linux-kernel - Re: [PATCH v5 3/3] mm/page_alloc: Keep memoryless cpuless node 0 offline

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: <20200701122353.GU2369@dhcp22.suse.cz>
Date:   Wed, 1 Jul 2020 14:23:53 +0200
From:   Michal Hocko <mhocko@...nel.org>
To:     Srikar Dronamraju <srikar@...ux.vnet.ibm.com>
Cc:     Christopher Lameter <cl@...ux.com>,
        Andrew Morton <akpm@...ux-foundation.org>,
        linuxppc-dev@...ts.ozlabs.org, linux-mm@...ck.org,
        linux-kernel@...r.kernel.org, Mel Gorman <mgorman@...e.de>,
        Vlastimil Babka <vbabka@...e.cz>,
        "Kirill A. Shutemov" <kirill@...temov.name>,
        Michael Ellerman <mpe@...erman.id.au>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        Gautham R Shenoy <ego@...ux.vnet.ibm.com>,
        Satheesh Rajendran <sathnaga@...ux.vnet.ibm.com>,
        David Hildenbrand <david@...hat.com>
Subject: Re: [PATCH v5 3/3] mm/page_alloc: Keep memoryless cpuless node 0
 offline

On Tue 30-06-20 09:31:25, Srikar Dronamraju wrote:
> * Christopher Lameter <cl@...ux.com> [2020-06-29 14:58:40]:
> 
> > On Wed, 24 Jun 2020, Srikar Dronamraju wrote:
> > 
> > > Currently Linux kernel with CONFIG_NUMA on a system with multiple
> > > possible nodes, marks node 0 as online at boot.  However in practice,
> > > there are systems which have node 0 as memoryless and cpuless.
> > 
> > Maybe add something to explain why you are not simply mapping the
> > existing memory to NUMA node 0 which is after all just a numbering scheme
> > used by the kernel and can be used arbitrarily?
> > 
> 
> I thought Michal Hocko already gave a clear picture on why mapping is a bad
> idea. https://lore.kernel.org/lkml/20200316085425.GB11482@dhcp22.suse.cz/t/#u
> Are you suggesting that we add that as part of the changelog?

Well, I was not aware x86 already does renumber. So there is a certain
precendence. As I've said I do not really like that but this is what
already is happening. If renumbering is not an option then just handle
that in the ppc code explicitly. Generic solution would be preferable of
course but as I've said it is really hard to check for correctness and
potential subtle issues.

-- 
Michal Hocko
SUSE Labs