[PATCH 3/8] cgroup: introduce cgroup namespaces

[serge . hallyn]

From: Aditya Kali <adityakali@xxxxxxxxxx>

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@xxxxxxxxxx>
Signed-off-by: Serge Hallyn <serge.hallyn@xxxxxxxxxxxxx>
---
Changelog: 2015-11-24
	- move cgroup_namespace.c into cgroup.c (and .h)
	- reformatting
	- make get_cgroup_ns return void
	- rename ns->root_cgrps to root_cset.
Changelog: 2015-12-08
	- Move init_cgroup_ns to other variable declarations
	- Remove accidental conversion of put-css_set to inline
	- Drop BUG_ON(NULL)
	- Remove unneeded pre declaration of struct cgroupns_operations.
	- cgroup.h: collect common ns declerations
---
 fs/proc/namespaces.c    |    3 +
 include/linux/cgroup.h  |   54 ++++++++++++++++--
 include/linux/nsproxy.h |    2 +
 include/linux/proc_ns.h |    4 ++
 kernel/cgroup.c         |  146 ++++++++++++++++++++++++++++++++++++++++++++++-
 kernel/fork.c           |    2 +-
 kernel/nsproxy.c        |   21 ++++++-
 7 files changed, 220 insertions(+), 12 deletions(-)

diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index f6e8354..bd61075 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -28,6 +28,9 @@ static const struct proc_ns_operations *ns_entries[] = {
 	&userns_operations,
 #endif
 	&mntns_operations,
+#ifdef CONFIG_CGROUPS
+	&cgroupns_operations,
+#endif
 };
 
 static const char *proc_ns_follow_link(struct dentry *dentry, void **cookie)
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 2b3e2314..906e348 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -17,9 +17,57 @@
 #include <linux/seq_file.h>
 #include <linux/kernfs.h>
 #include <linux/jump_label.h>
+#include <linux/nsproxy.h>
+#include <linux/types.h>
+#include <linux/ns_common.h>
+#include <linux/nsproxy.h>
+#include <linux/user_namespace.h>
 
 #include <linux/cgroup-defs.h>
 
+struct cgroup_namespace {
+	atomic_t		count;
+	struct ns_common	ns;
+	struct user_namespace	*user_ns;
+	struct css_set          *root_cset;
+};
+
+extern struct cgroup_namespace init_cgroup_ns;
+
+#ifdef CONFIG_CGROUPS
+
+void free_cgroup_ns(struct cgroup_namespace *ns);
+
+struct cgroup_namespace *copy_cgroup_ns(unsigned long flags,
+		struct user_namespace *user_ns,
+		struct cgroup_namespace *old_ns);
+
+char * cgroup_path(struct cgroup *cgrp, char *buf, size_t buflen);
+
+#else /* !CONFIG_CGROUPS */
+
+static inline void free_cgroup_ns(struct cgroup_namespace *ns) { }
+static inline struct cgroup_namespace *
+copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns,
+	       struct cgroup_namespace *old_ns)
+{
+	return old_ns;
+}
+
+#endif /* !CONFIG_CGROUPS */
+
+static inline void get_cgroup_ns(struct cgroup_namespace *ns)
+{
+	if (ns)
+		atomic_inc(&ns->count);
+}
+
+static inline void put_cgroup_ns(struct cgroup_namespace *ns)
+{
+	if (ns && atomic_dec_and_test(&ns->count))
+		free_cgroup_ns(ns);
+}
+
 #ifdef CONFIG_CGROUPS
 
 /*
@@ -509,12 +557,6 @@ static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen)
 	return kernfs_name(cgrp->kn, buf, buflen);
 }
 
-static inline char * __must_check cgroup_path(struct cgroup *cgrp, char *buf,
-					      size_t buflen)
-{
-	return kernfs_path(cgrp->kn, buf, buflen);
-}
-
 static inline void pr_cont_cgroup_name(struct cgroup *cgrp)
 {
 	pr_cont_kernfs_name(cgrp->kn);
diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h
index 35fa08f..ac0d65b 100644
--- a/include/linux/nsproxy.h
+++ b/include/linux/nsproxy.h
@@ -8,6 +8,7 @@ struct mnt_namespace;
 struct uts_namespace;
 struct ipc_namespace;
 struct pid_namespace;
+struct cgroup_namespace;
 struct fs_struct;
 
 /*
@@ -33,6 +34,7 @@ struct nsproxy {
 	struct mnt_namespace *mnt_ns;
 	struct pid_namespace *pid_ns_for_children;
 	struct net 	     *net_ns;
+	struct cgroup_namespace *cgroup_ns;
 };
 extern struct nsproxy init_nsproxy;
 
diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h
index 42dfc61..de0e771 100644
--- a/include/linux/proc_ns.h
+++ b/include/linux/proc_ns.h
@@ -9,6 +9,8 @@
 struct pid_namespace;
 struct nsproxy;
 struct path;
+struct task_struct;
+struct inode;
 
 struct proc_ns_operations {
 	const char *name;
@@ -24,6 +26,7 @@ extern const struct proc_ns_operations ipcns_operations;
 extern const struct proc_ns_operations pidns_operations;
 extern const struct proc_ns_operations userns_operations;
 extern const struct proc_ns_operations mntns_operations;
+extern const struct proc_ns_operations cgroupns_operations;
 
 /*
  * We always define these enumerators
@@ -34,6 +37,7 @@ enum {
 	PROC_UTS_INIT_INO	= 0xEFFFFFFEU,
 	PROC_USER_INIT_INO	= 0xEFFFFFFDU,
 	PROC_PID_INIT_INO	= 0xEFFFFFFCU,
+	PROC_CGROUP_INIT_INO	= 0xEFFFFFFBU,
 };
 
 #ifdef CONFIG_PROC_FS
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 7f2f007..92db64c 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -57,6 +57,9 @@
 #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
 #include <linux/kthread.h>
 #include <linux/delay.h>
+#include <linux/proc_ns.h>
+#include <linux/nsproxy.h>
+#include <linux/proc_ns.h>
 
 #include <linux/atomic.h>
 
@@ -208,6 +211,15 @@ 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 = 1, },
+	.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;
 
@@ -430,18 +442,18 @@ static inline bool cgroup_is_dead(const struct cgroup *cgrp)
 	return !(cgrp->self.flags & CSS_ONLINE);
 }
 
-static void cgroup_get(struct cgroup *cgrp)
+static inline void cgroup_get(struct cgroup *cgrp)
 {
 	WARN_ON_ONCE(cgroup_is_dead(cgrp));
 	css_get(&cgrp->self);
 }
 
-static bool cgroup_tryget(struct cgroup *cgrp)
+static inline bool cgroup_tryget(struct cgroup *cgrp)
 {
 	return css_tryget(&cgrp->self);
 }
 
-static void cgroup_put(struct cgroup *cgrp)
+static inline void cgroup_put(struct cgroup *cgrp)
 {
 	css_put(&cgrp->self);
 }
@@ -2189,6 +2201,22 @@ static struct file_system_type cgroup2_fs_type = {
 	.kill_sb = cgroup_kill_sb,
 };
 
+static char * cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen,
+			     struct cgroup_namespace *ns)
+{
+	struct cgroup *root;
+
+	root = cset_cgroup_from_root(ns->root_cset, cgrp->root);
+	return kernfs_path_from_node(root->kn, cgrp->kn, buf, buflen);
+}
+
+char * cgroup_path(struct cgroup *cgrp, char *buf, size_t buflen)
+{
+	return cgroup_path_ns(cgrp, buf, buflen,
+			current->nsproxy->cgroup_ns);
+}
+EXPORT_SYMBOL_GPL(cgroup_path);
+
 /**
  * task_cgroup_path - cgroup path of a task in the first cgroup hierarchy
  * @task: target task
@@ -5289,6 +5317,8 @@ 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 */
@@ -5805,6 +5835,116 @@ struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss)
 	return id > 0 ? idr_find(&ss->css_idr, id) : NULL;
 }
 
+/* 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;
+
+	cset = task_css_set(current);
+	get_css_set(cset);
+
+	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 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/fork.c b/kernel/fork.c
index ba7d1c0..7982fee 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1880,7 +1880,7 @@ 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 49746c8..64fe865 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 +112,9 @@ static struct nsproxy *create_new_namespaces(unsigned long flags,
 	return new_nsp;
 
 out_net:
+	if (new_nsp->cgroup_ns)
+		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 +142,8 @@ 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 +180,8 @@ 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);
+	if (ns->cgroup_ns)
+		put_cgroup_ns(ns->cgroup_ns);
 	put_net(ns->net_ns);
 	kmem_cache_free(nsproxy_cachep, ns);
 }
@@ -180,7 +197,7 @@ 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();
-- 
1.7.9.5

--
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/