Merge tag 'for-5.5/disk-revalidate-20191122' of git://git.kernel.dk/linux-block

Pull disk revalidation updates from Jens Axboe:
 "This continues the work that Jan Kara started to thoroughly cleanup
  and consolidate how we handle rescans and revalidations"

* tag 'for-5.5/disk-revalidate-20191122' of git://git.kernel.dk/linux-block:
  block: move clearing bd_invalidated into check_disk_size_change
  block: remove (__)blkdev_reread_part as an exported API
  block: fix bdev_disk_changed for non-partitioned devices
  block: move rescan_partitions to fs/block_dev.c
  block: merge invalidate_partitions into rescan_partitions
  block: refactor rescan_partitions

7 files changed, 135 insertions, 156 deletions

diff --git a/block/ioctl.c b/block/ioctl.c
index 8756efb1419e..7ac8a66c9787 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -155,48 +155,21 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user
 	}
 }
 
-/*
- * This is an exported API for the block driver, and will not
- * acquire bd_mutex. This API should be used in case that
- * caller has held bd_mutex already.
- */
-int __blkdev_reread_part(struct block_device *bdev)
+static int blkdev_reread_part(struct block_device *bdev)
 {
-	struct gendisk *disk = bdev->bd_disk;
+	int ret;
 
-	if (!disk_part_scan_enabled(disk) || bdev != bdev->bd_contains)
+	if (!disk_part_scan_enabled(bdev->bd_disk) || bdev != bdev->bd_contains)
 		return -EINVAL;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
 
-	lockdep_assert_held(&bdev->bd_mutex);
-
-	return rescan_partitions(disk, bdev);
-}
-EXPORT_SYMBOL(__blkdev_reread_part);
-
-/*
- * This is an exported API for the block driver, and will
- * try to acquire bd_mutex. If bd_mutex has been held already
- * in current context, please call __blkdev_reread_part().
- *
- * Make sure the held locks in current context aren't required
- * in open()/close() handler and I/O path for avoiding ABBA deadlock:
- * - bd_mutex is held before calling block driver's open/close
- *   handler
- * - reading partition table may submit I/O to the block device
- */
-int blkdev_reread_part(struct block_device *bdev)
-{
-	int res;
-
 	mutex_lock(&bdev->bd_mutex);
-	res = __blkdev_reread_part(bdev);
+	ret = bdev_disk_changed(bdev, false);
 	mutex_unlock(&bdev->bd_mutex);
 
-	return res;
+	return ret;
 }
-EXPORT_SYMBOL(blkdev_reread_part);
 
 static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
 		unsigned long arg, unsigned long flags)
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 3084d4cba5c7..1d20c9cf213f 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -442,12 +442,14 @@ static bool disk_unlock_native_capacity(struct gendisk *disk)
 	}
 }
 
-static int drop_partitions(struct gendisk *disk, struct block_device *bdev)
+int blk_drop_partitions(struct gendisk *disk, struct block_device *bdev)
 {
 	struct disk_part_iter piter;
 	struct hd_struct *part;
 	int res;
 
+	if (!disk_part_scan_enabled(disk))
+		return 0;
 	if (bdev->bd_part_count || bdev->bd_super)
 		return -EBUSY;
 	res = invalidate_partition(disk, 0);
@@ -462,148 +464,124 @@ static int drop_partitions(struct gendisk *disk, struct block_device *bdev)
 	return 0;
 }
 
-int rescan_partitions(struct gendisk *disk, struct block_device *bdev)
+static bool blk_add_partition(struct gendisk *disk, struct block_device *bdev,
+		struct parsed_partitions *state, int p)
 {
-	struct parsed_partitions *state = NULL;
+	sector_t size = state->parts[p].size;
+	sector_t from = state->parts[p].from;
 	struct hd_struct *part;
-	int p, highest, res;
-rescan:
-	if (state && !IS_ERR(state)) {
-		free_partitions(state);
-		state = NULL;
+
+	if (!size)
+		return true;
+
+	if (from >= get_capacity(disk)) {
+		printk(KERN_WARNING
+		       "%s: p%d start %llu is beyond EOD, ",
+		       disk->disk_name, p, (unsigned long long) from);
+		if (disk_unlock_native_capacity(disk))
+			return false;
+		return true;
 	}
 
-	res = drop_partitions(disk, bdev);
-	if (res)
-		return res;
+	if (from + size > get_capacity(disk)) {
+		printk(KERN_WARNING
+		       "%s: p%d size %llu extends beyond EOD, ",
+		       disk->disk_name, p, (unsigned long long) size);
+
+		if (disk_unlock_native_capacity(disk))
+			return false;
+
+		/*
+		 * We can not ignore partitions of broken tables created by for
+		 * example camera firmware, but we limit them to the end of the
+		 * disk to avoid creating invalid block devices.
+		 */
+		size = get_capacity(disk) - from;
+	}
+
+	part = add_partition(disk, p, from, size, state->parts[p].flags,
+			     &state->parts[p].info);
+	if (IS_ERR(part)) {
+		printk(KERN_ERR " %s: p%d could not be added: %ld\n",
+		       disk->disk_name, p, -PTR_ERR(part));
+		return true;
+	}
+
+#ifdef CONFIG_BLK_DEV_MD
+	if (state->parts[p].flags & ADDPART_FLAG_RAID)
+		md_autodetect_dev(part_to_dev(part)->devt);
+#endif
+	return true;
+}
+
+int blk_add_partitions(struct gendisk *disk, struct block_device *bdev)
+{
+	struct parsed_partitions *state;
+	int ret = -EAGAIN, p, highest;
 
-	if (disk->fops->revalidate_disk)
-		disk->fops->revalidate_disk(disk);
-	check_disk_size_change(disk, bdev, true);
-	bdev->bd_invalidated = 0;
-	if (!get_capacity(disk) || !(state = check_partition(disk, bdev)))
+	if (!disk_part_scan_enabled(disk))
+		return 0;
+
+	state = check_partition(disk, bdev);
+	if (!state)
 		return 0;
 	if (IS_ERR(state)) {
 		/*
-		 * I/O error reading the partition table.  If any
-		 * partition code tried to read beyond EOD, retry
-		 * after unlocking native capacity.
+		 * I/O error reading the partition table.  If we tried to read
+		 * beyond EOD, retry after unlocking the native capacity.
 		 */
 		if (PTR_ERR(state) == -ENOSPC) {
 			printk(KERN_WARNING "%s: partition table beyond EOD, ",
 			       disk->disk_name);
 			if (disk_unlock_native_capacity(disk))
-				goto rescan;
+				return -EAGAIN;
 		}
 		return -EIO;
 	}
 
-	/* Partitions are not supported on zoned block devices */
+	/*
+	 * Partitions are not supported on zoned block devices.
+	 */
 	if (bdev_is_zoned(bdev)) {
 		pr_warn("%s: ignoring partition table on zoned block device\n",
 			disk->disk_name);
-		goto out;
+		ret = 0;
+		goto out_free_state;
 	}
 
 	/*
-	 * If any partition code tried to read beyond EOD, try
-	 * unlocking native capacity even if partition table is
-	 * successfully read as we could be missing some partitions.
+	 * If we read beyond EOD, try unlocking native capacity even if the
+	 * partition table was successfully read as we could be missing some
+	 * partitions.
 	 */
 	if (state->access_beyond_eod) {
 		printk(KERN_WARNING
 		       "%s: partition table partially beyond EOD, ",
 		       disk->disk_name);
 		if (disk_unlock_native_capacity(disk))
-			goto rescan;
+			goto out_free_state;
 	}
 
 	/* tell userspace that the media / partition table may have changed */
 	kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE);
 
-	/* Detect the highest partition number and preallocate
-	 * disk->part_tbl.  This is an optimization and not strictly
-	 * necessary.
+	/*
+	 * Detect the highest partition number and preallocate disk->part_tbl.
+	 * This is an optimization and not strictly necessary.
 	 */
 	for (p = 1, highest = 0; p < state->limit; p++)
 		if (state->parts[p].size)
 			highest = p;
-
 	disk_expand_part_tbl(disk, highest);
 
-	/* add partitions */
-	for (p = 1; p < state->limit; p++) {
-		sector_t size, from;
-
-		size = state->parts[p].size;
-		if (!size)
-			continue;
-
-		from = state->parts[p].from;
-		if (from >= get_capacity(disk)) {
-			printk(KERN_WARNING
-			       "%s: p%d start %llu is beyond EOD, ",
-			       disk->disk_name, p, (unsigned long long) from);
-			if (disk_unlock_native_capacity(disk))
-				goto rescan;
-			continue;
-		}
-
-		if (from + size > get_capacity(disk)) {
-			printk(KERN_WARNING
-			       "%s: p%d size %llu extends beyond EOD, ",
-			       disk->disk_name, p, (unsigned long long) size);
-
-			if (disk_unlock_native_capacity(disk)) {
-				/* free state and restart */
-				goto rescan;
-			} else {
-				/*
-				 * we can not ignore partitions of broken tables
-				 * created by for example camera firmware, but
-				 * we limit them to the end of the disk to avoid
-				 * creating invalid block devices
-				 */
-				size = get_capacity(disk) - from;
-			}
-		}
+	for (p = 1; p < state->limit; p++)
+		if (!blk_add_partition(disk, bdev, state, p))
+			goto out_free_state;
 
-		part = add_partition(disk, p, from, size,
-				     state->parts[p].flags,
-				     &state->parts[p].info);
-		if (IS_ERR(part)) {
-			printk(KERN_ERR " %s: p%d could not be added: %ld\n",
-			       disk->disk_name, p, -PTR_ERR(part));
-			continue;
-		}
-#ifdef CONFIG_BLK_DEV_MD
-		if (state->parts[p].flags & ADDPART_FLAG_RAID)
-			md_autodetect_dev(part_to_dev(part)->devt);
-#endif
-	}
-out:
+	ret = 0;
+out_free_state:
 	free_partitions(state);
-	return 0;
-}
-
-int invalidate_partitions(struct gendisk *disk, struct block_device *bdev)
-{
-	int res;
-
-	if (!bdev->bd_invalidated)
-		return 0;
-
-	res = drop_partitions(disk, bdev);
-	if (res)
-		return res;
-
-	set_capacity(disk, 0);
-	check_disk_size_change(disk, bdev, false);
-	bdev->bd_invalidated = 0;
-	/* tell userspace that the media / partition table may have changed */
-	kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE);
-
-	return 0;
+	return ret;
 }
 
 unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p)
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index ef6e251857c8..739b372a5112 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -640,7 +640,9 @@ static void loop_reread_partitions(struct loop_device *lo,
 {
 	int rc;
 
-	rc = blkdev_reread_part(bdev);
+	mutex_lock(&bdev->bd_mutex);
+	rc = bdev_disk_changed(bdev, false);
+	mutex_unlock(&bdev->bd_mutex);
 	if (rc)
 		pr_warn("%s: partition scan of loop%d (%s) failed (rc=%d)\n",
 			__func__, lo->lo_number, lo->lo_file_name, rc);
@@ -1164,10 +1166,11 @@ out_unlock:
 		 * must be at least one and it can only become zero when the
 		 * current holder is released.
 		 */
-		if (release)
-			err = __blkdev_reread_part(bdev);
-		else
-			err = blkdev_reread_part(bdev);
+		if (!release)
+			mutex_lock(&bdev->bd_mutex);
+		err = bdev_disk_changed(bdev, false);
+		if (!release)
+			mutex_unlock(&bdev->bd_mutex);
 		if (err)
 			pr_warn("%s: partition scan of loop%d failed (rc=%d)\n",
 				__func__, lo_number, err);
diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c
index 5542d9eadfe0..7d079154f849 100644
--- a/drivers/s390/block/dasd_genhd.c
+++ b/drivers/s390/block/dasd_genhd.c
@@ -116,7 +116,9 @@ int dasd_scan_partitions(struct dasd_block *block)
 		return -ENODEV;
 	}
 
-	rc = blkdev_reread_part(bdev);
+	mutex_lock(&bdev->bd_mutex);
+	rc = bdev_disk_changed(bdev, false);
+	mutex_unlock(&bdev->bd_mutex);
 	if (rc)
 		DBF_DEV_EVENT(DBF_ERR, block->base,
 				"scan partitions error, rc %d", rc);
diff --git a/fs/block_dev.c b/fs/block_dev.c
index d612468ee66b..ee63c2732fa2 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1416,8 +1416,8 @@ static void flush_disk(struct block_device *bdev, bool kill_dirty)
  * and adjusts it if it differs. When shrinking the bdev size, its all caches
  * are freed.
  */
-void check_disk_size_change(struct gendisk *disk, struct block_device *bdev,
-		bool verbose)
+static void check_disk_size_change(struct gendisk *disk,
+		struct block_device *bdev, bool verbose)
 {
 	loff_t disk_size, bdev_size;
 
@@ -1433,6 +1433,7 @@ void check_disk_size_change(struct gendisk *disk, struct block_device *bdev,
 		if (bdev_size > disk_size)
 			flush_disk(bdev, false);
 	}
+	bdev->bd_invalidated = 0;
 }
 
 /**
@@ -1462,7 +1463,6 @@ int revalidate_disk(struct gendisk *disk)
 
 		mutex_lock(&bdev->bd_mutex);
 		check_disk_size_change(disk, bdev, ret == 0);
-		bdev->bd_invalidated = 0;
 		mutex_unlock(&bdev->bd_mutex);
 		bdput(bdev);
 	}
@@ -1508,18 +1508,44 @@ EXPORT_SYMBOL(bd_set_size);
 
 static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
 
-static void bdev_disk_changed(struct block_device *bdev, bool invalidate)
+int bdev_disk_changed(struct block_device *bdev, bool invalidate)
 {
-	if (disk_part_scan_enabled(bdev->bd_disk)) {
-		if (invalidate)
-			invalidate_partitions(bdev->bd_disk, bdev);
-		else
-			rescan_partitions(bdev->bd_disk, bdev);
+	struct gendisk *disk = bdev->bd_disk;
+	int ret;
+
+	lockdep_assert_held(&bdev->bd_mutex);
+
+rescan:
+	ret = blk_drop_partitions(disk, bdev);
+	if (ret)
+		return ret;
+
+	if (invalidate)
+		set_capacity(disk, 0);
+	else if (disk->fops->revalidate_disk)
+		disk->fops->revalidate_disk(disk);
+
+	check_disk_size_change(disk, bdev, !invalidate);
+
+	if (get_capacity(disk)) {
+		ret = blk_add_partitions(disk, bdev);
+		if (ret == -EAGAIN)
+			goto rescan;
 	} else {
-		check_disk_size_change(bdev->bd_disk, bdev, !invalidate);
-		bdev->bd_invalidated = 0;
+		/*
+		 * Tell userspace that the media / partition table may have
+		 * changed.
+		 */
+		kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE);
 	}
+
+	return ret;
 }
+/*
+ * Only exported for for loop and dasd for historic reasons.  Don't use in new
+ * code!
+ */
+EXPORT_SYMBOL_GPL(bdev_disk_changed);
 
 /*
  * bd_mutex locking:
diff --git a/include/linux/fs.h b/include/linux/fs.h
index a7c3f6dd5701..dde6dc4492a0 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2630,8 +2630,6 @@ extern void bd_finish_claiming(struct block_device *bdev,
 extern void bd_abort_claiming(struct block_device *bdev,
 			      struct block_device *whole, void *holder);
 extern void blkdev_put(struct block_device *bdev, fmode_t mode);
-extern int __blkdev_reread_part(struct block_device *bdev);
-extern int blkdev_reread_part(struct block_device *bdev);
 
 #ifdef CONFIG_SYSFS
 extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
@@ -2701,8 +2699,6 @@ extern void make_bad_inode(struct inode *);
 extern bool is_bad_inode(struct inode *);
 
 #ifdef CONFIG_BLOCK
-extern void check_disk_size_change(struct gendisk *disk,
-		struct block_device *bdev, bool verbose);
 extern int revalidate_disk(struct gendisk *);
 extern int check_disk_change(struct block_device *);
 extern int __invalidate_device(struct block_device *, bool);
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 8b5330dd5ac0..8bb63027e4d6 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -621,9 +621,10 @@ extern void blk_invalidate_devt(dev_t devt);
 extern dev_t blk_lookup_devt(const char *name, int partno);
 extern char *disk_name (struct gendisk *hd, int partno, char *buf);
 
+int bdev_disk_changed(struct block_device *bdev, bool invalidate);
+int blk_add_partitions(struct gendisk *disk, struct block_device *bdev);
+int blk_drop_partitions(struct gendisk *disk, struct block_device *bdev);
 extern int disk_expand_part_tbl(struct gendisk *disk, int target);
-extern int rescan_partitions(struct gendisk *disk, struct block_device *bdev);
-extern int invalidate_partitions(struct gendisk *disk, struct block_device *bdev);
 extern struct hd_struct * __must_check add_partition(struct gendisk *disk,
 						     int partno, sector_t start,
 						     sector_t len, int flags,