linux-kernel - Re: [PATCH 4/5] perf_events: add cgroup support (v7)

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <1294308909.2016.321.camel@laptop>
Date:	Thu, 06 Jan 2011 11:15:09 +0100
From:	Peter Zijlstra <peterz@...radead.org>
To:	Stephane Eranian <eranian@...gle.com>
Cc:	linux-kernel@...r.kernel.org, mingo@...e.hu, paulus@...ba.org,
	davem@...emloft.net, fweisbec@...il.com,
	perfmon2-devel@...ts.sf.net, eranian@...il.com,
	robert.richter@....com, acme@...hat.com, lizf@...fujitsu.com
Subject: Re: [PATCH 4/5] perf_events: add cgroup support (v7)

On Wed, 2011-01-05 at 22:39 +0100, Stephane Eranian wrote:
> Peter,
> 
> On Wed, Jan 5, 2011 at 2:01 PM, Stephane Eranian <eranian@...gle.com> wrote:
> > On Wed, Jan 5, 2011 at 12:23 PM, Peter Zijlstra <peterz@...radead.org> wrote:
> >> On Mon, 2011-01-03 at 18:20 +0200, Stephane Eranian wrote:
> >>> +void
> >>> +perf_cgroup_switch(struct task_struct *task, struct task_struct *next)
> >>> +{
> >>> +     struct perf_cgroup *cgrp_out = perf_cgroup_from_task(task);
> >>> +     struct perf_cgroup *cgrp_in = perf_cgroup_from_task(next);
> >>> +     struct perf_cpu_context *cpuctx;
> >>> +     struct pmu *pmu;
> >>> +     /*
> >>> +      * if task is DEAD, then css_out is irrelevant, it has
> >>> +      * been changed to init_cgrp in cgroup_exit() from do_exit().
> >>> +      * Furthermore, perf_cgroup_exit_task(), has scheduled out
> >>> +      * all css constrained events, only unconstrained events
> >>> +      * remain. Therefore we need to reschedule based on css_in.
> >>> +      */
> >>> +     if (task->state != TASK_DEAD && cgrp_out == cgrp_in)
> >>> +             return;
> >>
> >> I think that check is broken, TASK_DEAD is set way after calling
> >> cgroup_exit(), so if we get preempted in between there you'll still go
> >> funny.
> >>
> 
> I looked at this part again.
> 
> The original code checking for TASK_DEAD is correct.
> 
> The reason is simple, you're looking at perf_cgroup_switch() which is
> invoked as part of schedule() and NOT perf_event_task_exit() (called
> prior to cgroup_exit()).
> Thus, by the time you do the final schedule(), the task state has indeed
> been switched to TASK_DEAD.
> 
> I remember testing for this condition during the debug phase.

But, cgroup_exit() detaches the task from the cgroup, after which the
cgroup can disappear. Furthermore, we can schedule after cgroup_exit()
and before the explicit schedule() invocation.

Some of the exit functions (say proc_exit_connector) can block and cause
scheduling, and with PREEMPT=y we can get preempted.

This means you'll be context switching, and thus possibly calling
perf_cgroup_switch(), on a task who's cgroup is possibly destroyed.

So I'm not at all seeing how this is correct.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/