1 files changed, 41 insertions, 35 deletions

diff --git a/fs/super.c b/fs/super.c
index 34afe411cf2b..e781226e2880 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -54,7 +54,7 @@ static char *sb_writers_name[SB_FREEZE_LEVELS] = {
  * One thing we have to be careful of with a per-sb shrinker is that we don't
  * drop the last active reference to the superblock from within the shrinker.
  * If that happens we could trigger unregistering the shrinker from within the
- * shrinker path and that leads to deadlock on the shrinker_mutex. Hence we
+ * shrinker path and that leads to deadlock on the shrinker_rwsem. Hence we
  * take a passive reference to the superblock to avoid this from occurring.
  */
 static unsigned long super_cache_scan(struct shrinker *shrink,
@@ -236,7 +236,6 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags,
 					&type->s_writers_key[i]))
 			goto fail;
 	}
-	init_waitqueue_head(&s->s_writers.wait_unfrozen);
 	s->s_bdi = &noop_backing_dev_info;
 	s->s_flags = flags;
 	if (s->s_user_ns != &init_user_ns)
@@ -595,7 +594,7 @@ retry:
 	fc->s_fs_info = NULL;
 	s->s_type = fc->fs_type;
 	s->s_iflags |= fc->s_iflags;
-	strlcpy(s->s_id, s->s_type->name, sizeof(s->s_id));
+	strscpy(s->s_id, s->s_type->name, sizeof(s->s_id));
 	list_add_tail(&s->s_list, &super_blocks);
 	hlist_add_head(&s->s_instances, &s->s_type->fs_supers);
 	spin_unlock(&sb_lock);
@@ -674,7 +673,7 @@ retry:
 		return ERR_PTR(err);
 	}
 	s->s_type = type;
-	strlcpy(s->s_id, type->name, sizeof(s->s_id));
+	strscpy(s->s_id, type->name, sizeof(s->s_id));
 	list_add_tail(&s->s_list, &super_blocks);
 	hlist_add_head(&s->s_instances, &type->fs_supers);
 	spin_unlock(&sb_lock);
@@ -903,6 +902,7 @@ int reconfigure_super(struct fs_context *fc)
 	struct super_block *sb = fc->root->d_sb;
 	int retval;
 	bool remount_ro = false;
+	bool remount_rw = false;
 	bool force = fc->sb_flags & SB_FORCE;
 
 	if (fc->sb_flags_mask & ~MS_RMT_MASK)
@@ -920,7 +920,7 @@ int reconfigure_super(struct fs_context *fc)
 		    bdev_read_only(sb->s_bdev))
 			return -EACCES;
 #endif
-
+		remount_rw = !(fc->sb_flags & SB_RDONLY) && sb_rdonly(sb);
 		remount_ro = (fc->sb_flags & SB_RDONLY) && !sb_rdonly(sb);
 	}
 
@@ -943,13 +943,18 @@ int reconfigure_super(struct fs_context *fc)
 	 */
 	if (remount_ro) {
 		if (force) {
-			sb->s_readonly_remount = 1;
-			smp_wmb();
+			sb_start_ro_state_change(sb);
 		} else {
 			retval = sb_prepare_remount_readonly(sb);
 			if (retval)
 				return retval;
 		}
+	} else if (remount_rw) {
+		/*
+		 * Protect filesystem's reconfigure code from writes from
+		 * userspace until reconfigure finishes.
+		 */
+		sb_start_ro_state_change(sb);
 	}
 
 	if (fc->ops->reconfigure) {
@@ -965,9 +970,7 @@ int reconfigure_super(struct fs_context *fc)
 
 	WRITE_ONCE(sb->s_flags, ((sb->s_flags & ~fc->sb_flags_mask) |
 				 (fc->sb_flags & fc->sb_flags_mask)));
-	/* Needs to be ordered wrt mnt_is_readonly() */
-	smp_wmb();
-	sb->s_readonly_remount = 0;
+	sb_end_ro_state_change(sb);
 
 	/*
 	 * Some filesystems modify their metadata via some other path than the
@@ -982,7 +985,7 @@ int reconfigure_super(struct fs_context *fc)
 	return 0;
 
 cancel_readonly:
-	sb->s_readonly_remount = 0;
+	sb_end_ro_state_change(sb);
 	return retval;
 }
 
@@ -1206,6 +1209,22 @@ int get_tree_keyed(struct fs_context *fc,
 EXPORT_SYMBOL(get_tree_keyed);
 
 #ifdef CONFIG_BLOCK
+static void fs_mark_dead(struct block_device *bdev)
+{
+	struct super_block *sb;
+
+	sb = get_super(bdev);
+	if (!sb)
+		return;
+
+	if (sb->s_op->shutdown)
+		sb->s_op->shutdown(sb);
+	drop_super(sb);
+}
+
+static const struct blk_holder_ops fs_holder_ops = {
+	.mark_dead		= fs_mark_dead,
+};
 
 static int set_bdev_super(struct super_block *s, void *data)
 {
@@ -1239,16 +1258,13 @@ int get_tree_bdev(struct fs_context *fc,
 {
 	struct block_device *bdev;
 	struct super_block *s;
-	fmode_t mode = FMODE_READ | FMODE_EXCL;
 	int error = 0;
 
-	if (!(fc->sb_flags & SB_RDONLY))
-		mode |= FMODE_WRITE;
-
 	if (!fc->source)
 		return invalf(fc, "No source specified");
 
-	bdev = blkdev_get_by_path(fc->source, mode, fc->fs_type);
+	bdev = blkdev_get_by_path(fc->source, sb_open_mode(fc->sb_flags),
+				  fc->fs_type, &fs_holder_ops);
 	if (IS_ERR(bdev)) {
 		errorf(fc, "%s: Can't open blockdev", fc->source);
 		return PTR_ERR(bdev);
@@ -1262,7 +1278,7 @@ int get_tree_bdev(struct fs_context *fc,
 	if (bdev->bd_fsfreeze_count > 0) {
 		mutex_unlock(&bdev->bd_fsfreeze_mutex);
 		warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev);
-		blkdev_put(bdev, mode);
+		blkdev_put(bdev, fc->fs_type);
 		return -EBUSY;
 	}
 
@@ -1271,7 +1287,7 @@ int get_tree_bdev(struct fs_context *fc,
 	s = sget_fc(fc, test_bdev_super_fc, set_bdev_super_fc);
 	mutex_unlock(&bdev->bd_fsfreeze_mutex);
 	if (IS_ERR(s)) {
-		blkdev_put(bdev, mode);
+		blkdev_put(bdev, fc->fs_type);
 		return PTR_ERR(s);
 	}
 
@@ -1280,7 +1296,7 @@ int get_tree_bdev(struct fs_context *fc,
 		if ((fc->sb_flags ^ s->s_flags) & SB_RDONLY) {
 			warnf(fc, "%pg: Can't mount, would change RO state", bdev);
 			deactivate_locked_super(s);
-			blkdev_put(bdev, mode);
+			blkdev_put(bdev, fc->fs_type);
 			return -EBUSY;
 		}
 
@@ -1292,10 +1308,9 @@ int get_tree_bdev(struct fs_context *fc,
 		 * holding an active reference.
 		 */
 		up_write(&s->s_umount);
-		blkdev_put(bdev, mode);
+		blkdev_put(bdev, fc->fs_type);
 		down_write(&s->s_umount);
 	} else {
-		s->s_mode = mode;
 		snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
 		shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s",
 					fc->fs_type->name, s->s_id);
@@ -1327,13 +1342,10 @@ struct dentry *mount_bdev(struct file_system_type *fs_type,
 {
 	struct block_device *bdev;
 	struct super_block *s;
-	fmode_t mode = FMODE_READ | FMODE_EXCL;
 	int error = 0;
 
-	if (!(flags & SB_RDONLY))
-		mode |= FMODE_WRITE;
-
-	bdev = blkdev_get_by_path(dev_name, mode, fs_type);
+	bdev = blkdev_get_by_path(dev_name, sb_open_mode(flags), fs_type,
+				  &fs_holder_ops);
 	if (IS_ERR(bdev))
 		return ERR_CAST(bdev);
 
@@ -1369,10 +1381,9 @@ struct dentry *mount_bdev(struct file_system_type *fs_type,
 		 * holding an active reference.
 		 */
 		up_write(&s->s_umount);
-		blkdev_put(bdev, mode);
+		blkdev_put(bdev, fs_type);
 		down_write(&s->s_umount);
 	} else {
-		s->s_mode = mode;
 		snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
 		shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s",
 					fs_type->name, s->s_id);
@@ -1392,7 +1403,7 @@ struct dentry *mount_bdev(struct file_system_type *fs_type,
 error_s:
 	error = PTR_ERR(s);
 error_bdev:
-	blkdev_put(bdev, mode);
+	blkdev_put(bdev, fs_type);
 error:
 	return ERR_PTR(error);
 }
@@ -1401,13 +1412,11 @@ EXPORT_SYMBOL(mount_bdev);
 void kill_block_super(struct super_block *sb)
 {
 	struct block_device *bdev = sb->s_bdev;
-	fmode_t mode = sb->s_mode;
 
 	bdev->bd_super = NULL;
 	generic_shutdown_super(sb);
 	sync_blockdev(bdev);
-	WARN_ON_ONCE(!(mode & FMODE_EXCL));
-	blkdev_put(bdev, mode | FMODE_EXCL);
+	blkdev_put(bdev, sb->s_type);
 }
 
 EXPORT_SYMBOL(kill_block_super);
@@ -1706,7 +1715,6 @@ int freeze_super(struct super_block *sb)
 	if (ret) {
 		sb->s_writers.frozen = SB_UNFROZEN;
 		sb_freeze_unlock(sb, SB_FREEZE_PAGEFAULT);
-		wake_up(&sb->s_writers.wait_unfrozen);
 		deactivate_locked_super(sb);
 		return ret;
 	}
@@ -1722,7 +1730,6 @@ int freeze_super(struct super_block *sb)
 				"VFS:Filesystem freeze failed\n");
 			sb->s_writers.frozen = SB_UNFROZEN;
 			sb_freeze_unlock(sb, SB_FREEZE_FS);
-			wake_up(&sb->s_writers.wait_unfrozen);
 			deactivate_locked_super(sb);
 			return ret;
 		}
@@ -1768,7 +1775,6 @@ static int thaw_super_locked(struct super_block *sb)
 	sb->s_writers.frozen = SB_UNFROZEN;
 	sb_freeze_unlock(sb, SB_FREEZE_FS);
 out:
-	wake_up(&sb->s_writers.wait_unfrozen);
 	deactivate_locked_super(sb);
 	return 0;
 }