linux-kernel - Re: [PATCH v4 6/6] hwmon: (k10temp) Add debugfs support

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: <e1d351d3-ffc4-9241-c5fd-0703637d9eee@roeck-us.net>
Date:   Thu, 23 Jan 2020 20:47:32 -0800
From:   Guenter Roeck <linux@...ck-us.net>
To:     Ken Moffat <zarniwhoop73@...glemail.com>
Cc:     linux-hwmon@...r.kernel.org, linux-kernel@...r.kernel.org,
        Clemens Ladisch <clemens@...isch.de>,
        Jean Delvare <jdelvare@...e.com>,
        Brad Campbell <lists2009@...rfbargle.com>,
        Ondrej Čerman <ocerman@...1.eu>,
        Bernhard Gebetsberger <bernhard.gebetsberger@....at>,
        Holger Kiehl <Holger.Kiehl@....de>,
        Michael Larabel <michael@...ronix.com>,
        Jonathan McDowell <noodles@...th.li>,
        Sebastian Reichel <sebastian.reichel@...labora.com>,
        Darren Salt <devspam@...eofthesa.me.uk>
Subject: Re: [PATCH v4 6/6] hwmon: (k10temp) Add debugfs support

Hi Ken,

On 1/23/20 4:01 PM, Ken Moffat wrote:
> Hi Guenter,
> 

Thanks a lot for the additional information. The following
is interesting.

> -0x059960: 00000000 08400001 00004623 00000039
> +0x059960: 00000000 08400001 00008241 00000045

The last two blocks also temperatures. In the AMD thermal code,
we find definitions for CG_MULT_THERMAL_STATUS and
CG_THERMAL_RANGE. The first consists of 2 x 9 bit (0x23
and 0x43 above for idle and under load), the second is just
a value. On Zen2, the address for those values is 20 higher
(0x05997c instead of 0x059968), but the numbers are pretty
much the same. The AMD thermal code reads those values for
some graphics chips and displays it directly in degrees C.

I am just not sure what exactly it represents. I see those
temperatures on 3900X as well. Actually, it looks like all
chips report them, including server chips, so it is not the
graphics temperature. But it is definitely worth keeping an eye
on it; maybe someone can figure out what it is.

> Hope this is not a waste of your time.

No, it is definitely worth it. It will give me data to work with
in the future.

> Would you like similar for the 2500u ?
> 
Yes, that would be great.

Thanks,
Guenter