Merge tag 'for-5.11/block-2020-12-14' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "Another series of killing more code than what is being added, again
  thanks to Christoph's relentless cleanups and tech debt tackling.

  This contains:

   - blk-iocost improvements (Baolin Wang)

   - part0 iostat fix (Jeffle Xu)

   - Disable iopoll for split bios (Jeffle Xu)

   - block tracepoint cleanups (Christoph Hellwig)

   - Merging of struct block_device and hd_struct (Christoph Hellwig)

   - Rework/cleanup of how block device sizes are updated (Christoph
     Hellwig)

   - Simplification of gendisk lookup and removal of block device
     aliasing (Christoph Hellwig)

   - Block device ioctl cleanups (Christoph Hellwig)

   - Removal of bdget()/blkdev_get() as exported API (Christoph Hellwig)

   - Disk change rework, avoid ->revalidate_disk() (Christoph Hellwig)

   - sbitmap improvements (Pavel Begunkov)

   - Hybrid polling fix (Pavel Begunkov)

   - bvec iteration improvements (Pavel Begunkov)

   - Zone revalidation fixes (Damien Le Moal)

   - blk-throttle limit fix (Yu Kuai)

   - Various little fixes"

* tag 'for-5.11/block-2020-12-14' of git://git.kernel.dk/linux-block: (126 commits)
  blk-mq: fix msec comment from micro to milli seconds
  blk-mq: update arg in comment of blk_mq_map_queue
  blk-mq: add helper allocating tagset->tags
  Revert "block: Fix a lockdep complaint triggered by request queue flushing"
  nvme-loop: use blk_mq_hctx_set_fq_lock_class to set loop's lock class
  blk-mq: add new API of blk_mq_hctx_set_fq_lock_class
  block: disable iopoll for split bio
  block: Improve blk_revalidate_disk_zones() checks
  sbitmap: simplify wrap check
  sbitmap: replace CAS with atomic and
  sbitmap: remove swap_lock
  sbitmap: optimise sbitmap_deferred_clear()
  blk-mq: skip hybrid polling if iopoll doesn't spin
  blk-iocost: Factor out the base vrate change into a separate function
  blk-iocost: Factor out the active iocgs' state check into a separate function
  blk-iocost: Move the usage ratio calculation to the correct place
  blk-iocost: Remove unnecessary advance declaration
  blk-iocost: Fix some typos in comments
  blktrace: fix up a kerneldoc comment
  block: remove the request_queue to argument request based tracepoints
  ...

1 files changed, 52 insertions, 63 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 0037c6ecab65..0445f44ae635 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -464,7 +464,7 @@ struct md_io {
 	bio_end_io_t *orig_bi_end_io;
 	void *orig_bi_private;
 	unsigned long start_time;
-	struct hd_struct *part;
+	struct block_device *part;
 };
 
 static void md_end_io(struct bio *bio)
@@ -2414,7 +2414,6 @@ EXPORT_SYMBOL(md_integrity_add_rdev);
 static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev)
 {
 	char b[BDEVNAME_SIZE];
-	struct kobject *ko;
 	int err;
 
 	/* prevent duplicates */
@@ -2477,9 +2476,8 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev)
 	if ((err = kobject_add(&rdev->kobj, &mddev->kobj, "dev-%s", b)))
 		goto fail;
 
-	ko = &part_to_dev(rdev->bdev->bd_part)->kobj;
 	/* failure here is OK */
-	err = sysfs_create_link(&rdev->kobj, ko, "block");
+	err = sysfs_create_link(&rdev->kobj, bdev_kobj(rdev->bdev), "block");
 	rdev->sysfs_state = sysfs_get_dirent_safe(rdev->kobj.sd, "state");
 	rdev->sysfs_unack_badblocks =
 		sysfs_get_dirent_safe(rdev->kobj.sd, "unacknowledged_bad_blocks");
@@ -5355,10 +5353,9 @@ array_size_store(struct mddev *mddev, const char *buf, size_t len)
 
 	if (!err) {
 		mddev->array_sectors = sectors;
-		if (mddev->pers) {
-			set_capacity(mddev->gendisk, mddev->array_sectors);
-			revalidate_disk_size(mddev->gendisk, true);
-		}
+		if (mddev->pers)
+			set_capacity_and_notify(mddev->gendisk,
+						mddev->array_sectors);
 	}
 	mddev_unlock(mddev);
 	return err ?: len;
@@ -5765,11 +5762,12 @@ static int md_alloc(dev_t dev, char *name)
 	return error;
 }
 
-static struct kobject *md_probe(dev_t dev, int *part, void *data)
+static void md_probe(dev_t dev)
 {
+	if (MAJOR(dev) == MD_MAJOR && MINOR(dev) >= 512)
+		return;
 	if (create_on_open)
 		md_alloc(dev, NULL);
-	return NULL;
 }
 
 static int add_named_array(const char *val, const struct kernel_param *kp)
@@ -6107,8 +6105,7 @@ int do_md_run(struct mddev *mddev)
 	md_wakeup_thread(mddev->thread);
 	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
 
-	set_capacity(mddev->gendisk, mddev->array_sectors);
-	revalidate_disk_size(mddev->gendisk, true);
+	set_capacity_and_notify(mddev->gendisk, mddev->array_sectors);
 	clear_bit(MD_NOT_READY, &mddev->flags);
 	mddev->changed = 1;
 	kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
@@ -6423,10 +6420,9 @@ static int do_md_stop(struct mddev *mddev, int mode,
 			if (rdev->raid_disk >= 0)
 				sysfs_unlink_rdev(mddev, rdev);
 
-		set_capacity(disk, 0);
+		set_capacity_and_notify(disk, 0);
 		mutex_unlock(&mddev->open_mutex);
 		mddev->changed = 1;
-		revalidate_disk_size(disk, true);
 
 		if (mddev->ro)
 			mddev->ro = 0;
@@ -6535,7 +6531,7 @@ static void autorun_devices(int part)
 			break;
 		}
 
-		md_probe(dev, NULL, NULL);
+		md_probe(dev);
 		mddev = mddev_find(dev);
 		if (!mddev || !mddev->gendisk) {
 			if (mddev)
@@ -7257,8 +7253,8 @@ static int update_size(struct mddev *mddev, sector_t num_sectors)
 		if (mddev_is_clustered(mddev))
 			md_cluster_ops->update_size(mddev, old_dev_sectors);
 		else if (mddev->queue) {
-			set_capacity(mddev->gendisk, mddev->array_sectors);
-			revalidate_disk_size(mddev->gendisk, true);
+			set_capacity_and_notify(mddev->gendisk,
+						mddev->array_sectors);
 		}
 	}
 	return rv;
@@ -7480,7 +7476,6 @@ static inline bool md_ioctl_valid(unsigned int cmd)
 {
 	switch (cmd) {
 	case ADD_NEW_DISK:
-	case BLKROSET:
 	case GET_ARRAY_INFO:
 	case GET_BITMAP_FILE:
 	case GET_DISK_INFO:
@@ -7507,7 +7502,6 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 	int err = 0;
 	void __user *argp = (void __user *)arg;
 	struct mddev *mddev = NULL;
-	int ro;
 	bool did_set_md_closing = false;
 
 	if (!md_ioctl_valid(cmd))
@@ -7687,35 +7681,6 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 			goto unlock;
 		}
 		break;
-
-	case BLKROSET:
-		if (get_user(ro, (int __user *)(arg))) {
-			err = -EFAULT;
-			goto unlock;
-		}
-		err = -EINVAL;
-
-		/* if the bdev is going readonly the value of mddev->ro
-		 * does not matter, no writes are coming
-		 */
-		if (ro)
-			goto unlock;
-
-		/* are we are already prepared for writes? */
-		if (mddev->ro != 1)
-			goto unlock;
-
-		/* transitioning to readauto need only happen for
-		 * arrays that call md_write_start
-		 */
-		if (mddev->pers) {
-			err = restart_array(mddev);
-			if (err == 0) {
-				mddev->ro = 2;
-				set_disk_ro(mddev->gendisk, 0);
-			}
-		}
-		goto unlock;
 	}
 
 	/*
@@ -7809,6 +7774,36 @@ static int md_compat_ioctl(struct block_device *bdev, fmode_t mode,
 }
 #endif /* CONFIG_COMPAT */
 
+static int md_set_read_only(struct block_device *bdev, bool ro)
+{
+	struct mddev *mddev = bdev->bd_disk->private_data;
+	int err;
+
+	err = mddev_lock(mddev);
+	if (err)
+		return err;
+
+	if (!mddev->raid_disks && !mddev->external) {
+		err = -ENODEV;
+		goto out_unlock;
+	}
+
+	/*
+	 * Transitioning to read-auto need only happen for arrays that call
+	 * md_write_start and which are not ready for writes yet.
+	 */
+	if (!ro && mddev->ro == 1 && mddev->pers) {
+		err = restart_array(mddev);
+		if (err)
+			goto out_unlock;
+		mddev->ro = 2;
+	}
+
+out_unlock:
+	mddev_unlock(mddev);
+	return err;
+}
+
 static int md_open(struct block_device *bdev, fmode_t mode)
 {
 	/*
@@ -7886,6 +7881,7 @@ const struct block_device_operations md_fops =
 #endif
 	.getgeo		= md_getgeo,
 	.check_events	= md_check_events,
+	.set_read_only	= md_set_read_only,
 };
 
 static int md_thread(void *arg)
@@ -8445,7 +8441,7 @@ static int is_mddev_idle(struct mddev *mddev, int init)
 	rcu_read_lock();
 	rdev_for_each_rcu(rdev, mddev) {
 		struct gendisk *disk = rdev->bdev->bd_disk;
-		curr_events = (int)part_stat_read_accum(&disk->part0, sectors) -
+		curr_events = (int)part_stat_read_accum(disk->part0, sectors) -
 			      atomic_read(&disk->sync_io);
 		/* sync IO will cause sync_io to increase before the disk_stats
 		 * as sync_io is counted when a request starts, and
@@ -9015,10 +9011,9 @@ void md_do_sync(struct md_thread *thread)
 		mddev_lock_nointr(mddev);
 		md_set_array_sectors(mddev, mddev->pers->size(mddev, 0, 0));
 		mddev_unlock(mddev);
-		if (!mddev_is_clustered(mddev)) {
-			set_capacity(mddev->gendisk, mddev->array_sectors);
-			revalidate_disk_size(mddev->gendisk, true);
-		}
+		if (!mddev_is_clustered(mddev))
+			set_capacity_and_notify(mddev->gendisk,
+						mddev->array_sectors);
 	}
 
 	spin_lock(&mddev->lock);
@@ -9547,18 +9542,15 @@ static int __init md_init(void)
 	if (!md_rdev_misc_wq)
 		goto err_rdev_misc_wq;
 
-	if ((ret = register_blkdev(MD_MAJOR, "md")) < 0)
+	ret = __register_blkdev(MD_MAJOR, "md", md_probe);
+	if (ret < 0)
 		goto err_md;
 
-	if ((ret = register_blkdev(0, "mdp")) < 0)
+	ret = __register_blkdev(0, "mdp", md_probe);
+	if (ret < 0)
 		goto err_mdp;
 	mdp_major = ret;
 
-	blk_register_region(MKDEV(MD_MAJOR, 0), 512, THIS_MODULE,
-			    md_probe, NULL, NULL);
-	blk_register_region(MKDEV(mdp_major, 0), 1UL<<MINORBITS, THIS_MODULE,
-			    md_probe, NULL, NULL);
-
 	register_reboot_notifier(&md_notifier);
 	raid_table_header = register_sysctl_table(raid_root_table);
 
@@ -9825,9 +9817,6 @@ static __exit void md_exit(void)
 	struct list_head *tmp;
 	int delay = 1;
 
-	blk_unregister_region(MKDEV(MD_MAJOR,0), 512);
-	blk_unregister_region(MKDEV(mdp_major,0), 1U << MINORBITS);
-
 	unregister_blkdev(MD_MAJOR,"md");
 	unregister_blkdev(mdp_major, "mdp");
 	unregister_reboot_notifier(&md_notifier);