block: switch polling to be bio based

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>
Link: https://lore.kernel.org/r/20211012111226.760968-15-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>

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)

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)

block/bio.c

@@ -282,6 +282,7 @@ void bio_init(struct bio *bio, struct bio_vec *table,
 
 	atomic_set(&bio->__bi_remaining, 1);
 	atomic_set(&bio->__bi_cnt, 1);
+	bio->bi_cookie = BLK_QC_T_NONE;
 
 	bio->bi_max_vecs = max_vecs;
 	bio->bi_io_vec = table;

block/blk-core.c

@@ -915,25 +915,22 @@ end_io:
 	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 (unlikely(bio_queue_enter(bio) != 0))
-		return BLK_QC_T_NONE;
+		return;
 
 	if (!submit_bio_checks(bio) || !blk_crypto_bio_prep(&bio))
 		goto queue_exit;
-	if (disk->fops->submit_bio) {
-		ret = disk->fops->submit_bio(bio);
-		goto queue_exit;
+	if (!disk->fops->submit_bio) {
+		blk_mq_submit_bio(bio);
+		return;
 	}
-	return blk_mq_submit_bio(bio);
-
+	disk->fops->submit_bio(bio);
 queue_exit:
 	blk_queue_exit(disk->queue);
-	return ret;
 }
 
 /*
@@ -955,10 +952,9 @@ queue_exit:
  * 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);
 
@@ -975,7 +971,7 @@ 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
@@ -998,22 +994,19 @@ 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;
 
 	current->bio_list = bio_list;
 
 	do {
-		ret = __submit_bio(bio);
+		__submit_bio(bio);
 	} while ((bio = bio_list_pop(&bio_list[0])));
 
 	current->bio_list = NULL;
-	return ret;
 }
 
 /**
@@ -1025,7 +1018,7 @@ 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)
 {
 	/*
 	 * We only want one ->submit_bio to be active at a time, else stack
@@ -1033,14 +1026,12 @@ 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);
 
@@ -1057,10 +1048,10 @@ 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,
@@ -1092,19 +1083,91 @@ 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

block/blk-exec.c

@@ -65,13 +65,19 @@ EXPORT_SYMBOL_GPL(blk_execute_rq_nowait);
 
 static bool blk_rq_is_poll(struct request *rq)
 {
-	return rq->mq_hctx && rq->mq_hctx->type == HCTX_TYPE_POLL;
+	if (!rq->mq_hctx)
+		return false;
+	if (rq->mq_hctx->type != HCTX_TYPE_POLL)
+		return false;
+	if (WARN_ON_ONCE(!rq->bio))
+		return false;
+	return true;
 }
 
 static void blk_rq_poll_completion(struct request *rq, struct completion *wait)
 {
 	do {
-		blk_poll(rq->q, request_to_qc_t(rq->mq_hctx, rq), 0);
+		bio_poll(rq->bio, 0);
 		cond_resched();
 	} while (!completion_done(wait));
 }

block/blk-mq.c

@@ -65,6 +65,9 @@ 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)
 {
@@ -81,6 +84,13 @@ 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.
@@ -819,6 +829,8 @@ 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);
 
@@ -2045,19 +2057,15 @@ 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
@@ -2067,7 +2075,6 @@ 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:
@@ -2076,7 +2083,6 @@ 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;
 	}
 
@@ -2085,7 +2091,6 @@ 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;
@@ -2119,7 +2124,7 @@ 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;
@@ -2133,7 +2138,6 @@ insert:
  * 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
@@ -2141,7 +2145,7 @@ insert:
  * 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;
@@ -2150,7 +2154,7 @@ 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)
@@ -2163,11 +2167,10 @@ 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;
@@ -2247,10 +2250,8 @@ static inline unsigned short blk_plug_max_rq_count(struct blk_plug *plug)
  *
  * 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);
@@ -2259,9 +2260,7 @@ 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);
@@ -2278,8 +2277,6 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
 
 	rq_qos_throttle(q, bio);
 
-	hipri = bio->bi_opf & REQ_POLLED;
-
 	plug = blk_mq_plug(q, bio);
 	if (plug && plug->cached_rq) {
 		rq = plug->cached_rq;
@@ -2310,8 +2307,6 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
 
 	rq_qos_track(q, rq, bio);
 
-	cookie = request_to_qc_t(rq->mq_hctx, rq);
-
 	blk_mq_bio_to_request(rq, bio, nr_segs);
 
 	ret = blk_crypto_init_request(rq);
@@ -2319,7 +2314,7 @@ 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;
 	}
 
 	if (unlikely(is_flush_fua)) {
@@ -2375,7 +2370,7 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
 		if (same_queue_rq) {
 			trace_block_unplug(q, 1, true);
 			blk_mq_try_issue_directly(same_queue_rq->mq_hctx,
-						  same_queue_rq, &cookie);
+						  same_queue_rq);
 		}
 	} else if ((q->nr_hw_queues > 1 && is_sync) ||
 		   !rq->mq_hctx->dispatch_busy) {
@@ -2383,18 +2378,15 @@ 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(rq->mq_hctx, rq, &cookie);
+		blk_mq_try_issue_directly(rq->mq_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)
@@ -4084,25 +4076,8 @@ 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))
@@ -4110,7 +4085,6 @@ 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)
 {

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);

block/fops.c

@@ -61,7 +61,6 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
 	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))
@@ -102,13 +101,12 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
 	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);
@@ -141,14 +139,6 @@ 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;
@@ -162,6 +152,8 @@ 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;
@@ -200,7 +192,6 @@ 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)) &
@@ -262,9 +253,9 @@ 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) {
@@ -297,7 +288,7 @@ 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);
@@ -594,7 +585,7 @@ const struct file_operations def_blk_fops = {
 	.llseek		= blkdev_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	= blkdev_ioctl,

drivers/block/brd.c

@@ -282,7 +282,7 @@ out:
 	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;
@@ -299,16 +299,14 @@ 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,

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);
 

drivers/block/drbd/drbd_req.c

@@ -1596,7 +1596,7 @@ 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;
 
@@ -1609,7 +1609,6 @@ 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,

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 = {

drivers/block/null_blk/main.c

@@ -1422,7 +1422,7 @@ 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);
@@ -1434,7 +1434,6 @@ 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)

drivers/block/pktcdvd.c

@@ -2400,7 +2400,7 @@ 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];
@@ -2423,7 +2423,7 @@ 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)) {
@@ -2455,10 +2455,9 @@ 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)

drivers/block/ps3vram.c

@@ -578,7 +578,7 @@ out:
 	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 = {

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 @@ req_err:
 	if (st)
 		bio->bi_status = st;
 	bio_endio(bio);
-	return BLK_QC_T_NONE;
 }
 
 /*----------------- Device Setup -------------------*/

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,

drivers/md/bcache/request.c

@@ -1163,7 +1163,7 @@ 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;
@@ -1176,7 +1176,7 @@ 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)) {
@@ -1222,8 +1222,6 @@ 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,
@@ -1273,7 +1271,7 @@ 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;
@@ -1282,7 +1280,7 @@ 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));
@@ -1298,7 +1296,7 @@ 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),
@@ -1314,7 +1312,6 @@ 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,

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;
 

drivers/md/dm.c

@@ -1183,14 +1183,13 @@ 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;
 
@@ -1226,7 +1225,7 @@ 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))) {
@@ -1248,8 +1247,6 @@ 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)
@@ -1336,7 +1333,7 @@ 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;
@@ -1346,8 +1343,7 @@ 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,
@@ -1361,7 +1357,7 @@ 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);
 	}
 }
 
@@ -1405,7 +1401,7 @@ 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;
 }
@@ -1520,11 +1516,10 @@ 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);
@@ -1567,19 +1562,17 @@ 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 */
 	dm_io_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;
 
@@ -1609,10 +1602,9 @@ 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;
 }
 
 /*-----------------------------------------------------------------