userns: Restrict when proc and sysfs can be mounted

Only allow unprivileged mounts of proc and sysfs if they are already
mounted when the user namespace is created.

proc and sysfs are interesting because they have content that is
per namespace, and so fresh mounts are needed when new namespaces
are created while at the same time proc and sysfs have content that
is shared between every instance.

Respect the policy of who may see the shared content of proc and sysfs
by only allowing new mounts if there was an existing mount at the time
the user namespace was created.

In practice there are only two interesting cases: proc and sysfs are
mounted at their usual places, proc and sysfs are not mounted at all
(some form of mount namespace jail).

Cc: stable@vger.kernel.org
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>

6 files changed, 37 insertions, 0 deletions

diff --git a/fs/namespace.c b/fs/namespace.c
index 968d4c5..d581e45 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2763,6 +2763,27 @@ bool current_chrooted(void)
 	return chrooted;
 }
 
+void update_mnt_policy(struct user_namespace *userns)
+{
+	struct mnt_namespace *ns = current->nsproxy->mnt_ns;
+	struct mount *mnt;
+
+	down_read(&namespace_sem);
+	list_for_each_entry(mnt, &ns->list, mnt_list) {
+		switch (mnt->mnt.mnt_sb->s_magic) {
+		case SYSFS_MAGIC:
+			userns->may_mount_sysfs = true;
+			break;
+		case PROC_SUPER_MAGIC:
+			userns->may_mount_proc = true;
+			break;
+		}
+		if (userns->may_mount_sysfs && userns->may_mount_proc)
+			break;
+	}
+	up_read(&namespace_sem);
+}
+
 static void *mntns_get(struct task_struct *task)
 {
 	struct mnt_namespace *ns = NULL;
diff --git a/fs/proc/root.c b/fs/proc/root.c
index c6e9fac..9c7fab1 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -16,6 +16,7 @@
 #include <linux/sched.h>
 #include <linux/module.h>
 #include <linux/bitops.h>
+#include <linux/user_namespace.h>
 #include <linux/mount.h>
 #include <linux/pid_namespace.h>
 #include <linux/parser.h>
@@ -108,6 +109,9 @@ static struct dentry *proc_mount(struct file_system_type *fs_type,
 	} else {
 		ns = task_active_pid_ns(current);
 		options = data;
+
+		if (!current_user_ns()->may_mount_proc)
+			return ERR_PTR(-EPERM);
 	}
 
 	sb = sget(fs_type, proc_test_super, proc_set_super, flags, ns);
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index 8d924b5..afd8327 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -19,6 +19,7 @@
 #include <linux/module.h>
 #include <linux/magic.h>
 #include <linux/slab.h>
+#include <linux/user_namespace.h>
 
 #include "sysfs.h"
 
@@ -111,6 +112,9 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
 	struct super_block *sb;
 	int error;
 
+	if (!(flags & MS_KERNMOUNT) && !current_user_ns()->may_mount_sysfs)
+		return ERR_PTR(-EPERM);
+
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
 	if (!info)
 		return ERR_PTR(-ENOMEM);
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 4ce0093..b6b215f 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -26,6 +26,8 @@ struct user_namespace {
 	kuid_t			owner;
 	kgid_t			group;
 	unsigned int		proc_inum;
+	bool			may_mount_sysfs;
+	bool			may_mount_proc;
 };
 
 extern struct user_namespace init_user_ns;
@@ -82,4 +84,6 @@ static inline void put_user_ns(struct user_namespace *ns)
 
 #endif
 
+void update_mnt_policy(struct user_namespace *userns);
+
 #endif /* _LINUX_USER_H */
diff --git a/kernel/user.c b/kernel/user.c
index e81978e..8e635a1 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -51,6 +51,8 @@ struct user_namespace init_user_ns = {
 	.owner = GLOBAL_ROOT_UID,
 	.group = GLOBAL_ROOT_GID,
 	.proc_inum = PROC_USER_INIT_INO,
+	.may_mount_sysfs = true,
+	.may_mount_proc = true,
 };
 EXPORT_SYMBOL_GPL(init_user_ns);
 
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 0f1e428..a54f26f 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -96,6 +96,8 @@ int create_user_ns(struct cred *new)
 
 	set_cred_user_ns(new, ns);
 
+	update_mnt_policy(ns);
+
 	return 0;
 }