linux-kernel - Re: WARNING: CPU: 1 PID: 0 at arch/x86/kernel/cpu/cpuid-deps.c:123 do_clear_cpu_cap+0xdc/0x130 on Intel(R) Atom(TM) CPU N450 system

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <9f0ff555-860c-4e3a-9865-b921b0f7d187@intel.com>
Date: Fri, 17 Oct 2025 15:44:11 -0700
From: Sohil Mehta <sohil.mehta@...el.com>
To: Dave Hansen <dave.hansen@...el.com>,
	Laurențiu Păncescu <lpancescu@...il.com>
CC: Salvatore Bonaccorso <carnil@...ian.org>, Thomas Gleixner
	<tglx@...utronix.de>, Ingo Molnar <mingo@...hat.com>, Borislav Petkov
	<bp@...en8.de>, Dave Hansen <dave.hansen@...ux.intel.com>, <x86@...nel.org>,
	"H. Peter Anvin" <hpa@...or.com>, "Chang S. Bae" <chang.seok.bae@...el.com>,
	Andi Kleen <ak@...ux.intel.com>, Eric Biggers <ebiggers@...gle.com>,
	<linux-kernel@...r.kernel.org>, <1117002@...s.debian.org>
Subject: Re: WARNING: CPU: 1 PID: 0 at arch/x86/kernel/cpu/cpuid-deps.c:123
 do_clear_cpu_cap+0xdc/0x130 on Intel(R) Atom(TM) CPU N450 system

On 10/17/2025 3:01 PM, Dave Hansen wrote:
> I'm not quite sure why newer kernels are complaining. The
> "alternatives_patched" check has been around since ~6.10. If someone has
> some spare time on their hands, they could bisect it. But I'm not sure
> it will change anything.
> 

I would bet on commit 15b7ddcf66fb ("x86/cpu/intel: Fix fast string
initialization for extended Families"). It started honoring the
preference set in MSR_IA32_MISC_ENABLE which seems to have unmasked this
issue.

The commit has the following snippet:

"X86_FEATURE_REP_GOOD is cleared in early_init_intel() if
MISC_ENABLE.FAST_STRING is 0. But it gets set later on unconditionally
for all Family 6 processors in init_intel(). This not only overrides the
BIOS preference but also contradicts the earlier check.

Fix this by combining the related checks and always relying on the BIOS
provided preference for fast string operations."