[RFC PATCH bpf-next 02/12] namei: add vfs_walk_ancestors()

[Justin Suess <utilityemal77@gmail.com>]

Add a callback-based walk over a path and its ancestors, built on
__path_walk_parent(): the kernel owns the loop and the callback must
not sleep, so an rcu-walk engine can be added later without changing
the API.

Disconnected root dentries are reported to the callback instead of
terminating the walk; continuing over one resumes at the root of its
mount.  A disconnected mountpoint landed on by a mount crossing - the
one position this walk visits that a dget_parent()/follow_up() loop
never does - is additionally flagged VFS_WALK_POS_MOUNTPOINT, so
security callers can reproduce their pre-conversion evaluation
sequence exactly.

Suggested-by: NeilBrown <neil@brown.name>
Suggested-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Justin Suess <utilityemal77@gmail.com>
---
 fs/namei.c            | 76 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/namei.h | 14 ++++++++
 2 files changed, 90 insertions(+)

diff --git a/fs/namei.c b/fs/namei.c
index 808fb4bed7c4..2e6ea19714b2 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2229,6 +2229,82 @@ static struct dentry *__path_walk_parent(struct path *path, const struct path *r
 	return dget(path->dentry);
 }
 
+/**
+ * vfs_walk_ancestors - invoke a callback on a path and each of its ancestors
+ * @path: path to walk up from; the caller's path is never modified
+ * @cb: callback invoked on @path, then on each ancestor up to the real
+ *      root, crossing mount boundaries.  @cb must not sleep and returns
+ *      %VFS_WALK_CONTINUE, %VFS_WALK_STOP or a negative errno to abort the
+ *      walk.  @ancestor is only valid during the invocation; @cb must take
+ *      its own references to keep a position.
+ *      A position whose dentry is a disconnected root is flagged with
+ *      %VFS_WALK_POS_DISCONNECTED (plus %VFS_WALK_POS_MOUNTPOINT when it
+ *      is a mountpoint a mount crossing landed on rather than a parent);
+ *      if @cb continues over it, the walk resumes at the root of that
+ *      position's mount.
+ * @data: opaque argument passed to @cb
+ * @flags: %VFS_WALK_* flags; none defined yet, pass 0
+ *
+ * Returns: 0 once the real root was reached, 1 if @cb stopped the walk, or
+ * the negative errno @cb aborted with.
+ */
+int vfs_walk_ancestors(const struct path *path,
+		       int (*cb)(const struct path *ancestor,
+				 unsigned int pos_flags, void *data),
+		       void *data, unsigned int flags)
+{
+	const struct path root = {};
+	struct path walk = *path;
+	unsigned int pos_flags = 0;
+	int ret;
+
+	path_get(&walk);
+	if (unlikely(IS_ROOT(walk.dentry) &&
+		     walk.dentry != walk.mnt->mnt_root))
+		pos_flags = VFS_WALK_POS_DISCONNECTED;
+	for (;;) {
+		struct dentry *parent;
+
+		ret = cb(&walk, pos_flags, data);
+		if (ret < 0)
+			break;
+		if (ret == VFS_WALK_STOP) {
+			ret = 1;
+			break;
+		}
+
+		if (unlikely(pos_flags & VFS_WALK_POS_DISCONNECTED)) {
+			dput(walk.dentry);
+			walk.dentry = dget(walk.mnt->mnt_root);
+			pos_flags = 0;
+			continue;
+		}
+		parent = __path_walk_parent(&walk, &root, LOOKUP_BENEATH);
+		if (IS_ERR(parent)) {
+			/* The real root. */
+			ret = 0;
+			break;
+		}
+		/*
+		 * A mount crossing can step onto a disconnected root, whose
+		 * parent is itself: only then is the mountpoint itself
+		 * visited, flagged, next iteration.
+		 */
+		if (unlikely(parent == walk.dentry))
+			pos_flags = VFS_WALK_POS_DISCONNECTED |
+				    VFS_WALK_POS_MOUNTPOINT;
+		else if (unlikely(IS_ROOT(parent) &&
+				  parent != walk.mnt->mnt_root))
+			pos_flags = VFS_WALK_POS_DISCONNECTED;
+		else
+			pos_flags = 0;
+		dput(walk.dentry);
+		walk.dentry = parent;
+	}
+	path_put(&walk);
+	return ret;
+}
+
 static struct dentry *follow_dotdot(struct nameidata *nd)
 {
 	struct dentry *parent;
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 86d657b24fc6..3e198de7a0d3 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -162,6 +162,20 @@ extern int follow_down_one(struct path *);
 extern int follow_down(struct path *path, unsigned int flags);
 extern int follow_up(struct path *);
 
+/* per-position flags passed to the vfs_walk_ancestors() callback */
+#define VFS_WALK_POS_DISCONNECTED	BIT(0)
+/* the position is a mountpoint landed on by a mount crossing */
+#define VFS_WALK_POS_MOUNTPOINT		BIT(1)
+
+/* vfs_walk_ancestors() callback verdicts; negative values abort the walk */
+#define VFS_WALK_STOP		0
+#define VFS_WALK_CONTINUE	1
+
+int vfs_walk_ancestors(const struct path *path,
+		       int (*cb)(const struct path *ancestor,
+				 unsigned int pos_flags, void *data),
+		       void *data, unsigned int flags);
+
 int start_renaming(struct renamedata *rd, int lookup_flags,
 		   struct qstr *old_last, struct qstr *new_last);
 int start_renaming_dentry(struct renamedata *rd, int lookup_flags,
-- 
2.55.0