Merge tag 'for-5.17/block-2022-01-11' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - Unify where the struct request handling code is located in the blk-mq
   code (Christoph)

 - Header cleanups (Christoph)

 - Clean up the io_context handling code (Christoph, me)

 - Get rid of ->rq_disk in struct request (Christoph)

 - Error handling fix for add_disk() (Christoph)

 - request allocation cleanusp (Christoph)

 - Documentation updates (Eric, Matthew)

 - Remove trivial crypto unregister helper (Eric)

 - Reduce shared tag overhead (John)

 - Reduce poll_stats memory overhead (me)

 - Known indirect function call for dio (me)

 - Use atomic references for struct request (me)

 - Support request list issue for block and NVMe (me)

 - Improve queue dispatch pinning (Ming)

 - Improve the direct list issue code (Keith)

 - BFQ improvements (Jan)

 - Direct completion helper and use it in mmc block (Sebastian)

 - Use raw spinlock for the blktrace code (Wander)

 - fsync error handling fix (Ye)

 - Various fixes and cleanups (Lukas, Randy, Yang, Tetsuo, Ming, me)

* tag 'for-5.17/block-2022-01-11' of git://git.kernel.dk/linux-block: (132 commits)
  MAINTAINERS: add entries for block layer documentation
  docs: block: remove queue-sysfs.rst
  docs: sysfs-block: document virt_boundary_mask
  docs: sysfs-block: document stable_writes
  docs: sysfs-block: fill in missing documentation from queue-sysfs.rst
  docs: sysfs-block: add contact for nomerges
  docs: sysfs-block: sort alphabetically
  docs: sysfs-block: move to stable directory
  block: don't protect submit_bio_checks by q_usage_counter
  block: fix old-style declaration
  nvme-pci: fix queue_rqs list splitting
  block: introduce rq_list_move
  block: introduce rq_list_for_each_safe macro
  block: move rq_list macros to blk-mq.h
  block: drop needless assignment in set_task_ioprio()
  block: remove unnecessary trailing '\'
  bio.h: fix kernel-doc warnings
  block: check minor range in device_add_disk()
  block: use "unsigned long" for blk_validate_block_size().
  block: fix error unwinding in device_add_disk
  ...

Documentation/block/index.rst

@@ -20,7 +20,6 @@ Block
    kyber-iosched
    null_blk
    pr
-   queue-sysfs
    request
    stat
    switching-sched

Documentation/core-api/kernel-api.rst

@@ -294,9 +294,6 @@ Block Devices
 .. kernel-doc:: block/blk-settings.c
    :export:
 
-.. kernel-doc:: block/blk-exec.c
-   :export:
-
 .. kernel-doc:: block/blk-flush.c
    :export:
 

Documentation/translations/zh_CN/core-api/kernel-api.rst

@@ -292,8 +292,6 @@ block/blk-sysfs.c
 
 block/blk-settings.c
 
-block/blk-exec.c
-
 block/blk-flush.c
 
 block/blk-lib.c

MAINTAINERS

@@ -3416,6 +3416,8 @@ M:	Jens Axboe <axboe@kernel.dk>
 L:	linux-block@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git
+F:	Documentation/ABI/stable/sysfs-block
+F:	Documentation/block/
 F:	block/
 F:	drivers/block/
 F:	include/linux/blk*

block/Kconfig

@@ -35,6 +35,9 @@ config BLK_CGROUP_RWSTAT
 config BLK_DEV_BSG_COMMON
 	tristate
 
+config BLK_ICQ
+	bool
+
 config BLK_DEV_BSGLIB
 	bool "Block layer SG support v4 helper lib"
 	select BLK_DEV_BSG_COMMON

block/Kconfig.iosched

@@ -18,6 +18,7 @@ config MQ_IOSCHED_KYBER
 
 config IOSCHED_BFQ
 	tristate "BFQ I/O scheduler"
+	select BLK_ICQ
 	help
 	BFQ I/O scheduler for BLK-MQ. BFQ distributes the bandwidth of
 	of the device among all processes according to their weights,

block/Makefile

@@ -5,7 +5,7 @@
 
 obj-y		:= bdev.o fops.o bio.o elevator.o blk-core.o blk-sysfs.o \
 			blk-flush.o blk-settings.o blk-ioc.o blk-map.o \
-			blk-exec.o blk-merge.o blk-timeout.o \
+			blk-merge.o blk-timeout.o \
 			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
 			blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \
 			genhd.o ioprio.o badblocks.o partitions/ blk-rq-qos.o \

block/bdev.c

@@ -665,7 +665,7 @@ static void blkdev_flush_mapping(struct block_device *bdev)
 static int blkdev_get_whole(struct block_device *bdev, fmode_t mode)
 {
 	struct gendisk *disk = bdev->bd_disk;
-	int ret = 0;
+	int ret;
 
 	if (disk->fops->open) {
 		ret = disk->fops->open(bdev, mode);
@@ -750,14 +750,6 @@ struct block_device *blkdev_get_no_open(dev_t dev)
 	if (!kobject_get_unless_zero(&bdev->bd_device.kobj))
 		bdev = NULL;
 	iput(inode);
-
-	if (!bdev)
-		return NULL;
-	if ((bdev->bd_disk->flags & GENHD_FL_HIDDEN)) {
-		put_device(&bdev->bd_device);
-		return NULL;
-	}
-
 	return bdev;
 }
 
@@ -837,7 +829,7 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 		 * used in blkdev_get/put().
 		 */
 		if ((mode & FMODE_WRITE) && !bdev->bd_write_holder &&
-		    (disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE)) {
+		    (disk->event_flags & DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE)) {
 			bdev->bd_write_holder = true;
 			unblock_events = false;
 		}
@@ -963,15 +955,15 @@ void blkdev_put(struct block_device *bdev, fmode_t mode)
 EXPORT_SYMBOL(blkdev_put);
 
 /**
- * lookup_bdev  - lookup a struct block_device by name
- * @pathname:	special file representing the block device
- * @dev:	return value of the block device's dev_t
+ * lookup_bdev() - Look up a struct block_device by name.
+ * @pathname: Name of the block device in the filesystem.
+ * @dev: Pointer to the block device's dev_t, if found.
  *
  * Lookup the block device's dev_t at @pathname in the current
- * namespace if possible and return it by @dev.
+ * namespace if possible and return it in @dev.
  *
- * RETURNS:
- * 0 if succeeded, errno otherwise.
+ * Context: May sleep.
+ * Return: 0 if succeeded, negative errno otherwise.
  */
 int lookup_bdev(const char *pathname, dev_t *dev)
 {

block/bfq-iosched.h

@@ -25,7 +25,7 @@
 #define BFQ_DEFAULT_GRP_IOPRIO	0
 #define BFQ_DEFAULT_GRP_CLASS	IOPRIO_CLASS_BE
 
-#define MAX_PID_STR_LENGTH 12
+#define MAX_BFQQ_NAME_LENGTH 16
 
 /*
  * Soft real-time applications are extremely more latency sensitive
@@ -170,6 +170,9 @@ struct bfq_entity {
 	/* budget, used also to calculate F_i: F_i = S_i + @budget / @weight */
 	int budget;
 
+	/* Number of requests allocated in the subtree of this entity */
+	int allocated;
+
 	/* device weight, if non-zero, it overrides the default weight of
 	 * bfq_group_data */
 	int dev_weight;
@@ -266,8 +269,6 @@ struct bfq_queue {
 	struct request *next_rq;
 	/* number of sync and async requests queued */
 	int queued[2];
-	/* number of requests currently allocated */
-	int allocated;
 	/* number of pending metadata requests */
 	int meta_pending;
 	/* fifo list of requests in sort_list */
@@ -387,6 +388,8 @@ struct bfq_queue {
 	struct bfq_queue *tentative_waker_bfqq;
 	/* number of times the same tentative waker has been detected */
 	unsigned int num_waker_detections;
+	/* time when we started considering this waker */
+	u64 waker_detection_started;
 
 	/* node for woken_list, see below */
 	struct hlist_node woken_list_node;
@@ -768,6 +771,7 @@ struct bfq_data {
 	 * function)
 	 */
 	unsigned int word_depths[2][2];
+	unsigned int full_depth_shift;
 };
 
 enum bfqq_state_flags {
@@ -1079,26 +1083,27 @@ void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq);
 /* --------------- end of interface of B-WF2Q+ ---------------- */
 
 /* Logging facilities. */
-static inline void bfq_pid_to_str(int pid, char *str, int len)
+static inline void bfq_bfqq_name(struct bfq_queue *bfqq, char *str, int len)
 {
-	if (pid != -1)
-		snprintf(str, len, "%d", pid);
+	char type = bfq_bfqq_sync(bfqq) ? 'S' : 'A';
+
+	if (bfqq->pid != -1)
+		snprintf(str, len, "bfq%d%c", bfqq->pid, type);
 	else
-		snprintf(str, len, "SHARED-");
+		snprintf(str, len, "bfqSHARED-%c", type);
 }
 
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
 struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
 
 #define bfq_log_bfqq(bfqd, bfqq, fmt, args...)	do {			\
-	char pid_str[MAX_PID_STR_LENGTH];	\
+	char pid_str[MAX_BFQQ_NAME_LENGTH];				\
 	if (likely(!blk_trace_note_message_enabled((bfqd)->queue)))	\
 		break;							\
-	bfq_pid_to_str((bfqq)->pid, pid_str, MAX_PID_STR_LENGTH);	\
+	bfq_bfqq_name((bfqq), pid_str, MAX_BFQQ_NAME_LENGTH);		\
 	blk_add_cgroup_trace_msg((bfqd)->queue,				\
 			bfqg_to_blkg(bfqq_group(bfqq))->blkcg,		\
-			"bfq%s%c " fmt, pid_str,			\
-			bfq_bfqq_sync((bfqq)) ? 'S' : 'A', ##args);	\
+			"%s " fmt, pid_str, ##args);			\
 } while (0)
 
 #define bfq_log_bfqg(bfqd, bfqg, fmt, args...)	do {			\
@@ -1109,13 +1114,11 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
 #else /* CONFIG_BFQ_GROUP_IOSCHED */
 
 #define bfq_log_bfqq(bfqd, bfqq, fmt, args...) do {	\
-	char pid_str[MAX_PID_STR_LENGTH];	\
+	char pid_str[MAX_BFQQ_NAME_LENGTH];				\
 	if (likely(!blk_trace_note_message_enabled((bfqd)->queue)))	\
 		break;							\
-	bfq_pid_to_str((bfqq)->pid, pid_str, MAX_PID_STR_LENGTH);	\
-	blk_add_trace_msg((bfqd)->queue, "bfq%s%c " fmt, pid_str,	\
-			bfq_bfqq_sync((bfqq)) ? 'S' : 'A',		\
-				##args);	\
+	bfq_bfqq_name((bfqq), pid_str, MAX_BFQQ_NAME_LENGTH);		\
+	blk_add_trace_msg((bfqd)->queue, "%s " fmt, pid_str, ##args);	\
 } while (0)
 #define bfq_log_bfqg(bfqd, bfqg, fmt, args...)		do {} while (0)
 

block/bio.c

@@ -26,7 +26,7 @@
 #include "blk-rq-qos.h"
 
 struct bio_alloc_cache {
-	struct bio_list		free_list;
+	struct bio		*free_list;
 	unsigned int		nr;
 };
 
@@ -630,7 +630,8 @@ static void bio_alloc_cache_prune(struct bio_alloc_cache *cache,
 	unsigned int i = 0;
 	struct bio *bio;
 
-	while ((bio = bio_list_pop(&cache->free_list)) != NULL) {
+	while ((bio = cache->free_list) != NULL) {
+		cache->free_list = bio->bi_next;
 		cache->nr--;
 		bio_free(bio);
 		if (++i == nr)
@@ -689,7 +690,8 @@ void bio_put(struct bio *bio)
 
 		bio_uninit(bio);
 		cache = per_cpu_ptr(bio->bi_pool->cache, get_cpu());
-		bio_list_add_head(&cache->free_list, bio);
+		bio->bi_next = cache->free_list;
+		cache->free_list = bio;
 		if (++cache->nr > ALLOC_CACHE_MAX + ALLOC_CACHE_SLACK)
 			bio_alloc_cache_prune(cache, ALLOC_CACHE_SLACK);
 		put_cpu();
@@ -1704,8 +1706,9 @@ struct bio *bio_alloc_kiocb(struct kiocb *kiocb, unsigned short nr_vecs,
 		return bio_alloc_bioset(GFP_KERNEL, nr_vecs, bs);
 
 	cache = per_cpu_ptr(bs->cache, get_cpu());
-	bio = bio_list_pop(&cache->free_list);
-	if (bio) {
+	if (cache->free_list) {
+		bio = cache->free_list;
+		cache->free_list = bio->bi_next;
 		cache->nr--;
 		put_cpu();
 		bio_init(bio, nr_vecs ? bio->bi_inline_vecs : NULL, nr_vecs);

block/blk-cgroup.c

@@ -30,6 +30,7 @@
 #include <linux/blk-cgroup.h>
 #include <linux/tracehook.h>
 #include <linux/psi.h>
+#include <linux/part_stat.h>
 #include "blk.h"
 #include "blk-ioprio.h"
 #include "blk-throttle.h"

block/blk-crypto-profile.c

@@ -463,11 +463,6 @@ bool blk_crypto_register(struct blk_crypto_profile *profile,
 }
 EXPORT_SYMBOL_GPL(blk_crypto_register);
 
-void blk_crypto_unregister(struct request_queue *q)
-{
-	q->crypto_profile = NULL;
-}
-
 /**
  * blk_crypto_intersect_capabilities() - restrict supported crypto capabilities
  *					 by child device

block/blk-exec.c

-// SPDX-License-Identifier: GPL-2.0
-/*
- * Functions related to setting various queue properties from drivers
- */
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/bio.h>
-#include <linux/blkdev.h>
-#include <linux/blk-mq.h>
-#include <linux/sched/sysctl.h>
-
-#include "blk.h"
-#include "blk-mq-sched.h"
-
-/**
- * blk_end_sync_rq - executes a completion event on a request
- * @rq: request to complete
- * @error: end I/O status of the request
- */
-static void blk_end_sync_rq(struct request *rq, blk_status_t error)
-{
-	struct completion *waiting = rq->end_io_data;
-
-	rq->end_io_data = (void *)(uintptr_t)error;
-
-	/*
-	 * complete last, if this is a stack request the process (and thus
-	 * the rq pointer) could be invalid right after this complete()
-	 */
-	complete(waiting);
-}
-
-/**
- * blk_execute_rq_nowait - insert a request to I/O scheduler for execution
- * @bd_disk:	matching gendisk
- * @rq:		request to insert
- * @at_head:    insert request at head or tail of queue
- * @done:	I/O completion handler
- *
- * Description:
- *    Insert a fully prepared request at the back of the I/O scheduler queue
- *    for execution.  Don't wait for completion.
- *
- * Note:
- *    This function will invoke @done directly if the queue is dead.
- */
-void blk_execute_rq_nowait(struct gendisk *bd_disk, struct request *rq,
-			   int at_head, rq_end_io_fn *done)
-{
-	WARN_ON(irqs_disabled());
-	WARN_ON(!blk_rq_is_passthrough(rq));
-
-	rq->rq_disk = bd_disk;
-	rq->end_io = done;
-
-	blk_account_io_start(rq);
-
-	/*
-	 * don't check dying flag for MQ because the request won't
-	 * be reused after dying flag is set
-	 */
-	blk_mq_sched_insert_request(rq, at_head, true, false);
-}
-EXPORT_SYMBOL_GPL(blk_execute_rq_nowait);
-
-static bool blk_rq_is_poll(struct request *rq)
-{
-	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 {
-		bio_poll(rq->bio, NULL, 0);
-		cond_resched();
-	} while (!completion_done(wait));
-}
-
-/**
- * blk_execute_rq - insert a request into queue for execution
- * @bd_disk:	matching gendisk
- * @rq:		request to insert
- * @at_head:    insert request at head or tail of queue
- *
- * Description:
- *    Insert a fully prepared request at the back of the I/O scheduler queue
- *    for execution and wait for completion.
- * Return: The blk_status_t result provided to blk_mq_end_request().
- */
-blk_status_t blk_execute_rq(struct gendisk *bd_disk, struct request *rq, int at_head)
-{
-	DECLARE_COMPLETION_ONSTACK(wait);
-	unsigned long hang_check;
-
-	rq->end_io_data = &wait;
-	blk_execute_rq_nowait(bd_disk, rq, at_head, blk_end_sync_rq);
-
-	/* Prevent hang_check timer from firing at us during very long I/O */
-	hang_check = sysctl_hung_task_timeout_secs;
-
-	if (blk_rq_is_poll(rq))
-		blk_rq_poll_completion(rq, &wait);
-	else if (hang_check)
-		while (!wait_for_completion_io_timeout(&wait, hang_check * (HZ/2)));
-	else
-		wait_for_completion_io(&wait);
-
-	return (blk_status_t)(uintptr_t)rq->end_io_data;
-}
-EXPORT_SYMBOL(blk_execute_rq);

block/blk-flush.c

@@ -69,6 +69,7 @@
 #include <linux/blkdev.h>
 #include <linux/gfp.h>
 #include <linux/blk-mq.h>
+#include <linux/part_stat.h>
 
 #include "blk.h"
 #include "blk-mq.h"
@@ -95,6 +96,12 @@ enum {
 static void blk_kick_flush(struct request_queue *q,
 			   struct blk_flush_queue *fq, unsigned int flags);
 
+static inline struct blk_flush_queue *
+blk_get_flush_queue(struct request_queue *q, struct blk_mq_ctx *ctx)
+{
+	return blk_mq_map_queue(q, REQ_OP_FLUSH, ctx)->fq;
+}
+
 static unsigned int blk_flush_policy(unsigned long fflags, struct request *rq)
 {
 	unsigned int policy = 0;
@@ -138,7 +145,7 @@ static void blk_flush_queue_rq(struct request *rq, bool add_front)
 
 static void blk_account_io_flush(struct request *rq)
 {
-	struct block_device *part = rq->rq_disk->part0;
+	struct block_device *part = rq->q->disk->part0;
 
 	part_stat_lock();
 	part_stat_inc(part, ios[STAT_FLUSH]);
@@ -222,7 +229,7 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error)
 	/* release the tag's ownership to the req cloned from */
 	spin_lock_irqsave(&fq->mq_flush_lock, flags);
 
-	if (!refcount_dec_and_test(&flush_rq->ref)) {
+	if (!req_ref_put_and_test(flush_rq)) {
 		fq->rq_status = error;
 		spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
 		return;
@@ -235,8 +242,10 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error)
 	 * avoiding use-after-free.
 	 */
 	WRITE_ONCE(flush_rq->state, MQ_RQ_IDLE);
-	if (fq->rq_status != BLK_STS_OK)
+	if (fq->rq_status != BLK_STS_OK) {
 		error = fq->rq_status;
+		fq->rq_status = BLK_STS_OK;
+	}
 
 	if (!q->elevator) {
 		flush_rq->tag = BLK_MQ_NO_TAG;
@@ -332,7 +341,6 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq,
 	flush_rq->cmd_flags = REQ_OP_FLUSH | REQ_PREFLUSH;
 	flush_rq->cmd_flags |= (flags & REQ_DRV) | (flags & REQ_FAILFAST_MASK);
 	flush_rq->rq_flags |= RQF_FLUSH_SEQ;
-	flush_rq->rq_disk = first_rq->rq_disk;
 	flush_rq->end_io = flush_end_io;
 	/*
 	 * Order WRITE ->end_io and WRITE rq->ref, and its pair is the one
@@ -341,7 +349,7 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq,
 	 * and READ flush_rq->end_io
 	 */
 	smp_wmb();
-	refcount_set(&flush_rq->ref, 1);
+	req_ref_set(flush_rq, 1);
 
 	blk_flush_queue_rq(flush_rq, false);
 }

block/blk-integrity.c

@@ -411,7 +411,7 @@ void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION
 	if (disk->queue->crypto_profile) {
 		pr_warn("blk-integrity: Integrity and hardware inline encryption are not supported together. Disabling hardware inline encryption.\n");
-		blk_crypto_unregister(disk->queue);
+		disk->queue->crypto_profile = NULL;
 	}
 #endif
 }

block/blk-ioprio.c

@@ -62,6 +62,7 @@ struct ioprio_blkg {
 struct ioprio_blkcg {
 	struct blkcg_policy_data cpd;
 	enum prio_policy	 prio_policy;
+	bool			 prio_set;
 };
 
 static inline struct ioprio_blkg *pd_to_ioprio(struct blkg_policy_data *pd)
@@ -112,7 +113,7 @@ static ssize_t ioprio_set_prio_policy(struct kernfs_open_file *of, char *buf,
 	if (ret < 0)
 		return ret;
 	blkcg->prio_policy = ret;
-
+	blkcg->prio_set = true;
 	return nbytes;
 }
 
@@ -190,6 +191,10 @@ static void blkcg_ioprio_track(struct rq_qos *rqos, struct request *rq,
 			       struct bio *bio)
 {
 	struct ioprio_blkcg *blkcg = ioprio_blkcg_from_bio(bio);
+	u16 prio;
+
+	if (!blkcg->prio_set)
+		return;
 
 	/*
 	 * Except for IOPRIO_CLASS_NONE, higher I/O priority numbers
@@ -199,8 +204,10 @@ static void blkcg_ioprio_track(struct rq_qos *rqos, struct request *rq,
 	 * bio I/O priority is not modified. If the bio I/O priority equals
 	 * IOPRIO_CLASS_NONE, the cgroup I/O priority is assigned to the bio.
 	 */
-	bio->bi_ioprio = max_t(u16, bio->bi_ioprio,
+	prio = max_t(u16, bio->bi_ioprio,
 			IOPRIO_PRIO_VALUE(blkcg->prio_policy, 0));
+	if (prio > bio->bi_ioprio)
+		bio->bi_ioprio = prio;
 }
 
 static void blkcg_ioprio_exit(struct rq_qos *rqos)

block/blk-merge.c

@@ -8,10 +8,12 @@
 #include <linux/blkdev.h>
 #include <linux/blk-integrity.h>
 #include <linux/scatterlist.h>
+#include <linux/part_stat.h>
 
 #include <trace/events/block.h>
 
 #include "blk.h"
+#include "blk-mq-sched.h"
 #include "blk-rq-qos.h"
 #include "blk-throttle.h"
 
@@ -775,8 +777,7 @@ static struct request *attempt_merge(struct request_queue *q,
 	if (req_op(req) != req_op(next))
 		return NULL;
 
-	if (rq_data_dir(req) != rq_data_dir(next)
-	    || req->rq_disk != next->rq_disk)
+	if (rq_data_dir(req) != rq_data_dir(next))
 		return NULL;
 
 	if (req_op(req) == REQ_OP_WRITE_SAME &&
@@ -903,10 +904,6 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	if (bio_data_dir(bio) != rq_data_dir(rq))
 		return false;
 
-	/* must be same device */
-	if (rq->rq_disk != bio->bi_bdev->bd_disk)
-		return false;
-
 	/* only merge integrity protected bio into ditto rq */
 	if (blk_integrity_merge_bio(rq->q, rq, bio) == false)
 		return false;
@@ -1067,7 +1064,6 @@ static enum bio_merge_status blk_attempt_bio_merge(struct request_queue *q,
  * @q: request_queue new bio is being queued at
  * @bio: new bio being queued
  * @nr_segs: number of segments in @bio
- * @same_queue_rq: output value, will be true if there's an existing request
  * from the passed in @q already in the plug list
  *
  * Determine whether @bio being queued on @q can be merged with the previous
@@ -1084,7 +1080,7 @@ static enum bio_merge_status blk_attempt_bio_merge(struct request_queue *q,
  * Caller must ensure !blk_queue_nomerges(q) beforehand.
  */
 bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
-		unsigned int nr_segs, bool *same_queue_rq)
+		unsigned int nr_segs)
 {
 	struct blk_plug *plug;
 	struct request *rq;
@@ -1096,12 +1092,6 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 	/* check the previously added entry for a quick merge attempt */
 	rq = rq_list_peek(&plug->mq_list);
 	if (rq->q == q) {
-		/*
-		 * Only blk-mq multiple hardware queues case checks the rq in
-		 * the same queue, there should be only one such rq in a queue
-		 */
-		*same_queue_rq = true;
-
 		if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) ==
 				BIO_MERGE_OK)
 			return true;

block/blk-mq-debugfs.c

@@ -11,6 +11,7 @@
 #include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-debugfs.h"
+#include "blk-mq-sched.h"
 #include "blk-mq-tag.h"
 #include "blk-rq-qos.h"
 
@@ -29,6 +30,9 @@ static int queue_poll_stat_show(void *data, struct seq_file *m)
 	struct request_queue *q = data;
 	int bucket;
 
+	if (!q->poll_stat)
+		return 0;
+
 	for (bucket = 0; bucket < (BLK_MQ_POLL_STATS_BKTS / 2); bucket++) {
 		seq_printf(m, "read  (%d Bytes): ", 1 << (9 + bucket));
 		print_stat(m, &q->poll_stat[2 * bucket]);
@@ -122,7 +126,6 @@ static const char *const blk_queue_flag_name[] = {
 	QUEUE_FLAG_NAME(FUA),
 	QUEUE_FLAG_NAME(DAX),
 	QUEUE_FLAG_NAME(STATS),
-	QUEUE_FLAG_NAME(POLL_STATS),
 	QUEUE_FLAG_NAME(REGISTERED),
 	QUEUE_FLAG_NAME(QUIESCED),
 	QUEUE_FLAG_NAME(PCI_P2PDMA),

block/blk-mq-sched.c

@@ -18,32 +18,6 @@
 #include "blk-mq-tag.h"
 #include "blk-wbt.h"
 
-void blk_mq_sched_assign_ioc(struct request *rq)
-{
-	struct request_queue *q = rq->q;
-	struct io_context *ioc;
-	struct io_cq *icq;
-
-	/*
-	 * May not have an IO context if it's a passthrough request
-	 */
-	ioc = current->io_context;
-	if (!ioc)
-		return;
-
-	spin_lock_irq(&q->queue_lock);
-	icq = ioc_lookup_icq(ioc, q);
-	spin_unlock_irq(&q->queue_lock);
-
-	if (!icq) {
-		icq = ioc_create_icq(ioc, q, GFP_ATOMIC);
-		if (!icq)
-			return;
-	}
-	get_io_context(icq->ioc);
-	rq->elv.icq = icq;
-}
-
 /*
  * Mark a hardware queue as needing a restart. For shared queues, maintain
  * a count of how many hardware queues are marked for restart.
@@ -501,7 +475,8 @@ void blk_mq_sched_insert_requests(struct blk_mq_hw_ctx *hctx,
 		 * us one extra enqueue & dequeue to sw queue.
 		 */
 		if (!hctx->dispatch_busy && !run_queue_async) {
-			blk_mq_try_issue_list_directly(hctx, list);
+			blk_mq_run_dispatch_ops(hctx->queue,
+				blk_mq_try_issue_list_directly(hctx, list));
 			if (list_empty(list))
 				goto out;
 		}

block/blk-mq-sched.h

@@ -8,8 +8,6 @@
 
 #define MAX_SCHED_RQ (16 * BLKDEV_DEFAULT_RQ)
 
-void blk_mq_sched_assign_ioc(struct request *rq);
-
 bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
 		unsigned int nr_segs, struct request **merged_request);
 bool blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,

block/blk-mq-sysfs.c

@@ -36,8 +36,6 @@ static void blk_mq_hw_sysfs_release(struct kobject *kobj)
 	struct blk_mq_hw_ctx *hctx = container_of(kobj, struct blk_mq_hw_ctx,
 						  kobj);
 
-	if (hctx->flags & BLK_MQ_F_BLOCKING)
-		cleanup_srcu_struct(hctx->srcu);
 	blk_free_flush_queue(hctx->fq);
 	sbitmap_free(&hctx->ctx_map);
 	free_cpumask_var(hctx->cpumask);

block/blk-mq-tag.c

@@ -215,7 +215,8 @@ void blk_mq_put_tags(struct blk_mq_tags *tags, int *tag_array, int nr_tags)
 
 struct bt_iter_data {
 	struct blk_mq_hw_ctx *hctx;
-	busy_iter_fn *fn;
+	struct request_queue *q;
+	busy_tag_iter_fn *fn;
 	void *data;
 	bool reserved;
 };
@@ -228,7 +229,7 @@ static struct request *blk_mq_find_and_get_req(struct blk_mq_tags *tags,
 
 	spin_lock_irqsave(&tags->lock, flags);
 	rq = tags->rqs[bitnr];
-	if (!rq || rq->tag != bitnr || !refcount_inc_not_zero(&rq->ref))
+	if (!rq || rq->tag != bitnr || !req_ref_inc_not_zero(rq))
 		rq = NULL;
 	spin_unlock_irqrestore(&tags->lock, flags);
 	return rq;
@@ -238,11 +239,18 @@ static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 {
 	struct bt_iter_data *iter_data = data;
 	struct blk_mq_hw_ctx *hctx = iter_data->hctx;
-	struct blk_mq_tags *tags = hctx->tags;
+	struct request_queue *q = iter_data->q;
+	struct blk_mq_tag_set *set = q->tag_set;
 	bool reserved = iter_data->reserved;
+	struct blk_mq_tags *tags;
 	struct request *rq;
 	bool ret = true;
 
+	if (blk_mq_is_shared_tags(set->flags))
+		tags = set->shared_tags;
+	else
+		tags = hctx->tags;
+
 	if (!reserved)
 		bitnr += tags->nr_reserved_tags;
 	/*
@@ -253,8 +261,8 @@ static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 	if (!rq)
 		return true;
 
-	if (rq->q == hctx->queue && rq->mq_hctx == hctx)
-		ret = iter_data->fn(hctx, rq, iter_data->data, reserved);
+	if (rq->q == q && (!hctx || rq->mq_hctx == hctx))
+		ret = iter_data->fn(rq, iter_data->data, reserved);
 	blk_mq_put_rq_ref(rq);
 	return ret;
 }
@@ -262,6 +270,7 @@ static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 /**
  * bt_for_each - iterate over the requests associated with a hardware queue
  * @hctx:	Hardware queue to examine.
+ * @q:		Request queue to examine.
  * @bt:		sbitmap to examine. This is either the breserved_tags member
  *		or the bitmap_tags member of struct blk_mq_tags.
  * @fn:		Pointer to the function that will be called for each request
@@ -273,14 +282,16 @@ static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
  * @reserved:	Indicates whether @bt is the breserved_tags member or the
  *		bitmap_tags member of struct blk_mq_tags.
  */
-static void bt_for_each(struct blk_mq_hw_ctx *hctx, struct sbitmap_queue *bt,
-			busy_iter_fn *fn, void *data, bool reserved)
+static void bt_for_each(struct blk_mq_hw_ctx *hctx, struct request_queue *q,
+			struct sbitmap_queue *bt, busy_tag_iter_fn *fn,
+			void *data, bool reserved)
 {
 	struct bt_iter_data iter_data = {
 		.hctx = hctx,
 		.fn = fn,
 		.data = data,
 		.reserved = reserved,
+		.q = q,
 	};
 
 	sbitmap_for_each_set(&bt->sb, bt_iter, &iter_data);
@@ -457,12 +468,9 @@ EXPORT_SYMBOL(blk_mq_tagset_wait_completed_request);
  * called for all requests on all queues that share that tag set and not only
  * for requests associated with @q.
  */
-void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
+void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_tag_iter_fn *fn,
 		void *priv)
 {
-	struct blk_mq_hw_ctx *hctx;
-	int i;
-
 	/*
 	 * __blk_mq_update_nr_hw_queues() updates nr_hw_queues and queue_hw_ctx
 	 * while the queue is frozen. So we can use q_usage_counter to avoid
@@ -471,8 +479,22 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 	if (!percpu_ref_tryget(&q->q_usage_counter))
 		return;
 
+	if (blk_mq_is_shared_tags(q->tag_set->flags)) {
+		struct blk_mq_tags *tags = q->tag_set->shared_tags;
+		struct sbitmap_queue *bresv = &tags->breserved_tags;
+		struct sbitmap_queue *btags = &tags->bitmap_tags;
+
+		if (tags->nr_reserved_tags)
+			bt_for_each(NULL, q, bresv, fn, priv, true);
+		bt_for_each(NULL, q, btags, fn, priv, false);
+	} else {
+		struct blk_mq_hw_ctx *hctx;
+		int i;
+
 		queue_for_each_hw_ctx(q, hctx, i) {
 			struct blk_mq_tags *tags = hctx->tags;
+			struct sbitmap_queue *bresv = &tags->breserved_tags;
+			struct sbitmap_queue *btags = &tags->bitmap_tags;
 
 			/*
 			 * If no software queues are currently mapped to this
@@ -482,8 +504,9 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 				continue;
 
 			if (tags->nr_reserved_tags)
-			bt_for_each(hctx, &tags->breserved_tags, fn, priv, true);
-		bt_for_each(hctx, &tags->bitmap_tags, fn, priv, false);
+				bt_for_each(hctx, q, bresv, fn, priv, true);
+			bt_for_each(hctx, q, btags, fn, priv, false);
+		}
 	}
 	blk_queue_exit(q);
 }

block/blk-mq-tag.h

@@ -28,7 +28,7 @@ extern void blk_mq_tag_resize_shared_tags(struct blk_mq_tag_set *set,
 extern void blk_mq_tag_update_sched_shared_tags(struct request_queue *q);
 
 extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool);
-void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
+void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_tag_iter_fn *fn,
 		void *priv);
 void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn,
 		void *priv);

block/blk-mq.h

@@ -65,9 +65,6 @@ void blk_mq_request_bypass_insert(struct request *rq, bool at_head,
 				  bool run_queue);
 void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 				struct list_head *list);
-
-/* Used by blk_insert_cloned_request() to issue request directly */
-blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last);
 void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 				    struct list_head *list);
 
@@ -377,5 +374,24 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
 	return __blk_mq_active_requests(hctx) < depth;
 }
 
+/* run the code block in @dispatch_ops with rcu/srcu read lock held */
+#define __blk_mq_run_dispatch_ops(q, check_sleep, dispatch_ops)	\
+do {								\
+	if (!blk_queue_has_srcu(q)) {				\
+		rcu_read_lock();				\
+		(dispatch_ops);					\
+		rcu_read_unlock();				\
+	} else {						\
+		int srcu_idx;					\
+								\
+		might_sleep_if(check_sleep);			\
+		srcu_idx = srcu_read_lock((q)->srcu);		\
+		(dispatch_ops);					\
+		srcu_read_unlock((q)->srcu, srcu_idx);		\
+	}							\
+} while (0)
+
+#define blk_mq_run_dispatch_ops(q, dispatch_ops)		\
+	__blk_mq_run_dispatch_ops(q, true, dispatch_ops)	\
 
 #endif

block/blk-stat.c

@@ -15,7 +15,7 @@
 struct blk_queue_stats {
 	struct list_head callbacks;
 	spinlock_t lock;
-	bool enable_accounting;
+	int accounting;
 };
 
 void blk_rq_stat_init(struct blk_rq_stat *stat)
@@ -161,7 +161,7 @@ void blk_stat_remove_callback(struct request_queue *q,
 
 	spin_lock_irqsave(&q->stats->lock, flags);
 	list_del_rcu(&cb->list);
-	if (list_empty(&q->stats->callbacks) && !q->stats->enable_accounting)
+	if (list_empty(&q->stats->callbacks) && !q->stats->accounting)
 		blk_queue_flag_clear(QUEUE_FLAG_STATS, q);
 	spin_unlock_irqrestore(&q->stats->lock, flags);
 
@@ -184,12 +184,23 @@ void blk_stat_free_callback(struct blk_stat_callback *cb)
 		call_rcu(&cb->rcu, blk_stat_free_callback_rcu);
 }
 
+void blk_stat_disable_accounting(struct request_queue *q)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&q->stats->lock, flags);
+	if (!--q->stats->accounting)
+		blk_queue_flag_clear(QUEUE_FLAG_STATS, q);
+	spin_unlock_irqrestore(&q->stats->lock, flags);
+}
+EXPORT_SYMBOL_GPL(blk_stat_disable_accounting);
+
 void blk_stat_enable_accounting(struct request_queue *q)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&q->stats->lock, flags);
-	q->stats->enable_accounting = true;
+	if (!q->stats->accounting++)
 		blk_queue_flag_set(QUEUE_FLAG_STATS, q);
 	spin_unlock_irqrestore(&q->stats->lock, flags);
 }
@@ -205,7 +216,7 @@ struct blk_queue_stats *blk_alloc_queue_stats(void)
 
 	INIT_LIST_HEAD(&stats->callbacks);
 	spin_lock_init(&stats->lock);
-	stats->enable_accounting = false;
+	stats->accounting = 0;
 
 	return stats;
 }
@@ -219,3 +230,21 @@ void blk_free_queue_stats(struct blk_queue_stats *stats)
 
 	kfree(stats);
 }
+
+bool blk_stats_alloc_enable(struct request_queue *q)
+{
+	struct blk_rq_stat *poll_stat;
+
+	poll_stat = kcalloc(BLK_MQ_POLL_STATS_BKTS, sizeof(*poll_stat),
+				GFP_ATOMIC);
+	if (!poll_stat)
+		return false;
+
+	if (cmpxchg(&q->poll_stat, NULL, poll_stat) != NULL) {
+		kfree(poll_stat);
+		return true;
+	}
+
+	blk_stat_add_callback(q, q->poll_cb);
+	return false;
+}

block/blk-stat.h

@@ -64,11 +64,13 @@ struct blk_stat_callback {
 
 struct blk_queue_stats *blk_alloc_queue_stats(void);
 void blk_free_queue_stats(struct blk_queue_stats *);
+bool blk_stats_alloc_enable(struct request_queue *q);
 
 void blk_stat_add(struct request *rq, u64 now);
 
 /* record time/size info in request but not add a callback */
 void blk_stat_enable_accounting(struct request_queue *q);
+void blk_stat_disable_accounting(struct request_queue *q);
 
 /**
  * blk_stat_alloc_callback() - Allocate a block statistics callback.

block/blk-sysfs.c

@@ -16,6 +16,7 @@
 #include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-debugfs.h"
+#include "blk-mq-sched.h"
 #include "blk-wbt.h"
 #include "blk-throttle.h"
 
@@ -734,7 +735,8 @@ static void blk_free_queue_rcu(struct rcu_head *rcu_head)
 {
 	struct request_queue *q = container_of(rcu_head, struct request_queue,
 					       rcu_head);
-	kmem_cache_free(blk_requestq_cachep, q);
+
+	kmem_cache_free(blk_get_queue_kmem_cache(blk_queue_has_srcu(q)), q);
 }
 
 /* Unconfigure the I/O scheduler and dissociate from the cgroup controller. */
@@ -747,7 +749,7 @@ static void blk_exit_queue(struct request_queue *q)
 	 */
 	if (q->elevator) {
 		ioc_clear_queue(q);
-		__elevator_exit(q, q->elevator);
+		elevator_exit(q);
 	}
 
 	/*
@@ -785,14 +787,15 @@ static void blk_release_queue(struct kobject *kobj)
 
 	might_sleep();
 
-	if (test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags))
+	if (q->poll_stat)
 		blk_stat_remove_callback(q, q->poll_cb);
 	blk_stat_free_callback(q->poll_cb);
 
-	blk_free_queue_stats(q->stats);
-
 	blk_exit_queue(q);
 
+	blk_free_queue_stats(q->stats);
+	kfree(q->poll_stat);
+
 	blk_queue_free_zone_bitmaps(q);
 
 	if (queue_is_mq(q))

block/blk-throttle.c

@@ -13,6 +13,7 @@
 #include <linux/blk-cgroup.h>
 #include "blk.h"
 #include "blk-cgroup-rwstat.h"
+#include "blk-stat.h"
 #include "blk-throttle.h"
 
 /* Max dispatch from a group in 1 round */

block/blk.h

@@ -2,15 +2,10 @@
 #ifndef BLK_INTERNAL_H
 #define BLK_INTERNAL_H
 
-#include <linux/idr.h>
-#include <linux/blk-mq.h>
-#include <linux/part_stat.h>
 #include <linux/blk-crypto.h>
 #include <linux/memblock.h>	/* for max_pfn/max_low_pfn */
 #include <xen/xen.h>
 #include "blk-crypto-internal.h"
-#include "blk-mq.h"
-#include "blk-mq-sched.h"
 
 struct elevator_type;
 
@@ -32,15 +27,10 @@ struct blk_flush_queue {
 };
 
 extern struct kmem_cache *blk_requestq_cachep;
+extern struct kmem_cache *blk_requestq_srcu_cachep;
 extern struct kobj_type blk_queue_ktype;
 extern struct ida blk_queue_ida;
 
-static inline struct blk_flush_queue *
-blk_get_flush_queue(struct request_queue *q, struct blk_mq_ctx *ctx)
-{
-	return blk_mq_map_queue(q, REQ_OP_FLUSH, ctx)->fq;
-}
-
 static inline void __blk_get_queue(struct request_queue *q)
 {
 	kobject_get(&q->kobj);
@@ -250,16 +240,13 @@ static inline void blk_integrity_del(struct gendisk *disk)
 
 unsigned long blk_rq_timeout(unsigned long timeout);
 void blk_add_timer(struct request *req);
-void blk_print_req_error(struct request *req, blk_status_t status);
+const char *blk_status_to_str(blk_status_t status);
 
 bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
-		unsigned int nr_segs, bool *same_queue_rq);
+		unsigned int nr_segs);
 bool blk_bio_list_merge(struct request_queue *q, struct list_head *list,
 			struct bio *bio, unsigned int nr_segs);
 
-void __blk_account_io_start(struct request *req);
-void __blk_account_io_done(struct request *req, u64 now);
-
 /*
  * Plug flush limits
  */
@@ -275,19 +262,10 @@ void blk_insert_flush(struct request *rq);
 
 int elevator_switch_mq(struct request_queue *q,
 			      struct elevator_type *new_e);
-void __elevator_exit(struct request_queue *, struct elevator_queue *);
+void elevator_exit(struct request_queue *q);
 int elv_register_queue(struct request_queue *q, bool uevent);
 void elv_unregister_queue(struct request_queue *q);
 
-static inline void elevator_exit(struct request_queue *q,
-		struct elevator_queue *e)
-{
-	lockdep_assert_held(&q->sysfs_lock);
-
-	blk_mq_sched_free_rqs(q);
-	__elevator_exit(q, e);
-}
-
 ssize_t part_size_show(struct device *dev, struct device_attribute *attr,
 		char *buf);
 ssize_t part_stat_show(struct device *dev, struct device_attribute *attr,
@@ -347,26 +325,10 @@ int blk_dev_init(void);
  */
 static inline bool blk_do_io_stat(struct request *rq)
 {
-	return (rq->rq_flags & RQF_IO_STAT) && rq->rq_disk;
-}
-
-static inline 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 (blk_do_io_stat(req) && req->part &&
-	    !(req->rq_flags & RQF_FLUSH_SEQ))
-		__blk_account_io_done(req, now);
+	return (rq->rq_flags & RQF_IO_STAT) && rq->q->disk;
 }
 
-static inline void blk_account_io_start(struct request *req)
-{
-	if (blk_do_io_stat(req))
-		__blk_account_io_start(req);
-}
+void update_io_ticks(struct block_device *part, unsigned long now, bool end);
 
 static inline void req_set_nomerge(struct request_queue *q, struct request *req)
 {
@@ -402,13 +364,15 @@ static inline unsigned int bio_aligned_discard_max_sectors(
 /*
  * Internal io_context interface
  */
-void get_io_context(struct io_context *ioc);
-struct io_cq *ioc_lookup_icq(struct io_context *ioc, struct request_queue *q);
-struct io_cq *ioc_create_icq(struct io_context *ioc, struct request_queue *q,
-			     gfp_t gfp_mask);
+struct io_cq *ioc_find_get_icq(struct request_queue *q);
+struct io_cq *ioc_lookup_icq(struct request_queue *q);
+#ifdef CONFIG_BLK_ICQ
 void ioc_clear_queue(struct request_queue *q);
-
-int create_task_io_context(struct task_struct *task, gfp_t gfp_mask, int node);
+#else
+static inline void ioc_clear_queue(struct request_queue *q)
+{
+}
+#endif /* CONFIG_BLK_ICQ */
 
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
 extern ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page);
@@ -467,7 +431,15 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio,
 		struct page *page, unsigned int len, unsigned int offset,
 		unsigned int max_sectors, bool *same_page);
 
-struct request_queue *blk_alloc_queue(int node_id);
+static inline struct kmem_cache *blk_get_queue_kmem_cache(bool srcu)
+{
+	if (srcu)
+		return blk_requestq_srcu_cachep;
+	return blk_requestq_cachep;
+}
+struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu);
+
+int disk_scan_partitions(struct gendisk *disk, fmode_t mode);
 
 int disk_alloc_events(struct gendisk *disk);
 void disk_add_events(struct gendisk *disk);
@@ -493,4 +465,45 @@ int disk_register_independent_access_ranges(struct gendisk *disk,
 				struct blk_independent_access_ranges *new_iars);
 void disk_unregister_independent_access_ranges(struct gendisk *disk);
 
+#ifdef CONFIG_FAIL_MAKE_REQUEST
+bool should_fail_request(struct block_device *part, unsigned int bytes);
+#else /* CONFIG_FAIL_MAKE_REQUEST */
+static inline bool should_fail_request(struct block_device *part,
+					unsigned int bytes)
+{
+	return false;
+}
+#endif /* CONFIG_FAIL_MAKE_REQUEST */
+
+/*
+ * Optimized request reference counting. Ideally we'd make timeouts be more
+ * clever, as that's the only reason we need references at all... But until
+ * this happens, this is faster than using refcount_t. Also see:
+ *
+ * abc54d634334 ("io_uring: switch to atomic_t for io_kiocb reference count")
+ */
+#define req_ref_zero_or_close_to_overflow(req)	\
+	((unsigned int) atomic_read(&(req->ref)) + 127u <= 127u)
+
+static inline bool req_ref_inc_not_zero(struct request *req)
+{
+	return atomic_inc_not_zero(&req->ref);
+}
+
+static inline bool req_ref_put_and_test(struct request *req)
+{
+	WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req));
+	return atomic_dec_and_test(&req->ref);
+}
+
+static inline void req_ref_set(struct request *req, int value)
+{
+	atomic_set(&req->ref, value);
+}
+
+static inline int req_ref_read(struct request *req)
+{
+	return atomic_read(&req->ref);
+}
+
 #endif /* BLK_INTERNAL_H */

block/bsg-lib.c

@@ -92,7 +92,7 @@ static int bsg_transport_sg_io_fn(struct request_queue *q, struct sg_io_v4 *hdr,
 		goto out_unmap_bidi_rq;
 
 	bio = rq->bio;
-	blk_execute_rq(NULL, rq, !(hdr->flags & BSG_FLAG_Q_AT_TAIL));
+	blk_execute_rq(rq, !(hdr->flags & BSG_FLAG_Q_AT_TAIL));
 
 	/*
 	 * The assignments below don't make much sense, but are kept for

block/elevator.c

@@ -188,8 +188,10 @@ static void elevator_release(struct kobject *kobj)
 	kfree(e);
 }
 
-void __elevator_exit(struct request_queue *q, struct elevator_queue *e)
+void elevator_exit(struct request_queue *q)
 {
+	struct elevator_queue *e = q->elevator;
+
 	mutex_lock(&e->sysfs_lock);
 	blk_mq_exit_sched(q, e);
 	mutex_unlock(&e->sysfs_lock);
@@ -595,7 +597,8 @@ int elevator_switch_mq(struct request_queue *q,
 			elv_unregister_queue(q);
 
 		ioc_clear_queue(q);
-		elevator_exit(q, q->elevator);
+		blk_mq_sched_free_rqs(q);
+		elevator_exit(q);
 	}
 
 	ret = blk_mq_init_sched(q, new_e);
@@ -605,7 +608,8 @@ int elevator_switch_mq(struct request_queue *q,
 	if (new_e) {
 		ret = elv_register_queue(q, true);
 		if (ret) {
-			elevator_exit(q, q->elevator);
+			blk_mq_sched_free_rqs(q);
+			elevator_exit(q);
 			goto out;
 		}
 	}

block/kyber-iosched.c

@@ -433,6 +433,7 @@ static void kyber_exit_sched(struct elevator_queue *e)
 	int i;
 
 	del_timer_sync(&kqd->timer);
+	blk_stat_disable_accounting(kqd->q);
 
 	for (i = 0; i < KYBER_NUM_DOMAINS; i++)
 		sbitmap_queue_free(&kqd->domain_tokens[i]);

drivers/block/brd.c

@@ -405,7 +405,6 @@ static int brd_alloc(int i)
 	disk->minors		= max_part;
 	disk->fops		= &brd_fops;
 	disk->private_data	= brd;
-	disk->flags		= GENHD_FL_EXT_DEVT;
 	strlcpy(disk->disk_name, buf, DISK_NAME_LEN);
 	set_capacity(disk, rd_size * 2);