cgroup: introduce cgroup namespaces

Introduce the ability to create new cgroup namespace. The newly created
cgroup namespace remembers the cgroup of the process at the point
of creation of the cgroup namespace (referred as cgroupns-root).
The main purpose of cgroup namespace is to virtualize the contents
of /proc/self/cgroup file. Processes inside a cgroup namespace
are only able to see paths relative to their namespace root
(unless they are moved outside of their cgroupns-root, at which point
 they will see a relative path from their cgroupns-root).
For a correctly setup container this enables container-tools
(like libcontainer, lxc, lmctfy, etc.) to create completely virtualized
containers without leaking system level cgroup hierarchy to the task.
This patch only implements the 'unshare' part of the cgroupns.

Signed-off-by: Aditya Kali <adityakali@google.com>
Signed-off-by: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

4 files changed, 192 insertions, 10 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 7ad61915967f..b001c5d36bec 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -59,6 +59,9 @@
 #include <linux/delay.h>
 #include <linux/atomic.h>
 #include <linux/cpuset.h>
+#include <linux/proc_ns.h>
+#include <linux/nsproxy.h>
+#include <linux/proc_ns.h>
 #include <net/sock.h>
 
 /*
@@ -212,6 +215,15 @@ static unsigned long have_fork_callback __read_mostly;
 static unsigned long have_exit_callback __read_mostly;
 static unsigned long have_free_callback __read_mostly;
 
+/* cgroup namespace for init task */
+struct cgroup_namespace init_cgroup_ns = {
+	.count		= { .counter = 2, },
+	.user_ns	= &init_user_ns,
+	.ns.ops		= &cgroupns_operations,
+	.ns.inum	= PROC_CGROUP_INIT_INO,
+	.root_cset	= &init_css_set,
+};
+
 /* Ditto for the can_fork callback. */
 static unsigned long have_canfork_callback __read_mostly;
 
@@ -2177,6 +2189,35 @@ static struct file_system_type cgroup2_fs_type = {
 	.kill_sb = cgroup_kill_sb,
 };
 
+static char *cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen,
+				   struct cgroup_namespace *ns)
+{
+	struct cgroup *root = cset_cgroup_from_root(ns->root_cset, cgrp->root);
+	int ret;
+
+	ret = kernfs_path_from_node(cgrp->kn, root->kn, buf, buflen);
+	if (ret < 0 || ret >= buflen)
+		return NULL;
+	return buf;
+}
+
+char *cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen,
+		     struct cgroup_namespace *ns)
+{
+	char *ret;
+
+	mutex_lock(&cgroup_mutex);
+	spin_lock_bh(&css_set_lock);
+
+	ret = cgroup_path_ns_locked(cgrp, buf, buflen, ns);
+
+	spin_unlock_bh(&css_set_lock);
+	mutex_unlock(&cgroup_mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cgroup_path_ns);
+
 /**
  * task_cgroup_path - cgroup path of a task in the first cgroup hierarchy
  * @task: target task
@@ -2204,7 +2245,7 @@ char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
 
 	if (root) {
 		cgrp = task_cgroup_from_root(task, root);
-		path = cgroup_path(cgrp, buf, buflen);
+		path = cgroup_path_ns_locked(cgrp, buf, buflen, &init_cgroup_ns);
 	} else {
 		/* if no hierarchy exists, everyone is in "/" */
 		if (strlcpy(buf, "/", buflen) < buflen)
@@ -5297,6 +5338,8 @@ int __init cgroup_init(void)
 	BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files));
 	BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files));
 
+	get_user_ns(init_cgroup_ns.user_ns);
+
 	mutex_lock(&cgroup_mutex);
 
 	/* Add init_css_set to the hash table */
@@ -5438,7 +5481,8 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
 		 * " (deleted)" is appended to the cgroup path.
 		 */
 		if (cgroup_on_dfl(cgrp) || !(tsk->flags & PF_EXITING)) {
-			path = cgroup_path(cgrp, buf, PATH_MAX);
+			path = cgroup_path_ns_locked(cgrp, buf, PATH_MAX,
+						current->nsproxy->cgroup_ns);
 			if (!path) {
 				retval = -ENAMETOOLONG;
 				goto out_unlock;
@@ -5720,7 +5764,9 @@ static void cgroup_release_agent(struct work_struct *work)
 	if (!pathbuf || !agentbuf)
 		goto out;
 
-	path = cgroup_path(cgrp, pathbuf, PATH_MAX);
+	spin_lock_bh(&css_set_lock);
+	path = cgroup_path_ns_locked(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns);
+	spin_unlock_bh(&css_set_lock);
 	if (!path)
 		goto out;
 
@@ -5931,6 +5977,127 @@ void cgroup_sk_free(struct sock_cgroup_data *skcd)
 
 #endif	/* CONFIG_SOCK_CGROUP_DATA */
 
+/* cgroup namespaces */
+
+static struct cgroup_namespace *alloc_cgroup_ns(void)
+{
+	struct cgroup_namespace *new_ns;
+	int ret;
+
+	new_ns = kzalloc(sizeof(struct cgroup_namespace), GFP_KERNEL);
+	if (!new_ns)
+		return ERR_PTR(-ENOMEM);
+	ret = ns_alloc_inum(&new_ns->ns);
+	if (ret) {
+		kfree(new_ns);
+		return ERR_PTR(ret);
+	}
+	atomic_set(&new_ns->count, 1);
+	new_ns->ns.ops = &cgroupns_operations;
+	return new_ns;
+}
+
+void free_cgroup_ns(struct cgroup_namespace *ns)
+{
+	put_css_set(ns->root_cset);
+	put_user_ns(ns->user_ns);
+	ns_free_inum(&ns->ns);
+	kfree(ns);
+}
+EXPORT_SYMBOL(free_cgroup_ns);
+
+struct cgroup_namespace *copy_cgroup_ns(unsigned long flags,
+					struct user_namespace *user_ns,
+					struct cgroup_namespace *old_ns)
+{
+	struct cgroup_namespace *new_ns = NULL;
+	struct css_set *cset = NULL;
+	int err;
+
+	BUG_ON(!old_ns);
+
+	if (!(flags & CLONE_NEWCGROUP)) {
+		get_cgroup_ns(old_ns);
+		return old_ns;
+	}
+
+	/* Allow only sysadmin to create cgroup namespace. */
+	err = -EPERM;
+	if (!ns_capable(user_ns, CAP_SYS_ADMIN))
+		goto err_out;
+
+	mutex_lock(&cgroup_mutex);
+	spin_lock_bh(&css_set_lock);
+
+	cset = task_css_set(current);
+	get_css_set(cset);
+
+	spin_unlock_bh(&css_set_lock);
+	mutex_unlock(&cgroup_mutex);
+
+	err = -ENOMEM;
+	new_ns = alloc_cgroup_ns();
+	if (!new_ns)
+		goto err_out;
+
+	new_ns->user_ns = get_user_ns(user_ns);
+	new_ns->root_cset = cset;
+
+	return new_ns;
+
+err_out:
+	if (cset)
+		put_css_set(cset);
+	kfree(new_ns);
+	return ERR_PTR(err);
+}
+
+static inline struct cgroup_namespace *to_cg_ns(struct ns_common *ns)
+{
+	return container_of(ns, struct cgroup_namespace, ns);
+}
+
+static int cgroupns_install(struct nsproxy *nsproxy, void *ns)
+{
+	pr_info("setns not supported for cgroup namespace");
+	return -EINVAL;
+}
+
+static struct ns_common *cgroupns_get(struct task_struct *task)
+{
+	struct cgroup_namespace *ns = NULL;
+	struct nsproxy *nsproxy;
+
+	task_lock(task);
+	nsproxy = task->nsproxy;
+	if (nsproxy) {
+		ns = nsproxy->cgroup_ns;
+		get_cgroup_ns(ns);
+	}
+	task_unlock(task);
+
+	return ns ? &ns->ns : NULL;
+}
+
+static void cgroupns_put(struct ns_common *ns)
+{
+	put_cgroup_ns(to_cg_ns(ns));
+}
+
+const struct proc_ns_operations cgroupns_operations = {
+	.name		= "cgroup",
+	.type		= CLONE_NEWCGROUP,
+	.get		= cgroupns_get,
+	.put		= cgroupns_put,
+	.install	= cgroupns_install,
+};
+
+static __init int cgroup_namespaces_init(void)
+{
+	return 0;
+}
+subsys_initcall(cgroup_namespaces_init);
+
 #ifdef CONFIG_CGROUP_DEBUG
 static struct cgroup_subsys_state *
 debug_css_alloc(struct cgroup_subsys_state *parent_css)
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 41989ab4db57..d393125b228c 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2714,10 +2714,10 @@ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns,
 		goto out;
 
 	retval = -ENAMETOOLONG;
-	rcu_read_lock();
-	css = task_css(tsk, cpuset_cgrp_id);
-	p = cgroup_path(css->cgroup, buf, PATH_MAX);
-	rcu_read_unlock();
+	css = task_get_css(tsk, cpuset_cgrp_id);
+	p = cgroup_path_ns(css->cgroup, buf, PATH_MAX,
+			   current->nsproxy->cgroup_ns);
+	css_put(css);
 	if (!p)
 		goto out_free;
 	seq_puts(m, p);
diff --git a/kernel/fork.c b/kernel/fork.c
index 2e391c754ae7..6611a6267949 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1884,7 +1884,7 @@ static int check_unshare_flags(unsigned long unshare_flags)
 	if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND|
 				CLONE_VM|CLONE_FILES|CLONE_SYSVSEM|
 				CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET|
-				CLONE_NEWUSER|CLONE_NEWPID))
+				CLONE_NEWUSER|CLONE_NEWPID|CLONE_NEWCGROUP))
 		return -EINVAL;
 	/*
 	 * Not implemented, but pretend it works if there is nothing
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 49746c81ad8d..782102e59eed 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -25,6 +25,7 @@
 #include <linux/proc_ns.h>
 #include <linux/file.h>
 #include <linux/syscalls.h>
+#include <linux/cgroup.h>
 
 static struct kmem_cache *nsproxy_cachep;
 
@@ -39,6 +40,9 @@ struct nsproxy init_nsproxy = {
 #ifdef CONFIG_NET
 	.net_ns			= &init_net,
 #endif
+#ifdef CONFIG_CGROUPS
+	.cgroup_ns		= &init_cgroup_ns,
+#endif
 };
 
 static inline struct nsproxy *create_nsproxy(void)
@@ -92,6 +96,13 @@ static struct nsproxy *create_new_namespaces(unsigned long flags,
 		goto out_pid;
 	}
 
+	new_nsp->cgroup_ns = copy_cgroup_ns(flags, user_ns,
+					    tsk->nsproxy->cgroup_ns);
+	if (IS_ERR(new_nsp->cgroup_ns)) {
+		err = PTR_ERR(new_nsp->cgroup_ns);
+		goto out_cgroup;
+	}
+
 	new_nsp->net_ns = copy_net_ns(flags, user_ns, tsk->nsproxy->net_ns);
 	if (IS_ERR(new_nsp->net_ns)) {
 		err = PTR_ERR(new_nsp->net_ns);
@@ -101,6 +112,8 @@ static struct nsproxy *create_new_namespaces(unsigned long flags,
 	return new_nsp;
 
 out_net:
+	put_cgroup_ns(new_nsp->cgroup_ns);
+out_cgroup:
 	if (new_nsp->pid_ns_for_children)
 		put_pid_ns(new_nsp->pid_ns_for_children);
 out_pid:
@@ -128,7 +141,8 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk)
 	struct nsproxy *new_ns;
 
 	if (likely(!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
-			      CLONE_NEWPID | CLONE_NEWNET)))) {
+			      CLONE_NEWPID | CLONE_NEWNET |
+			      CLONE_NEWCGROUP)))) {
 		get_nsproxy(old_ns);
 		return 0;
 	}
@@ -165,6 +179,7 @@ void free_nsproxy(struct nsproxy *ns)
 		put_ipc_ns(ns->ipc_ns);
 	if (ns->pid_ns_for_children)
 		put_pid_ns(ns->pid_ns_for_children);
+	put_cgroup_ns(ns->cgroup_ns);
 	put_net(ns->net_ns);
 	kmem_cache_free(nsproxy_cachep, ns);
 }
@@ -180,7 +195,7 @@ int unshare_nsproxy_namespaces(unsigned long unshare_flags,
 	int err = 0;
 
 	if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
-			       CLONE_NEWNET | CLONE_NEWPID)))
+			       CLONE_NEWNET | CLONE_NEWPID | CLONE_NEWCGROUP)))
 		return 0;
 
 	user_ns = new_cred ? new_cred->user_ns : current_user_ns();