cgroup_clone: use pid of newly created task for new cgroup

cgroup_clone creates a new cgroup with the pid of the task. This works
correctly for unshare, but for clone cgroup_clone is called from
copy_namespaces inside copy_process, which happens before the new pid is
created. As a result, the new cgroup was created with current's pid.
This patch:

1. Moves the call inside copy_process to after the new pid
is created
2. Passes the struct pid into ns_cgroup_clone (as it is not
yet attached to the task)
3. Passes a name from ns_cgroup_clone() into cgroup_clone()
so as to keep cgroup_clone() itself simpler
4. Uses pid_vnr() to get the process id value, so that the
pid used to name the new cgroup is always the pid as it
would be known to the task which did the cloning or
unsharing. I think that is the most intuitive thing to
do. This way, task t1 does clone(CLONE_NEWPID) to get
t2, which does clone(CLONE_NEWPID) to get t3, then the
cgroup for t3 will be named for the pid by which t2 knows
t3.

(Thanks to Dan Smith for finding the main bug)

Changelog:
June 11: Incorporate Paul Menage's feedback: don't pass
NULL to ns_cgroup_clone from unshare, and reduce
patch size by using 'nodename' in cgroup_clone.
June 10: Original version

[[e-mail]: build fix]
[[e-mail]: coding-style fixes]
Signed-off-by: Serge Hallyn <[e-mail]>
Acked-by: Paul Menage <[e-mail]>
Tested-by: Dan Smith <[e-mail]>
Cc: Balbir Singh <[e-mail]>
Cc: KAMEZAWA Hiroyuki <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

include/linux/cgroup.h

···
 	return task_subsys_state(task, subsys_id)->cgroup;
 }
 
-int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *ss);
+int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *ss,
+							char *nodename);
 
 /* A cgroup_iter should be treated as an opaque object */
 struct cgroup_iter {

include/linux/nsproxy.h

···
 }
 
 #ifdef CONFIG_CGROUP_NS
-int ns_cgroup_clone(struct task_struct *tsk);
+int ns_cgroup_clone(struct task_struct *tsk, struct pid *pid);
 #else
-static inline int ns_cgroup_clone(struct task_struct *tsk) { return 0; }
+static inline int ns_cgroup_clone(struct task_struct *tsk, struct pid *pid)
+{
+	return 0;
+}
 #endif
 
 #endif

kernel/cgroup.c

···
  * cgroup_clone - clone the cgroup the given subsystem is attached to
  * @tsk: the task to be moved
  * @subsys: the given subsystem
+ * @nodename: the name for the new cgroup
  *
  * Duplicate the current cgroup in the hierarchy that the given
  * subsystem is attached to, and move this task into the new
  * child.
  */
-int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys)
+int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
+							char *nodename)
 {
 	struct dentry *dentry;
 	int ret = 0;
-	char nodename[MAX_CGROUP_TYPE_NAMELEN];
 	struct cgroup *parent, *child;
 	struct inode *inode;
 	struct css_set *cg;
···
 	}
 	cg = tsk->cgroups;
 	parent = task_cgroup(tsk, subsys->subsys_id);
-
-	snprintf(nodename, MAX_CGROUP_TYPE_NAMELEN, "%d", tsk->pid);
 
 	/* Pin the hierarchy */
 	atomic_inc(&parent->root->sb->s_active);

kernel/fork.c

···
 	if (clone_flags & CLONE_THREAD)
 		p->tgid = current->tgid;
 
+	if (current->nsproxy != p->nsproxy) {
+		retval = ns_cgroup_clone(p, pid);
+		if (retval)
+			goto bad_fork_free_pid;
+	}
+
 	p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
 	/*
 	 * Clear TID on mm_release()?

kernel/ns_cgroup.c

···
 #include <linux/module.h>
 #include <linux/cgroup.h>
 #include <linux/fs.h>
+#include <linux/proc_fs.h>
 #include <linux/slab.h>
 #include <linux/nsproxy.h>
 
···
 			    struct ns_cgroup, css);
 }
 
-int ns_cgroup_clone(struct task_struct *task)
+int ns_cgroup_clone(struct task_struct *task, struct pid *pid)
 {
-	return cgroup_clone(task, &ns_subsys);
+	char name[PROC_NUMBUF];
+
+	snprintf(name, PROC_NUMBUF, "%d", pid_vnr(pid));
+	return cgroup_clone(task, &ns_subsys, name);
 }
 
 /*

kernel/nsproxy.c

···
 		goto out;
 	}
 
-	err = ns_cgroup_clone(tsk);
-	if (err) {
-		put_nsproxy(new_ns);
-		goto out;
-	}
-
 	tsk->nsproxy = new_ns;
 
 out:
···
 		goto out;
 	}
 
-	err = ns_cgroup_clone(current);
+	err = ns_cgroup_clone(current, task_pid(current));
 	if (err)
 		put_nsproxy(*new_nsp);