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: <02EC6936-C879-4681-AC37-76DFAA7DA3AC@icloud.com>
Date:   Sun, 7 Mar 2021 16:10:07 -0800
From:   Theodore Dubois <tblodt@...oud.com>
To:     linux-kernel@...r.kernel.org
Cc:     tglx@...utronix.de
Subject: What clockevents are needed to boot properly?

I'm playing around with a new kernel arch and running into problems with properly configuring the clockevents, especially with SMP. Without SMP you can easily set up a clockevents masked to cpu 0, and this seems to work fine. But on SMP this fails silently: high-res timers created on cpu != 0 never fire.

The obvious next thing to try would be to set the mask of the clockevents to cpu_possible_mask, but this silently fails as well: the clockevents just doesn't get used at all. There seem to be a lot of drivers in the tree that do this, I'm not sure why it works for those.

Do you have to register a new clockevents for each CPU? I can't find a lot of information on this.

~Theodore

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ