nsproxy: support CLONE_NEWTIME with setns()

So far setns() was missing time namespace support. This was partially due
to it simply not being implemented but also because vdso_join_timens()
could still fail which made switching to multiple namespaces atomically
problematic. This is now fixed so support CLONE_NEWTIME with setns()

Signed-off-by: Christian Brauner <[email protected]>
Reviewed-by: Andrei Vagin <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Michael Kerrisk <[email protected]>
Cc: Serge Hallyn <[email protected]>
Cc: Dmitry Safonov <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

Author: Christian Brauner

include/linux/time_namespace.h

@@ -33,6 +33,7 @@ extern struct time_namespace init_time_ns;
 #ifdef CONFIG_TIME_NS
 extern int vdso_join_timens(struct task_struct *task,
 			    struct time_namespace *ns);
+extern void timens_commit(struct task_struct *tsk, struct time_namespace *ns);
 
 static inline struct time_namespace *get_time_ns(struct time_namespace *ns)
 {
@@ -96,6 +97,11 @@ static inline int vdso_join_timens(struct task_struct *task,
 	return 0;
 }
 
+static inline void timens_commit(struct task_struct *tsk,
+				 struct time_namespace *ns)
+{
+}
+
 static inline struct time_namespace *get_time_ns(struct time_namespace *ns)
 {
 	return NULL;

kernel/nsproxy.c

@@ -262,8 +262,8 @@ void exit_task_namespaces(struct task_struct *p)
 static int check_setns_flags(unsigned long flags)
 {
 	if (!flags || (flags & ~(CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
-				 CLONE_NEWNET | CLONE_NEWUSER | CLONE_NEWPID |
-				 CLONE_NEWCGROUP)))
+				 CLONE_NEWNET | CLONE_NEWTIME | CLONE_NEWUSER |
+				 CLONE_NEWPID | CLONE_NEWCGROUP)))
 		return -EINVAL;
 
 #ifndef CONFIG_USER_NS
@@ -290,6 +290,10 @@ static int check_setns_flags(unsigned long flags)
 	if (flags & CLONE_NEWNET)
 		return -EINVAL;
 #endif
+#ifndef CONFIG_TIME_NS
+	if (flags & CLONE_NEWTIME)
+		return -EINVAL;
+#endif
 
 	return 0;
 }
@@ -464,6 +468,14 @@ static int validate_nsset(struct nsset *nsset, struct pid *pid)
 	}
 #endif
 
+#ifdef CONFIG_TIME_NS
+	if (flags & CLONE_NEWTIME) {
+		ret = validate_ns(nsset, &nsp->time_ns->ns);
+		if (ret)
+			goto out;
+	}
+#endif
+
 out:
 	if (pid_ns)
 		put_pid_ns(pid_ns);
@@ -507,6 +519,11 @@ static void commit_nsset(struct nsset *nsset)
 		exit_sem(me);
 #endif
 
+#ifdef CONFIG_TIME_NS
+	if (flags & CLONE_NEWTIME)
+		timens_commit(me, nsset->nsproxy->time_ns);
+#endif
+
 	/* transfer ownership */
 	switch_task_namespaces(me, nsset->nsproxy);
 	nsset->nsproxy = NULL;

kernel/time/namespace.c

@@ -280,7 +280,7 @@ static void timens_put(struct ns_common *ns)
 	put_time_ns(to_time_ns(ns));
 }
 
-static void timens_commit(struct task_struct *tsk, struct time_namespace *ns)
+void timens_commit(struct task_struct *tsk, struct time_namespace *ns)
 {
 	timens_set_vvar_page(tsk, ns);
 	vdso_join_timens(tsk, ns);
@@ -298,9 +298,6 @@ static int timens_install(struct nsset *nsset, struct ns_common *new)
 	    !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
-
-	timens_commit(current, ns);
-
 	get_time_ns(ns);
 	put_time_ns(nsproxy->time_ns);
 	nsproxy->time_ns = ns;