Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Mon, 25 May 2020 20:08:34 +0200
From:   Peter Zijlstra <peterz@infradead.org>
To:     Andy Lutomirski <luto@amacapital.net>
Cc:     Rasmus Villemoes <linux@rasmusvillemoes.dk>,
        Andy Lutomirski <luto@kernel.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        LKML <linux-kernel@vger.kernel.org>, X86 ML <x86@kernel.org>
Subject: Re: [RFC][PATCH 0/4] x86/entry: disallow #DB more
Message-ID: <20200525180834.GF317569@hirez.programming.kicks-ass.net>
References: <20200525110101.GG325303@hirez.programming.kicks-ass.net>
 <2E6DBDE0-FEEA-467F-A380-4ED736B6C912@amacapital.net>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
Content-Transfer-Encoding: 8bit
In-Reply-To: <2E6DBDE0-FEEA-467F-A380-4ED736B6C912@amacapital.net>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Mon, May 25, 2020 at 10:19:08AM -0700, Andy Lutomirski wrote:

> How about adding it to cpu_tlbstate?  A lot of NMIs are going to read
> that anyway to check CR3.

That might work I suppose; we're really pushing the name of it though.
Also, that's PTI specific IIRC, and we're getting to the point where a
significant number of CPUs no longer need that, right?

> And blaming KVM is a bit misplaced. This isn’t KVM’s fault — it’s
> Intel’s. VT-x has two modes: DR access exits and DR access doesn’t
> exit. There’s no shadow mode.

It's virt, I can't be arsed to care, whoever misdesigned it.
We already have debugreg pvops, they can do shadow there.