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>] [day] [month] [year] [list]
Message-ID: <4E9CA6E5.4040607@atlas.cz>
Date:	Tue, 18 Oct 2011 00:06:29 +0200
From:	Clarinet <clarinet@...as.cz>
To:	linux-kernel@...r.kernel.org
Subject: Halting kernel changes BIOS mutithreading setting

Dear all,

I am at the wits' end with the following behavior: my custom kernel 
changes the "Simultaneous Multithreading" BIOS setting when halted. Let 
me explain details.

Hardware: Supermicro 6016TT-TF (board X8DTT-F), 2x Xeon E5645 (6 cores 
each), 16GB RAM.

Software: custom kernel 2.6.38.6 (.config attached), diskless boot.

Problem: I set the BIOS setting "Simultaneous Multithreading" to 
"Disabled" and start Linux. Dmesg and /proc/cpuinfo show 12 processors 
(correct). After system reboot ("shutdown -r now") system still shows 12 
processors (correct). When I call "shutdown -h now", computer halts. I 
turn it on, boot Linux, and system shows 24 processors (but the BIOS 
setup still says "Simultaneous Multithreading = Disabled" if I check it 
after the next reboot). The only way to return to 12 processors is to go 
to BIOS settings and (at least) save settings again (no other changes 
needed, just saving settings).

I tried several live distributions (Debian Live 6.0.2, Ubuntu 11.04, 
11.10) but none of them shows this behavior.

I tried to compile my custom kernel with various changes in ACPI/PM 
configuration but have not found any configuration that would behave 
"normally".

I tried to compile various kernel versions - 2.6.35.7 behaves normally, 
but 2.6.38.6 and 2.6.39.4 show the described behavior.

Any hint to what can be wrong with my kernel would be greatly 
appreciated. Thank you!

Best regards,

Jiri Polach

View attachment ".config" of type "text/plain" (52764 bytes)

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ