[PATCHv3 7/8] cgroup: mount cgroupns-root when inside non-init cgroupns

[Aditya Kali]

This patch enables cgroup mounting inside userns when a process
as appropriate privileges. The cgroup filesystem mounted is
rooted at the cgroupns-root. Thus, in a container-setup, only
the hierarchy under the cgroupns-root is exposed inside the container.
This allows container management tools to run inside the containers
without depending on any global state.
In order to support this, a new kernfs api is added to lookup the
dentry for the cgroupns-root.

Signed-off-by: Aditya Kali <adityakali@xxxxxxxxxx>
---
 fs/kernfs/mount.c      | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/kernfs.h |  2 ++
 kernel/cgroup.c        | 46 +++++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 95 insertions(+), 1 deletion(-)

diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index f973ae9..efe5e15 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -62,6 +62,54 @@ struct kernfs_root *kernfs_root_from_sb(struct super_block *sb)
 	return NULL;
 }
 
+/**
+ * kernfs_obtain_root - get a dentry for the given kernfs_node
+ * @sb: the kernfs super_block
+ * @kn: kernfs_node for which a dentry is needed
+ *
+ * This can used used by callers which want to mount only a part of the kernfs
+ * as root of the filesystem.
+ */
+struct dentry *kernfs_obtain_root(struct super_block *sb,
+				  struct kernfs_node *kn)
+{
+	struct dentry *dentry;
+	struct inode *inode;
+
+	BUG_ON(sb->s_op != &kernfs_sops);
+
+	/* inode for the given kernfs_node should already exist. */
+	inode = ilookup(sb, kn->ino);
+	if (!inode) {
+		pr_debug("kernfs: could not get inode for '");
+		pr_cont_kernfs_path(kn);
+		pr_cont("'.\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* instantiate and link root dentry */
+	dentry = d_obtain_root(inode);
+	if (!dentry) {
+		pr_debug("kernfs: could not get dentry for '");
+		pr_cont_kernfs_path(kn);
+		pr_cont("'.\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	/* If this is a new dentry, set it up. We need kernfs_mutex because this
+	 * may be called by callers other than kernfs_fill_super. */
+	mutex_lock(&kernfs_mutex);
+	if (!dentry->d_fsdata) {
+		kernfs_get(kn);
+		dentry->d_fsdata = kn;
+	} else {
+		WARN_ON(dentry->d_fsdata != kn);
+	}
+	mutex_unlock(&kernfs_mutex);
+
+	return dentry;
+}
+
 static int kernfs_fill_super(struct super_block *sb, unsigned long magic)
 {
 	struct kernfs_super_info *info = kernfs_info(sb);
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 3c2be75..b9538e0 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -274,6 +274,8 @@ void kernfs_put(struct kernfs_node *kn);
 struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry);
 struct kernfs_root *kernfs_root_from_sb(struct super_block *sb);
 
+struct dentry *kernfs_obtain_root(struct super_block *sb,
+				  struct kernfs_node *kn);
 struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
 				       unsigned int flags, void *priv);
 void kernfs_destroy_root(struct kernfs_root *root);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index b1ae6d9..e779890 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1438,6 +1438,14 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 			return -ENOENT;
 	}
 
+	/* If inside a non-init cgroup namespace, only allow default hierarchy
+	 * to be mounted.
+	 */
+	if ((current->nsproxy->cgroup_ns != &init_cgroup_ns) &&
+	    !(opts->flags & CGRP_ROOT_SANE_BEHAVIOR)) {
+		return -EINVAL;
+	}
+
 	if (opts->flags & CGRP_ROOT_SANE_BEHAVIOR) {
 		pr_warn("sane_behavior: this is still under development and its behaviors will change, proceed at your own risk\n");
 		if (nr_opts != 1) {
@@ -1630,6 +1638,15 @@ static void init_cgroup_root(struct cgroup_root *root,
 		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags);
 }
 
+struct dentry *cgroupns_get_root(struct super_block *sb,
+				 struct cgroup_namespace *ns)
+{
+	struct dentry *nsdentry;
+
+	nsdentry = kernfs_obtain_root(sb, ns->root_cgrp->kn);
+	return nsdentry;
+}
+
 static int cgroup_setup_root(struct cgroup_root *root, unsigned int ss_mask)
 {
 	LIST_HEAD(tmp_links);
@@ -1734,6 +1751,14 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 	int ret;
 	int i;
 	bool new_sb;
+	struct cgroup_namespace *ns =
+		get_cgroup_ns(current->nsproxy->cgroup_ns);
+
+	/* Check if the caller has permission to mount. */
+	if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) {
+		put_cgroup_ns(ns);
+		return ERR_PTR(-EPERM);
+	}
 
 	/*
 	 * The first time anyone tries to mount a cgroup, enable the list
@@ -1866,11 +1891,28 @@ out_free:
 	kfree(opts.release_agent);
 	kfree(opts.name);
 
-	if (ret)
+	if (ret) {
+		put_cgroup_ns(ns);
 		return ERR_PTR(ret);
+	}
 
 	dentry = kernfs_mount(fs_type, flags, root->kf_root,
 				CGROUP_SUPER_MAGIC, &new_sb);
+
+	if (!IS_ERR(dentry) && (root == &cgrp_dfl_root)) {
+		/* If this mount is for the default hierarchy in non-init cgroup
+		 * namespace, then instead of root cgroup's dentry, we return
+		 * the dentry corresponding to the cgroupns->root_cgrp.
+		 */
+		if (ns != &init_cgroup_ns) {
+			struct dentry *nsdentry;
+
+			nsdentry = cgroupns_get_root(dentry->d_sb, ns);
+			dput(dentry);
+			dentry = nsdentry;
+		}
+	}
+
 	if (IS_ERR(dentry) || !new_sb)
 		cgroup_put(&root->cgrp);
 
@@ -1883,6 +1925,7 @@ out_free:
 		deactivate_super(pinned_sb);
 	}
 
+	put_cgroup_ns(ns);
 	return dentry;
 }
 
@@ -1911,6 +1954,7 @@ static struct file_system_type cgroup_fs_type = {
 	.name = "cgroup",
 	.mount = cgroup_mount,
 	.kill_sb = cgroup_kill_sb,
+	.fs_flags = FS_USERNS_MOUNT,
 };
 
 static struct kobject *cgroup_kobj;
-- 
2.2.0.rc0.207.ga3a616c

--
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/