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;
Content-Type: text/plain;
        charset=utf-8
Mime-Version: 1.0 (1.0)
Subject: Re: [PATCH v2 5/7] x86/mm, tracing: Fix CR2 corruption
From:   Andy Lutomirski <luto@amacapital.net>
In-Reply-To: <CAHk-=wiJ4no+TW-8KTfpO-Q5+aaTGVoBJzrnFTvj_zGpVbrGfA@mail.gmail.com>
Date:   Thu, 4 Jul 2019 20:16:54 -0700
Cc:     Peter Zijlstra <peterz@infradead.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        Borislav Petkov <bp@alien8.de>, Ingo Molnar <mingo@kernel.org>,
        Steven Rostedt <rostedt@goodmis.org>,
        Andrew Lutomirski <luto@kernel.org>,
        Peter Anvin <hpa@zytor.com>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        Juergen Gross <jgross@suse.com>,
        Linux List Kernel Mailing <linux-kernel@vger.kernel.org>,
        He Zhe <zhe.he@windriver.com>,
        Joel Fernandes <joel@joelfernandes.org>, devel@etsukata.com
Content-Transfer-Encoding: quoted-printable
Message-Id: <41D6F2E2-C4CF-41DF-A843-FCBD03B7BEEB@amacapital.net>
References: <20190704195555.580363209@infradead.org> <20190704200050.534802824@infradead.org> <CAHk-=wiJ4no+TW-8KTfpO-Q5+aaTGVoBJzrnFTvj_zGpVbrGfA@mail.gmail.com>
To:     Linus Torvalds <torvalds@linux-foundation.org>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk


> On Jul 4, 2019, at 7:18 PM, Linus Torvalds <torvalds@linux-foundation.org>=
 wrote:
>=20
>> On Fri, Jul 5, 2019 at 5:03 AM Peter Zijlstra <peterz@infradead.org> wrot=
e:
>>=20
>> Despire the current efforts to read CR2 before tracing happens there
>> still exist a number of possible holes:
>=20
> So this whole series disturbs me for the simple reason that I thought
> tracing was supposed to save/restore cr2 and make it unnecessary to
> worry about this in non-tracing code.
>=20
> That is very much what the NMI code explicitly does. Why shouldn't all
> the other tracing code do the same thing in case they can take page
> faults?
>=20

If nothing else, MOV to CR2 is architecturally serializing, so, unless there=
=E2=80=99s some fancy unwinding involved, this will be quite slow.=