linux-kernel - Re: [tip:sched/core] sched/rt: Simplify the IPI based RT balancing logic

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]

Date:   Sat, 20 Jan 2018 10:26:16 +0530
From:   Pavan Kondeti <pkondeti@...eaurora.org>
To:     Steven Rostedt <rostedt@...dmis.org>
Cc:     williams@...hat.com, Ingo Molnar <mingo@...nel.org>,
        LKML <linux-kernel@...r.kernel.org>,
        Peter Zijlstra <peterz@...radead.org>,
        Thomas Gleixner <tglx@...utronix.de>, bristot@...hat.com,
        jkacur@...hat.com, efault@....de, hpa@...or.com,
        torvalds@...ux-foundation.org, swood@...hat.com,
        linux-tip-commits@...r.kernel.org
Subject: Re: [tip:sched/core] sched/rt: Simplify the IPI based RT balancing
 logic

Hi Steve,

On Fri, Jan 19, 2018 at 02:51:15PM -0500, Steven Rostedt wrote:
> On Sat, 20 Jan 2018 00:27:56 +0530
> Pavan Kondeti <pkondeti@...eaurora.org> wrote:
> 
> > Hi Steve,
> > 
> > Thanks for the patch.
> > 
> > On Fri, Jan 19, 2018 at 01:12:54PM -0500, Steven Rostedt wrote:
> > > On Fri, 19 Jan 2018 13:11:21 -0500
> > > Steven Rostedt <rostedt@...dmis.org> wrote:
> > >   
> > > >  void rto_push_irq_work_func(struct irq_work *work)
> > > >  {
> > > > +	struct root_domain *rd =
> > > > +		container_of(work, struct root_domain, rto_push_work);
> > > >  	struct rq *rq;  
> > > 
> > > Notice that I also remove the dependency on rq from getting the rd.
> > >   
> > 
> > Nice. This snippet it self solves the original problem, I reported.
> > I will test your patch and let you know the results.
> > 
> >
> 
> I'll break the patch up into two then. One with this snippet, and the
> other with the rd ref counting.
> 

Yeah, this snippet fixed the original problem.

I have not seen "use after free" of rd in my testing. But I can see
we are operating on a rd for which refcount is 0. After applying your
refcount patch, it never happened. I also verified that we are freeing
the rd via IRQ work by dropping the last reference.

Thanks for your help with the patches. Please copy linux-stable for
the 1st patch.

Feel free to use
Tested-by: Pavankumar Kondeti <pkondeti@...eaurora.org>

Thanks,
Pavan
-- 
Qualcomm India Private Limited, on behalf of Qualcomm Innovation Center, Inc.
Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum, a Linux Foundation Collaborative Project.