From mboxrd@z Thu Jan 1 00:00:00 1970 From: Michael Reinelt Subject: Re: Core2Duo locked at 800MHz Date: Tue, 27 Nov 2007 14:36:16 +0000 Message-ID: <474C2B60.5000501@reinelt.co.at> References: <474A6C62.3070103@reinelt.co.at> <20071126190929.GE15764@redhat.com> <474BB4F2.9040604@reinelt.co.at> <1196160448.23251.21.camel@queen.suse.de> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <1196160448.23251.21.camel@queen.suse.de> List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: cpufreq-bounces@lists.linux.org.uk Errors-To: cpufreq-bounces+glkc-cpufreq=m.gmane.org+glkc-cpufreq=m.gmane.org@lists.linux.org.uk To: trenn@suse.de Cc: Dave Jones , cpufreq@lists.linux.org.uk Hi THomas, > It is probably limited through _PPC again. > Dave, Len: Can you please add the patch that _PPC changes are printed > with cpufreq.debug, pls. > I posted this a while ago on the cpufreq list: > Subject: [PATCH] Print _PPC changes via cpufreq debug layer > http://article.gmane.org/gmane.linux.kernel.cpufreq/5642 Looks like it is :-( I applied your patch and did the debugging again, and found the following: merlin.merlin.local:/home/michi # grep PPC Lifebook.syslog* cpufreq-core: CPU 0: _PPC is 0 - frequency not limited cpufreq-core: CPU 1: _PPC is 0 - frequency not limited cpufreq-core: CPU 0: _PPC is 1 - frequency limited cpufreq-core: CPU 1: _PPC is 1 - frequency limited cpufreq-core: CPU 0: _PPC is 2 - frequency limited cpufreq-core: CPU 1: _PPC is 2 - frequency limited cpufreq-core: CPU 0: _PPC is 3 - frequency limited cpufreq-core: CPU 1: _PPC is 3 - frequency limited cpufreq-core: CPU 0: _PPC is 4 - frequency limited cpufreq-core: CPU 1: _PPC is 4 - frequency limited cpufreq-core: CPU 0: _PPC is 5 - frequency limited the first PPC message appears where acpi_cpufreq isn't even loaded. As I found these tables in the debug output: freq-table: table entry 0: 2401000 kHz, 0 index freq-table: table entry 1: 2400000 kHz, 1 index freq-table: table entry 2: 2000000 kHz, 2 index freq-table: table entry 3: 1600000 kHz, 3 index freq-table: table entry 4: 1200000 kHz, 4 index freq-table: table entry 5: 800000 kHz, 5 index acpi-cpufreq: *P0: 2401 MHz, 35000 mW, 10 uS acpi-cpufreq: P1: 2400 MHz, 35000 mW, 10 uS acpi-cpufreq: P2: 2000 MHz, 28000 mW, 10 uS acpi-cpufreq: P3: 1600 MHz, 22000 mW, 10 uS acpi-cpufreq: P4: 1200 MHz, 16000 mW, 10 uS acpi-cpufreq: P5: 800 MHz, 14000 mW, 10 uS as the reported _PPC value shows up after the corresponding P state has been entered, I guess thats the reason for my problem: Looks like my notebook can enter a certain P-state, but can never leave it towards a higher frequency. so... - wtf is _PPC? - does this look like a BIOS bug? - i remember seeing some sort of "disable _PPC by a specific module parameter" patch somewhere... "ignore_ppc" or something... is this an "official" patch which is worth to give it a try? Somebody knows an official location for this patch? I'm happily looking forward to get this issue solved! thanks, Michael -- Michael Reinelt http://home.pages.at/reinelt GPG-Key 0xDF13BA50 ICQ #288386781