cgroup: introduce cancel_attach()

Add cancel_attach() operation to struct cgroup_subsys.  cancel_attach()
can be used when can_attach() operation prepares something for the subsys,
but we should rollback what can_attach() operation has prepared if attach
task fails after we've succeeded in can_attach().
Signed-off-by: NDaisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Acked-by: NLi Zefan <lizf@cn.fujitsu.com>
Reviewed-by: NPaul Menage <menage@google.com>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Acked-by: NKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Documentation/cgroups/cgroups.txt

@@ -536,10 +536,21 @@ returns an error, this will abort the attach operation.  If a NULL
 task is passed, then a successful result indicates that *any*
 unspecified task can be moved into the cgroup. Note that this isn't
 called on a fork. If this method returns 0 (success) then this should
-remain valid while the caller holds cgroup_mutex. If threadgroup is
+remain valid while the caller holds cgroup_mutex and it is ensured that either
+attach() or cancel_attach() will be called in future. If threadgroup is
 true, then a successful result indicates that all threads in the given
 thread's threadgroup can be moved together.
 
+void cancel_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+	       struct task_struct *task, bool threadgroup)
+(cgroup_mutex held by caller)
+
+Called when a task attach operation has failed after can_attach() has succeeded.
+A subsystem whose can_attach() has some side-effects should provide this
+function, so that the subsytem can implement a rollback. If not, not necessary.
+This will be called only about subsystems whose can_attach() operation have
+succeeded.
+
 void attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
 	    struct cgroup *old_cgrp, struct task_struct *task,
 	    bool threadgroup)

include/linux/cgroup.h

@@ -428,6 +428,8 @@ struct cgroup_subsys {
 	void (*destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp);
 	int (*can_attach)(struct cgroup_subsys *ss, struct cgroup *cgrp,
 			  struct task_struct *tsk, bool threadgroup);
+	void (*cancel_attach)(struct cgroup_subsys *ss, struct cgroup *cgrp,
+			  struct task_struct *tsk, bool threadgroup);
 	void (*attach)(struct cgroup_subsys *ss, struct cgroup *cgrp,
 			struct cgroup *old_cgrp, struct task_struct *tsk,
 			bool threadgroup);

kernel/cgroup.c

@@ -1554,7 +1554,7 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 {
 	int retval = 0;
-	struct cgroup_subsys *ss;
+	struct cgroup_subsys *ss, *failed_ss = NULL;
 	struct cgroup *oldcgrp;
 	struct css_set *cg;
 	struct css_set *newcg;
@@ -1568,8 +1568,16 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 	for_each_subsys(root, ss) {
 		if (ss->can_attach) {
 			retval = ss->can_attach(ss, cgrp, tsk, false);
-			if (retval)
-				return retval;
+			if (retval) {
+				/*
+				 * Remember on which subsystem the can_attach()
+				 * failed, so that we only call cancel_attach()
+				 * against the subsystems whose can_attach()
+				 * succeeded. (See below)
+				 */
+				failed_ss = ss;
+				goto out;
+			}
 		}
 	}
 
@@ -1583,14 +1591,17 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 	 */
 	newcg = find_css_set(cg, cgrp);
 	put_css_set(cg);
-	if (!newcg)
-		return -ENOMEM;
+	if (!newcg) {
+		retval = -ENOMEM;
+		goto out;
+	}
 
 	task_lock(tsk);
 	if (tsk->flags & PF_EXITING) {
 		task_unlock(tsk);
 		put_css_set(newcg);
-		return -ESRCH;
+		retval = -ESRCH;
+		goto out;
 	}
 	rcu_assign_pointer(tsk->cgroups, newcg);
 	task_unlock(tsk);
@@ -1616,7 +1627,22 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 	 * is no longer empty.
 	 */
 	cgroup_wakeup_rmdir_waiter(cgrp);
-	return 0;
+out:
+	if (retval) {
+		for_each_subsys(root, ss) {
+			if (ss == failed_ss)
+				/*
+				 * This subsystem was the one that failed the
+				 * can_attach() check earlier, so we don't need
+				 * to call cancel_attach() against it or any
+				 * remaining subsystems.
+				 */
+				break;
+			if (ss->cancel_attach)
+				ss->cancel_attach(ss, cgrp, tsk, false);
+		}
+	}
+	return retval;
 }
 
 /*