linux-kernel - Re: [PATCH] cpu-topology: warn if NUMA configurations conflicts with lower layer

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: <c43342d0-7e4d-3be0-0fe1-8d802b0d7065@arm.com>
Date:   Thu, 2 Jan 2020 13:22:19 +0000
From:   Valentin Schneider <valentin.schneider@....com>
To:     "Zengtao (B)" <prime.zeng@...ilicon.com>,
        Sudeep Holla <sudeep.holla@....com>
Cc:     Linuxarm <linuxarm@...wei.com>,
        Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        "Rafael J. Wysocki" <rafael@...nel.org>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        Morten Rasmussen <morten.rasmussen@....com>
Subject: Re: [PATCH] cpu-topology: warn if NUMA configurations conflicts with
 lower layer

On 02/01/2020 12:47, Zengtao (B) wrote:
>>
>> As I said, wrong configurations need to be detected when generating
>> DT/ACPI if possible. The above will print warning on systems with NUMA
>> within package.
>>
>> NUMA:  0-7, 8-15
>> core_siblings:   0-15
>>
>> The above is the example where the die has 16 CPUs and 2 NUMA nodes
>> within a package, your change throws error to the above config which is
>> wrong.
>>
> From your example, the core 7 and core 8 has got different LLC but the same Low
> Level cache?

AFAIA what matters here is memory controllers, less so LLCs. Cores within
a single die could have private LLCs and separate memory controllers, or
shared LLC and separate memory controllers.

> From schedule view of point, lower level sched domain should be a subset of higher
> Level sched domain.
> 

Right, and that is checked when you have sched_debug on the cmdline
(or write 1 to /sys/kernel/debug/sched_debug & regenerate the sched domains)

Now, I don't know how this plays out for the numa-in-package topologies like
the one suggested by Sudeep. x86 and AMD had to play some games to get
numa-in-package topologies working, see e.g.

  cebf15eb09a2 ("x86, sched: Add new topology for multi-NUMA-node CPUs")

perhaps you need to "lie" here and ensure sub-NUMA sched domain levels are
a subset of the NUMA levels, i.e. lie for core_siblings. I might go and
play with this to see how it behaves.