From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from ozlabs.org (ozlabs.org [103.22.144.67]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 9D6F31A058C for ; Thu, 7 May 2015 20:35:48 +1000 (AEST) Received: from e28smtp06.in.ibm.com (e28smtp06.in.ibm.com [122.248.162.6]) (using TLSv1 with cipher CAMELLIA256-SHA (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id E8DBC140079 for ; Thu, 7 May 2015 20:35:46 +1000 (AEST) Received: from /spool/local by e28smtp06.in.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Thu, 7 May 2015 16:05:43 +0530 Received: from d28relay01.in.ibm.com (d28relay01.in.ibm.com [9.184.220.58]) by d28dlp03.in.ibm.com (Postfix) with ESMTP id A1489125804B for ; Thu, 7 May 2015 16:07:48 +0530 (IST) Received: from d28av05.in.ibm.com (d28av05.in.ibm.com [9.184.220.67]) by d28relay01.in.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id t47AZeus17301666 for ; Thu, 7 May 2015 16:05:40 +0530 Received: from d28av05.in.ibm.com (localhost [127.0.0.1]) by d28av05.in.ibm.com (8.14.4/8.14.4/NCO v10.0 AVout) with ESMTP id t47AZdVc021008 for ; Thu, 7 May 2015 16:05:39 +0530 Message-ID: <554B3FE9.7050908@linux.vnet.ibm.com> Date: Thu, 07 May 2015 16:05:21 +0530 From: Shilpasri G Bhat MIME-Version: 1.0 To: Preeti U Murthy , linuxppc-dev@ozlabs.org, linux-kernel@vger.kernel.org Subject: Re: [PATCH v3 1/6] cpufreq: poowernv: Handle throttling due to Pmax capping at chip level References: <1430729652-14813-1-git-send-email-shilpa.bhat@linux.vnet.ibm.com> <1430729652-14813-2-git-send-email-shilpa.bhat@linux.vnet.ibm.com> <55483E4B.4080405@linux.vnet.ibm.com> <55485DE9.4070609@linux.vnet.ibm.com> <55488188.9070908@linux.vnet.ibm.com> In-Reply-To: <55488188.9070908@linux.vnet.ibm.com> Content-Type: text/plain; charset=utf-8 Cc: viresh.kumar@linaro.org, rjw@rjwysocki.net, linux-pm@vger.kernel.org List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On 05/05/2015 02:08 PM, Preeti U Murthy wrote: > On 05/05/2015 11:36 AM, Shilpasri G Bhat wrote: >> Hi Preeti, >> >> On 05/05/2015 09:21 AM, Preeti U Murthy wrote: >>> Hi Shilpa, >>> >>> On 05/04/2015 02:24 PM, Shilpasri G Bhat wrote: >>>> The On-Chip-Controller(OCC) can throttle cpu frequency by reducing the >>>> max allowed frequency for that chip if the chip exceeds its power or >>>> temperature limits. As Pmax capping is a chip level condition report >>>> this throttling behavior at chip level and also do not set the global >>>> 'throttled' on Pmax capping instead set the per-chip throttled >>>> variable. Report unthrottling if Pmax is restored after throttling. >>>> >>>> This patch adds a structure to store chip id and throttled state of >>>> the chip. >>>> >>>> Signed-off-by: Shilpasri G Bhat >>>> --- >>>> drivers/cpufreq/powernv-cpufreq.c | 59 ++++++++++++++++++++++++++++++++++++--- >>>> 1 file changed, 55 insertions(+), 4 deletions(-) >>>> >>>> diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c >>>> index ebef0d8..d0c18c9 100644 >>>> --- a/drivers/cpufreq/powernv-cpufreq.c >>>> +++ b/drivers/cpufreq/powernv-cpufreq.c >>>> @@ -27,6 +27,7 @@ >>>> #include >>>> #include >>>> #include >>>> +#include >>>> >>>> #include >>>> #include >>>> @@ -42,6 +43,13 @@ >>>> static struct cpufreq_frequency_table powernv_freqs[POWERNV_MAX_PSTATES+1]; >>>> static bool rebooting, throttled; >>>> >>>> +static struct chip { >>>> + unsigned int id; >>>> + bool throttled; >>>> +} *chips; >>>> + >>>> +static int nr_chips; >>>> + >>>> /* >>>> * Note: The set of pstates consists of contiguous integers, the >>>> * smallest of which is indicated by powernv_pstate_info.min, the >>>> @@ -301,22 +309,33 @@ static inline unsigned int get_nominal_index(void) >>>> static void powernv_cpufreq_throttle_check(unsigned int cpu) >>>> { >>>> unsigned long pmsr; >>>> - int pmsr_pmax, pmsr_lp; >>>> + int pmsr_pmax, pmsr_lp, i; >>>> >>>> pmsr = get_pmspr(SPRN_PMSR); >>>> >>>> + for (i = 0; i < nr_chips; i++) >>>> + if (chips[i].id == cpu_to_chip_id(cpu)) >>>> + break; >>>> + >>>> /* Check for Pmax Capping */ >>>> pmsr_pmax = (s8)PMSR_MAX(pmsr); >>>> if (pmsr_pmax != powernv_pstate_info.max) { >>>> - throttled = true; >>>> - pr_info("CPU %d Pmax is reduced to %d\n", cpu, pmsr_pmax); >>>> - pr_info("Max allowed Pstate is capped\n"); >>>> + if (chips[i].throttled) >>>> + goto next; >>>> + chips[i].throttled = true; >>>> + pr_info("CPU %d on Chip %u has Pmax reduced to %d\n", cpu, >>>> + chips[i].id, pmsr_pmax); >>>> + } else if (chips[i].throttled) { >>>> + chips[i].throttled = false; >>> >>> Is this check on pmax sufficient to indicate that the chip is unthrottled ? >> >> Unthrottling due to Pmax uncapping here is specific to a chip. So it is >> sufficient to decide throttling/unthrottling when OCC is active for that chip. > > Ok then we can perhaps exit after detecting unthrottling here. This won't work for older firmwares which do not clear "Frequency control enabled bit" on OCC reset cycle. So let us check for remaining two conditions on unthrottling as well. >> >>> >>>> + pr_info("CPU %d on Chip %u has Pmax restored to %d\n", cpu, >>>> + chips[i].id, pmsr_pmax); >>>> } >>>> >>>> /* >>>> * Check for Psafe by reading LocalPstate >>>> * or check if Psafe_mode_active is set in PMSR. >>>> */ >>>> +next: >>>> pmsr_lp = (s8)PMSR_LP(pmsr); >>>> if ((pmsr_lp < powernv_pstate_info.min) || >>>> (pmsr & PMSR_PSAFE_ENABLE)) { >>>> @@ -414,6 +433,33 @@ static struct cpufreq_driver powernv_cpufreq_driver = { >>>> .attr = powernv_cpu_freq_attr, >>> >>> What about the situation where although occ is active, this particular >>> chip has been throttled and we end up repeatedly reporting "pstate set >>> to safe" and "frequency control disabled from OS" ? Should we not have a >>> check on (chips[i].throttled) before reporting an anomaly for these two >>> scenarios as well just like you have for pmsr_pmax ? >> >> We will not have "Psafe" and "frequency control disabled" repeatedly printed >> because of global variable 'throttled', which is set to true on passing any of >> these two conditions. >> >> It is quite unlikely behavior to have only one chip in "Psafe" or "frequency >> control disabled" state. These two conditions are most likely to happen during >> an OCC reset cycle which will occur across all chips. > > Let us then add a comment to indicate that Psafe and frequency control > disabled conditions will fail *only if OCC is inactive* and not > otherwise and that this is a system wide phenomenon. > I agree that adding a comment here will clear global vs local throttling scenarios, but this will contradict the architectural design of OCC wherein it can independently go to "Psafe" and "frequency control disabled" state. It is the implementation in FSP today that has made the above two states global. My point is adding a comment here may be confusing if at all for the future firmwares this implementation is changed. Having said that the current patch set still seems fit for the newer implementation for the following reason: 1) The aim here is to identify any sort of throttling and report it to the user with least flooding of error messages, which will happen even if OCC can independently reset and restore. 2) On unthrottling verify throttling on the chips with the exception of Pmax capping is also taken care by this patch set. Thanks and Regards, Shilpa