Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit f9f9e7b7 authored by Tejun Heo's avatar Tejun Heo
Browse files

Revert "cgroup: simplify threadgroup locking" 



This reverts commit b5ba75b5.

d59cfc09 ("sched, cgroup: replace signal_struct->group_rwsem with
a global percpu_rwsem") and b5ba75b5 ("cgroup: simplify
threadgroup locking") changed how cgroup synchronizes against task
fork and exits so that it uses global percpu_rwsem instead of
per-process rwsem; unfortunately, the write [un]lock paths of
percpu_rwsem always involve synchronize_rcu_expedited() which turned
out to be too expensive.

Improvements for percpu_rwsem are scheduled to be merged in the coming
v4.4-rc1 merge window which alleviates this issue.  For now, revert
the two commits to restore per-process rwsem.  They will be re-applied
for the v4.4-rc1 merge window.

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


Reported-by: default avatarChristian Borntraeger <borntraeger@de.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: stable@vger.kernel.org # v4.2+
parent 6ff33f39

kernel/cgroup.c

+33 −12
Original line number Original line Diff line number Diff line
@@ -2460,13 +2460,14 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, 
	if (!cgrp)

	if (!cgrp)

		return -ENODEV;

		return -ENODEV;





	percpu_down_write(&cgroup_threadgroup_rwsem);

retry_find_task:

	rcu_read_lock();

	rcu_read_lock();

	if (pid) {

	if (pid) {

		tsk = find_task_by_vpid(pid);

		tsk = find_task_by_vpid(pid);

		if (!tsk) {

		if (!tsk) {

			rcu_read_unlock();

			ret = -ESRCH;

			ret = -ESRCH;

			goto out_unlock_rcu;

			goto out_unlock_cgroup;

		}

		}

	} else {

	} else {

		tsk = current;

		tsk = current;
@@ -2482,23 +2483,37 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, 
	 */

	 */

	if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) {

	if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) {

		ret = -EINVAL;

		ret = -EINVAL;

		goto out_unlock_rcu;

		rcu_read_unlock();

		goto out_unlock_cgroup;

	}

	}





	get_task_struct(tsk);

	get_task_struct(tsk);

	rcu_read_unlock();

	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);

	ret = cgroup_procs_write_permission(tsk, cgrp, of);

	if (!ret)

	if (!ret)

		ret = cgroup_attach_task(cgrp, tsk, threadgroup);

		ret = cgroup_attach_task(cgrp, tsk, threadgroup);





	put_task_struct(tsk);

	goto out_unlock_threadgroup;



out_unlock_rcu:

	rcu_read_unlock();

out_unlock_threadgroup:

	percpu_up_write(&cgroup_threadgroup_rwsem);

	percpu_up_write(&cgroup_threadgroup_rwsem);



	put_task_struct(tsk);

out_unlock_cgroup:

	cgroup_kn_unlock(of->kn);

	cgroup_kn_unlock(of->kn);

	return ret ?: nbytes;

	return ret ?: nbytes;

}

}
@@ -2643,8 +2658,6 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) 




	lockdep_assert_held(&cgroup_mutex);

	lockdep_assert_held(&cgroup_mutex);





	percpu_down_write(&cgroup_threadgroup_rwsem);



	/* look up all csses currently attached to @cgrp's subtree */

	/* look up all csses currently attached to @cgrp's subtree */

	down_read(&css_set_rwsem);

	down_read(&css_set_rwsem);

	css_for_each_descendant_pre(css, cgroup_css(cgrp, NULL)) {

	css_for_each_descendant_pre(css, cgroup_css(cgrp, NULL)) {
@@ -2700,8 +2713,17 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) 
				goto out_finish;

				goto out_finish;

			last_task = task;

			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);

			ret = cgroup_migrate(src_cset->dfl_cgrp, task, true);





			percpu_up_write(&cgroup_threadgroup_rwsem);

			put_task_struct(task);

			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))

			if (WARN(ret, "cgroup: failed to update controllers for the default hierarchy (%d), further operations may crash or hang\n", ret))
@@ -2711,7 +2733,6 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) 




out_finish:

out_finish:

	cgroup_migrate_finish(&preloaded_csets);

	cgroup_migrate_finish(&preloaded_csets);

	percpu_up_write(&cgroup_threadgroup_rwsem);

	return ret;

	return ret;

}

}