linux-kernel - Re: [patch V6 11/19] x86/cpu: Use common topology code for AMD

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

Date: Thu, 14 Mar 2024 10:21:34 +0000
From: "Yuezhang.Mo@...y.com" <Yuezhang.Mo@...y.com>
To: "tglx@...utronix.de" <tglx@...utronix.de>
CC: "andrew.cooper3@...rix.com" <andrew.cooper3@...rix.com>,
        "andy@...radead.org" <andy@...radead.org>,
        "arjan@...ux.intel.com"
	<arjan@...ux.intel.com>,
        "dimitri.sivanich@....com"
	<dimitri.sivanich@....com>,
        "feng.tang@...el.com" <feng.tang@...el.com>,
        "jgross@...e.com" <jgross@...e.com>,
        "kan.liang@...ux.intel.com"
	<kan.liang@...ux.intel.com>,
        "kprateek.nayak@....com"
	<kprateek.nayak@....com>,
        "linux-kernel@...r.kernel.org"
	<linux-kernel@...r.kernel.org>,
        "mhklinux@...look.com"
	<mhklinux@...look.com>,
        "paulmck@...nel.org" <paulmck@...nel.org>,
        "peterz@...radead.org" <peterz@...radead.org>,
        "ray.huang@....com"
	<ray.huang@....com>,
        "rui.zhang@...el.com" <rui.zhang@...el.com>,
        "sohil.mehta@...el.com" <sohil.mehta@...el.com>,
        "thomas.lendacky@....com"
	<thomas.lendacky@....com>,
        "wendy.wang@...el.com" <wendy.wang@...el.com>,
        "x86@...nel.org" <x86@...nel.org>
Subject: Re: [patch V6 11/19] x86/cpu: Use common topology code for AMD

I ran xfstests generic/650 and found that it failed.

The reason for the failure is that this appears in dmesg:

[  649.590421] smpboot: CPU 2 is now offline
[  650.132920] smpboot: Booting Node 0 Processor 3 APIC 0x13
[  650.133432] LVT offset 0 assigned for vector 0x400
[  650.148931] ACPI: \_PR_.P003: Found 2 idle states
[  650.149478] BUG: arch topology borken
[  650.149483]      the CLS domain not a subset of the MC domain
[  650.149486] BUG: arch topology borken
[  650.149487]      the CLS domain not a subset of the MC domain

I prepared the following script to reproduce this issue.

#! /bin/sh

sysfs_cpu_dir="/sys/devices/system/cpu"
nrcpus=$(getconf _NPROCESSORS_CONF)
hotplug_cpus=()
for ((i = 0; i < nrcpus; i++ )); do
	test -e "$sysfs_cpu_dir/cpu$i/online" && hotplug_cpus+=("$i")
done

nr_hotplug_cpus="${#hotplug_cpus[@]}"

for ((i=0; i<20;i++)); do
	idx=$(( RANDOM % nr_hotplug_cpus ))
	cpu="${hotplug_cpus[$idx]}"
	action=$(( RANDOM % 2 ))

	echo "$action" > "$sysfs_cpu_dir/cpu$cpu/online" 2>/dev/null
	sleep 0.5
done

If run the script without this commit, the issue cannot be reproduced.