Merge branch 'for-linus' of git://neil.brown.name/md

* 'for-linus' of git://neil.brown.name/md:
  md: Fix - again - partition detection when array becomes active
  Fix over-zealous flush_disk when changing device size.
  md: avoid spinlock problem in blk_throtl_exit
  md: correctly handle probe of an 'mdp' device.
  md: don't set_capacity before array is active.
  md: Fix raid1->raid0 takeover

14 files changed, 56 insertions, 24 deletions

diff --git a/block/genhd.c b/block/genhd.c
index 6a5b772aa201..cbf1112a885c 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1355,7 +1355,7 @@ int invalidate_partition(struct gendisk *disk, int partno)
 	struct block_device *bdev = bdget_disk(disk, partno);
 	if (bdev) {
 		fsync_bdev(bdev);
-		res = __invalidate_device(bdev);
+		res = __invalidate_device(bdev, true);
 		bdput(bdev);
 	}
 	return res;
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index b9ba04fc2b34..77fc76f8aea9 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -3281,7 +3281,7 @@ static int set_geometry(unsigned int cmd, struct floppy_struct *g,
 			struct block_device *bdev = opened_bdev[cnt];
 			if (!bdev || ITYPE(drive_state[cnt].fd_device) != type)
 				continue;
-			__invalidate_device(bdev);
+			__invalidate_device(bdev, true);
 		}
 		mutex_unlock(&open_lock);
 	} else {
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 8a2f767f26d8..0ed7f6bc2a7f 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -216,7 +216,6 @@ static int linear_run (mddev_t *mddev)
 
 	if (md_check_no_bitmap(mddev))
 		return -EINVAL;
-	mddev->queue->queue_lock = &mddev->queue->__queue_lock;
 	conf = linear_conf(mddev, mddev->raid_disks);
 
 	if (!conf)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 0cc30ecda4c1..818313e277e7 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -553,6 +553,9 @@ static mddev_t * mddev_find(dev_t unit)
 {
 	mddev_t *mddev, *new = NULL;
 
+	if (unit && MAJOR(unit) != MD_MAJOR)
+		unit &= ~((1<<MdpMinorShift)-1);
+
  retry:
 	spin_lock(&all_mddevs_lock);
 
@@ -4138,10 +4141,10 @@ array_size_store(mddev_t *mddev, const char *buf, size_t len)
 	}
 
 	mddev->array_sectors = sectors;
-	set_capacity(mddev->gendisk, mddev->array_sectors);
-	if (mddev->pers)
+	if (mddev->pers) {
+		set_capacity(mddev->gendisk, mddev->array_sectors);
 		revalidate_disk(mddev->gendisk);
-
+	}
 	return len;
 }
 
@@ -4624,6 +4627,7 @@ static int do_md_run(mddev_t *mddev)
 	}
 	set_capacity(mddev->gendisk, mddev->array_sectors);
 	revalidate_disk(mddev->gendisk);
+	mddev->changed = 1;
 	kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
 out:
 	return err;
@@ -4712,6 +4716,7 @@ static void md_clean(mddev_t *mddev)
 	mddev->sync_speed_min = mddev->sync_speed_max = 0;
 	mddev->recovery = 0;
 	mddev->in_sync = 0;
+	mddev->changed = 0;
 	mddev->degraded = 0;
 	mddev->safemode = 0;
 	mddev->bitmap_info.offset = 0;
@@ -4827,6 +4832,7 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
 
 		set_capacity(disk, 0);
 		mutex_unlock(&mddev->open_mutex);
+		mddev->changed = 1;
 		revalidate_disk(disk);
 
 		if (mddev->ro)
@@ -6011,7 +6017,7 @@ static int md_open(struct block_device *bdev, fmode_t mode)
 	atomic_inc(&mddev->openers);
 	mutex_unlock(&mddev->open_mutex);
 
-	check_disk_size_change(mddev->gendisk, bdev);
+	check_disk_change(bdev);
  out:
 	return err;
 }
@@ -6026,6 +6032,21 @@ static int md_release(struct gendisk *disk, fmode_t mode)
 
 	return 0;
 }
+
+static int md_media_changed(struct gendisk *disk)
+{
+	mddev_t *mddev = disk->private_data;
+
+	return mddev->changed;
+}
+
+static int md_revalidate(struct gendisk *disk)
+{
+	mddev_t *mddev = disk->private_data;
+
+	mddev->changed = 0;
+	return 0;
+}
 static const struct block_device_operations md_fops =
 {
 	.owner		= THIS_MODULE,
@@ -6036,6 +6057,8 @@ static const struct block_device_operations md_fops =
 	.compat_ioctl	= md_compat_ioctl,
 #endif
 	.getgeo		= md_getgeo,
+	.media_changed  = md_media_changed,
+	.revalidate_disk= md_revalidate,
 };
 
 static int md_thread(void * arg)
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 7e90b8593b2a..12215d437fcc 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -274,6 +274,8 @@ struct mddev_s
 	atomic_t			active;		/* general refcount */
 	atomic_t			openers;	/* number of active opens */
 
+	int				changed;	/* True if we might need to
+							 * reread partition info */
 	int				degraded;	/* whether md should consider
 							 * adding a spare
 							 */
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 6d7ddf32ef2e..3a62d440e27b 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -435,7 +435,6 @@ static int multipath_run (mddev_t *mddev)
 	 * bookkeeping area. [whatever we allocate in multipath_run(),
 	 * should be freed in multipath_stop()]
 	 */
-	mddev->queue->queue_lock = &mddev->queue->__queue_lock;
 
 	conf = kzalloc(sizeof(multipath_conf_t), GFP_KERNEL);
 	mddev->private = conf;
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 637a96855edb..c0ac457f1218 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -361,7 +361,6 @@ static int raid0_run(mddev_t *mddev)
 	if (md_check_no_bitmap(mddev))
 		return -EINVAL;
 	blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
-	mddev->queue->queue_lock = &mddev->queue->__queue_lock;
 
 	/* if private is not null, we are here after takeover */
 	if (mddev->private == NULL) {
@@ -670,6 +669,7 @@ static void *raid0_takeover_raid1(mddev_t *mddev)
 	mddev->new_layout = 0;
 	mddev->new_chunk_sectors = 128; /* by default set chunk size to 64k */
 	mddev->delta_disks = 1 - mddev->raid_disks;
+	mddev->raid_disks = 1;
 	/* make sure it will be not marked as dirty */
 	mddev->recovery_cp = MaxSector;
 
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index a23ffa397ba9..06cd712807d0 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -593,7 +593,10 @@ static int flush_pending_writes(conf_t *conf)
 	if (conf->pending_bio_list.head) {
 		struct bio *bio;
 		bio = bio_list_get(&conf->pending_bio_list);
+		/* Only take the spinlock to quiet a warning */
+		spin_lock(conf->mddev->queue->queue_lock);
 		blk_remove_plug(conf->mddev->queue);
+		spin_unlock(conf->mddev->queue->queue_lock);
 		spin_unlock_irq(&conf->device_lock);
 		/* flush any pending bitmap writes to
 		 * disk before proceeding w/ I/O */
@@ -959,7 +962,7 @@ static int make_request(mddev_t *mddev, struct bio * bio)
 		atomic_inc(&r1_bio->remaining);
 		spin_lock_irqsave(&conf->device_lock, flags);
 		bio_list_add(&conf->pending_bio_list, mbio);
-		blk_plug_device(mddev->queue);
+		blk_plug_device_unlocked(mddev->queue);
 		spin_unlock_irqrestore(&conf->device_lock, flags);
 	}
 	r1_bio_write_done(r1_bio, bio->bi_vcnt, behind_pages, behind_pages != NULL);
@@ -2021,7 +2024,6 @@ static int run(mddev_t *mddev)
 	if (IS_ERR(conf))
 		return PTR_ERR(conf);
 
-	mddev->queue->queue_lock = &conf->device_lock;
 	list_for_each_entry(rdev, &mddev->disks, same_set) {
 		disk_stack_limits(mddev->gendisk, rdev->bdev,
 				  rdev->data_offset << 9);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 3b607b28741b..747d061d8e05 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -662,7 +662,10 @@ static int flush_pending_writes(conf_t *conf)
 	if (conf->pending_bio_list.head) {
 		struct bio *bio;
 		bio = bio_list_get(&conf->pending_bio_list);
+		/* Spinlock only taken to quiet a warning */
+		spin_lock(conf->mddev->queue->queue_lock);
 		blk_remove_plug(conf->mddev->queue);
+		spin_unlock(conf->mddev->queue->queue_lock);
 		spin_unlock_irq(&conf->device_lock);
 		/* flush any pending bitmap writes to disk
 		 * before proceeding w/ I/O */
@@ -971,7 +974,7 @@ static int make_request(mddev_t *mddev, struct bio * bio)
 		atomic_inc(&r10_bio->remaining);
 		spin_lock_irqsave(&conf->device_lock, flags);
 		bio_list_add(&conf->pending_bio_list, mbio);
-		blk_plug_device(mddev->queue);
+		blk_plug_device_unlocked(mddev->queue);
 		spin_unlock_irqrestore(&conf->device_lock, flags);
 	}
 
@@ -2304,8 +2307,6 @@ static int run(mddev_t *mddev)
 	if (!conf)
 		goto out;
 
-	mddev->queue->queue_lock = &conf->device_lock;
-
 	mddev->thread = conf->thread;
 	conf->thread = NULL;
 
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 702812824195..78536fdbd87f 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5204,7 +5204,6 @@ static int run(mddev_t *mddev)
 
 		mddev->queue->backing_dev_info.congested_data = mddev;
 		mddev->queue->backing_dev_info.congested_fn = raid5_congested;
-		mddev->queue->queue_lock = &conf->device_lock;
 		mddev->queue->unplug_fn = raid5_unplug_queue;
 
 		chunk_size = mddev->chunk_sectors << 9;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 94d41db62004..f05bf16cd979 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -933,9 +933,9 @@ EXPORT_SYMBOL_GPL(bd_unlink_disk_holder);
  * when a disk has been changed -- either by a media change or online
  * resize.
  */
-static void flush_disk(struct block_device *bdev)
+static void flush_disk(struct block_device *bdev, bool kill_dirty)
 {
-	if (__invalidate_device(bdev)) {
+	if (__invalidate_device(bdev, kill_dirty)) {
 		char name[BDEVNAME_SIZE] = "";
 
 		if (bdev->bd_disk)
@@ -972,7 +972,7 @@ void check_disk_size_change(struct gendisk *disk, struct block_device *bdev)
 		       "%s: detected capacity change from %lld to %lld\n",
 		       name, bdev_size, disk_size);
 		i_size_write(bdev->bd_inode, disk_size);
-		flush_disk(bdev);
+		flush_disk(bdev, false);
 	}
 }
 EXPORT_SYMBOL(check_disk_size_change);
@@ -1025,7 +1025,7 @@ int check_disk_change(struct block_device *bdev)
 	if (!(events & DISK_EVENT_MEDIA_CHANGE))
 		return 0;
 
-	flush_disk(bdev);
+	flush_disk(bdev, true);
 	if (bdops->revalidate_disk)
 		bdops->revalidate_disk(bdev->bd_disk);
 	return 1;
@@ -1606,7 +1606,7 @@ fail:
 }
 EXPORT_SYMBOL(lookup_bdev);
 
-int __invalidate_device(struct block_device *bdev)
+int __invalidate_device(struct block_device *bdev, bool kill_dirty)
 {
 	struct super_block *sb = get_super(bdev);
 	int res = 0;
@@ -1619,7 +1619,7 @@ int __invalidate_device(struct block_device *bdev)
 		 * hold).
 		 */
 		shrink_dcache_sb(sb);
-		res = invalidate_inodes(sb);
+		res = invalidate_inodes(sb, kill_dirty);
 		drop_super(sb);
 	}
 	invalidate_bdev(bdev);
diff --git a/fs/inode.c b/fs/inode.c
index 9c2b795ccc93..0647d80accf6 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -548,11 +548,14 @@ void evict_inodes(struct super_block *sb)
 /**
  * invalidate_inodes	- attempt to free all inodes on a superblock
  * @sb:		superblock to operate on
+ * @kill_dirty: flag to guide handling of dirty inodes
  *
  * Attempts to free all inodes for a given superblock.  If there were any
  * busy inodes return a non-zero value, else zero.
+ * If @kill_dirty is set, discard dirty inodes too, otherwise treat
+ * them as busy.
  */
-int invalidate_inodes(struct super_block *sb)
+int invalidate_inodes(struct super_block *sb, bool kill_dirty)
 {
 	int busy = 0;
 	struct inode *inode, *next;
@@ -564,6 +567,10 @@ int invalidate_inodes(struct super_block *sb)
 	list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
 		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE))
 			continue;
+		if (inode->i_state & I_DIRTY && !kill_dirty) {
+			busy = 1;
+			continue;
+		}
 		if (atomic_read(&inode->i_count)) {
 			busy = 1;
 			continue;
diff --git a/fs/internal.h b/fs/internal.h
index 0663568b1247..9b976b57d7fe 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -112,4 +112,4 @@ extern void release_open_intent(struct nameidata *);
  */
 extern int get_nr_dirty_inodes(void);
 extern void evict_inodes(struct super_block *);
-extern int invalidate_inodes(struct super_block *);
+extern int invalidate_inodes(struct super_block *, bool);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 97d08d8a7de8..e38b50a4b9d2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2140,7 +2140,7 @@ extern void check_disk_size_change(struct gendisk *disk,
 				   struct block_device *bdev);
 extern int revalidate_disk(struct gendisk *);
 extern int check_disk_change(struct block_device *);
-extern int __invalidate_device(struct block_device *);
+extern int __invalidate_device(struct block_device *, bool);
 extern int invalidate_partition(struct gendisk *, int);
 #endif
 unsigned long invalidate_mapping_pages(struct address_space *mapping,