Merge tag 'for-6.4/block-2023-04-21' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - drbd patches, bringing us closer to unifying the out-of-tree version
   and the in tree one (Andreas, Christoph)

 - support for auto-quiesce for the s390 dasd driver (Stefan)

 - MD pull request via Song:
      - md/bitmap: Optimal last page size (Jon Derrick)
      - Various raid10 fixes (Yu Kuai, Li Nan)
      - md: add error_handlers for raid0 and linear (Mariusz Tkaczyk)

 - NVMe pull request via Christoph:
      - Drop redundant pci_enable_pcie_error_reporting (Bjorn Helgaas)
      - Validate nvmet module parameters (Chaitanya Kulkarni)
      - Fence TCP socket on receive error (Chris Leech)
      - Fix async event trace event (Keith Busch)
      - Minor cleanups (Chaitanya Kulkarni, zhenwei pi)
      - Fix and cleanup nvmet Identify handling (Damien Le Moal,
        Christoph Hellwig)
      - Fix double blk_mq_complete_request race in the timeout handler
        (Lei Yin)
      - Fix irq locking in nvme-fcloop (Ming Lei)
      - Remove queue mapping helper for rdma devices (Sagi Grimberg)

 - use structured request attribute checks for nbd (Jakub)

 - fix blk-crypto race conditions between keyslot management (Eric)

 - add sed-opal support for reading read locking range attributes
   (Ondrej)

 - make fault injection configurable for null_blk (Akinobu)

 - clean up the request insertion API (Christoph)

 - clean up the queue running API (Christoph)

 - blkg config helper cleanups (Tejun)

 - lazy init support for blk-iolatency (Tejun)

 - various fixes and tweaks to ublk (Ming)

 - remove hybrid polling. It hasn't really been useful since we got
   async polled IO support, and these days we don't support sync polled
   IO at all (Keith)

 - misc fixes, cleanups, improvements (Zhong, Ondrej, Colin, Chengming,
   Chaitanya, me)

* tag 'for-6.4/block-2023-04-21' of git://git.kernel.dk/linux: (118 commits)
  nbd: fix incomplete validation of ioctl arg
  ublk: don't return 0 in case of any failure
  sed-opal: geometry feature reporting command
  null_blk: Always check queue mode setting from configfs
  block: ublk: switch to ioctl command encoding
  blk-mq: fix the blk_mq_add_to_requeue_list call in blk_kick_flush
  block, bfq: Fix division by zero error on zero wsum
  fault-inject: fix build error when FAULT_INJECTION_CONFIGFS=y and CONFIGFS_FS=m
  block: store bdev->bd_disk->fops->submit_bio state in bdev
  block: re-arrange the struct block_device fields for better layout
  md/raid5: remove unused working_disks variable
  md/raid10: don't call bio_start_io_acct twice for bio which experienced read error
  md/raid10: fix memleak of md thread
  md/raid10: fix memleak for 'conf->bio_split'
  md/raid10: fix leak of 'r10bio->remaining' for recovery
  md/raid10: don't BUG_ON() in raise_barrier()
  md: fix soft lockup in status_resync
  md: add error_handlers for raid0 and linear
  md: Use optimal I/O size for last bitmap page
  md: Fix types in sb writer
  ...

1 files changed, 256 insertions, 409 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 2831f78f86a0..f6dad0886a2f 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -32,12 +32,10 @@
 
 #include <trace/events/block.h>
 
-#include <linux/blk-mq.h>
 #include <linux/t10-pi.h>
 #include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-debugfs.h"
-#include "blk-mq-tag.h"
 #include "blk-pm.h"
 #include "blk-stat.h"
 #include "blk-mq-sched.h"
@@ -46,51 +44,19 @@
 
 static DEFINE_PER_CPU(struct llist_head, blk_cpu_done);
 
-static void blk_mq_poll_stats_start(struct request_queue *q);
-static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
-
-static int blk_mq_poll_stats_bkt(const struct request *rq)
-{
-	int ddir, sectors, bucket;
-
-	ddir = rq_data_dir(rq);
-	sectors = blk_rq_stats_sectors(rq);
-
-	bucket = ddir + 2 * ilog2(sectors);
-
-	if (bucket < 0)
-		return -1;
-	else if (bucket >= BLK_MQ_POLL_STATS_BKTS)
-		return ddir + BLK_MQ_POLL_STATS_BKTS - 2;
-
-	return bucket;
-}
-
-#define BLK_QC_T_SHIFT		16
-#define BLK_QC_T_INTERNAL	(1U << 31)
+static void blk_mq_insert_request(struct request *rq, blk_insert_t flags);
+static void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
+		struct list_head *list);
 
 static inline struct blk_mq_hw_ctx *blk_qc_to_hctx(struct request_queue *q,
 		blk_qc_t qc)
 {
-	return xa_load(&q->hctx_table,
-			(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)
-{
-	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);
+	return xa_load(&q->hctx_table, qc);
 }
 
 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));
+	return rq->mq_hctx->queue_num;
 }
 
 /*
@@ -840,6 +806,12 @@ static void blk_complete_request(struct request *req)
 		req->q->integrity.profile->complete_fn(req, total_bytes);
 #endif
 
+	/*
+	 * Upper layers may call blk_crypto_evict_key() anytime after the last
+	 * bio_endio().  Therefore, the keyslot must be released before that.
+	 */
+	blk_crypto_rq_put_keyslot(req);
+
 	blk_account_io_completion(req, total_bytes);
 
 	do {
@@ -905,6 +877,13 @@ bool blk_update_request(struct request *req, blk_status_t error,
 		req->q->integrity.profile->complete_fn(req, nr_bytes);
 #endif
 
+	/*
+	 * Upper layers may call blk_crypto_evict_key() anytime after the last
+	 * bio_endio().  Therefore, the keyslot must be released before that.
+	 */
+	if (blk_crypto_rq_has_keyslot(req) && nr_bytes >= blk_rq_bytes(req))
+		__blk_crypto_rq_put_keyslot(req);
+
 	if (unlikely(error && !blk_rq_is_passthrough(req) &&
 		     !(req->rq_flags & RQF_QUIET)) &&
 		     !test_bit(GD_DEAD, &req->q->disk->state)) {
@@ -976,17 +955,6 @@ bool blk_update_request(struct request *req, blk_status_t error,
 }
 EXPORT_SYMBOL_GPL(blk_update_request);
 
-static void __blk_account_io_done(struct request *req, u64 now)
-{
-	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();
-}
-
 static inline void blk_account_io_done(struct request *req, u64 now)
 {
 	/*
@@ -995,40 +963,41 @@ static inline void blk_account_io_done(struct request *req, u64 now)
 	 * containing request is enough.
 	 */
 	if (blk_do_io_stat(req) && req->part &&
-	    !(req->rq_flags & RQF_FLUSH_SEQ))
-		__blk_account_io_done(req, now);
-}
-
-static void __blk_account_io_start(struct request *rq)
-{
-	/*
-	 * All non-passthrough requests are created from a bio with one
-	 * exception: when a flush command that is part of a flush sequence
-	 * generated by the state machine in blk-flush.c is cloned onto the
-	 * lower device by dm-multipath we can get here without a bio.
-	 */
-	if (rq->bio)
-		rq->part = rq->bio->bi_bdev;
-	else
-		rq->part = rq->q->disk->part0;
+	    !(req->rq_flags & RQF_FLUSH_SEQ)) {
+		const int sgrp = op_stat_group(req_op(req));
 
-	part_stat_lock();
-	update_io_ticks(rq->part, jiffies, false);
-	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();
+	}
 }
 
 static inline void blk_account_io_start(struct request *req)
 {
-	if (blk_do_io_stat(req))
-		__blk_account_io_start(req);
+	if (blk_do_io_stat(req)) {
+		/*
+		 * All non-passthrough requests are created from a bio with one
+		 * exception: when a flush command that is part of a flush sequence
+		 * generated by the state machine in blk-flush.c is cloned onto the
+		 * lower device by dm-multipath we can get here without a bio.
+		 */
+		if (req->bio)
+			req->part = req->bio->bi_bdev;
+		else
+			req->part = req->q->disk->part0;
+
+		part_stat_lock();
+		update_io_ticks(req->part, jiffies, false);
+		part_stat_unlock();
+	}
 }
 
 static inline void __blk_mq_end_request_acct(struct request *rq, u64 now)
 {
-	if (rq->rq_flags & RQF_STATS) {
-		blk_mq_poll_stats_start(rq->q);
+	if (rq->rq_flags & RQF_STATS)
 		blk_stat_add(rq, now);
-	}
 
 	blk_mq_sched_completed_request(rq, now);
 	blk_account_io_done(rq, now);
@@ -1322,6 +1291,8 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
  */
 void blk_execute_rq_nowait(struct request *rq, bool at_head)
 {
+	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
+
 	WARN_ON(irqs_disabled());
 	WARN_ON(!blk_rq_is_passthrough(rq));
 
@@ -1332,10 +1303,13 @@ void blk_execute_rq_nowait(struct request *rq, bool at_head)
 	 * device, directly accessing the plug instead of using blk_mq_plug()
 	 * should not have any consequences.
 	 */
-	if (current->plug)
+	if (current->plug && !at_head) {
 		blk_add_rq_to_plug(current->plug, rq);
-	else
-		blk_mq_sched_insert_request(rq, at_head, true, false);
+		return;
+	}
+
+	blk_mq_insert_request(rq, at_head ? BLK_MQ_INSERT_AT_HEAD : 0);
+	blk_mq_run_hw_queue(hctx, false);
 }
 EXPORT_SYMBOL_GPL(blk_execute_rq_nowait);
 
@@ -1383,6 +1357,7 @@ static void blk_rq_poll_completion(struct request *rq, struct completion *wait)
  */
 blk_status_t blk_execute_rq(struct request *rq, bool at_head)
 {
+	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
 	struct blk_rq_wait wait = {
 		.done = COMPLETION_INITIALIZER_ONSTACK(wait.done),
 	};
@@ -1394,7 +1369,8 @@ blk_status_t blk_execute_rq(struct request *rq, bool at_head)
 	rq->end_io = blk_end_sync_rq;
 
 	blk_account_io_start(rq);
-	blk_mq_sched_insert_request(rq, at_head, true, false);
+	blk_mq_insert_request(rq, at_head ? BLK_MQ_INSERT_AT_HEAD : 0);
+	blk_mq_run_hw_queue(hctx, false);
 
 	if (blk_rq_is_poll(rq)) {
 		blk_rq_poll_completion(rq, &wait.done);
@@ -1434,12 +1410,17 @@ static void __blk_mq_requeue_request(struct request *rq)
 
 void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list)
 {
+	struct request_queue *q = rq->q;
+
 	__blk_mq_requeue_request(rq);
 
 	/* this request will be re-inserted to io scheduler queue */
 	blk_mq_sched_requeue_request(rq);
 
-	blk_mq_add_to_requeue_list(rq, true, kick_requeue_list);
+	blk_mq_add_to_requeue_list(rq, BLK_MQ_INSERT_AT_HEAD);
+
+	if (kick_requeue_list)
+		blk_mq_kick_requeue_list(q);
 }
 EXPORT_SYMBOL(blk_mq_requeue_request);
 
@@ -1455,33 +1436,33 @@ static void blk_mq_requeue_work(struct work_struct *work)
 	spin_unlock_irq(&q->requeue_lock);
 
 	list_for_each_entry_safe(rq, next, &rq_list, queuelist) {
-		if (!(rq->rq_flags & (RQF_SOFTBARRIER | RQF_DONTPREP)))
-			continue;
-
-		rq->rq_flags &= ~RQF_SOFTBARRIER;
-		list_del_init(&rq->queuelist);
 		/*
-		 * If RQF_DONTPREP, rq has contained some driver specific
-		 * data, so insert it to hctx dispatch list to avoid any
-		 * merge.
+		 * If RQF_DONTPREP ist set, the request has been started by the
+		 * driver already and might have driver-specific data allocated
+		 * already.  Insert it into the hctx dispatch list to avoid
+		 * block layer merges for the request.
 		 */
-		if (rq->rq_flags & RQF_DONTPREP)
-			blk_mq_request_bypass_insert(rq, false, false);
-		else
-			blk_mq_sched_insert_request(rq, true, false, false);
+		if (rq->rq_flags & RQF_DONTPREP) {
+			rq->rq_flags &= ~RQF_SOFTBARRIER;
+			list_del_init(&rq->queuelist);
+			blk_mq_request_bypass_insert(rq, 0);
+		} else if (rq->rq_flags & RQF_SOFTBARRIER) {
+			rq->rq_flags &= ~RQF_SOFTBARRIER;
+			list_del_init(&rq->queuelist);
+			blk_mq_insert_request(rq, BLK_MQ_INSERT_AT_HEAD);
+		}
 	}
 
 	while (!list_empty(&rq_list)) {
 		rq = list_entry(rq_list.next, struct request, queuelist);
 		list_del_init(&rq->queuelist);
-		blk_mq_sched_insert_request(rq, false, false, false);
+		blk_mq_insert_request(rq, 0);
 	}
 
 	blk_mq_run_hw_queues(q, false);
 }
 
-void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
-				bool kick_requeue_list)
+void blk_mq_add_to_requeue_list(struct request *rq, blk_insert_t insert_flags)
 {
 	struct request_queue *q = rq->q;
 	unsigned long flags;
@@ -1493,16 +1474,13 @@ void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
 	BUG_ON(rq->rq_flags & RQF_SOFTBARRIER);
 
 	spin_lock_irqsave(&q->requeue_lock, flags);
-	if (at_head) {
+	if (insert_flags & BLK_MQ_INSERT_AT_HEAD) {
 		rq->rq_flags |= RQF_SOFTBARRIER;
 		list_add(&rq->queuelist, &q->requeue_list);
 	} else {
 		list_add_tail(&rq->queuelist, &q->requeue_list);
 	}
 	spin_unlock_irqrestore(&q->requeue_lock, flags);
-
-	if (kick_requeue_list)
-		blk_mq_kick_requeue_list(q);
 }
 
 void blk_mq_kick_requeue_list(struct request_queue *q)
@@ -2158,24 +2136,6 @@ out:
 	return true;
 }
 
-/**
- * __blk_mq_run_hw_queue - Run a hardware queue.
- * @hctx: Pointer to the hardware queue to run.
- *
- * Send pending requests to the hardware.
- */
-static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
-{
-	/*
-	 * We can't run the queue inline with ints disabled. Ensure that
-	 * we catch bad users of this early.
-	 */
-	WARN_ON_ONCE(in_interrupt());
-
-	blk_mq_run_dispatch_ops(hctx->queue,
-			blk_mq_sched_dispatch_requests(hctx));
-}
-
 static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx)
 {
 	int cpu = cpumask_first_and(hctx->cpumask, cpu_online_mask);
@@ -2232,42 +2192,19 @@ select_cpu:
 }
 
 /**
- * __blk_mq_delay_run_hw_queue - Run (or schedule to run) a hardware queue.
+ * blk_mq_delay_run_hw_queue - Run a hardware queue asynchronously.
  * @hctx: Pointer to the hardware queue to run.
- * @async: If we want to run the queue asynchronously.
  * @msecs: Milliseconds of delay to wait before running the queue.
  *
- * If !@async, try to run the queue now. Else, run the queue asynchronously and
- * with a delay of @msecs.
+ * Run a hardware queue asynchronously with a delay of @msecs.
  */
-static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
-					unsigned long msecs)
+void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
 {
 	if (unlikely(blk_mq_hctx_stopped(hctx)))
 		return;
-
-	if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) {
-		if (cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)) {
-			__blk_mq_run_hw_queue(hctx);
-			return;
-		}
-	}
-
 	kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work,
 				    msecs_to_jiffies(msecs));
 }
-
-/**
- * blk_mq_delay_run_hw_queue - Run a hardware queue asynchronously.
- * @hctx: Pointer to the hardware queue to run.
- * @msecs: Milliseconds of delay to wait before running the queue.
- *
- * Run a hardware queue asynchronously with a delay of @msecs.
- */
-void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
-{
-	__blk_mq_delay_run_hw_queue(hctx, true, msecs);
-}
 EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
 
 /**
@@ -2284,6 +2221,11 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 	bool need_run;
 
 	/*
+	 * We can't run the queue inline with interrupts disabled.
+	 */
+	WARN_ON_ONCE(!async && in_interrupt());
+
+	/*
 	 * When queue is quiesced, we may be switching io scheduler, or
 	 * updating nr_hw_queues, or other things, and we can't run queue
 	 * any more, even __blk_mq_hctx_has_pending() can't be called safely.
@@ -2295,8 +2237,17 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 		need_run = !blk_queue_quiesced(hctx->queue) &&
 		blk_mq_hctx_has_pending(hctx));
 
-	if (need_run)
-		__blk_mq_delay_run_hw_queue(hctx, async, 0);
+	if (!need_run)
+		return;
+
+	if (async || (hctx->flags & BLK_MQ_F_BLOCKING) ||
+	    !cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)) {
+		blk_mq_delay_run_hw_queue(hctx, 0);
+		return;
+	}
+
+	blk_mq_run_dispatch_ops(hctx->queue,
+				blk_mq_sched_dispatch_requests(hctx));
 }
 EXPORT_SYMBOL(blk_mq_run_hw_queue);
 
@@ -2461,80 +2412,52 @@ EXPORT_SYMBOL(blk_mq_start_stopped_hw_queues);
 
 static void blk_mq_run_work_fn(struct work_struct *work)
 {
-	struct blk_mq_hw_ctx *hctx;
-
-	hctx = container_of(work, struct blk_mq_hw_ctx, run_work.work);
-
-	/*
-	 * If we are stopped, don't run the queue.
-	 */
-	if (blk_mq_hctx_stopped(hctx))
-		return;
-
-	__blk_mq_run_hw_queue(hctx);
-}
-
-static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx,
-					    struct request *rq,
-					    bool at_head)
-{
-	struct blk_mq_ctx *ctx = rq->mq_ctx;
-	enum hctx_type type = hctx->type;
-
-	lockdep_assert_held(&ctx->lock);
-
-	trace_block_rq_insert(rq);
-
-	if (at_head)
-		list_add(&rq->queuelist, &ctx->rq_lists[type]);
-	else
-		list_add_tail(&rq->queuelist, &ctx->rq_lists[type]);
-}
-
-void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
-			     bool at_head)
-{
-	struct blk_mq_ctx *ctx = rq->mq_ctx;
-
-	lockdep_assert_held(&ctx->lock);
+	struct blk_mq_hw_ctx *hctx =
+		container_of(work, struct blk_mq_hw_ctx, run_work.work);
 
-	__blk_mq_insert_req_list(hctx, rq, at_head);
-	blk_mq_hctx_mark_pending(hctx, ctx);
+	blk_mq_run_dispatch_ops(hctx->queue,
+				blk_mq_sched_dispatch_requests(hctx));
 }
 
 /**
  * blk_mq_request_bypass_insert - Insert a request at dispatch list.
  * @rq: Pointer to request to be inserted.
- * @at_head: true if the request should be inserted at the head of the list.
- * @run_queue: If we should run the hardware queue after inserting the request.
+ * @flags: BLK_MQ_INSERT_*
  *
  * Should only be used carefully, when the caller knows we want to
  * bypass a potential IO scheduler on the target device.
  */
-void blk_mq_request_bypass_insert(struct request *rq, bool at_head,
-				  bool run_queue)
+void blk_mq_request_bypass_insert(struct request *rq, blk_insert_t flags)
 {
 	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
 
 	spin_lock(&hctx->lock);
-	if (at_head)
+	if (flags & BLK_MQ_INSERT_AT_HEAD)
 		list_add(&rq->queuelist, &hctx->dispatch);
 	else
 		list_add_tail(&rq->queuelist, &hctx->dispatch);
 	spin_unlock(&hctx->lock);
-
-	if (run_queue)
-		blk_mq_run_hw_queue(hctx, false);
 }
 
-void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
-			    struct list_head *list)
-
+static void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx,
+		struct blk_mq_ctx *ctx, struct list_head *list,
+		bool run_queue_async)
 {
 	struct request *rq;
 	enum hctx_type type = hctx->type;
 
 	/*
+	 * Try to issue requests directly if the hw queue isn't busy to save an
+	 * extra enqueue & dequeue to the sw queue.
+	 */
+	if (!hctx->dispatch_busy && !run_queue_async) {
+		blk_mq_run_dispatch_ops(hctx->queue,
+			blk_mq_try_issue_list_directly(hctx, list));
+		if (list_empty(list))
+			goto out;
+	}
+
+	/*
 	 * preemption doesn't flush plug list, so it's possible ctx->cpu is
 	 * offline now
 	 */
@@ -2547,6 +2470,70 @@ void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 	list_splice_tail_init(list, &ctx->rq_lists[type]);
 	blk_mq_hctx_mark_pending(hctx, ctx);
 	spin_unlock(&ctx->lock);
+out:
+	blk_mq_run_hw_queue(hctx, run_queue_async);
+}
+
+static void blk_mq_insert_request(struct request *rq, blk_insert_t flags)
+{
+	struct request_queue *q = rq->q;
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
+
+	if (blk_rq_is_passthrough(rq)) {
+		/*
+		 * Passthrough request have to be added to hctx->dispatch
+		 * directly.  The device may be in a situation where it can't
+		 * handle FS request, and always returns BLK_STS_RESOURCE for
+		 * them, which gets them added to hctx->dispatch.
+		 *
+		 * If a passthrough request is required to unblock the queues,
+		 * and it is added to the scheduler queue, there is no chance to
+		 * dispatch it given we prioritize requests in hctx->dispatch.
+		 */
+		blk_mq_request_bypass_insert(rq, flags);
+	} else if (rq->rq_flags & RQF_FLUSH_SEQ) {
+		/*
+		 * Firstly normal IO request is inserted to scheduler queue or
+		 * sw queue, meantime we add flush request to dispatch queue(
+		 * hctx->dispatch) directly and there is at most one in-flight
+		 * flush request for each hw queue, so it doesn't matter to add
+		 * flush request to tail or front of the dispatch queue.
+		 *
+		 * Secondly in case of NCQ, flush request belongs to non-NCQ
+		 * command, and queueing it will fail when there is any
+		 * in-flight normal IO request(NCQ command). When adding flush
+		 * rq to the front of hctx->dispatch, it is easier to introduce
+		 * extra time to flush rq's latency because of S_SCHED_RESTART
+		 * compared with adding to the tail of dispatch queue, then
+		 * chance of flush merge is increased, and less flush requests
+		 * will be issued to controller. It is observed that ~10% time
+		 * is saved in blktests block/004 on disk attached to AHCI/NCQ
+		 * drive when adding flush rq to the front of hctx->dispatch.
+		 *
+		 * Simply queue flush rq to the front of hctx->dispatch so that
+		 * intensive flush workloads can benefit in case of NCQ HW.
+		 */
+		blk_mq_request_bypass_insert(rq, BLK_MQ_INSERT_AT_HEAD);
+	} else if (q->elevator) {
+		LIST_HEAD(list);
+
+		WARN_ON_ONCE(rq->tag != BLK_MQ_NO_TAG);
+
+		list_add(&rq->queuelist, &list);
+		q->elevator->type->ops.insert_requests(hctx, &list, flags);
+	} else {
+		trace_block_rq_insert(rq);
+
+		spin_lock(&ctx->lock);
+		if (flags & BLK_MQ_INSERT_AT_HEAD)
+			list_add(&rq->queuelist, &ctx->rq_lists[hctx->type]);
+		else
+			list_add_tail(&rq->queuelist,
+				      &ctx->rq_lists[hctx->type]);
+		blk_mq_hctx_mark_pending(hctx, ctx);
+		spin_unlock(&ctx->lock);
+	}
 }
 
 static void blk_mq_bio_to_request(struct request *rq, struct bio *bio,
@@ -2600,49 +2587,19 @@ static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
 	return ret;
 }
 
-static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
-						struct request *rq,
-						bool bypass_insert, bool last)
+static bool blk_mq_get_budget_and_tag(struct request *rq)
 {
-	struct request_queue *q = rq->q;
-	bool run_queue = true;
 	int budget_token;
 
-	/*
-	 * RCU or SRCU read lock is needed before checking quiesced flag.
-	 *
-	 * When queue is stopped or quiesced, ignore 'bypass_insert' from
-	 * blk_mq_request_issue_directly(), and return BLK_STS_OK to caller,
-	 * and avoid driver to try to dispatch again.
-	 */
-	if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)) {
-		run_queue = false;
-		bypass_insert = false;
-		goto insert;
-	}
-
-	if ((rq->rq_flags & RQF_ELV) && !bypass_insert)
-		goto insert;
-
-	budget_token = blk_mq_get_dispatch_budget(q);
+	budget_token = blk_mq_get_dispatch_budget(rq->q);
 	if (budget_token < 0)
-		goto insert;
-
+		return false;
 	blk_mq_set_rq_budget_token(rq, budget_token);
-
 	if (!blk_mq_get_driver_tag(rq)) {
-		blk_mq_put_dispatch_budget(q, budget_token);
-		goto insert;
+		blk_mq_put_dispatch_budget(rq->q, budget_token);
+		return false;
 	}
-
-	return __blk_mq_issue_directly(hctx, rq, last);
-insert:
-	if (bypass_insert)
-		return BLK_STS_RESOURCE;
-
-	blk_mq_sched_insert_request(rq, false, run_queue, false);
-
-	return BLK_STS_OK;
+	return true;
 }
 
 /**
@@ -2658,18 +2615,46 @@ insert:
 static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 		struct request *rq)
 {
-	blk_status_t ret =
-		__blk_mq_try_issue_directly(hctx, rq, false, true);
+	blk_status_t ret;
+
+	if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(rq->q)) {
+		blk_mq_insert_request(rq, 0);
+		return;
+	}
+
+	if ((rq->rq_flags & RQF_ELV) || !blk_mq_get_budget_and_tag(rq)) {
+		blk_mq_insert_request(rq, 0);
+		blk_mq_run_hw_queue(hctx, false);
+		return;
+	}
 
-	if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE)
-		blk_mq_request_bypass_insert(rq, false, true);
-	else if (ret != BLK_STS_OK)
+	ret = __blk_mq_issue_directly(hctx, rq, true);
+	switch (ret) {
+	case BLK_STS_OK:
+		break;
+	case BLK_STS_RESOURCE:
+	case BLK_STS_DEV_RESOURCE:
+		blk_mq_request_bypass_insert(rq, 0);
+		blk_mq_run_hw_queue(hctx, false);
+		break;
+	default:
 		blk_mq_end_request(rq, ret);
+		break;
+	}
 }
 
 static blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last)
 {
-	return __blk_mq_try_issue_directly(rq->mq_hctx, rq, true, last);
+	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
+
+	if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(rq->q)) {
+		blk_mq_insert_request(rq, 0);
+		return BLK_STS_OK;
+	}
+
+	if (!blk_mq_get_budget_and_tag(rq))
+		return BLK_STS_RESOURCE;
+	return __blk_mq_issue_directly(hctx, rq, last);
 }
 
 static void blk_mq_plug_issue_direct(struct blk_plug *plug)
@@ -2697,7 +2682,8 @@ static void blk_mq_plug_issue_direct(struct blk_plug *plug)
 			break;
 		case BLK_STS_RESOURCE:
 		case BLK_STS_DEV_RESOURCE:
-			blk_mq_request_bypass_insert(rq, false, true);
+			blk_mq_request_bypass_insert(rq, 0);
+			blk_mq_run_hw_queue(hctx, false);
 			goto out;
 		default:
 			blk_mq_end_request(rq, ret);
@@ -2743,7 +2729,16 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched)
 
 	plug->mq_list = requeue_list;
 	trace_block_unplug(this_hctx->queue, depth, !from_sched);
-	blk_mq_sched_insert_requests(this_hctx, this_ctx, &list, from_sched);
+
+	percpu_ref_get(&this_hctx->queue->q_usage_counter);
+	if (this_hctx->queue->elevator) {
+		this_hctx->queue->elevator->type->ops.insert_requests(this_hctx,
+				&list, 0);
+		blk_mq_run_hw_queue(this_hctx, from_sched);
+	} else {
+		blk_mq_insert_requests(this_hctx, this_ctx, &list, from_sched);
+	}
+	percpu_ref_put(&this_hctx->queue->q_usage_counter);
 }
 
 void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
@@ -2789,7 +2784,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 	} while (!rq_list_empty(plug->mq_list));
 }
 
-void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
+static void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 		struct list_head *list)
 {
 	int queued = 0;
@@ -2807,8 +2802,9 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 			break;
 		case BLK_STS_RESOURCE:
 		case BLK_STS_DEV_RESOURCE:
-			blk_mq_request_bypass_insert(rq, false,
-						     list_empty(list));
+			blk_mq_request_bypass_insert(rq, 0);
+			if (list_empty(list))
+				blk_mq_run_hw_queue(hctx, false);
 			goto out;
 		default:
 			blk_mq_end_request(rq, ret);
@@ -2934,6 +2930,7 @@ void blk_mq_submit_bio(struct bio *bio)
 	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 	struct blk_plug *plug = blk_mq_plug(bio);
 	const int is_sync = op_is_sync(bio->bi_opf);
+	struct blk_mq_hw_ctx *hctx;
 	struct request *rq;
 	unsigned int nr_segs = 1;
 	blk_status_t ret;
@@ -2965,7 +2962,7 @@ void blk_mq_submit_bio(struct bio *bio)
 
 	blk_mq_bio_to_request(rq, bio, nr_segs);
 
-	ret = blk_crypto_init_request(rq);
+	ret = blk_crypto_rq_get_keyslot(rq);
 	if (ret != BLK_STS_OK) {
 		bio->bi_status = ret;
 		bio_endio(bio);
@@ -2978,15 +2975,19 @@ void blk_mq_submit_bio(struct bio *bio)
 		return;
 	}
 
-	if (plug)
+	if (plug) {
 		blk_add_rq_to_plug(plug, rq);
-	else if ((rq->rq_flags & RQF_ELV) ||
-		 (rq->mq_hctx->dispatch_busy &&
-		  (q->nr_hw_queues == 1 || !is_sync)))
-		blk_mq_sched_insert_request(rq, false, true, true);
-	else
-		blk_mq_run_dispatch_ops(rq->q,
-				blk_mq_try_issue_directly(rq->mq_hctx, rq));
+		return;
+	}
+
+	hctx = rq->mq_hctx;
+	if ((rq->rq_flags & RQF_ELV) ||
+	    (hctx->dispatch_busy && (q->nr_hw_queues == 1 || !is_sync))) {
+		blk_mq_insert_request(rq, 0);
+		blk_mq_run_hw_queue(hctx, true);
+	} else {
+		blk_mq_run_dispatch_ops(q, blk_mq_try_issue_directly(hctx, rq));
+	}
 }
 
 #ifdef CONFIG_BLK_MQ_STACKING
@@ -3034,8 +3035,9 @@ blk_status_t blk_insert_cloned_request(struct request *rq)
 	if (q->disk && should_fail_request(q->disk->part0, blk_rq_bytes(rq)))
 		return BLK_STS_IOERR;
 
-	if (blk_crypto_insert_cloned_request(rq))
-		return BLK_STS_IOERR;
+	ret = blk_crypto_rq_get_keyslot(rq);
+	if (ret != BLK_STS_OK)
+		return ret;
 
 	blk_account_io_start(rq);
 
@@ -4206,14 +4208,8 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	/* mark the queue as mq asap */
 	q->mq_ops = set->ops;
 
-	q->poll_cb = blk_stat_alloc_callback(blk_mq_poll_stats_fn,
-					     blk_mq_poll_stats_bkt,
-					     BLK_MQ_POLL_STATS_BKTS, q);
-	if (!q->poll_cb)
-		goto err_exit;
-
 	if (blk_mq_alloc_ctxs(q))
-		goto err_poll;
+		goto err_exit;
 
 	/* init q->mq_kobj and sw queues' kobjects */
 	blk_mq_sysfs_init(q);
@@ -4241,11 +4237,6 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 
 	q->nr_requests = set->queue_depth;
 
-	/*
-	 * Default to classic polling
-	 */
-	q->poll_nsec = BLK_MQ_POLL_CLASSIC;
-
 	blk_mq_init_cpu_queues(q, set->nr_hw_queues);
 	blk_mq_add_queue_tag_set(set, q);
 	blk_mq_map_swqueue(q);
@@ -4253,9 +4244,6 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 
 err_hctxs:
 	blk_mq_release(q);
-err_poll:
-	blk_stat_free_callback(q->poll_cb);
-	q->poll_cb = NULL;
 err_exit:
 	q->mq_ops = NULL;
 	return -ENOMEM;
@@ -4752,138 +4740,8 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
 }
 EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues);
 
-/* Enable polling stats and return whether they were already enabled. */
-static bool blk_poll_stats_enable(struct request_queue *q)
-{
-	if (q->poll_stat)
-		return true;
-
-	return blk_stats_alloc_enable(q);
-}
-
-static void blk_mq_poll_stats_start(struct request_queue *q)
-{
-	/*
-	 * We don't arm the callback if polling stats are not enabled or the
-	 * callback is already active.
-	 */
-	if (!q->poll_stat || blk_stat_is_active(q->poll_cb))
-		return;
-
-	blk_stat_activate_msecs(q->poll_cb, 100);
-}
-
-static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb)
-{
-	struct request_queue *q = cb->data;
-	int bucket;
-
-	for (bucket = 0; bucket < BLK_MQ_POLL_STATS_BKTS; bucket++) {
-		if (cb->stat[bucket].nr_samples)
-			q->poll_stat[bucket] = cb->stat[bucket];
-	}
-}
-
-static unsigned long blk_mq_poll_nsecs(struct request_queue *q,
-				       struct request *rq)
-{
-	unsigned long ret = 0;
-	int bucket;
-
-	/*
-	 * If stats collection isn't on, don't sleep but turn it on for
-	 * future users
-	 */
-	if (!blk_poll_stats_enable(q))
-		return 0;
-
-	/*
-	 * As an optimistic guess, use half of the mean service time
-	 * for this type of request. We can (and should) make this smarter.
-	 * For instance, if the completion latencies are tight, we can
-	 * get closer than just half the mean. This is especially
-	 * important on devices where the completion latencies are longer
-	 * than ~10 usec. We do use the stats for the relevant IO size
-	 * if available which does lead to better estimates.
-	 */
-	bucket = blk_mq_poll_stats_bkt(rq);
-	if (bucket < 0)
-		return ret;
-
-	if (q->poll_stat[bucket].nr_samples)
-		ret = (q->poll_stat[bucket].mean + 1) / 2;
-
-	return ret;
-}
-
-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 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;
-
-	/*
-	 * If we get here, hybrid polling is enabled. Hence poll_nsec can be:
-	 *
-	 *  0:	use half of prev avg
-	 * >0:	use this specific value
-	 */
-	if (q->poll_nsec > 0)
-		nsecs = q->poll_nsec;
-	else
-		nsecs = blk_mq_poll_nsecs(q, rq);
-
-	if (!nsecs)
-		return false;
-
-	rq->rq_flags |= RQF_MQ_POLL_SLEPT;
-
-	/*
-	 * This will be replaced with the stats tracking code, using
-	 * 'avg_completion_time / 2' as the pre-sleep target.
-	 */
-	kt = nsecs;
-
-	mode = HRTIMER_MODE_REL;
-	hrtimer_init_sleeper_on_stack(&hs, CLOCK_MONOTONIC, mode);
-	hrtimer_set_expires(&hs.timer, kt);
-
-	do {
-		if (blk_mq_rq_state(rq) == MQ_RQ_COMPLETE)
-			break;
-		set_current_state(TASK_UNINTERRUPTIBLE);
-		hrtimer_sleeper_start_expires(&hs, mode);
-		if (hs.task)
-			io_schedule();
-		hrtimer_cancel(&hs.timer);
-		mode = HRTIMER_MODE_ABS;
-	} while (hs.task && !signal_pending(current));
-
-	__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 int blk_mq_poll_classic(struct request_queue *q, blk_qc_t cookie,
-			       struct io_comp_batch *iob, unsigned int flags)
+int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, struct io_comp_batch *iob,
+		unsigned int flags)
 {
 	struct blk_mq_hw_ctx *hctx = blk_qc_to_hctx(q, cookie);
 	long state = get_current_state();
@@ -4910,17 +4768,6 @@ static int blk_mq_poll_classic(struct request_queue *q, blk_qc_t cookie,
 	return 0;
 }
 
-int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, struct io_comp_batch *iob,
-		unsigned int flags)
-{
-	if (!(flags & BLK_POLL_NOSLEEP) &&
-	    q->poll_nsec != BLK_MQ_POLL_CLASSIC) {
-		if (blk_mq_poll_hybrid(q, cookie))
-			return 1;
-	}
-	return blk_mq_poll_classic(q, cookie, iob, flags);
-}
-
 unsigned int blk_mq_rq_cpu(struct request *rq)
 {
 	return rq->mq_ctx->cpu;