cgroup: simplify threadgroup locking

Note: This commit was originally committed as b5ba75b5fc0e but got
      reverted by f9f9e7b77614 due to the performance regression from
      the percpu_rwsem write down/up operations added to cgroup task
      migration path.  percpu_rwsem changes which alleviate the
      performance issue are pending for v4.4-rc1 merge window.
      Re-apply.

Now that threadgroup locking is made global, code paths around it can
be simplified.

* lock-verify-unlock-retry dancing removed from __cgroup_procs_write().

* Race protection against de_thread() removed from
  cgroup_update_dfl_csses().

Signed-off-by: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/g/55F8097A.7000206@de.ibm.com

1 files changed, 12 insertions, 33 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 115091e..2cf0f79 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2460,14 +2460,13 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 	if (!cgrp)
 		return -ENODEV;
 
-retry_find_task:
+	percpu_down_write(&cgroup_threadgroup_rwsem);
 	rcu_read_lock();
 	if (pid) {
 		tsk = find_task_by_vpid(pid);
 		if (!tsk) {
-			rcu_read_unlock();
 			ret = -ESRCH;
-			goto out_unlock_cgroup;
+			goto out_unlock_rcu;
 		}
 	} else {
 		tsk = current;
@@ -2483,37 +2482,23 @@ retry_find_task:
 	 */
 	if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) {
 		ret = -EINVAL;
-		rcu_read_unlock();
-		goto out_unlock_cgroup;
+		goto out_unlock_rcu;
 	}
 
 	get_task_struct(tsk);
 	rcu_read_unlock();
 
-	percpu_down_write(&cgroup_threadgroup_rwsem);
-	if (threadgroup) {
-		if (!thread_group_leader(tsk)) {
-			/*
-			 * a race with de_thread from another thread's exec()
-			 * may strip us of our leadership, if this happens,
-			 * there is no choice but to throw this task away and
-			 * try again; this is
-			 * "double-double-toil-and-trouble-check locking".
-			 */
-			percpu_up_write(&cgroup_threadgroup_rwsem);
-			put_task_struct(tsk);
-			goto retry_find_task;
-		}
-	}
-
 	ret = cgroup_procs_write_permission(tsk, cgrp, of);
 	if (!ret)
 		ret = cgroup_attach_task(cgrp, tsk, threadgroup);
 
-	percpu_up_write(&cgroup_threadgroup_rwsem);
-
 	put_task_struct(tsk);
-out_unlock_cgroup:
+	goto out_unlock_threadgroup;
+
+out_unlock_rcu:
+	rcu_read_unlock();
+out_unlock_threadgroup:
+	percpu_up_write(&cgroup_threadgroup_rwsem);
 	cgroup_kn_unlock(of->kn);
 	return ret ?: nbytes;
 }
@@ -2658,6 +2643,8 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 
 	lockdep_assert_held(&cgroup_mutex);
 
+	percpu_down_write(&cgroup_threadgroup_rwsem);
+
 	/* look up all csses currently attached to @cgrp's subtree */
 	down_read(&css_set_rwsem);
 	css_for_each_descendant_pre(css, cgroup_css(cgrp, NULL)) {
@@ -2713,17 +2700,8 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 				goto out_finish;
 			last_task = task;
 
-			percpu_down_write(&cgroup_threadgroup_rwsem);
-			/* raced against de_thread() from another thread? */
-			if (!thread_group_leader(task)) {
-				percpu_up_write(&cgroup_threadgroup_rwsem);
-				put_task_struct(task);
-				continue;
-			}
-
 			ret = cgroup_migrate(src_cset->dfl_cgrp, task, true);
 
-			percpu_up_write(&cgroup_threadgroup_rwsem);
 			put_task_struct(task);
 
 			if (WARN(ret, "cgroup: failed to update controllers for the default hierarchy (%d), further operations may crash or hang\n", ret))
@@ -2733,6 +2711,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 
 out_finish:
 	cgroup_migrate_finish(&preloaded_csets);
+	percpu_up_write(&cgroup_threadgroup_rwsem);
 	return ret;
 }