Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 4 Jan 2018 12:06:22 -0500
From:      Eric McCorkle <eric@metricspace.net>
To:        Brett Glass <brett@lariat.org>, =?UTF-8?Q?Dag-Erling_Sm=c3=b8rgrav?= <des@des.no>, Erich Dollansky <freebsd.ed.lists@sumeritec.com>
Cc:        "freebsd-security@freebsd.org" <freebsd-security@freebsd.org>, "Ronald F. Guilmette" <rfg@tristatelogic.com>
Subject:   Re: Intel hardware bug
Message-ID:  <13341e69-a8f5-253d-ccb8-e2c14d2322f9@metricspace.net>
In-Reply-To: <ae3298c9-d4f2-83a4-5fbf-52dbb1a49aa0@metricspace.net>
References:  <02563ce4-437c-ab96-54bb-a8b591900ba0@FreeBSD.org> <19876.1515025752@segfault.tristatelogic.com> <20180104132807.266fe46c.freebsd.ed.lists@sumeritec.com> <86vaghu0ps.fsf@desk.des.no> <201801041552.IAA17267@mail.lariat.net> <736a2b77-d4a0-b03f-8a6b-6a717f5744d4@metricspace.net> <201801041621.JAA17566@mail.lariat.net> <ae3298c9-d4f2-83a4-5fbf-52dbb1a49aa0@metricspace.net>

next in thread | previous in thread | raw e-mail | index | archive | help
On 01/04/2018 12:03, Eric McCorkle wrote:

> You could block meltdown, I suppose, by making the entire
> kernel address space absolutely forbidden under penalty of an
> uncatchable signal.

Actually, scratch that; it doesn't work.  The caches are still affected,
and could be measured by another core.

I suppose you could attempt to flush them upon killing a process in this
way, but you still have a window, so it's only a probabilistic defense.



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?13341e69-a8f5-253d-ccb8-e2c14d2322f9>