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

Message-ID: <ed6360d9-e191-4e52-88f2-70ebcba26cdd@intel.com>
Date: Fri, 17 Oct 2025 08:52:07 -0700
From: Sohil Mehta <sohil.mehta@...el.com>
To: Andi Kleen <ak@...ux.intel.com>, Salvatore Bonaccorso <carnil@...ian.org>
CC: Thomas Gleixner <tglx@...utronix.de>, Ingo Molnar <mingo@...hat.com>,
	Borislav Petkov <bp@...en8.de>, Dave Hansen <dave.hansen@...ux.intel.com>,
	Laurențiu Păncescu <lpancescu@...il.com>,
	<x86@...nel.org>, "H. Peter Anvin" <hpa@...or.com>, "Chang S. Bae"
	<chang.seok.bae@...el.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 8:36 AM, Andi Kleen wrote:
>> [    0.351035] smp: Bringing up secondary CPUs ...
>> [    0.351876] smpboot: x86: Booting SMP configuration:
>> [    0.351888] .... node  #0, CPUs:      #1
>> [    0.008282] Disabled fast string operations
> 
> It's probably caused by that. I guess he disabled fast strings in his
> BIOS and if he switches that setting it would go away.
> 
> The related code would need to be moved earlier in the boot sequence to
> make the alternative patching work.
> 

I am not sure about moving the code.

Based on the CPU information in the dmesg:
smpboot: CPU0: Intel(R) Atom(TM) CPU N450   @ 1.66GHz (family: 0x6,
model: 0x1c, stepping: 0xa)

This code should behave the same way on Boot CPU and secondary CPUs. So,
as Dave mentioned, it is likely to be an (BIOS) issue if it is exposed
inconsistently across CPUs.

	if (c->x86_vfm >= INTEL_PENTIUM_M_DOTHAN) {
		rdmsrq(MSR_IA32_MISC_ENABLE, misc_enable);
		if (misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING) {
			/* X86_FEATURE_ERMS is set based on CPUID */
			set_cpu_cap(c, X86_FEATURE_REP_GOOD);
		} else {
			pr_info("Disabled fast string operations\n");
			setup_clear_cpu_cap(X86_FEATURE_REP_GOOD);
			setup_clear_cpu_cap(X86_FEATURE_ERMS);
		}
	}



> But in practice it's unlikely it causes any real functional problems
>