linux-kernel - Re: [PATCH v6] workqueue: Fix edge cases for calc of pool's cpumask

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 for Android: free password hash cracker in your pocket

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

Message-ID: <20170727183148.GH742618@devbig577.frc2.facebook.com>
Date:   Thu, 27 Jul 2017 14:31:48 -0400
From:   Tejun Heo <tj@...nel.org>
To:     Michael Bringmann <mwb@...ux.vnet.ibm.com>
Cc:     Lai Jiangshan <jiangshanlai@...il.com>,
        linux-kernel@...r.kernel.org, nfont@...ux.vnet.ibm.com
Subject: Re: [PATCH v6] workqueue: Fix edge cases for calc of pool's cpumask

On Thu, Jul 27, 2017 at 01:15:48PM -0500, Michael Bringmann wrote:
> 
> On NUMA systems with dynamic processors, the content of the cpumask
> may change over time.  As new processors are added via DLPAR operations,
> workqueues are created for them.  Depending upon the order in which CPUs
> are added/removed, we may run into problems with the content of the
> cpumask used by the workqueues.  This patch deals with situations where
> the online cpumask for a node is a proper superset of possible cpumask
> for the node.  It also deals with edge cases where the order in which
> CPUs are removed/added from the online cpumask may leave the set for a
> node empty, and require execution by CPUs on another node.
> 
> In these and other cases, the patch attempts to ensure that a valid,
> usable cpumask is used to set up newly created pools for workqueues.
> This patch provides a fix for NUMA systems which can add/subtract
> processors dynamically.  The patch is expected to be an intermediate
> one while developers search for any underlying issues.

Please start with describing what the underlying problem is - CPU <->
NUMA node mapping change on powerpc.  The mapping shouldn't change,
not just for workqueue, but because we don't have any kind of
synchronization around the mapping throughout allocation paths.  And
then, please describe how this patch can at least prevent immediate
crashes in a lot of cases.

Thanks.

-- 
tejun