MIME-Version: 1.0
References: <20230207072902.5528-1-jgross@suse.com> <20230207072902.5528-5-jgross@suse.com>
 <CAHk-=wi53OX86-yLBp4rCHOH67XhVbzV78qa63mh4-rOhxQSLw@mail.gmail.com> <59a24334-35c7-8afa-f35d-d654dd2823ba@suse.com>
In-Reply-To: <59a24334-35c7-8afa-f35d-d654dd2823ba@suse.com>
From:   Linus Torvalds <torvalds@linux-foundation.org>
Date:   Wed, 8 Feb 2023 07:42:13 -0800
Message-ID: <CAHk-=wiWAv7gQewr=i=oOD+89CFjAzaXiotUb2wS+oWGUP6z+g@mail.gmail.com>
Subject: Re: [PATCH 4/6] x86/mtrr: don't let mtrr_type_lookup() return MTRR_TYPE_INVALID
To:     Juergen Gross <jgross@suse.com>
Cc:     linux-kernel@vger.kernel.org, x86@kernel.org,
        lists@nerdbynature.de, mikelley@microsoft.com,
        Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        "H. Peter Anvin" <hpa@zytor.com>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

On Tue, Feb 7, 2023 at 10:20 PM Juergen Gross <jgross@suse.com> wrote:
>
> Are you sure? In the SDM I'm reading:
>
> * E (MTRRs enabled) flag, bit 11 =E2=80=94 MTRRs are enabled when set; al=
l MTRRs are
>    disabled when clear, and the UC memory type is applied to all of physi=
cal
>    memory.
>
> So UC it should be IMHO.

Right you are. I clearly misread that section when I did my original patch.

                Linus