From mboxrd@z Thu Jan  1 00:00:00 1970
Return-path: <bp@suse.de>
Received: from mx2.suse.de ([195.135.220.15])	by Galois.linutronix.de with
 esmtps (TLS1.0:DHE_RSA_CAMELLIA_256_CBC_SHA1:256)	(Exim 4.80)	(envelope-from
 <bp@suse.de>)	id 1f8p9B-0004XZ-9P	for speck@linutronix.de; Wed, 18 Apr 2018
 17:37:27 +0200
Received: from relay2.suse.de (charybdis-ext.suse.de [195.135.220.254])
	by mx2.suse.de (Postfix) with ESMTP id 54DE5AC3B
	for <speck@linutronix.de>; Wed, 18 Apr 2018 15:37:18 +0000 (UTC)
Date: Wed, 18 Apr 2018 17:37:13 +0200
From: Borislav Petkov <bp@suse.de>
Subject: 
 [MODERATED] Re: ***UNCHECKED*** [patch 3/8] [PATCH v1.3.1 3/7] Linux Patch 3
Message-ID: <20180418153712.GD4290@pd.tnic>
References: <20180418141551.07CBB6111A@crypto-ml.lab.linutronix.de>
MIME-Version: 1.0
In-Reply-To: <20180418141551.07CBB6111A@crypto-ml.lab.linutronix.de>
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: quoted-printable
To: speck@linutronix.de
List-ID: <speck.linutronix.de>

On Thu, Apr 12, 2018 at 10:26:52PM -0400, speck for konrad.wilk_at_oracle.com=
 wrote:
> diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
> index 561cb228605a..73f76d0f5181 100644
> --- a/arch/x86/kernel/cpu/bugs.c
> +++ b/arch/x86/kernel/cpu/bugs.c
> @@ -72,6 +72,9 @@ void __init check_bugs(void)
>  	 */
>  	if (!direct_gbpages)
>  		set_memory_4k((unsigned long)__va(0), 1);
> +
> +	if (mdd_at_boot())
> +		wrmsrl(MSR_IA32_SPEC_CTRL, SPEC_CTRL_MDD);

You can't do this on the common path as that would explode on !Intel.

Instead, move that check to init_intel().

And add to init_amd_zn() code reading MSR 0xc0011020, setting bit 10 to
1b and then writing it back in the mdd_at_boot() case. We have a define
for that MSR already - MSR_AMD64_LS_CFG.

> =20
> @@ -317,7 +320,14 @@ static void __init spectre_v2_select_mitigation(void)
>  #undef pr_fmt
>  #define pr_fmt(fmt)     "MDD: " fmt
> =20
> -static enum md_mitigation md_mode =3D MD_NONE;
> +enum md_mitigation md_mode =3D MD_NONE;
> +/* When switching from lower privilege level (cpl3) to higher (cpl0). */
> +u64 spec_ctrl_priv;
> +EXPORT_SYMBOL_GPL(spec_ctrl_priv);
> +
> +/* When switching from higher to lower privilege level. */
> +u64 spec_ctrl_unpriv;
> +EXPORT_SYMBOL_GPL(spec_ctrl_unpriv);

I don't like exporting some arbitrary variables to the rest of the
kernel. Do accessors instead pls.

--=20
Regards/Gruss,
    Boris.

SUSE Linux GmbH, GF: Felix Imend=C3=B6rffer, Jane Smithard, Graham Norton, HR=
B 21284 (AG N=C3=BCrnberg)
--=20