linux-kernel - Re: [PATCH v10 1/7] x86/tsc: remove tsc

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 for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <CAGM2reYc7bgcqjqhvattvRMQefxpNXU3FkXJdC1XrGQVpRzsxQ@mail.gmail.com>
Date:   Tue, 19 Jun 2018 13:50:54 -0400
From:   Pavel Tatashin <pasha.tatashin@...cle.com>
To:     tglx@...utronix.de
Cc:     Steven Sistare <steven.sistare@...cle.com>,
        Daniel Jordan <daniel.m.jordan@...cle.com>,
        linux@...linux.org.uk, schwidefsky@...ibm.com,
        Heiko Carstens <heiko.carstens@...ibm.com>,
        john.stultz@...aro.org, sboyd@...eaurora.org, x86@...nel.org,
        LKML <linux-kernel@...r.kernel.org>, mingo@...hat.com,
        hpa@...or.com, douly.fnst@...fujitsu.com, peterz@...radead.org,
        prarit@...hat.com, feng.tang@...el.com,
        Petr Mladek <pmladek@...e.com>, gnomes@...rguk.ukuu.org.uk
Subject: Re: [PATCH v10 1/7] x86/tsc: remove tsc_disabled flag

> > tsc_disabled is set when notsc is passed as kernel parameter. The reason we
> > have notsc is to avoid timing problems on multi-socket systems.  We already
> > have a mechanism, however, to detect and resolve these issues by invoking
> > tsc unstable path. Thus, make notsc to behave the same as tsc=unstable.
>
> notsc also excludes TSC from being used at all, while with your change its
> suddenly used in sched_clock().

Hi Thomas,

Thank you for the review. I will reword the patch comment. Currently,
at the end it says: "Thus, make notsc to behave the same as
tsc=unstable." To emphasize this, I will change the patch title to
this:

x86/tsc: redefine notsc to behave as tsc=unstable

And in the comment I will mention that as a consequence of this change
tsc is going to be used by sched_clock() when notsc is provided.

Thank you,
Pavel