[RFC 1/2] fs/super.c: add new super block sub devices super_block_dev

[Luis R. Rodriguez]

From: "Luis R. Rodriguez" <mcgrof@xxxxxxxx>

Modern filesystems are using the get_anon_bdev() for
internal notions of volumes, snapshots for a single super block
but never exposing them directly to the VFS layer. While this
works its leaves the VFS layer growing dumb over what filesystems
are doing. This creates a new super block subdevice which we can
use to start stuffing in information about the underlying bdev's
and its associated super block to start off with. This at least
now lets us implement proper support for ustat() once filesystems
are modified to use this data structure and respective helpers.

Signed-off-by: Luis R. Rodriguez <mcgrof@xxxxxxxx>
---
 fs/super.c         | 90 ++++++++++++++++++++++++++++++++++++++++++++++++++++--
 include/linux/fs.h | 10 ++++++
 2 files changed, 98 insertions(+), 2 deletions(-)

diff --git a/fs/super.c b/fs/super.c
index d20d5b1..f96ad1c 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -133,6 +133,90 @@ static unsigned long super_cache_count(struct shrinker *shrink,
 	return total_objects;
 }
 
+static bool super_dev_match(struct super_block *sb, dev_t dev)
+{
+	struct super_block_dev *sbdev;
+
+	if (sb->s_dev == dev)
+		return true;
+
+	if (list_empty(&sb->s_sbdevs))
+		return false;
+
+	list_for_each_entry(sbdev, &sb->s_sbdevs, entry)
+		if (sbdev->anon_dev ==  dev)
+			return true;
+
+	return false;
+}
+
+struct super_block_dev *get_anon_sbdev(struct super_block *sb)
+{
+	struct super_block_dev *sbdev;
+	int ret;
+
+	sbdev = kzalloc(sizeof(struct super_block_dev), GFP_USER);
+	if (!sbdev)
+		return NULL;
+
+	ret = get_anon_bdev(&sbdev->anon_dev);
+	if (ret) {
+		kfree(sbdev);
+		return NULL;
+	}
+
+	sbdev->sb = sb;
+
+	spin_lock(&sb_lock);
+	list_add_tail(&sbdev->entry, &sb->s_sbdevs);
+	spin_unlock(&sb_lock);
+
+	return sbdev;
+}
+EXPORT_SYMBOL_GPL(get_anon_sbdev);
+
+void free_anon_sbdev(struct super_block_dev *sbdev)
+{
+	struct super_block *sb;
+	struct super_block_dev *sbdev_i, *tmp;
+
+	if (!sbdev)
+		return;
+
+	sb = sbdev->sb;
+
+	spin_lock(&sb_lock);
+
+	WARN_ON(list_empty(&sb->s_sbdevs));
+
+	list_for_each_entry_safe(sbdev_i, tmp, &sb->s_sbdevs, entry) {
+		if (sbdev == sbdev_i) {
+			list_del_init(&sbdev_i->entry);
+			break;
+		}
+	}
+
+	spin_unlock(&sb_lock);
+
+	free_anon_bdev(sbdev->anon_dev);
+	kfree(sbdev);
+}
+EXPORT_SYMBOL_GPL(free_anon_sbdev);
+
+static void free_anon_sbdevs(struct super_block *sb)
+{
+	struct super_block_dev *sbdev, *tmp;
+
+	if (list_empty(&sb->s_sbdevs))
+		return;
+
+	list_for_each_entry_safe(sbdev, tmp, &sb->s_sbdevs, entry) {
+		list_del_init(&sbdev->entry);
+		free_anon_bdev(sbdev->anon_dev);
+		kfree(sbdev);
+	}
+}
+
 /**
  *	destroy_super	-	frees a superblock
  *	@s: superblock to free
@@ -150,6 +234,7 @@ static void destroy_super(struct super_block *s)
 	WARN_ON(!list_empty(&s->s_mounts));
 	kfree(s->s_subtype);
 	kfree(s->s_options);
+	free_anon_sbdevs(s);
 	kfree_rcu(s, rcu);
 }
 
@@ -188,6 +273,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 	INIT_HLIST_NODE(&s->s_instances);
 	INIT_HLIST_BL_HEAD(&s->s_anon);
 	INIT_LIST_HEAD(&s->s_inodes);
+	INIT_LIST_HEAD(&s->s_sbdevs);
 
 	if (list_lru_init(&s->s_dentry_lru))
 		goto fail;
@@ -652,7 +738,7 @@ restart:
 	spin_unlock(&sb_lock);
 	return NULL;
 }
- 
+
 struct super_block *user_get_super(dev_t dev)
 {
 	struct super_block *sb;
@@ -662,7 +748,7 @@ rescan:
 	list_for_each_entry(sb, &super_blocks, s_list) {
 		if (hlist_unhashed(&sb->s_instances))
 			continue;
-		if (sb->s_dev ==  dev) {
+		if (super_dev_match(sb, dev)) {
 			sb->s_count++;
 			spin_unlock(&sb_lock);
 			down_read(&sb->s_umount);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e11d60c..9de1128 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1172,6 +1172,13 @@ struct sb_writers {
 #endif
 };
 
+/* we can expand this to help the VFS layer with modern filesystems */
+struct super_block_dev {
+	struct super_block	*sb;
+	struct list_head	entry;		/* For struct sb->s_sbdevs */
+	dev_t			anon_dev;
+};
+
 struct super_block {
 	struct list_head	s_list;		/* Keep this first */
 	dev_t			s_dev;		/* search index; _not_ kdev_t */
@@ -1196,6 +1203,7 @@ struct super_block {
 
 	struct list_head	s_inodes;	/* all inodes */
 	struct hlist_bl_head	s_anon;		/* anonymous dentries for (nfs) exporting */
+	struct list_head	s_sbdevs;	/* internal fs dev_t */
 	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
 	struct block_device	*s_bdev;
 	struct backing_dev_info *s_bdi;
@@ -1796,6 +1804,8 @@ void deactivate_locked_super(struct super_block *sb);
 int set_anon_super(struct super_block *s, void *data);
 int get_anon_bdev(dev_t *);
 void free_anon_bdev(dev_t);
+struct super_block_dev *get_anon_sbdev(struct super_block *sb);
+void free_anon_sbdev(struct super_block_dev *sbdev);
 struct super_block *sget(struct file_system_type *type,
 			int (*test)(struct super_block *,void *),
 			int (*set)(struct super_block *,void *),
-- 
2.0.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/