RE: [PATCH v9 06/13] cpufreq: amd-pstate: implement Pstate EPP support for the AMD processors

[Yuan, Perry]

[AMD Official Use Only - General]

Hi Mario. 

> -----Original Message-----
> From: Limonciello, Mario <Mario.Limonciello@xxxxxxx>
> Sent: Wednesday, January 4, 2023 9:05 AM
> To: Yuan, Perry <Perry.Yuan@xxxxxxx>; rafael.j.wysocki@xxxxxxxxx; Huang,
> Ray <Ray.Huang@xxxxxxx>; viresh.kumar@xxxxxxxxxx
> Cc: Sharma, Deepak <Deepak.Sharma@xxxxxxx>; Fontenot, Nathan
> <Nathan.Fontenot@xxxxxxx>; Deucher, Alexander
> <Alexander.Deucher@xxxxxxx>; Huang, Shimmer
> <Shimmer.Huang@xxxxxxx>; Du, Xiaojian <Xiaojian.Du@xxxxxxx>; Meng,
> Li (Jassmine) <Li.Meng@xxxxxxx>; Karny, Wyes <Wyes.Karny@xxxxxxx>;
> linux-pm@xxxxxxxxxxxxxxx; linux-kernel@xxxxxxxxxxxxxxx
> Subject: Re: [PATCH v9 06/13] cpufreq: amd-pstate: implement Pstate EPP
> support for the AMD processors
> 
> On 12/25/2022 10:34, Perry Yuan wrote:
> > From: Perry Yuan <Perry.Yuan@xxxxxxx>
> >
> > Add EPP driver support for AMD SoCs which support a dedicated MSR for
> > CPPC.  EPP is used by the DPM controller to configure the frequency
> > that a core operates at during short periods of activity.
> >
> > The SoC EPP targets are configured on a scale from 0 to 255 where 0
> > represents maximum performance and 255 represents maximum
> efficiency.
> >
> > The amd-pstate driver exports profile string names to userspace that
> > are tied to specific EPP values.
> >
> > The balance_performance string (0x80) provides the best balance for
> > efficiency versus power on most systems, but users can choose other
> > strings to meet their needs as well.
> >
> > $ cat
> >
> /sys/devices/system/cpu/cpufreq/policy0/energy_performance_available_
> p
> > references default performance balance_performance balance_power
> power
> >
> > $ cat
> >
> /sys/devices/system/cpu/cpufreq/policy0/energy_performance_preferenc
> e
> > balance_performance
> >
> > To enable the driver,it needs to add `amd_pstate=active` to kernel
> > command line and kernel will load the active mode epp driver
> >
> > Signed-off-by: Perry Yuan <Perry.Yuan@xxxxxxx>
> > ---
> >   drivers/cpufreq/amd-pstate.c | 374
> ++++++++++++++++++++++++++++++++++-
> >   include/linux/amd-pstate.h   |  10 +
> >   2 files changed, 378 insertions(+), 6 deletions(-)
> >
> > diff --git a/drivers/cpufreq/amd-pstate.c
> > b/drivers/cpufreq/amd-pstate.c index 65c16edbbb20..779bbb58d909
> 100644
> > --- a/drivers/cpufreq/amd-pstate.c
> > +++ b/drivers/cpufreq/amd-pstate.c
> > @@ -59,7 +59,9 @@
> >    * we disable it by default to go acpi-cpufreq on these processors and add
> a
> >    * module parameter to be able to enable it manually for debugging.
> >    */
> > +static struct cpufreq_driver *default_pstate_driver;
> 
> Considering how this is used and that it can be changed dynamically via sysfs,
> I think this pointer would be better named "current_pstate_driver" or
> perhaps "active_pstate_driver".

current_pstate_driver looks better, will change it in v10. 
thanks for the suggestion.

Perry. 

> 
> >   static struct cpufreq_driver amd_pstate_driver;
> > +static struct cpufreq_driver amd_pstate_epp_driver;
> >   static int cppc_state = AMD_PSTATE_DISABLE;
> >
> >   static inline int get_mode_idx_from_str(const char *str, size_t
> > size) @@ -73,6 +75,114 @@ static inline int get_mode_idx_from_str(const
> char *str, size_t size)
> >   	return -EINVAL;
> >   }
> >
> > +static DEFINE_MUTEX(amd_pstate_limits_lock);
> > +static DEFINE_MUTEX(amd_pstate_driver_lock);
> > +
> > +static s16 amd_pstate_get_epp(struct amd_cpudata *cpudata, u64
> > +cppc_req_cached) {
> > +	u64 epp;
> > +	int ret;
> > +
> > +	if (boot_cpu_has(X86_FEATURE_CPPC)) {
> > +		if (!cppc_req_cached) {
> > +			epp = rdmsrl_on_cpu(cpudata->cpu,
> MSR_AMD_CPPC_REQ,
> > +					&cppc_req_cached);
> > +			if (epp)
> > +				return epp;
> > +		}
> > +		epp = (cppc_req_cached >> 24) & 0xFF;
> > +	} else {
> > +		ret = cppc_get_epp_perf(cpudata->cpu, &epp);
> > +		if (ret < 0) {
> > +			pr_debug("Could not retrieve energy perf value
> (%d)\n", ret);
> > +			return -EIO;
> > +		}
> > +	}
> > +
> > +	return (s16)(epp & 0xff);
> > +}
> > +
> > +static int amd_pstate_get_energy_pref_index(struct amd_cpudata
> > +*cpudata) {
> > +	s16 epp;
> > +	int index = -EINVAL;
> > +
> > +	epp = amd_pstate_get_epp(cpudata, 0);
> > +	if (epp < 0)
> > +		return epp;
> > +
> > +	switch (epp) {
> > +	case HWP_EPP_PERFORMANCE:
> > +		index = EPP_INDEX_PERFORMANCE;
> > +		break;
> > +	case HWP_EPP_BALANCE_PERFORMANCE:
> > +		index = EPP_INDEX_BALANCE_PERFORMANCE;
> > +		break;
> > +	case HWP_EPP_BALANCE_POWERSAVE:
> > +		index = EPP_INDEX_BALANCE_POWERSAVE;
> > +		break;
> > +	case HWP_EPP_POWERSAVE:
> > +		index = EPP_INDEX_POWERSAVE;
> > +		break;
> > +	default:
> > +		break;
> > +	}
> > +
> > +	return index;
> > +}
> > +
> > +static int amd_pstate_set_epp(struct amd_cpudata *cpudata, u32 epp) {
> > +	int ret;
> > +	struct cppc_perf_ctrls perf_ctrls;
> > +
> > +	if (boot_cpu_has(X86_FEATURE_CPPC)) {
> > +		u64 value = READ_ONCE(cpudata->cppc_req_cached);
> > +
> > +		value &= ~GENMASK_ULL(31, 24);
> > +		value |= (u64)epp << 24;
> > +		WRITE_ONCE(cpudata->cppc_req_cached, value);
> > +
> > +		ret = wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ,
> value);
> > +		if (!ret)
> > +			cpudata->epp_cached = epp;
> > +	} else {
> > +		perf_ctrls.energy_perf = epp;
> > +		ret = cppc_set_epp_perf(cpudata->cpu, &perf_ctrls, 1);
> > +		if (ret) {
> > +			pr_debug("failed to set energy perf value (%d)\n",
> ret);
> > +			return ret;
> > +		}
> > +		cpudata->epp_cached = epp;
> > +	}
> > +
> > +	return ret;
> > +}
> > +
> > +static int amd_pstate_set_energy_pref_index(struct amd_cpudata
> *cpudata,
> > +		int pref_index)
> > +{
> > +	int epp = -EINVAL;
> > +	int ret;
> > +
> > +	if (!pref_index) {
> > +		pr_debug("EPP pref_index is invalid\n");
> > +		return -EINVAL;
> > +	}
> > +
> > +	if (epp == -EINVAL)
> > +		epp = epp_values[pref_index];
> > +
> > +	if (epp > 0 && cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
> {
> > +		pr_debug("EPP cannot be set under performance policy\n");
> > +		return -EBUSY;
> > +	}
> > +
> > +	ret = amd_pstate_set_epp(cpudata, epp);
> > +
> > +	return ret;
> > +}
> > +
> >   static inline int pstate_enable(bool enable)
> >   {
> >   	return wrmsrl_safe(MSR_AMD_CPPC_ENABLE, enable); @@ -81,11
> +191,21
> > @@ static inline int pstate_enable(bool enable)
> >   static int cppc_enable(bool enable)
> >   {
> >   	int cpu, ret = 0;
> > +	struct cppc_perf_ctrls perf_ctrls;
> >
> >   	for_each_present_cpu(cpu) {
> >   		ret = cppc_set_enable(cpu, enable);
> >   		if (ret)
> >   			return ret;
> > +
> > +		/* Enable autonomous mode for EPP */
> > +		if (cppc_state == AMD_PSTATE_ACTIVE) {
> > +			/* Set desired perf as zero to allow EPP firmware
> control */
> > +			perf_ctrls.desired_perf = 0;
> > +			ret = cppc_set_perf(cpu, &perf_ctrls);
> > +			if (ret)
> > +				return ret;
> > +		}
> >   	}
> >
> >   	return ret;
> > @@ -429,7 +549,7 @@ static void amd_pstate_boost_init(struct
> amd_cpudata *cpudata)
> >   		return;
> >
> >   	cpudata->boost_supported = true;
> > -	amd_pstate_driver.boost_enabled = true;
> > +	default_pstate_driver->boost_enabled = true;
> >   }
> >
> >   static void amd_perf_ctl_reset(unsigned int cpu) @@ -603,10 +723,61
> > @@ static ssize_t show_amd_pstate_highest_perf(struct cpufreq_policy
> *policy,
> >   	return sprintf(&buf[0], "%u\n", perf);
> >   }
> >
> > +static ssize_t show_energy_performance_available_preferences(
> > +				struct cpufreq_policy *policy, char *buf) {
> > +	int i = 0;
> > +	int offset = 0;
> > +
> > +	while (energy_perf_strings[i] != NULL)
> > +		offset += sysfs_emit_at(buf, offset, "%s ",
> > +energy_perf_strings[i++]);
> > +
> > +	sysfs_emit_at(buf, offset, "\n");
> > +
> > +	return offset;
> > +}
> > +
> > +static ssize_t store_energy_performance_preference(
> > +		struct cpufreq_policy *policy, const char *buf, size_t count) {
> > +	struct amd_cpudata *cpudata = policy->driver_data;
> > +	char str_preference[21];
> > +	ssize_t ret;
> > +
> > +	ret = sscanf(buf, "%20s", str_preference);
> > +	if (ret != 1)
> > +		return -EINVAL;
> > +
> > +	ret = match_string(energy_perf_strings, -1, str_preference);
> > +	if (ret < 0)
> > +		return -EINVAL;
> > +
> > +	mutex_lock(&amd_pstate_limits_lock);
> > +	ret = amd_pstate_set_energy_pref_index(cpudata, ret);
> > +	mutex_unlock(&amd_pstate_limits_lock);
> > +
> > +	return ret ?: count;
> > +}
> > +
> > +static ssize_t show_energy_performance_preference(
> > +				struct cpufreq_policy *policy, char *buf) {
> > +	struct amd_cpudata *cpudata = policy->driver_data;
> > +	int preference;
> > +
> > +	preference = amd_pstate_get_energy_pref_index(cpudata);
> > +	if (preference < 0)
> > +		return preference;
> > +
> > +	return sysfs_emit(buf, "%s\n", energy_perf_strings[preference]); }
> > +
> >   cpufreq_freq_attr_ro(amd_pstate_max_freq);
> >   cpufreq_freq_attr_ro(amd_pstate_lowest_nonlinear_freq);
> >
> >   cpufreq_freq_attr_ro(amd_pstate_highest_perf);
> > +cpufreq_freq_attr_rw(energy_performance_preference);
> > +cpufreq_freq_attr_ro(energy_performance_available_preferences);
> >
> >   static struct freq_attr *amd_pstate_attr[] = {
> >   	&amd_pstate_max_freq,
> > @@ -615,6 +786,181 @@ static struct freq_attr *amd_pstate_attr[] = {
> >   	NULL,
> >   };
> >
> > +static struct freq_attr *amd_pstate_epp_attr[] = {
> > +	&amd_pstate_max_freq,
> > +	&amd_pstate_lowest_nonlinear_freq,
> > +	&amd_pstate_highest_perf,
> > +	&energy_performance_preference,
> > +	&energy_performance_available_preferences,
> > +	NULL,
> > +};
> > +
> > +static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) {
> > +	int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret;
> > +	struct amd_cpudata *cpudata;
> > +	struct device *dev;
> > +	int rc;
> > +	u64 value;
> > +
> > +	dev = get_cpu_device(policy->cpu);
> > +	if (!dev)
> > +		goto free_cpudata1;
> > +
> > +	cpudata = kzalloc(sizeof(*cpudata), GFP_KERNEL);
> > +	if (!cpudata)
> > +		return -ENOMEM;
> > +
> > +	cpudata->cpu = policy->cpu;
> > +	cpudata->epp_policy = 0;
> > +
> > +	rc = amd_pstate_init_perf(cpudata);
> > +	if (rc)
> > +		goto free_cpudata1;
> > +
> > +	min_freq = amd_get_min_freq(cpudata);
> > +	max_freq = amd_get_max_freq(cpudata);
> > +	nominal_freq = amd_get_nominal_freq(cpudata);
> > +	lowest_nonlinear_freq = amd_get_lowest_nonlinear_freq(cpudata);
> > +	if (min_freq < 0 || max_freq < 0 || min_freq > max_freq) {
> > +		dev_err(dev, "min_freq(%d) or max_freq(%d) value is
> incorrect\n",
> > +				min_freq, max_freq);
> > +		ret = -EINVAL;
> > +		goto free_cpudata1;
> > +	}
> > +
> > +	policy->cpuinfo.min_freq = min_freq;
> > +	policy->cpuinfo.max_freq = max_freq;
> > +	/* It will be updated by governor */
> > +	policy->cur = policy->cpuinfo.min_freq;
> > +
> > +	/* Initial processor data capability frequencies */
> > +	cpudata->max_freq = max_freq;
> > +	cpudata->min_freq = min_freq;
> > +	cpudata->nominal_freq = nominal_freq;
> > +	cpudata->lowest_nonlinear_freq = lowest_nonlinear_freq;
> > +
> > +	policy->driver_data = cpudata;
> > +
> > +	cpudata->epp_cached = amd_pstate_get_epp(cpudata, value);
> > +
> > +	policy->min = policy->cpuinfo.min_freq;
> > +	policy->max = policy->cpuinfo.max_freq;
> > +
> > +	/*
> > +	 * Set the policy to powersave to provide a valid fallback value in case
> > +	 * the default cpufreq governor is neither powersave nor
> performance.
> > +	 */
> > +	policy->policy = CPUFREQ_POLICY_POWERSAVE;
> > +
> > +	if (boot_cpu_has(X86_FEATURE_CPPC)) {
> > +		policy->fast_switch_possible = true;
> > +		ret = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ,
> &value);
> > +		if (ret)
> > +			return ret;
> > +		WRITE_ONCE(cpudata->cppc_req_cached, value);
> > +
> > +		ret = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1,
> &value);
> > +		if (ret)
> > +			return ret;
> > +		WRITE_ONCE(cpudata->cppc_cap1_cached, value);
> > +	}
> > +	amd_pstate_boost_init(cpudata);
> > +
> > +	return 0;
> > +
> > +free_cpudata1:
> > +	kfree(cpudata);
> > +	return ret;
> > +}
> > +
> > +static int amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy) {
> > +	pr_debug("CPU %d exiting\n", policy->cpu);
> > +	policy->fast_switch_possible = false;
> > +	return 0;
> > +}
> > +
> > +static void amd_pstate_epp_init(unsigned int cpu) {
> > +	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
> > +	struct amd_cpudata *cpudata = policy->driver_data;
> > +	u32 max_perf, min_perf;
> > +	u64 value;
> > +	s16 epp;
> > +
> > +	max_perf = READ_ONCE(cpudata->highest_perf);
> > +	min_perf = READ_ONCE(cpudata->lowest_perf);
> > +
> > +	value = READ_ONCE(cpudata->cppc_req_cached);
> > +
> > +	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
> > +		min_perf = max_perf;
> > +
> > +	/* Initial min/max values for CPPC Performance Controls Register */
> > +	value &= ~AMD_CPPC_MIN_PERF(~0L);
> > +	value |= AMD_CPPC_MIN_PERF(min_perf);
> > +
> > +	value &= ~AMD_CPPC_MAX_PERF(~0L);
> > +	value |= AMD_CPPC_MAX_PERF(max_perf);
> > +
> > +	/* CPPC EPP feature require to set zero to the desire perf bit */
> > +	value &= ~AMD_CPPC_DES_PERF(~0L);
> > +	value |= AMD_CPPC_DES_PERF(0);
> > +
> > +	if (cpudata->epp_policy == cpudata->policy)
> > +		goto skip_epp;
> > +
> > +	cpudata->epp_policy = cpudata->policy;
> > +
> > +	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) {
> > +		epp = amd_pstate_get_epp(cpudata, value);
> > +		if (epp < 0)
> > +			goto skip_epp;
> > +		/* force the epp value to be zero for performance policy */
> > +		epp = 0;
> > +	} else {
> > +		/* Get BIOS pre-defined epp value */
> > +		epp = amd_pstate_get_epp(cpudata, value);
> > +		if (epp)
> > +			goto skip_epp;
> > +	}
> > +	/* Set initial EPP value */
> > +	if (boot_cpu_has(X86_FEATURE_CPPC)) {
> > +		value &= ~GENMASK_ULL(31, 24);
> > +		value |= (u64)epp << 24;
> > +	}
> > +
> > +skip_epp:
> > +	WRITE_ONCE(cpudata->cppc_req_cached, value);
> > +	amd_pstate_set_epp(cpudata, epp);
> > +	cpufreq_cpu_put(policy);
> > +}
> > +
> > +static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy) {
> > +	struct amd_cpudata *cpudata = policy->driver_data;
> > +
> > +	if (!policy->cpuinfo.max_freq)
> > +		return -ENODEV;
> > +
> > +	pr_debug("set_policy: cpuinfo.max %u policy->max %u\n",
> > +				policy->cpuinfo.max_freq, policy->max);
> > +
> > +	cpudata->policy = policy->policy;
> > +
> > +	amd_pstate_epp_init(policy->cpu);
> > +
> > +	return 0;
> > +}
> > +
> > +static int amd_pstate_epp_verify_policy(struct cpufreq_policy_data
> > +*policy) {
> > +	cpufreq_verify_within_cpu_limits(policy);
> > +	pr_debug("policy_max =%d, policy_min=%d\n", policy->max, policy-
> >min);
> > +	return 0;
> > +}
> > +
> >   static struct cpufreq_driver amd_pstate_driver = {
> >   	.flags		= CPUFREQ_CONST_LOOPS |
> CPUFREQ_NEED_UPDATE_LIMITS,
> >   	.verify		= amd_pstate_verify,
> > @@ -628,6 +974,16 @@ static struct cpufreq_driver amd_pstate_driver = {
> >   	.attr		= amd_pstate_attr,
> >   };
> >
> > +static struct cpufreq_driver amd_pstate_epp_driver = {
> > +	.flags		= CPUFREQ_CONST_LOOPS,
> > +	.verify		= amd_pstate_epp_verify_policy,
> > +	.setpolicy	= amd_pstate_epp_set_policy,
> > +	.init		= amd_pstate_epp_cpu_init,
> > +	.exit		= amd_pstate_epp_cpu_exit,
> > +	.name		= "amd_pstate_epp",
> > +	.attr		= amd_pstate_epp_attr,
> > +};
> > +
> >   static int __init amd_pstate_init(void)
> >   {
> >   	int ret;
> > @@ -656,7 +1012,8 @@ static int __init amd_pstate_init(void)
> >   	/* capability check */
> >   	if (boot_cpu_has(X86_FEATURE_CPPC)) {
> >   		pr_debug("AMD CPPC MSR based functionality is
> supported\n");
> > -		amd_pstate_driver.adjust_perf = amd_pstate_adjust_perf;
> > +		if (cppc_state == AMD_PSTATE_PASSIVE)
> > +			default_pstate_driver->adjust_perf =
> amd_pstate_adjust_perf;
> >   	} else {
> >   		pr_debug("AMD CPPC shared memory based functionality is
> supported\n");
> >   		static_call_update(amd_pstate_enable, cppc_enable); @@ -
> 667,14
> > +1024,13 @@ static int __init amd_pstate_init(void)
> >   	/* enable amd pstate feature */
> >   	ret = amd_pstate_enable(true);
> >   	if (ret) {
> > -		pr_err("failed to enable amd-pstate with return %d\n", ret);
> > +		pr_err("failed to enable with return %d\n", ret);
> >   		return ret;
> >   	}
> >
> > -	ret = cpufreq_register_driver(&amd_pstate_driver);
> > +	ret = cpufreq_register_driver(default_pstate_driver);
> >   	if (ret)
> > -		pr_err("failed to register amd_pstate_driver with
> return %d\n",
> > -		       ret);
> > +		pr_err("failed to register with return %d\n", ret);
> >
> >   	return ret;
> >   }
> > @@ -696,6 +1052,12 @@ static int __init amd_pstate_param(char *str)
> >   		if (cppc_state == AMD_PSTATE_DISABLE)
> >   			pr_info("driver is explicitly disabled\n");
> >
> > +		if (cppc_state == AMD_PSTATE_ACTIVE)
> > +			default_pstate_driver = &amd_pstate_epp_driver;
> > +
> > +		if (cppc_state == AMD_PSTATE_PASSIVE)
> > +			default_pstate_driver = &amd_pstate_driver;
> > +
> >   		return 0;
> >   	}
> >
> > diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h
> > index dae2ce0f6735..8341a2a2948a 100644
> > --- a/include/linux/amd-pstate.h
> > +++ b/include/linux/amd-pstate.h
> > @@ -47,6 +47,10 @@ struct amd_aperf_mperf {
> >    * @prev: Last Aperf/Mperf/tsc count value read from register
> >    * @freq: current cpu frequency value
> >    * @boost_supported: check whether the Processor or SBIOS supports
> > boost mode
> > + * @epp_policy: Last saved policy used to set energy-performance
> > + preference
> > + * @epp_cached: Cached CPPC energy-performance preference value
> > + * @policy: Cpufreq policy value
> > + * @cppc_cap1_cached Cached MSR_AMD_CPPC_CAP1 register value
> >    *
> >    * The amd_cpudata is key private data for each CPU thread in AMD P-
> State, and
> >    * represents all the attributes and goals that AMD P-State requests at
> runtime.
> > @@ -72,6 +76,12 @@ struct amd_cpudata {
> >
> >   	u64	freq;
> >   	bool	boost_supported;
> > +
> > +	/* EPP feature related attributes*/
> > +	s16	epp_policy;
> > +	s16	epp_cached;
> > +	u32	policy;
> > +	u64	cppc_cap1_cached;
> >   };
> >
> >   /*