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
  ...

11 files changed, 162 insertions, 177 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index fe6bdfbbef66..0a41efe02208 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -124,7 +124,7 @@ void __bio_advance(struct bio *, unsigned bytes);
 /**
  * bio_advance - increment/complete a bio by some number of bytes
  * @bio:	bio to advance
- * @bytes:	number of bytes to complete
+ * @nbytes:	number of bytes to complete
  *
  * This updates bi_sector, bi_size and bi_idx; if the number of bytes to
  * complete doesn't align with a bvec boundary, then bv_len and bv_offset will
@@ -332,7 +332,7 @@ extern struct bio *bio_split(struct bio *bio, int sectors,
  * @gfp:	gfp mask
  * @bs:		bio set to allocate from
  *
- * Returns a bio representing the next @sectors of @bio - if the bio is smaller
+ * Return: a bio representing the next @sectors of @bio - if the bio is smaller
  * than @sectors, returns the original bio unchanged.
  */
 static inline struct bio *bio_next_split(struct bio *bio, int sectors,
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 2949d9ac7484..d319ffa59354 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -4,7 +4,6 @@
 
 #include <linux/blkdev.h>
 #include <linux/sbitmap.h>
-#include <linux/srcu.h>
 #include <linux/lockdep.h>
 #include <linux/scatterlist.h>
 #include <linux/prefetch.h>
@@ -100,7 +99,6 @@ struct request {
 		struct request *rq_next;
 	};
 
-	struct gendisk *rq_disk;
 	struct block_device *part;
 #ifdef CONFIG_BLK_RQ_ALLOC_TIME
 	/* Time that the first bio started allocating this request. */
@@ -140,7 +138,7 @@ struct request {
 	unsigned short ioprio;
 
 	enum mq_rq_state state;
-	refcount_t ref;
+	atomic_t ref;
 
 	unsigned long deadline;
 
@@ -218,6 +216,56 @@ static inline unsigned short req_get_ioprio(struct request *req)
 #define rq_dma_dir(rq) \
 	(op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE)
 
+#define rq_list_add(listptr, rq)	do {		\
+	(rq)->rq_next = *(listptr);			\
+	*(listptr) = rq;				\
+} while (0)
+
+#define rq_list_pop(listptr)				\
+({							\
+	struct request *__req = NULL;			\
+	if ((listptr) && *(listptr))	{		\
+		__req = *(listptr);			\
+		*(listptr) = __req->rq_next;		\
+	}						\
+	__req;						\
+})
+
+#define rq_list_peek(listptr)				\
+({							\
+	struct request *__req = NULL;			\
+	if ((listptr) && *(listptr))			\
+		__req = *(listptr);			\
+	__req;						\
+})
+
+#define rq_list_for_each(listptr, pos)			\
+	for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos))
+
+#define rq_list_for_each_safe(listptr, pos, nxt)			\
+	for (pos = rq_list_peek((listptr)), nxt = rq_list_next(pos);	\
+		pos; pos = nxt, nxt = pos ? rq_list_next(pos) : NULL)
+
+#define rq_list_next(rq)	(rq)->rq_next
+#define rq_list_empty(list)	((list) == (struct request *) NULL)
+
+/**
+ * rq_list_move() - move a struct request from one list to another
+ * @src: The source list @rq is currently in
+ * @dst: The destination list that @rq will be appended to
+ * @rq: The request to move
+ * @prev: The request preceding @rq in @src (NULL if @rq is the head)
+ */
+static inline void rq_list_move(struct request **src, struct request **dst,
+				struct request *rq, struct request *prev)
+{
+	if (prev)
+		prev->rq_next = rq->rq_next;
+	else
+		*src = rq->rq_next;
+	rq_list_add(dst, rq);
+}
+
 enum blk_eh_timer_return {
 	BLK_EH_DONE,		/* drivers has completed the command */
 	BLK_EH_RESET_TIMER,	/* reset timer and try again */
@@ -376,13 +424,6 @@ struct blk_mq_hw_ctx {
 	 * q->unused_hctx_list.
 	 */
 	struct list_head	hctx_list;
-
-	/**
-	 * @srcu: Sleepable RCU. Use as lock when type of the hardware queue is
-	 * blocking (BLK_MQ_F_BLOCKING). Must be the last member - see also
-	 * blk_mq_hw_ctx_size().
-	 */
-	struct srcu_struct	srcu[];
 };
 
 /**
@@ -479,8 +520,6 @@ struct blk_mq_queue_data {
 	bool last;
 };
 
-typedef bool (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *,
-		bool);
 typedef bool (busy_tag_iter_fn)(struct request *, void *, bool);
 
 /**
@@ -504,6 +543,14 @@ struct blk_mq_ops {
 	void (*commit_rqs)(struct blk_mq_hw_ctx *);
 
 	/**
+	 * @queue_rqs: Queue a list of new requests. Driver is guaranteed
+	 * that each request belongs to the same queue. If the driver doesn't
+	 * empty the @rqlist completely, then the rest will be queued
+	 * individually by the block layer upon return.
+	 */
+	void (*queue_rqs)(struct request **rqlist);
+
+	/**
 	 * @get_budget: Reserve budget before queue request, once .queue_rq is
 	 * run, it is driver's responsibility to release the
 	 * reserved budget. Also we have to handle failure case
@@ -752,6 +799,17 @@ static inline void blk_mq_set_request_complete(struct request *rq)
 	WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);
 }
 
+/*
+ * Complete the request directly instead of deferring it to softirq or
+ * completing it another CPU. Useful in preemptible instead of an interrupt.
+ */
+static inline void blk_mq_complete_request_direct(struct request *rq,
+		   void (*complete)(struct request *rq))
+{
+	WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);
+	complete(rq);
+}
+
 void blk_mq_start_request(struct request *rq);
 void blk_mq_end_request(struct request *rq, blk_status_t error);
 void __blk_mq_end_request(struct request *rq, blk_status_t error);
@@ -879,9 +937,6 @@ static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio,
 	rq->__data_len = bio->bi_iter.bi_size;
 	rq->bio = rq->biotail = bio;
 	rq->ioprio = bio_prio(bio);
-
-	if (bio->bi_bdev)
-		rq->rq_disk = bio->bi_bdev->bd_disk;
 }
 
 void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx,
@@ -917,10 +972,9 @@ int blk_rq_unmap_user(struct bio *);
 int blk_rq_map_kern(struct request_queue *, struct request *, void *,
 		unsigned int, gfp_t);
 int blk_rq_append_bio(struct request *rq, struct bio *bio);
-void blk_execute_rq_nowait(struct gendisk *, struct request *, int,
-		rq_end_io_fn *);
-blk_status_t blk_execute_rq(struct gendisk *bd_disk, struct request *rq,
-		int at_head);
+void blk_execute_rq_nowait(struct request *rq, bool at_head,
+		rq_end_io_fn *end_io);
+blk_status_t blk_execute_rq(struct request *rq, bool at_head);
 
 struct req_iterator {
 	struct bvec_iter iter;
@@ -947,7 +1001,6 @@ struct req_iterator {
  * blk_rq_pos()			: the current sector
  * blk_rq_bytes()		: bytes left in the entire request
  * blk_rq_cur_bytes()		: bytes left in the current segment
- * blk_rq_err_bytes()		: bytes left till the next error boundary
  * blk_rq_sectors()		: sectors left in the entire request
  * blk_rq_cur_sectors()		: sectors left in the current segment
  * blk_rq_stats_sectors()	: sectors of the entire request used for stats
@@ -971,8 +1024,6 @@ static inline int blk_rq_cur_bytes(const struct request *rq)
 	return bio_iovec(rq->bio).bv_len;
 }
 
-unsigned int blk_rq_err_bytes(const struct request *rq);
-
 static inline unsigned int blk_rq_sectors(const struct request *rq)
 {
 	return blk_rq_bytes(rq) >> SECTOR_SHIFT;
@@ -1135,14 +1186,4 @@ static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
 }
 #endif /* CONFIG_BLK_DEV_ZONED */
 
-#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
-# error	"You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform"
-#endif
-#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
-void rq_flush_dcache_pages(struct request *rq);
-#else
-static inline void rq_flush_dcache_pages(struct request *rq)
-{
-}
-#endif /* ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE */
 #endif /* BLK_MQ_H */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index bd4370baccca..9c95df26fc26 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -16,6 +16,7 @@
 #include <linux/percpu-refcount.h>
 #include <linux/blkzoned.h>
 #include <linux/sbitmap.h>
+#include <linux/srcu.h>
 
 struct module;
 struct request_queue;
@@ -44,7 +45,7 @@ struct blk_crypto_profile;
  */
 #define BLKCG_MAX_POLS		6
 
-static inline int blk_validate_block_size(unsigned int bsize)
+static inline int blk_validate_block_size(unsigned long bsize)
 {
 	if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize))
 		return -EINVAL;
@@ -267,7 +268,7 @@ struct request_queue {
 	int			poll_nsec;
 
 	struct blk_stat_callback	*poll_cb;
-	struct blk_rq_stat	poll_stat[BLK_MQ_POLL_STATS_BKTS];
+	struct blk_rq_stat	*poll_stat;
 
 	struct timer_list	timeout;
 	struct work_struct	timeout_work;
@@ -373,11 +374,18 @@ struct request_queue {
 	 * devices that do not have multiple independent access ranges.
 	 */
 	struct blk_independent_access_ranges *ia_ranges;
+
+	/**
+	 * @srcu: Sleepable RCU. Use as lock when type of the request queue
+	 * is blocking (BLK_MQ_F_BLOCKING). Must be the last member
+	 */
+	struct srcu_struct	srcu[];
 };
 
 /* Keep blk_queue_flag_name[] in sync with the definitions below */
 #define QUEUE_FLAG_STOPPED	0	/* queue is stopped */
 #define QUEUE_FLAG_DYING	1	/* queue being torn down */
+#define QUEUE_FLAG_HAS_SRCU	2	/* SRCU is allocated */
 #define QUEUE_FLAG_NOMERGES     3	/* disable merge attempts */
 #define QUEUE_FLAG_SAME_COMP	4	/* complete on same CPU-group */
 #define QUEUE_FLAG_FAIL_IO	5	/* fake timeout */
@@ -397,7 +405,6 @@ struct request_queue {
 #define QUEUE_FLAG_FUA		18	/* device supports FUA writes */
 #define QUEUE_FLAG_DAX		19	/* device supports DAX */
 #define QUEUE_FLAG_STATS	20	/* track IO start and completion times */
-#define QUEUE_FLAG_POLL_STATS	21	/* collecting stats for hybrid polling */
 #define QUEUE_FLAG_REGISTERED	22	/* queue has been registered to a disk */
 #define QUEUE_FLAG_QUIESCED	24	/* queue has been quiesced */
 #define QUEUE_FLAG_PCI_P2PDMA	25	/* device supports PCI p2p requests */
@@ -416,6 +423,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
 #define blk_queue_dying(q)	test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags)
+#define blk_queue_has_srcu(q)	test_bit(QUEUE_FLAG_HAS_SRCU, &(q)->queue_flags)
 #define blk_queue_dead(q)	test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags)
 #define blk_queue_init_done(q)	test_bit(QUEUE_FLAG_INIT_DONE, &(q)->queue_flags)
 #define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
@@ -1171,8 +1179,6 @@ int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned lo
 bool blk_crypto_register(struct blk_crypto_profile *profile,
 			 struct request_queue *q);
 
-void blk_crypto_unregister(struct request_queue *q);
-
 #else /* CONFIG_BLK_INLINE_ENCRYPTION */
 
 static inline bool blk_crypto_register(struct blk_crypto_profile *profile,
@@ -1181,8 +1187,6 @@ static inline bool blk_crypto_register(struct blk_crypto_profile *profile,
 	return true;
 }
 
-static inline void blk_crypto_unregister(struct request_queue *q) { }
-
 #endif /* CONFIG_BLK_INLINE_ENCRYPTION */
 
 enum blk_unique_id {
@@ -1335,33 +1339,4 @@ struct io_comp_batch {
 
 #define DEFINE_IO_COMP_BATCH(name)	struct io_comp_batch name = { }
 
-#define rq_list_add(listptr, rq)	do {		\
-	(rq)->rq_next = *(listptr);			\
-	*(listptr) = rq;				\
-} while (0)
-
-#define rq_list_pop(listptr)				\
-({							\
-	struct request *__req = NULL;			\
-	if ((listptr) && *(listptr))	{		\
-		__req = *(listptr);			\
-		*(listptr) = __req->rq_next;		\
-	}						\
-	__req;						\
-})
-
-#define rq_list_peek(listptr)				\
-({							\
-	struct request *__req = NULL;			\
-	if ((listptr) && *(listptr))			\
-		__req = *(listptr);			\
-	__req;						\
-})
-
-#define rq_list_for_each(listptr, pos)			\
-	for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos)) \
-
-#define rq_list_next(rq)	(rq)->rq_next
-#define rq_list_empty(list)	((list) == (struct request *) NULL)
-
 #endif /* _LINUX_BLKDEV_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 493b87e3616b..58e911cb3885 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2786,8 +2786,6 @@ static inline int filemap_fdatawait(struct address_space *mapping)
 
 extern bool filemap_range_has_page(struct address_space *, loff_t lstart,
 				  loff_t lend);
-extern bool filemap_range_needs_writeback(struct address_space *,
-					  loff_t lstart, loff_t lend);
 extern int filemap_write_and_wait_range(struct address_space *mapping,
 				        loff_t lstart, loff_t lend);
 extern int __filemap_fdatawrite_range(struct address_space *mapping,
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 74c410263113..6906a45bc761 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -39,57 +39,24 @@ struct partition_meta_info {
 /**
  * DOC: genhd capability flags
  *
- * ``GENHD_FL_REMOVABLE`` (0x0001): indicates that the block device
- * gives access to removable media.
- * When set, the device remains present even when media is not
- * inserted.
- * Must not be set for devices which are removed entirely when the
+ * ``GENHD_FL_REMOVABLE``: indicates that the block device gives access to
+ * removable media.  When set, the device remains present even when media is not
+ * inserted.  Shall not be set for devices which are removed entirely when the
  * media is removed.
  *
- * ``GENHD_FL_CD`` (0x0008): the block device is a CD-ROM-style
- * device.
- * Affects responses to the ``CDROM_GET_CAPABILITY`` ioctl.
+ * ``GENHD_FL_HIDDEN``: the block device is hidden; it doesn't produce events,
+ * doesn't appear in sysfs, and can't be opened from userspace or using
+ * blkdev_get*. Used for the underlying components of multipath devices.
  *
- * ``GENHD_FL_SUPPRESS_PARTITION_INFO`` (0x0020): don't include
- * partition information in ``/proc/partitions`` or in the output of
- * printk_all_partitions().
- * Used for the null block device and some MMC devices.
+ * ``GENHD_FL_NO_PART``: partition support is disabled.  The kernel will not
+ * scan for partitions from add_disk, and users can't add partitions manually.
  *
- * ``GENHD_FL_EXT_DEVT`` (0x0040): the driver supports extended
- * dynamic ``dev_t``, i.e. it wants extended device numbers
- * (``BLOCK_EXT_MAJOR``).
- * This affects the maximum number of partitions.
- *
- * ``GENHD_FL_NATIVE_CAPACITY`` (0x0080): based on information in the
- * partition table, the device's capacity has been extended to its
- * native capacity; i.e. the device has hidden capacity used by one
- * of the partitions (this is a flag used so that native capacity is
- * only ever unlocked once).
- *
- * ``GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE`` (0x0100): event polling is
- * blocked whenever a writer holds an exclusive lock.
- *
- * ``GENHD_FL_NO_PART_SCAN`` (0x0200): partition scanning is disabled.
- * Used for loop devices in their default settings and some MMC
- * devices.
- *
- * ``GENHD_FL_HIDDEN`` (0x0400): the block device is hidden; it
- * doesn't produce events, doesn't appear in sysfs, and doesn't have
- * an associated ``bdev``.
- * Implies ``GENHD_FL_SUPPRESS_PARTITION_INFO`` and
- * ``GENHD_FL_NO_PART_SCAN``.
- * Used for multipath devices.
  */
-#define GENHD_FL_REMOVABLE			0x0001
-/* 2 is unused (used to be GENHD_FL_DRIVERFS) */
-/* 4 is unused (used to be GENHD_FL_MEDIA_CHANGE_NOTIFY) */
-#define GENHD_FL_CD				0x0008
-#define GENHD_FL_SUPPRESS_PARTITION_INFO	0x0020
-#define GENHD_FL_EXT_DEVT			0x0040
-#define GENHD_FL_NATIVE_CAPACITY		0x0080
-#define GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE	0x0100
-#define GENHD_FL_NO_PART_SCAN			0x0200
-#define GENHD_FL_HIDDEN				0x0400
+enum {
+	GENHD_FL_REMOVABLE			= 1 << 0,
+	GENHD_FL_HIDDEN				= 1 << 1,
+	GENHD_FL_NO_PART			= 1 << 2,
+};
 
 enum {
 	DISK_EVENT_MEDIA_CHANGE			= 1 << 0, /* media changed */
@@ -101,6 +68,8 @@ enum {
 	DISK_EVENT_FLAG_POLL			= 1 << 0,
 	/* Forward events to udev */
 	DISK_EVENT_FLAG_UEVENT			= 1 << 1,
+	/* Block event polling when open for exclusive write */
+	DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE	= 1 << 2,
 };
 
 struct disk_events;
@@ -115,13 +84,13 @@ struct blk_integrity {
 };
 
 struct gendisk {
-	/* major, first_minor and minors are input parameters only,
-	 * don't use directly.  Use disk_devt() and disk_max_parts().
+	/*
+	 * major/first_minor/minors should not be set by any new driver, the
+	 * block core will take care of allocating them automatically.
 	 */
-	int major;			/* major number of driver */
+	int major;
 	int first_minor;
-	int minors;                     /* maximum number of minors, =1 for
-                                         * disks that can't be partitioned. */
+	int minors;
 
 	char disk_name[DISK_NAME_LEN];	/* name of major driver */
 
@@ -140,6 +109,7 @@ struct gendisk {
 #define GD_NEED_PART_SCAN		0
 #define GD_READ_ONLY			1
 #define GD_DEAD				2
+#define GD_NATIVE_CAPACITY		3
 
 	struct mutex open_mutex;	/* open/close mutex */
 	unsigned open_partitions;	/* number of open partitions */
@@ -184,19 +154,6 @@ static inline bool disk_live(struct gendisk *disk)
 #define disk_to_cdi(disk)	NULL
 #endif
 
-static inline int disk_max_parts(struct gendisk *disk)
-{
-	if (disk->flags & GENHD_FL_EXT_DEVT)
-		return DISK_MAX_PARTS;
-	return disk->minors;
-}
-
-static inline bool disk_part_scan_enabled(struct gendisk *disk)
-{
-	return disk_max_parts(disk) > 1 &&
-		!(disk->flags & GENHD_FL_NO_PART_SCAN);
-}
-
 static inline dev_t disk_devt(struct gendisk *disk)
 {
 	return MKDEV(disk->major, disk->first_minor);
diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h
index 0a9dc40b7be8..14f7eaf1b443 100644
--- a/include/linux/iocontext.h
+++ b/include/linux/iocontext.h
@@ -99,55 +99,40 @@ struct io_cq {
 struct io_context {
 	atomic_long_t refcount;
 	atomic_t active_ref;
-	atomic_t nr_tasks;
 
+	unsigned short ioprio;
+
+#ifdef CONFIG_BLK_ICQ
 	/* all the fields below are protected by this lock */
 	spinlock_t lock;
 
-	unsigned short ioprio;
-
 	struct radix_tree_root	icq_tree;
 	struct io_cq __rcu	*icq_hint;
 	struct hlist_head	icq_list;
 
 	struct work_struct release_work;
+#endif /* CONFIG_BLK_ICQ */
 };
 
-/**
- * get_io_context_active - get active reference on ioc
- * @ioc: ioc of interest
- *
- * Only iocs with active reference can issue new IOs.  This function
- * acquires an active reference on @ioc.  The caller must already have an
- * active reference on @ioc.
- */
-static inline void get_io_context_active(struct io_context *ioc)
-{
-	WARN_ON_ONCE(atomic_long_read(&ioc->refcount) <= 0);
-	WARN_ON_ONCE(atomic_read(&ioc->active_ref) <= 0);
-	atomic_long_inc(&ioc->refcount);
-	atomic_inc(&ioc->active_ref);
-}
-
-static inline void ioc_task_link(struct io_context *ioc)
-{
-	get_io_context_active(ioc);
-
-	WARN_ON_ONCE(atomic_read(&ioc->nr_tasks) <= 0);
-	atomic_inc(&ioc->nr_tasks);
-}
-
 struct task_struct;
 #ifdef CONFIG_BLOCK
 void put_io_context(struct io_context *ioc);
-void put_io_context_active(struct io_context *ioc);
 void exit_io_context(struct task_struct *task);
-struct io_context *get_task_io_context(struct task_struct *task,
-				       gfp_t gfp_flags, int node);
+int __copy_io(unsigned long clone_flags, struct task_struct *tsk);
+static inline int copy_io(unsigned long clone_flags, struct task_struct *tsk)
+{
+	if (!current->io_context)
+		return 0;
+	return __copy_io(clone_flags, tsk);
+}
 #else
 struct io_context;
 static inline void put_io_context(struct io_context *ioc) { }
 static inline void exit_io_context(struct task_struct *task) { }
-#endif
+static inline int copy_io(unsigned long clone_flags, struct task_struct *tsk)
+{
+	return 0;
+}
+#endif /* CONFIG_BLOCK */
 
-#endif
+#endif /* IOCONTEXT_H */
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index d150a9082b31..422bdf9f4e76 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -962,6 +962,35 @@ static inline int add_to_page_cache(struct page *page,
 int __filemap_add_folio(struct address_space *mapping, struct folio *folio,
 		pgoff_t index, gfp_t gfp, void **shadowp);
 
+bool filemap_range_has_writeback(struct address_space *mapping,
+				 loff_t start_byte, loff_t end_byte);
+
+/**
+ * filemap_range_needs_writeback - check if range potentially needs writeback
+ * @mapping:           address space within which to check
+ * @start_byte:        offset in bytes where the range starts
+ * @end_byte:          offset in bytes where the range ends (inclusive)
+ *
+ * Find at least one page in the range supplied, usually used to check if
+ * direct writing in this range will trigger a writeback. Used by O_DIRECT
+ * read/write with IOCB_NOWAIT, to see if the caller needs to do
+ * filemap_write_and_wait_range() before proceeding.
+ *
+ * Return: %true if the caller should do filemap_write_and_wait_range() before
+ * doing O_DIRECT to a page in this range, %false otherwise.
+ */
+static inline bool filemap_range_needs_writeback(struct address_space *mapping,
+						 loff_t start_byte,
+						 loff_t end_byte)
+{
+	if (!mapping->nrpages)
+		return false;
+	if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) &&
+	    !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK))
+		return false;
+	return filemap_range_has_writeback(mapping, start_byte, end_byte);
+}
+
 /**
  * struct readahead_control - Describes a readahead request.
  *
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index 477a800a9543..6794d7322cbd 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -164,7 +164,7 @@ static inline struct scsi_driver *scsi_cmd_to_driver(struct scsi_cmnd *cmd)
 {
 	struct request *rq = scsi_cmd_to_rq(cmd);
 
-	return *(struct scsi_driver **)rq->rq_disk->private_data;
+	return *(struct scsi_driver **)rq->q->disk->private_data;
 }
 
 void scsi_done(struct scsi_cmnd *cmd);
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index d1c6fc83b1e3..ab7557d84f75 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -275,9 +275,9 @@ scmd_printk(const char *, const struct scsi_cmnd *, const char *, ...);
 	do {								\
 		struct request *__rq = scsi_cmd_to_rq((scmd));		\
 									\
-		if (__rq->rq_disk)					\
+		if (__rq->q->disk)					\
 			sdev_dbg((scmd)->device, "[%s] " fmt,		\
-				 __rq->rq_disk->disk_name, ##a);	\
+				 __rq->q->disk->disk_name, ##a);	\
 		else							\
 			sdev_dbg((scmd)->device, fmt, ##a);		\
 	} while (0)
diff --git a/include/scsi/scsi_ioctl.h b/include/scsi/scsi_ioctl.h
index d2cb9aeaf1f1..beac64e38b87 100644
--- a/include/scsi/scsi_ioctl.h
+++ b/include/scsi/scsi_ioctl.h
@@ -45,8 +45,8 @@ typedef struct scsi_fctargaddress {
 
 int scsi_ioctl_block_when_processing_errors(struct scsi_device *sdev,
 		int cmd, bool ndelay);
-int scsi_ioctl(struct scsi_device *sdev, struct gendisk *disk, fmode_t mode,
-		int cmd, void __user *arg);
+int scsi_ioctl(struct scsi_device *sdev, fmode_t mode, int cmd,
+		void __user *arg);
 int get_sg_io_hdr(struct sg_io_hdr *hdr, const void __user *argp);
 int put_sg_io_hdr(const struct sg_io_hdr *hdr, void __user *argp);
 bool scsi_cmd_allowed(unsigned char *cmd, fmode_t mode);
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index a95daa4d4caa..27170e40e8c9 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -85,7 +85,7 @@ TRACE_EVENT(block_rq_requeue,
 	),
 
 	TP_fast_assign(
-		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->dev	   = rq->q->disk ? disk_devt(rq->q->disk) : 0;
 		__entry->sector    = blk_rq_trace_sector(rq);
 		__entry->nr_sector = blk_rq_trace_nr_sectors(rq);
 
@@ -128,7 +128,7 @@ TRACE_EVENT(block_rq_complete,
 	),
 
 	TP_fast_assign(
-		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->dev	   = rq->q->disk ? disk_devt(rq->q->disk) : 0;
 		__entry->sector    = blk_rq_pos(rq);
 		__entry->nr_sector = nr_bytes >> 9;
 		__entry->error     = blk_status_to_errno(error);
@@ -161,7 +161,7 @@ DECLARE_EVENT_CLASS(block_rq,
 	),
 
 	TP_fast_assign(
-		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->dev	   = rq->q->disk ? disk_devt(rq->q->disk) : 0;
 		__entry->sector    = blk_rq_trace_sector(rq);
 		__entry->nr_sector = blk_rq_trace_nr_sectors(rq);
 		__entry->bytes     = blk_rq_bytes(rq);
@@ -512,7 +512,7 @@ TRACE_EVENT(block_rq_remap,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= disk_devt(rq->rq_disk);
+		__entry->dev		= disk_devt(rq->q->disk);
 		__entry->sector		= blk_rq_pos(rq);
 		__entry->nr_sector	= blk_rq_sectors(rq);
 		__entry->old_dev	= dev;