Date: Thu, 4 Jan 2018 23:42:55 +0300 From: Lev Serebryakov <lev@FreeBSD.org> To: Julian Elischer <julian@freebsd.org>, "freebsd-security@freebsd.org" <freebsd-security@freebsd.org> Subject: Re: clang way to patch for Spectre? Message-ID: <1401022152.20180104234255@serebryakov.spb.ru> In-Reply-To: <43417734-d420-5be9-333b-8d0d02d7a58a@freebsd.org> References: <291645341.20180104190237@serebryakov.spb.ru> <43417734-d420-5be9-333b-8d0d02d7a58a@freebsd.org>
next in thread | previous in thread | raw e-mail | index | archive | help
Hello Julian, Thursday, January 4, 2018, 8:49:50 PM, you wrote: >> https://reviews.llvm.org/D41723 >> >> > not really.. > What's to stop an unprivileged used bringing his own compiler? or a > precompiled binary? As far as I understand, Spectre can not cross boundaries, so precompiled binary will be able read its own memory via bug. To read all memory via Spectre (don't confuse it with Meltdown) code must be privileged. And this codegen patch eliminate "gadgets" in kernel which could be exploited by userland code. -- Best regards, Lev mailto:lev@FreeBSD.org
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?1401022152.20180104234255>