1 files changed, 52 insertions, 18 deletions

diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index c758809d5bcf..0e7ae12c96d2 100644
--- a/include/linux/pid_namespace.h
+++ b/include/linux/pid_namespace.h
@@ -17,18 +17,10 @@
 struct fs_pin;
 
 #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
-/*
- * sysctl for vm.memfd_noexec
- * 0: memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL
- *	acts like MFD_EXEC was set.
- * 1: memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL
- *	acts like MFD_NOEXEC_SEAL was set.
- * 2: memfd_create() without MFD_NOEXEC_SEAL will be
- *	rejected.
- */
-#define MEMFD_NOEXEC_SCOPE_EXEC			0
-#define MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL		1
-#define MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED	2
+/* modes for vm.memfd_noexec sysctl */
+#define MEMFD_NOEXEC_SCOPE_EXEC			0 /* MFD_EXEC implied if unset */
+#define MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL		1 /* MFD_NOEXEC_SEAL implied if unset */
+#define MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED	2 /* same as 1, except MFD_EXEC rejected */
 #endif
 
 struct pid_namespace {
@@ -38,6 +30,7 @@ struct pid_namespace {
 	struct task_struct *child_reaper;
 	struct kmem_cache *pid_cachep;
 	unsigned int level;
+	int pid_max;
 	struct pid_namespace *parent;
 #ifdef CONFIG_BSD_PROCESS_ACCT
 	struct fs_pin *bacct;
@@ -46,10 +39,14 @@ struct pid_namespace {
 	struct ucounts *ucounts;
 	int reboot;	/* group exit code if this pidns was rebooted */
 	struct ns_common ns;
-#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
-	/* sysctl for vm.memfd_noexec */
+	struct work_struct	work;
+#ifdef CONFIG_SYSCTL
+	struct ctl_table_set	set;
+	struct ctl_table_header *sysctls;
+#if defined(CONFIG_MEMFD_CREATE)
 	int memfd_noexec_scope;
 #endif
+#endif
 } __randomize_layout;
 
 extern struct pid_namespace init_pid_ns;
@@ -57,19 +54,43 @@ extern struct pid_namespace init_pid_ns;
 #define PIDNS_ADDING (1U << 31)
 
 #ifdef CONFIG_PID_NS
+static inline struct pid_namespace *to_pid_ns(struct ns_common *ns)
+{
+	return container_of(ns, struct pid_namespace, ns);
+}
+
 static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns)
 {
-	if (ns != &init_pid_ns)
-		refcount_inc(&ns->ns.count);
+	ns_ref_inc(ns);
 	return ns;
 }
 
-extern struct pid_namespace *copy_pid_ns(unsigned long flags,
+#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
+static inline int pidns_memfd_noexec_scope(struct pid_namespace *ns)
+{
+	int scope = MEMFD_NOEXEC_SCOPE_EXEC;
+
+	for (; ns; ns = ns->parent)
+		scope = max(scope, READ_ONCE(ns->memfd_noexec_scope));
+
+	return scope;
+}
+#else
+static inline int pidns_memfd_noexec_scope(struct pid_namespace *ns)
+{
+	return 0;
+}
+#endif
+
+extern struct pid_namespace *copy_pid_ns(u64 flags,
 	struct user_namespace *user_ns, struct pid_namespace *ns);
 extern void zap_pid_ns_processes(struct pid_namespace *pid_ns);
 extern int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd);
 extern void put_pid_ns(struct pid_namespace *ns);
 
+extern bool pidns_is_ancestor(struct pid_namespace *child,
+			      struct pid_namespace *ancestor);
+
 #else /* !CONFIG_PID_NS */
 #include <linux/err.h>
 
@@ -78,7 +99,12 @@ static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns)
 	return ns;
 }
 
-static inline struct pid_namespace *copy_pid_ns(unsigned long flags,
+static inline int pidns_memfd_noexec_scope(struct pid_namespace *ns)
+{
+	return 0;
+}
+
+static inline struct pid_namespace *copy_pid_ns(u64 flags,
 	struct user_namespace *user_ns, struct pid_namespace *ns)
 {
 	if (flags & CLONE_NEWPID)
@@ -99,11 +125,19 @@ static inline int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd)
 {
 	return 0;
 }
+
+static inline bool pidns_is_ancestor(struct pid_namespace *child,
+				     struct pid_namespace *ancestor)
+{
+	return false;
+}
 #endif /* CONFIG_PID_NS */
 
 extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk);
 void pidhash_init(void);
 void pid_idr_init(void);
+int register_pidns_sysctls(struct pid_namespace *pidns);
+void unregister_pidns_sysctls(struct pid_namespace *pidns);
 
 static inline bool task_is_in_init_pid_ns(struct task_struct *tsk)
 {