Merge tag 'for-6.1/block-2022-10-03' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe pull requests via Christoph:
      - handle number of queue changes in the TCP and RDMA drivers
        (Daniel Wagner)
      - allow changing the number of queues in nvmet (Daniel Wagner)
      - also consider host_iface when checking ip options (Daniel
        Wagner)
      - don't map pages which can't come from HIGHMEM (Fabio M. De
        Francesco)
      - avoid unnecessary flush bios in nvmet (Guixin Liu)
      - shrink and better pack the nvme_iod structure (Keith Busch)
      - add comment for unaligned "fake" nqn (Linjun Bao)
      - print actual source IP address through sysfs "address" attr
        (Martin Belanger)
      - various cleanups (Jackie Liu, Wolfram Sang, Genjian Zhang)
      - handle effects after freeing the request (Keith Busch)
      - copy firmware_rev on each init (Keith Busch)
      - restrict management ioctls to admin (Keith Busch)
      - ensure subsystem reset is single threaded (Keith Busch)
      - report the actual number of tagset maps in nvme-pci (Keith
        Busch)
      - small fabrics authentication fixups (Christoph Hellwig)
      - add common code for tagset allocation and freeing (Christoph
        Hellwig)
      - stop using the request_queue in nvmet (Christoph Hellwig)
      - set min_align_mask before calculating max_hw_sectors (Rishabh
        Bhatnagar)
      - send a rediscover uevent when a persistent discovery controller
        reconnects (Sagi Grimberg)
      - misc nvmet-tcp fixes (Varun Prakash, zhenwei pi)

 - MD pull request via Song:
      - Various raid5 fix and clean up, by Logan Gunthorpe and David
        Sloan.
      - Raid10 performance optimization, by Yu Kuai.

 - sbitmap wakeup hang fixes (Hugh, Keith, Jan, Yu)

 - IO scheduler switching quisce fix (Keith)

 - s390/dasd block driver updates (Stefan)

 - support for recovery for the ublk driver (ZiyangZhang)

 - rnbd drivers fixes and updates (Guoqing, Santosh, ye, Christoph)

 - blk-mq and null_blk map fixes (Bart)

 - various bcache fixes (Coly, Jilin, Jules)

 - nbd signal hang fix (Shigeru)

 - block writeback throttling fix (Yu)

 - optimize the passthrough mapping handling (me)

 - prepare block cgroups to being gendisk based (Christoph)

 - get rid of an old PSI hack in the block layer, moving it to the
   callers instead where it belongs (Christoph)

 - blk-throttle fixes and cleanups (Yu)

 - misc fixes and cleanups (Liu Shixin, Liu Song, Miaohe, Pankaj,
   Ping-Xiang, Wolfram, Saurabh, Li Jinlin, Li Lei, Lin, Li zeming,
   Miaohe, Bart, Coly, Gaosheng

* tag 'for-6.1/block-2022-10-03' of git://git.kernel.dk/linux: (162 commits)
  sbitmap: fix lockup while swapping
  block: add rationale for not using blk_mq_plug() when applicable
  block: adapt blk_mq_plug() to not plug for writes that require a zone lock
  s390/dasd: use blk_mq_alloc_disk
  blk-cgroup: don't update the blkg lookup hint in blkg_conf_prep
  nvmet: don't look at the request_queue in nvmet_bdev_set_limits
  nvmet: don't look at the request_queue in nvmet_bdev_zone_mgmt_emulate_all
  blk-mq: use quiesced elevator switch when reinitializing queues
  block: replace blk_queue_nowait with bdev_nowait
  nvme: remove nvme_ctrl_init_connect_q
  nvme-loop: use the tagset alloc/free helpers
  nvme-loop: store the generic nvme_ctrl in set->driver_data
  nvme-loop: initialize sqsize later
  nvme-fc: use the tagset alloc/free helpers
  nvme-fc: store the generic nvme_ctrl in set->driver_data
  nvme-fc: keep ctrl->sqsize in sync with opts->queue_size
  nvme-rdma: use the tagset alloc/free helpers
  nvme-rdma: store the generic nvme_ctrl in set->driver_data
  nvme-tcp: use the tagset alloc/free helpers
  nvme-tcp: store the generic nvme_ctrl in set->driver_data
  ...

15 files changed, 65 insertions, 24 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index ca22b06700a9..2c5806997bbf 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -509,7 +509,7 @@ static inline void bio_set_dev(struct bio *bio, struct block_device *bdev)
 {
 	bio_clear_flag(bio, BIO_REMAPPED);
 	if (bio->bi_bdev != bdev)
-		bio_clear_flag(bio, BIO_THROTTLED);
+		bio_clear_flag(bio, BIO_BPS_THROTTLED);
 	bio->bi_bdev = bdev;
 	bio_associate_blkg(bio);
 }
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 9f40dbc65f82..dd5841a42c33 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -18,14 +18,14 @@
 
 struct bio;
 struct cgroup_subsys_state;
-struct request_queue;
+struct gendisk;
 
 #define FC_APPID_LEN              129
 
 #ifdef CONFIG_BLK_CGROUP
 extern struct cgroup_subsys_state * const blkcg_root_css;
 
-void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay);
+void blkcg_schedule_throttle(struct gendisk *disk, bool use_memdelay);
 void blkcg_maybe_throttle_current(void);
 bool blk_cgroup_congested(void);
 void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css);
@@ -39,7 +39,6 @@ struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio);
 
 static inline void blkcg_maybe_throttle_current(void) { }
 static inline bool blk_cgroup_congested(void) { return false; }
-static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { }
 static inline struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio)
 {
 	return NULL;
diff --git a/include/linux/blk-mq-pci.h b/include/linux/blk-mq-pci.h
index 0b1f45c62623..ca544e1d3508 100644
--- a/include/linux/blk-mq-pci.h
+++ b/include/linux/blk-mq-pci.h
@@ -5,7 +5,7 @@
 struct blk_mq_queue_map;
 struct pci_dev;
 
-int blk_mq_pci_map_queues(struct blk_mq_queue_map *qmap, struct pci_dev *pdev,
-			  int offset);
+void blk_mq_pci_map_queues(struct blk_mq_queue_map *qmap, struct pci_dev *pdev,
+			   int offset);
 
 #endif /* _LINUX_BLK_MQ_PCI_H */
diff --git a/include/linux/blk-mq-rdma.h b/include/linux/blk-mq-rdma.h
index 5cc5f0f36218..53b58c610e76 100644
--- a/include/linux/blk-mq-rdma.h
+++ b/include/linux/blk-mq-rdma.h
@@ -5,7 +5,7 @@
 struct blk_mq_tag_set;
 struct ib_device;
 
-int blk_mq_rdma_map_queues(struct blk_mq_queue_map *map,
+void blk_mq_rdma_map_queues(struct blk_mq_queue_map *map,
 		struct ib_device *dev, int first_vec);
 
 #endif /* _LINUX_BLK_MQ_RDMA_H */
diff --git a/include/linux/blk-mq-virtio.h b/include/linux/blk-mq-virtio.h
index 687ae287e1dc..13226e9b22dd 100644
--- a/include/linux/blk-mq-virtio.h
+++ b/include/linux/blk-mq-virtio.h
@@ -5,7 +5,7 @@
 struct blk_mq_queue_map;
 struct virtio_device;
 
-int blk_mq_virtio_map_queues(struct blk_mq_queue_map *qmap,
+void blk_mq_virtio_map_queues(struct blk_mq_queue_map *qmap,
 		struct virtio_device *vdev, int first_vec);
 
 #endif /* _LINUX_BLK_MQ_VIRTIO_H */
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index de384f5d2c37..00a15808c137 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -268,9 +268,16 @@ static inline void rq_list_move(struct request **src, struct request **dst,
 	rq_list_add(dst, rq);
 }
 
+/**
+ * enum blk_eh_timer_return - How the timeout handler should proceed
+ * @BLK_EH_DONE: The block driver completed the command or will complete it at
+ *	a later time.
+ * @BLK_EH_RESET_TIMER: Reset the request timer and continue waiting for the
+ *	request to complete.
+ */
 enum blk_eh_timer_return {
-	BLK_EH_DONE,		/* drivers has completed the command */
-	BLK_EH_RESET_TIMER,	/* reset timer and try again */
+	BLK_EH_DONE,
+	BLK_EH_RESET_TIMER,
 };
 
 #define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */
@@ -630,7 +637,7 @@ struct blk_mq_ops {
 	 * @map_queues: This allows drivers specify their own queue mapping by
 	 * overriding the setup-time function that builds the mq_map.
 	 */
-	int (*map_queues)(struct blk_mq_tag_set *set);
+	void (*map_queues)(struct blk_mq_tag_set *set);
 
 #ifdef CONFIG_BLK_DEBUG_FS
 	/**
@@ -880,7 +887,7 @@ void blk_mq_freeze_queue_wait(struct request_queue *q);
 int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
 				     unsigned long timeout);
 
-int blk_mq_map_queues(struct blk_mq_queue_map *qmap);
+void blk_mq_map_queues(struct blk_mq_queue_map *qmap);
 void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues);
 
 void blk_mq_quiesce_queue_nowait(struct request_queue *q);
@@ -963,11 +970,11 @@ blk_status_t blk_insert_cloned_request(struct request *rq);
 
 struct rq_map_data {
 	struct page **pages;
-	int page_order;
-	int nr_entries;
 	unsigned long offset;
-	int null_mapped;
-	int from_user;
+	unsigned short page_order;
+	unsigned short nr_entries;
+	bool null_mapped;
+	bool from_user;
 };
 
 int blk_rq_map_user(struct request_queue *, struct request *,
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 1ef99790f6ed..e0b098089ef2 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -321,11 +321,10 @@ enum {
 	BIO_NO_PAGE_REF,	/* don't put release vec pages */
 	BIO_CLONED,		/* doesn't own data */
 	BIO_BOUNCED,		/* bio is a bounce bio */
-	BIO_WORKINGSET,		/* contains userspace workingset pages */
 	BIO_QUIET,		/* Make BIO Quiet */
 	BIO_CHAIN,		/* chained bio, ->bi_remaining in effect */
 	BIO_REFFED,		/* bio has elevated ->bi_cnt */
-	BIO_THROTTLED,		/* This bio has already been subjected to
+	BIO_BPS_THROTTLED,	/* This bio has already been subjected to
 				 * throttling rules. Don't do it again. */
 	BIO_TRACE_COMPLETION,	/* bio_endio() should trace the final completion
 				 * of this bio. */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8038c5fbde40..3e187a02924f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -618,7 +618,6 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 #define blk_queue_quiesced(q)	test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags)
 #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_nowait(q)	test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags)
 #define blk_queue_sq_sched(q)	test_bit(QUEUE_FLAG_SQ_SCHED, &(q)->queue_flags)
 
 extern void blk_set_pm_only(struct request_queue *q);
@@ -1280,6 +1279,11 @@ static inline bool bdev_fua(struct block_device *bdev)
 	return test_bit(QUEUE_FLAG_FUA, &bdev_get_queue(bdev)->queue_flags);
 }
 
+static inline bool bdev_nowait(struct block_device *bdev)
+{
+	return test_bit(QUEUE_FLAG_NOWAIT, &bdev_get_queue(bdev)->queue_flags);
+}
+
 static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
@@ -1300,6 +1304,15 @@ static inline bool bdev_is_zoned(struct block_device *bdev)
 	return false;
 }
 
+static inline bool bdev_op_is_zoned_write(struct block_device *bdev,
+					  blk_opf_t op)
+{
+	if (!bdev_is_zoned(bdev))
+		return false;
+
+	return op == REQ_OP_WRITE || op == REQ_OP_WRITE_ZEROES;
+}
+
 static inline sector_t bdev_zone_sectors(struct block_device *bdev)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index ae53d74f3696..050d7d0cd81b 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -1482,8 +1482,8 @@ struct nvmf_connect_command {
 };
 
 enum {
-	NVME_CONNECT_AUTHREQ_ASCR	= (1 << 2),
-	NVME_CONNECT_AUTHREQ_ATR	= (1 << 1),
+	NVME_CONNECT_AUTHREQ_ASCR	= (1U << 18),
+	NVME_CONNECT_AUTHREQ_ATR	= (1U << 17),
 };
 
 struct nvmf_connect_data {
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 0178b2040ea3..201dc7281640 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -1173,6 +1173,8 @@ struct readahead_control {
 	pgoff_t _index;
 	unsigned int _nr_pages;
 	unsigned int _batch_count;
+	bool _workingset;
+	unsigned long _pflags;
 };
 
 #define DEFINE_READAHEAD(ractl, f, r, m, i)				\
diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index 8f5a86e210b9..4d2d5205ab58 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -575,8 +575,9 @@ void sbitmap_queue_wake_all(struct sbitmap_queue *sbq);
  * sbitmap_queue_wake_up() - Wake up some of waiters in one waitqueue
  * on a &struct sbitmap_queue.
  * @sbq: Bitmap queue to wake up.
+ * @nr: Number of bits cleared.
  */
-void sbitmap_queue_wake_up(struct sbitmap_queue *sbq);
+void sbitmap_queue_wake_up(struct sbitmap_queue *sbq, int nr);
 
 /**
  * sbitmap_queue_show() - Dump &struct sbitmap_queue information to a &struct
diff --git a/include/linux/sed-opal.h b/include/linux/sed-opal.h
index 1ac0d712a9c3..6f837bb6c715 100644
--- a/include/linux/sed-opal.h
+++ b/include/linux/sed-opal.h
@@ -43,6 +43,7 @@ static inline bool is_sed_ioctl(unsigned int cmd)
 	case IOC_OPAL_MBR_DONE:
 	case IOC_OPAL_WRITE_SHADOW_MBR:
 	case IOC_OPAL_GENERIC_TABLE_RW:
+	case IOC_OPAL_GET_STATUS:
 		return true;
 	}
 	return false;
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 9b0a028bf053..fcf25f1642a3 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -276,7 +276,7 @@ struct scsi_host_template {
 	 *
 	 * Status: OPTIONAL
 	 */
-	int (* map_queues)(struct Scsi_Host *shost);
+	void (* map_queues)(struct Scsi_Host *shost);
 
 	/*
 	 * SCSI interface of blk_poll - poll for IO completions.
diff --git a/include/uapi/linux/sed-opal.h b/include/uapi/linux/sed-opal.h
index 6f5af1a84213..2573772e2fb3 100644
--- a/include/uapi/linux/sed-opal.h
+++ b/include/uapi/linux/sed-opal.h
@@ -132,6 +132,18 @@ struct opal_read_write_table {
 	__u64 priv;
 };
 
+#define OPAL_FL_SUPPORTED		0x00000001
+#define OPAL_FL_LOCKING_SUPPORTED	0x00000002
+#define OPAL_FL_LOCKING_ENABLED		0x00000004
+#define OPAL_FL_LOCKED			0x00000008
+#define OPAL_FL_MBR_ENABLED		0x00000010
+#define OPAL_FL_MBR_DONE		0x00000020
+
+struct opal_status {
+	__u32 flags;
+	__u32 reserved;
+};
+
 #define IOC_OPAL_SAVE		    _IOW('p', 220, struct opal_lock_unlock)
 #define IOC_OPAL_LOCK_UNLOCK	    _IOW('p', 221, struct opal_lock_unlock)
 #define IOC_OPAL_TAKE_OWNERSHIP	    _IOW('p', 222, struct opal_key)
@@ -148,5 +160,6 @@ struct opal_read_write_table {
 #define IOC_OPAL_MBR_DONE           _IOW('p', 233, struct opal_mbr_done)
 #define IOC_OPAL_WRITE_SHADOW_MBR   _IOW('p', 234, struct opal_shadow_mbr)
 #define IOC_OPAL_GENERIC_TABLE_RW   _IOW('p', 235, struct opal_read_write_table)
+#define IOC_OPAL_GET_STATUS         _IOR('p', 236, struct opal_status)
 
 #endif /* _UAPI_SED_OPAL_H */
diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h
index 677edaab2b66..8f88e3a29998 100644
--- a/include/uapi/linux/ublk_cmd.h
+++ b/include/uapi/linux/ublk_cmd.h
@@ -17,7 +17,8 @@
 #define	UBLK_CMD_STOP_DEV	0x07
 #define	UBLK_CMD_SET_PARAMS	0x08
 #define	UBLK_CMD_GET_PARAMS	0x09
-
+#define	UBLK_CMD_START_USER_RECOVERY	0x10
+#define	UBLK_CMD_END_USER_RECOVERY	0x11
 /*
  * IO commands, issued by ublk server, and handled by ublk driver.
  *
@@ -74,9 +75,14 @@
  */
 #define UBLK_F_NEED_GET_DATA (1UL << 2)
 
+#define UBLK_F_USER_RECOVERY	(1UL << 3)
+
+#define UBLK_F_USER_RECOVERY_REISSUE	(1UL << 4)
+
 /* device state */
 #define UBLK_S_DEV_DEAD	0
 #define UBLK_S_DEV_LIVE	1
+#define UBLK_S_DEV_QUIESCED	2
 
 /* shipped via sqe->cmd of io_uring command */
 struct ublksrv_ctrl_cmd {