recent update shows wrong cpu freq (5.3 ghz)

a recent update, possibly 20210307 has made cpu frequency reporting go wrong
this is a 3800x, it never goes above 4.5 ghz, but now it shows a core running at 5.38 ghz, which its not, temperatures are normal, idling at 28-30C

cat /proc/cpuinfo | sort -r | grep MHz:
cpu MHz : 5381.542
cpu MHz : 3900.000
cpu MHz : 3621.831
cpu MHz : 2200.000
cpu MHz : 2200.000
cpu MHz : 2200.000
cpu MHz : 2200.000
cpu MHz : 2200.000
cpu MHz : 2200.000
cpu MHz : 2200.000
cpu MHz : 2200.000
cpu MHz : 2200.000
cpu MHz : 2200.000
cpu MHz : 2200.000
cpu MHz : 2200.000
cpu MHz : 2200.000

lscpu:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
Address sizes: 43 bits physical, 48 bits virtual
CPU(s): 16
On-line CPU(s) list: 0-15
Thread(s) per core: 2
Core(s) per socket: 8
Socket(s): 1
NUMA node(s): 1
Vendor ID: AuthenticAMD
CPU family: 23
Model: 113
Model name: AMD Ryzen 7 3800X 8-Core Processor
Stepping: 0
Frequency boost: enabled
CPU MHz: 2200.000
CPU max MHz: 5381.5420
CPU min MHz: 2200.0000
BogoMIPS: 7785.17
Virtualization: AMD-V
L1d cache: 256 KiB
L1i cache: 256 KiB
L2 cache: 4 MiB
L3 cache: 32 MiB
NUMA node0 CPU(s): 0-15
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Full AMD retpoline, IBPB conditional, STIBP conditional, RSB fill
ing
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflu
sh mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant
_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq mon
itor ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf
lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osv
w ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx
cpb cat_l3 cdp_l3 hw_pstate sme ssbd mba sev ibpb stibp vmmcall sev_es fsgsb
ase bmi1 avx2 smep bmi2 cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsav
eopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local
clzero irperf xsaveerptr rdpru wbnoinvd arat npt lbrv svm_lock nrip_save tsc

scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vms
ave_vmload vgif umip rdpid overflow_recov succor smca

Hi
A bug report would be in order for this…

What does the output (as root user) show for the following command (boost state support bit);


cpupower frequency-info

For example (as my user it’s wrong) on an intel CPU as root correct…


cpupower frequency-info

 boost state support:
    Supported: yes
    Active: yes
    25500 MHz max turbo 4 active cores

boost state support:
    Supported: yes
    Active: yes
    3600 MHz max turbo 4 active cores

openSUSE:Submitting bug reports - openSUSE

thanks, i reported the bug, never done that before so hope i didnt mess it up

cpupower frequency-info
analyzing CPU 0:
  driver: acpi-cpufreq
  CPUs which run at the same hardware frequency: 0
  CPUs which need to have their frequency coordinated by software: 0
  maximum transition latency:  Cannot determine or is not supported.
  hardware limits: 2.20 GHz - 5.11 GHz
  available frequency steps:  5.11 GHz, 3.90 GHz, 2.80 GHz, 2.20 GHz
  available cpufreq governors: ondemand performance schedutil
  current policy: frequency should be within 2.20 GHz and 5.11 GHz.
                  The governor "schedutil" may decide which speed to use
                  within this range.
  current CPU frequency: 3.90 GHz (asserted by call to hardware)
  boost state support:
    Supported: yes
    Active: yes
    Total States: 3
    Pstate-P0:  3900MHz
    Pstate-P1:  2800MHz
    Pstate-P2:  2200MHz

Linux 5.10.20 Released - Fixes The Erroneous Record-Breaking AMD Clock Frequencies
https://www.phoronix.com/scan.php?page=news_item&px=Linux-5.10.20-Fixes-Freq-Report

its back in 5.11.2 then

Hi
Yes, a regression :wink: What was the bug report number, can you post the link to it :wink:

It’s not back, it is the same bug: Linux 5.10.20 Released - Fixes The Erroneous Record-Breaking AMD Clock Frequencies - Phoronix

This patch is that fix that is already in Linux 5.12 Git and now in Linux 5.10.20 and will be in the imminent 5.11.3 point release as well.

Here I see 5.11.2, but in Kernel:stable I see 5.11.5.