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>

diff --git a/fs/namespace.c b/fs/namespace.c
index 968d4c5eae03aa18b1326e09371aa5ada795939e..d581e45c0a9fd6ada94edd2bb6ea4fe4c7fc9e23 100644 (file)
--- 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 c6e9fac26bace4e9b63bd57dce624589dc67dfd7..9c7fab1d23f0d17d68446bf3d46ce1a906ae0907 100644 (file)
--- 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 8d924b5ec733450e37599c8338ab69ea3b15027f..afd83273e6cea8112e1570c8835bfa829303b2f8 100644 (file)
--- 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 4ce009324933ebc2b048ebd5f834b0c1bf44e52d..b6b215f13b453091ff2be0fae11b37a5a51c0c84 100644 (file)
--- 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 e81978e8c03b2b5f1a38d62248d8408fbfcd2d13..8e635a18ab521e48cfc4195cfb9f199de5e0c3b3 100644 (file)
--- 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 0f1e42884577c93b891a7da6aa149733ba2d5141..a54f26f82eb250a60c7f24ecc651c6c1bbf8cc88 100644 (file)
--- 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;
 }