sysctl: add the kernel.ns_last_pid control

The sysctl works on the current task's pid namespace, getting and setting
its last_pid field.

Writing is allowed for CAP_SYS_ADMIN-capable tasks thus making it possible
to create a task with desired pid value.  This ability is required badly
for the checkpoint/restore in userspace.

This approach suits all the parties for now.

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Acked-by: Tejun Heo <tj@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Serge Hallyn <serue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 42 insertions, 1 deletions

diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 6d8cd8b2c30d..8c20fbd8b42d 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -415,6 +415,14 @@ PIDs of value pid_max or larger are not allocated.
 
 ==============================================================
 
+ns_last_pid:
+
+The last pid allocated in the current (the one task using this sysctl
+lives in) pid namespace. When selecting a pid for a next task on fork
+kernel tries to allocate a number starting from this one.
+
+==============================================================
+
 powersave-nap: (PPC only)
 
 If set, Linux-PPC will use the 'nap' mode of powersaving,
diff --git a/kernel/pid.c b/kernel/pid.c
index fa5f72227e5f..ce8e00deaccb 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -137,7 +137,9 @@ static int pid_before(int base, int a, int b)
 }
 
 /*
- * We might be racing with someone else trying to set pid_ns->last_pid.
+ * We might be racing with someone else trying to set pid_ns->last_pid
+ * at the pid allocation time (there's also a sysctl for this, but racing
+ * with this one is OK, see comment in kernel/pid_namespace.c about it).
  * We want the winner to have the "later" value, because if the
  * "earlier" value prevails, then a pid may get reused immediately.
  *
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index e9c9adc84ca6..a8968396046d 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -191,9 +191,40 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
         return;
 }
 
+static int pid_ns_ctl_handler(struct ctl_table *table, int write,
+                void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+        struct ctl_table tmp = *table;
+
+        if (write && !capable(CAP_SYS_ADMIN))
+                return -EPERM;
+
+        /*
+         * Writing directly to ns' last_pid field is OK, since this field
+         * is volatile in a living namespace anyway and a code writing to
+         * it should synchronize its usage with external means.
+         */
+
+        tmp.data = &current->nsproxy->pid_ns->last_pid;
+        return proc_dointvec(&tmp, write, buffer, lenp, ppos);
+}
+
+static struct ctl_table pid_ns_ctl_table[] = {
+        {
+                .procname = "ns_last_pid",
+                .maxlen = sizeof(int),
+                .mode = 0666, /* permissions are checked in the handler */
+                .proc_handler = pid_ns_ctl_handler,
+        },
+        { }
+};
+
+static struct ctl_path kern_path[] = { { .procname = "kernel", }, { } };
+
 static __init int pid_namespaces_init(void)
 {
         pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC);
+        register_sysctl_paths(kern_path, pid_ns_ctl_table);
         return 0;
 }