linux-api.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [PATCH v2] pid_ns: Introduce ioctl to set vector of ns_last_pid's on ns hierarhy
@ 2017-04-27 10:57 Kirill Tkhai
       [not found] ` <149329053642.12846.16389129928422677700.stgit-bi+AKbBUZKY6gyzm1THtWbp2dZbC/Bob@public.gmane.org>
  0 siblings, 1 reply; 2+ messages in thread
From: Kirill Tkhai @ 2017-04-27 10:57 UTC (permalink / raw)
  To: agruenba-H+wXaHxf7aLQT0dZR+AlfA, keescook-F7+t8E8rja9g9hUCZPvPmw,
	linux-api-u79uwXL29TY76Z2rM5mHXA,
	linux-kernel-u79uwXL29TY76Z2rM5mHXA,
	viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn,
	oleg-H+wXaHxf7aLQT0dZR+AlfA, paul-r2n+y4ga6xFZroRs9YW3xA,
	ktkhai-5HdwGun5lf+gSpxsJD1C4w, ebiederm-aS9lmoZGLiVWk0Htik3J/w,
	avagin-GEFAQzZX7r8dnm+yROfE0A,
	linux-fsdevel-u79uwXL29TY76Z2rM5mHXA,
	mtk.manpages-Re5JQEeQqe8AvxtiuMwx3w,
	akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b,
	luto-kltTT9wpgjJwATOyAt5JVQ, gorcunov-GEFAQzZX7r8dnm+yROfE0A,
	mingo-DgEjT+Ai2ygdnm+yROfE0A, serge-A9i7LUbDfNHQT0dZR+AlfA

On implementing of nested pid namespaces support in CRIU
(checkpoint-restore in userspace tool) we run into
the situation, that it's impossible to create a task with
specific NSpid effectively. After commit 49f4d8b93ccf
"pidns: Capture the user namespace and filter ns_last_pid"
it is impossible to set ns_last_pid on any pid namespace,
except task's active pid_ns (before the commit it was possible
to write to pid_ns_for_children). Thus, if a restored task
in a container has more than one pid_ns levels, the restorer
code must have a task helper for every pid namespace
of the task's pid_ns hierarhy.

This is a big problem, because of communication with
a helper for every pid_ns in the hierarchy is not cheap.
It's not performance-good as it implies many helpers wakeups
to create a single task (independently, how you communicate
with the helpers). This patch tries to decide the problem.

It introduces a new pid_ns ioctl(NS_SET_LAST_PID_VEC),
which allows to set a vector of last pids on pid_ns hierarchy.
The vector is passed as array of pids in struct ns_ioc_pid_vec,
written in reverse order. The first number corresponds to
the opened namespace ns_last_pid, the second is to its parent, etc.
So, if you have the pid namespaces hierarchy like:

pid_ns1 (grand father)
  |
  v
pid_ns2 (father)
  |
  v
pid_ns3 (child)

and the pid_ns3 is open, then the corresponding vector will be
{last_ns_pid3, last_ns_pid2, last_ns_pid1}. This vector may be
shorter and it may contain less levels. For example,
{last_ns_pid3, last_ns_pid2} or even {last_ns_pid3}, in dependence
of which levels you want to populate.

v2: Kill pid_ns->child_reaper check as it's impossible to have
such a pid namespace file open.
Use generic namespaces ioctl() number.
Pass pids as array, not as a string.

Signed-off-by: Kirill Tkhai <ktkhai-5HdwGun5lf+gSpxsJD1C4w@public.gmane.org>
---
 fs/nsfs.c                     |    5 +++++
 include/linux/pid_namespace.h |   12 ++++++++++++
 include/uapi/linux/nsfs.h     |    7 +++++++
 kernel/pid_namespace.c        |   35 +++++++++++++++++++++++++++++++++++
 4 files changed, 59 insertions(+)

diff --git a/fs/nsfs.c b/fs/nsfs.c
index 323f492e0822..f669a1552003 100644
--- a/fs/nsfs.c
+++ b/fs/nsfs.c
@@ -6,6 +6,7 @@
 #include <linux/ktime.h>
 #include <linux/seq_file.h>
 #include <linux/user_namespace.h>
+#include <linux/pid_namespace.h>
 #include <linux/nsfs.h>
 #include <linux/uaccess.h>
 
@@ -186,6 +187,10 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl,
 		argp = (uid_t __user *) arg;
 		uid = from_kuid_munged(current_user_ns(), user_ns->owner);
 		return put_user(uid, argp);
+	case NS_SET_LAST_PID_VEC:
+		if (ns->ops->type != CLONE_NEWPID)
+			return -EINVAL;
+		return pidns_set_last_pid_vec(ns, (void *)arg);
 	default:
 		return -ENOTTY;
 	}
diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index c2a989dee876..c8dc4173a4e8 100644
--- a/include/linux/pid_namespace.h
+++ b/include/linux/pid_namespace.h
@@ -9,6 +9,7 @@
 #include <linux/nsproxy.h>
 #include <linux/kref.h>
 #include <linux/ns_common.h>
+#include <uapi/linux/nsfs.h>
 
 struct pidmap {
        atomic_t nr_free;
@@ -103,6 +104,17 @@ static inline int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd)
 }
 #endif /* CONFIG_PID_NS */
 
+#if defined(CONFIG_PID_NS) && defined(CONFIG_CHECKPOINT_RESTORE)
+extern long pidns_set_last_pid_vec(struct ns_common *ns,
+				   struct ns_ioc_pid_vec __user *vec);
+#else /* CONFIG_PID_NS && CONFIG_CHECKPOINT_RESTORE */
+static inline long pidns_set_last_pid_vec(struct ns_common *ns,
+					  struct ns_ioc_pid_vec __user *vec)
+{
+	return -ENOTTY;
+}
+#endif /* CONFIG_PID_NS && CONFIG_CHECKPOINT_RESTORE */
+
 extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk);
 void pidhash_init(void);
 void pidmap_init(void);
diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h
index 1a3ca79f466b..59adf97d1d63 100644
--- a/include/uapi/linux/nsfs.h
+++ b/include/uapi/linux/nsfs.h
@@ -14,5 +14,12 @@
 #define NS_GET_NSTYPE		_IO(NSIO, 0x3)
 /* Get owner UID (in the caller's user namespace) for a user namespace */
 #define NS_GET_OWNER_UID	_IO(NSIO, 0x4)
+/* Set a vector of ns_last_pid for a pid namespace stack */
+#define NS_SET_LAST_PID_VEC	_IO(NSIO, 0x5)
+
+struct ns_ioc_pid_vec {
+	unsigned int nr;
+	pid_t pid[0];
+};
 
 #endif /* __LINUX_NSFS_H */
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index de461aa0bf9a..f68ee8793606 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -21,6 +21,7 @@
 #include <linux/export.h>
 #include <linux/sched/task.h>
 #include <linux/sched/signal.h>
+#include <uapi/linux/nsfs.h>
 
 struct pid_cache {
 	int nr_ids;
@@ -428,6 +429,40 @@ static struct ns_common *pidns_get_parent(struct ns_common *ns)
 	return &get_pid_ns(pid_ns)->ns;
 }
 
+#ifdef CONFIG_CHECKPOINT_RESTORE
+long pidns_set_last_pid_vec(struct ns_common *ns,
+			    struct ns_ioc_pid_vec __user *vec)
+{
+	struct pid_namespace *pid_ns = to_pid_ns(ns);
+	pid_t pid, __user *pid_ptr;
+	unsigned int nr;
+
+	if (get_user(nr, &vec->nr))
+		return -EFAULT;
+	if (nr > 32 || nr < 1)
+		return -EINVAL;
+
+	pid_ptr = &vec->pid[0];
+	do {
+		if (!ns_capable(pid_ns->user_ns, CAP_SYS_ADMIN))
+			return -EPERM;
+
+		if (get_user(pid, pid_ptr))
+			return -EFAULT;
+		if (pid < 0 || pid > pid_max)
+			return -EINVAL;
+
+		/* Write directly: see the comment in pid_ns_ctl_handler() */
+		pid_ns->last_pid = pid;
+
+		pid_ns = pid_ns->parent;
+		pid_ptr++;
+	} while (--nr > 0 && pid_ns);
+
+	return nr ? -EINVAL : 0;
+}
+#endif	/* CONFIG_CHECKPOINT_RESTORE */
+
 static struct user_namespace *pidns_owner(struct ns_common *ns)
 {
 	return to_pid_ns(ns)->user_ns;

^ permalink raw reply	[flat|nested] 2+ messages in thread

* Re: [PATCH v2] pid_ns: Introduce ioctl to set vector of ns_last_pid's on ns hierarhy
       [not found] ` <149329053642.12846.16389129928422677700.stgit-bi+AKbBUZKY6gyzm1THtWbp2dZbC/Bob@public.gmane.org>
@ 2017-04-27 11:55   ` Greg KH
  0 siblings, 0 replies; 2+ messages in thread
From: Greg KH @ 2017-04-27 11:55 UTC (permalink / raw)
  To: Kirill Tkhai
  Cc: agruenba-H+wXaHxf7aLQT0dZR+AlfA, keescook-F7+t8E8rja9g9hUCZPvPmw,
	linux-api-u79uwXL29TY76Z2rM5mHXA,
	linux-kernel-u79uwXL29TY76Z2rM5mHXA,
	viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn,
	oleg-H+wXaHxf7aLQT0dZR+AlfA, paul-r2n+y4ga6xFZroRs9YW3xA,
	ebiederm-aS9lmoZGLiVWk0Htik3J/w, avagin-GEFAQzZX7r8dnm+yROfE0A,
	linux-fsdevel-u79uwXL29TY76Z2rM5mHXA,
	mtk.manpages-Re5JQEeQqe8AvxtiuMwx3w,
	akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b,
	luto-kltTT9wpgjJwATOyAt5JVQ, gorcunov-GEFAQzZX7r8dnm+yROfE0A,
	mingo-DgEjT+Ai2ygdnm+yROfE0A, serge-A9i7LUbDfNHQT0dZR+AlfA

On Thu, Apr 27, 2017 at 01:57:16PM +0300, Kirill Tkhai wrote:
> --- a/include/uapi/linux/nsfs.h
> +++ b/include/uapi/linux/nsfs.h
> @@ -14,5 +14,12 @@
>  #define NS_GET_NSTYPE		_IO(NSIO, 0x3)
>  /* Get owner UID (in the caller's user namespace) for a user namespace */
>  #define NS_GET_OWNER_UID	_IO(NSIO, 0x4)
> +/* Set a vector of ns_last_pid for a pid namespace stack */
> +#define NS_SET_LAST_PID_VEC	_IO(NSIO, 0x5)
> +
> +struct ns_ioc_pid_vec {
> +	unsigned int nr;

Please make this an explicit type, variables that cross the user/kernel
boundry should be using __u32 and friends, not vague things like "int".

thanks,

greg k-h

^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2017-04-27 11:55 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2017-04-27 10:57 [PATCH v2] pid_ns: Introduce ioctl to set vector of ns_last_pid's on ns hierarhy Kirill Tkhai
     [not found] ` <149329053642.12846.16389129928422677700.stgit-bi+AKbBUZKY6gyzm1THtWbp2dZbC/Bob@public.gmane.org>
2017-04-27 11:55   ` Greg KH

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).