Merge tag 'for-5.16/block-2021-10-29' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - mq-deadline accounting improvements (Bart)

 - blk-wbt timer fix (Andrea)

 - Untangle the block layer includes (Christoph)

 - Rework the poll support to be bio based, which will enable adding
   support for polling for bio based drivers (Christoph)

 - Block layer core support for multi-actuator drives (Damien)

 - blk-crypto improvements (Eric)

 - Batched tag allocation support (me)

 - Request completion batching support (me)

 - Plugging improvements (me)

 - Shared tag set improvements (John)

 - Concurrent queue quiesce support (Ming)

 - Cache bdev in ->private_data for block devices (Pavel)

 - bdev dio improvements (Pavel)

 - Block device invalidation and block size improvements (Xie)

 - Various cleanups, fixes, and improvements (Christoph, Jackie,
   Masahira, Tejun, Yu, Pavel, Zheng, me)

* tag 'for-5.16/block-2021-10-29' of git://git.kernel.dk/linux-block: (174 commits)
  blk-mq-debugfs: Show active requests per queue for shared tags
  block: improve readability of blk_mq_end_request_batch()
  virtio-blk: Use blk_validate_block_size() to validate block size
  loop: Use blk_validate_block_size() to validate block size
  nbd: Use blk_validate_block_size() to validate block size
  block: Add a helper to validate the block size
  block: re-flow blk_mq_rq_ctx_init()
  block: prefetch request to be initialized
  block: pass in blk_mq_tags to blk_mq_rq_ctx_init()
  block: add rq_flags to struct blk_mq_alloc_data
  block: add async version of bio_set_polled
  block: kill DIO_MULTI_BIO
  block: kill unused polling bits in __blkdev_direct_IO()
  block: avoid extra iter advance with async iocb
  block: Add independent access ranges support
  blk-mq: don't issue request directly in case that current is to be blocked
  sbitmap: silence data race warning
  blk-cgroup: synchronize blkg creation against policy deactivation
  block: refactor bio_iov_bvec_set()
  block: add single bio async direct IO helper
  ...

1 files changed, 162 insertions, 242 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index 4d8f5fe91588..fd389a16013c 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -18,6 +18,7 @@
 #include <linux/blkdev.h>
 #include <linux/blk-mq.h>
 #include <linux/blk-pm.h>
+#include <linux/blk-integrity.h>
 #include <linux/highmem.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
@@ -49,6 +50,7 @@
 #include "blk-mq.h"
 #include "blk-mq-sched.h"
 #include "blk-pm.h"
+#include "blk-throttle.h"
 
 struct dentry *blk_debugfs_root;
 
@@ -214,8 +216,7 @@ int blk_status_to_errno(blk_status_t status)
 }
 EXPORT_SYMBOL_GPL(blk_status_to_errno);
 
-static void print_req_error(struct request *req, blk_status_t status,
-		const char *caller)
+void blk_print_req_error(struct request *req, blk_status_t status)
 {
 	int idx = (__force int)status;
 
@@ -223,9 +224,9 @@ static void print_req_error(struct request *req, blk_status_t status,
 		return;
 
 	printk_ratelimited(KERN_ERR
-		"%s: %s error, dev %s, sector %llu op 0x%x:(%s) flags 0x%x "
+		"%s error, dev %s, sector %llu op 0x%x:(%s) flags 0x%x "
 		"phys_seg %u prio class %u\n",
-		caller, blk_errors[idx].name,
+		blk_errors[idx].name,
 		req->rq_disk ? req->rq_disk->disk_name : "?",
 		blk_rq_pos(req), req_op(req), blk_op_str(req_op(req)),
 		req->cmd_flags & ~REQ_OP_MASK,
@@ -233,33 +234,6 @@ static void print_req_error(struct request *req, blk_status_t status,
 		IOPRIO_PRIO_CLASS(req->ioprio));
 }
 
-static void req_bio_endio(struct request *rq, struct bio *bio,
-			  unsigned int nbytes, blk_status_t error)
-{
-	if (error)
-		bio->bi_status = error;
-
-	if (unlikely(rq->rq_flags & RQF_QUIET))
-		bio_set_flag(bio, BIO_QUIET);
-
-	bio_advance(bio, nbytes);
-
-	if (req_op(rq) == REQ_OP_ZONE_APPEND && error == BLK_STS_OK) {
-		/*
-		 * Partial zone append completions cannot be supported as the
-		 * BIO fragments may end up not being written sequentially.
-		 */
-		if (bio->bi_iter.bi_size)
-			bio->bi_status = BLK_STS_IOERR;
-		else
-			bio->bi_iter.bi_sector = rq->__sector;
-	}
-
-	/* don't actually finish bio if it's part of flush sequence */
-	if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ))
-		bio_endio(bio);
-}
-
 void blk_dump_rq_flags(struct request *rq, char *msg)
 {
 	printk(KERN_INFO "%s: dev %s: flags=%llx\n", msg,
@@ -402,7 +376,7 @@ void blk_cleanup_queue(struct request_queue *q)
 	 */
 	mutex_lock(&q->sysfs_lock);
 	if (q->elevator)
-		blk_mq_sched_free_requests(q);
+		blk_mq_sched_free_rqs(q);
 	mutex_unlock(&q->sysfs_lock);
 
 	percpu_ref_exit(&q->q_usage_counter);
@@ -415,7 +389,7 @@ EXPORT_SYMBOL(blk_cleanup_queue);
 static bool blk_try_enter_queue(struct request_queue *q, bool pm)
 {
 	rcu_read_lock();
-	if (!percpu_ref_tryget_live(&q->q_usage_counter))
+	if (!percpu_ref_tryget_live_rcu(&q->q_usage_counter))
 		goto fail;
 
 	/*
@@ -430,7 +404,7 @@ static bool blk_try_enter_queue(struct request_queue *q, bool pm)
 	return true;
 
 fail_put:
-	percpu_ref_put(&q->q_usage_counter);
+	blk_queue_exit(q);
 fail:
 	rcu_read_unlock();
 	return false;
@@ -470,10 +444,11 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
 
 static inline int bio_queue_enter(struct bio *bio)
 {
-	struct gendisk *disk = bio->bi_bdev->bd_disk;
-	struct request_queue *q = disk->queue;
+	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 
 	while (!blk_try_enter_queue(q, false)) {
+		struct gendisk *disk = bio->bi_bdev->bd_disk;
+
 		if (bio->bi_opf & REQ_NOWAIT) {
 			if (test_bit(GD_DEAD, &disk->state))
 				goto dead;
@@ -553,7 +528,7 @@ struct request_queue *blk_alloc_queue(int node_id)
 
 	q->node = node_id;
 
-	atomic_set(&q->nr_active_requests_shared_sbitmap, 0);
+	atomic_set(&q->nr_active_requests_shared_tags, 0);
 
 	timer_setup(&q->timeout, blk_rq_timed_out_timer, 0);
 	INIT_WORK(&q->timeout_work, blk_timeout_work);
@@ -586,7 +561,7 @@ struct request_queue *blk_alloc_queue(int node_id)
 
 	blk_queue_dma_alignment(q, 511);
 	blk_set_default_limits(&q->limits);
-	q->nr_requests = BLKDEV_MAX_RQ;
+	q->nr_requests = BLKDEV_DEFAULT_RQ;
 
 	return q;
 
@@ -654,8 +629,9 @@ static void handle_bad_sector(struct bio *bio, sector_t maxsector)
 {
 	char b[BDEVNAME_SIZE];
 
-	pr_info_ratelimited("attempt to access beyond end of device\n"
+	pr_info_ratelimited("%s: attempt to access beyond end of device\n"
 			    "%s: rw=%d, want=%llu, limit=%llu\n",
+			    current->comm,
 			    bio_devname(bio, b), bio->bi_opf,
 			    bio_end_sector(bio), maxsector);
 }
@@ -797,7 +773,7 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q,
 static noinline_for_stack bool submit_bio_checks(struct bio *bio)
 {
 	struct block_device *bdev = bio->bi_bdev;
-	struct request_queue *q = bdev->bd_disk->queue;
+	struct request_queue *q = bdev_get_queue(bdev);
 	blk_status_t status = BLK_STS_IOERR;
 	struct blk_plug *plug;
 
@@ -839,7 +815,7 @@ static noinline_for_stack bool submit_bio_checks(struct bio *bio)
 	}
 
 	if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
-		bio_clear_hipri(bio);
+		bio_clear_polled(bio);
 
 	switch (bio_op(bio)) {
 	case REQ_OP_DISCARD:
@@ -912,25 +888,22 @@ 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;
 }
 
 /*
@@ -952,10 +925,9 @@ 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);
 
@@ -963,7 +935,7 @@ static blk_qc_t __submit_bio_noacct(struct bio *bio)
 	current->bio_list = bio_list_on_stack;
 
 	do {
-		struct request_queue *q = bio->bi_bdev->bd_disk->queue;
+		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 		struct bio_list lower, same;
 
 		/*
@@ -972,7 +944,7 @@ 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
@@ -981,7 +953,7 @@ static blk_qc_t __submit_bio_noacct(struct bio *bio)
 		bio_list_init(&lower);
 		bio_list_init(&same);
 		while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL)
-			if (q == bio->bi_bdev->bd_disk->queue)
+			if (q == bdev_get_queue(bio->bi_bdev))
 				bio_list_add(&same, bio);
 			else
 				bio_list_add(&lower, bio);
@@ -995,22 +967,19 @@ 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;
 }
 
 /**
@@ -1022,7 +991,7 @@ 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
@@ -1030,14 +999,12 @@ 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);
 
@@ -1054,10 +1021,10 @@ 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,
@@ -1068,7 +1035,7 @@ blk_qc_t submit_bio(struct bio *bio)
 
 		if (unlikely(bio_op(bio) == REQ_OP_WRITE_SAME))
 			count = queue_logical_block_size(
-					bio->bi_bdev->bd_disk->queue) >> 9;
+					bdev_get_queue(bio->bi_bdev)) >> 9;
 		else
 			count = bio_sectors(bio);
 
@@ -1089,20 +1056,93 @@ 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, struct io_comp_batch *iob, unsigned int flags)
+{
+	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
+	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(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, iob, 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, struct io_comp_batch *iob,
+		    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, iob, 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
  * @q:  the queue
@@ -1177,8 +1217,7 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *
 	if (blk_crypto_insert_cloned_request(rq))
 		return BLK_STS_IOERR;
 
-	if (blk_queue_io_stat(q))
-		blk_account_io_start(rq);
+	blk_account_io_start(rq);
 
 	/*
 	 * Since we have a scheduler attached on the top device,
@@ -1246,41 +1285,19 @@ again:
 	}
 }
 
-static void blk_account_io_completion(struct request *req, unsigned int bytes)
+void __blk_account_io_done(struct request *req, u64 now)
 {
-	if (req->part && blk_do_io_stat(req)) {
-		const int sgrp = op_stat_group(req_op(req));
-
-		part_stat_lock();
-		part_stat_add(req->part, sectors[sgrp], bytes >> 9);
-		part_stat_unlock();
-	}
-}
+	const int sgrp = op_stat_group(req_op(req));
 
-void blk_account_io_done(struct request *req, u64 now)
-{
-	/*
-	 * Account IO completion.  flush_rq isn't accounted as a
-	 * normal IO on queueing nor completion.  Accounting the
-	 * containing request is enough.
-	 */
-	if (req->part && blk_do_io_stat(req) &&
-	    !(req->rq_flags & RQF_FLUSH_SEQ)) {
-		const int sgrp = op_stat_group(req_op(req));
-
-		part_stat_lock();
-		update_io_ticks(req->part, jiffies, true);
-		part_stat_inc(req->part, ios[sgrp]);
-		part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns);
-		part_stat_unlock();
-	}
+	part_stat_lock();
+	update_io_ticks(req->part, jiffies, true);
+	part_stat_inc(req->part, ios[sgrp]);
+	part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns);
+	part_stat_unlock();
 }
 
-void blk_account_io_start(struct request *rq)
+void __blk_account_io_start(struct request *rq)
 {
-	if (!blk_do_io_stat(rq))
-		return;
-
 	/* passthrough requests can hold bios that do not have ->bi_bdev set */
 	if (rq->bio && rq->bio->bi_bdev)
 		rq->part = rq->bio->bi_bdev;
@@ -1376,112 +1393,6 @@ void blk_steal_bios(struct bio_list *list, struct request *rq)
 }
 EXPORT_SYMBOL_GPL(blk_steal_bios);
 
-/**
- * blk_update_request - Complete multiple bytes without completing the request
- * @req:      the request being processed
- * @error:    block status code
- * @nr_bytes: number of bytes to complete for @req
- *
- * Description:
- *     Ends I/O on a number of bytes attached to @req, but doesn't complete
- *     the request structure even if @req doesn't have leftover.
- *     If @req has leftover, sets it up for the next range of segments.
- *
- *     Passing the result of blk_rq_bytes() as @nr_bytes guarantees
- *     %false return from this function.
- *
- * Note:
- *	The RQF_SPECIAL_PAYLOAD flag is ignored on purpose in this function
- *      except in the consistency check at the end of this function.
- *
- * Return:
- *     %false - this request doesn't have any more data
- *     %true  - this request has more data
- **/
-bool blk_update_request(struct request *req, blk_status_t error,
-		unsigned int nr_bytes)
-{
-	int total_bytes;
-
-	trace_block_rq_complete(req, blk_status_to_errno(error), nr_bytes);
-
-	if (!req->bio)
-		return false;
-
-#ifdef CONFIG_BLK_DEV_INTEGRITY
-	if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ &&
-	    error == BLK_STS_OK)
-		req->q->integrity.profile->complete_fn(req, nr_bytes);
-#endif
-
-	if (unlikely(error && !blk_rq_is_passthrough(req) &&
-		     !(req->rq_flags & RQF_QUIET)))
-		print_req_error(req, error, __func__);
-
-	blk_account_io_completion(req, nr_bytes);
-
-	total_bytes = 0;
-	while (req->bio) {
-		struct bio *bio = req->bio;
-		unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes);
-
-		if (bio_bytes == bio->bi_iter.bi_size)
-			req->bio = bio->bi_next;
-
-		/* Completion has already been traced */
-		bio_clear_flag(bio, BIO_TRACE_COMPLETION);
-		req_bio_endio(req, bio, bio_bytes, error);
-
-		total_bytes += bio_bytes;
-		nr_bytes -= bio_bytes;
-
-		if (!nr_bytes)
-			break;
-	}
-
-	/*
-	 * completely done
-	 */
-	if (!req->bio) {
-		/*
-		 * Reset counters so that the request stacking driver
-		 * can find how many bytes remain in the request
-		 * later.
-		 */
-		req->__data_len = 0;
-		return false;
-	}
-
-	req->__data_len -= total_bytes;
-
-	/* update sector only for requests with clear definition of sector */
-	if (!blk_rq_is_passthrough(req))
-		req->__sector += total_bytes >> 9;
-
-	/* mixed attributes always follow the first bio */
-	if (req->rq_flags & RQF_MIXED_MERGE) {
-		req->cmd_flags &= ~REQ_FAILFAST_MASK;
-		req->cmd_flags |= req->bio->bi_opf & REQ_FAILFAST_MASK;
-	}
-
-	if (!(req->rq_flags & RQF_SPECIAL_PAYLOAD)) {
-		/*
-		 * If total number of sectors is less than the first segment
-		 * size, something has gone terribly wrong.
-		 */
-		if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) {
-			blk_dump_rq_flags(req, "request botched");
-			req->__data_len = blk_rq_cur_bytes(req);
-		}
-
-		/* recalculate the number of segments */
-		req->nr_phys_segments = blk_recalc_rq_segments(req);
-	}
-
-	return true;
-}
-EXPORT_SYMBOL_GPL(blk_update_request);
-
 #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
 /**
  * rq_flush_dcache_pages - Helper function to flush all pages in a request
@@ -1629,6 +1540,32 @@ int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork,
 }
 EXPORT_SYMBOL(kblockd_mod_delayed_work_on);
 
+void blk_start_plug_nr_ios(struct blk_plug *plug, unsigned short nr_ios)
+{
+	struct task_struct *tsk = current;
+
+	/*
+	 * If this is a nested plug, don't actually assign it.
+	 */
+	if (tsk->plug)
+		return;
+
+	plug->mq_list = NULL;
+	plug->cached_rq = NULL;
+	plug->nr_ios = min_t(unsigned short, nr_ios, BLK_MAX_REQUEST_COUNT);
+	plug->rq_count = 0;
+	plug->multiple_queues = false;
+	plug->has_elevator = false;
+	plug->nowait = false;
+	INIT_LIST_HEAD(&plug->cb_list);
+
+	/*
+	 * Store ordering should not be needed here, since a potential
+	 * preempt will imply a full memory barrier
+	 */
+	tsk->plug = plug;
+}
+
 /**
  * blk_start_plug - initialize blk_plug and track it inside the task_struct
  * @plug:	The &struct blk_plug that needs to be initialized
@@ -1654,25 +1591,7 @@ EXPORT_SYMBOL(kblockd_mod_delayed_work_on);
  */
 void blk_start_plug(struct blk_plug *plug)
 {
-	struct task_struct *tsk = current;
-
-	/*
-	 * If this is a nested plug, don't actually assign it.
-	 */
-	if (tsk->plug)
-		return;
-
-	INIT_LIST_HEAD(&plug->mq_list);
-	INIT_LIST_HEAD(&plug->cb_list);
-	plug->rq_count = 0;
-	plug->multiple_queues = false;
-	plug->nowait = false;
-
-	/*
-	 * Store ordering should not be needed here, since a potential
-	 * preempt will imply a full memory barrier
-	 */
-	tsk->plug = plug;
+	blk_start_plug_nr_ios(plug, 1);
 }
 EXPORT_SYMBOL(blk_start_plug);
 
@@ -1718,12 +1637,14 @@ struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, void *data,
 }
 EXPORT_SYMBOL(blk_check_plugged);
 
-void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
+void blk_flush_plug(struct blk_plug *plug, bool from_schedule)
 {
-	flush_plug_callbacks(plug, from_schedule);
-
-	if (!list_empty(&plug->mq_list))
+	if (!list_empty(&plug->cb_list))
+		flush_plug_callbacks(plug, from_schedule);
+	if (!rq_list_empty(plug->mq_list))
 		blk_mq_flush_plug_list(plug, from_schedule);
+	if (unlikely(!from_schedule && plug->cached_rq))
+		blk_mq_free_plug_rqs(plug);
 }
 
 /**
@@ -1738,11 +1659,10 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
  */
 void blk_finish_plug(struct blk_plug *plug)
 {
-	if (plug != current->plug)
-		return;
-	blk_flush_plug_list(plug, false);
-
-	current->plug = NULL;
+	if (plug == current->plug) {
+		blk_flush_plug(plug, false);
+		current->plug = NULL;
+	}
 }
 EXPORT_SYMBOL(blk_finish_plug);