Merge tag 'for-6.7/block-2023-10-30' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - Improvements to the queue_rqs() support, and adding null_blk support
   for that as well (Chengming)

 - Series improving badblocks support (Coly)

 - Key store support for sed-opal (Greg)

 - IBM partition string handling improvements (Jan)

 - Make number of ublk devices supported configurable (Mike)

 - Cancelation improvements for ublk (Ming)

 - MD pull requests via Song:
     - Handle timeout in md-cluster, by Denis Plotnikov
     - Cleanup pers->prepare_suspend, by Yu Kuai
     - Rewrite mddev_suspend(), by Yu Kuai
     - Simplify md_seq_ops, by Yu Kuai
     - Reduce unnecessary locking array_state_store(), by Mariusz
       Tkaczyk
     - Make rdev add/remove independent from daemon thread, by Yu Kuai
     - Refactor code around quiesce() and mddev_suspend(), by Yu Kuai

 - NVMe pull request via Keith:
     - nvme-auth updates (Mark)
     - nvme-tcp tls (Hannes)
     - nvme-fc annotaions (Kees)

 - Misc cleanups and improvements (Jiapeng, Joel)

* tag 'for-6.7/block-2023-10-30' of git://git.kernel.dk/linux: (95 commits)
  block: ublk_drv: Remove unused function
  md: cleanup pers->prepare_suspend()
  nvme-auth: allow mixing of secret and hash lengths
  nvme-auth: use transformed key size to create resp
  nvme-auth: alloc nvme_dhchap_key as single buffer
  nvmet-tcp: use 'spin_lock_bh' for state_lock()
  powerpc/pseries: PLPKS SED Opal keystore support
  block: sed-opal: keystore access for SED Opal keys
  block:sed-opal: SED Opal keystore
  ublk: simplify aborting request
  ublk: replace monitor with cancelable uring_cmd
  ublk: quiesce request queue when aborting queue
  ublk: rename mm_lock as lock
  ublk: move ublk_cancel_dev() out of ub->mutex
  ublk: make sure io cmd handled in submitter task context
  ublk: don't get ublk device reference in ublk_abort_queue()
  ublk: Make ublks_max configurable
  ublk: Limit dev_id/ub_number values
  md-cluster: check for timeout while a new disk adding
  nvme: rework NVME_AUTH Kconfig selection
  ...

1 files changed, 38 insertions, 32 deletions

diff --git a/drivers/md/md.h b/drivers/md/md.h
index 274e7d61d19f..ade83af123a2 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -246,10 +246,6 @@ struct md_cluster_info;
  *			    become failed.
  * @MD_HAS_PPL:  The raid array has PPL feature set.
  * @MD_HAS_MULTIPLE_PPLS: The raid array has multiple PPLs feature set.
- * @MD_ALLOW_SB_UPDATE: md_check_recovery is allowed to update the metadata
- *			 without taking reconfig_mutex.
- * @MD_UPDATING_SB: md_check_recovery is updating the metadata without
- *		     explicitly holding reconfig_mutex.
  * @MD_NOT_READY: do_md_run() is active, so 'array_state', ust not report that
  *		   array is ready yet.
  * @MD_BROKEN: This is used to stop writes and mark array as failed.
@@ -266,8 +262,6 @@ enum mddev_flags {
 	MD_FAILFAST_SUPPORTED,
 	MD_HAS_PPL,
 	MD_HAS_MULTIPLE_PPLS,
-	MD_ALLOW_SB_UPDATE,
-	MD_UPDATING_SB,
 	MD_NOT_READY,
 	MD_BROKEN,
 	MD_DELETED,
@@ -314,6 +308,7 @@ struct mddev {
 	unsigned long			sb_flags;
 
 	int				suspended;
+	struct mutex			suspend_mutex;
 	struct percpu_ref		active_io;
 	int				ro;
 	int				sysfs_active; /* set when sysfs deletes
@@ -451,7 +446,10 @@ struct mddev {
 	struct kernfs_node		*sysfs_degraded;	/*handle for 'degraded' */
 	struct kernfs_node		*sysfs_level;		/*handle for 'level' */
 
-	struct work_struct del_work;	/* used for delayed sysfs removal */
+	/* used for delayed sysfs removal */
+	struct work_struct del_work;
+	/* used for register new sync thread */
+	struct work_struct sync_work;
 
 	/* "lock" protects:
 	 *   flush_bio transition from NULL to !NULL
@@ -565,23 +563,6 @@ enum recovery_flags {
 	MD_RESYNCING_REMOTE,	/* remote node is running resync thread */
 };
 
-enum md_ro_state {
-	MD_RDWR,
-	MD_RDONLY,
-	MD_AUTO_READ,
-	MD_MAX_STATE
-};
-
-static inline bool md_is_rdwr(struct mddev *mddev)
-{
-	return (mddev->ro == MD_RDWR);
-}
-
-static inline bool is_md_suspended(struct mddev *mddev)
-{
-	return percpu_ref_is_dying(&mddev->active_io);
-}
-
 static inline int __must_check mddev_lock(struct mddev *mddev)
 {
 	return mutex_lock_interruptible(&mddev->reconfig_mutex);
@@ -641,7 +622,6 @@ struct md_personality
 	int (*start_reshape) (struct mddev *mddev);
 	void (*finish_reshape) (struct mddev *mddev);
 	void (*update_reshape_pos) (struct mddev *mddev);
-	void (*prepare_suspend) (struct mddev *mddev);
 	/* quiesce suspends or resumes internal processing.
 	 * 1 - stop new actions and wait for action io to complete
 	 * 0 - return to normal behaviour
@@ -766,7 +746,6 @@ extern void md_unregister_thread(struct mddev *mddev, struct md_thread __rcu **t
 extern void md_wakeup_thread(struct md_thread __rcu *thread);
 extern void md_check_recovery(struct mddev *mddev);
 extern void md_reap_sync_thread(struct mddev *mddev);
-extern int mddev_init_writes_pending(struct mddev *mddev);
 extern bool md_write_start(struct mddev *mddev, struct bio *bi);
 extern void md_write_inc(struct mddev *mddev, struct bio *bi);
 extern void md_write_end(struct mddev *mddev);
@@ -793,7 +772,8 @@ extern int md_integrity_register(struct mddev *mddev);
 extern int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev);
 extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale);
 
-extern void mddev_init(struct mddev *mddev);
+extern int mddev_init(struct mddev *mddev);
+extern void mddev_destroy(struct mddev *mddev);
 struct mddev *md_alloc(dev_t dev, char *name);
 void mddev_put(struct mddev *mddev);
 extern int md_run(struct mddev *mddev);
@@ -804,15 +784,14 @@ extern int md_rdev_init(struct md_rdev *rdev);
 extern void md_rdev_clear(struct md_rdev *rdev);
 
 extern void md_handle_request(struct mddev *mddev, struct bio *bio);
-extern void mddev_suspend(struct mddev *mddev);
+extern int mddev_suspend(struct mddev *mddev, bool interruptible);
 extern void mddev_resume(struct mddev *mddev);
 
 extern void md_reload_sb(struct mddev *mddev, int raid_disk);
 extern void md_update_sb(struct mddev *mddev, int force);
-extern void mddev_create_serial_pool(struct mddev *mddev, struct md_rdev *rdev,
-				     bool is_suspend);
-extern void mddev_destroy_serial_pool(struct mddev *mddev, struct md_rdev *rdev,
-				      bool is_suspend);
+extern void mddev_create_serial_pool(struct mddev *mddev, struct md_rdev *rdev);
+extern void mddev_destroy_serial_pool(struct mddev *mddev,
+				      struct md_rdev *rdev);
 struct md_rdev *md_find_rdev_nr_rcu(struct mddev *mddev, int nr);
 struct md_rdev *md_find_rdev_rcu(struct mddev *mddev, dev_t dev);
 
@@ -850,6 +829,33 @@ static inline void mddev_check_write_zeroes(struct mddev *mddev, struct bio *bio
 		mddev->queue->limits.max_write_zeroes_sectors = 0;
 }
 
+static inline int mddev_suspend_and_lock(struct mddev *mddev)
+{
+	int ret;
+
+	ret = mddev_suspend(mddev, true);
+	if (ret)
+		return ret;
+
+	ret = mddev_lock(mddev);
+	if (ret)
+		mddev_resume(mddev);
+
+	return ret;
+}
+
+static inline void mddev_suspend_and_lock_nointr(struct mddev *mddev)
+{
+	mddev_suspend(mddev, false);
+	mutex_lock(&mddev->reconfig_mutex);
+}
+
+static inline void mddev_unlock_and_resume(struct mddev *mddev)
+{
+	mddev_unlock(mddev);
+	mddev_resume(mddev);
+}
+
 struct mdu_array_info_s;
 struct mdu_disk_info_s;