Re: [PATCH V5 5/7] cpufreq: amd-pstate: Update amd-pstate preferred core ranking dynamically

From: Huang Rui <ray.huang@amd.com>
To: "Meng, Li (Jassmine)" <Li.Meng@amd.com>
Cc: "Rafael J . Wysocki" <rafael.j.wysocki@intel.com>,
	"linux-pm@vger.kernel.org" <linux-pm@vger.kernel.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"x86@kernel.org" <x86@kernel.org>,
	"linux-acpi@vger.kernel.org" <linux-acpi@vger.kernel.org>,
	Shuah Khan <skhan@linuxfoundation.org>,
	"linux-kselftest@vger.kernel.org"
	<linux-kselftest@vger.kernel.org>,
	"Fontenot, Nathan" <Nathan.Fontenot@amd.com>,
	"Sharma, Deepak" <Deepak.Sharma@amd.com>,
	"Deucher, Alexander" <Alexander.Deucher@amd.com>,
	"Limonciello, Mario" <Mario.Limonciello@amd.com>,
	"Huang, Shimmer" <Shimmer.Huang@amd.com>,
	"Yuan, Perry" <Perry.Yuan@amd.com>,
	"Du, Xiaojian" <Xiaojian.Du@amd.com>,
	Viresh Kumar <viresh.kumar@linaro.org>,
	Borislav Petkov <bp@alien8.de>,
	"Karny, Wyes" <Wyes.Karny@amd.com>
Subject: Re: [PATCH V5 5/7] cpufreq: amd-pstate: Update amd-pstate preferred core ranking dynamically
Date: Wed, 6 Sep 2023 21:57:35 +0800	[thread overview]
Message-ID: <ZPiFT1OUTOnH1s7U@amd.com> (raw)
In-Reply-To: <20230905015116.2268926-6-li.meng@amd.com>

On Tue, Sep 05, 2023 at 09:51:14AM +0800, Meng, Li (Jassmine) wrote:
> Preferred core rankings can be changed dynamically by the
> platform based on the workload and platform conditions and
> accounting for thermals and aging.
> When this occurs, cpu priority need to be set.
> 
> Signed-off-by: Meng Li <li.meng@amd.com>
> Reviewed-by: Wyes Karny <wyes.karny@amd.com>
> ---
>  drivers/cpufreq/amd-pstate.c | 36 ++++++++++++++++++++++++++++++++++--
>  include/linux/amd-pstate.h   | 11 +++++++++++
>  2 files changed, 45 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
> index 454eb6e789e7..8c19e1d50d29 100644
> --- a/drivers/cpufreq/amd-pstate.c
> +++ b/drivers/cpufreq/amd-pstate.c
> @@ -318,6 +318,7 @@ static int pstate_init_perf(struct amd_cpudata *cpudata)
>  	WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1));
>  	WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1));
>  	WRITE_ONCE(cpudata->lowest_perf, AMD_CPPC_LOWEST_PERF(cap1));
> +	WRITE_ONCE(cpudata->cppc_highest_perf, AMD_CPPC_HIGHEST_PERF(cap1));
>  
>  	return 0;
>  }
> @@ -339,6 +340,7 @@ static int cppc_init_perf(struct amd_cpudata *cpudata)
>  	WRITE_ONCE(cpudata->lowest_nonlinear_perf,
>  		   cppc_perf.lowest_nonlinear_perf);
>  	WRITE_ONCE(cpudata->lowest_perf, cppc_perf.lowest_perf);
> +	WRITE_ONCE(cpudata->cppc_highest_perf, cppc_perf.highest_perf);
>  
>  	if (cppc_state == AMD_PSTATE_ACTIVE)
>  		return 0;
> @@ -545,7 +547,7 @@ static void amd_pstate_adjust_perf(unsigned int cpu,
>  	if (target_perf < capacity)
>  		des_perf = DIV_ROUND_UP(cap_perf * target_perf, capacity);
>  
> -	min_perf = READ_ONCE(cpudata->highest_perf);
> +	min_perf = READ_ONCE(cpudata->lowest_perf);
>  	if (_min_perf < capacity)
>  		min_perf = DIV_ROUND_UP(cap_perf * _min_perf, capacity);
>  
> @@ -748,6 +750,34 @@ static void amd_pstate_init_prefcore(void)
>  	schedule_work(&sched_prefcore_work);
>  }
>  
> +static void amd_pstate_update_highest_perf(unsigned int cpu)
> +{
> +	struct cpufreq_policy *policy;
> +	struct amd_cpudata *cpudata;
> +	u32 prev_high = 0, cur_high = 0;
> +	u64 highest_perf;
> +	int ret;
> +
> +	if (!prefcore)
> +		return;
> +
> +	ret = amd_pstate_get_highest_perf(cpu, &highest_perf);
> +	if (ret)
> +		return;
> +
> +	policy = cpufreq_cpu_get(cpu);
> +	cpudata = policy->driver_data;
> +	cur_high = highest_perf;
> +	prev_high = READ_ONCE(cpudata->cppc_highest_perf);
> +
> +	if (prev_high != cur_high) {
> +		WRITE_ONCE(cpudata->cppc_highest_perf, cur_high);
> +		sched_set_itmt_core_prio(cur_high, cpu);
> +	}
> +
> +	cpufreq_cpu_put(policy);
> +}
> +
>  static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
>  {
>  	int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret;
> @@ -912,7 +942,7 @@ static ssize_t show_amd_pstate_highest_perf(struct cpufreq_policy *policy,
>  	u32 perf;
>  	struct amd_cpudata *cpudata = policy->driver_data;
>  
> -	perf = READ_ONCE(cpudata->highest_perf);
> +	perf = READ_ONCE(cpudata->cppc_highest_perf);
>  
>  	return sysfs_emit(buf, "%u\n", perf);
>  }
> @@ -1479,6 +1509,7 @@ static struct cpufreq_driver amd_pstate_driver = {
>  	.suspend	= amd_pstate_cpu_suspend,
>  	.resume		= amd_pstate_cpu_resume,
>  	.set_boost	= amd_pstate_set_boost,
> +	.update_highest_perf	= amd_pstate_update_highest_perf,
>  	.name		= "amd-pstate",
>  	.attr		= amd_pstate_attr,
>  };
> @@ -1493,6 +1524,7 @@ static struct cpufreq_driver amd_pstate_epp_driver = {
>  	.online		= amd_pstate_epp_cpu_online,
>  	.suspend	= amd_pstate_epp_suspend,
>  	.resume		= amd_pstate_epp_resume,
> +	.update_highest_perf	= amd_pstate_update_highest_perf,
>  	.name		= "amd-pstate-epp",
>  	.attr		= amd_pstate_epp_attr,
>  };
> diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h
> index 446394f84606..2159fd5693fe 100644
> --- a/include/linux/amd-pstate.h
> +++ b/include/linux/amd-pstate.h
> @@ -31,6 +31,11 @@ struct amd_aperf_mperf {
>  	u64 mperf;
>  	u64 tsc;
>  };
> +	/* For platforms that do not support the preferred core feature, the
> +	 * highest_pef may be configured with 166 or 255, to avoid max frequency
> +	 * calculated wrongly. we take the AMD_CPPC_HIGHEST_PERF(cap1) value as
> +	 * the default max perf.
> +	 */

This seems a duplicate commments?

Thanks,
Ray

>  
>  /**
>   * struct amd_cpudata - private CPU data for AMD P-State
> @@ -39,11 +44,16 @@ struct amd_aperf_mperf {
>   * @cppc_req_cached: cached performance request hints
>   * @highest_perf: the maximum performance an individual processor may reach,
>   *		  assuming ideal conditions
> + *		  For platforms that do not support the preferred core feature, the
> + *		  highest_pef may be configured with 166 or 255, to avoid max frequency
> + *		  calculated wrongly. we take the fixed value as the highest_perf.
>   * @nominal_perf: the maximum sustained performance level of the processor,
>   *		  assuming ideal operating conditions
>   * @lowest_nonlinear_perf: the lowest performance level at which nonlinear power
>   *			   savings are achieved
>   * @lowest_perf: the absolute lowest performance level of the processor
> + * @cppc_highest_perf: the maximum performance an individual processor may reach,
> + *		  assuming ideal conditions
>   * @max_freq: the frequency that mapped to highest_perf
>   * @min_freq: the frequency that mapped to lowest_perf
>   * @nominal_freq: the frequency that mapped to nominal_perf
> @@ -70,6 +80,7 @@ struct amd_cpudata {
>  	u32	nominal_perf;
>  	u32	lowest_nonlinear_perf;
>  	u32	lowest_perf;
> +	u32     cppc_highest_perf;
>  
>  	u32	max_freq;
>  	u32	min_freq;
> -- 
> 2.34.1
> 