[PATCHv4 2/2] userns: control capabilities of some user namespaces

[Mahesh Bandewar]

From: Mahesh Bandewar 

With this new notion of "controlled" user-namespaces, the controlled
user-namespaces are marked at the time of their creation while the
capabilities of processes that belong to them are controlled using the
global mask.

Init-user-ns is always uncontrolled and a process that has SYS_ADMIN
that belongs to uncontrolled user-ns can create another (child) user-
namespace that is uncontrolled. Any other process (that either does
not have SYS_ADMIN or belongs to a controlled user-ns) can only
create a user-ns that is controlled.

global-capability-whitelist (controlled_userns_caps_whitelist) is used
at the capability check-time and keeps the semantics for the processes
that belong to uncontrolled user-ns as it is. Processes that belong to
controlled user-ns however are subjected to different checks-

   (a) if the capability in question is controlled and process belongs
   to controlled user-ns, then it's always denied.
   (b) if the capability in question is NOT controlled then fall back
   to the traditional check.

Acked-by: Serge Hallyn 
Signed-off-by: Mahesh Bandewar 
---
v4:
  Rebase
v3:
  Rebase
v2:
  Don't recalculate user-ns flags for every setns() call.
v1:
  Initial submission.

 include/linux/capability.h |  4 
 include/linux/user_namespace.h | 25 +
 kernel/capability.c|  5 +
 kernel/user_namespace.c|  4 
 security/commoncap.c   |  8 
 5 files changed, 46 insertions(+)

diff --git a/include/linux/capability.h b/include/linux/capability.h
index 7d79a4689625..383f31f066f0 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -251,6 +251,10 @@ extern bool ptracer_capable(struct task_struct *tsk, 
struct user_namespace *ns);
 extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct 
cpu_vfs_cap_data *cpu_caps);
 int proc_douserns_caps_whitelist(struct ctl_table *table, int write,
 void __user *buff, size_t *lenp, loff_t *ppos);
+/* Controlled capability is capability that is missing from the capability-mask
+ * controlled_userns_caps_whitelist controlled via sysctl.
+ */
+bool is_capability_controlled(int cap);
 
 extern int cap_convert_nscap(struct dentry *dentry, void **ivalue, size_t 
size);
 
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index d6b74b91096b..a5c48684b317 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -32,6 +32,7 @@ struct uid_gid_map { /* 64 bytes -- 1 cache line */
 };
 
 #define USERNS_SETGROUPS_ALLOWED 1UL
+#define USERNS_CONTROLLED   2UL
 
 #define USERNS_INIT_FLAGS USERNS_SETGROUPS_ALLOWED
 
@@ -112,6 +113,21 @@ static inline void put_user_ns(struct user_namespace *ns)
__put_user_ns(ns);
 }
 
+/* Controlled user-ns is the one that is created by a process that does not
+ * have CAP_SYS_ADMIN (or descended from such an user-ns).
+ * For more details please see the sysctl description of
+ * controlled_userns_caps_whitelist.
+ */
+static inline bool is_user_ns_controlled(const struct user_namespace *ns)
+{
+   return ns->flags & USERNS_CONTROLLED;
+}
+
+static inline void mark_user_ns_controlled(struct user_namespace *ns)
+{
+   ns->flags |= USERNS_CONTROLLED;
+}
+
 struct seq_operations;
 extern const struct seq_operations proc_uid_seq_operations;
 extern const struct seq_operations proc_gid_seq_operations;
@@ -170,6 +186,15 @@ static inline struct ns_common *ns_get_owner(struct 
ns_common *ns)
 {
return ERR_PTR(-EPERM);
 }
+
+static inline bool is_user_ns_controlled(const struct user_namespace *ns)
+{
+   return false;
+}
+
+static inline void mark_user_ns_controlled(struct user_namespace *ns)
+{
+}
 #endif
 
 #endif /* _LINUX_USER_H */
diff --git a/kernel/capability.c b/kernel/capability.c
index 4a859b7d4902..bffe249922de 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -511,6 +511,11 @@ bool ptracer_capable(struct task_struct *tsk, struct 
user_namespace *ns)
 }
 
 /* Controlled-userns capabilities routines */
+bool is_capability_controlled(int cap)
+{
+   return !cap_raised(controlled_userns_caps_whitelist, cap);
+}
+
 #ifdef CONFIG_SYSCTL
 int proc_douserns_caps_whitelist(struct ctl_table *table, int write,
 void __user *buff, size_t *lenp, loff_t *ppos)
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 246d4d4ce5c7..ca0556d466b6 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -141,6 +141,10 @@ int create_user_ns(struct cred *new)
goto fail_keyring;
 
set_cred_user_ns(new, ns);
+   if (!ns_capable(parent_ns, CAP_SYS_ADMIN) ||
+   is_user_ns_controlled(parent_ns))
+   mark_user_ns_controlled(ns);
+
return 0;
 fail_keyring:
 #ifdef CONFIG_PERSISTENT_KEYRINGS
diff --git a/security/commoncap.c 

[PATCHv4 2/2] userns: control capabilities of some user namespaces

[Mahesh Bandewar]

From: Mahesh Bandewar 

With this new notion of "controlled" user-namespaces, the controlled
user-namespaces are marked at the time of their creation while the
capabilities of processes that belong to them are controlled using the
global mask.

Init-user-ns is always uncontrolled and a process that has SYS_ADMIN
that belongs to uncontrolled user-ns can create another (child) user-
namespace that is uncontrolled. Any other process (that either does
not have SYS_ADMIN or belongs to a controlled user-ns) can only
create a user-ns that is controlled.

global-capability-whitelist (controlled_userns_caps_whitelist) is used
at the capability check-time and keeps the semantics for the processes
that belong to uncontrolled user-ns as it is. Processes that belong to
controlled user-ns however are subjected to different checks-

   (a) if the capability in question is controlled and process belongs
   to controlled user-ns, then it's always denied.
   (b) if the capability in question is NOT controlled then fall back
   to the traditional check.

Acked-by: Serge Hallyn 
Signed-off-by: Mahesh Bandewar 
---
v4:
  Rebase
v3:
  Rebase
v2:
  Don't recalculate user-ns flags for every setns() call.
v1:
  Initial submission.

 include/linux/capability.h |  4 
 include/linux/user_namespace.h | 25 +
 kernel/capability.c|  5 +
 kernel/user_namespace.c|  4 
 security/commoncap.c   |  8 
 5 files changed, 46 insertions(+)

diff --git a/include/linux/capability.h b/include/linux/capability.h
index 7d79a4689625..383f31f066f0 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -251,6 +251,10 @@ extern bool ptracer_capable(struct task_struct *tsk, 
struct user_namespace *ns);
 extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct 
cpu_vfs_cap_data *cpu_caps);
 int proc_douserns_caps_whitelist(struct ctl_table *table, int write,
 void __user *buff, size_t *lenp, loff_t *ppos);
+/* Controlled capability is capability that is missing from the capability-mask
+ * controlled_userns_caps_whitelist controlled via sysctl.
+ */
+bool is_capability_controlled(int cap);
 
 extern int cap_convert_nscap(struct dentry *dentry, void **ivalue, size_t 
size);
 
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index d6b74b91096b..a5c48684b317 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -32,6 +32,7 @@ struct uid_gid_map { /* 64 bytes -- 1 cache line */
 };
 
 #define USERNS_SETGROUPS_ALLOWED 1UL
+#define USERNS_CONTROLLED   2UL
 
 #define USERNS_INIT_FLAGS USERNS_SETGROUPS_ALLOWED
 
@@ -112,6 +113,21 @@ static inline void put_user_ns(struct user_namespace *ns)
__put_user_ns(ns);
 }
 
+/* Controlled user-ns is the one that is created by a process that does not
+ * have CAP_SYS_ADMIN (or descended from such an user-ns).
+ * For more details please see the sysctl description of
+ * controlled_userns_caps_whitelist.
+ */
+static inline bool is_user_ns_controlled(const struct user_namespace *ns)
+{
+   return ns->flags & USERNS_CONTROLLED;
+}
+
+static inline void mark_user_ns_controlled(struct user_namespace *ns)
+{
+   ns->flags |= USERNS_CONTROLLED;
+}
+
 struct seq_operations;
 extern const struct seq_operations proc_uid_seq_operations;
 extern const struct seq_operations proc_gid_seq_operations;
@@ -170,6 +186,15 @@ static inline struct ns_common *ns_get_owner(struct 
ns_common *ns)
 {
return ERR_PTR(-EPERM);
 }
+
+static inline bool is_user_ns_controlled(const struct user_namespace *ns)
+{
+   return false;
+}
+
+static inline void mark_user_ns_controlled(struct user_namespace *ns)
+{
+}
 #endif
 
 #endif /* _LINUX_USER_H */
diff --git a/kernel/capability.c b/kernel/capability.c
index 4a859b7d4902..bffe249922de 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -511,6 +511,11 @@ bool ptracer_capable(struct task_struct *tsk, struct 
user_namespace *ns)
 }
 
 /* Controlled-userns capabilities routines */
+bool is_capability_controlled(int cap)
+{
+   return !cap_raised(controlled_userns_caps_whitelist, cap);
+}
+
 #ifdef CONFIG_SYSCTL
 int proc_douserns_caps_whitelist(struct ctl_table *table, int write,
 void __user *buff, size_t *lenp, loff_t *ppos)
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 246d4d4ce5c7..ca0556d466b6 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -141,6 +141,10 @@ int create_user_ns(struct cred *new)
goto fail_keyring;
 
set_cred_user_ns(new, ns);
+   if (!ns_capable(parent_ns, CAP_SYS_ADMIN) ||
+   is_user_ns_controlled(parent_ns))
+   mark_user_ns_controlled(ns);
+
return 0;
 fail_keyring:
 #ifdef CONFIG_PERSISTENT_KEYRINGS
diff --git a/security/commoncap.c b/security/commoncap.c
index 4f8e09340956..5454e9c03ee8 100644
---