[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20180108182220.34233ebc@alans-desktop>
Date: Mon, 8 Jan 2018 18:22:20 +0000
From: Alan Cox <gnomes@...rguk.ukuu.org.uk>
To: Will Deacon <will.deacon@....com>
Cc: Jayachandran C <jnair@...iumnetworks.com>,
Marc Zyngier <marc.zyngier@....com>,
linux-arm-kernel@...ts.infradead.org, lorenzo.pieralisi@....com,
ard.biesheuvel@...aro.org, catalin.marinas@....com,
linux-kernel@...r.kernel.org, labbott@...hat.com,
christoffer.dall@...aro.org
Subject: Re: [v2,03/11] arm64: Take into account ID_AA64PFR0_EL1.CSV3
> > On systems that are not vulnerable to variant 3, this is an unnecessary
> > overhead.
>
> KASLR can be bypassed on CPUs that are not vulnerable to variant 3 simply
> by timing how long accesses to kernel addresses from EL0 take -- please read
> the original KAISER paper for details about that attack on x86. kpti
> mitigates that. If you don't care about KASLR, don't enable it (arguably
> it's useless without kpti).
KASLR is primarily of value for remote protection.
Alan
Powered by blists - more mailing lists