Merge tag 'for-6.2/block-2022-12-08' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe pull requests via Christoph:
      - Support some passthrough commands without CAP_SYS_ADMIN (Kanchan
        Joshi)
      - Refactor PCIe probing and reset (Christoph Hellwig)
      - Various fabrics authentication fixes and improvements (Sagi
        Grimberg)
      - Avoid fallback to sequential scan due to transient issues (Uday
        Shankar)
      - Implement support for the DEAC bit in Write Zeroes (Christoph
        Hellwig)
      - Allow overriding the IEEE OUI and firmware revision in configfs
        for nvmet (Aleksandr Miloserdov)
      - Force reconnect when number of queue changes in nvmet (Daniel
        Wagner)
      - Minor fixes and improvements (Uros Bizjak, Joel Granados, Sagi
        Grimberg, Christoph Hellwig, Christophe JAILLET)
      - Fix and cleanup nvme-fc req allocation (Chaitanya Kulkarni)
      - Use the common tagset helpers in nvme-pci driver (Christoph
        Hellwig)
      - Cleanup the nvme-pci removal path (Christoph Hellwig)
      - Use kstrtobool() instead of strtobool (Christophe JAILLET)
      - Allow unprivileged passthrough of Identify Controller (Joel
        Granados)
      - Support io stats on the mpath device (Sagi Grimberg)
      - Minor nvmet cleanup (Sagi Grimberg)

 - MD pull requests via Song:
      - Code cleanups (Christoph)
      - Various fixes

 - Floppy pull request from Denis:
      - Fix a memory leak in the init error path (Yuan)

 - Series fixing some batch wakeup issues with sbitmap (Gabriel)

 - Removal of the pktcdvd driver that was deprecated more than 5 years
   ago, and subsequent removal of the devnode callback in struct
   block_device_operations as no users are now left (Greg)

 - Fix for partition read on an exclusively opened bdev (Jan)

 - Series of elevator API cleanups (Jinlong, Christoph)

 - Series of fixes and cleanups for blk-iocost (Kemeng)

 - Series of fixes and cleanups for blk-throttle (Kemeng)

 - Series adding concurrent support for sync queues in BFQ (Yu)

 - Series bringing drbd a bit closer to the out-of-tree maintained
   version (Christian, Joel, Lars, Philipp)

 - Misc drbd fixes (Wang)

 - blk-wbt fixes and tweaks for enable/disable (Yu)

 - Fixes for mq-deadline for zoned devices (Damien)

 - Add support for read-only and offline zones for null_blk
   (Shin'ichiro)

 - Series fixing the delayed holder tracking, as used by DM (Yu,
   Christoph)

 - Series enabling bio alloc caching for IRQ based IO (Pavel)

 - Series enabling userspace peer-to-peer DMA (Logan)

 - BFQ waker fixes (Khazhismel)

 - Series fixing elevator refcount issues (Christoph, Jinlong)

 - Series cleaning up references around queue destruction (Christoph)

 - Series doing quiesce by tagset, enabling cleanups in drivers
   (Christoph, Chao)

 - Series untangling the queue kobject and queue references (Christoph)

 - Misc fixes and cleanups (Bart, David, Dawei, Jinlong, Kemeng, Ye,
   Yang, Waiman, Shin'ichiro, Randy, Pankaj, Christoph)

* tag 'for-6.2/block-2022-12-08' of git://git.kernel.dk/linux: (247 commits)
  blktrace: Fix output non-blktrace event when blk_classic option enabled
  block: sed-opal: Don't include <linux/kernel.h>
  sed-opal: allow using IOC_OPAL_SAVE for locking too
  blk-cgroup: Fix typo in comment
  block: remove bio_set_op_attrs
  nvmet: don't open-code NVME_NS_ATTR_RO enumeration
  nvme-pci: use the tagset alloc/free helpers
  nvme: add the Apple shared tag workaround to nvme_alloc_io_tag_set
  nvme: only set reserved_tags in nvme_alloc_io_tag_set for fabrics controllers
  nvme: consolidate setting the tagset flags
  nvme: pass nr_maps explicitly to nvme_alloc_io_tag_set
  block: bio_copy_data_iter
  nvme-pci: split out a nvme_pci_ctrl_is_dead helper
  nvme-pci: return early on ctrl state mismatch in nvme_reset_work
  nvme-pci: rename nvme_disable_io_queues
  nvme-pci: cleanup nvme_suspend_queue
  nvme-pci: remove nvme_pci_disable
  nvme-pci: remove nvme_disable_admin_queue
  nvme: merge nvme_shutdown_ctrl into nvme_disable_ctrl
  nvme: use nvme_wait_ready in nvme_shutdown_ctrl
  ...

20 files changed, 81 insertions, 387 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 2c5806997bbf..b231a665682a 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -475,8 +475,6 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty);
 extern void bio_set_pages_dirty(struct bio *bio);
 extern void bio_check_pages_dirty(struct bio *bio);
 
-extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
-			       struct bio *src, struct bvec_iter *src_iter);
 extern void bio_copy_data(struct bio *dst, struct bio *src);
 extern void bio_free_pages(struct bio *bio);
 void guard_bio_eod(struct bio *bio);
diff --git a/include/linux/blk-crypto-profile.h b/include/linux/blk-crypto-profile.h
index bbab65bd5428..e6802b69cdd6 100644
--- a/include/linux/blk-crypto-profile.h
+++ b/include/linux/blk-crypto-profile.h
@@ -138,18 +138,6 @@ int devm_blk_crypto_profile_init(struct device *dev,
 
 unsigned int blk_crypto_keyslot_index(struct blk_crypto_keyslot *slot);
 
-blk_status_t blk_crypto_get_keyslot(struct blk_crypto_profile *profile,
-				    const struct blk_crypto_key *key,
-				    struct blk_crypto_keyslot **slot_ptr);
-
-void blk_crypto_put_keyslot(struct blk_crypto_keyslot *slot);
-
-bool __blk_crypto_cfg_supported(struct blk_crypto_profile *profile,
-				const struct blk_crypto_config *cfg);
-
-int __blk_crypto_evict_key(struct blk_crypto_profile *profile,
-			   const struct blk_crypto_key *key);
-
 void blk_crypto_reprogram_all_keys(struct blk_crypto_profile *profile);
 
 void blk_crypto_profile_destroy(struct blk_crypto_profile *profile);
diff --git a/include/linux/blk-crypto.h b/include/linux/blk-crypto.h
index 26b1b71c3091..1e3e5d0adf12 100644
--- a/include/linux/blk-crypto.h
+++ b/include/linux/blk-crypto.h
@@ -72,9 +72,6 @@ struct bio_crypt_ctx {
 #include <linux/blk_types.h>
 #include <linux/blkdev.h>
 
-struct request;
-struct request_queue;
-
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION
 
 static inline bool bio_has_crypt_ctx(struct bio *bio)
@@ -95,13 +92,15 @@ int blk_crypto_init_key(struct blk_crypto_key *blk_key, const u8 *raw_key,
 			unsigned int dun_bytes,
 			unsigned int data_unit_size);
 
-int blk_crypto_start_using_key(const struct blk_crypto_key *key,
-			       struct request_queue *q);
+int blk_crypto_start_using_key(struct block_device *bdev,
+			       const struct blk_crypto_key *key);
 
-int blk_crypto_evict_key(struct request_queue *q,
+int blk_crypto_evict_key(struct block_device *bdev,
 			 const struct blk_crypto_key *key);
 
-bool blk_crypto_config_supported(struct request_queue *q,
+bool blk_crypto_config_supported_natively(struct block_device *bdev,
+					  const struct blk_crypto_config *cfg);
+bool blk_crypto_config_supported(struct block_device *bdev,
 				 const struct blk_crypto_config *cfg);
 
 #else /* CONFIG_BLK_INLINE_ENCRYPTION */
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index d6119c5d1069..779fba613bd0 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -7,6 +7,7 @@
 #include <linux/lockdep.h>
 #include <linux/scatterlist.h>
 #include <linux/prefetch.h>
+#include <linux/srcu.h>
 
 struct blk_mq_tags;
 struct blk_flush_queue;
@@ -140,7 +141,6 @@ struct request {
 	struct blk_crypto_keyslot *crypt_keyslot;
 #endif
 
-	unsigned short write_hint;
 	unsigned short ioprio;
 
 	enum mq_rq_state state;
@@ -501,6 +501,8 @@ enum hctx_type {
  * @tag_list_lock: Serializes tag_list accesses.
  * @tag_list:	   List of the request queues that use this tag set. See also
  *		   request_queue.tag_set_list.
+ * @srcu:	   Use as lock when type of the request queue is blocking
+ *		   (BLK_MQ_F_BLOCKING).
  */
 struct blk_mq_tag_set {
 	struct blk_mq_queue_map	map[HCTX_MAX_TYPES];
@@ -521,6 +523,7 @@ struct blk_mq_tag_set {
 
 	struct mutex		tag_list_lock;
 	struct list_head	tag_list;
+	struct srcu_struct	*srcu;
 };
 
 /**
@@ -878,7 +881,9 @@ void blk_mq_start_hw_queues(struct request_queue *q);
 void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
 void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async);
 void blk_mq_quiesce_queue(struct request_queue *q);
-void blk_mq_wait_quiesce_done(struct request_queue *q);
+void blk_mq_wait_quiesce_done(struct blk_mq_tag_set *set);
+void blk_mq_quiesce_tagset(struct blk_mq_tag_set *set);
+void blk_mq_unquiesce_tagset(struct blk_mq_tag_set *set);
 void blk_mq_unquiesce_queue(struct request_queue *q);
 void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
 void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index e0b098089ef2..99be590f952f 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -472,13 +472,6 @@ static inline enum req_op bio_op(const struct bio *bio)
 	return bio->bi_opf & REQ_OP_MASK;
 }
 
-/* obsolete, don't use in new code */
-static inline void bio_set_op_attrs(struct bio *bio, enum req_op op,
-				    blk_opf_t op_flags)
-{
-	bio->bi_opf = op | op_flags;
-}
-
 static inline bool op_is_write(blk_opf_t op)
 {
 	return !!(op & (__force blk_opf_t)1);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 891f8cbcd043..301cf1cf4f2f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -22,7 +22,6 @@
 #include <linux/blkzoned.h>
 #include <linux/sched.h>
 #include <linux/sbitmap.h>
-#include <linux/srcu.h>
 #include <linux/uuid.h>
 #include <linux/xarray.h>
 
@@ -156,6 +155,7 @@ struct gendisk {
 	unsigned open_partitions;	/* number of open partitions */
 
 	struct backing_dev_info	*bdi;
+	struct kobject queue_kobj;	/* the queue/ directory */
 	struct kobject *slave_dir;
 #ifdef CONFIG_BLOCK_HOLDER_DEPRECATED
 	struct list_head slave_bdevs;
@@ -438,10 +438,7 @@ struct request_queue {
 
 	struct gendisk		*disk;
 
-	/*
-	 * queue kobject
-	 */
-	struct kobject kobj;
+	refcount_t		refs;
 
 	/*
 	 * mq queue kobject
@@ -544,18 +541,11 @@ struct request_queue {
 	struct mutex		debugfs_mutex;
 
 	bool			mq_sysfs_init_done;
-
-	/**
-	 * @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 */
@@ -580,6 +570,7 @@ struct request_queue {
 #define QUEUE_FLAG_HCTX_ACTIVE	28	/* at least one blk-mq hctx is active */
 #define QUEUE_FLAG_NOWAIT       29	/* device supports NOWAIT */
 #define QUEUE_FLAG_SQ_SCHED     30	/* single queue style io dispatch */
+#define QUEUE_FLAG_SKIP_TAGSET_QUIESCE	31 /* quiesce_tagset skip the queue*/
 
 #define QUEUE_FLAG_MQ_DEFAULT	((1UL << QUEUE_FLAG_IO_STAT) |		\
 				 (1UL << QUEUE_FLAG_SAME_COMP) |	\
@@ -591,7 +582,6 @@ 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_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)
 #define blk_queue_noxmerges(q)	\
@@ -620,6 +610,8 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 #define blk_queue_pm_only(q)	atomic_read(&(q)->pm_only)
 #define blk_queue_registered(q)	test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags)
 #define blk_queue_sq_sched(q)	test_bit(QUEUE_FLAG_SQ_SCHED, &(q)->queue_flags)
+#define blk_queue_skip_tagset_quiesce(q) \
+	test_bit(QUEUE_FLAG_SKIP_TAGSET_QUIESCE, &(q)->queue_flags)
 
 extern void blk_set_pm_only(struct request_queue *q);
 extern void blk_clear_pm_only(struct request_queue *q);
@@ -840,7 +832,6 @@ void set_capacity(struct gendisk *disk, sector_t size);
 #ifdef CONFIG_BLOCK_HOLDER_DEPRECATED
 int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
 void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk);
-int bd_register_pending_holders(struct gendisk *disk);
 #else
 static inline int bd_link_disk_holder(struct block_device *bdev,
 				      struct gendisk *disk)
@@ -851,10 +842,6 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev,
 					 struct gendisk *disk)
 {
 }
-static inline int bd_register_pending_holders(struct gendisk *disk)
-{
-	return 0;
-}
 #endif /* CONFIG_BLOCK_HOLDER_DEPRECATED */
 
 dev_t part_devt(struct gendisk *disk, u8 partno);
@@ -1349,12 +1336,7 @@ static inline int blk_rq_aligned(struct request_queue *q, unsigned long addr,
 /* assumes size > 256 */
 static inline unsigned int blksize_bits(unsigned int size)
 {
-	unsigned int bits = 8;
-	do {
-		bits++;
-		size >>= 1;
-	} while (size > 256);
-	return bits;
+	return order_base_2(size >> SECTOR_SHIFT) + SECTOR_SHIFT;
 }
 
 static inline unsigned int block_size(struct block_device *bdev)
@@ -1413,7 +1395,6 @@ struct block_device_operations {
 	void (*swap_slot_free_notify) (struct block_device *, unsigned long);
 	int (*report_zones)(struct gendisk *, sector_t sector,
 			unsigned int nr_zones, report_zones_cb cb, void *data);
-	char *(*devnode)(struct gendisk *disk, umode_t *mode);
 	/* returns the length of the identifier or a negative errno: */
 	int (*get_unique_id)(struct gendisk *disk, u8 id[16],
 			enum blk_unique_id id_type);
@@ -1458,7 +1439,6 @@ unsigned long bdev_start_io_acct(struct block_device *bdev,
 void bdev_end_io_acct(struct block_device *bdev, enum req_op op,
 		unsigned long start_time);
 
-void bio_start_io_acct_time(struct bio *bio, unsigned long start_time);
 unsigned long bio_start_io_acct(struct bio *bio);
 void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time,
 		struct block_device *orig_bdev);
diff --git a/include/linux/lru_cache.h b/include/linux/lru_cache.h
index 07add7882a5d..c9afcdd9324c 100644
--- a/include/linux/lru_cache.h
+++ b/include/linux/lru_cache.h
@@ -199,7 +199,6 @@ struct lru_cache {
 	unsigned long flags;
 
 
-	void  *lc_private;
 	const char *name;
 
 	/* nr_elements there */
@@ -241,7 +240,6 @@ extern struct lru_cache *lc_create(const char *name, struct kmem_cache *cache,
 		unsigned e_count, size_t e_size, size_t e_off);
 extern void lc_reset(struct lru_cache *lc);
 extern void lc_destroy(struct lru_cache *lc);
-extern void lc_set(struct lru_cache *lc, unsigned int enr, int index);
 extern void lc_del(struct lru_cache *lc, struct lc_element *element);
 
 extern struct lc_element *lc_get_cumulative(struct lru_cache *lc, unsigned int enr);
@@ -297,6 +295,5 @@ extern bool lc_is_used(struct lru_cache *lc, unsigned int enr);
 	container_of(ptr, type, member)
 
 extern struct lc_element *lc_element_by_index(struct lru_cache *lc, unsigned i);
-extern unsigned int lc_index_of(struct lru_cache *lc, struct lc_element *e);
 
 #endif
diff --git a/include/linux/mempool.h b/include/linux/mempool.h
index 0c964ac107c2..4aae6c06c5f2 100644
--- a/include/linux/mempool.h
+++ b/include/linux/mempool.h
@@ -30,6 +30,11 @@ static inline bool mempool_initialized(mempool_t *pool)
 	return pool->elements != NULL;
 }
 
+static inline bool mempool_is_saturated(mempool_t *pool)
+{
+	return READ_ONCE(pool->curr_nr) >= pool->min_nr;
+}
+
 void mempool_exit(mempool_t *pool);
 int mempool_init_node(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn,
 		      mempool_free_t *free_fn, void *pool_data,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 974ccca609d2..6a05a3bc0a28 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1129,7 +1129,7 @@ static inline void get_page(struct page *page)
 	folio_get(page_folio(page));
 }
 
-bool __must_check try_grab_page(struct page *page, unsigned int flags);
+int __must_check try_grab_page(struct page *page, unsigned int flags);
 
 static inline __must_check bool try_get_page(struct page *page)
 {
@@ -2979,6 +2979,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 #define FOLL_SPLIT_PMD	0x20000	/* split huge pmd before returning */
 #define FOLL_PIN	0x40000	/* pages must be released via unpin_user_page */
 #define FOLL_FAST_ONLY	0x80000	/* gup_fast: prevent fall-back to slow gup */
+#define FOLL_PCI_P2PDMA	0x100000 /* allow returning PCI P2PDMA pages */
 
 /*
  * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 5f74891556f3..9c49ec5d0e25 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -986,6 +986,25 @@ static inline bool is_zone_device_page(const struct page *page)
 {
 	return page_zonenum(page) == ZONE_DEVICE;
 }
+
+/*
+ * Consecutive zone device pages should not be merged into the same sgl
+ * or bvec segment with other types of pages or if they belong to different
+ * pgmaps. Otherwise getting the pgmap of a given segment is not possible
+ * without scanning the entire segment. This helper returns true either if
+ * both pages are not zone device pages or both pages are zone device pages
+ * with the same pgmap.
+ */
+static inline bool zone_device_pages_have_same_pgmap(const struct page *a,
+						     const struct page *b)
+{
+	if (is_zone_device_page(a) != is_zone_device_page(b))
+		return false;
+	if (!is_zone_device_page(a))
+		return true;
+	return a->pgmap == b->pgmap;
+}
+
 extern void memmap_init_zone_device(struct zone *, unsigned long,
 				    unsigned long, struct dev_pagemap *);
 #else
@@ -993,6 +1012,11 @@ static inline bool is_zone_device_page(const struct page *page)
 {
 	return false;
 }
+static inline bool zone_device_pages_have_same_pgmap(const struct page *a,
+						     const struct page *b)
+{
+	return true;
+}
 #endif
 
 static inline bool folio_is_zone_device(const struct folio *folio)
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 050d7d0cd81b..d6be2a686100 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -797,6 +797,7 @@ enum nvme_opcode {
 	nvme_cmd_zone_mgmt_send	= 0x79,
 	nvme_cmd_zone_mgmt_recv	= 0x7a,
 	nvme_cmd_zone_append	= 0x7d,
+	nvme_cmd_vendor_start	= 0x80,
 };
 
 #define nvme_opcode_name(opcode)	{ opcode, #opcode }
@@ -963,6 +964,7 @@ enum {
 	NVME_RW_PRINFO_PRCHK_GUARD	= 1 << 12,
 	NVME_RW_PRINFO_PRACT		= 1 << 13,
 	NVME_RW_DTYPE_STREAMS		= 1 << 4,
+	NVME_WZ_DEAC			= 1 << 9,
 };
 
 struct nvme_dsm_cmd {
diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h
deleted file mode 100644
index f9c5ac80d59b..000000000000
--- a/include/linux/pktcdvd.h
+++ /dev/null
@@ -1,197 +0,0 @@
-/*
- * Copyright (C) 2000 Jens Axboe <axboe@suse.de>
- * Copyright (C) 2001-2004 Peter Osterlund <petero2@telia.com>
- *
- * May be copied or modified under the terms of the GNU General Public
- * License.  See linux/COPYING for more information.
- *
- * Packet writing layer for ATAPI and SCSI CD-R, CD-RW, DVD-R, and
- * DVD-RW devices.
- *
- */
-#ifndef __PKTCDVD_H
-#define __PKTCDVD_H
-
-#include <linux/blkdev.h>
-#include <linux/completion.h>
-#include <linux/cdrom.h>
-#include <linux/kobject.h>
-#include <linux/sysfs.h>
-#include <linux/mempool.h>
-#include <uapi/linux/pktcdvd.h>
-
-/* default bio write queue congestion marks */
-#define PKT_WRITE_CONGESTION_ON    10000
-#define PKT_WRITE_CONGESTION_OFF   9000
-
-
-struct packet_settings
-{
-	__u32			size;		/* packet size in (512 byte) sectors */
-	__u8			fp;		/* fixed packets */
-	__u8			link_loss;	/* the rest is specified
-						 * as per Mt Fuji */
-	__u8			write_type;
-	__u8			track_mode;
-	__u8			block_mode;
-};
-
-/*
- * Very crude stats for now
- */
-struct packet_stats
-{
-	unsigned long		pkt_started;
-	unsigned long		pkt_ended;
-	unsigned long		secs_w;
-	unsigned long		secs_rg;
-	unsigned long		secs_r;
-};
-
-struct packet_cdrw
-{
-	struct list_head	pkt_free_list;
-	struct list_head	pkt_active_list;
-	spinlock_t		active_list_lock; /* Serialize access to pkt_active_list */
-	struct task_struct	*thread;
-	atomic_t		pending_bios;
-};
-
-/*
- * Switch to high speed reading after reading this many kilobytes
- * with no interspersed writes.
- */
-#define HI_SPEED_SWITCH 512
-
-struct packet_iosched
-{
-	atomic_t		attention;	/* Set to non-zero when queue processing is needed */
-	int			writing;	/* Non-zero when writing, zero when reading */
-	spinlock_t		lock;		/* Protecting read/write queue manipulations */
-	struct bio_list		read_queue;
-	struct bio_list		write_queue;
-	sector_t		last_write;	/* The sector where the last write ended */
-	int			successive_reads;
-};
-
-/*
- * 32 buffers of 2048 bytes
- */
-#if (PAGE_SIZE % CD_FRAMESIZE) != 0
-#error "PAGE_SIZE must be a multiple of CD_FRAMESIZE"
-#endif
-#define PACKET_MAX_SIZE		128
-#define FRAMES_PER_PAGE		(PAGE_SIZE / CD_FRAMESIZE)
-#define PACKET_MAX_SECTORS	(PACKET_MAX_SIZE * CD_FRAMESIZE >> 9)
-
-enum packet_data_state {
-	PACKET_IDLE_STATE,			/* Not used at the moment */
-	PACKET_WAITING_STATE,			/* Waiting for more bios to arrive, so */
-						/* we don't have to do as much */
-						/* data gathering */
-	PACKET_READ_WAIT_STATE,			/* Waiting for reads to fill in holes */
-	PACKET_WRITE_WAIT_STATE,		/* Waiting for the write to complete */
-	PACKET_RECOVERY_STATE,			/* Recover after read/write errors */
-	PACKET_FINISHED_STATE,			/* After write has finished */
-
-	PACKET_NUM_STATES			/* Number of possible states */
-};
-
-/*
- * Information needed for writing a single packet
- */
-struct pktcdvd_device;
-
-struct packet_data
-{
-	struct list_head	list;
-
-	spinlock_t		lock;		/* Lock protecting state transitions and */
-						/* orig_bios list */
-
-	struct bio_list		orig_bios;	/* Original bios passed to pkt_make_request */
-						/* that will be handled by this packet */
-	int			write_size;	/* Total size of all bios in the orig_bios */
-						/* list, measured in number of frames */
-
-	struct bio		*w_bio;		/* The bio we will send to the real CD */
-						/* device once we have all data for the */
-						/* packet we are going to write */
-	sector_t		sector;		/* First sector in this packet */
-	int			frames;		/* Number of frames in this packet */
-
-	enum packet_data_state	state;		/* Current state */
-	atomic_t		run_sm;		/* Incremented whenever the state */
-						/* machine needs to be run */
-	long			sleep_time;	/* Set this to non-zero to make the state */
-						/* machine run after this many jiffies. */
-
-	atomic_t		io_wait;	/* Number of pending IO operations */
-	atomic_t		io_errors;	/* Number of read/write errors during IO */
-
-	struct bio		*r_bios[PACKET_MAX_SIZE]; /* bios to use during data gathering */
-	struct page		*pages[PACKET_MAX_SIZE / FRAMES_PER_PAGE];
-
-	int			cache_valid;	/* If non-zero, the data for the zone defined */
-						/* by the sector variable is completely cached */
-						/* in the pages[] vector. */
-
-	int			id;		/* ID number for debugging */
-	struct pktcdvd_device	*pd;
-};
-
-struct pkt_rb_node {
-	struct rb_node		rb_node;
-	struct bio		*bio;
-};
-
-struct packet_stacked_data
-{
-	struct bio		*bio;		/* Original read request bio */
-	struct pktcdvd_device	*pd;
-};
-#define PSD_POOL_SIZE		64
-
-struct pktcdvd_device
-{
-	struct block_device	*bdev;		/* dev attached */
-	dev_t			pkt_dev;	/* our dev */
-	char			name[20];
-	struct packet_settings	settings;
-	struct packet_stats	stats;
-	int			refcnt;		/* Open count */
-	int			write_speed;	/* current write speed, kB/s */
-	int			read_speed;	/* current read speed, kB/s */
-	unsigned long		offset;		/* start offset */
-	__u8			mode_offset;	/* 0 / 8 */
-	__u8			type;
-	unsigned long		flags;
-	__u16			mmc3_profile;
-	__u32			nwa;		/* next writable address */
-	__u32			lra;		/* last recorded address */
-	struct packet_cdrw	cdrw;
-	wait_queue_head_t	wqueue;
-
-	spinlock_t		lock;		/* Serialize access to bio_queue */
-	struct rb_root		bio_queue;	/* Work queue of bios we need to handle */
-	int			bio_queue_size;	/* Number of nodes in bio_queue */
-	bool			congested;	/* Someone is waiting for bio_queue_size
-						 * to drop. */
-	sector_t		current_sector;	/* Keep track of where the elevator is */
-	atomic_t		scan_queue;	/* Set to non-zero when pkt_handle_queue */
-						/* needs to be run. */
-	mempool_t		rb_pool;	/* mempool for pkt_rb_node allocations */
-
-	struct packet_iosched   iosched;
-	struct gendisk		*disk;
-
-	int			write_congestion_off;
-	int			write_congestion_on;
-
-	struct device		*dev;		/* sysfs pktcdvd[0-7] dev */
-
-	struct dentry		*dfs_d_root;	/* debugfs: devname directory */
-	struct dentry		*dfs_f_info;	/* debugfs: info file */
-};
-
-#endif /* __PKTCDVD_H */
diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h
index d6e5a1feb947..f29aaaf2eb21 100644
--- a/include/linux/raid/pq.h
+++ b/include/linux/raid/pq.h
@@ -10,17 +10,9 @@
 
 #ifdef __KERNEL__
 
-/* Set to 1 to use kernel-wide empty_zero_page */
-#define RAID6_USE_EMPTY_ZERO_PAGE 0
 #include <linux/blkdev.h>
 
-/* We need a pre-zeroed page... if we don't want to use the kernel-provided
-   one define it here */
-#if RAID6_USE_EMPTY_ZERO_PAGE
-# define raid6_empty_zero_page empty_zero_page
-#else
 extern const char raid6_empty_zero_page[PAGE_SIZE];
-#endif
 
 #else /* ! __KERNEL__ */
 /* Used for testing in user space */
diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index 4d2d5205ab58..d662cf136021 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -87,11 +87,6 @@ struct sbitmap {
  */
 struct sbq_wait_state {
 	/**
-	 * @wait_cnt: Number of frees remaining before we wake up.
-	 */
-	atomic_t wait_cnt;
-
-	/**
 	 * @wait: Wait queue.
 	 */
 	wait_queue_head_t wait;
@@ -138,6 +133,17 @@ struct sbitmap_queue {
 	 * sbitmap_queue_get_shallow()
 	 */
 	unsigned int min_shallow_depth;
+
+	/**
+	 * @completion_cnt: Number of bits cleared passed to the
+	 * wakeup function.
+	 */
+	atomic_t completion_cnt;
+
+	/**
+	 * @wakeup_cnt: Number of thread wake ups issued.
+	 */
+	atomic_t wakeup_cnt;
 };
 
 /**
diff --git a/include/linux/sed-opal.h b/include/linux/sed-opal.h
index 6f837bb6c715..31ac562a17d7 100644
--- a/include/linux/sed-opal.h
+++ b/include/linux/sed-opal.h
@@ -11,7 +11,8 @@
 #define LINUX_OPAL_H
 
 #include <uapi/linux/sed-opal.h>
-#include <linux/kernel.h>
+#include <linux/compiler_types.h>
+#include <linux/types.h>
 
 struct opal_dev;
 
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 87fc3d0dda98..9f158238edba 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -250,8 +250,14 @@ void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode
 void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count);
 void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *xarray,
 		     loff_t start, size_t count);
+ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages,
+		size_t maxsize, unsigned maxpages, size_t *start,
+		unsigned gup_flags);
 ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages,
 			size_t maxsize, unsigned maxpages, size_t *start);
+ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
+		struct page ***pages, size_t maxsize, size_t *start,
+		unsigned gup_flags);
 ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages,
 			size_t maxsize, size_t *start);
 int iov_iter_npages(const struct iov_iter *i, int maxpages);
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 7f5a51aae0a7..a0307b516b09 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -209,7 +209,7 @@ __remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq
 	list_del(&wq_entry->entry);
 }
 
-void __wake_up(struct wait_queue_head *wq_head, unsigned int mode, int nr, void *key);
+int __wake_up(struct wait_queue_head *wq_head, unsigned int mode, int nr, void *key);
 void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key);
 void __wake_up_locked_key_bookmark(struct wait_queue_head *wq_head,
 		unsigned int mode, void *key, wait_queue_entry_t *bookmark);
diff --git a/include/trace/events/iocost.h b/include/trace/events/iocost.h
index 6d1626e7a4ce..af8bfed528fc 100644
--- a/include/trace/events/iocost.h
+++ b/include/trace/events/iocost.h
@@ -38,7 +38,7 @@ DECLARE_EVENT_CLASS(iocost_iocg_state,
 		__assign_str(cgroup, path);
 		__entry->now = now->now;
 		__entry->vnow = now->vnow;
-		__entry->vrate = now->vrate;
+		__entry->vrate = iocg->ioc->vtime_base_rate;
 		__entry->last_period = last_period;
 		__entry->cur_period = cur_period;
 		__entry->vtime = vtime;
@@ -160,7 +160,7 @@ TRACE_EVENT(iocost_ioc_vrate_adj,
 
 	TP_fast_assign(
 		__assign_str(devname, ioc_name(ioc));
-		__entry->old_vrate = atomic64_read(&ioc->vtime_rate);
+		__entry->old_vrate = ioc->vtime_base_rate;
 		__entry->new_vrate = new_vrate;
 		__entry->busy_level = ioc->busy_level;
 		__entry->read_missed_ppm = missed_ppm[READ];
diff --git a/include/uapi/linux/pktcdvd.h b/include/uapi/linux/pktcdvd.h
deleted file mode 100644
index 9cbb55d21c94..000000000000
--- a/include/uapi/linux/pktcdvd.h
+++ /dev/null
@@ -1,112 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * Copyright (C) 2000 Jens Axboe <axboe@suse.de>
- * Copyright (C) 2001-2004 Peter Osterlund <petero2@telia.com>
- *
- * May be copied or modified under the terms of the GNU General Public
- * License.  See linux/COPYING for more information.
- *
- * Packet writing layer for ATAPI and SCSI CD-R, CD-RW, DVD-R, and
- * DVD-RW devices.
- *
- */
-#ifndef _UAPI__PKTCDVD_H
-#define _UAPI__PKTCDVD_H
-
-#include <linux/types.h>
-
-/*
- * 1 for normal debug messages, 2 is very verbose. 0 to turn it off.
- */
-#define PACKET_DEBUG		1
-
-#define	MAX_WRITERS		8
-
-#define PKT_RB_POOL_SIZE	512
-
-/*
- * How long we should hold a non-full packet before starting data gathering.
- */
-#define PACKET_WAIT_TIME	(HZ * 5 / 1000)
-
-/*
- * use drive write caching -- we need deferred error handling to be
- * able to successfully recover with this option (drive will return good
- * status as soon as the cdb is validated).
- */
-#if defined(CONFIG_CDROM_PKTCDVD_WCACHE)
-#define USE_WCACHING		1
-#else
-#define USE_WCACHING		0
-#endif
-
-/*
- * No user-servicable parts beyond this point ->
- */
-
-/*
- * device types
- */
-#define PACKET_CDR		1
-#define	PACKET_CDRW		2
-#define PACKET_DVDR		3
-#define PACKET_DVDRW		4
-
-/*
- * flags
- */
-#define PACKET_WRITABLE		1	/* pd is writable */
-#define PACKET_NWA_VALID	2	/* next writable address valid */
-#define PACKET_LRA_VALID	3	/* last recorded address valid */
-#define PACKET_MERGE_SEGS	4	/* perform segment merging to keep */
-					/* underlying cdrom device happy */
-
-/*
- * Disc status -- from READ_DISC_INFO
- */
-#define PACKET_DISC_EMPTY	0
-#define PACKET_DISC_INCOMPLETE	1
-#define PACKET_DISC_COMPLETE	2
-#define PACKET_DISC_OTHER	3
-
-/*
- * write type, and corresponding data block type
- */
-#define PACKET_MODE1		1
-#define PACKET_MODE2		2
-#define PACKET_BLOCK_MODE1	8
-#define PACKET_BLOCK_MODE2	10
-
-/*
- * Last session/border status
- */
-#define PACKET_SESSION_EMPTY		0
-#define PACKET_SESSION_INCOMPLETE	1
-#define PACKET_SESSION_RESERVED		2
-#define PACKET_SESSION_COMPLETE		3
-
-#define PACKET_MCN			"4a656e734178626f65323030300000"
-
-#undef PACKET_USE_LS
-
-#define PKT_CTRL_CMD_SETUP	0
-#define PKT_CTRL_CMD_TEARDOWN	1
-#define PKT_CTRL_CMD_STATUS	2
-
-struct pkt_ctrl_command {
-	__u32 command;				/* in: Setup, teardown, status */
-	__u32 dev_index;			/* in/out: Device index */
-	__u32 dev;				/* in/out: Device nr for cdrw device */
-	__u32 pkt_dev;				/* in/out: Device nr for packet device */
-	__u32 num_devices;			/* out: Largest device index + 1 */
-	__u32 padding;				/* Not used */
-};
-
-/*
- * packet ioctls
- */
-#define PACKET_IOCTL_MAGIC	('X')
-#define PACKET_CTRL_CMD		_IOWR(PACKET_IOCTL_MAGIC, 1, struct pkt_ctrl_command)
-
-
-#endif /* _UAPI__PKTCDVD_H */
diff --git a/include/uapi/linux/sed-opal.h b/include/uapi/linux/sed-opal.h
index 2573772e2fb3..1fed3c9294fc 100644
--- a/include/uapi/linux/sed-opal.h
+++ b/include/uapi/linux/sed-opal.h
@@ -44,6 +44,11 @@ enum opal_lock_state {
 	OPAL_LK = 0x04, /* 0100 */
 };
 
+enum opal_lock_flags {
+	/* IOC_OPAL_SAVE will also store the provided key for locking */
+	OPAL_SAVE_FOR_LOCK = 0x01,
+};
+
 struct opal_key {
 	__u8 lr;
 	__u8 key_len;
@@ -76,7 +81,8 @@ struct opal_user_lr_setup {
 struct opal_lock_unlock {
 	struct opal_session_info session;
 	__u32 l_state;
-	__u8 __align[4];
+	__u16 flags;
+	__u8 __align[2];
 };
 
 struct opal_new_pw {