Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Mon, 22 Oct 2018 01:32:04 +0200 (CEST)
From:   Jiri Kosina <jikos@kernel.org>
To:     Pavel Machek <pavel@ucw.cz>
cc:     Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Josh Poimboeuf <jpoimboe@redhat.com>,
        Andrea Arcangeli <aarcange@redhat.com>,
        "Woodhouse, David" <dwmw@amazon.co.uk>,
        Andi Kleen <ak@linux.intel.com>,
        Tim Chen <tim.c.chen@linux.intel.com>,
        "Schaufler, Casey" <casey.schaufler@intel.com>,
        linux-kernel@vger.kernel.org, x86@kernel.org
Subject: Re: [PATCH v5 1/2] x86/speculation: apply IBPB more strictly to
 avoid cross-process data leak
In-Reply-To: <20181021193827.GB26042@amd>
Message-ID: <nycvar.YFH.7.76.1810220130390.23511@cbobk.fhfr.pm>
References: <nycvar.YFH.7.76.1809101119280.15880@cbobk.fhfr.pm> <nycvar.YFH.7.76.1809101123020.15880@cbobk.fhfr.pm> <20181021193827.GB26042@amd>
User-Agent: Alpine 2.21 (LSU 202 2017-01-01)
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Sun, 21 Oct 2018, Pavel Machek wrote:

> Imagine JIT running evil code (flash, javascript). JIT will prevent evil 
> code from doing ptrace() (or maybe there is syscall filter in effect or 
> something like that), but if evil code can poison branch buffers and do 
> timings, security problem stays.

JITs sort of remove the traditional unix security domain boundary between 
mutually (un)trusted code (processess and threads), that's a more general 
problem, yes.

> Do we need prctl(I_DONT_RUN_EVIL_CODE)?

That's basically the level of fine-graining Tim's followup patchset 
(that's currently being discussed) is eventually going to achieve.

Thanks,

-- 
Jiri Kosina
SUSE Labs