[PATCH 00/15] amd-pstate 6.14 cleanups and improvements

[PATCH 00/15] amd-pstate 6.14 cleanups and improvements

[Mario Limonciello]

This series started as work on the behavior around boost numerator that
was changed in the last few kernels to make it more expected.

As part of the process, of these improvements I found various other
optimizations that made a lot of sense in the context of the code.

While I was working on the issues I found it was really helpful to have
ftrace for EPP, so it introduces that as well.

Lastly a bug was reported requesting that amd-pstate default policy be
changed for client systems that don't use other software after bootup
so it includes that change too.

Mario Limonciello (15):
  cpufreq/amd-pstate: Add trace event for EPP perf updates
  cpufreq/amd-pstate: convert mutex use to guard()
  cpufreq/amd-pstate: Drop cached epp_policy variable
  cpufreq/amd-pstate: Use FIELD_PREP and FIELD_GET macros
  cpufreq/amd-pstate: Store the boost numerator as highest perf again
  cpufreq/amd-pstate: Use boost numerator for upper bound of frequencies
  cpufreq/amd-pstate: Only update the cached value in msr_set_epp() on
    success
  cpufreq/amd-pstate: store all values in cpudata struct in khz
  cpufreq/amd-pstate: Change amd_pstate_update_perf() to return an int
  cpufreq/amd-pstate: Move limit updating code
  cpufreq/amd-pstate: Cache EPP value and use that everywhere
  cpufreq/amd-pstate: Always write EPP value when updating perf
  cpufreq/amd-pstate: Check if CPPC request has changed before writing
    to the MSR or shared memory
  cpufreq/amd-pstate: Drop ret variable from
    amd_pstate_set_energy_pref_index()
  cpufreq/amd-pstate: Set different default EPP policy for Epyc and
    Ryzen

 Documentation/admin-guide/pm/amd-pstate.rst |   4 +-
 drivers/cpufreq/amd-pstate-trace.h          |  52 ++-
 drivers/cpufreq/amd-pstate-ut.c             |  12 +-
 drivers/cpufreq/amd-pstate.c                | 395 ++++++++++----------
 drivers/cpufreq/amd-pstate.h                |   2 -
 5 files changed, 244 insertions(+), 221 deletions(-)


base-commit: ab9e5b2eb56412cb8c63b46b935878d29205418e
-- 
2.43.0

[PATCH 01/15] cpufreq/amd-pstate: Add trace event for EPP perf updates

[Mario Limonciello]

In "active" mode the most important thing for debugging whether
an issue is hardware or software based is to look at what was the
last thing written to the CPPC request MSR or shared memory region.

The 'amd_pstate_epp_perf' trace event shows the values being written
for all CPUs.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 drivers/cpufreq/amd-pstate-trace.h | 45 ++++++++++++++++++++++++++++++
 drivers/cpufreq/amd-pstate.c       | 28 +++++++++++++++++++
 2 files changed, 73 insertions(+)

diff --git a/drivers/cpufreq/amd-pstate-trace.h b/drivers/cpufreq/amd-pstate-trace.h
index 35f38ae67fb13..e2221a4b6901c 100644
--- a/drivers/cpufreq/amd-pstate-trace.h
+++ b/drivers/cpufreq/amd-pstate-trace.h
@@ -88,6 +88,51 @@ TRACE_EVENT(amd_pstate_perf,
 		 )
 );
 
+TRACE_EVENT(amd_pstate_epp_perf,
+
+	TP_PROTO(unsigned int cpu_id,
+		 unsigned int highest_perf,
+		 unsigned int epp,
+		 unsigned int min_perf,
+		 unsigned int max_perf,
+		 bool boost
+		 ),
+
+	TP_ARGS(cpu_id,
+		highest_perf,
+		epp,
+		min_perf,
+		max_perf,
+		boost),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, cpu_id)
+		__field(unsigned int, highest_perf)
+		__field(unsigned int, epp)
+		__field(unsigned int, min_perf)
+		__field(unsigned int, max_perf)
+		__field(bool, boost)
+		),
+
+	TP_fast_assign(
+		__entry->cpu_id = cpu_id;
+		__entry->highest_perf = highest_perf;
+		__entry->epp = epp;
+		__entry->min_perf = min_perf;
+		__entry->max_perf = max_perf;
+		__entry->boost = boost;
+		),
+
+	TP_printk("cpu%u: [%u<->%u]/%u, epp=%u, boost=%u",
+		  (unsigned int)__entry->cpu_id,
+		  (unsigned int)__entry->min_perf,
+		  (unsigned int)__entry->max_perf,
+		  (unsigned int)__entry->highest_perf,
+		  (unsigned int)__entry->epp,
+		  (bool)__entry->boost
+		 )
+);
+
 #endif /* _AMD_PSTATE_TRACE_H */
 
 /* This part must be outside protection */
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 66fb7aee95d24..4d1da49d345ec 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -324,6 +324,14 @@ static int amd_pstate_set_energy_pref_index(struct amd_cpudata *cpudata,
 		return -EBUSY;
 	}
 
+	if (trace_amd_pstate_epp_perf_enabled()) {
+		trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf,
+					  epp,
+					  AMD_CPPC_MIN_PERF(cpudata->cppc_req_cached),
+					  AMD_CPPC_MAX_PERF(cpudata->cppc_req_cached),
+					  cpudata->boost_state);
+	}
+
 	ret = amd_pstate_set_epp(cpudata, epp);
 
 	return ret;
@@ -1596,6 +1604,13 @@ static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
 
 	WRITE_ONCE(cpudata->cppc_req_cached, value);
 
+	if (trace_amd_pstate_epp_perf_enabled()) {
+		trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf, epp,
+					  cpudata->min_limit_perf,
+					  cpudata->max_limit_perf,
+					  cpudata->boost_state);
+	}
+
 	amd_pstate_update_perf(cpudata, cpudata->min_limit_perf, 0U,
 			       cpudata->max_limit_perf, false);
 
@@ -1639,6 +1654,13 @@ static void amd_pstate_epp_reenable(struct amd_cpudata *cpudata)
 
 	max_perf = READ_ONCE(cpudata->highest_perf);
 
+	if (trace_amd_pstate_epp_perf_enabled()) {
+		trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf,
+					  cpudata->epp_cached,
+					  AMD_CPPC_MIN_PERF(cpudata->cppc_req_cached),
+					  max_perf, cpudata->boost_state);
+	}
+
 	amd_pstate_update_perf(cpudata, 0, 0, max_perf, false);
 	amd_pstate_set_epp(cpudata, cpudata->epp_cached);
 }
@@ -1667,6 +1689,12 @@ static int amd_pstate_epp_cpu_offline(struct cpufreq_policy *policy)
 
 	mutex_lock(&amd_pstate_limits_lock);
 
+	if (trace_amd_pstate_epp_perf_enabled()) {
+		trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf,
+					  AMD_CPPC_EPP_BALANCE_POWERSAVE,
+					  min_perf, min_perf, cpudata->boost_state);
+	}
+
 	amd_pstate_update_perf(cpudata, min_perf, 0, min_perf, false);
 	amd_pstate_set_epp(cpudata, AMD_CPPC_EPP_BALANCE_POWERSAVE);
 
-- 
2.43.0

RE: [PATCH 01/15] cpufreq/amd-pstate: Add trace event for EPP perf updates

[Yuan, Perry]

[AMD Official Use Only - AMD Internal Distribution Only]

> -----Original Message-----
> From: Limonciello, Mario <Mario.Limonciello@amd.com>
> Sent: Friday, December 6, 2024 6:29 AM
> To: Shenoy, Gautham Ranjal <gautham.shenoy@amd.com>
> Cc: Yuan, Perry <Perry.Yuan@amd.com>; linux-kernel@vger.kernel.org; linux-
> pm@vger.kernel.org; Ugwekar, Dhananjay <Dhananjay.Ugwekar@amd.com>;
> Limonciello, Mario <Mario.Limonciello@amd.com>
> Subject: [PATCH 01/15] cpufreq/amd-pstate: Add trace event for EPP perf updates
>
> In "active" mode the most important thing for debugging whether an issue is
> hardware or software based is to look at what was the last thing written to the CPPC
> request MSR or shared memory region.
>
> The 'amd_pstate_epp_perf' trace event shows the values being written for all CPUs.
>
> Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
> ---
>  drivers/cpufreq/amd-pstate-trace.h | 45 ++++++++++++++++++++++++++++++
>  drivers/cpufreq/amd-pstate.c       | 28 +++++++++++++++++++
>  2 files changed, 73 insertions(+)
>
> diff --git a/drivers/cpufreq/amd-pstate-trace.h b/drivers/cpufreq/amd-pstate-trace.h
> index 35f38ae67fb13..e2221a4b6901c 100644
> --- a/drivers/cpufreq/amd-pstate-trace.h
> +++ b/drivers/cpufreq/amd-pstate-trace.h
> @@ -88,6 +88,51 @@ TRACE_EVENT(amd_pstate_perf,
>                )
>  );
>
> +TRACE_EVENT(amd_pstate_epp_perf,
> +
> +     TP_PROTO(unsigned int cpu_id,
> +              unsigned int highest_perf,
> +              unsigned int epp,
> +              unsigned int min_perf,
> +              unsigned int max_perf,
> +              bool boost
> +              ),
> +
> +     TP_ARGS(cpu_id,
> +             highest_perf,
> +             epp,
> +             min_perf,
> +             max_perf,
> +             boost),
> +
> +     TP_STRUCT__entry(
> +             __field(unsigned int, cpu_id)
> +             __field(unsigned int, highest_perf)
> +             __field(unsigned int, epp)
> +             __field(unsigned int, min_perf)
> +             __field(unsigned int, max_perf)
> +             __field(bool, boost)
> +             ),
> +
> +     TP_fast_assign(
> +             __entry->cpu_id = cpu_id;
> +             __entry->highest_perf = highest_perf;
> +             __entry->epp = epp;
> +             __entry->min_perf = min_perf;
> +             __entry->max_perf = max_perf;
> +             __entry->boost = boost;
> +             ),
> +
> +     TP_printk("cpu%u: [%u<->%u]/%u, epp=%u, boost=%u",
> +               (unsigned int)__entry->cpu_id,
> +               (unsigned int)__entry->min_perf,
> +               (unsigned int)__entry->max_perf,
> +               (unsigned int)__entry->highest_perf,
> +               (unsigned int)__entry->epp,
> +               (bool)__entry->boost
> +              )
> +);
> +
>  #endif /* _AMD_PSTATE_TRACE_H */
>
>  /* This part must be outside protection */ diff --git a/drivers/cpufreq/amd-pstate.c
> b/drivers/cpufreq/amd-pstate.c index 66fb7aee95d24..4d1da49d345ec 100644
> --- a/drivers/cpufreq/amd-pstate.c
> +++ b/drivers/cpufreq/amd-pstate.c
> @@ -324,6 +324,14 @@ static int amd_pstate_set_energy_pref_index(struct
> amd_cpudata *cpudata,
>               return -EBUSY;
>       }
>
> +     if (trace_amd_pstate_epp_perf_enabled()) {
> +             trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf,
> +                                       epp,
> +                                       AMD_CPPC_MIN_PERF(cpudata-
> >cppc_req_cached),
> +                                       AMD_CPPC_MAX_PERF(cpudata-
> >cppc_req_cached),
> +                                       cpudata->boost_state);
> +     }
> +
>       ret = amd_pstate_set_epp(cpudata, epp);
>
>       return ret;
> @@ -1596,6 +1604,13 @@ static int amd_pstate_epp_update_limit(struct
> cpufreq_policy *policy)
>
>       WRITE_ONCE(cpudata->cppc_req_cached, value);
>
> +     if (trace_amd_pstate_epp_perf_enabled()) {
> +             trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf,
> epp,
> +                                       cpudata->min_limit_perf,
> +                                       cpudata->max_limit_perf,
> +                                       cpudata->boost_state);
> +     }
> +
>       amd_pstate_update_perf(cpudata, cpudata->min_limit_perf, 0U,
>                              cpudata->max_limit_perf, false);
>
> @@ -1639,6 +1654,13 @@ static void amd_pstate_epp_reenable(struct
> amd_cpudata *cpudata)
>
>       max_perf = READ_ONCE(cpudata->highest_perf);
>
> +     if (trace_amd_pstate_epp_perf_enabled()) {
> +             trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf,
> +                                       cpudata->epp_cached,
> +                                       AMD_CPPC_MIN_PERF(cpudata-
> >cppc_req_cached),
> +                                       max_perf, cpudata->boost_state);
> +     }
> +
>       amd_pstate_update_perf(cpudata, 0, 0, max_perf, false);
>       amd_pstate_set_epp(cpudata, cpudata->epp_cached);  } @@ -1667,6
> +1689,12 @@ static int amd_pstate_epp_cpu_offline(struct cpufreq_policy *policy)
>
>       mutex_lock(&amd_pstate_limits_lock);
>
> +     if (trace_amd_pstate_epp_perf_enabled()) {
> +             trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf,
> +
> AMD_CPPC_EPP_BALANCE_POWERSAVE,
> +                                       min_perf, min_perf, cpudata->boost_state);
> +     }
> +
>       amd_pstate_update_perf(cpudata, min_perf, 0, min_perf, false);
>       amd_pstate_set_epp(cpudata,
> AMD_CPPC_EPP_BALANCE_POWERSAVE);
>
> --
> 2.43.0

LGTM

Reviewed-by: Perry Yuan <perry.yuan@amd.com>

Re: [PATCH 01/15] cpufreq/amd-pstate: Add trace event for EPP perf updates

[Gautham R. Shenoy]

On Thu, Dec 05, 2024 at 04:28:33PM -0600, Mario Limonciello wrote:
> In "active" mode the most important thing for debugging whether
> an issue is hardware or software based is to look at what was the
> last thing written to the CPPC request MSR or shared memory region.
> 
> The 'amd_pstate_epp_perf' trace event shows the values being written
> for all CPUs.
> 
> Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>

Thank you Mario for adding this. This is useful for correlating the
frequencies requested by the userspace with the min_per/max_perf/epp
values chosen by the hardware.

The patch looks good to me.

Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>

--
Thanks and Regards
gautham.

> ---
>  drivers/cpufreq/amd-pstate-trace.h | 45 ++++++++++++++++++++++++++++++
>  drivers/cpufreq/amd-pstate.c       | 28 +++++++++++++++++++
>  2 files changed, 73 insertions(+)
> 
> diff --git a/drivers/cpufreq/amd-pstate-trace.h b/drivers/cpufreq/amd-pstate-trace.h
> index 35f38ae67fb13..e2221a4b6901c 100644
> --- a/drivers/cpufreq/amd-pstate-trace.h
> +++ b/drivers/cpufreq/amd-pstate-trace.h
> @@ -88,6 +88,51 @@ TRACE_EVENT(amd_pstate_perf,
>  		 )
>  );
>  
> +TRACE_EVENT(amd_pstate_epp_perf,
> +
> +	TP_PROTO(unsigned int cpu_id,
> +		 unsigned int highest_perf,
> +		 unsigned int epp,
> +		 unsigned int min_perf,
> +		 unsigned int max_perf,
> +		 bool boost
> +		 ),
> +
> +	TP_ARGS(cpu_id,
> +		highest_perf,
> +		epp,
> +		min_perf,
> +		max_perf,
> +		boost),
> +
> +	TP_STRUCT__entry(
> +		__field(unsigned int, cpu_id)
> +		__field(unsigned int, highest_perf)
> +		__field(unsigned int, epp)
> +		__field(unsigned int, min_perf)
> +		__field(unsigned int, max_perf)
> +		__field(bool, boost)
> +		),
> +
> +	TP_fast_assign(
> +		__entry->cpu_id = cpu_id;
> +		__entry->highest_perf = highest_perf;
> +		__entry->epp = epp;
> +		__entry->min_perf = min_perf;
> +		__entry->max_perf = max_perf;
> +		__entry->boost = boost;
> +		),
> +
> +	TP_printk("cpu%u: [%u<->%u]/%u, epp=%u, boost=%u",
> +		  (unsigned int)__entry->cpu_id,
> +		  (unsigned int)__entry->min_perf,
> +		  (unsigned int)__entry->max_perf,
> +		  (unsigned int)__entry->highest_perf,
> +		  (unsigned int)__entry->epp,
> +		  (bool)__entry->boost
> +		 )
> +);
> +
>  #endif /* _AMD_PSTATE_TRACE_H */
>  
>  /* This part must be outside protection */
> diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
> index 66fb7aee95d24..4d1da49d345ec 100644
> --- a/drivers/cpufreq/amd-pstate.c
> +++ b/drivers/cpufreq/amd-pstate.c
> @@ -324,6 +324,14 @@ static int amd_pstate_set_energy_pref_index(struct amd_cpudata *cpudata,
>  		return -EBUSY;
>  	}
>  
> +	if (trace_amd_pstate_epp_perf_enabled()) {
> +		trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf,
> +					  epp,
> +					  AMD_CPPC_MIN_PERF(cpudata->cppc_req_cached),
> +					  AMD_CPPC_MAX_PERF(cpudata->cppc_req_cached),
> +					  cpudata->boost_state);
> +	}
> +
>  	ret = amd_pstate_set_epp(cpudata, epp);
>  
>  	return ret;
> @@ -1596,6 +1604,13 @@ static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
>  
>  	WRITE_ONCE(cpudata->cppc_req_cached, value);
>  
> +	if (trace_amd_pstate_epp_perf_enabled()) {
> +		trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf, epp,
> +					  cpudata->min_limit_perf,
> +					  cpudata->max_limit_perf,
> +					  cpudata->boost_state);
> +	}
> +
>  	amd_pstate_update_perf(cpudata, cpudata->min_limit_perf, 0U,
>  			       cpudata->max_limit_perf, false);
>  
> @@ -1639,6 +1654,13 @@ static void amd_pstate_epp_reenable(struct amd_cpudata *cpudata)
>  
>  	max_perf = READ_ONCE(cpudata->highest_perf);
>  
> +	if (trace_amd_pstate_epp_perf_enabled()) {
> +		trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf,
> +					  cpudata->epp_cached,
> +					  AMD_CPPC_MIN_PERF(cpudata->cppc_req_cached),
> +					  max_perf, cpudata->boost_state);
> +	}
> +
>  	amd_pstate_update_perf(cpudata, 0, 0, max_perf, false);
>  	amd_pstate_set_epp(cpudata, cpudata->epp_cached);
>  }
> @@ -1667,6 +1689,12 @@ static int amd_pstate_epp_cpu_offline(struct cpufreq_policy *policy)
>  
>  	mutex_lock(&amd_pstate_limits_lock);
>  
> +	if (trace_amd_pstate_epp_perf_enabled()) {
> +		trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf,
> +					  AMD_CPPC_EPP_BALANCE_POWERSAVE,
> +					  min_perf, min_perf, cpudata->boost_state);
> +	}
> +
>  	amd_pstate_update_perf(cpudata, min_perf, 0, min_perf, false);
>  	amd_pstate_set_epp(cpudata, AMD_CPPC_EPP_BALANCE_POWERSAVE);
>  
> -- 
> 2.43.0
> 

[PATCH 02/15] cpufreq/amd-pstate: convert mutex use to guard()

[Mario Limonciello]

Using scoped guard declaration will unlock mutexes automatically.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 drivers/cpufreq/amd-pstate.c | 32 ++++++++++++--------------------
 1 file changed, 12 insertions(+), 20 deletions(-)

diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 4d1da49d345ec..7eb013585df51 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -752,12 +752,12 @@ static int amd_pstate_set_boost(struct cpufreq_policy *policy, int state)
 		pr_err("Boost mode is not supported by this processor or SBIOS\n");
 		return -EOPNOTSUPP;
 	}
-	mutex_lock(&amd_pstate_driver_lock);
+	guard(mutex)(&amd_pstate_driver_lock);
+
 	ret = amd_pstate_cpu_boost_update(policy, state);
 	WRITE_ONCE(cpudata->boost_state, !ret ? state : false);
 	policy->boost_enabled = !ret ? state : false;
 	refresh_frequency_limits(policy);
-	mutex_unlock(&amd_pstate_driver_lock);
 
 	return ret;
 }
@@ -848,7 +848,8 @@ static void amd_pstate_update_limits(unsigned int cpu)
 	if (!amd_pstate_prefcore)
 		return;
 
-	mutex_lock(&amd_pstate_driver_lock);
+	guard(mutex)(&amd_pstate_driver_lock);
+
 	ret = amd_get_highest_perf(cpu, &cur_high);
 	if (ret)
 		goto free_cpufreq_put;
@@ -868,7 +869,6 @@ static void amd_pstate_update_limits(unsigned int cpu)
 	if (!highest_perf_changed)
 		cpufreq_update_policy(cpu);
 
-	mutex_unlock(&amd_pstate_driver_lock);
 }
 
 /*
@@ -1201,11 +1201,11 @@ static ssize_t store_energy_performance_preference(
 	if (ret < 0)
 		return -EINVAL;
 
-	mutex_lock(&amd_pstate_limits_lock);
+	guard(mutex)(&amd_pstate_limits_lock);
+
 	ret = amd_pstate_set_energy_pref_index(cpudata, ret);
-	mutex_unlock(&amd_pstate_limits_lock);
 
-	return ret ?: count;
+	return ret ? ret : count;
 }
 
 static ssize_t show_energy_performance_preference(
@@ -1369,13 +1369,10 @@ EXPORT_SYMBOL_GPL(amd_pstate_update_status);
 static ssize_t status_show(struct device *dev,
 			   struct device_attribute *attr, char *buf)
 {
-	ssize_t ret;
 
-	mutex_lock(&amd_pstate_driver_lock);
-	ret = amd_pstate_show_status(buf);
-	mutex_unlock(&amd_pstate_driver_lock);
+	guard(mutex)(&amd_pstate_driver_lock);
 
-	return ret;
+	return amd_pstate_show_status(buf);
 }
 
 static ssize_t status_store(struct device *a, struct device_attribute *b,
@@ -1384,9 +1381,8 @@ static ssize_t status_store(struct device *a, struct device_attribute *b,
 	char *p = memchr(buf, '\n', count);
 	int ret;
 
-	mutex_lock(&amd_pstate_driver_lock);
+	guard(mutex)(&amd_pstate_driver_lock);
 	ret = amd_pstate_update_status(buf, p ? p - buf : count);
-	mutex_unlock(&amd_pstate_driver_lock);
 
 	return ret < 0 ? ret : count;
 }
@@ -1687,7 +1683,7 @@ static int amd_pstate_epp_cpu_offline(struct cpufreq_policy *policy)
 
 	min_perf = READ_ONCE(cpudata->lowest_perf);
 
-	mutex_lock(&amd_pstate_limits_lock);
+	guard(mutex)(&amd_pstate_limits_lock);
 
 	if (trace_amd_pstate_epp_perf_enabled()) {
 		trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf,
@@ -1698,8 +1694,6 @@ static int amd_pstate_epp_cpu_offline(struct cpufreq_policy *policy)
 	amd_pstate_update_perf(cpudata, min_perf, 0, min_perf, false);
 	amd_pstate_set_epp(cpudata, AMD_CPPC_EPP_BALANCE_POWERSAVE);
 
-	mutex_unlock(&amd_pstate_limits_lock);
-
 	return 0;
 }
 
@@ -1728,13 +1722,11 @@ static int amd_pstate_epp_resume(struct cpufreq_policy *policy)
 	struct amd_cpudata *cpudata = policy->driver_data;
 
 	if (cpudata->suspended) {
-		mutex_lock(&amd_pstate_limits_lock);
+		guard(mutex)(&amd_pstate_limits_lock);
 
 		/* enable amd pstate from suspend state*/
 		amd_pstate_epp_reenable(cpudata);
 
-		mutex_unlock(&amd_pstate_limits_lock);
-
 		cpudata->suspended = false;
 	}
 
-- 
2.43.0

Re: [PATCH 02/15] cpufreq/amd-pstate: convert mutex use to guard()

[Gautham R. Shenoy]

On Thu, Dec 05, 2024 at 04:28:34PM -0600, Mario Limonciello wrote:
> Using scoped guard declaration will unlock mutexes automatically.
> 
> Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>


Looks good to me.

Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>

--
Thanks and Regards
gautham.
> ---
>  drivers/cpufreq/amd-pstate.c | 32 ++++++++++++--------------------
>  1 file changed, 12 insertions(+), 20 deletions(-)
> 
> diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
> index 4d1da49d345ec..7eb013585df51 100644
> --- a/drivers/cpufreq/amd-pstate.c
> +++ b/drivers/cpufreq/amd-pstate.c
> @@ -752,12 +752,12 @@ static int amd_pstate_set_boost(struct cpufreq_policy *policy, int state)
>  		pr_err("Boost mode is not supported by this processor or SBIOS\n");
>  		return -EOPNOTSUPP;
>  	}
> -	mutex_lock(&amd_pstate_driver_lock);
> +	guard(mutex)(&amd_pstate_driver_lock);
> +
>  	ret = amd_pstate_cpu_boost_update(policy, state);
>  	WRITE_ONCE(cpudata->boost_state, !ret ? state : false);
>  	policy->boost_enabled = !ret ? state : false;
>  	refresh_frequency_limits(policy);
> -	mutex_unlock(&amd_pstate_driver_lock);
>  
>  	return ret;
>  }
> @@ -848,7 +848,8 @@ static void amd_pstate_update_limits(unsigned int cpu)
>  	if (!amd_pstate_prefcore)
>  		return;
>  
> -	mutex_lock(&amd_pstate_driver_lock);
> +	guard(mutex)(&amd_pstate_driver_lock);
> +
>  	ret = amd_get_highest_perf(cpu, &cur_high);
>  	if (ret)
>  		goto free_cpufreq_put;
> @@ -868,7 +869,6 @@ static void amd_pstate_update_limits(unsigned int cpu)
>  	if (!highest_perf_changed)
>  		cpufreq_update_policy(cpu);
>  
> -	mutex_unlock(&amd_pstate_driver_lock);
>  }
>  
>  /*
> @@ -1201,11 +1201,11 @@ static ssize_t store_energy_performance_preference(
>  	if (ret < 0)
>  		return -EINVAL;
>  
> -	mutex_lock(&amd_pstate_limits_lock);
> +	guard(mutex)(&amd_pstate_limits_lock);
> +
>  	ret = amd_pstate_set_energy_pref_index(cpudata, ret);
> -	mutex_unlock(&amd_pstate_limits_lock);
>  
> -	return ret ?: count;
> +	return ret ? ret : count;
>  }
>  
>  static ssize_t show_energy_performance_preference(
> @@ -1369,13 +1369,10 @@ EXPORT_SYMBOL_GPL(amd_pstate_update_status);
>  static ssize_t status_show(struct device *dev,
>  			   struct device_attribute *attr, char *buf)
>  {
> -	ssize_t ret;
>  
> -	mutex_lock(&amd_pstate_driver_lock);
> -	ret = amd_pstate_show_status(buf);
> -	mutex_unlock(&amd_pstate_driver_lock);
> +	guard(mutex)(&amd_pstate_driver_lock);
>  
> -	return ret;
> +	return amd_pstate_show_status(buf);
>  }
>  
>  static ssize_t status_store(struct device *a, struct device_attribute *b,
> @@ -1384,9 +1381,8 @@ static ssize_t status_store(struct device *a, struct device_attribute *b,
>  	char *p = memchr(buf, '\n', count);
>  	int ret;
>  
> -	mutex_lock(&amd_pstate_driver_lock);
> +	guard(mutex)(&amd_pstate_driver_lock);
>  	ret = amd_pstate_update_status(buf, p ? p - buf : count);
> -	mutex_unlock(&amd_pstate_driver_lock);
>  
>  	return ret < 0 ? ret : count;
>  }
> @@ -1687,7 +1683,7 @@ static int amd_pstate_epp_cpu_offline(struct cpufreq_policy *policy)
>  
>  	min_perf = READ_ONCE(cpudata->lowest_perf);
>  
> -	mutex_lock(&amd_pstate_limits_lock);
> +	guard(mutex)(&amd_pstate_limits_lock);
>  
>  	if (trace_amd_pstate_epp_perf_enabled()) {
>  		trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf,
> @@ -1698,8 +1694,6 @@ static int amd_pstate_epp_cpu_offline(struct cpufreq_policy *policy)
>  	amd_pstate_update_perf(cpudata, min_perf, 0, min_perf, false);
>  	amd_pstate_set_epp(cpudata, AMD_CPPC_EPP_BALANCE_POWERSAVE);
>  
> -	mutex_unlock(&amd_pstate_limits_lock);
> -
>  	return 0;
>  }
>  
> @@ -1728,13 +1722,11 @@ static int amd_pstate_epp_resume(struct cpufreq_policy *policy)
>  	struct amd_cpudata *cpudata = policy->driver_data;
>  
>  	if (cpudata->suspended) {
> -		mutex_lock(&amd_pstate_limits_lock);
> +		guard(mutex)(&amd_pstate_limits_lock);
>  
>  		/* enable amd pstate from suspend state*/
>  		amd_pstate_epp_reenable(cpudata);
>  
> -		mutex_unlock(&amd_pstate_limits_lock);
> -
>  		cpudata->suspended = false;
>  	}
>  
> -- 
> 2.43.0
> 

[PATCH 03/15] cpufreq/amd-pstate: Drop cached epp_policy variable

[Mario Limonciello]

epp_policy is not used by any of the current code and there
is no need to cache it.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 drivers/cpufreq/amd-pstate.c | 3 ---
 drivers/cpufreq/amd-pstate.h | 2 --
 2 files changed, 5 deletions(-)

diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 7eb013585df51..22e212ca514c5 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -1476,7 +1476,6 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 		return -ENOMEM;
 
 	cpudata->cpu = policy->cpu;
-	cpudata->epp_policy = 0;
 
 	ret = amd_pstate_init_perf(cpudata);
 	if (ret)
@@ -1583,8 +1582,6 @@ static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
 	value &= ~AMD_CPPC_DES_PERF(~0L);
 	value |= AMD_CPPC_DES_PERF(0);
 
-	cpudata->epp_policy = cpudata->policy;
-
 	/* Get BIOS pre-defined epp value */
 	epp = amd_pstate_get_epp(cpudata, value);
 	if (epp < 0) {
diff --git a/drivers/cpufreq/amd-pstate.h b/drivers/cpufreq/amd-pstate.h
index cd573bc6b6db8..7765c82f975c6 100644
--- a/drivers/cpufreq/amd-pstate.h
+++ b/drivers/cpufreq/amd-pstate.h
@@ -57,7 +57,6 @@ struct amd_aperf_mperf {
  * @hw_prefcore: check whether HW supports preferred core featue.
  * 		  Only when hw_prefcore and early prefcore param are true,
  * 		  AMD P-State driver supports preferred core featue.
- * @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
@@ -94,7 +93,6 @@ struct amd_cpudata {
 	bool	hw_prefcore;
 
 	/* EPP feature related attributes*/
-	s16	epp_policy;
 	s16	epp_cached;
 	u32	policy;
 	u64	cppc_cap1_cached;
-- 
2.43.0

Re: [PATCH 03/15] cpufreq/amd-pstate: Drop cached epp_policy variable

[Gautham R. Shenoy]

On Thu, Dec 05, 2024 at 04:28:35PM -0600, Mario Limonciello wrote:
> epp_policy is not used by any of the current code and there
> is no need to cache it.
> 
> Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>

Looks good to me.

Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
--
Thanks and Regards
gautham.


> ---
>  drivers/cpufreq/amd-pstate.c | 3 ---
>  drivers/cpufreq/amd-pstate.h | 2 --
>  2 files changed, 5 deletions(-)
> 
> diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
> index 7eb013585df51..22e212ca514c5 100644
> --- a/drivers/cpufreq/amd-pstate.c
> +++ b/drivers/cpufreq/amd-pstate.c
> @@ -1476,7 +1476,6 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
>  		return -ENOMEM;
>  
>  	cpudata->cpu = policy->cpu;
> -	cpudata->epp_policy = 0;
>  
>  	ret = amd_pstate_init_perf(cpudata);
>  	if (ret)
> @@ -1583,8 +1582,6 @@ static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
>  	value &= ~AMD_CPPC_DES_PERF(~0L);
>  	value |= AMD_CPPC_DES_PERF(0);
>  
> -	cpudata->epp_policy = cpudata->policy;
> -
>  	/* Get BIOS pre-defined epp value */
>  	epp = amd_pstate_get_epp(cpudata, value);
>  	if (epp < 0) {
> diff --git a/drivers/cpufreq/amd-pstate.h b/drivers/cpufreq/amd-pstate.h
> index cd573bc6b6db8..7765c82f975c6 100644
> --- a/drivers/cpufreq/amd-pstate.h
> +++ b/drivers/cpufreq/amd-pstate.h
> @@ -57,7 +57,6 @@ struct amd_aperf_mperf {
>   * @hw_prefcore: check whether HW supports preferred core featue.
>   * 		  Only when hw_prefcore and early prefcore param are true,
>   * 		  AMD P-State driver supports preferred core featue.
> - * @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
> @@ -94,7 +93,6 @@ struct amd_cpudata {
>  	bool	hw_prefcore;
>  
>  	/* EPP feature related attributes*/
> -	s16	epp_policy;
>  	s16	epp_cached;
>  	u32	policy;
>  	u64	cppc_cap1_cached;
> -- 
> 2.43.0
> 

[PATCH 04/15] cpufreq/amd-pstate: Use FIELD_PREP and FIELD_GET macros

[Mario Limonciello]

The FIELD_PREP and FIELD_GET macros improve readability and help
to avoid shifting bugs.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 drivers/cpufreq/amd-pstate.c | 45 ++++++++++++++++--------------------
 1 file changed, 20 insertions(+), 25 deletions(-)

diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 22e212ca514c5..dbe014f3c2beb 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -22,6 +22,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/bitfield.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -88,6 +89,11 @@ static bool cppc_enabled;
 static bool amd_pstate_prefcore = true;
 static struct quirk_entry *quirks;
 
+#define AMD_PSTATE_MAX_PERF_MASK		GENMASK(7, 0)
+#define AMD_PSTATE_MIN_PERF_MASK		GENMASK(15, 8)
+#define AMD_PSTATE_DES_PERF_MASK		GENMASK(23, 16)
+#define AMD_PSTATE_EPP_PERF_MASK		GENMASK(31, 24)
+
 /*
  * AMD Energy Preference Performance (EPP)
  * The EPP is used in the CCLK DPM controller to drive
@@ -182,7 +188,6 @@ static DEFINE_MUTEX(amd_pstate_driver_lock);
 
 static s16 msr_get_epp(struct amd_cpudata *cpudata, u64 cppc_req_cached)
 {
-	u64 epp;
 	int ret;
 
 	if (!cppc_req_cached) {
@@ -192,9 +197,8 @@ static s16 msr_get_epp(struct amd_cpudata *cpudata, u64 cppc_req_cached)
 			return ret;
 		}
 	}
-	epp = (cppc_req_cached >> 24) & 0xFF;
 
-	return (s16)epp;
+	return FIELD_GET(AMD_PSTATE_EPP_PERF_MASK, cppc_req_cached);
 }
 
 DEFINE_STATIC_CALL(amd_pstate_get_epp, msr_get_epp);
@@ -269,12 +273,11 @@ static inline void amd_pstate_update_perf(struct amd_cpudata *cpudata,
 
 static int msr_set_epp(struct amd_cpudata *cpudata, u32 epp)
 {
-	int ret;
-
 	u64 value = READ_ONCE(cpudata->cppc_req_cached);
+	int ret;
 
-	value &= ~GENMASK_ULL(31, 24);
-	value |= (u64)epp << 24;
+	value &= ~AMD_PSTATE_EPP_PERF_MASK;
+	value |= FIELD_PREP(AMD_PSTATE_EPP_PERF_MASK, epp);
 	WRITE_ONCE(cpudata->cppc_req_cached, value);
 
 	ret = wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value);
@@ -533,18 +536,15 @@ static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf,
 		des_perf = 0;
 	}
 
-	value &= ~AMD_CPPC_MIN_PERF(~0L);
-	value |= AMD_CPPC_MIN_PERF(min_perf);
-
-	value &= ~AMD_CPPC_DES_PERF(~0L);
-	value |= AMD_CPPC_DES_PERF(des_perf);
-
 	/* limit the max perf when core performance boost feature is disabled */
 	if (!cpudata->boost_supported)
 		max_perf = min_t(unsigned long, nominal_perf, max_perf);
 
-	value &= ~AMD_CPPC_MAX_PERF(~0L);
-	value |= AMD_CPPC_MAX_PERF(max_perf);
+	value &= ~(AMD_PSTATE_MAX_PERF_MASK | AMD_PSTATE_MIN_PERF_MASK |
+		   AMD_PSTATE_DES_PERF_MASK);
+	value |= FIELD_PREP(AMD_PSTATE_MAX_PERF_MASK, max_perf);
+	value |= FIELD_PREP(AMD_PSTATE_DES_PERF_MASK, des_perf);
+	value |= FIELD_PREP(AMD_PSTATE_MIN_PERF_MASK, min_perf);
 
 	if (trace_amd_pstate_perf_enabled() && amd_pstate_sample(cpudata)) {
 		trace_amd_pstate_perf(min_perf, des_perf, max_perf, cpudata->freq,
@@ -1571,16 +1571,11 @@ static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
 	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
 		min_perf = min(cpudata->nominal_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);
+	value &= ~(AMD_PSTATE_MAX_PERF_MASK | AMD_PSTATE_MIN_PERF_MASK |
+		   AMD_PSTATE_DES_PERF_MASK);
+	value |= FIELD_PREP(AMD_PSTATE_MAX_PERF_MASK, max_perf);
+	value |= FIELD_PREP(AMD_PSTATE_DES_PERF_MASK, 0);
+	value |= FIELD_PREP(AMD_PSTATE_MIN_PERF_MASK, min_perf);
 
 	/* Get BIOS pre-defined epp value */
 	epp = amd_pstate_get_epp(cpudata, value);
-- 
2.43.0

Re: [PATCH 04/15] cpufreq/amd-pstate: Use FIELD_PREP and FIELD_GET macros

[Gautham R. Shenoy]

On Thu, Dec 05, 2024 at 04:28:36PM -0600, Mario Limonciello wrote:
> The FIELD_PREP and FIELD_GET macros improve readability and help
> to avoid shifting bugs.

Indeed.

The code looks better with this.

Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
--
Thanks and Regards
gautham.

> 
> Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
> ---
>  drivers/cpufreq/amd-pstate.c | 45 ++++++++++++++++--------------------
>  1 file changed, 20 insertions(+), 25 deletions(-)
> 
> diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
> index 22e212ca514c5..dbe014f3c2beb 100644
> --- a/drivers/cpufreq/amd-pstate.c
> +++ b/drivers/cpufreq/amd-pstate.c
> @@ -22,6 +22,7 @@
>  
>  #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
>  
> +#include <linux/bitfield.h>
>  #include <linux/kernel.h>
>  #include <linux/module.h>
>  #include <linux/init.h>
> @@ -88,6 +89,11 @@ static bool cppc_enabled;
>  static bool amd_pstate_prefcore = true;
>  static struct quirk_entry *quirks;
>  
> +#define AMD_PSTATE_MAX_PERF_MASK		GENMASK(7, 0)
> +#define AMD_PSTATE_MIN_PERF_MASK		GENMASK(15, 8)
> +#define AMD_PSTATE_DES_PERF_MASK		GENMASK(23, 16)
> +#define AMD_PSTATE_EPP_PERF_MASK		GENMASK(31, 24)
> +
>  /*
>   * AMD Energy Preference Performance (EPP)
>   * The EPP is used in the CCLK DPM controller to drive
> @@ -182,7 +188,6 @@ static DEFINE_MUTEX(amd_pstate_driver_lock);
>  
>  static s16 msr_get_epp(struct amd_cpudata *cpudata, u64 cppc_req_cached)
>  {
> -	u64 epp;
>  	int ret;
>  
>  	if (!cppc_req_cached) {
> @@ -192,9 +197,8 @@ static s16 msr_get_epp(struct amd_cpudata *cpudata, u64 cppc_req_cached)
>  			return ret;
>  		}
>  	}
> -	epp = (cppc_req_cached >> 24) & 0xFF;
>  
> -	return (s16)epp;
> +	return FIELD_GET(AMD_PSTATE_EPP_PERF_MASK, cppc_req_cached);
>  }
>  
>  DEFINE_STATIC_CALL(amd_pstate_get_epp, msr_get_epp);
> @@ -269,12 +273,11 @@ static inline void amd_pstate_update_perf(struct amd_cpudata *cpudata,
>  
>  static int msr_set_epp(struct amd_cpudata *cpudata, u32 epp)
>  {
> -	int ret;
> -
>  	u64 value = READ_ONCE(cpudata->cppc_req_cached);
> +	int ret;
>  
> -	value &= ~GENMASK_ULL(31, 24);
> -	value |= (u64)epp << 24;
> +	value &= ~AMD_PSTATE_EPP_PERF_MASK;
> +	value |= FIELD_PREP(AMD_PSTATE_EPP_PERF_MASK, epp);
>  	WRITE_ONCE(cpudata->cppc_req_cached, value);
>  
>  	ret = wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value);
> @@ -533,18 +536,15 @@ static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf,
>  		des_perf = 0;
>  	}
>  
> -	value &= ~AMD_CPPC_MIN_PERF(~0L);
> -	value |= AMD_CPPC_MIN_PERF(min_perf);
> -
> -	value &= ~AMD_CPPC_DES_PERF(~0L);
> -	value |= AMD_CPPC_DES_PERF(des_perf);
> -
>  	/* limit the max perf when core performance boost feature is disabled */
>  	if (!cpudata->boost_supported)
>  		max_perf = min_t(unsigned long, nominal_perf, max_perf);
>  
> -	value &= ~AMD_CPPC_MAX_PERF(~0L);
> -	value |= AMD_CPPC_MAX_PERF(max_perf);
> +	value &= ~(AMD_PSTATE_MAX_PERF_MASK | AMD_PSTATE_MIN_PERF_MASK |
> +		   AMD_PSTATE_DES_PERF_MASK);
> +	value |= FIELD_PREP(AMD_PSTATE_MAX_PERF_MASK, max_perf);
> +	value |= FIELD_PREP(AMD_PSTATE_DES_PERF_MASK, des_perf);
> +	value |= FIELD_PREP(AMD_PSTATE_MIN_PERF_MASK, min_perf);
>  
>  	if (trace_amd_pstate_perf_enabled() && amd_pstate_sample(cpudata)) {
>  		trace_amd_pstate_perf(min_perf, des_perf, max_perf, cpudata->freq,
> @@ -1571,16 +1571,11 @@ static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
>  	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
>  		min_perf = min(cpudata->nominal_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);
> +	value &= ~(AMD_PSTATE_MAX_PERF_MASK | AMD_PSTATE_MIN_PERF_MASK |
> +		   AMD_PSTATE_DES_PERF_MASK);
> +	value |= FIELD_PREP(AMD_PSTATE_MAX_PERF_MASK, max_perf);
> +	value |= FIELD_PREP(AMD_PSTATE_DES_PERF_MASK, 0);
> +	value |= FIELD_PREP(AMD_PSTATE_MIN_PERF_MASK, min_perf);
>  
>  	/* Get BIOS pre-defined epp value */
>  	epp = amd_pstate_get_epp(cpudata, value);
> -- 
> 2.43.0
> 

[PATCH 05/15] cpufreq/amd-pstate: Store the boost numerator as highest perf again

[Mario Limonciello]

commit ad4caad58d91d ("cpufreq: amd-pstate: Merge
amd_pstate_highest_perf_set() into amd_get_boost_ratio_numerator()")
changed the semantics for highest perf and commit 18d9b52271213
("cpufreq/amd-pstate: Use nominal perf for limits when boost is disabled")
worked around those semantic changes.

This however is a confusing result and furthermore makes it awkward to
change frequency limits and boost due to the scaling differences. Restore
the boost numerator to highest perf again.

Suggested-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com>
Fixes: ad4caad58d91 ("cpufreq: amd-pstate: Merge amd_pstate_highest_perf_set() into amd_get_boost_ratio_numerator()")
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 Documentation/admin-guide/pm/amd-pstate.rst |  4 +---
 drivers/cpufreq/amd-pstate.c                | 25 ++++++++++++---------
 2 files changed, 16 insertions(+), 13 deletions(-)

diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst
index 210a808b74ec2..412423c54f258 100644
--- a/Documentation/admin-guide/pm/amd-pstate.rst
+++ b/Documentation/admin-guide/pm/amd-pstate.rst
@@ -251,9 +251,7 @@ performance supported in `AMD CPPC Performance Capability <perf_cap_>`_).
 In some ASICs, the highest CPPC performance is not the one in the ``_CPC``
 table, so we need to expose it to sysfs. If boost is not active, but
 still supported, this maximum frequency will be larger than the one in
-``cpuinfo``. On systems that support preferred core, the driver will have
-different values for some cores than others and this will reflect the values
-advertised by the platform at bootup.
+``cpuinfo``.
 This attribute is read-only.
 
 ``amd_pstate_lowest_nonlinear_freq``
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index dbe014f3c2beb..738f63d70546f 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -408,15 +408,19 @@ static inline int amd_pstate_cppc_enable(bool enable)
 
 static int msr_init_perf(struct amd_cpudata *cpudata)
 {
-	u64 cap1;
+	u64 cap1, numerator;
 
 	int ret = rdmsrl_safe_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1,
 				     &cap1);
 	if (ret)
 		return ret;
 
-	WRITE_ONCE(cpudata->highest_perf, AMD_CPPC_HIGHEST_PERF(cap1));
-	WRITE_ONCE(cpudata->max_limit_perf, AMD_CPPC_HIGHEST_PERF(cap1));
+	ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator);
+	if (ret)
+		return ret;
+
+	WRITE_ONCE(cpudata->highest_perf, numerator);
+	WRITE_ONCE(cpudata->max_limit_perf, numerator);
 	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));
@@ -428,13 +432,18 @@ static int msr_init_perf(struct amd_cpudata *cpudata)
 static int shmem_init_perf(struct amd_cpudata *cpudata)
 {
 	struct cppc_perf_caps cppc_perf;
+	u64 numerator;
 
 	int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf);
 	if (ret)
 		return ret;
 
-	WRITE_ONCE(cpudata->highest_perf, cppc_perf.highest_perf);
-	WRITE_ONCE(cpudata->max_limit_perf, cppc_perf.highest_perf);
+	ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator);
+	if (ret)
+		return ret;
+
+	WRITE_ONCE(cpudata->highest_perf, numerator);
+	WRITE_ONCE(cpudata->max_limit_perf, numerator);
 	WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf);
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf,
 		   cppc_perf.lowest_nonlinear_perf);
@@ -920,7 +929,6 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata)
 {
 	int ret;
 	u32 min_freq, max_freq;
-	u64 numerator;
 	u32 nominal_perf, nominal_freq;
 	u32 lowest_nonlinear_perf, lowest_nonlinear_freq;
 	u32 boost_ratio, lowest_nonlinear_ratio;
@@ -942,10 +950,7 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata)
 
 	nominal_perf = READ_ONCE(cpudata->nominal_perf);
 
-	ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator);
-	if (ret)
-		return ret;
-	boost_ratio = div_u64(numerator << SCHED_CAPACITY_SHIFT, nominal_perf);
+	boost_ratio = div_u64(cpudata->highest_perf << SCHED_CAPACITY_SHIFT, nominal_perf);
 	max_freq = (nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT) * 1000;
 
 	lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf);
-- 
2.43.0

Re: [PATCH 05/15] cpufreq/amd-pstate: Store the boost numerator as highest perf again

[Gautham R. Shenoy]

On Thu, Dec 05, 2024 at 04:28:37PM -0600, Mario Limonciello wrote:
> commit ad4caad58d91d ("cpufreq: amd-pstate: Merge
> amd_pstate_highest_perf_set() into amd_get_boost_ratio_numerator()")
> changed the semantics for highest perf and commit 18d9b52271213
> ("cpufreq/amd-pstate: Use nominal perf for limits when boost is disabled")
> worked around those semantic changes.
> 
> This however is a confusing result and furthermore makes it awkward to
> change frequency limits and boost due to the scaling differences. Restore
> the boost numerator to highest perf again.

The patch looks good to me.

Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>

--
Thanks and Regards
gautham.


> 
> Suggested-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com>
> Fixes: ad4caad58d91 ("cpufreq: amd-pstate: Merge amd_pstate_highest_perf_set() into amd_get_boost_ratio_numerator()")
> Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
> ---
>  Documentation/admin-guide/pm/amd-pstate.rst |  4 +---
>  drivers/cpufreq/amd-pstate.c                | 25 ++++++++++++---------
>  2 files changed, 16 insertions(+), 13 deletions(-)
> 
> diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst
> index 210a808b74ec2..412423c54f258 100644
> --- a/Documentation/admin-guide/pm/amd-pstate.rst
> +++ b/Documentation/admin-guide/pm/amd-pstate.rst
> @@ -251,9 +251,7 @@ performance supported in `AMD CPPC Performance Capability <perf_cap_>`_).
>  In some ASICs, the highest CPPC performance is not the one in the ``_CPC``
>  table, so we need to expose it to sysfs. If boost is not active, but
>  still supported, this maximum frequency will be larger than the one in
> -``cpuinfo``. On systems that support preferred core, the driver will have
> -different values for some cores than others and this will reflect the values
> -advertised by the platform at bootup.
> +``cpuinfo``.
>  This attribute is read-only.
>  
>  ``amd_pstate_lowest_nonlinear_freq``
> diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
> index dbe014f3c2beb..738f63d70546f 100644
> --- a/drivers/cpufreq/amd-pstate.c
> +++ b/drivers/cpufreq/amd-pstate.c
> @@ -408,15 +408,19 @@ static inline int amd_pstate_cppc_enable(bool enable)
>  
>  static int msr_init_perf(struct amd_cpudata *cpudata)
>  {
> -	u64 cap1;
> +	u64 cap1, numerator;
>  
>  	int ret = rdmsrl_safe_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1,
>  				     &cap1);
>  	if (ret)
>  		return ret;
>  
> -	WRITE_ONCE(cpudata->highest_perf, AMD_CPPC_HIGHEST_PERF(cap1));
> -	WRITE_ONCE(cpudata->max_limit_perf, AMD_CPPC_HIGHEST_PERF(cap1));
> +	ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator);
> +	if (ret)
> +		return ret;
> +
> +	WRITE_ONCE(cpudata->highest_perf, numerator);
> +	WRITE_ONCE(cpudata->max_limit_perf, numerator);
>  	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));
> @@ -428,13 +432,18 @@ static int msr_init_perf(struct amd_cpudata *cpudata)
>  static int shmem_init_perf(struct amd_cpudata *cpudata)
>  {
>  	struct cppc_perf_caps cppc_perf;
> +	u64 numerator;
>  
>  	int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf);
>  	if (ret)
>  		return ret;
>  
> -	WRITE_ONCE(cpudata->highest_perf, cppc_perf.highest_perf);
> -	WRITE_ONCE(cpudata->max_limit_perf, cppc_perf.highest_perf);
> +	ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator);
> +	if (ret)
> +		return ret;
> +
> +	WRITE_ONCE(cpudata->highest_perf, numerator);
> +	WRITE_ONCE(cpudata->max_limit_perf, numerator);
>  	WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf);
>  	WRITE_ONCE(cpudata->lowest_nonlinear_perf,
>  		   cppc_perf.lowest_nonlinear_perf);
> @@ -920,7 +929,6 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata)
>  {
>  	int ret;
>  	u32 min_freq, max_freq;
> -	u64 numerator;
>  	u32 nominal_perf, nominal_freq;
>  	u32 lowest_nonlinear_perf, lowest_nonlinear_freq;
>  	u32 boost_ratio, lowest_nonlinear_ratio;
> @@ -942,10 +950,7 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata)
>  
>  	nominal_perf = READ_ONCE(cpudata->nominal_perf);
>  
> -	ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator);
> -	if (ret)
> -		return ret;
> -	boost_ratio = div_u64(numerator << SCHED_CAPACITY_SHIFT, nominal_perf);
> +	boost_ratio = div_u64(cpudata->highest_perf << SCHED_CAPACITY_SHIFT, nominal_perf);
>  	max_freq = (nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT) * 1000;
>  
>  	lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf);
> -- 
> 2.43.0
> 

[PATCH 06/15] cpufreq/amd-pstate: Use boost numerator for upper bound of frequencies

[Mario Limonciello]

commit 18d9b5227121 ("cpufreq/amd-pstate: Use nominal perf for limits
when boost is disabled") introduced different semantics for min/max limits
based upon whether the user turned off boost from sysfs.

This however is not necessary when the highest perf value is the boost
numerator.

Suggested-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com>
Fixes: 18d9b5227121 ("cpufreq/amd-pstate: Use nominal perf for limits when boost is disabled")
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 drivers/cpufreq/amd-pstate.c | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 738f63d70546f..14bd6faa3d730 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -601,16 +601,13 @@ static int amd_pstate_verify(struct cpufreq_policy_data *policy_data)
 
 static int amd_pstate_update_min_max_limit(struct cpufreq_policy *policy)
 {
-	u32 max_limit_perf, min_limit_perf, lowest_perf, max_perf;
+	u32 max_limit_perf, min_limit_perf, lowest_perf, max_perf, max_freq;
 	struct amd_cpudata *cpudata = policy->driver_data;
 
-	if (cpudata->boost_supported && !policy->boost_enabled)
-		max_perf = READ_ONCE(cpudata->nominal_perf);
-	else
-		max_perf = READ_ONCE(cpudata->highest_perf);
-
-	max_limit_perf = div_u64(policy->max * max_perf, policy->cpuinfo.max_freq);
-	min_limit_perf = div_u64(policy->min * max_perf, policy->cpuinfo.max_freq);
+	max_perf = READ_ONCE(cpudata->highest_perf);
+	max_freq = READ_ONCE(cpudata->max_freq);
+	max_limit_perf = div_u64(policy->max * max_perf, max_freq);
+	min_limit_perf = div_u64(policy->min * max_perf, max_freq);
 
 	lowest_perf = READ_ONCE(cpudata->lowest_perf);
 	if (min_limit_perf < lowest_perf)
-- 
2.43.0

Re: [PATCH 06/15] cpufreq/amd-pstate: Use boost numerator for upper bound of frequencies

[Gautham R. Shenoy]

On Thu, Dec 05, 2024 at 04:28:38PM -0600, Mario Limonciello wrote:
> commit 18d9b5227121 ("cpufreq/amd-pstate: Use nominal perf for limits
> when boost is disabled") introduced different semantics for min/max limits
> based upon whether the user turned off boost from sysfs.
> 
> This however is not necessary when the highest perf value is the boost
> numerator.
> 
> Suggested-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com>
> Fixes: 18d9b5227121 ("cpufreq/amd-pstate: Use nominal perf for limits when boost is disabled")
> Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
> ---
>  drivers/cpufreq/amd-pstate.c | 13 +++++--------
>  1 file changed, 5 insertions(+), 8 deletions(-)
> 
> diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
> index 738f63d70546f..14bd6faa3d730 100644
> --- a/drivers/cpufreq/amd-pstate.c
> +++ b/drivers/cpufreq/amd-pstate.c
> @@ -601,16 +601,13 @@ static int amd_pstate_verify(struct cpufreq_policy_data *policy_data)
>  
>  static int amd_pstate_update_min_max_limit(struct cpufreq_policy *policy)
>  {
> -	u32 max_limit_perf, min_limit_perf, lowest_perf, max_perf;
> +	u32 max_limit_perf, min_limit_perf, lowest_perf, max_perf, max_freq;
>  	struct amd_cpudata *cpudata = policy->driver_data;
>  
> -	if (cpudata->boost_supported && !policy->boost_enabled)
> -		max_perf = READ_ONCE(cpudata->nominal_perf);
> -	else
> -		max_perf = READ_ONCE(cpudata->highest_perf);
> -
> -	max_limit_perf = div_u64(policy->max * max_perf, policy->cpuinfo.max_freq);
> -	min_limit_perf = div_u64(policy->min * max_perf, policy->cpuinfo.max_freq);
> +	max_perf = READ_ONCE(cpudata->highest_perf);
> +	max_freq = READ_ONCE(cpudata->max_freq);
> +	max_limit_perf = div_u64(policy->max * max_perf, max_freq);
> +	min_limit_perf = div_u64(policy->min * max_perf, max_freq);

Looks good to me.

At some point in the future, we should consider using nominal_perf and
nominal_freq as the baseline for the freq-->perf and perf-->freq
conversions. That is invariant to boost being enabled or not.

Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>

--
Thanks and Regards
gautham.




>  
>  	lowest_perf = READ_ONCE(cpudata->lowest_perf);
>  	if (min_limit_perf < lowest_perf)
> -- 
> 2.43.0
> 

[PATCH 07/15] cpufreq/amd-pstate: Only update the cached value in msr_set_epp() on success

[Mario Limonciello]

If writing the MSR MSR_AMD_CPPC_REQ fails then the cached value in the
amd_cpudata structure should not be updated.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 drivers/cpufreq/amd-pstate.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 14bd6faa3d730..ce70d1bfa55d0 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -278,11 +278,15 @@ static int msr_set_epp(struct amd_cpudata *cpudata, u32 epp)
 
 	value &= ~AMD_PSTATE_EPP_PERF_MASK;
 	value |= FIELD_PREP(AMD_PSTATE_EPP_PERF_MASK, epp);
-	WRITE_ONCE(cpudata->cppc_req_cached, value);
 
 	ret = wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value);
-	if (!ret)
-		cpudata->epp_cached = epp;
+	if (ret) {
+		pr_err("failed to set energy perf value (%d)\n", ret);
+		return ret;
+	}
+
+	cpudata->epp_cached = epp;
+	WRITE_ONCE(cpudata->cppc_req_cached, value);
 
 	return ret;
 }
-- 
2.43.0

Re: [PATCH 07/15] cpufreq/amd-pstate: Only update the cached value in msr_set_epp() on success

[Gautham R. Shenoy]

On Thu, Dec 05, 2024 at 04:28:39PM -0600, Mario Limonciello wrote:
> If writing the MSR MSR_AMD_CPPC_REQ fails then the cached value in the
> amd_cpudata structure should not be updated.

Considering that the remote MSR update can fail only if either the
cpudata->cpu is invalid or if that CPU is not online, this is the
right thing to do.

Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>

--
Thanks and Regards
gautham.



> 
> Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
> ---
>  drivers/cpufreq/amd-pstate.c | 10 +++++++---
>  1 file changed, 7 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
> index 14bd6faa3d730..ce70d1bfa55d0 100644
> --- a/drivers/cpufreq/amd-pstate.c
> +++ b/drivers/cpufreq/amd-pstate.c
> @@ -278,11 +278,15 @@ static int msr_set_epp(struct amd_cpudata *cpudata, u32 epp)
>  
>  	value &= ~AMD_PSTATE_EPP_PERF_MASK;
>  	value |= FIELD_PREP(AMD_PSTATE_EPP_PERF_MASK, epp);
> -	WRITE_ONCE(cpudata->cppc_req_cached, value);
>  
>  	ret = wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value);
> -	if (!ret)
> -		cpudata->epp_cached = epp;
> +	if (ret) {
> +		pr_err("failed to set energy perf value (%d)\n", ret);
> +		return ret;
> +	}
> +
> +	cpudata->epp_cached = epp;
> +	WRITE_ONCE(cpudata->cppc_req_cached, value);
>  
>  	return ret;
>  }
> -- 
> 2.43.0
> 

[PATCH 08/15] cpufreq/amd-pstate: store all values in cpudata struct in khz

[Mario Limonciello]

Storing values in the cpudata structure in different units leads
to confusion and hardcoded conversions elsewhere.  After ratios are
calculated store everything in khz for any future use. Adjust all
relevant consumers for this change as well.

Suggested-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 drivers/cpufreq/amd-pstate-ut.c | 12 +++++-------
 drivers/cpufreq/amd-pstate.c    | 30 +++++++++++++++---------------
 2 files changed, 20 insertions(+), 22 deletions(-)

diff --git a/drivers/cpufreq/amd-pstate-ut.c b/drivers/cpufreq/amd-pstate-ut.c
index a261d7300951e..3a0a380c3590c 100644
--- a/drivers/cpufreq/amd-pstate-ut.c
+++ b/drivers/cpufreq/amd-pstate-ut.c
@@ -207,7 +207,6 @@ static void amd_pstate_ut_check_freq(u32 index)
 	int cpu = 0;
 	struct cpufreq_policy *policy = NULL;
 	struct amd_cpudata *cpudata = NULL;
-	u32 nominal_freq_khz;
 
 	for_each_possible_cpu(cpu) {
 		policy = cpufreq_cpu_get(cpu);
@@ -215,14 +214,13 @@ static void amd_pstate_ut_check_freq(u32 index)
 			break;
 		cpudata = policy->driver_data;
 
-		nominal_freq_khz = cpudata->nominal_freq*1000;
-		if (!((cpudata->max_freq >= nominal_freq_khz) &&
-			(nominal_freq_khz > cpudata->lowest_nonlinear_freq) &&
+		if (!((cpudata->max_freq >= cpudata->nominal_freq) &&
+			(cpudata->nominal_freq > cpudata->lowest_nonlinear_freq) &&
 			(cpudata->lowest_nonlinear_freq > cpudata->min_freq) &&
 			(cpudata->min_freq > 0))) {
 			amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL;
 			pr_err("%s cpu%d max=%d >= nominal=%d > lowest_nonlinear=%d > min=%d > 0, the formula is incorrect!\n",
-				__func__, cpu, cpudata->max_freq, nominal_freq_khz,
+				__func__, cpu, cpudata->max_freq, cpudata->nominal_freq,
 				cpudata->lowest_nonlinear_freq, cpudata->min_freq);
 			goto skip_test;
 		}
@@ -236,13 +234,13 @@ static void amd_pstate_ut_check_freq(u32 index)
 
 		if (cpudata->boost_supported) {
 			if ((policy->max == cpudata->max_freq) ||
-					(policy->max == nominal_freq_khz))
+					(policy->max == cpudata->nominal_freq))
 				amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_PASS;
 			else {
 				amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL;
 				pr_err("%s cpu%d policy_max=%d should be equal cpu_max=%d or cpu_nominal=%d !\n",
 					__func__, cpu, policy->max, cpudata->max_freq,
-					nominal_freq_khz);
+					cpudata->nominal_freq);
 				goto skip_test;
 			}
 		} else {
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index ce70d1bfa55d0..464db6745d84e 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -739,8 +739,8 @@ static int amd_pstate_cpu_boost_update(struct cpufreq_policy *policy, bool on)
 
 	if (on)
 		policy->cpuinfo.max_freq = max_freq;
-	else if (policy->cpuinfo.max_freq > nominal_freq * 1000)
-		policy->cpuinfo.max_freq = nominal_freq * 1000;
+	else if (policy->cpuinfo.max_freq > nominal_freq)
+		policy->cpuinfo.max_freq = nominal_freq;
 
 	policy->max = policy->cpuinfo.max_freq;
 
@@ -940,29 +940,29 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata)
 		return ret;
 
 	if (quirks && quirks->lowest_freq)
-		min_freq = quirks->lowest_freq * 1000;
+		min_freq = quirks->lowest_freq;
 	else
-		min_freq = cppc_perf.lowest_freq * 1000;
+		min_freq = cppc_perf.lowest_freq;
 
 	if (quirks && quirks->nominal_freq)
-		nominal_freq = quirks->nominal_freq ;
+		nominal_freq = quirks->nominal_freq;
 	else
 		nominal_freq = cppc_perf.nominal_freq;
 
 	nominal_perf = READ_ONCE(cpudata->nominal_perf);
 
 	boost_ratio = div_u64(cpudata->highest_perf << SCHED_CAPACITY_SHIFT, nominal_perf);
-	max_freq = (nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT) * 1000;
+	max_freq = (nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT);
 
 	lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf);
 	lowest_nonlinear_ratio = div_u64(lowest_nonlinear_perf << SCHED_CAPACITY_SHIFT,
 					 nominal_perf);
-	lowest_nonlinear_freq = (nominal_freq * lowest_nonlinear_ratio >> SCHED_CAPACITY_SHIFT) * 1000;
+	lowest_nonlinear_freq = (nominal_freq * lowest_nonlinear_ratio >> SCHED_CAPACITY_SHIFT);
 
-	WRITE_ONCE(cpudata->min_freq, min_freq);
-	WRITE_ONCE(cpudata->lowest_nonlinear_freq, lowest_nonlinear_freq);
-	WRITE_ONCE(cpudata->nominal_freq, nominal_freq);
-	WRITE_ONCE(cpudata->max_freq, max_freq);
+	WRITE_ONCE(cpudata->min_freq, min_freq * 1000);
+	WRITE_ONCE(cpudata->lowest_nonlinear_freq, lowest_nonlinear_freq * 1000);
+	WRITE_ONCE(cpudata->nominal_freq, nominal_freq * 1000);
+	WRITE_ONCE(cpudata->max_freq, max_freq * 1000);
 
 	/**
 	 * Below values need to be initialized correctly, otherwise driver will fail to load
@@ -970,15 +970,15 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata)
 	 * lowest_nonlinear_freq is a value between [min_freq, nominal_freq]
 	 * Check _CPC in ACPI table objects if any values are incorrect
 	 */
-	if (min_freq <= 0 || max_freq <= 0 || nominal_freq <= 0 || min_freq > max_freq) {
+	if (min_freq <= 0 || max_freq <= 0 || cpudata->nominal_freq <= 0 || min_freq > max_freq) {
 		pr_err("min_freq(%d) or max_freq(%d) or nominal_freq(%d) value is incorrect\n",
-			min_freq, max_freq, nominal_freq * 1000);
+			min_freq, max_freq, cpudata->nominal_freq);
 		return -EINVAL;
 	}
 
-	if (lowest_nonlinear_freq <= min_freq || lowest_nonlinear_freq > nominal_freq * 1000) {
+	if (lowest_nonlinear_freq <= min_freq || lowest_nonlinear_freq > cpudata->nominal_freq) {
 		pr_err("lowest_nonlinear_freq(%d) value is out of range [min_freq(%d), nominal_freq(%d)]\n",
-			lowest_nonlinear_freq, min_freq, nominal_freq * 1000);
+			lowest_nonlinear_freq, min_freq, cpudata->nominal_freq);
 		return -EINVAL;
 	}
 
-- 
2.43.0

Re: [PATCH 08/15] cpufreq/amd-pstate: store all values in cpudata struct in khz

[Gautham R. Shenoy]

On Thu, Dec 05, 2024 at 04:28:40PM -0600, Mario Limonciello wrote:
> Storing values in the cpudata structure in different units leads
> to confusion and hardcoded conversions elsewhere.  After ratios are
> calculated store everything in khz for any future use. Adjust all
> relevant consumers for this change as well.
> 
> Suggested-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com>
> Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>

Thanks for cleaning this up.

This also makes the code in-line with the comment for cpudata->nominal_freq which says

 * @nominal_freq: the frequency (in khz) that mapped to nominal_perf

Couple of minor nits. See below.

> ---
>  drivers/cpufreq/amd-pstate-ut.c | 12 +++++-------
>  drivers/cpufreq/amd-pstate.c    | 30 +++++++++++++++---------------
>  2 files changed, 20 insertions(+), 22 deletions(-)
> 
> diff --git a/drivers/cpufreq/amd-pstate-ut.c b/drivers/cpufreq/amd-pstate-ut.c
> index a261d7300951e..3a0a380c3590c 100644
> --- a/drivers/cpufreq/amd-pstate-ut.c
> +++ b/drivers/cpufreq/amd-pstate-ut.c
> @@ -207,7 +207,6 @@ static void amd_pstate_ut_check_freq(u32 index)
>  	int cpu = 0;
>  	struct cpufreq_policy *policy = NULL;
>  	struct amd_cpudata *cpudata = NULL;
> -	u32 nominal_freq_khz;
>  
>  	for_each_possible_cpu(cpu) {
>  		policy = cpufreq_cpu_get(cpu);
> @@ -215,14 +214,13 @@ static void amd_pstate_ut_check_freq(u32 index)
>  			break;
>  		cpudata = policy->driver_data;
>  
> -		nominal_freq_khz = cpudata->nominal_freq*1000;
> -		if (!((cpudata->max_freq >= nominal_freq_khz) &&
> -			(nominal_freq_khz > cpudata->lowest_nonlinear_freq) &&
> +		if (!((cpudata->max_freq >= cpudata->nominal_freq) &&
> +			(cpudata->nominal_freq > cpudata->lowest_nonlinear_freq) &&
>  			(cpudata->lowest_nonlinear_freq > cpudata->min_freq) &&
>  			(cpudata->min_freq > 0))) {
>  			amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL;
>  			pr_err("%s cpu%d max=%d >= nominal=%d > lowest_nonlinear=%d > min=%d > 0, the formula is incorrect!\n",
> -				__func__, cpu, cpudata->max_freq, nominal_freq_khz,
> +				__func__, cpu, cpudata->max_freq, cpudata->nominal_freq,
>  				cpudata->lowest_nonlinear_freq, cpudata->min_freq);
>  			goto skip_test;
>  		}
> @@ -236,13 +234,13 @@ static void amd_pstate_ut_check_freq(u32 index)
>  
>  		if (cpudata->boost_supported) {
>  			if ((policy->max == cpudata->max_freq) ||
> -					(policy->max == nominal_freq_khz))
> +					(policy->max == cpudata->nominal_freq))
>  				amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_PASS;
>  			else {
>  				amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL;
>  				pr_err("%s cpu%d policy_max=%d should be equal cpu_max=%d or cpu_nominal=%d !\n",
>  					__func__, cpu, policy->max, cpudata->max_freq,
> -					nominal_freq_khz);
> +					cpudata->nominal_freq);
>  				goto skip_test;
>  			}
>  		} else {
> diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
> index ce70d1bfa55d0..464db6745d84e 100644
> --- a/drivers/cpufreq/amd-pstate.c
> +++ b/drivers/cpufreq/amd-pstate.c
> @@ -739,8 +739,8 @@ static int amd_pstate_cpu_boost_update(struct cpufreq_policy *policy, bool on)
>  
>  	if (on)
>  		policy->cpuinfo.max_freq = max_freq;
> -	else if (policy->cpuinfo.max_freq > nominal_freq * 1000)
> -		policy->cpuinfo.max_freq = nominal_freq * 1000;
> +	else if (policy->cpuinfo.max_freq > nominal_freq)
> +		policy->cpuinfo.max_freq = nominal_freq;
>  
>  	policy->max = policy->cpuinfo.max_freq;
>  
> @@ -940,29 +940,29 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata)
>  		return ret;
>  
>  	if (quirks && quirks->lowest_freq)
> -		min_freq = quirks->lowest_freq * 1000;
> +		min_freq = quirks->lowest_freq;
>  	else
> -		min_freq = cppc_perf.lowest_freq * 1000;
> +		min_freq = cppc_perf.lowest_freq;
>  
>  	if (quirks && quirks->nominal_freq)
> -		nominal_freq = quirks->nominal_freq ;
> +		nominal_freq = quirks->nominal_freq;
>  	else
>  		nominal_freq = cppc_perf.nominal_freq;
>  
>  	nominal_perf = READ_ONCE(cpudata->nominal_perf);
>  
>  	boost_ratio = div_u64(cpudata->highest_perf << SCHED_CAPACITY_SHIFT, nominal_perf);
> -	max_freq = (nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT) * 1000;
> +	max_freq = (nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT);
>  
>  	lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf);
>  	lowest_nonlinear_ratio = div_u64(lowest_nonlinear_perf << SCHED_CAPACITY_SHIFT,
>  					 nominal_perf);
> -	lowest_nonlinear_freq = (nominal_freq * lowest_nonlinear_ratio >> SCHED_CAPACITY_SHIFT) * 1000;
> +	lowest_nonlinear_freq = (nominal_freq * lowest_nonlinear_ratio >> SCHED_CAPACITY_SHIFT);
>  
> -	WRITE_ONCE(cpudata->min_freq, min_freq);
> -	WRITE_ONCE(cpudata->lowest_nonlinear_freq, lowest_nonlinear_freq);
> -	WRITE_ONCE(cpudata->nominal_freq, nominal_freq);
> -	WRITE_ONCE(cpudata->max_freq, max_freq);
> +	WRITE_ONCE(cpudata->min_freq, min_freq * 1000);
> +	WRITE_ONCE(cpudata->lowest_nonlinear_freq, lowest_nonlinear_freq * 1000);
> +	WRITE_ONCE(cpudata->nominal_freq, nominal_freq * 1000);
> +	WRITE_ONCE(cpudata->max_freq, max_freq * 1000);
>  
>  	/**
>  	 * Below values need to be initialized correctly, otherwise driver will fail to load
> @@ -970,15 +970,15 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata)
>  	 * lowest_nonlinear_freq is a value between [min_freq, nominal_freq]
>  	 * Check _CPC in ACPI table objects if any values are incorrect
>  	 */
> -	if (min_freq <= 0 || max_freq <= 0 || nominal_freq <= 0 || min_freq > max_freq) {

> +	if (min_freq <= 0 || max_freq <= 0 || cpudata->nominal_freq <= 0 || min_freq > max_freq) {
>  		pr_err("min_freq(%d) or max_freq(%d) or nominal_freq(%d) value is incorrect\n",
> -			min_freq, max_freq, nominal_freq * 1000);
> +			min_freq, max_freq, cpudata->nominal_freq);
>  		return -EINVAL;


We don't need this change. This looks odd since we are using min_freq
and max_freq from local variables, but nominal_freq from cpudata.

We may just as well use the local variables in all the cases since
"cpudata->nominal_freq = nominal_freq * 1000", and thus won't make any
difference to the checks above.


>  	}
>  
> -	if (lowest_nonlinear_freq <= min_freq || lowest_nonlinear_freq > nominal_freq * 1000) {
                                                                         ^^^^^^^^^^^^^^^^^^^^

Simply replace this with nominal_freq ?

Because both lowest_nonlinear_freq and nominal_freq are in MHz at this
point.

> +	if (lowest_nonlinear_freq <= min_freq || lowest_nonlinear_freq > cpudata->nominal_freq) {
>  		pr_err("lowest_nonlinear_freq(%d) value is out of range [min_freq(%d), nominal_freq(%d)]\n",
> -			lowest_nonlinear_freq, min_freq, nominal_freq * 1000);
> +			lowest_nonlinear_freq, min_freq, cpudata->nominal_freq);
                                                         ^^^^^^^^^^^^^^^^^^^^^^

Likewise, this can just be nominal_freq
>  		return -EINVAL;
>  	}
>  
> -- 
> 2.43.0
> 

Other than that,
Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>

--
Thanks and Regards
gautham.

[PATCH 09/15] cpufreq/amd-pstate: Change amd_pstate_update_perf() to return an int

[Mario Limonciello]

As msr_update_perf() calls an MSR it's possible that it fails. Pass
this return code up to the caller.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 drivers/cpufreq/amd-pstate.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 464db6745d84e..842e7e3c5eaf2 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -251,24 +251,26 @@ static int amd_pstate_get_energy_pref_index(struct amd_cpudata *cpudata)
 	return index;
 }
 
-static void msr_update_perf(struct amd_cpudata *cpudata, u32 min_perf,
+static int msr_update_perf(struct amd_cpudata *cpudata, u32 min_perf,
 			       u32 des_perf, u32 max_perf, bool fast_switch)
 {
-	if (fast_switch)
+	if (fast_switch) {
 		wrmsrl(MSR_AMD_CPPC_REQ, READ_ONCE(cpudata->cppc_req_cached));
-	else
-		wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ,
-			      READ_ONCE(cpudata->cppc_req_cached));
+		return 0;
+	}
+
+	return wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ,
+			     READ_ONCE(cpudata->cppc_req_cached));
 }
 
 DEFINE_STATIC_CALL(amd_pstate_update_perf, msr_update_perf);
 
-static inline void amd_pstate_update_perf(struct amd_cpudata *cpudata,
+static inline int amd_pstate_update_perf(struct amd_cpudata *cpudata,
 					  u32 min_perf, u32 des_perf,
 					  u32 max_perf, bool fast_switch)
 {
-	static_call(amd_pstate_update_perf)(cpudata, min_perf, des_perf,
-					    max_perf, fast_switch);
+	return static_call(amd_pstate_update_perf)(cpudata, min_perf, des_perf,
+						   max_perf, fast_switch);
 }
 
 static int msr_set_epp(struct amd_cpudata *cpudata, u32 epp)
@@ -480,7 +482,7 @@ static inline int amd_pstate_init_perf(struct amd_cpudata *cpudata)
 	return static_call(amd_pstate_init_perf)(cpudata);
 }
 
-static void shmem_update_perf(struct amd_cpudata *cpudata,
+static int shmem_update_perf(struct amd_cpudata *cpudata,
 			     u32 min_perf, u32 des_perf,
 			     u32 max_perf, bool fast_switch)
 {
@@ -490,7 +492,7 @@ static void shmem_update_perf(struct amd_cpudata *cpudata,
 	perf_ctrls.min_perf = min_perf;
 	perf_ctrls.desired_perf = des_perf;
 
-	cppc_set_perf(cpudata->cpu, &perf_ctrls);
+	return cppc_set_perf(cpudata->cpu, &perf_ctrls);
 }
 
 static inline bool amd_pstate_sample(struct amd_cpudata *cpudata)
-- 
2.43.0

Re: [PATCH 09/15] cpufreq/amd-pstate: Change amd_pstate_update_perf() to return an int

[Gautham R. Shenoy]

On Thu, Dec 05, 2024 at 04:28:41PM -0600, Mario Limonciello wrote:
> As msr_update_perf() calls an MSR it's possible that it fails. Pass
> this return code up to the caller.
> 
> Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>

Looks good to me.

Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
--
Thanks and Regards
gautham.

> ---
>  drivers/cpufreq/amd-pstate.c | 22 ++++++++++++----------
>  1 file changed, 12 insertions(+), 10 deletions(-)
> 
> diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
> index 464db6745d84e..842e7e3c5eaf2 100644
> --- a/drivers/cpufreq/amd-pstate.c
> +++ b/drivers/cpufreq/amd-pstate.c
> @@ -251,24 +251,26 @@ static int amd_pstate_get_energy_pref_index(struct amd_cpudata *cpudata)
>  	return index;
>  }
>  
> -static void msr_update_perf(struct amd_cpudata *cpudata, u32 min_perf,
> +static int msr_update_perf(struct amd_cpudata *cpudata, u32 min_perf,
>  			       u32 des_perf, u32 max_perf, bool fast_switch)
>  {
> -	if (fast_switch)
> +	if (fast_switch) {
>  		wrmsrl(MSR_AMD_CPPC_REQ, READ_ONCE(cpudata->cppc_req_cached));
> -	else
> -		wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ,
> -			      READ_ONCE(cpudata->cppc_req_cached));
> +		return 0;
> +	}
> +
> +	return wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ,
> +			     READ_ONCE(cpudata->cppc_req_cached));
>  }
>  
>  DEFINE_STATIC_CALL(amd_pstate_update_perf, msr_update_perf);
>  
> -static inline void amd_pstate_update_perf(struct amd_cpudata *cpudata,
> +static inline int amd_pstate_update_perf(struct amd_cpudata *cpudata,
>  					  u32 min_perf, u32 des_perf,
>  					  u32 max_perf, bool fast_switch)
>  {
> -	static_call(amd_pstate_update_perf)(cpudata, min_perf, des_perf,
> -					    max_perf, fast_switch);
> +	return static_call(amd_pstate_update_perf)(cpudata, min_perf, des_perf,
> +						   max_perf, fast_switch);
>  }
>  
>  static int msr_set_epp(struct amd_cpudata *cpudata, u32 epp)
> @@ -480,7 +482,7 @@ static inline int amd_pstate_init_perf(struct amd_cpudata *cpudata)
>  	return static_call(amd_pstate_init_perf)(cpudata);
>  }
>  
> -static void shmem_update_perf(struct amd_cpudata *cpudata,
> +static int shmem_update_perf(struct amd_cpudata *cpudata,
>  			     u32 min_perf, u32 des_perf,
>  			     u32 max_perf, bool fast_switch)
>  {
> @@ -490,7 +492,7 @@ static void shmem_update_perf(struct amd_cpudata *cpudata,
>  	perf_ctrls.min_perf = min_perf;
>  	perf_ctrls.desired_perf = des_perf;
>  
> -	cppc_set_perf(cpudata->cpu, &perf_ctrls);
> +	return cppc_set_perf(cpudata->cpu, &perf_ctrls);
>  }
>  
>  static inline bool amd_pstate_sample(struct amd_cpudata *cpudata)
> -- 
> 2.43.0
> 

[PATCH 10/15] cpufreq/amd-pstate: Move limit updating code

[Mario Limonciello]

The limit updating code in amd_pstate_epp_update_limit() should not
only apply to EPP updates.  Move it to amd_pstate_update_min_max_limit()
so other callers can benefit as well.

With this move it's not necessary to have clamp_t calls anymore because
the verify callback is called when setting limits.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 drivers/cpufreq/amd-pstate.c | 24 ++++--------------------
 1 file changed, 4 insertions(+), 20 deletions(-)

diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 842e7e3c5eaf2..5ee53b45c1ca1 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -537,10 +537,6 @@ static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf,
 	u32 nominal_perf = READ_ONCE(cpudata->nominal_perf);
 	u64 value = prev;
 
-	min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf,
-			cpudata->max_limit_perf);
-	max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf,
-			cpudata->max_limit_perf);
 	des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf);
 
 	max_freq = READ_ONCE(cpudata->max_limit_freq);
@@ -616,11 +612,9 @@ static int amd_pstate_update_min_max_limit(struct cpufreq_policy *policy)
 	min_limit_perf = div_u64(policy->min * max_perf, max_freq);
 
 	lowest_perf = READ_ONCE(cpudata->lowest_perf);
-	if (min_limit_perf < lowest_perf)
-		min_limit_perf = lowest_perf;
 
-	if (max_limit_perf < min_limit_perf)
-		max_limit_perf = min_limit_perf;
+	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
+		min_limit_perf = min(cpudata->nominal_perf, max_limit_perf);
 
 	WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf);
 	WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf);
@@ -1562,28 +1556,18 @@ static void amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy)
 static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
 {
 	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);
 	amd_pstate_update_min_max_limit(policy);
 
-	max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf,
-			cpudata->max_limit_perf);
-	min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf,
-			cpudata->max_limit_perf);
 	value = READ_ONCE(cpudata->cppc_req_cached);
 
-	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
-		min_perf = min(cpudata->nominal_perf, max_perf);
-
 	value &= ~(AMD_PSTATE_MAX_PERF_MASK | AMD_PSTATE_MIN_PERF_MASK |
 		   AMD_PSTATE_DES_PERF_MASK);
-	value |= FIELD_PREP(AMD_PSTATE_MAX_PERF_MASK, max_perf);
+	value |= FIELD_PREP(AMD_PSTATE_MAX_PERF_MASK, cpudata->max_limit_perf);
 	value |= FIELD_PREP(AMD_PSTATE_DES_PERF_MASK, 0);
-	value |= FIELD_PREP(AMD_PSTATE_MIN_PERF_MASK, min_perf);
+	value |= FIELD_PREP(AMD_PSTATE_MIN_PERF_MASK, cpudata->min_limit_perf);
 
 	/* Get BIOS pre-defined epp value */
 	epp = amd_pstate_get_epp(cpudata, value);
-- 
2.43.0

Re: [PATCH 10/15] cpufreq/amd-pstate: Move limit updating code

[kernel test robot]

Hi Mario,

kernel test robot noticed the following build warnings:

[auto build test WARNING on ab9e5b2eb56412cb8c63b46b935878d29205418e]

url:    https://github.com/intel-lab-lkp/linux/commits/Mario-Limonciello/cpufreq-amd-pstate-Add-trace-event-for-EPP-perf-updates/20241206-063920
base:   ab9e5b2eb56412cb8c63b46b935878d29205418e
patch link:    https://lore.kernel.org/r/20241205222847.7889-11-mario.limonciello%40amd.com
patch subject: [PATCH 10/15] cpufreq/amd-pstate: Move limit updating code
config: x86_64-buildonly-randconfig-001-20241206 (https://download.01.org/0day-ci/archive/20241206/202412061054.cJTnhP0n-lkp@intel.com/config)
compiler: gcc-12 (Debian 12.2.0-14) 12.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20241206/202412061054.cJTnhP0n-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202412061054.cJTnhP0n-lkp@intel.com/

All warnings (new ones prefixed by >>):

   drivers/cpufreq/amd-pstate.c: In function 'amd_pstate_update_min_max_limit':
>> drivers/cpufreq/amd-pstate.c:606:45: warning: variable 'lowest_perf' set but not used [-Wunused-but-set-variable]
     606 |         u32 max_limit_perf, min_limit_perf, lowest_perf, max_perf, max_freq;
         |                                             ^~~~~~~~~~~


vim +/lowest_perf +606 drivers/cpufreq/amd-pstate.c

ec437d71db77a18 Huang Rui         2021-12-24  603  
febab20caebac95 Wyes Karny        2023-11-17  604  static int amd_pstate_update_min_max_limit(struct cpufreq_policy *policy)
febab20caebac95 Wyes Karny        2023-11-17  605  {
b623ceabb704d2d Mario Limonciello 2024-12-05 @606  	u32 max_limit_perf, min_limit_perf, lowest_perf, max_perf, max_freq;
febab20caebac95 Wyes Karny        2023-11-17  607  	struct amd_cpudata *cpudata = policy->driver_data;
febab20caebac95 Wyes Karny        2023-11-17  608  
18d9b5227121389 Mario Limonciello 2024-10-12  609  	max_perf = READ_ONCE(cpudata->highest_perf);
b623ceabb704d2d Mario Limonciello 2024-12-05  610  	max_freq = READ_ONCE(cpudata->max_freq);
b623ceabb704d2d Mario Limonciello 2024-12-05  611  	max_limit_perf = div_u64(policy->max * max_perf, max_freq);
b623ceabb704d2d Mario Limonciello 2024-12-05  612  	min_limit_perf = div_u64(policy->min * max_perf, max_freq);
febab20caebac95 Wyes Karny        2023-11-17  613  
8164f743326404f Meng Li           2024-02-27  614  	lowest_perf = READ_ONCE(cpudata->lowest_perf);
8164f743326404f Meng Li           2024-02-27  615  
6fbd2a2609d0033 Mario Limonciello 2024-12-05  616  	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
6fbd2a2609d0033 Mario Limonciello 2024-12-05  617  		min_limit_perf = min(cpudata->nominal_perf, max_limit_perf);
8164f743326404f Meng Li           2024-02-27  618  
febab20caebac95 Wyes Karny        2023-11-17  619  	WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf);
febab20caebac95 Wyes Karny        2023-11-17  620  	WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf);
febab20caebac95 Wyes Karny        2023-11-17  621  	WRITE_ONCE(cpudata->max_limit_freq, policy->max);
febab20caebac95 Wyes Karny        2023-11-17  622  	WRITE_ONCE(cpudata->min_limit_freq, policy->min);
febab20caebac95 Wyes Karny        2023-11-17  623  
febab20caebac95 Wyes Karny        2023-11-17  624  	return 0;
febab20caebac95 Wyes Karny        2023-11-17  625  }
febab20caebac95 Wyes Karny        2023-11-17  626  

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH 10/15] cpufreq/amd-pstate: Move limit updating code

[Gautham R. Shenoy]

On Thu, Dec 05, 2024 at 04:28:42PM -0600, Mario Limonciello wrote:
> The limit updating code in amd_pstate_epp_update_limit() should not
> only apply to EPP updates.  Move it to amd_pstate_update_min_max_limit()
> so other callers can benefit as well.
> 
> With this move it's not necessary to have clamp_t calls anymore because
> the verify callback is called when setting limits.

Nice catch!!

The patch looks good to me.

Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>

--
Thanks and Regards
gautham.

> 
> Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
> ---
>  drivers/cpufreq/amd-pstate.c | 24 ++++--------------------
>  1 file changed, 4 insertions(+), 20 deletions(-)
> 
> diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
> index 842e7e3c5eaf2..5ee53b45c1ca1 100644
> --- a/drivers/cpufreq/amd-pstate.c
> +++ b/drivers/cpufreq/amd-pstate.c
> @@ -537,10 +537,6 @@ static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf,
>  	u32 nominal_perf = READ_ONCE(cpudata->nominal_perf);
>  	u64 value = prev;
>  
> -	min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf,
> -			cpudata->max_limit_perf);
> -	max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf,
> -			cpudata->max_limit_perf);
>  	des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf);
>  
>  	max_freq = READ_ONCE(cpudata->max_limit_freq);
> @@ -616,11 +612,9 @@ static int amd_pstate_update_min_max_limit(struct cpufreq_policy *policy)
>  	min_limit_perf = div_u64(policy->min * max_perf, max_freq);
>  
>  	lowest_perf = READ_ONCE(cpudata->lowest_perf);
> -	if (min_limit_perf < lowest_perf)
> -		min_limit_perf = lowest_perf;
>  
> -	if (max_limit_perf < min_limit_perf)
> -		max_limit_perf = min_limit_perf;
> +	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
> +		min_limit_perf = min(cpudata->nominal_perf, max_limit_perf);
>  
>  	WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf);
>  	WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf);
> @@ -1562,28 +1556,18 @@ static void amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy)
>  static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
>  {
>  	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);
>  	amd_pstate_update_min_max_limit(policy);
>  
> -	max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf,
> -			cpudata->max_limit_perf);
> -	min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf,
> -			cpudata->max_limit_perf);
>  	value = READ_ONCE(cpudata->cppc_req_cached);
>  
> -	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
> -		min_perf = min(cpudata->nominal_perf, max_perf);
> -
>  	value &= ~(AMD_PSTATE_MAX_PERF_MASK | AMD_PSTATE_MIN_PERF_MASK |
>  		   AMD_PSTATE_DES_PERF_MASK);
> -	value |= FIELD_PREP(AMD_PSTATE_MAX_PERF_MASK, max_perf);
> +	value |= FIELD_PREP(AMD_PSTATE_MAX_PERF_MASK, cpudata->max_limit_perf);
>  	value |= FIELD_PREP(AMD_PSTATE_DES_PERF_MASK, 0);
> -	value |= FIELD_PREP(AMD_PSTATE_MIN_PERF_MASK, min_perf);
> +	value |= FIELD_PREP(AMD_PSTATE_MIN_PERF_MASK, cpudata->min_limit_perf);
>  
>  	/* Get BIOS pre-defined epp value */
>  	epp = amd_pstate_get_epp(cpudata, value);
> -- 
> 2.43.0
> 

[PATCH 11/15] cpufreq/amd-pstate: Cache EPP value and use that everywhere

[Mario Limonciello]

Cache the value in cpudata->epp_cached, and use that for all callers.
As all callers use cached value merge amd_pstate_get_energy_pref_index()
into show_energy_performance_preference().

Check if the EPP value is changed before writing it to MSR or
shared memory region.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 drivers/cpufreq/amd-pstate.c | 107 +++++++++++++++--------------------
 1 file changed, 45 insertions(+), 62 deletions(-)

diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 5ee53b45c1ca1..20de3a9fd992d 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -186,29 +186,28 @@ static inline int get_mode_idx_from_str(const char *str, size_t size)
 static DEFINE_MUTEX(amd_pstate_limits_lock);
 static DEFINE_MUTEX(amd_pstate_driver_lock);
 
-static s16 msr_get_epp(struct amd_cpudata *cpudata, u64 cppc_req_cached)
+static s16 msr_get_epp(struct amd_cpudata *cpudata)
 {
+	u64 value;
 	int ret;
 
-	if (!cppc_req_cached) {
-		ret = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, &cppc_req_cached);
-		if (ret < 0) {
-			pr_debug("Could not retrieve energy perf value (%d)\n", ret);
-			return ret;
-		}
+	ret = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, &value);
+	if (ret < 0) {
+		pr_debug("Could not retrieve energy perf value (%d)\n", ret);
+		return ret;
 	}
 
-	return FIELD_GET(AMD_PSTATE_EPP_PERF_MASK, cppc_req_cached);
+	return FIELD_GET(AMD_PSTATE_EPP_PERF_MASK, value);
 }
 
 DEFINE_STATIC_CALL(amd_pstate_get_epp, msr_get_epp);
 
-static inline s16 amd_pstate_get_epp(struct amd_cpudata *cpudata, u64 cppc_req_cached)
+static inline s16 amd_pstate_get_epp(struct amd_cpudata *cpudata)
 {
-	return static_call(amd_pstate_get_epp)(cpudata, cppc_req_cached);
+	return static_call(amd_pstate_get_epp)(cpudata);
 }
 
-static s16 shmem_get_epp(struct amd_cpudata *cpudata, u64 dummy)
+static s16 shmem_get_epp(struct amd_cpudata *cpudata)
 {
 	u64 epp;
 	int ret;
@@ -222,35 +221,6 @@ static s16 shmem_get_epp(struct amd_cpudata *cpudata, u64 dummy)
 	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 AMD_CPPC_EPP_PERFORMANCE:
-		index = EPP_INDEX_PERFORMANCE;
-		break;
-	case AMD_CPPC_EPP_BALANCE_PERFORMANCE:
-		index = EPP_INDEX_BALANCE_PERFORMANCE;
-		break;
-	case AMD_CPPC_EPP_BALANCE_POWERSAVE:
-		index = EPP_INDEX_BALANCE_POWERSAVE;
-		break;
-	case AMD_CPPC_EPP_POWERSAVE:
-		index = EPP_INDEX_POWERSAVE;
-		break;
-	default:
-		break;
-	}
-
-	return index;
-}
-
 static int msr_update_perf(struct amd_cpudata *cpudata, u32 min_perf,
 			       u32 des_perf, u32 max_perf, bool fast_switch)
 {
@@ -275,19 +245,23 @@ static inline int amd_pstate_update_perf(struct amd_cpudata *cpudata,
 
 static int msr_set_epp(struct amd_cpudata *cpudata, u32 epp)
 {
-	u64 value = READ_ONCE(cpudata->cppc_req_cached);
+	u64 value, prev;
 	int ret;
 
+	value = prev = READ_ONCE(cpudata->cppc_req_cached);
 	value &= ~AMD_PSTATE_EPP_PERF_MASK;
 	value |= FIELD_PREP(AMD_PSTATE_EPP_PERF_MASK, epp);
 
+	if (value == prev)
+		return 0;
+
 	ret = wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value);
 	if (ret) {
 		pr_err("failed to set energy perf value (%d)\n", ret);
 		return ret;
 	}
 
-	cpudata->epp_cached = epp;
+	WRITE_ONCE(cpudata->epp_cached, epp);
 	WRITE_ONCE(cpudata->cppc_req_cached, value);
 
 	return ret;
@@ -305,13 +279,16 @@ static int shmem_set_epp(struct amd_cpudata *cpudata, u32 epp)
 	int ret;
 	struct cppc_perf_ctrls perf_ctrls;
 
+	if (epp == cpudata->epp_cached)
+		return 0;
+
 	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;
+	WRITE_ONCE(cpudata->epp_cached, epp);
 
 	return ret;
 }
@@ -1216,9 +1193,22 @@ static ssize_t show_energy_performance_preference(
 	struct amd_cpudata *cpudata = policy->driver_data;
 	int preference;
 
-	preference = amd_pstate_get_energy_pref_index(cpudata);
-	if (preference < 0)
-		return preference;
+	switch (cpudata->epp_cached) {
+	case AMD_CPPC_EPP_PERFORMANCE:
+		preference = EPP_INDEX_PERFORMANCE;
+		break;
+	case AMD_CPPC_EPP_BALANCE_PERFORMANCE:
+		preference = EPP_INDEX_BALANCE_PERFORMANCE;
+		break;
+	case AMD_CPPC_EPP_BALANCE_POWERSAVE:
+		preference = EPP_INDEX_BALANCE_POWERSAVE;
+		break;
+	case AMD_CPPC_EPP_POWERSAVE:
+		preference = EPP_INDEX_POWERSAVE;
+		break;
+	default:
+		return -EINVAL;
+	}
 
 	return sysfs_emit(buf, "%s\n", energy_perf_strings[preference]);
 }
@@ -1503,7 +1493,7 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 
 	policy->driver_data = cpudata;
 
-	cpudata->epp_cached = cpudata->epp_default = amd_pstate_get_epp(cpudata, 0);
+	cpudata->epp_cached = cpudata->epp_default = amd_pstate_get_epp(cpudata);
 
 	policy->min = policy->cpuinfo.min_freq;
 	policy->max = policy->cpuinfo.max_freq;
@@ -1557,35 +1547,26 @@ static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
 {
 	struct amd_cpudata *cpudata = policy->driver_data;
 	u64 value;
-	s16 epp;
 
 	amd_pstate_update_min_max_limit(policy);
 
 	value = READ_ONCE(cpudata->cppc_req_cached);
 
 	value &= ~(AMD_PSTATE_MAX_PERF_MASK | AMD_PSTATE_MIN_PERF_MASK |
-		   AMD_PSTATE_DES_PERF_MASK);
+		   AMD_PSTATE_DES_PERF_MASK | AMD_PSTATE_EPP_PERF_MASK);
 	value |= FIELD_PREP(AMD_PSTATE_MAX_PERF_MASK, cpudata->max_limit_perf);
 	value |= FIELD_PREP(AMD_PSTATE_DES_PERF_MASK, 0);
 	value |= FIELD_PREP(AMD_PSTATE_MIN_PERF_MASK, cpudata->min_limit_perf);
 
-	/* Get BIOS pre-defined epp value */
-	epp = amd_pstate_get_epp(cpudata, value);
-	if (epp < 0) {
-		/**
-		 * This return value can only be negative for shared_memory
-		 * systems where EPP register read/write not supported.
-		 */
-		return epp;
-	}
-
 	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
-		epp = 0;
+		WRITE_ONCE(cpudata->epp_cached, 0);
+	value |= FIELD_PREP(AMD_PSTATE_EPP_PERF_MASK, cpudata->epp_cached);
 
 	WRITE_ONCE(cpudata->cppc_req_cached, value);
 
 	if (trace_amd_pstate_epp_perf_enabled()) {
-		trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf, epp,
+		trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf,
+					  cpudata->epp_cached,
 					  cpudata->min_limit_perf,
 					  cpudata->max_limit_perf,
 					  cpudata->boost_state);
@@ -1594,7 +1575,7 @@ static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
 	amd_pstate_update_perf(cpudata, cpudata->min_limit_perf, 0U,
 			       cpudata->max_limit_perf, false);
 
-	return amd_pstate_set_epp(cpudata, epp);
+	return amd_pstate_set_epp(cpudata, READ_ONCE(cpudata->epp_cached));
 }
 
 static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy)
@@ -1610,6 +1591,8 @@ static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy)
 
 	cpudata->policy = policy->policy;
 
+	guard(mutex)(&amd_pstate_limits_lock);
+
 	ret = amd_pstate_epp_update_limit(policy);
 	if (ret)
 		return ret;
-- 
2.43.0

Re: [PATCH 11/15] cpufreq/amd-pstate: Cache EPP value and use that everywhere

[Gautham R. Shenoy]

Hello Mario,

On Thu, Dec 05, 2024 at 04:28:43PM -0600, Mario Limonciello wrote:
> Cache the value in cpudata->epp_cached, and use that for all callers.
> As all callers use cached value merge amd_pstate_get_energy_pref_index()
> into show_energy_performance_preference().
> 
> Check if the EPP value is changed before writing it to MSR or
> shared memory region.

The patch looks ok to me. Just one comment below:

[..snip..]

> @@ -1610,6 +1591,8 @@ static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy)
>  
>  	cpudata->policy = policy->policy;
>  
> +	guard(mutex)(&amd_pstate_limits_lock);
> +

Shouldn't this hunk be a different patch. The changelog doesn't say
anything about making amd_pstate_epp_update_limit() call while holding
the amd_pstate_limits_lock.


>  	ret = amd_pstate_epp_update_limit(policy);
>  	if (ret)
>  		return ret;
> -- 
> 2.43.0
>

For the rest of the patch

Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>

--
Thanks and Regards
gautham.

Re: [PATCH 11/15] cpufreq/amd-pstate: Cache EPP value and use that everywhere

[Mario Limonciello]

On 12/6/2024 10:14, Gautham R. Shenoy wrote:
> Hello Mario,
> 
> On Thu, Dec 05, 2024 at 04:28:43PM -0600, Mario Limonciello wrote:
>> Cache the value in cpudata->epp_cached, and use that for all callers.
>> As all callers use cached value merge amd_pstate_get_energy_pref_index()
>> into show_energy_performance_preference().
>>
>> Check if the EPP value is changed before writing it to MSR or
>> shared memory region.
> 
> The patch looks ok to me. Just one comment below:
> 
> [..snip..]
> 
>> @@ -1610,6 +1591,8 @@ static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy)
>>   
>>   	cpudata->policy = policy->policy;
>>   
>> +	guard(mutex)(&amd_pstate_limits_lock);
>> +
> 
> Shouldn't this hunk be a different patch. The changelog doesn't say
> anything about making amd_pstate_epp_update_limit() call while holding
> the amd_pstate_limits_lock.

I'll drop the hunk entirely.  I'm intending an overhaul of all the mutex 
handling code after this series is landed.

> 
> 
>>   	ret = amd_pstate_epp_update_limit(policy);
>>   	if (ret)
>>   		return ret;
>> -- 
>> 2.43.0
>>
> 
> For the rest of the patch
> 
> Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
Thx

> 
> --
> Thanks and Regards
> gautham.

[PATCH 12/15] cpufreq/amd-pstate: Always write EPP value when updating perf

[Mario Limonciello]

For MSR systems the EPP value is in the same register as perf targets
and so divding them into two separate MSR writes is wasteful.

In msr_update_perf(), update both EPP and perf values in one write to
MSR_AMD_CPPC_REQ, and cache them if successful.

To accomplish this plumb the EPP value into the update_perf call and modify
all its callers to check the return value.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 drivers/cpufreq/amd-pstate.c | 71 ++++++++++++++++++++++--------------
 1 file changed, 43 insertions(+), 28 deletions(-)

diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 20de3a9fd992d..8598f50e18b58 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -222,25 +222,36 @@ static s16 shmem_get_epp(struct amd_cpudata *cpudata)
 }
 
 static int msr_update_perf(struct amd_cpudata *cpudata, u32 min_perf,
-			       u32 des_perf, u32 max_perf, bool fast_switch)
+			   u32 des_perf, u32 max_perf, u32 epp, bool fast_switch)
 {
+	u64 value;
+
+	value = READ_ONCE(cpudata->cppc_req_cached);
 	if (fast_switch) {
 		wrmsrl(MSR_AMD_CPPC_REQ, READ_ONCE(cpudata->cppc_req_cached));
 		return 0;
+	} else {
+		int ret = wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ,
+					READ_ONCE(cpudata->cppc_req_cached));
+		if (ret)
+			return ret;
 	}
 
-	return wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ,
-			     READ_ONCE(cpudata->cppc_req_cached));
+	WRITE_ONCE(cpudata->cppc_req_cached, value);
+	WRITE_ONCE(cpudata->epp_cached, epp);
+
+	return 0;
 }
 
 DEFINE_STATIC_CALL(amd_pstate_update_perf, msr_update_perf);
 
 static inline int amd_pstate_update_perf(struct amd_cpudata *cpudata,
 					  u32 min_perf, u32 des_perf,
-					  u32 max_perf, bool fast_switch)
+					  u32 max_perf, u32 epp,
+					  bool fast_switch)
 {
 	return static_call(amd_pstate_update_perf)(cpudata, min_perf, des_perf,
-						   max_perf, fast_switch);
+						   max_perf, epp, fast_switch);
 }
 
 static int msr_set_epp(struct amd_cpudata *cpudata, u32 epp)
@@ -459,12 +470,19 @@ static inline int amd_pstate_init_perf(struct amd_cpudata *cpudata)
 	return static_call(amd_pstate_init_perf)(cpudata);
 }
 
-static int shmem_update_perf(struct amd_cpudata *cpudata,
-			     u32 min_perf, u32 des_perf,
-			     u32 max_perf, bool fast_switch)
+static int shmem_update_perf(struct amd_cpudata *cpudata, u32 min_perf,
+			     u32 des_perf, u32 max_perf, u32 epp, bool fast_switch)
 {
 	struct cppc_perf_ctrls perf_ctrls;
 
+	if (cppc_state == AMD_PSTATE_ACTIVE) {
+		int ret = shmem_set_epp(cpudata, epp);
+
+		if (ret)
+			return ret;
+		WRITE_ONCE(cpudata->epp_cached, epp);
+	}
+
 	perf_ctrls.max_perf = max_perf;
 	perf_ctrls.min_perf = min_perf;
 	perf_ctrls.desired_perf = des_perf;
@@ -545,10 +563,10 @@ static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf,
 
 	WRITE_ONCE(cpudata->cppc_req_cached, value);
 
-	amd_pstate_update_perf(cpudata, min_perf, des_perf,
-			       max_perf, fast_switch);
+	amd_pstate_update_perf(cpudata, min_perf, des_perf, max_perf, 0, fast_switch);
 
 cpufreq_policy_put:
+
 	cpufreq_cpu_put(policy);
 }
 
@@ -1547,6 +1565,7 @@ static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
 {
 	struct amd_cpudata *cpudata = policy->driver_data;
 	u64 value;
+	u32 epp;
 
 	amd_pstate_update_min_max_limit(policy);
 
@@ -1559,23 +1578,19 @@ static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
 	value |= FIELD_PREP(AMD_PSTATE_MIN_PERF_MASK, cpudata->min_limit_perf);
 
 	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
-		WRITE_ONCE(cpudata->epp_cached, 0);
-	value |= FIELD_PREP(AMD_PSTATE_EPP_PERF_MASK, cpudata->epp_cached);
-
-	WRITE_ONCE(cpudata->cppc_req_cached, value);
+		epp = 0;
+	else
+		epp = READ_ONCE(cpudata->epp_cached);
 
 	if (trace_amd_pstate_epp_perf_enabled()) {
-		trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf,
-					  cpudata->epp_cached,
+		trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf, epp,
 					  cpudata->min_limit_perf,
 					  cpudata->max_limit_perf,
 					  cpudata->boost_state);
 	}
 
-	amd_pstate_update_perf(cpudata, cpudata->min_limit_perf, 0U,
-			       cpudata->max_limit_perf, false);
-
-	return amd_pstate_set_epp(cpudata, READ_ONCE(cpudata->epp_cached));
+	return amd_pstate_update_perf(cpudata, cpudata->min_limit_perf, 0U,
+				      cpudata->max_limit_perf, epp, false);
 }
 
 static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy)
@@ -1606,7 +1621,7 @@ static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy)
 	return 0;
 }
 
-static void amd_pstate_epp_reenable(struct amd_cpudata *cpudata)
+static int amd_pstate_epp_reenable(struct amd_cpudata *cpudata)
 {
 	u64 max_perf;
 	int ret;
@@ -1624,17 +1639,19 @@ static void amd_pstate_epp_reenable(struct amd_cpudata *cpudata)
 					  max_perf, cpudata->boost_state);
 	}
 
-	amd_pstate_update_perf(cpudata, 0, 0, max_perf, false);
-	amd_pstate_set_epp(cpudata, cpudata->epp_cached);
+	return amd_pstate_update_perf(cpudata, 0, 0, max_perf, cpudata->epp_cached, false);
 }
 
 static int amd_pstate_epp_cpu_online(struct cpufreq_policy *policy)
 {
 	struct amd_cpudata *cpudata = policy->driver_data;
+	int ret;
 
 	pr_debug("AMD CPU Core %d going online\n", cpudata->cpu);
 
-	amd_pstate_epp_reenable(cpudata);
+	ret = amd_pstate_epp_reenable(cpudata);
+	if (ret)
+		return ret;
 	cpudata->suspended = false;
 
 	return 0;
@@ -1658,10 +1675,8 @@ static int amd_pstate_epp_cpu_offline(struct cpufreq_policy *policy)
 					  min_perf, min_perf, cpudata->boost_state);
 	}
 
-	amd_pstate_update_perf(cpudata, min_perf, 0, min_perf, false);
-	amd_pstate_set_epp(cpudata, AMD_CPPC_EPP_BALANCE_POWERSAVE);
-
-	return 0;
+	return amd_pstate_update_perf(cpudata, min_perf, 0, min_perf,
+				      AMD_CPPC_EPP_BALANCE_POWERSAVE, false);
 }
 
 static int amd_pstate_epp_suspend(struct cpufreq_policy *policy)
-- 
2.43.0

[PATCH 13/15] cpufreq/amd-pstate: Check if CPPC request has changed before writing to the MSR or shared memory

[Mario Limonciello]

Move the common MSR field formatting code to msr_update_perf() from
its callers.

Ensure that the MSR write is necessary before flushing a write out.
Also drop the comparison from the passive flow tracing.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 drivers/cpufreq/amd-pstate-trace.h |  7 +----
 drivers/cpufreq/amd-pstate.c       | 47 +++++++++++-------------------
 2 files changed, 18 insertions(+), 36 deletions(-)

diff --git a/drivers/cpufreq/amd-pstate-trace.h b/drivers/cpufreq/amd-pstate-trace.h
index e2221a4b6901c..8d692415d9050 100644
--- a/drivers/cpufreq/amd-pstate-trace.h
+++ b/drivers/cpufreq/amd-pstate-trace.h
@@ -32,7 +32,6 @@ TRACE_EVENT(amd_pstate_perf,
 		 u64 aperf,
 		 u64 tsc,
 		 unsigned int cpu_id,
-		 bool changed,
 		 bool fast_switch
 		 ),
 
@@ -44,7 +43,6 @@ TRACE_EVENT(amd_pstate_perf,
 		aperf,
 		tsc,
 		cpu_id,
-		changed,
 		fast_switch
 		),
 
@@ -57,7 +55,6 @@ TRACE_EVENT(amd_pstate_perf,
 		__field(unsigned long long, aperf)
 		__field(unsigned long long, tsc)
 		__field(unsigned int, cpu_id)
-		__field(bool, changed)
 		__field(bool, fast_switch)
 		),
 
@@ -70,11 +67,10 @@ TRACE_EVENT(amd_pstate_perf,
 		__entry->aperf = aperf;
 		__entry->tsc = tsc;
 		__entry->cpu_id = cpu_id;
-		__entry->changed = changed;
 		__entry->fast_switch = fast_switch;
 		),
 
-	TP_printk("amd_min_perf=%lu amd_des_perf=%lu amd_max_perf=%lu freq=%llu mperf=%llu aperf=%llu tsc=%llu cpu_id=%u changed=%s fast_switch=%s",
+	TP_printk("amd_min_perf=%lu amd_des_perf=%lu amd_max_perf=%lu freq=%llu mperf=%llu aperf=%llu tsc=%llu cpu_id=%u fast_switch=%s",
 		  (unsigned long)__entry->min_perf,
 		  (unsigned long)__entry->target_perf,
 		  (unsigned long)__entry->capacity,
@@ -83,7 +79,6 @@ TRACE_EVENT(amd_pstate_perf,
 		  (unsigned long long)__entry->aperf,
 		  (unsigned long long)__entry->tsc,
 		  (unsigned int)__entry->cpu_id,
-		  (__entry->changed) ? "true" : "false",
 		  (__entry->fast_switch) ? "true" : "false"
 		 )
 );
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 8598f50e18b58..06464e2dd905f 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -224,15 +224,26 @@ static s16 shmem_get_epp(struct amd_cpudata *cpudata)
 static int msr_update_perf(struct amd_cpudata *cpudata, u32 min_perf,
 			   u32 des_perf, u32 max_perf, u32 epp, bool fast_switch)
 {
-	u64 value;
+	u64 value, prev;
+
+	value = prev = READ_ONCE(cpudata->cppc_req_cached);
+
+	value &= ~(AMD_PSTATE_MAX_PERF_MASK | AMD_PSTATE_MIN_PERF_MASK |
+		   AMD_PSTATE_DES_PERF_MASK | AMD_PSTATE_EPP_PERF_MASK);
+	value |= FIELD_PREP(AMD_PSTATE_MAX_PERF_MASK, max_perf);
+	value |= FIELD_PREP(AMD_PSTATE_DES_PERF_MASK, des_perf);
+	value |= FIELD_PREP(AMD_PSTATE_MIN_PERF_MASK, min_perf);
+	value |= FIELD_PREP(AMD_PSTATE_EPP_PERF_MASK, epp);
+
+	if (value == prev)
+		return 0;
 
-	value = READ_ONCE(cpudata->cppc_req_cached);
 	if (fast_switch) {
-		wrmsrl(MSR_AMD_CPPC_REQ, READ_ONCE(cpudata->cppc_req_cached));
+		wrmsrl(MSR_AMD_CPPC_REQ, value);
 		return 0;
 	} else {
-		int ret = wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ,
-					READ_ONCE(cpudata->cppc_req_cached));
+		int ret = wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value);
+
 		if (ret)
 			return ret;
 	}
@@ -528,9 +539,7 @@ static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf,
 {
 	unsigned long max_freq;
 	struct cpufreq_policy *policy = cpufreq_cpu_get(cpudata->cpu);
-	u64 prev = READ_ONCE(cpudata->cppc_req_cached);
 	u32 nominal_perf = READ_ONCE(cpudata->nominal_perf);
-	u64 value = prev;
 
 	des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf);
 
@@ -546,27 +555,14 @@ static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf,
 	if (!cpudata->boost_supported)
 		max_perf = min_t(unsigned long, nominal_perf, max_perf);
 
-	value &= ~(AMD_PSTATE_MAX_PERF_MASK | AMD_PSTATE_MIN_PERF_MASK |
-		   AMD_PSTATE_DES_PERF_MASK);
-	value |= FIELD_PREP(AMD_PSTATE_MAX_PERF_MASK, max_perf);
-	value |= FIELD_PREP(AMD_PSTATE_DES_PERF_MASK, des_perf);
-	value |= FIELD_PREP(AMD_PSTATE_MIN_PERF_MASK, min_perf);
-
 	if (trace_amd_pstate_perf_enabled() && amd_pstate_sample(cpudata)) {
 		trace_amd_pstate_perf(min_perf, des_perf, max_perf, cpudata->freq,
 			cpudata->cur.mperf, cpudata->cur.aperf, cpudata->cur.tsc,
-				cpudata->cpu, (value != prev), fast_switch);
+				cpudata->cpu, fast_switch);
 	}
 
-	if (value == prev)
-		goto cpufreq_policy_put;
-
-	WRITE_ONCE(cpudata->cppc_req_cached, value);
-
 	amd_pstate_update_perf(cpudata, min_perf, des_perf, max_perf, 0, fast_switch);
 
-cpufreq_policy_put:
-
 	cpufreq_cpu_put(policy);
 }
 
@@ -1564,19 +1560,10 @@ static void amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy)
 static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
 {
 	struct amd_cpudata *cpudata = policy->driver_data;
-	u64 value;
 	u32 epp;
 
 	amd_pstate_update_min_max_limit(policy);
 
-	value = READ_ONCE(cpudata->cppc_req_cached);
-
-	value &= ~(AMD_PSTATE_MAX_PERF_MASK | AMD_PSTATE_MIN_PERF_MASK |
-		   AMD_PSTATE_DES_PERF_MASK | AMD_PSTATE_EPP_PERF_MASK);
-	value |= FIELD_PREP(AMD_PSTATE_MAX_PERF_MASK, cpudata->max_limit_perf);
-	value |= FIELD_PREP(AMD_PSTATE_DES_PERF_MASK, 0);
-	value |= FIELD_PREP(AMD_PSTATE_MIN_PERF_MASK, cpudata->min_limit_perf);
-
 	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
 		epp = 0;
 	else
-- 
2.43.0

[PATCH 14/15] cpufreq/amd-pstate: Drop ret variable from amd_pstate_set_energy_pref_index()

[Mario Limonciello]

The ret variable is not necessary.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 drivers/cpufreq/amd-pstate.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 06464e2dd905f..b361e691fd33e 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -318,13 +318,11 @@ static int shmem_set_epp(struct amd_cpudata *cpudata, u32 epp)
 static int amd_pstate_set_energy_pref_index(struct amd_cpudata *cpudata,
 		int pref_index)
 {
-	int epp = -EINVAL;
-	int ret;
+	int epp;
 
 	if (!pref_index)
 		epp = cpudata->epp_default;
-
-	if (epp == -EINVAL)
+	else
 		epp = epp_values[pref_index];
 
 	if (epp > 0 && cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) {
@@ -340,9 +338,7 @@ static int amd_pstate_set_energy_pref_index(struct amd_cpudata *cpudata,
 					  cpudata->boost_state);
 	}
 
-	ret = amd_pstate_set_epp(cpudata, epp);
-
-	return ret;
+	return amd_pstate_set_epp(cpudata, epp);
 }
 
 static inline int msr_cppc_enable(bool enable)
-- 
2.43.0

[PATCH 15/15] cpufreq/amd-pstate: Set different default EPP policy for Epyc and Ryzen

[Mario Limonciello]

For Ryzen systems the EPP policy set by the BIOS is generally configured
to performance as this is the default register value for the CPPC request
MSR.

If a user doesn't use additional software to configure EPP then the system
will default biased towards performance and consume extra battery. Instead
configure the default to "balanced_performance" for this case.

Suggested-by: Artem S. Tashkinov <aros@gmx.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219526
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 drivers/cpufreq/amd-pstate.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index b361e691fd33e..57775839a1c44 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -1503,8 +1503,6 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 
 	policy->driver_data = cpudata;
 
-	cpudata->epp_cached = cpudata->epp_default = amd_pstate_get_epp(cpudata);
-
 	policy->min = policy->cpuinfo.min_freq;
 	policy->max = policy->cpuinfo.max_freq;
 
@@ -1515,10 +1513,13 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 	 * the default cpufreq governor is neither powersave nor performance.
 	 */
 	if (amd_pstate_acpi_pm_profile_server() ||
-	    amd_pstate_acpi_pm_profile_undefined())
+	    amd_pstate_acpi_pm_profile_undefined()) {
 		policy->policy = CPUFREQ_POLICY_PERFORMANCE;
-	else
+		cpudata->epp_default = amd_pstate_get_epp(cpudata);
+	} else {
 		policy->policy = CPUFREQ_POLICY_POWERSAVE;
+		cpudata->epp_default = AMD_CPPC_EPP_BALANCE_PERFORMANCE;
+	}
 
 	if (cpu_feature_enabled(X86_FEATURE_CPPC)) {
 		ret = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, &value);
@@ -1531,6 +1532,9 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 			return ret;
 		WRITE_ONCE(cpudata->cppc_cap1_cached, value);
 	}
+	ret = amd_pstate_set_epp(cpudata, cpudata->epp_default);
+	if (ret)
+		return ret;
 
 	current_pstate_driver->adjust_perf = NULL;
 
-- 
2.43.0