2009-04-23 07:28:58

by Chris Wright

[permalink] [raw]
Subject: [patch 013/100] ACPI: cap off P-state transition latency from buggy BIOSes

-stable review patch. If anyone has any objections, please let us know.
---------------------

From: Venkatesh Pallipadi <[email protected]>

upstream commit: a59d1637eb0e0a37ee0e5c92800c60abe3624e24

Some BIOSes report very high frequency transition latency which are plainly
wrong on CPus that can change frequency using native MSR interface.

One such system is IBM T42 (2327-8ZU) as reported by Owen Taylor and
Rik van Riel.

cpufreq_ondemand driver uses this transition latency to come up with a
reasonable sampling interval to sample CPU usage and with such high
latency value, ondemand sampling interval ends up being very high
(0.5 sec, in this particular case), resulting in performance impact due to
slow response to increasing frequency.

Fix it by capping-off the transition latency to 20uS for native MSR based
frequency transitions.

mjg: We've confirmed that this also helps on the X31

Signed-off-by: Venkatesh Pallipadi <[email protected]>
Acked-by: Matthew Garrett <[email protected]>
Signed-off-by: Len Brown <[email protected]>
Signed-off-by: Chris Wright <[email protected]>
---

arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c | 12 ++++++++++++
1 file changed, 12 insertions(+)

--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -680,6 +680,18 @@ static int acpi_cpufreq_cpu_init(struct
perf->states[i].transition_latency * 1000;
}

+ /* Check for high latency (>20uS) from buggy BIOSes, like on T42 */
+ if (perf->control_register.space_id == ACPI_ADR_SPACE_FIXED_HARDWARE &&
+ policy->cpuinfo.transition_latency > 20 * 1000) {
+ static int print_once;
+ policy->cpuinfo.transition_latency = 20 * 1000;
+ if (!print_once) {
+ print_once = 1;
+ printk(KERN_INFO "Capping off P-state tranision latency"
+ " at 20 uS\n");
+ }
+ }
+
data->max_freq = perf->states[0].core_frequency * 1000;
/* table init */
for (i=0; i<perf->state_count; i++) {


2009-04-25 15:58:29

by Martin Steigerwald

[permalink] [raw]
Subject: Re: [patch 013/100] ACPI: cap off P-state transition latency from buggy BIOSes

Am Donnerstag 23 April 2009 schrieb Chris Wright:
> -stable review patch. If anyone has any objections, please let us
> know. ---------------------
>
> From: Venkatesh Pallipadi <[email protected]>
>
> upstream commit: a59d1637eb0e0a37ee0e5c92800c60abe3624e24
>
> Some BIOSes report very high frequency transition latency which are
> plainly wrong on CPus that can change frequency using native MSR
> interface.
>
> One such system is IBM T42 (2327-8ZU) as reported by Owen Taylor and
> Rik van Riel.
>
> cpufreq_ondemand driver uses this transition latency to come up with a
> reasonable sampling interval to sample CPU usage and with such high
> latency value, ondemand sampling interval ends up being very high
> (0.5 sec, in this particular case), resulting in performance impact due
> to slow response to increasing frequency.
>
> Fix it by capping-off the transition latency to 20uS for native MSR
> based frequency transitions.
>
> mjg: We've confirmed that this also helps on the X31
>
> Signed-off-by: Venkatesh Pallipadi <[email protected]>
> Acked-by: Matthew Garrett <[email protected]>
> Signed-off-by: Len Brown <[email protected]>
> Signed-off-by: Chris Wright <[email protected]>
> ---
>
> arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c | 12 ++++++++++++
> 1 file changed, 12 insertions(+)
>
> --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
> +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
> @@ -680,6 +680,18 @@ static int acpi_cpufreq_cpu_init(struct
> perf->states[i].transition_latency * 1000;
> }
>
> + /* Check for high latency (>20uS) from buggy BIOSes, like on T42 */
> + if (perf->control_register.space_id == ACPI_ADR_SPACE_FIXED_HARDWARE
> && + policy->cpuinfo.transition_latency > 20 * 1000) {
> + static int print_once;
> + policy->cpuinfo.transition_latency = 20 * 1000;
> + if (!print_once) {
> + print_once = 1;
> + printk(KERN_INFO "Capping off P-state tranision latency"

typo: tranision => transition

> + " at 20 uS\n");
> + }
> + }
> +
> data->max_freq = perf->states[0].core_frequency * 1000;
> /* table init */
> for (i=0; i<perf->state_count; i++) {
--
Martin 'Helios' Steigerwald - http://www.Lichtvoll.de
GPG: 03B0 0D6C 0040 0710 4AFA B82F 991B EAAC A599 84C7


Attachments:
(No filename) (2.21 kB)
signature.asc (197.00 B)
This is a digitally signed message part.
Download all attachments