Bug 9636 - IBM Thinkcentre 9210-CTO: cpufreq reports too low max freq on Intel P4
Summary: IBM Thinkcentre 9210-CTO: cpufreq reports too low max freq on Intel P4
Status: CLOSED INSUFFICIENT_DATA
Alias: None
Product: ACPI
Classification: Unclassified
Component: Power-Processor (show other bugs)
Hardware: All Linux
: P1 high
Assignee: Zhang Rui
URL:
Keywords:
Depends on:
Blocks:
 
Reported: 2007-12-26 04:34 UTC by Peter Ganzhorn
Modified: 2009-05-23 19:50 UTC (History)
5 users (show)

See Also:
Kernel Version: 2.6.23
Subsystem:
Regression: No
Bisected commit-id:


Attachments
/proc/cpuinfo of the affected machine. (1.13 KB, text/plain)
2007-12-26 04:35 UTC, Peter Ganzhorn
Details
acpidump output. (105.92 KB, text/plain)
2008-01-27 03:21 UTC, Peter Ganzhorn
Details
Results of running "acpidump" (136.71 KB, text/plain)
2009-05-23 19:44 UTC, Evgeny
Details
Results of running "grep . /sys/devices/system/cpu/cpu0/cpufreq/*" (849 bytes, text/plain)
2009-05-23 19:47 UTC, Evgeny
Details
ACPI related messages in dmesg (3.99 KB, text/plain)
2009-05-23 19:50 UTC, Evgeny
Details

Description Peter Ganzhorn 2007-12-26 04:34:40 UTC
Most recent kernel where this bug did not occur: -
Distribution: Debian testing
Hardware Environment: Intel P4 3.0GHz HT, Intel 945 chipset
Software Environment: Debian testing
Problem Description:
Using the acpi-cpufreq driver the CPU will not switch to a frequency higher than 1.5 GHz; the sysfs cpufreq interface (cpuinfo_max_freq) reports 1.5 GHz to be the maximum frequency available as well.
The same kernel without cpufreq support enabled does not show those problems, the CPU will run at 3 GHz without cpufreq.
Kernel 2.6.23 and 2.6.24-rc* both show the problem.

Here some output with cpufreq enabled:
# cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_max_freq 
1500000
# cat /sys/devices/system/cpu/cpu0/cpufreq/cpuinfo_max_freq 
1500000
# cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_available_frequencies 
1500000 1400000

Actually it *should* report frequencies up to 3 GHz, but only does report up to 1.5 GHz.
I'm gonna attach the /proc/cpuinfo data to this bug report, let me know if you need any other information.
This is a really, really nasty bug.

Steps to reproduce: Depends on my hardware I guess.
Comment 1 Peter Ganzhorn 2007-12-26 04:35:37 UTC
Created attachment 14189 [details]
/proc/cpuinfo of the affected machine.
Comment 2 Peter Ganzhorn 2007-12-26 04:39:09 UTC
BTW: I'm using the ondemand-governor and acpi-cpufreq as driver:

# cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_driver 
acpi-cpufreq
# cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor 
ondemand
Comment 3 Thomas Renninger 2008-01-01 10:15:47 UTC
First, look out for a BIOS update.

If this does not help, do you see any acpi warnings/errors in dmesg:
dmesg |grep -i acpi

If the BIOS update does not help, pls attach apcidump output.

This sounds like wrongly exported BIOS values for this CPU, which often get fixed up by BIOS upgrades or possibly an ACPI interpreter bug.
Comment 4 Peter Ganzhorn 2008-01-27 03:20:13 UTC
Latest BIOS update done, didn't help at all.
BTW the machine is an IBM ThinkCentre 9210-CTO.

$ dmesg |grep -i acpi
 BIOS-e820: 000000003f520000 - 000000003f536000 (ACPI data)
 BIOS-e820: 000000003f536000 - 000000003f600000 (ACPI NVS)
ACPI: RSDP 000F6590, 0014 (r0 PTLTD )
ACPI: RSDT 3F53003F, 0040 (r1 PTLTD    RSDT    60400D0  LTP        0)
ACPI: FACP 3F535E2B, 0074 (r1 IBM    THINKCEN  60400D0 PTL         1)
ACPI: DSDT 3F530761, 56CA (r1    IBM THINKCEN  60400D0 MSFT  100000E)
ACPI: FACS 3F58BFC0, 0040
ACPI: TCPA 3F535E9F, 0032 (r2 IBM    THINKCEN  60400D0 PTL         1)
ACPI: MCFG 3F535ED1, 003C (r1 PTLTD    MCFG    60400D0  LTP        0)
ACPI: APIC 3F535F0D, 0068 (r1 PTLTD      APIC    60400D0  LTP        0)
ACPI: BOOT 3F535F75, 0028 (r1 PTLTD  $SBFTBL$  60400D0  LTP        1)
ACPI: ASF! 3F535F9D, 0063 (r32   CETP     CETP  60400D0 PTL         1)
ACPI: SSDT 3F53007F, 01FB (r1  PmRef    CpuPm     3000 INTL 20030224)
ACPI: PM-Timer IO Port: 0x1008
ACPI: Local APIC address 0xfee00000
ACPI: LAPIC (acpi_id[0x00] lapic_id[0x00] enabled)
ACPI: LAPIC (acpi_id[0x01] lapic_id[0x01] enabled)
ACPI: LAPIC_NMI (acpi_id[0x00] high edge lint[0x1])
ACPI: LAPIC_NMI (acpi_id[0x01] high edge lint[0x1])
ACPI: IOAPIC (id[0x02] address[0xfec00000] gsi_base[0])
ACPI: INT_SRC_OVR (bus 0 bus_irq 0 global_irq 2 high edge)
ACPI: INT_SRC_OVR (bus 0 bus_irq 9 global_irq 9 high level)
ACPI: IRQ0 used by override.
ACPI: IRQ2 used by override.
ACPI: IRQ9 used by override.
Using ACPI (MADT) for SMP configuration information
ACPI: Core revision 20070126
ACPI: bus type pci registered
ACPI: EC: Look up EC in DSDT
ACPI: Interpreter enabled
ACPI: (supports S0 S5)
ACPI: Using IOAPIC for interrupt routing
ACPI: PCI Root Bridge [PCI0] (0000:00)
PCI quirk: region 1000-107f claimed by ICH6 ACPI/GPIO/TCO
ACPI: PCI Interrupt Routing Table [\_SB_.PCI0._PRT]
ACPI: PCI Interrupt Routing Table [\_SB_.PCI0.EXP0._PRT]
ACPI: PCI Interrupt Routing Table [\_SB_.PCI0.EXP1._PRT]
ACPI: PCI Interrupt Routing Table [\_SB_.PCI0.SLOT._PRT]
ACPI: PCI Interrupt Link [LNKA] (IRQs 3 4 5 *7 9 10 11 12 14 15)
ACPI: PCI Interrupt Link [LNKB] (IRQs 3 4 *5 7 9 10 11 12 14 15)
ACPI: PCI Interrupt Link [LNKC] (IRQs 3 4 5 7 9 *10 11 12 14 15)
ACPI: PCI Interrupt Link [LNKD] (IRQs 3 4 5 7 *9 10 11 12 14 15)
ACPI: PCI Interrupt Link [LNKE] (IRQs 3 4 5 7 9 10 11 12 14 15) *0, disabled.
ACPI: PCI Interrupt Link [LNKF] (IRQs *3 4 5 7 9 10 11 12 14 15)
ACPI: PCI Interrupt Link [LNKG] (IRQs 3 4 5 7 9 10 11 12 14 15) *0, disabled.
ACPI: PCI Interrupt Link [LNKH] (IRQs 3 4 5 7 9 10 *11 12 14 15)
pnp: PnP ACPI init
ACPI: bus type pnp registered
pnp: PnP ACPI: found 14 devices
ACPI: ACPI bus type pnp unregistered
PCI: Using ACPI for IRQ routing
ACPI: RTC can wake from S4
ACPI: PCI Interrupt 0000:00:1c.0[A] -> GSI 17 (level, low) -> IRQ 16
ACPI: PCI Interrupt 0000:00:1c.1[B] -> GSI 16 (level, low) -> IRQ 17
ACPI: Power Button (FF) [PWRF]
ACPI: Power Button (CM) [PWRB]
ACPI: SSDT 3F53030A, 01C3 (r1  PmRef  Cpu0Ist     3000 INTL 20030224)
ACPI: Processor [CPU0] (supports 8 throttling states)
ACPI: SSDT 3F53027A, 0090 (r1  PmRef  Cpu1Ist     3000 INTL 20030224)
ACPI: Processor [CPU1] (supports 8 throttling states)
ACPI: Thermal Zone [THM0] (60 C)
ACPI: PCI Interrupt 0000:00:02.0[A] -> GSI 16 (level, low) -> IRQ 17
ACPI: PCI Interrupt 0000:02:00.0[A] -> GSI 16 (level, low) -> IRQ 17
ACPI: PCI Interrupt 0000:00:1f.2[B] -> GSI 19 (level, low) -> IRQ 18
ACPI: PCI Interrupt 0000:00:1d.0[A] -> GSI 23 (level, low) -> IRQ 19
ACPI: PCI Interrupt 0000:00:1d.1[B] -> GSI 19 (level, low) -> IRQ 18
ACPI: PCI Interrupt 0000:00:1d.2[C] -> GSI 18 (level, low) -> IRQ 20
ACPI: PCI Interrupt 0000:00:1d.3[D] -> GSI 16 (level, low) -> IRQ 17
ACPI: PCI Interrupt 0000:00:1f.3[B] -> GSI 19 (level, low) -> IRQ 18

acpidump output attached. Sorry for the little delay but I didn't have physical access to the machine to do the BIOS upgrade for the last 2 weeks.
Thanks for investigating this :)

Peter
Comment 5 Peter Ganzhorn 2008-01-27 03:21:18 UTC
Created attachment 14595 [details]
acpidump output.
Comment 6 Zhang Rui 2009-03-24 17:52:43 UTC
hi, Peter,
does the problem still exist in the latest kernel, say 2.6.29?
If yes, please
1. acpidump --addr 0x3f53030a --length 0x1c3 > cpu0ist
2. acpidump --addr 0x3f53027a --length 0x90 > cpu1ist
3. attach the output of "grep . /sys/devices/system/cpu/cpu0/cpufreq/*"
   attach cpu0ist, cpu1ist.
Comment 7 Zhang Rui 2009-03-30 07:40:33 UTC
Ping Peter,
please re-open this bug if the problem still exists in the latest kernel
and you can provide the info requested in comment #6.
Comment 8 Evgeny 2009-05-23 19:42:07 UTC
The problem still exists on gentoo-modified 2.6.29 kernel.
Comment 9 Evgeny 2009-05-23 19:44:04 UTC
Created attachment 21507 [details]
Results of running "acpidump"
Comment 10 Evgeny 2009-05-23 19:47:04 UTC
Created attachment 21508 [details]
Results of running "grep . /sys/devices/system/cpu/cpu0/cpufreq/*"

Hardware: Pentium D, 3.0GHz
Comment 11 Evgeny 2009-05-23 19:50:35 UTC
Created attachment 21509 [details]
ACPI related messages in dmesg

Please re-open

Note You need to log in before you can comment on or make changes to this bug.