lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Mon, 6 May 2024 10:21:59 +0800
From: "liwei (JK)" <liwei728@...wei.com>
To: Pierre Gondois <pierre.gondois@....com>, Viresh Kumar
	<viresh.kumar@...aro.org>, Ionela Voinescu <ionela.voinescu@....com>, Beata
 Michalska <beata.michalska@....com>, Vanshidhar Konda
	<vanshikonda@...amperecomputing.com>
CC: <rafael@...nel.org>, <al.stone@...aro.org>, <ashwin.chaugule@...aro.org>,
	<linux-pm@...r.kernel.org>, <linux-kernel@...r.kernel.org>,
	<liwei391@...wei.com>, <liaoyu15@...wei.com>
Subject: Re: [PATCH] cpufreq/cppc: changing highest_perf to nominal_perf in
 cppc_cpufreq_cpu_init()



在 2024/5/3 22:19, Pierre Gondois 写道:
> Hello Liwei,
> The change itself seems ok, but I'm not sure I understand what the
> issue is exactly.
> 
> On 4/29/24 12:49, Viresh Kumar wrote:
>> CC'ing few folks who are working with the driver.
>>
>> On 28-04-24, 17:28, liwei wrote:
>>> When turning on turbo, if frequency configuration takes effect slowly,
>>> the updated policy->cur may be equal to the frequency configured in
>>> governor->limits(), performance governor will not adjust the frequency,
>>> configured frequency will remain at turbo-freq.
>>>
>>> Simplified call stack looks as follows:
>>> cpufreq_register_driver(&cppc_cpufreq_driver)
>>>     ...
>>>     cppc_cpufreq_cpu_init()
>>>         cppc_get_perf_caps()
>>>         policy->max = cppc_perf_to_khz(caps, caps->nominal_perf)
>>>             cppc_set_perf(highest_perf) // set highest_perf
>>>             policy->cur = cpufreq_driver->get() // if cur == policy->max
> 
> During the driver initialization, we have:
> cppc_cpufreq_cpu_init()
> \-policy->max = cppc_perf_to_khz(caps, caps->nominal_perf)
> \-policy->cur = cppc_perf_to_khz(caps, caps->highest_perf);
> \-cpu_data->perf_ctrls.desired_perf = caps->highest_perf;
> \-cppc_set_perf(cpu, &cpu_data->perf_ctrls); // set freq to highest_perf
> so here:
> policy->max = nominal_freq
> policy->cur = highest_freq
> 
> 
> And then for the cpufreq framework:
> cpufreq_online()
> // IIUC there is some delay here, so policy->cur = nominal_freq ?
> // i.e. the freq. was requested to change to the highest_freq,
> // but the change is not effective yet ?
> \-policy->cur = cpufreq_driver->get(policy->cpu);
> \-cpufreq_init_policy()
>    \-cpufreq_set_policy()
>      \-cpufreq_start_governor()
>        \-cpufreq_verify_current_freq()
>          \-new_freq = cpufreq_driver->get(policy->cpu); // new_freq = 
> nominal_freq ?
>          \-if (policy->cur != new_freq)
>          \-  cpufreq_out_of_sync()
>            \- policy->cur = new_freq;
>      \-cpufreq_start_governor()
>        \-cpufreq_gov_performance_limits()
>          \-__cpufreq_driver_target(target_freq=policy->max) // with 
> policy->max = nominal_freq ?
>            \-if (target_freq == policy->cur)
>            \-  // do nothing
> 
> I am not sure I understand when you are turning the turbo on with:
> # echo 1 > /sys/devices/system/cpu/cpufreq/boost
> 
> Or do you mean that turbo is available but not turned on ?
> 

Sorry, my description is not clear enough. The scenario described above 
is during the kernel initialization process, turbo is available but 
boost is not turned on.

I found this problem is to read 
/sys/devices/system/cpu/cpufreq/policyX/cpuinfo_cur_freq directly after 
OS startup, and found that some frequencies are in turbo state and 
/sys/devices/system/cpu/cpufreq/boost has not been modified, its value 
is still 0.

LiWei
> 
> Regards,
> Pierre
> 
>>>     cpufreq_init_policy()
>>>         ...
>>>         cpufreq_start_governor() // governor: performance
>>>             new_freq = cpufreq_driver->get() // if new_freq == 
>>> policy->max
>>>             if (policy->cur != new_freq)
>>>             cpufreq_out_of_sync(policy, new_freq)
>>>                 ...
>>>                 policy->cur = new_freq
>>>             ...
>>>             policy->governor->limits()
>>>                 __cpufreq_driver_target(policy->max)
>>>                     if (policy->cur==target)
>>>                     // generate error, keep set highest_perf
>>>                         ret
>>>                     cppc_set_perf(target)
>>>
>>> Fix this by changing highest_perf to nominal_perf in 
>>> cppc_cpufreq_cpu_init().
>>>
>>> Fixes: 5477fb3bd1e8 ("ACPI / CPPC: Add a CPUFreq driver for use with 
>>> CPPC")
>>> Signed-off-by: liwei <liwei728@...wei.com>
>>> ---
>>>   drivers/cpufreq/cppc_cpufreq.c | 8 ++++----
>>>   1 file changed, 4 insertions(+), 4 deletions(-)
>>>
>>> diff --git a/drivers/cpufreq/cppc_cpufreq.c 
>>> b/drivers/cpufreq/cppc_cpufreq.c
>>> index 64420d9cfd1e..db04a82b8a97 100644
>>> --- a/drivers/cpufreq/cppc_cpufreq.c
>>> +++ b/drivers/cpufreq/cppc_cpufreq.c
>>> @@ -669,14 +669,14 @@ static int cppc_cpufreq_cpu_init(struct 
>>> cpufreq_policy *policy)
>>>       if (caps->highest_perf > caps->nominal_perf)
>>>           boost_supported = true;
>>> -    /* Set policy->cur to max now. The governors will adjust later. */
>>> -    policy->cur = cppc_perf_to_khz(caps, caps->highest_perf);
>>> -    cpu_data->perf_ctrls.desired_perf =  caps->highest_perf;
>>> +    /* Set policy->cur to norm now. */
>>> +    policy->cur = cppc_perf_to_khz(caps, caps->nominal_perf);
>>> +    cpu_data->perf_ctrls.desired_perf =  caps->nominal_perf;
>>>       ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls);
>>>       if (ret) {
>>>           pr_debug("Err setting perf value:%d on CPU:%d. ret:%d\n",
>>> -             caps->highest_perf, cpu, ret);
>>> +             caps->nominal_perf, cpu, ret);
>>>           goto out;
>>>       }
>>> -- 
>>> 2.25.1
>>

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ