ns: Introduce Time Namespace

Time Namespace isolates clock values.

The kernel provides access to several clocks CLOCK_REALTIME,
CLOCK_MONOTONIC, CLOCK_BOOTTIME, etc.

CLOCK_REALTIME
      System-wide clock that measures real (i.e., wall-clock) time.

CLOCK_MONOTONIC
      Clock that cannot be set and represents monotonic time since
      some unspecified starting point.

CLOCK_BOOTTIME
      Identical to CLOCK_MONOTONIC, except it also includes any time
      that the system is suspended.

For many users, the time namespace means the ability to changes date and
time in a container (CLOCK_REALTIME). Providing per namespace notions of
CLOCK_REALTIME would be complex with a massive overhead, but has a dubious
value.

But in the context of checkpoint/restore functionality, monotonic and
boottime clocks become interesting. Both clocks are monotonic with
unspecified starting points. These clocks are widely used to measure time
slices and set timers. After restoring or migrating processes, it has to be
guaranteed that they never go backward. In an ideal case, the behavior of
these clocks should be the same as for a case when a whole system is
suspended. All this means that it is required to set CLOCK_MONOTONIC and
CLOCK_BOOTTIME clocks, which can be achieved by adding per-namespace
offsets for clocks.

A time namespace is similar to a pid namespace in the way how it is
created: unshare(CLONE_NEWTIME) system call creates a new time namespace,
but doesn't set it to the current process. Then all children of the process
will be born in the new time namespace, or a process can use the setns()
system call to join a namespace.

This scheme allows setting clock offsets for a namespace, before any
processes appear in it.

All available clone flags have been used, so CLONE_NEWTIME uses the highest
bit of CSIGNAL. It means that it can be used only with the unshare() and
the clone3() system calls.

[ tglx: Adjusted paragraph about clone3() to reality and massaged the
  	changelog a bit. ]

Co-developed-by: Dmitry Safonov <dima@arista.com>
Signed-off-by: Andrei Vagin <avagin@gmail.com>
Signed-off-by: Dmitry Safonov <dima@arista.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://criu.org/Time_namespace
Link: https://lists.openvz.org/pipermail/criu/2018-June/041504.html
Link: https://lore.kernel.org/r/20191112012724.250792-4-dima@arista.com

2 files changed, 218 insertions, 0 deletions

diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index 1867044800bb..c8f00168afe8 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -19,3 +19,4 @@ obj-$(CONFIG_TICK_ONESHOT)			+= tick-oneshot.o tick-sched.o
 obj-$(CONFIG_HAVE_GENERIC_VDSO)			+= vsyscall.o
 obj-$(CONFIG_DEBUG_FS)				+= timekeeping_debug.o
 obj-$(CONFIG_TEST_UDELAY)			+= test_udelay.o
+obj-$(CONFIG_TIME_NS)				+= namespace.o
diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
new file mode 100644
index 000000000000..2662a69e0382
--- /dev/null
+++ b/kernel/time/namespace.c
@@ -0,0 +1,217 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Author: Andrei Vagin <avagin@openvz.org>
+ * Author: Dmitry Safonov <dima@arista.com>
+ */
+
+#include <linux/time_namespace.h>
+#include <linux/user_namespace.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/task.h>
+#include <linux/proc_ns.h>
+#include <linux/export.h>
+#include <linux/time.h>
+#include <linux/slab.h>
+#include <linux/cred.h>
+#include <linux/err.h>
+
+static struct ucounts *inc_time_namespaces(struct user_namespace *ns)
+{
+	return inc_ucount(ns, current_euid(), UCOUNT_TIME_NAMESPACES);
+}
+
+static void dec_time_namespaces(struct ucounts *ucounts)
+{
+	dec_ucount(ucounts, UCOUNT_TIME_NAMESPACES);
+}
+
+/**
+ * clone_time_ns - Clone a time namespace
+ * @user_ns:	User namespace which owns a new namespace.
+ * @old_ns:	Namespace to clone
+ *
+ * Clone @old_ns and set the clone refcount to 1
+ *
+ * Return: The new namespace or ERR_PTR.
+ */
+static struct time_namespace *clone_time_ns(struct user_namespace *user_ns,
+					  struct time_namespace *old_ns)
+{
+	struct time_namespace *ns;
+	struct ucounts *ucounts;
+	int err;
+
+	err = -ENOSPC;
+	ucounts = inc_time_namespaces(user_ns);
+	if (!ucounts)
+		goto fail;
+
+	err = -ENOMEM;
+	ns = kmalloc(sizeof(*ns), GFP_KERNEL);
+	if (!ns)
+		goto fail_dec;
+
+	kref_init(&ns->kref);
+
+	err = ns_alloc_inum(&ns->ns);
+	if (err)
+		goto fail_free;
+
+	ns->ucounts = ucounts;
+	ns->ns.ops = &timens_operations;
+	ns->user_ns = get_user_ns(user_ns);
+	return ns;
+
+fail_free:
+	kfree(ns);
+fail_dec:
+	dec_time_namespaces(ucounts);
+fail:
+	return ERR_PTR(err);
+}
+
+/**
+ * copy_time_ns - Create timens_for_children from @old_ns
+ * @flags:	Cloning flags
+ * @user_ns:	User namespace which owns a new namespace.
+ * @old_ns:	Namespace to clone
+ *
+ * If CLONE_NEWTIME specified in @flags, creates a new timens_for_children;
+ * adds a refcounter to @old_ns otherwise.
+ *
+ * Return: timens_for_children namespace or ERR_PTR.
+ */
+struct time_namespace *copy_time_ns(unsigned long flags,
+	struct user_namespace *user_ns, struct time_namespace *old_ns)
+{
+	if (!(flags & CLONE_NEWTIME))
+		return get_time_ns(old_ns);
+
+	return clone_time_ns(user_ns, old_ns);
+}
+
+void free_time_ns(struct kref *kref)
+{
+	struct time_namespace *ns;
+
+	ns = container_of(kref, struct time_namespace, kref);
+	dec_time_namespaces(ns->ucounts);
+	put_user_ns(ns->user_ns);
+	ns_free_inum(&ns->ns);
+	kfree(ns);
+}
+
+static struct time_namespace *to_time_ns(struct ns_common *ns)
+{
+	return container_of(ns, struct time_namespace, ns);
+}
+
+static struct ns_common *timens_get(struct task_struct *task)
+{
+	struct time_namespace *ns = NULL;
+	struct nsproxy *nsproxy;
+
+	task_lock(task);
+	nsproxy = task->nsproxy;
+	if (nsproxy) {
+		ns = nsproxy->time_ns;
+		get_time_ns(ns);
+	}
+	task_unlock(task);
+
+	return ns ? &ns->ns : NULL;
+}
+
+static struct ns_common *timens_for_children_get(struct task_struct *task)
+{
+	struct time_namespace *ns = NULL;
+	struct nsproxy *nsproxy;
+
+	task_lock(task);
+	nsproxy = task->nsproxy;
+	if (nsproxy) {
+		ns = nsproxy->time_ns_for_children;
+		get_time_ns(ns);
+	}
+	task_unlock(task);
+
+	return ns ? &ns->ns : NULL;
+}
+
+static void timens_put(struct ns_common *ns)
+{
+	put_time_ns(to_time_ns(ns));
+}
+
+static int timens_install(struct nsproxy *nsproxy, struct ns_common *new)
+{
+	struct time_namespace *ns = to_time_ns(new);
+
+	if (!current_is_single_threaded())
+		return -EUSERS;
+
+	if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) ||
+	    !ns_capable(current_user_ns(), CAP_SYS_ADMIN))
+		return -EPERM;
+
+	get_time_ns(ns);
+	put_time_ns(nsproxy->time_ns);
+	nsproxy->time_ns = ns;
+
+	get_time_ns(ns);
+	put_time_ns(nsproxy->time_ns_for_children);
+	nsproxy->time_ns_for_children = ns;
+	return 0;
+}
+
+int timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk)
+{
+	struct ns_common *nsc = &nsproxy->time_ns_for_children->ns;
+	struct time_namespace *ns = to_time_ns(nsc);
+
+	/* create_new_namespaces() already incremented the ref counter */
+	if (nsproxy->time_ns == nsproxy->time_ns_for_children)
+		return 0;
+
+	get_time_ns(ns);
+	put_time_ns(nsproxy->time_ns);
+	nsproxy->time_ns = ns;
+
+	return 0;
+}
+
+static struct user_namespace *timens_owner(struct ns_common *ns)
+{
+	return to_time_ns(ns)->user_ns;
+}
+
+const struct proc_ns_operations timens_operations = {
+	.name		= "time",
+	.type		= CLONE_NEWTIME,
+	.get		= timens_get,
+	.put		= timens_put,
+	.install	= timens_install,
+	.owner		= timens_owner,
+};
+
+const struct proc_ns_operations timens_for_children_operations = {
+	.name		= "time_for_children",
+	.type		= CLONE_NEWTIME,
+	.get		= timens_for_children_get,
+	.put		= timens_put,
+	.install	= timens_install,
+	.owner		= timens_owner,
+};
+
+struct time_namespace init_time_ns = {
+	.kref		= KREF_INIT(3),
+	.user_ns	= &init_user_ns,
+	.ns.inum	= PROC_TIME_INIT_INO,
+	.ns.ops		= &timens_operations,
+};
+
+static int __init time_ns_init(void)
+{
+	return 0;
+}
+subsys_initcall(time_ns_init);