linux-kernel - Re: [PATCHv3] iommu/intel: Ratelimit each dmar fault printing

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: <1521579013.2686.83.camel@arista.com>
Date:   Tue, 20 Mar 2018 20:50:13 +0000
From:   Dmitry Safonov <dima@...sta.com>
To:     Joerg Roedel <joro@...tes.org>
Cc:     linux-kernel@...r.kernel.org, 0x7f454c46@...il.com,
        Alex Williamson <alex.williamson@...hat.com>,
        David Woodhouse <dwmw2@...radead.org>,
        Ingo Molnar <mingo@...nel.org>,
        Lu Baolu <baolu.lu@...ux.intel.com>,
        iommu@...ts.linux-foundation.org
Subject: Re: [PATCHv3] iommu/intel: Ratelimit each dmar fault printing

On Thu, 2018-03-15 at 16:28 +0100, Joerg Roedel wrote:
> On Thu, Mar 15, 2018 at 02:42:00PM +0000, Dmitry Safonov wrote:
> > But even with loop-limit we will need ratelimit each printk()
> > *also*.
> > Otherwise loop-limit will be based on time spent printing, not on
> > anything else..
> > The patch makes sense even with loop-limit in my opinion.
> 
> Looks like I mis-read your patch, somehow it looked to me as if you
> replace all 'ratelimited' usages with a call to __ratelimit(), but
> you
> just move 'ratelimited' into the loop, which actually makes sense.

So, is it worth to apply the patch?

> But still, this alone is no proper fix for the soft-lockups you are
> seeing.

Hmm, but this fixes my softlockup issue, because it's about time spent
in printk() inside irq-disabled section, rather about exiting the dmar-
clearing loop.
And on my hw doesn't make any difference to limit loop or not because
clearing a fault is much faster than hw could generate a new fault.
ITOW, it fixes the softlockup for me and the loop-related lockup can't
happen on hw I have (so it's the other issue, [possible?] on other hw).

-- 
Thanks,
             Dmitry