, true, last);
 	hctx_unlock(hctx, srcu_idx);
 
 	return ret;
@@ -2186,10 +2189,8 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
  *
  * It will not queue the request if there is an error with the bio, or at the
  * request creation.
- *
- * Returns: Request queue cookie.
  */
-blk_qc_t blk_mq_submit_bio(struct bio *bio)
+void blk_mq_submit_bio(struct bio *bio)
 {
 	struct request_queue *q = bio->bi_bdev->bd_disk->queue;
 	const int is_sync = op_is_sync(bio->bi_opf);
@@ -2201,9 +2202,7 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
 	struct blk_plug *plug;
 	struct request *same_queue_rq = NULL;
 	unsigned int nr_segs;
-	blk_qc_t cookie;
 	blk_status_t ret;
-	bool hipri;
 
 	blk_queue_bounce(q, &bio);
 	__blk_queue_split(&bio, &nr_segs);
@@ -2220,8 +2219,6 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
 
 	rq_qos_throttle(q, bio);
 
-	hipri = bio->bi_opf & REQ_POLLED;
-
 	data.cmd_flags = bio->bi_opf;
 	rq = __blk_mq_alloc_request(&data);
 	if (unlikely(!rq)) {
@@ -2235,8 +2232,6 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
 
 	rq_qos_track(q, rq, bio);
 
-	cookie = request_to_qc_t(data.hctx, rq);
-
 	blk_mq_bio_to_request(rq, bio, nr_segs);
 
 	ret = blk_crypto_init_request(rq);
@@ -2244,7 +2239,7 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
 		bio->bi_status = ret;
 		bio_endio(bio);
 		blk_mq_free_request(rq);
-		return BLK_QC_T_NONE;
+		return;
 	}
 
 	plug = blk_mq_plug(q, bio);
@@ -2300,8 +2295,7 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
 		if (same_queue_rq) {
 			data.hctx = same_queue_rq->mq_hctx;
 			trace_block_unplug(q, 1, true);
-			blk_mq_try_issue_directly(data.hctx, same_queue_rq,
-					&cookie);
+			blk_mq_try_issue_directly(data.hctx, same_queue_rq);
 		}
 	} else if ((q->nr_hw_queues > 1 && is_sync) ||
 			!data.hctx->dispatch_busy) {
@@ -2309,18 +2303,15 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
 		 * There is no scheduler and we can try to send directly
 		 * to the hardware.
 		 */
-		blk_mq_try_issue_directly(data.hctx, rq, &cookie);
+		blk_mq_try_issue_directly(data.hctx, rq);
 	} else {
 		/* Default case. */
 		blk_mq_sched_insert_request(rq, false, true, true);
 	}
 
-	if (!hipri)
-		return BLK_QC_T_NONE;
-	return cookie;
+	return;
 queue_exit:
 	blk_queue_exit(q);
-	return BLK_QC_T_NONE;
 }
 
 static size_t order_to_size(unsigned int order)
@@ -3983,25 +3974,8 @@ static int blk_mq_poll_classic(struct request_queue *q, blk_qc_t cookie,
 	return 0;
 }
 
-/**
- * blk_poll - poll for IO completions
- * @q:  the queue
- * @cookie: cookie passed back at IO submission time
- * @flags: BLK_POLL_* flags that control the behavior
- *
- * Description:
- *    Poll for completions on the passed in queue. Returns number of
- *    completed entries found.
- */
-int blk_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags)
+int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags)
 {
-	if (cookie == BLK_QC_T_NONE ||
-	    !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
-		return 0;
-
-	if (current->plug)
-		blk_flush_plug_list(current->plug, false);
-
 	if (!(flags & BLK_POLL_NOSLEEP) &&
 	    q->poll_nsec != BLK_MQ_POLL_CLASSIC) {
 		if (blk_mq_poll_hybrid(q, cookie))
@@ -4009,7 +3983,6 @@ int blk_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags)
 	}
 	return blk_mq_poll_classic(q, cookie, flags);
 }
-EXPORT_SYMBOL_GPL(blk_poll);
 
 unsigned int blk_mq_rq_cpu(struct request *rq)
 {
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 8444e00e8d25..66d1a628a2a1 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -37,6 +37,8 @@ struct blk_mq_ctx {
 	struct kobject		kobj;
 } ____cacheline_aligned_in_smp;
 
+void blk_mq_submit_bio(struct bio *bio);
+int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags);
 void blk_mq_exit_queue(struct request_queue *q);
 int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
 void blk_mq_wake_waiters(struct request_queue *q);
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 95694113e38e..274e2634ea58 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -285,7 +285,7 @@ static int brd_do_bvec(struct brd_device *brd, struct page *page,
 	return err;
 }
 
-static blk_qc_t brd_submit_bio(struct bio *bio)
+static void brd_submit_bio(struct bio *bio)
 {
 	struct brd_device *brd = bio->bi_bdev->bd_disk->private_data;
 	sector_t sector = bio->bi_iter.bi_sector;
@@ -302,16 +302,14 @@ static blk_qc_t brd_submit_bio(struct bio *bio)
 
 		err = brd_do_bvec(brd, bvec.bv_page, len, bvec.bv_offset,
 				  bio_op(bio), sector);
-		if (err)
-			goto io_error;
+		if (err) {
+			bio_io_error(bio);
+			return;
+		}
 		sector += len >> SECTOR_SHIFT;
 	}
 
 	bio_endio(bio);
-	return BLK_QC_T_NONE;
-io_error:
-	bio_io_error(bio);
-	return BLK_QC_T_NONE;
 }
 
 static int brd_rw_page(struct block_device *bdev, sector_t sector,
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 5d9181382ce1..6674a0b88341 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1448,7 +1448,7 @@ extern void conn_free_crypto(struct drbd_connection *connection);
 /* drbd_req */
 extern void do_submit(struct work_struct *ws);
 extern void __drbd_make_request(struct drbd_device *, struct bio *);
-extern blk_qc_t drbd_submit_bio(struct bio *bio);
+void drbd_submit_bio(struct bio *bio);
 extern int drbd_read_remote(struct drbd_device *device, struct drbd_request *req);
 extern int is_valid_ar_handle(struct drbd_request *, sector_t);
 
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 13beb98a7c5a..0a2b3cb7e0bd 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -1597,7 +1597,7 @@ void do_submit(struct work_struct *ws)
 	}
 }
 
-blk_qc_t drbd_submit_bio(struct bio *bio)
+void drbd_submit_bio(struct bio *bio)
 {
 	struct drbd_device *device = bio->bi_bdev->bd_disk->private_data;
 
@@ -1610,7 +1610,6 @@ blk_qc_t drbd_submit_bio(struct bio *bio)
 
 	inc_ap_bio(device);
 	__drbd_make_request(device, bio);
-	return BLK_QC_T_NONE;
 }
 
 static bool net_timeout_reached(struct drbd_request *net_req,
diff --git a/drivers/block/n64cart.c b/drivers/block/n64cart.c
index 7b4dd10af9ec..f95fd4f04f28 100644
--- a/drivers/block/n64cart.c
+++ b/drivers/block/n64cart.c
@@ -84,7 +84,7 @@ static bool n64cart_do_bvec(struct device *dev, struct bio_vec *bv, u32 pos)
 	return true;
 }
 
-static blk_qc_t n64cart_submit_bio(struct bio *bio)
+static void n64cart_submit_bio(struct bio *bio)
 {
 	struct bio_vec bvec;
 	struct bvec_iter iter;
@@ -92,16 +92,14 @@ static blk_qc_t n64cart_submit_bio(struct bio *bio)
 	u32 pos = bio->bi_iter.bi_sector << SECTOR_SHIFT;
 
 	bio_for_each_segment(bvec, bio, iter) {
-		if (!n64cart_do_bvec(dev, &bvec, pos))
-			goto io_error;
+		if (!n64cart_do_bvec(dev, &bvec, pos)) {
+			bio_io_error(bio);
+			return;
+		}
 		pos += bvec.bv_len;
 	}
 
 	bio_endio(bio);
-	return BLK_QC_T_NONE;
-io_error:
-	bio_io_error(bio);
-	return BLK_QC_T_NONE;
 }
 
 static const struct block_device_operations n64cart_fops = {
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index 3b320b005aa8..7ce063871a5d 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -1426,7 +1426,7 @@ static struct nullb_queue *nullb_to_queue(struct nullb *nullb)
 	return &nullb->queues[index];
 }
 
-static blk_qc_t null_submit_bio(struct bio *bio)
+static void null_submit_bio(struct bio *bio)
 {
 	sector_t sector = bio->bi_iter.bi_sector;
 	sector_t nr_sectors = bio_sectors(bio);
@@ -1438,7 +1438,6 @@ static blk_qc_t null_submit_bio(struct bio *bio)
 	cmd->bio = bio;
 
 	null_handle_cmd(cmd, sector, nr_sectors, bio_op(bio));
-	return BLK_QC_T_NONE;
 }
 
 static bool should_timeout_request(struct request *rq)
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index f69b5c69c2a6..5bfb26f90b6d 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2402,7 +2402,7 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio)
 	}
 }
 
-static blk_qc_t pkt_submit_bio(struct bio *bio)
+static void pkt_submit_bio(struct bio *bio)
 {
 	struct pktcdvd_device *pd;
 	char b[BDEVNAME_SIZE];
@@ -2425,7 +2425,7 @@ static blk_qc_t pkt_submit_bio(struct bio *bio)
 	 */
 	if (bio_data_dir(bio) == READ) {
 		pkt_make_request_read(pd, bio);
-		return BLK_QC_T_NONE;
+		return;
 	}
 
 	if (!test_bit(PACKET_WRITABLE, &pd->flags)) {
@@ -2457,10 +2457,9 @@ static blk_qc_t pkt_submit_bio(struct bio *bio)
 		pkt_make_request_write(bio->bi_bdev->bd_disk->queue, split);
 	} while (split != bio);
 
-	return BLK_QC_T_NONE;
+	return;
 end_io:
 	bio_io_error(bio);
-	return BLK_QC_T_NONE;
 }
 
 static void pkt_init_queue(struct pktcdvd_device *pd)
diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c
index 7fbf469651c4..507520cab9c3 100644
--- a/drivers/block/ps3vram.c
+++ b/drivers/block/ps3vram.c
@@ -578,7 +578,7 @@ static struct bio *ps3vram_do_bio(struct ps3_system_bus_device *dev,
 	return next;
 }
 
-static blk_qc_t ps3vram_submit_bio(struct bio *bio)
+static void ps3vram_submit_bio(struct bio *bio)
 {
 	struct ps3_system_bus_device *dev = bio->bi_bdev->bd_disk->private_data;
 	struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev);
@@ -594,13 +594,11 @@ static blk_qc_t ps3vram_submit_bio(struct bio *bio)
 	spin_unlock_irq(&priv->lock);
 
 	if (busy)
-		return BLK_QC_T_NONE;
+		return;
 
 	do {
 		bio = ps3vram_do_bio(dev, bio);
 	} while (bio);
-
-	return BLK_QC_T_NONE;
 }
 
 static const struct block_device_operations ps3vram_fops = {
diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c
index 1cc40b0ea761..268252380e88 100644
--- a/drivers/block/rsxx/dev.c
+++ b/drivers/block/rsxx/dev.c
@@ -50,7 +50,7 @@ struct rsxx_bio_meta {
 
 static struct kmem_cache *bio_meta_pool;
 
-static blk_qc_t rsxx_submit_bio(struct bio *bio);
+static void rsxx_submit_bio(struct bio *bio);
 
 /*----------------- Block Device Operations -----------------*/
 static int rsxx_blkdev_ioctl(struct block_device *bdev,
@@ -120,7 +120,7 @@ static void bio_dma_done_cb(struct rsxx_cardinfo *card,
 	}
 }
 
-static blk_qc_t rsxx_submit_bio(struct bio *bio)
+static void rsxx_submit_bio(struct bio *bio)
 {
 	struct rsxx_cardinfo *card = bio->bi_bdev->bd_disk->private_data;
 	struct rsxx_bio_meta *bio_meta;
@@ -169,7 +169,7 @@ static blk_qc_t rsxx_submit_bio(struct bio *bio)
 	if (st)
 		goto queue_err;
 
-	return BLK_QC_T_NONE;
+	return;
 
 queue_err:
 	kmem_cache_free(bio_meta_pool, bio_meta);
@@ -177,7 +177,6 @@ static blk_qc_t rsxx_submit_bio(struct bio *bio)
 	if (st)
 		bio->bi_status = st;
 	bio_endio(bio);
-	return BLK_QC_T_NONE;
 }
 
 /*----------------- Device Setup -------------------*/
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index fcaf2750f68f..a68297fb51a2 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1598,22 +1598,18 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 /*
  * Handler function for all zram I/O requests.
  */
-static blk_qc_t zram_submit_bio(struct bio *bio)
+static void zram_submit_bio(struct bio *bio)
 {
 	struct zram *zram = bio->bi_bdev->bd_disk->private_data;
 
 	if (!valid_io_request(zram, bio->bi_iter.bi_sector,
 					bio->bi_iter.bi_size)) {
 		atomic64_inc(&zram->stats.invalid_io);
-		goto error;
+		bio_io_error(bio);
+		return;
 	}
 
 	__zram_make_request(zram, bio);
-	return BLK_QC_T_NONE;
-
-error:
-	bio_io_error(bio);
-	return BLK_QC_T_NONE;
 }
 
 static void zram_slot_free_notify(struct block_device *bdev,
diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index 5924f09c217b..6716003d4cb6 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -47,7 +47,7 @@ static struct pblk_global_caches pblk_caches = {
 
 struct bio_set pblk_bio_set;
 
-static blk_qc_t pblk_submit_bio(struct bio *bio)
+static void pblk_submit_bio(struct bio *bio)
 {
 	struct pblk *pblk = bio->bi_bdev->bd_disk->queue->queuedata;
 
@@ -55,7 +55,7 @@ static blk_qc_t pblk_submit_bio(struct bio *bio)
 		pblk_discard(pblk, bio);
 		if (!(bio->bi_opf & REQ_PREFLUSH)) {
 			bio_endio(bio);
-			return BLK_QC_T_NONE;
+			return;
 		}
 	}
 
@@ -75,8 +75,6 @@ static blk_qc_t pblk_submit_bio(struct bio *bio)
 
 		pblk_write_to_cache(pblk, bio, PBLK_IOTYPE_USER);
 	}
-
-	return BLK_QC_T_NONE;
 }
 
 static const struct block_device_operations pblk_bops = {
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 29c231758293..b549147a567f 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -1169,7 +1169,7 @@ static void quit_max_writeback_rate(struct cache_set *c,
 
 /* Cached devices - read & write stuff */
 
-blk_qc_t cached_dev_submit_bio(struct bio *bio)
+void cached_dev_submit_bio(struct bio *bio)
 {
 	struct search *s;
 	struct block_device *orig_bdev = bio->bi_bdev;
@@ -1182,7 +1182,7 @@ blk_qc_t cached_dev_submit_bio(struct bio *bio)
 		     dc->io_disable)) {
 		bio->bi_status = BLK_STS_IOERR;
 		bio_endio(bio);
-		return BLK_QC_T_NONE;
+		return;
 	}
 
 	if (likely(d->c)) {
@@ -1228,8 +1228,6 @@ blk_qc_t cached_dev_submit_bio(struct bio *bio)
 	} else
 		/* I/O request sent to backing device */
 		detached_dev_do_request(d, bio, orig_bdev, start_time);
-
-	return BLK_QC_T_NONE;
 }
 
 static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode,
@@ -1279,7 +1277,7 @@ static void flash_dev_nodata(struct closure *cl)
 	continue_at(cl, search_free, NULL);
 }
 
-blk_qc_t flash_dev_submit_bio(struct bio *bio)
+void flash_dev_submit_bio(struct bio *bio)
 {
 	struct search *s;
 	struct closure *cl;
@@ -1288,7 +1286,7 @@ blk_qc_t flash_dev_submit_bio(struct bio *bio)
 	if (unlikely(d->c && test_bit(CACHE_SET_IO_DISABLE, &d->c->flags))) {
 		bio->bi_status = BLK_STS_IOERR;
 		bio_endio(bio);
-		return BLK_QC_T_NONE;
+		return;
 	}
 
 	s = search_alloc(bio, d, bio->bi_bdev, bio_start_io_acct(bio));
@@ -1304,7 +1302,7 @@ blk_qc_t flash_dev_submit_bio(struct bio *bio)
 		continue_at_nobarrier(&s->cl,
 				      flash_dev_nodata,
 				      bcache_wq);
-		return BLK_QC_T_NONE;
+		return;
 	} else if (bio_data_dir(bio)) {
 		bch_keybuf_check_overlapping(&s->iop.c->moving_gc_keys,
 					&KEY(d->id, bio->bi_iter.bi_sector, 0),
@@ -1320,7 +1318,6 @@ blk_qc_t flash_dev_submit_bio(struct bio *bio)
 	}
 
 	continue_at(cl, search_free, NULL);
-	return BLK_QC_T_NONE;
 }
 
 static int flash_dev_ioctl(struct bcache_device *d, fmode_t mode,
diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h
index 82b38366a95d..38ab4856eaab 100644
--- a/drivers/md/bcache/request.h
+++ b/drivers/md/bcache/request.h
@@ -37,10 +37,10 @@ unsigned int bch_get_congested(const struct cache_set *c);
 void bch_data_insert(struct closure *cl);
 
 void bch_cached_dev_request_init(struct cached_dev *dc);
-blk_qc_t cached_dev_submit_bio(struct bio *bio);
+void cached_dev_submit_bio(struct bio *bio);
 
 void bch_flash_dev_request_init(struct bcache_device *d);
-blk_qc_t flash_dev_submit_bio(struct bio *bio);
+void flash_dev_submit_bio(struct bio *bio);
 
 extern struct kmem_cache *bch_search_cache;
 
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 3c7c2d257018..363f12a285ce 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1292,14 +1292,13 @@ static noinline void __set_swap_bios_limit(struct mapped_device *md, int latch)
 	mutex_unlock(&md->swap_bios_lock);
 }
 
-static blk_qc_t __map_bio(struct dm_target_io *tio)
+static void __map_bio(struct dm_target_io *tio)
 {
 	int r;
 	sector_t sector;
 	struct bio *clone = &tio->clone;
 	struct dm_io *io = tio->io;
 	struct dm_target *ti = tio->ti;
-	blk_qc_t ret = BLK_QC_T_NONE;
 
 	clone->bi_end_io = clone_endio;
 
@@ -1326,7 +1325,7 @@ static blk_qc_t __map_bio(struct dm_target_io *tio)
 	case DM_MAPIO_REMAPPED:
 		/* the bio has been remapped so dispatch it */
 		trace_block_bio_remap(clone, bio_dev(io->orig_bio), sector);
-		ret = submit_bio_noacct(clone);
+		submit_bio_noacct(clone);
 		break;
 	case DM_MAPIO_KILL:
 		if (unlikely(swap_bios_limit(ti, clone))) {
@@ -1348,8 +1347,6 @@ static blk_qc_t __map_bio(struct dm_target_io *tio)
 		DMWARN("unimplemented target map return value: %d", r);
 		BUG();
 	}
-
-	return ret;
 }
 
 static void bio_setup_sector(struct bio *bio, sector_t sector, unsigned len)
@@ -1436,7 +1433,7 @@ static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci,
 	}
 }
 
-static blk_qc_t __clone_and_map_simple_bio(struct clone_info *ci,
+static void __clone_and_map_simple_bio(struct clone_info *ci,
 					   struct dm_target_io *tio, unsigned *len)
 {
 	struct bio *clone = &tio->clone;
@@ -1446,8 +1443,7 @@ static blk_qc_t __clone_and_map_simple_bio(struct clone_info *ci,
 	__bio_clone_fast(clone, ci->bio);
 	if (len)
 		bio_setup_sector(clone, ci->sector, *len);
-
-	return __map_bio(tio);
+	__map_bio(tio);
 }
 
 static void __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti,
@@ -1461,7 +1457,7 @@ static void __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti,
 
 	while ((bio = bio_list_pop(&blist))) {
 		tio = container_of(bio, struct dm_target_io, clone);
-		(void) __clone_and_map_simple_bio(ci, tio, len);
+		__clone_and_map_simple_bio(ci, tio, len);
 	}
 }
 
@@ -1505,7 +1501,7 @@ static int __clone_and_map_data_bio(struct clone_info *ci, struct dm_target *ti,
 		free_tio(tio);
 		return r;
 	}
-	(void) __map_bio(tio);
+	__map_bio(tio);
 
 	return 0;
 }
@@ -1620,11 +1616,10 @@ static void init_clone_info(struct clone_info *ci, struct mapped_device *md,
 /*
  * Entry point to split a bio into clones and submit them to the targets.
  */
-static blk_qc_t __split_and_process_bio(struct mapped_device *md,
+static void __split_and_process_bio(struct mapped_device *md,
 					struct dm_table *map, struct bio *bio)
 {
 	struct clone_info ci;
-	blk_qc_t ret = BLK_QC_T_NONE;
 	int error = 0;
 
 	init_clone_info(&ci, md, map, bio);
@@ -1667,19 +1662,17 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 
 			bio_chain(b, bio);
 			trace_block_split(b, bio->bi_iter.bi_sector);
-			ret = submit_bio_noacct(bio);
+			submit_bio_noacct(bio);
 		}
 	}
 
 	/* drop the extra reference count */
 	dec_pending(ci.io, errno_to_blk_status(error));
-	return ret;
 }
 
-static blk_qc_t dm_submit_bio(struct bio *bio)
+static void dm_submit_bio(struct bio *bio)
 {
 	struct mapped_device *md = bio->bi_bdev->bd_disk->private_data;
-	blk_qc_t ret = BLK_QC_T_NONE;
 	int srcu_idx;
 	struct dm_table *map;
 
@@ -1709,10 +1702,9 @@ static blk_qc_t dm_submit_bio(struct bio *bio)
 	if (is_abnormal_io(bio))
 		blk_queue_split(&bio);
 
-	ret = __split_and_process_bio(md, map, bio);
+	__split_and_process_bio(md, map, bio);
 out:
 	dm_put_live_table(md, srcu_idx);
-	return ret;
 }
 
 /*-----------------------------------------------------------------
diff --git a/drivers/md/md.c b/drivers/md/md.c
index d806be8cc210..7a98437a376b 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -465,19 +465,19 @@ static void md_end_io(struct bio *bio)
 		bio->bi_end_io(bio);
 }
 
-static blk_qc_t md_submit_bio(struct bio *bio)
+static void md_submit_bio(struct bio *bio)
 {
 	const int rw = bio_data_dir(bio);
 	struct mddev *mddev = bio->bi_bdev->bd_disk->private_data;
 
 	if (mddev == NULL || mddev->pers == NULL) {
 		bio_io_error(bio);
-		return BLK_QC_T_NONE;
+		return;
 	}
 
 	if (unlikely(test_bit(MD_BROKEN, &mddev->flags)) && (rw == WRITE)) {
 		bio_io_error(bio);
-		return BLK_QC_T_NONE;
+		return;
 	}
 
 	blk_queue_split(&bio);
@@ -486,7 +486,7 @@ static blk_qc_t md_submit_bio(struct bio *bio)
 		if (bio_sectors(bio) != 0)
 			bio->bi_status = BLK_STS_IOERR;
 		bio_endio(bio);
-		return BLK_QC_T_NONE;
+		return;
 	}
 
 	if (bio->bi_end_io != md_end_io) {
@@ -508,8 +508,6 @@ static blk_qc_t md_submit_bio(struct bio *bio)
 	bio->bi_opf &= ~REQ_NOMERGE;
 
 	md_handle_request(mddev, bio);
-
-	return BLK_QC_T_NONE;
 }
 
 /* mddev_suspend makes sure no new requests are submitted
diff --git a/drivers/nvdimm/blk.c b/drivers/nvdimm/blk.c
index 088d3dd6f6fa..b6c6866f9259 100644
--- a/drivers/nvdimm/blk.c
+++ b/drivers/nvdimm/blk.c
@@ -162,7 +162,7 @@ static int nsblk_do_bvec(struct nd_namespace_blk *nsblk,
 	return err;
 }
 
-static blk_qc_t nd_blk_submit_bio(struct bio *bio)
+static void nd_blk_submit_bio(struct bio *bio)
 {
 	struct bio_integrity_payload *bip;
 	struct nd_namespace_blk *nsblk = bio->bi_bdev->bd_disk->private_data;
@@ -173,7 +173,7 @@ static blk_qc_t nd_blk_submit_bio(struct bio *bio)
 	bool do_acct;
 
 	if (!bio_integrity_prep(bio))
-		return BLK_QC_T_NONE;
+		return;
 
 	bip = bio_integrity(bio);
 	rw = bio_data_dir(bio);
@@ -199,7 +199,6 @@ static blk_qc_t nd_blk_submit_bio(struct bio *bio)
 		bio_end_io_acct(bio, start);
 
 	bio_endio(bio);
-	return BLK_QC_T_NONE;
 }
 
 static int nsblk_rw_bytes(struct nd_namespace_common *ndns,
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 92dec4952297..4295fa809420 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1440,7 +1440,7 @@ static int btt_do_bvec(struct btt *btt, struct bio_integrity_payload *bip,
 	return ret;
 }
 
-static blk_qc_t btt_submit_bio(struct bio *bio)
+static void btt_submit_bio(struct bio *bio)
 {
 	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct btt *btt = bio->bi_bdev->bd_disk->private_data;
@@ -1451,7 +1451,7 @@ static blk_qc_t btt_submit_bio(struct bio *bio)
 	bool do_acct;
 
 	if (!bio_integrity_prep(bio))
-		return BLK_QC_T_NONE;
+		return;
 
 	do_acct = blk_queue_io_stat(bio->bi_bdev->bd_disk->queue);
 	if (do_acct)
@@ -1483,7 +1483,6 @@ static blk_qc_t btt_submit_bio(struct bio *bio)
 		bio_end_io_acct(bio, start);
 
 	bio_endio(bio);
-	return BLK_QC_T_NONE;
 }
 
 static int btt_rw_page(struct block_device *bdev, sector_t sector,
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 1e0615b8565e..773385e16b4d 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -190,7 +190,7 @@ static blk_status_t pmem_do_write(struct pmem_device *pmem,
 	return rc;
 }
 
-static blk_qc_t pmem_submit_bio(struct bio *bio)
+static void pmem_submit_bio(struct bio *bio)
 {
 	int ret = 0;
 	blk_status_t rc = 0;
@@ -229,7 +229,6 @@ static blk_qc_t pmem_submit_bio(struct bio *bio)
 		bio->bi_status = errno_to_blk_status(ret);
 
 	bio_endio(bio);
-	return BLK_QC_T_NONE;
 }
 
 static int pmem_rw_page(struct block_device *bdev, sector_t sector,
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 1f2ecb2fe9b1..fe0b8da3de7f 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1032,7 +1032,7 @@ static void nvme_execute_rq_polled(struct request_queue *q,
 	blk_execute_rq_nowait(bd_disk, rq, at_head, nvme_end_sync_rq);
 
 	while (!completion_done(&wait)) {
-		blk_poll(q, request_to_qc_t(rq->mq_hctx, rq), 0);
+		bio_poll(rq->bio, 0);
 		cond_resched();
 	}
 }
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index b5fbdb416022..c1b4d627c05b 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -297,12 +297,11 @@ static bool nvme_available_path(struct nvme_ns_head *head)
 	return false;
 }
 
-static blk_qc_t nvme_ns_head_submit_bio(struct bio *bio)
+static void nvme_ns_head_submit_bio(struct bio *bio)
 {
 	struct nvme_ns_head *head = bio->bi_bdev->bd_disk->private_data;
 	struct device *dev = disk_to_dev(head->disk);
 	struct nvme_ns *ns;
-	blk_qc_t ret = BLK_QC_T_NONE;
 	int srcu_idx;
 
 	/*
@@ -319,7 +318,7 @@ static blk_qc_t nvme_ns_head_submit_bio(struct bio *bio)
 		bio->bi_opf |= REQ_NVME_MPATH;
 		trace_block_bio_remap(bio, disk_devt(ns->head->disk),
 				      bio->bi_iter.bi_sector);
-		ret = submit_bio_noacct(bio);
+		submit_bio_noacct(bio);
 	} else if (nvme_available_path(head)) {
 		dev_warn_ratelimited(dev, "no usable path - requeuing I/O\n");
 
@@ -334,7 +333,6 @@ static blk_qc_t nvme_ns_head_submit_bio(struct bio *bio)
 	}
 
 	srcu_read_unlock(&head->srcu, srcu_idx);
-	return ret;
 }
 
 static int nvme_ns_head_open(struct block_device *bdev, fmode_t mode)
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 7faa56399999..72a34d1486d1 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -31,7 +31,7 @@
 
 static int dcssblk_open(struct block_device *bdev, fmode_t mode);
 static void dcssblk_release(struct gendisk *disk, fmode_t mode);
-static blk_qc_t dcssblk_submit_bio(struct bio *bio);
+static void dcssblk_submit_bio(struct bio *bio);
 static long dcssblk_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
 		long nr_pages, void **kaddr, pfn_t *pfn);
 
@@ -855,7 +855,7 @@ dcssblk_release(struct gendisk *disk, fmode_t mode)
 	up_write(&dcssblk_devices_sem);
 }
 
-static blk_qc_t
+static void
 dcssblk_submit_bio(struct bio *bio)
 {
 	struct dcssblk_dev_info *dev_info;
@@ -909,10 +909,9 @@ dcssblk_submit_bio(struct bio *bio)
 		bytes_done += bvec.bv_len;
 	}
 	bio_endio(bio);
-	return BLK_QC_T_NONE;
+	return;
 fail:
 	bio_io_error(bio);
-	return BLK_QC_T_NONE;
 }
 
 static long
diff --git a/drivers/s390/block/xpram.c b/drivers/s390/block/xpram.c
index 91ef710edfd2..aa49a6022d45 100644
--- a/drivers/s390/block/xpram.c
+++ b/drivers/s390/block/xpram.c
@@ -181,7 +181,7 @@ static unsigned long xpram_highest_page_index(void)
 /*
  * Block device make request function.
  */
-static blk_qc_t xpram_submit_bio(struct bio *bio)
+static void xpram_submit_bio(struct bio *bio)
 {
 	xpram_device_t *xdev = bio->bi_bdev->bd_disk->private_data;
 	struct bio_vec bvec;
@@ -223,10 +223,9 @@ static blk_qc_t xpram_submit_bio(struct bio *bio)
 		}
 	}
 	bio_endio(bio);
-	return BLK_QC_T_NONE;
+	return;
 fail:
 	bio_io_error(bio);
-	return BLK_QC_T_NONE;
 }
 
 static int xpram_getgeo(struct block_device *bdev, struct hd_geometry *geo)
diff --git a/fs/block_dev.c b/fs/block_dev.c
index c9bdaa138909..6be5ddba86a3 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -239,7 +239,6 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 	bool should_dirty = false;
 	struct bio bio;
 	ssize_t ret;
-	blk_qc_t qc;
 
 	if ((pos | iov_iter_alignment(iter)) &
 	    (bdev_logical_block_size(bdev) - 1))
@@ -280,13 +279,12 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 	if (iocb->ki_flags & IOCB_HIPRI)
 		bio_set_polled(&bio, iocb);
 
-	qc = submit_bio(&bio);
+	submit_bio(&bio);
 	for (;;) {
 		set_current_state(TASK_UNINTERRUPTIBLE);
 		if (!READ_ONCE(bio.bi_private))
 			break;
-		if (!(iocb->ki_flags & IOCB_HIPRI) ||
-		    !blk_poll(bdev_get_queue(bdev), qc, 0))
+		if (!(iocb->ki_flags & IOCB_HIPRI) || !bio_poll(&bio, 0))
 			blk_io_schedule();
 	}
 	__set_current_state(TASK_RUNNING);
@@ -319,14 +317,6 @@ struct blkdev_dio {
 
 static struct bio_set blkdev_dio_pool;
 
-static int blkdev_iopoll(struct kiocb *kiocb, unsigned int flags)
-{
-	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), flags);
-}
-
 static void blkdev_bio_end_io(struct bio *bio)
 {
 	struct blkdev_dio *dio = bio->bi_private;
@@ -340,6 +330,8 @@ static void blkdev_bio_end_io(struct bio *bio)
 			struct kiocb *iocb = dio->iocb;
 			ssize_t ret;
 
+			WRITE_ONCE(iocb->private, NULL);
+
 			if (likely(!dio->bio.bi_status)) {
 				ret = dio->size;
 				iocb->ki_pos += ret;
@@ -378,7 +370,6 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	bool do_poll = (iocb->ki_flags & IOCB_HIPRI);
 	bool is_read = (iov_iter_rw(iter) == READ), is_sync;
 	loff_t pos = iocb->ki_pos;
-	blk_qc_t qc = BLK_QC_T_NONE;
 	int ret = 0;
 
 	if ((pos | iov_iter_alignment(iter)) &
@@ -440,9 +431,9 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 		if (!nr_pages) {
 			if (do_poll)
 				bio_set_polled(bio, iocb);
-			qc = submit_bio(bio);
+			submit_bio(bio);
 			if (do_poll)
-				WRITE_ONCE(iocb->ki_cookie, qc);
+				WRITE_ONCE(iocb->private, bio);
 			break;
 		}
 		if (!dio->multi_bio) {
@@ -475,7 +466,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 		if (!READ_ONCE(dio->waiter))
 			break;
 
-		if (!do_poll || !blk_poll(bdev_get_queue(bdev), qc, 0))
+		if (!do_poll || !bio_poll(bio, 0))
 			blk_io_schedule();
 	}
 	__set_current_state(TASK_RUNNING);
@@ -1825,7 +1816,7 @@ const struct file_operations def_blk_fops = {
 	.llseek		= block_llseek,
 	.read_iter	= blkdev_read_iter,
 	.write_iter	= blkdev_write_iter,
-	.iopoll		= blkdev_iopoll,
+	.iopoll		= iocb_bio_iopoll,
 	.mmap		= generic_file_mmap,
 	.fsync		= blkdev_fsync,
 	.unlocked_ioctl	= block_ioctl,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 33f14573f2ec..450d82998c23 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -8104,7 +8104,7 @@ static struct btrfs_dio_private *btrfs_create_dio_private(struct bio *dio_bio,
 	return dip;
 }
 
-static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap,
+static void btrfs_submit_direct(struct inode *inode, struct iomap *iomap,
 		struct bio *dio_bio, loff_t file_offset)
 {
 	const bool write = (btrfs_op(dio_bio) == BTRFS_MAP_WRITE);
@@ -8133,7 +8133,7 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap,
 		}
 		dio_bio->bi_status = BLK_STS_RESOURCE;
 		bio_endio(dio_bio);
-		return BLK_QC_T_NONE;
+		return;
 	}
 
 	if (!write) {
@@ -8227,15 +8227,13 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap,
 
 		free_extent_map(em);
 	} while (submit_len > 0);
-	return BLK_QC_T_NONE;
+	return;
 
 out_err_em:
 	free_extent_map(em);
 out_err:
 	dip->dio_bio->bi_status = status;
 	btrfs_dio_private_put(dip);
-
-	return BLK_QC_T_NONE;
 }
 
 const struct iomap_ops btrfs_dio_iomap_ops = {
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 816dedcbd541..6146c4203fda 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -913,7 +913,7 @@ const struct file_operations ext4_file_operations = {
 	.llseek		= ext4_llseek,
 	.read_iter	= ext4_file_read_iter,
 	.write_iter	= ext4_file_write_iter,
-	.iopoll		= iomap_dio_iopoll,
+	.iopoll		= iocb_bio_iopoll,
 	.unlocked_ioctl = ext4_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext4_compat_ioctl,
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index a0b542d84cd9..d51d0c663bde 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -1334,7 +1334,7 @@ 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,
+	.iopoll		= iocb_bio_iopoll,
 	.unlocked_ioctl	= gfs2_ioctl,
 	.compat_ioctl	= gfs2_compat_ioctl,
 	.mmap		= gfs2_mmap,
@@ -1367,7 +1367,7 @@ 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,
+	.iopoll		= iocb_bio_iopoll,
 	.unlocked_ioctl	= gfs2_ioctl,
 	.compat_ioctl	= gfs2_compat_ioctl,
 	.mmap		= gfs2_mmap,
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 9b6c26da3a2d..76bc7c4b0deb 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -38,8 +38,7 @@ struct iomap_dio {
 		struct {
 			struct iov_iter		*iter;
 			struct task_struct	*waiter;
-			struct request_queue	*last_queue;
-			blk_qc_t		cookie;
+			struct bio		*poll_bio;
 		} submit;
 
 		/* used for aio completion: */
@@ -49,31 +48,21 @@ struct iomap_dio {
 	};
 };
 
-int iomap_dio_iopoll(struct kiocb *kiocb, unsigned int flags)
-{
-	struct request_queue *q = READ_ONCE(kiocb->private);
-
-	if (!q)
-		return 0;
-	return blk_poll(q, READ_ONCE(kiocb->ki_cookie), flags);
-}
-EXPORT_SYMBOL_GPL(iomap_dio_iopoll);
-
 static void iomap_dio_submit_bio(struct iomap_dio *dio, struct iomap *iomap,
 		struct bio *bio, loff_t pos)
 {
 	atomic_inc(&dio->ref);
 
-	if (dio->iocb->ki_flags & IOCB_HIPRI)
+	if (dio->iocb->ki_flags & IOCB_HIPRI) {
 		bio_set_polled(bio, dio->iocb);
+		dio->submit.poll_bio = bio;
+	}
 
-	dio->submit.last_queue = bdev_get_queue(iomap->bdev);
 	if (dio->dops && dio->dops->submit_io)
-		dio->submit.cookie = dio->dops->submit_io(
-				file_inode(dio->iocb->ki_filp),
-				iomap, bio, pos);
+		dio->dops->submit_io(file_inode(dio->iocb->ki_filp), iomap, bio,
+				     pos);
 	else
-		dio->submit.cookie = submit_bio(bio);
+		submit_bio(bio);
 }
 
 ssize_t iomap_dio_complete(struct iomap_dio *dio)
@@ -166,9 +155,11 @@ static void iomap_dio_bio_end_io(struct bio *bio)
 		} else if (dio->flags & IOMAP_DIO_WRITE) {
 			struct inode *inode = file_inode(dio->iocb->ki_filp);
 
+			WRITE_ONCE(dio->iocb->private, NULL);
 			INIT_WORK(&dio->aio.work, iomap_dio_complete_work);
 			queue_work(inode->i_sb->s_dio_done_wq, &dio->aio.work);
 		} else {
+			WRITE_ONCE(dio->iocb->private, NULL);
 			iomap_dio_complete_work(&dio->aio.work);
 		}
 	}
@@ -492,8 +483,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 
 	dio->submit.iter = iter;
 	dio->submit.waiter = current;
-	dio->submit.cookie = BLK_QC_T_NONE;
-	dio->submit.last_queue = NULL;
+	dio->submit.poll_bio = NULL;
 
 	if (iov_iter_rw(iter) == READ) {
 		if (pos >= dio->i_size)
@@ -609,8 +599,7 @@ __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);
+	WRITE_ONCE(iocb->private, dio->submit.poll_bio);
 
 	/*
 	 * We are about to drop our additional submission reference, which
@@ -637,10 +626,8 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 			if (!READ_ONCE(dio->submit.waiter))
 				break;
 
-			if (!(iocb->ki_flags & IOCB_HIPRI) ||
-			    !dio->submit.last_queue ||
-			    !blk_poll(dio->submit.last_queue,
-					 dio->submit.cookie, 0))
+			if (!dio->submit.poll_bio ||
+			    !bio_poll(dio->submit.poll_bio, 0))
 				blk_io_schedule();
 		}
 		__set_current_state(TASK_RUNNING);
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 396ef36dcd0a..d33f6e8bd313 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1429,7 +1429,7 @@ 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,
+	.iopoll		= iocb_bio_iopoll,
 	.unlocked_ioctl	= xfs_file_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= xfs_file_compat_ioctl,
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index cd145d318b17..2db3ba568bcf 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -1143,7 +1143,7 @@ static const struct file_operations zonefs_file_operations = {
 	.write_iter	= zonefs_file_write_iter,
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= iter_file_splice_write,
-	.iopoll		= iomap_dio_iopoll,
+	.iopoll		= iocb_bio_iopoll,
 };
 
 static struct kmem_cache *zonefs_inode_cachep;
diff --git a/include/linux/bio.h b/include/linux/bio.h
index feaebd2367a0..bc6ad6d71208 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -422,7 +422,7 @@ static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned short nr_iovecs)
 	return bio_alloc_bioset(gfp_mask, nr_iovecs, &fs_bio_set);
 }
 
-extern blk_qc_t submit_bio(struct bio *);
+void submit_bio(struct bio *bio);
 
 extern void bio_endio(struct bio *);
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 02a4aab0aeac..21140132a30d 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -148,9 +148,9 @@ struct blk_mq_hw_ctx {
 	/** @kobj: Kernel object for sysfs. */
 	struct kobject		kobj;
 
-	/** @poll_considered: Count times blk_poll() was called. */
+	/** @poll_considered: Count times blk_mq_poll() was called. */
 	unsigned long		poll_considered;
-	/** @poll_invoked: Count how many requests blk_poll() polled. */
+	/** @poll_invoked: Count how many requests blk_mq_poll() polled. */
 	unsigned long		poll_invoked;
 	/** @poll_success: Count how many polled requests were completed. */
 	unsigned long		poll_success;
@@ -605,16 +605,6 @@ static inline void *blk_mq_rq_to_pdu(struct request *rq)
 	for ((i) = 0; (i) < (hctx)->nr_ctx &&				\
 	     ({ ctx = (hctx)->ctxs[(i)]; 1; }); (i)++)
 
-static inline blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx,
-		struct request *rq)
-{
-	if (rq->tag != -1)
-		return rq->tag | (hctx->queue_num << BLK_QC_T_SHIFT);
-
-	return rq->internal_tag | (hctx->queue_num << BLK_QC_T_SHIFT) |
-			BLK_QC_T_INTERNAL;
-}
-
 static inline void blk_mq_cleanup_rq(struct request *rq)
 {
 	if (rq->q->mq_ops->cleanup_rq)
@@ -633,7 +623,6 @@ static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio,
 		rq->rq_disk = bio->bi_bdev->bd_disk;
 }
 
-blk_qc_t blk_mq_submit_bio(struct bio *bio);
 void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx,
 		struct lock_class_key *key);
 
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index bb53aaa36caf..6e6c2af48d74 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -212,6 +212,9 @@ static inline void bio_issue_init(struct bio_issue *issue,
 			((u64)size << BIO_ISSUE_SIZE_SHIFT));
 }
 
+typedef unsigned int blk_qc_t;
+#define BLK_QC_T_NONE		-1U
+
 /*
  * main unit of I/O for the block layer and lower layers (ie drivers and
  * stacking drivers)
@@ -231,8 +234,8 @@ struct bio {
 
 	struct bvec_iter	bi_iter;
 
+	blk_qc_t		bi_cookie;
 	bio_end_io_t		*bi_end_io;
-
 	void			*bi_private;
 #ifdef CONFIG_BLK_CGROUP
 	/*
@@ -388,7 +391,7 @@ enum req_flag_bits {
 	/* command specific flags for REQ_OP_WRITE_ZEROES: */
 	__REQ_NOUNMAP,		/* do not free blocks when zeroing */
 
-	__REQ_POLLED,		/* caller polls for completion using blk_poll */
+	__REQ_POLLED,		/* caller polls for completion using bio_poll */
 
 	/* for driver use */
 	__REQ_DRV,
@@ -501,11 +504,6 @@ static inline int op_stat_group(unsigned int op)
 	return op_is_write(op);
 }
 
-typedef unsigned int blk_qc_t;
-#define BLK_QC_T_NONE		-1U
-#define BLK_QC_T_SHIFT		16
-#define BLK_QC_T_INTERNAL	(1U << 31)
-
 struct blk_rq_stat {
 	u64 mean;
 	u64 min;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 821d721f78e7..561b04117bd4 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -38,6 +38,7 @@ struct sg_io_hdr;
 struct bsg_job;
 struct blkcg_gq;
 struct blk_flush_queue;
+struct kiocb;
 struct pr_ops;
 struct rq_qos;
 struct blk_queue_stats;
@@ -900,7 +901,7 @@ static inline void rq_flush_dcache_pages(struct request *rq)
 
 extern int blk_register_queue(struct gendisk *disk);
 extern void blk_unregister_queue(struct gendisk *disk);
-blk_qc_t submit_bio_noacct(struct bio *bio);
+void submit_bio_noacct(struct bio *bio);
 extern void blk_rq_init(struct request_queue *q, struct request *rq);
 extern void blk_put_request(struct request *);
 extern struct request *blk_get_request(struct request_queue *, unsigned int op,
@@ -950,7 +951,8 @@ blk_status_t errno_to_blk_status(int errno);
 #define BLK_POLL_ONESHOT		(1 << 0)
 /* do not sleep to wait for the expected completion time */
 #define BLK_POLL_NOSLEEP		(1 << 1)
-int blk_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags);
+int bio_poll(struct bio *bio, unsigned int flags);
+int iocb_bio_iopoll(struct kiocb *kiocb, unsigned int flags);
 
 static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
 {
@@ -1854,7 +1856,7 @@ static inline void blk_ksm_unregister(struct request_queue *q) { }
 
 
 struct block_device_operations {
-	blk_qc_t (*submit_bio) (struct bio *bio);
+	void (*submit_bio)(struct bio *bio);
 	int (*open) (struct block_device *, fmode_t);
 	void (*release) (struct gendisk *, fmode_t);
 	int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 483fb557d92f..876ec2b11a7d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -332,11 +332,7 @@ struct kiocb {
 	int			ki_flags;
 	u16			ki_hint;
 	u16			ki_ioprio; /* See linux/ioprio.h */
-	union {
-		unsigned int		ki_cookie; /* for ->iopoll */
-		struct wait_page_queue	*ki_waitq; /* for async buffered IO */
-	};
-
+	struct wait_page_queue	*ki_waitq; /* for async buffered IO */
 	randomized_struct_fields_end
 };
 
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 56e5949ccb60..ac825a498816 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -251,7 +251,7 @@ int iomap_writepages(struct address_space *mapping,
 struct iomap_dio_ops {
 	int (*end_io)(struct kiocb *iocb, ssize_t size, int error,
 		      unsigned flags);
-	blk_qc_t (*submit_io)(struct inode *inode, struct iomap *iomap,
+	void (*submit_io)(struct inode *inode, struct iomap *iomap,
 			struct bio *bio, loff_t file_offset);
 };
 
@@ -275,7 +275,6 @@ struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
 		unsigned int dio_flags);
 ssize_t iomap_dio_complete(struct iomap_dio *dio);
-int iomap_dio_iopoll(struct kiocb *kiocb, unsigned int flags);
 
 #ifdef CONFIG_SWAP
 struct file;
diff --git a/mm/page_io.c b/mm/page_io.c
index ed2eded74f3a..a68faab5b310 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -358,8 +358,6 @@ int swap_readpage(struct page *page, bool synchronous)
 	struct bio *bio;
 	int ret = 0;
 	struct swap_info_struct *sis = page_swap_info(page);
-	blk_qc_t qc;
-	struct gendisk *disk;
 	unsigned long pflags;
 
 	VM_BUG_ON_PAGE(!PageSwapCache(page) && !synchronous, page);
@@ -409,8 +407,6 @@ int swap_readpage(struct page *page, bool synchronous)
 	bio->bi_iter.bi_sector = swap_page_sector(page);
 	bio->bi_end_io = end_swap_bio_read;
 	bio_add_page(bio, page, thp_size(page), 0);
-
-	disk = bio->bi_bdev->bd_disk;
 	/*
 	 * Keep this task valid during swap readpage because the oom killer may
 	 * attempt to access it in the page fault retry time check.
@@ -422,13 +418,13 @@ int swap_readpage(struct page *page, bool synchronous)
 	}
 	count_vm_event(PSWPIN);
 	bio_get(bio);
-	qc = submit_bio(bio);
+	submit_bio(bio);
 	while (synchronous) {
 		set_current_state(TASK_UNINTERRUPTIBLE);
 		if (!READ_ONCE(bio->bi_private))
 			break;
 
-		if (!blk_poll(disk->queue, qc, 0))
+		if (!bio_poll(bio, 0))
 			blk_io_schedule();
 	}
 	__set_current_state(TASK_RUNNING);
-- 
2.30.2

[PATCH 14/16] block: don't allow writing to the poll queue attribute

[Christoph Hellwig]

The poll attribute is a historic artefact from before when we had
explicit poll queues that require driver specific configuration.
Just print a warning when writing to the attribute.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Tested-by: Mark Wunderlich <mark.wunderlich@intel.com>
---
 block/blk-sysfs.c | 23 ++++-------------------
 1 file changed, 4 insertions(+), 19 deletions(-)

diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index f89e2fc3963b..f78e73ca6091 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -428,26 +428,11 @@ static ssize_t queue_poll_show(struct request_queue *q, char *page)
 static ssize_t queue_poll_store(struct request_queue *q, const char *page,
 				size_t count)
 {
-	unsigned long poll_on;
-	ssize_t ret;
-
-	if (!q->tag_set || q->tag_set->nr_maps <= HCTX_TYPE_POLL ||
-	    !q->tag_set->map[HCTX_TYPE_POLL].nr_queues)
+	if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
 		return -EINVAL;
-
-	ret = queue_var_store(&poll_on, page, count);
-	if (ret < 0)
-		return ret;
-
-	if (poll_on) {
-		blk_queue_flag_set(QUEUE_FLAG_POLL, q);
-	} else {
-		blk_mq_freeze_queue(q);
-		blk_queue_flag_clear(QUEUE_FLAG_POLL, q);
-		blk_mq_unfreeze_queue(q);
-	}
-
-	return ret;
+	pr_info_ratelimited("writes to the poll attribute are ignored.\n");
+	pr_info_ratelimited("please use driver specific parameters instead.\n");
+	return count;
 }
 
 static ssize_t queue_io_timeout_show(struct request_queue *q, char *page)
-- 
2.30.2

[PATCH 15/16] nvme-multipath: set QUEUE_FLAG_NOWAIT

[Christoph Hellwig]

The nvme multipathing code just dispatches bios to one of the blk-mq
based paths and never blocks on its own, so set QUEUE_FLAG_NOWAIT
to support REQ_NOWAIT bios.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Mark Wunderlich <mark.wunderlich@intel.com>
---
 drivers/nvme/host/multipath.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index c1b4d627c05b..f77b774699de 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -449,6 +449,8 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 			ctrl->subsys->instance, head->instance);
 
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, head->disk->queue);
+	blk_queue_flag_set(QUEUE_FLAG_NOWAIT, head->disk->queue);
+
 	/* set to a default value of 512 until the disk is validated */
 	blk_queue_logical_block_size(head->disk->queue, 512);
 	blk_set_stacking_limits(&head->disk->queue->limits);
-- 
2.30.2

[PATCH 16/16] nvme-multipath: enable polled I/O

[Christoph Hellwig]

Set the poll queue flag to enable polling, given that the multipath
node just dispatches the bios to a lower queue.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Mark Wunderlich <mark.wunderlich@intel.com>
---
 drivers/nvme/host/multipath.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index f77b774699de..48ea649d6c24 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -450,6 +450,15 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, head->disk->queue);
 	blk_queue_flag_set(QUEUE_FLAG_NOWAIT, head->disk->queue);
+	/*
+	 * This assumes all controllers that refer to a namespace either
+	 * support poll queues or not.  That is not a strict guarantee,
+	 * but if the assumption is wrong the effect is only suboptimal
+	 * performance but not correctness problem.
+	 */
+	if (ctrl->tagset->nr_maps > HCTX_TYPE_POLL &&
+	    ctrl->tagset->map[HCTX_TYPE_POLL].nr_queues)
+		blk_queue_flag_set(QUEUE_FLAG_POLL, head->disk->queue);
 
 	/* set to a default value of 512 until the disk is validated */
 	blk_queue_logical_block_size(head->disk->queue, 512);
-- 
2.30.2

Re: switch block layer polling to a bio based model v4

[Keith Busch]

On Tue, Jun 15, 2021 at 03:10:18PM +0200, Christoph Hellwig wrote:
> Chances since v3:
>  - rebased to the latests for-5.14/block tree
>  - fix the refcount logic in __blkdev_direct_IO
>  - split up a patch to make it easier to review
>  - grab a queue reference in bio_poll
>  - better document the RCU assumptions in bio_poll

It still doesn't look like a failover will work when polling through
pvsync2. We previously discussed that here:

  https://marc.info/?l=linux-block&m=162100971816071&w=2

Re: switch block layer polling to a bio based model v4

[Christoph Hellwig]

On Tue, Jun 15, 2021 at 07:37:06AM -0700, Keith Busch wrote:
> On Tue, Jun 15, 2021 at 03:10:18PM +0200, Christoph Hellwig wrote:
> > Chances since v3:
> >  - rebased to the latests for-5.14/block tree
> >  - fix the refcount logic in __blkdev_direct_IO
> >  - split up a patch to make it easier to review
> >  - grab a queue reference in bio_poll
> >  - better document the RCU assumptions in bio_poll
> 
> It still doesn't look like a failover will work when polling through
> pvsync2. We previously discussed that here:
> 
>   https://marc.info/?l=linux-block&m=162100971816071&w=2

Yes, sorry for losing this.  I'll resend with that added after a short
delay to see if anything else needs attention.

Re: [PATCH 13/16] block: switch polling to be bio based

[Ming Lei]

On Tue, Jun 15, 2021 at 03:10:31PM +0200, Christoph Hellwig wrote:
> Replace the blk_poll interface that requires the caller to keep a queue
> and cookie from the submissions with polling based on the bio.
> 
> Polling for the bio itself leads to a few advantages:
> 
>  - the cookie construction can made entirely private in blk-mq.c
>  - the caller does not need to remember the request_queue and cookie
>    separately and thus sidesteps their lifetime issues
>  - keeping the device and the cookie inside the bio allows to trivially
>    support polling BIOs remapping by stacking drivers
>  - a lot of code to propagate the cookie back up the submission path can
>    be removed entirely.
> 

...

> +/**
> + * bio_poll - poll for BIO completions
> + * @bio: bio to poll for
> + * @flags: BLK_POLL_* flags that control the behavior
> + *
> + * Poll for completions on queue associated with the bio. Returns number of
> + * completed entries found.
> + *
> + * Note: the caller must either be the context that submitted @bio, or
> + * be in a RCU critical section to prevent freeing of @bio.
> + */
> +int bio_poll(struct bio *bio, unsigned int flags)
> +{
> +	struct request_queue *q = bio->bi_bdev->bd_disk->queue;
> +	blk_qc_t cookie = READ_ONCE(bio->bi_cookie);
> +	int ret;
> +
> +	if (cookie == BLK_QC_T_NONE ||
> +	    !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
> +		return 0;
> +
> +	if (current->plug)
> +		blk_flush_plug_list(current->plug, false);
> +
> +	if (blk_queue_enter(q, BLK_MQ_REQ_NOWAIT))
> +		return 0;
> +	if (WARN_ON_ONCE(!queue_is_mq(q)))
> +		ret = 0;	/* not yet implemented, should not happen */
> +	else
> +		ret = blk_mq_poll(q, cookie, flags);
> +	blk_queue_exit(q);
> +	return ret;
> +}
> +EXPORT_SYMBOL_GPL(bio_poll);
> +
> +/*
> + * Helper to implement file_operations.iopoll.  Requires the bio to be stored
> + * in iocb->private, and cleared before freeing the bio.
> + */
> +int iocb_bio_iopoll(struct kiocb *kiocb, unsigned int flags)
> +{
> +	struct bio *bio;
> +	int ret = 0;
> +
> +	/*
> +	 * Note: the bio cache only uses SLAB_TYPESAFE_BY_RCU, so bio can
> +	 * point to a freshly allocated bio at this point.  If that happens
> +	 * we have a few cases to consider:
> +	 *
> +	 *  1) the bio is beeing initialized and bi_bdev is NULL.  We can just
> +	 *     simply nothing in this case
> +	 *  2) the bio points to a not poll enabled device.  bio_poll will catch
> +	 *     this and return 0
> +	 *  3) the bio points to a poll capable device, including but not
> +	 *     limited to the one that the original bio pointed to.  In this
> +	 *     case we will call into the actual poll method and poll for I/O,
> +	 *     even if we don't need to, but it won't cause harm either.
> +	 *
> +	 * For cases 2) and 3) above the RCU grace period ensures that bi_bdev
> +	 * is still allocated. Because partitions hold a reference to the whole
> +	 * device bdev and thus disk, the disk is also still valid.  Grabbing
> +	 * a reference to the queue in bio_poll() ensures the hctxs and requests
> +	 * are still valid as well.
> +	 */

Not sure disk is valid, we only hold the disk when opening a bdev, but
the bdev can be closed during polling. Also disk always holds one
reference on request queue, so if disk is valid, no need to grab queue's
refcnt in bio_poll().


Thanks,
Ming

Re: [PATCH 13/16] block: switch polling to be bio based

[Christoph Hellwig]

On Wed, Jun 16, 2021 at 10:30:23AM +0800, Ming Lei wrote:
> Not sure disk is valid, we only hold the disk when opening a bdev, but
> the bdev can be closed during polling.

How?  On a block device the caller needs to hold the block device open
to read/write from it.  On a file systems the file systems needs to
be mounted, which also holds a bdev reference.

> Also disk always holds one
> reference on request queue, so if disk is valid, no need to grab queue's
> refcnt in bio_poll().

But we need to avoid going into the lowlevel blk-mq polling code to not
reference the potentially freed hctxs or tags as correctly pointed by
yourself on the previous iteration.

Re: [PATCH 13/16] block: switch polling to be bio based

[Ming Lei]

On Fri, Jun 18, 2021 at 04:01:47PM +0200, Christoph Hellwig wrote:
> On Wed, Jun 16, 2021 at 10:30:23AM +0800, Ming Lei wrote:
> > Not sure disk is valid, we only hold the disk when opening a bdev, but
> > the bdev can be closed during polling.
> 
> How?  On a block device the caller needs to hold the block device open
> to read/write from it.  On a file systems the file systems needs to
> be mounted, which also holds a bdev reference.

+       rcu_read_lock();
+       bio = READ_ONCE(kiocb->private);
+       if (bio && bio->bi_bdev)

The bio may be ended now from another polling job, then the disk is
closed & deleted, and released. Then request queue & hctxs are released.

+               ret = bio_poll(bio, flags);

But disk & request queue & hctx can still be referred in above bio_poll().

+       rcu_read_unlock();

> 
> > Also disk always holds one
> > reference on request queue, so if disk is valid, no need to grab queue's
> > refcnt in bio_poll().
> 
> But we need to avoid going into the lowlevel blk-mq polling code to not
> reference the potentially freed hctxs or tags as correctly pointed by
> yourself on the previous iteration.

If request queue isn't released, hctx won't be freed too. Tagset can be
freed, but it is supposed to not be touched after request queue is cleanup.


Thanks, 
Ming

Re: [PATCH 13/16] block: switch polling to be bio based

[Christoph Hellwig]

On Fri, Jun 18, 2021 at 10:27:20PM +0800, Ming Lei wrote:
> > How?  On a block device the caller needs to hold the block device open
> > to read/write from it.  On a file systems the file systems needs to
> > be mounted, which also holds a bdev reference.
> 
> +       rcu_read_lock();
> +       bio = READ_ONCE(kiocb->private);
> +       if (bio && bio->bi_bdev)
> 
> The bio may be ended now from another polling job, then the disk is
> closed & deleted, and released. Then request queue & hctxs are released.
> 
> +               ret = bio_poll(bio, flags);
> 
> But disk & request queue & hctx can still be referred in above bio_poll().

I don't see how this can happen.  A bio stashed into kiocb->private needs
to belong to the correct device initially.  For it to point to the "wrong"
device it needs to have been completed on the correct one, and then be
reused for a different device.  At the point it is reused that device
must obviously have been alive, and for it to be freed a RCU grace
period must have been passed.  And that grace period can't have started
earlier than when iocb_bio_iopoll was called.

Re: [PATCH 13/16] block: switch polling to be bio based

[Ming Lei]

On Mon, Jun 21, 2021 at 09:20:05AM +0200, Christoph Hellwig wrote:
> On Fri, Jun 18, 2021 at 10:27:20PM +0800, Ming Lei wrote:
> > > How?  On a block device the caller needs to hold the block device open
> > > to read/write from it.  On a file systems the file systems needs to
> > > be mounted, which also holds a bdev reference.
> > 
> > +       rcu_read_lock();
> > +       bio = READ_ONCE(kiocb->private);
> > +       if (bio && bio->bi_bdev)
> > 
> > The bio may be ended now from another polling job, then the disk is
> > closed & deleted, and released. Then request queue & hctxs are released.
> > 
> > +               ret = bio_poll(bio, flags);
> > 
> > But disk & request queue & hctx can still be referred in above bio_poll().
> 
> I don't see how this can happen.  A bio stashed into kiocb->private needs
> to belong to the correct device initially.  For it to point to the "wrong"
> device it needs to have been completed on the correct one, and then be
> reused for a different device.  At the point it is reused that device
> must obviously have been alive, and for it to be freed a RCU grace
> period must have been passed.  And that grace period can't have started
> earlier than when iocb_bio_iopoll was called.

gendisk isn't freed after a RCU grace period, so even though bio->bi_bdev
may not be freed really, but the gendisk may have been freed already.

+       rcu_read_lock();
+       bio = READ_ONCE(kiocb->private);
+       if (bio && bio->bi_bdev)

The bio may be ended now from another polling job, and it is freed
and re-allocated & freed, then bio->bi_bdev->bd_disk is freed too, which
will be observed in the following bio_poll().

+               ret = bio_poll(bio, flags);


Thanks,
Ming

Re: switch block layer polling to a bio based model v4

[Sagi Grimberg]

On 10/12/21 5:58 PM, Jens Axboe wrote:
> On 10/12/21 8:57 AM, Sagi Grimberg wrote:
>>
>>>> Hi all,
>>>>
>>>> This series clean up the block polling code a bit and changes the interface
>>>> to poll for a specific bio instead of a request_queue and cookie pair.
>>>>
>>>> Polling for the bio itself leads to a few advantages:
>>>>
>>>>     - the cookie construction can made entirely private in blk-mq.c
>>>>     - the caller does not need to remember the request_queue and cookie
>>>>       separately and thus sidesteps their lifetime issues
>>>>     - keeping the device and the cookie inside the bio allows to trivially
>>>>       support polling BIOs remapping by stacking drivers
>>>>     - a lot of code to propagate the cookie back up the submission path can
>>>>       removed entirely
>>>>
>>>> The one major caveat is that this requires RCU freeing polled BIOs to make
>>>> sure the bio that contains the polling information is still alive when
>>>> io_uring tries to poll it through the iocb. For synchronous polling all the
>>>> callers have a bio reference anyway, so this is not an issue.
>>>
>>> I ran this through the usual peak testing, and it doesn't seem to regress
>>> anything for me. We're still at around ~7.4M polled IOPS on a single CPU
>>> core:
>>>
>>> taskset -c 0,16 t/io_uring -d128 -b512 -s32 -c32 -p1 -F1 -B1 -D1 -n2 /dev/nvme1n1 /dev/nvme2n1
>>> Added file /dev/nvme1n1 (submitter 0)
>>> Added file /dev/nvme2n1 (submitter 1)
>>> polled=1, fixedbufs=1, register_files=1, buffered=0, QD=128
>>> Engine=io_uring, sq_ring=128, cq_ring=256
>>> submitter=0, tid=1199
>>> submitter=1, tid=1200
>>> IOPS=7322112, BW=3575MiB/s, IOS/call=32/31, inflight=(110 71)
>>> IOPS=7452736, BW=3639MiB/s, IOS/call=32/31, inflight=(52 80)
>>> IOPS=7419904, BW=3623MiB/s, IOS/call=32/31, inflight=(78 104)
>>> IOPS=7392576, BW=3609MiB/s, IOS/call=32/32, inflight=(75 102)
>>
>> Jens, is that with nvme_core.multipath=Y ?
> 
> No, I don't have multipath enabled. I can run that too, if you'd like.

That would be useful to learn. thanks.

Re: switch block layer polling to a bio based model v4

[Christoph Hellwig]

On Tue, Oct 12, 2021 at 05:57:43PM +0300, Sagi Grimberg wrote:
> Jens, is that with nvme_core.multipath=Y ?

That is the default.  But for most PCI device namespaces are private
by default so we won't use the multipath code anyway.  Only for
dual ported devices, and even for those that flag might need to be set
explicitly at namespace creation time.

Re: switch block layer polling to a bio based model v4

[Jens Axboe]

On 10/12/21 8:57 AM, Sagi Grimberg wrote:
> 
>>> Hi all,
>>>
>>> This series clean up the block polling code a bit and changes the interface
>>> to poll for a specific bio instead of a request_queue and cookie pair.
>>>
>>> Polling for the bio itself leads to a few advantages:
>>>
>>>    - the cookie construction can made entirely private in blk-mq.c
>>>    - the caller does not need to remember the request_queue and cookie
>>>      separately and thus sidesteps their lifetime issues
>>>    - keeping the device and the cookie inside the bio allows to trivially
>>>      support polling BIOs remapping by stacking drivers
>>>    - a lot of code to propagate the cookie back up the submission path can
>>>      removed entirely
>>>
>>> The one major caveat is that this requires RCU freeing polled BIOs to make
>>> sure the bio that contains the polling information is still alive when
>>> io_uring tries to poll it through the iocb. For synchronous polling all the
>>> callers have a bio reference anyway, so this is not an issue.
>>
>> I ran this through the usual peak testing, and it doesn't seem to regress
>> anything for me. We're still at around ~7.4M polled IOPS on a single CPU
>> core:
>>
>> taskset -c 0,16 t/io_uring -d128 -b512 -s32 -c32 -p1 -F1 -B1 -D1 -n2 /dev/nvme1n1 /dev/nvme2n1
>> Added file /dev/nvme1n1 (submitter 0)
>> Added file /dev/nvme2n1 (submitter 1)
>> polled=1, fixedbufs=1, register_files=1, buffered=0, QD=128
>> Engine=io_uring, sq_ring=128, cq_ring=256
>> submitter=0, tid=1199
>> submitter=1, tid=1200
>> IOPS=7322112, BW=3575MiB/s, IOS/call=32/31, inflight=(110 71)
>> IOPS=7452736, BW=3639MiB/s, IOS/call=32/31, inflight=(52 80)
>> IOPS=7419904, BW=3623MiB/s, IOS/call=32/31, inflight=(78 104)
>> IOPS=7392576, BW=3609MiB/s, IOS/call=32/32, inflight=(75 102)
> 
> Jens, is that with nvme_core.multipath=Y ?

No, I don't have multipath enabled. I can run that too, if you'd like.

-- 
Jens Axboe

Re: switch block layer polling to a bio based model v4

[Sagi Grimberg]

>> Hi all,
>>
>> This series clean up the block polling code a bit and changes the interface
>> to poll for a specific bio instead of a request_queue and cookie pair.
>>
>> Polling for the bio itself leads to a few advantages:
>>
>>    - the cookie construction can made entirely private in blk-mq.c
>>    - the caller does not need to remember the request_queue and cookie
>>      separately and thus sidesteps their lifetime issues
>>    - keeping the device and the cookie inside the bio allows to trivially
>>      support polling BIOs remapping by stacking drivers
>>    - a lot of code to propagate the cookie back up the submission path can
>>      removed entirely
>>
>> The one major caveat is that this requires RCU freeing polled BIOs to make
>> sure the bio that contains the polling information is still alive when
>> io_uring tries to poll it through the iocb. For synchronous polling all the
>> callers have a bio reference anyway, so this is not an issue.
> 
> I ran this through the usual peak testing, and it doesn't seem to regress
> anything for me. We're still at around ~7.4M polled IOPS on a single CPU
> core:
> 
> taskset -c 0,16 t/io_uring -d128 -b512 -s32 -c32 -p1 -F1 -B1 -D1 -n2 /dev/nvme1n1 /dev/nvme2n1
> Added file /dev/nvme1n1 (submitter 0)
> Added file /dev/nvme2n1 (submitter 1)
> polled=1, fixedbufs=1, register_files=1, buffered=0, QD=128
> Engine=io_uring, sq_ring=128, cq_ring=256
> submitter=0, tid=1199
> submitter=1, tid=1200
> IOPS=7322112, BW=3575MiB/s, IOS/call=32/31, inflight=(110 71)
> IOPS=7452736, BW=3639MiB/s, IOS/call=32/31, inflight=(52 80)
> IOPS=7419904, BW=3623MiB/s, IOS/call=32/31, inflight=(78 104)
> IOPS=7392576, BW=3609MiB/s, IOS/call=32/32, inflight=(75 102)

Jens, is that with nvme_core.multipath=Y ?

Re: switch block layer polling to a bio based model v4

[Jens Axboe]

On 10/12/21 5:12 AM, Christoph Hellwig wrote:
> Hi all,
> 
> This series clean up the block polling code a bit and changes the interface
> to poll for a specific bio instead of a request_queue and cookie pair.
> 
> Polling for the bio itself leads to a few advantages:
> 
>   - the cookie construction can made entirely private in blk-mq.c
>   - the caller does not need to remember the request_queue and cookie
>     separately and thus sidesteps their lifetime issues
>   - keeping the device and the cookie inside the bio allows to trivially
>     support polling BIOs remapping by stacking drivers
>   - a lot of code to propagate the cookie back up the submission path can
>     removed entirely
> 
> The one major caveat is that this requires RCU freeing polled BIOs to make
> sure the bio that contains the polling information is still alive when
> io_uring tries to poll it through the iocb. For synchronous polling all the
> callers have a bio reference anyway, so this is not an issue.

I ran this through the usual peak testing, and it doesn't seem to regress
anything for me. We're still at around ~7.4M polled IOPS on a single CPU
core:

taskset -c 0,16 t/io_uring -d128 -b512 -s32 -c32 -p1 -F1 -B1 -D1 -n2 /dev/nvme1n1 /dev/nvme2n1
Added file /dev/nvme1n1 (submitter 0)
Added file /dev/nvme2n1 (submitter 1)
polled=1, fixedbufs=1, register_files=1, buffered=0, QD=128
Engine=io_uring, sq_ring=128, cq_ring=256
submitter=0, tid=1199
submitter=1, tid=1200
IOPS=7322112, BW=3575MiB/s, IOS/call=32/31, inflight=(110 71)
IOPS=7452736, BW=3639MiB/s, IOS/call=32/31, inflight=(52 80)
IOPS=7419904, BW=3623MiB/s, IOS/call=32/31, inflight=(78 104)
IOPS=7392576, BW=3609MiB/s, IOS/call=32/32, inflight=(75 102)

with some of my pending changes and hacks. Using IRQ mode, we're at around 4.9M
and I don't see any particular impact of needing deferred RCU free of the bio
for that case.

-- 
Jens Axboe

switch block layer polling to a bio based model v4

[Christoph Hellwig]

Hi all,

This series clean up the block polling code a bit and changes the interface
to poll for a specific bio instead of a request_queue and cookie pair.

Polling for the bio itself leads to a few advantages:

  - the cookie construction can made entirely private in blk-mq.c
  - the caller does not need to remember the request_queue and cookie
    separately and thus sidesteps their lifetime issues
  - keeping the device and the cookie inside the bio allows to trivially
    support polling BIOs remapping by stacking drivers
  - a lot of code to propagate the cookie back up the submission path can
    removed entirely

The one major caveat is that this requires RCU freeing polled BIOs to make
sure the bio that contains the polling information is still alive when
io_uring tries to poll it through the iocb. For synchronous polling all the
callers have a bio reference anyway, so this is not an issue.

Git tree:

   git://git.infradead.org/users/hch/block.git bio-poll

Gitweb:

    http://git.infradead.org/users/hch/block.git/shortlog/refs/heads/bio-poll

Chances since v3:
 - rebased to the latests for-5.16/block tree + "two small blk-mq cleanups"
 - fix the refcount logic in __blkdev_direct_IO
 - split up a patch to make it easier to review
 - grab a queue reference in bio_poll
 - better document the RCU assumptions in bio_poll

Chances since v2:
 - remove support for writing to the poll attribute
 - better document the block_device life time assumptions in bio_poll
 - only set QUEUE_FLAG_POLL on nvme-multipath queues where it makes sense

Chances since v1:
 - use SLAB_TYPESAFE_BY_RCU to only free the pages backing the bio
   slabs bio RCU
 - split the spin argument to bio_poll to avoid sleeping under RCU from
   io_uring
 - add support for polling nvme multipath devices

Diffstat:
 arch/m68k/emu/nfblock.c             |    3 
 arch/xtensa/platforms/iss/simdisk.c |    3 
 block/bio.c                         |    4 
 block/blk-core.c                    |  129 ++++++++++++++++++++------
 block/blk-merge.c                   |    2 
 block/blk-mq-debugfs.c              |    2 
 block/blk-mq.c                      |  173 ++++++++++++++----------------------
 block/blk-mq.h                      |    6 -
 block/blk-sysfs.c                   |   23 ----
 drivers/block/brd.c                 |   12 +-
 drivers/block/drbd/drbd_int.h       |    2 
 drivers/block/drbd/drbd_req.c       |    3 
 drivers/block/n64cart.c             |   12 +-
 drivers/block/null_blk/main.c       |    3 
 drivers/block/pktcdvd.c             |    7 -
 drivers/block/ps3vram.c             |    6 -
 drivers/block/rsxx/dev.c            |    7 -
 drivers/block/zram/zram_drv.c       |   10 --
 drivers/lightnvm/pblk-init.c        |    6 -
 drivers/md/bcache/request.c         |   13 +-
 drivers/md/bcache/request.h         |    4 
 drivers/md/dm.c                     |   28 ++---
 drivers/md/md.c                     |   10 --
 drivers/nvdimm/blk.c                |    5 -
 drivers/nvdimm/btt.c                |    5 -
 drivers/nvdimm/pmem.c               |    3 
 drivers/nvme/host/core.c            |    4 
 drivers/nvme/host/multipath.c       |   17 ++-
 drivers/s390/block/dcssblk.c        |    7 -
 drivers/s390/block/xpram.c          |    5 -
 drivers/scsi/scsi_debug.c           |   10 +-
 fs/block_dev.c                      |   44 ++-------
 fs/btrfs/inode.c                    |    8 -
 fs/direct-io.c                      |   14 --
 fs/ext4/file.c                      |    2 
 fs/gfs2/file.c                      |    4 
 fs/io_uring.c                       |   14 +-
 fs/iomap/direct-io.c                |   56 ++++++-----
 fs/xfs/xfs_file.c                   |    2 
 fs/zonefs/super.c                   |    2 
 include/linux/bio.h                 |    4 
 include/linux/blk-mq.h              |   15 ---
 include/linux/blk_types.h           |   34 +------
 include/linux/blkdev.h              |   12 +-
 include/linux/bvec.h                |    2 
 include/linux/fs.h                  |    8 -
 include/linux/iomap.h               |    3 
 mm/page_io.c                        |   10 --
 48 files changed, 350 insertions(+), 408 deletions(-)