This patch set adds support for two features to get a finer control
over the impact of Thermal Throttling on performance.
1) Patch 1: Adds support to read Thermal fast Sampling Period (_TFP)
ACPI object and use it over "Thermal Sampling Period (_TSP)" for
Passive cooling if both are present.
2) Patch 2: Adds support to reduce the CPUFREQ reduction percentage
and not always cause throttling in steps of "20%".
Both patches can be applied independently.
---
v1[1] -> v2:
- Patch 1: add ACPI spec section info in commit description and rebased.
- Patch 2: add info about hardware in the commit description.
- Patch 2: switched CPUFREQ THERMAL tuning macros to static variables.
- Patch 2: update the tunings for Tegra241 SoC only using soc_id check.
Jeff Brasen (1):
ACPI: thermal: Add Thermal fast Sampling Period (_TFP) support
Srikar Srimath Tirumala (1):
ACPI: processor: reduce CPUFREQ thermal reduction pctg for Tegra241
drivers/acpi/processor_thermal.c | 41 +++++++++++++++++++++++++++++---
drivers/acpi/thermal.c | 25 ++++++++++---------
2 files changed, 52 insertions(+), 14 deletions(-)
[1] https://lore.kernel.org/lkml/[email protected]/
--
2.17.1
From: Srikar Srimath Tirumala <[email protected]>
Current implementation of processor_thermal performs software throttling
in fixed steps of "20%" which can be too coarse for some platforms.
We observed some performance gain after reducing the throttle percentage.
Change the CPUFREQ thermal reduction percentage and maximum thermal steps
to be configurable. Also, update the default values of both for Nvidia
Tegra241 (Grace) SoC. The thermal reduction percentage is reduced to "5%"
and accordingly the maximum number of thermal steps are increased as they
are derived from the reduction percentage.
Signed-off-by: Srikar Srimath Tirumala <[email protected]>
Signed-off-by: Sumit Gupta <[email protected]>
---
drivers/acpi/processor_thermal.c | 41 +++++++++++++++++++++++++++++---
1 file changed, 38 insertions(+), 3 deletions(-)
diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c
index b7c6287eccca..30f2801abce6 100644
--- a/drivers/acpi/processor_thermal.c
+++ b/drivers/acpi/processor_thermal.c
@@ -26,7 +26,16 @@
*/
#define CPUFREQ_THERMAL_MIN_STEP 0
-#define CPUFREQ_THERMAL_MAX_STEP 3
+
+static int cpufreq_thermal_max_step = 3;
+
+/*
+ * Minimum throttle percentage for processor_thermal cooling device.
+ * The processor_thermal driver uses it to calculate the percentage amount by
+ * which cpu frequency must be reduced for each cooling state. This is also used
+ * to calculate the maximum number of throttling steps or cooling states.
+ */
+static int cpufreq_thermal_pctg = 20;
static DEFINE_PER_CPU(unsigned int, cpufreq_thermal_reduction_pctg);
@@ -71,7 +80,7 @@ static int cpufreq_get_max_state(unsigned int cpu)
if (!cpu_has_cpufreq(cpu))
return 0;
- return CPUFREQ_THERMAL_MAX_STEP;
+ return cpufreq_thermal_max_step;
}
static int cpufreq_get_cur_state(unsigned int cpu)
@@ -113,7 +122,8 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state)
if (!policy)
return -EINVAL;
- max_freq = (policy->cpuinfo.max_freq * (100 - reduction_pctg(i) * 20)) / 100;
+ max_freq = (policy->cpuinfo.max_freq *
+ (100 - reduction_pctg(i) * cpufreq_thermal_pctg)) / 100;
cpufreq_cpu_put(policy);
@@ -126,10 +136,35 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state)
return 0;
}
+#define SMCCC_SOC_ID_T241 0x036b0241
+
+void acpi_thermal_cpufreq_config_nvidia(void)
+{
+#ifdef CONFIG_HAVE_ARM_SMCCC_DISCOVERY
+ s32 soc_id = arm_smccc_get_soc_id_version();
+
+ /* Check JEP106 code for NVIDIA Tegra241 chip (036b:0241) */
+ if ((soc_id < 0) || (soc_id != SMCCC_SOC_ID_T241))
+ return;
+
+ /* Reduce the CPUFREQ Thermal reduction percentage to 5% */
+ cpufreq_thermal_pctg = 5;
+
+ /*
+ * Derive the MAX_STEP from minimum throttle percentage so that the reduction
+ * percentage doesn't end up becoming negative. Also, cap the MAX_STEP so that
+ * the CPU performance doesn't become 0.
+ */
+ cpufreq_thermal_max_step = ((100 / cpufreq_thermal_pctg) - 1);
+#endif
+}
+
void acpi_thermal_cpufreq_init(struct cpufreq_policy *policy)
{
unsigned int cpu;
+ acpi_thermal_cpufreq_config_nvidia();
+
for_each_cpu(cpu, policy->related_cpus) {
struct acpi_processor *pr = per_cpu(processors, cpu);
int ret;
--
2.17.1
From: Jeff Brasen <[email protected]>
Add support of "Thermal fast Sampling Period (_TFP)" for Passive cooling.
As per [1], _TFP overrides the "Thermal Sampling Period (_TSP)" if both
are present in a Thermal zone.
[1] ACPI Specification 6.4 - section 11.4.17. _TFP (Thermal fast Sampling
Period)"
Signed-off-by: Jeff Brasen <[email protected]>
Signed-off-by: Sumit Gupta <[email protected]>
---
drivers/acpi/thermal.c | 25 ++++++++++++++-----------
1 file changed, 14 insertions(+), 11 deletions(-)
diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index f14e68266ccd..d0bbf42cae9c 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -102,7 +102,7 @@ struct acpi_thermal_passive {
struct acpi_handle_list devices;
unsigned long tc1;
unsigned long tc2;
- unsigned long tsp;
+ unsigned long passive_delay;
};
struct acpi_thermal_active {
@@ -287,11 +287,17 @@ static void __acpi_thermal_trips_update(struct acpi_thermal *tz, int flag)
tz->trips.passive.tc2 = tmp;
status = acpi_evaluate_integer(tz->device->handle,
- "_TSP", NULL, &tmp);
- if (ACPI_FAILURE(status))
- tz->trips.passive.trip.valid = false;
- else
- tz->trips.passive.tsp = tmp;
+ "_TFP", NULL, &tmp);
+ if (ACPI_FAILURE(status)) {
+ status = acpi_evaluate_integer(tz->device->handle,
+ "_TSP", NULL, &tmp);
+ if (ACPI_FAILURE(status))
+ tz->trips.passive.trip.valid = false;
+ else
+ tz->trips.passive.passive_delay = tmp * 100;
+ } else {
+ tz->trips.passive.passive_delay = tmp;
+ }
}
}
}
@@ -683,7 +689,6 @@ static int acpi_thermal_register_thermal_zone(struct acpi_thermal *tz)
{
struct acpi_thermal_trip *acpi_trip;
struct thermal_trip *trip;
- int passive_delay = 0;
int trip_count = 0;
int result;
int i;
@@ -694,10 +699,8 @@ static int acpi_thermal_register_thermal_zone(struct acpi_thermal *tz)
if (tz->trips.hot.valid)
trip_count++;
- if (tz->trips.passive.trip.valid) {
+ if (tz->trips.passive.trip.valid)
trip_count++;
- passive_delay = tz->trips.passive.tsp * 100;
- }
for (i = 0; i < ACPI_THERMAL_MAX_ACTIVE && tz->trips.active[i].trip.valid; i++)
trip_count++;
@@ -746,7 +749,7 @@ static int acpi_thermal_register_thermal_zone(struct acpi_thermal *tz)
0, tz,
&acpi_thermal_zone_ops,
NULL,
- passive_delay,
+ tz->trips.passive.passive_delay,
tz->polling_frequency * 100);
if (IS_ERR(tz->thermal_zone)) {
result = PTR_ERR(tz->thermal_zone);
--
2.17.1
Hi Sumit,
kernel test robot noticed the following build warnings:
[auto build test WARNING on rafael-pm/linux-next]
[also build test WARNING on linus/master v6.6-rc1 next-20230913]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Sumit-Gupta/ACPI-thermal-Add-Thermal-fast-Sampling-Period-_TFP-support/20230914-004929
base: https://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git linux-next
patch link: https://lore.kernel.org/r/20230913164659.9345-3-sumitg%40nvidia.com
patch subject: [Patch v2 2/2] ACPI: processor: reduce CPUFREQ thermal reduction pctg for Tegra241
config: i386-defconfig (https://download.01.org/0day-ci/archive/20230914/[email protected]/config)
compiler: gcc-7 (Ubuntu 7.5.0-6ubuntu2) 7.5.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20230914/[email protected]/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 <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
All warnings (new ones prefixed by >>):
>> drivers/acpi/processor_thermal.c:141:6: warning: no previous declaration for 'acpi_thermal_cpufreq_config_nvidia' [-Wmissing-declarations]
void acpi_thermal_cpufreq_config_nvidia(void)
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
vim +/acpi_thermal_cpufreq_config_nvidia +141 drivers/acpi/processor_thermal.c
140
> 141 void acpi_thermal_cpufreq_config_nvidia(void)
142 {
143 #ifdef CONFIG_HAVE_ARM_SMCCC_DISCOVERY
144 s32 soc_id = arm_smccc_get_soc_id_version();
145
146 /* Check JEP106 code for NVIDIA Tegra241 chip (036b:0241) */
147 if ((soc_id < 0) || (soc_id != SMCCC_SOC_ID_T241))
148 return;
149
150 /* Reduce the CPUFREQ Thermal reduction percentage to 5% */
151 cpufreq_thermal_pctg = 5;
152
153 /*
154 * Derive the MAX_STEP from minimum throttle percentage so that the reduction
155 * percentage doesn't end up becoming negative. Also, cap the MAX_STEP so that
156 * the CPU performance doesn't become 0.
157 */
158 cpufreq_thermal_max_step = ((100 / cpufreq_thermal_pctg) - 1);
159 #endif
160 }
161
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
Hi Sumit,
kernel test robot noticed the following build warnings:
[auto build test WARNING on rafael-pm/linux-next]
[also build test WARNING on linus/master v6.6-rc1 next-20230913]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Sumit-Gupta/ACPI-thermal-Add-Thermal-fast-Sampling-Period-_TFP-support/20230914-004929
base: https://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git linux-next
patch link: https://lore.kernel.org/r/20230913164659.9345-3-sumitg%40nvidia.com
patch subject: [Patch v2 2/2] ACPI: processor: reduce CPUFREQ thermal reduction pctg for Tegra241
config: arm64-defconfig (https://download.01.org/0day-ci/archive/20230914/[email protected]/config)
compiler: aarch64-linux-gcc (GCC) 13.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20230914/[email protected]/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 <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
All warnings (new ones prefixed by >>):
>> drivers/acpi/processor_thermal.c:141:6: warning: no previous prototype for 'acpi_thermal_cpufreq_config_nvidia' [-Wmissing-prototypes]
141 | void acpi_thermal_cpufreq_config_nvidia(void)
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
vim +/acpi_thermal_cpufreq_config_nvidia +141 drivers/acpi/processor_thermal.c
140
> 141 void acpi_thermal_cpufreq_config_nvidia(void)
142 {
143 #ifdef CONFIG_HAVE_ARM_SMCCC_DISCOVERY
144 s32 soc_id = arm_smccc_get_soc_id_version();
145
146 /* Check JEP106 code for NVIDIA Tegra241 chip (036b:0241) */
147 if ((soc_id < 0) || (soc_id != SMCCC_SOC_ID_T241))
148 return;
149
150 /* Reduce the CPUFREQ Thermal reduction percentage to 5% */
151 cpufreq_thermal_pctg = 5;
152
153 /*
154 * Derive the MAX_STEP from minimum throttle percentage so that the reduction
155 * percentage doesn't end up becoming negative. Also, cap the MAX_STEP so that
156 * the CPU performance doesn't become 0.
157 */
158 cpufreq_thermal_max_step = ((100 / cpufreq_thermal_pctg) - 1);
159 #endif
160 }
161
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
Hi Sumit,
kernel test robot noticed the following build warnings:
[auto build test WARNING on rafael-pm/linux-next]
[also build test WARNING on linus/master v6.6-rc1 next-20230913]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Sumit-Gupta/ACPI-thermal-Add-Thermal-fast-Sampling-Period-_TFP-support/20230914-004929
base: https://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git linux-next
patch link: https://lore.kernel.org/r/20230913164659.9345-3-sumitg%40nvidia.com
patch subject: [Patch v2 2/2] ACPI: processor: reduce CPUFREQ thermal reduction pctg for Tegra241
config: i386-randconfig-062-20230914 (https://download.01.org/0day-ci/archive/20230914/[email protected]/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/20230914/[email protected]/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 <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
sparse warnings: (new ones prefixed by >>)
>> drivers/acpi/processor_thermal.c:141:6: sparse: sparse: symbol 'acpi_thermal_cpufreq_config_nvidia' was not declared. Should it be static?
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
On Tue, Sep 19, 2023 at 1:27 PM Sumit Gupta <[email protected]> wrote:
>
>
>
> > Hi Sumit,
> >
> > kernel test robot noticed the following build warnings:
> >
> > [auto build test WARNING on rafael-pm/linux-next]
> > [also build test WARNING on linus/master v6.6-rc1 next-20230913]
> > [If your patch is applied to the wrong git tree, kindly drop us a note.
> > And when submitting patch, we suggest to use '--base' as documented in
> > https://git-scm.com/docs/git-format-patch#_base_tree_information]
> >
> > url: https://github.com/intel-lab-lkp/linux/commits/Sumit-Gupta/ACPI-thermal-Add-Thermal-fast-Sampling-Period-_TFP-support/20230914-004929
> > base: https://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git linux-next
> > patch link: https://lore.kernel.org/r/20230913164659.9345-3-sumitg%40nvidia.com
> > patch subject: [Patch v2 2/2] ACPI: processor: reduce CPUFREQ thermal reduction pctg for Tegra241
> > config: i386-defconfig (https://download.01.org/0day-ci/archive/20230914/[email protected]/config)
> > compiler: gcc-7 (Ubuntu 7.5.0-6ubuntu2) 7.5.0
> > reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20230914/[email protected]/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 <[email protected]>
> > | Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
> >
> > All warnings (new ones prefixed by >>):
> >
> >>> drivers/acpi/processor_thermal.c:141:6: warning: no previous declaration for 'acpi_thermal_cpufreq_config_nvidia' [-Wmissing-declarations]
> > void acpi_thermal_cpufreq_config_nvidia(void)
> > ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> >
>
> Thank you for the report.
> The below change fixes the warning for me.
>
> -void acpi_thermal_cpufreq_config_nvidia(void)
> +static void acpi_thermal_cpufreq_config_nvidia(void)
>
>
> Hi Rafael,
> If there is no other comment. Could you please add the change while
> applying or you prefer me sending new version ?
Please update.
Besides, I haven't said that I will apply it without changes yet.
Thanks!
> Hi Sumit,
>
> kernel test robot noticed the following build warnings:
>
> [auto build test WARNING on rafael-pm/linux-next]
> [also build test WARNING on linus/master v6.6-rc1 next-20230913]
> [If your patch is applied to the wrong git tree, kindly drop us a note.
> And when submitting patch, we suggest to use '--base' as documented in
> https://git-scm.com/docs/git-format-patch#_base_tree_information]
>
> url: https://github.com/intel-lab-lkp/linux/commits/Sumit-Gupta/ACPI-thermal-Add-Thermal-fast-Sampling-Period-_TFP-support/20230914-004929
> base: https://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git linux-next
> patch link: https://lore.kernel.org/r/20230913164659.9345-3-sumitg%40nvidia.com
> patch subject: [Patch v2 2/2] ACPI: processor: reduce CPUFREQ thermal reduction pctg for Tegra241
> config: i386-defconfig (https://download.01.org/0day-ci/archive/20230914/[email protected]/config)
> compiler: gcc-7 (Ubuntu 7.5.0-6ubuntu2) 7.5.0
> reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20230914/[email protected]/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 <[email protected]>
> | Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
>
> All warnings (new ones prefixed by >>):
>
>>> drivers/acpi/processor_thermal.c:141:6: warning: no previous declaration for 'acpi_thermal_cpufreq_config_nvidia' [-Wmissing-declarations]
> void acpi_thermal_cpufreq_config_nvidia(void)
> ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
>
Thank you for the report.
The below change fixes the warning for me.
-void acpi_thermal_cpufreq_config_nvidia(void)
+static void acpi_thermal_cpufreq_config_nvidia(void)
Hi Rafael,
If there is no other comment. Could you please add the change while
applying or you prefer me sending new version ?
Thank you,
Sumit Gupta
>
> vim +/acpi_thermal_cpufreq_config_nvidia +141 drivers/acpi/processor_thermal.c
>
> 140
> > 141 void acpi_thermal_cpufreq_config_nvidia(void)
> 142 {
> 143 #ifdef CONFIG_HAVE_ARM_SMCCC_DISCOVERY
> 144 s32 soc_id = arm_smccc_get_soc_id_version();
> 145
> 146 /* Check JEP106 code for NVIDIA Tegra241 chip (036b:0241) */
> 147 if ((soc_id < 0) || (soc_id != SMCCC_SOC_ID_T241))
> 148 return;
> 149
> 150 /* Reduce the CPUFREQ Thermal reduction percentage to 5% */
> 151 cpufreq_thermal_pctg = 5;
> 152
> 153 /*
> 154 * Derive the MAX_STEP from minimum throttle percentage so that the reduction
> 155 * percentage doesn't end up becoming negative. Also, cap the MAX_STEP so that
> 156 * the CPU performance doesn't become 0.
> 157 */
> 158 cpufreq_thermal_max_step = ((100 / cpufreq_thermal_pctg) - 1);
> 159 #endif
> 160 }
> 161
>
> --
> 0-DAY CI Kernel Test Service
> https://github.com/intel/lkp-tests/wiki
>>
>>> Hi Sumit,
>>>
>>> kernel test robot noticed the following build warnings:
>>>
>>> [auto build test WARNING on rafael-pm/linux-next]
>>> [also build test WARNING on linus/master v6.6-rc1 next-20230913]
>>> [If your patch is applied to the wrong git tree, kindly drop us a note.
>>> And when submitting patch, we suggest to use '--base' as documented in
>>> https://git-scm.com/docs/git-format-patch#_base_tree_information]
>>>
>>> url: https://github.com/intel-lab-lkp/linux/commits/Sumit-Gupta/ACPI-thermal-Add-Thermal-fast-Sampling-Period-_TFP-support/20230914-004929
>>> base: https://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git linux-next
>>> patch link: https://lore.kernel.org/r/20230913164659.9345-3-sumitg%40nvidia.com
>>> patch subject: [Patch v2 2/2] ACPI: processor: reduce CPUFREQ thermal reduction pctg for Tegra241
>>> config: i386-defconfig (https://download.01.org/0day-ci/archive/20230914/[email protected]/config)
>>> compiler: gcc-7 (Ubuntu 7.5.0-6ubuntu2) 7.5.0
>>> reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20230914/[email protected]/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 <[email protected]>
>>> | Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
>>>
>>> All warnings (new ones prefixed by >>):
>>>
>>>>> drivers/acpi/processor_thermal.c:141:6: warning: no previous declaration for 'acpi_thermal_cpufreq_config_nvidia' [-Wmissing-declarations]
>>> void acpi_thermal_cpufreq_config_nvidia(void)
>>> ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
>>>
>>
>> Thank you for the report.
>> The below change fixes the warning for me.
>>
>> -void acpi_thermal_cpufreq_config_nvidia(void)
>> +static void acpi_thermal_cpufreq_config_nvidia(void)
>>
>>
>> Hi Rafael,
>> If there is no other comment. Could you please add the change while
>> applying or you prefer me sending new version ?
>
> Please update.
>
> Besides, I haven't said that I will apply it without changes yet.
>
> Thanks!
Sure, will wait for more comments and add this change in v2.
Thank you,
Sumit Gupta
On Wed, Sep 13, 2023 at 6:47 PM Sumit Gupta <[email protected]> wrote:
>
> From: Srikar Srimath Tirumala <[email protected]>
>
> Current implementation of processor_thermal performs software throttling
> in fixed steps of "20%" which can be too coarse for some platforms.
> We observed some performance gain after reducing the throttle percentage.
> Change the CPUFREQ thermal reduction percentage and maximum thermal steps
> to be configurable. Also, update the default values of both for Nvidia
> Tegra241 (Grace) SoC. The thermal reduction percentage is reduced to "5%"
> and accordingly the maximum number of thermal steps are increased as they
> are derived from the reduction percentage.
>
> Signed-off-by: Srikar Srimath Tirumala <[email protected]>
> Signed-off-by: Sumit Gupta <[email protected]>
> ---
> drivers/acpi/processor_thermal.c | 41 +++++++++++++++++++++++++++++---
> 1 file changed, 38 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c
> index b7c6287eccca..30f2801abce6 100644
> --- a/drivers/acpi/processor_thermal.c
> +++ b/drivers/acpi/processor_thermal.c
> @@ -26,7 +26,16 @@
> */
>
> #define CPUFREQ_THERMAL_MIN_STEP 0
> -#define CPUFREQ_THERMAL_MAX_STEP 3
> +
> +static int cpufreq_thermal_max_step = 3;
__read_mostly I suppose?
> +
> +/*
> + * Minimum throttle percentage for processor_thermal cooling device.
+ *
> + * The processor_thermal driver uses it to calculate the percentage amount by
> + * which cpu frequency must be reduced for each cooling state. This is also used
> + * to calculate the maximum number of throttling steps or cooling states.
> + */
> +static int cpufreq_thermal_pctg = 20;
__read_mostly here too?
>
> static DEFINE_PER_CPU(unsigned int, cpufreq_thermal_reduction_pctg);
>
> @@ -71,7 +80,7 @@ static int cpufreq_get_max_state(unsigned int cpu)
> if (!cpu_has_cpufreq(cpu))
> return 0;
>
> - return CPUFREQ_THERMAL_MAX_STEP;
> + return cpufreq_thermal_max_step;
> }
>
> static int cpufreq_get_cur_state(unsigned int cpu)
> @@ -113,7 +122,8 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state)
> if (!policy)
> return -EINVAL;
>
> - max_freq = (policy->cpuinfo.max_freq * (100 - reduction_pctg(i) * 20)) / 100;
> + max_freq = (policy->cpuinfo.max_freq *
> + (100 - reduction_pctg(i) * cpufreq_thermal_pctg)) / 100;
>
> cpufreq_cpu_put(policy);
>
> @@ -126,10 +136,35 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state)
> return 0;
> }
>
#ifdef CONFIG_HAVE_ARM_SMCCC_DISCOVERY
> +#define SMCCC_SOC_ID_T241 0x036b0241
> +
> +void acpi_thermal_cpufreq_config_nvidia(void)
static void ?
> +{
> +#ifdef CONFIG_HAVE_ARM_SMCCC_DISCOVERY
> + s32 soc_id = arm_smccc_get_soc_id_version();
> +
> + /* Check JEP106 code for NVIDIA Tegra241 chip (036b:0241) */
> + if ((soc_id < 0) || (soc_id != SMCCC_SOC_ID_T241))
Inner parens are redundant.
> + return;
> +
> + /* Reduce the CPUFREQ Thermal reduction percentage to 5% */
> + cpufreq_thermal_pctg = 5;
> +
> + /*
> + * Derive the MAX_STEP from minimum throttle percentage so that the reduction
> + * percentage doesn't end up becoming negative. Also, cap the MAX_STEP so that
> + * the CPU performance doesn't become 0.
> + */
> + cpufreq_thermal_max_step = ((100 / cpufreq_thermal_pctg) - 1);
Outer parens are redundant.
> +#endif
> +}
#else
static inline void void acpi_thermal_cpufreq_config_nvidia(void) {}
#endif
> +
> void acpi_thermal_cpufreq_init(struct cpufreq_policy *policy)
> {
> unsigned int cpu;
>
> + acpi_thermal_cpufreq_config_nvidia();
> +
> for_each_cpu(cpu, policy->related_cpus) {
> struct acpi_processor *pr = per_cpu(processors, cpu);
> int ret;
> --
And patch [1/2] needs to be rebased on the current ACPI thermal
material in linux-next.
Thanks!
On 04/10/23 01:07, Rafael J. Wysocki wrote:
> External email: Use caution opening links or attachments
>
>
> On Wed, Sep 13, 2023 at 6:47 PM Sumit Gupta <[email protected]> wrote:
>>
>> From: Srikar Srimath Tirumala <[email protected]>
>>
>> Current implementation of processor_thermal performs software throttling
>> in fixed steps of "20%" which can be too coarse for some platforms.
>> We observed some performance gain after reducing the throttle percentage.
>> Change the CPUFREQ thermal reduction percentage and maximum thermal steps
>> to be configurable. Also, update the default values of both for Nvidia
>> Tegra241 (Grace) SoC. The thermal reduction percentage is reduced to "5%"
>> and accordingly the maximum number of thermal steps are increased as they
>> are derived from the reduction percentage.
>>
>> Signed-off-by: Srikar Srimath Tirumala <[email protected]>
>> Signed-off-by: Sumit Gupta <[email protected]>
>> ---
>> drivers/acpi/processor_thermal.c | 41 +++++++++++++++++++++++++++++---
>> 1 file changed, 38 insertions(+), 3 deletions(-)
>>
>> diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c
>> index b7c6287eccca..30f2801abce6 100644
>> --- a/drivers/acpi/processor_thermal.c
>> +++ b/drivers/acpi/processor_thermal.c
>> @@ -26,7 +26,16 @@
>> */
>>
>> #define CPUFREQ_THERMAL_MIN_STEP 0
>> -#define CPUFREQ_THERMAL_MAX_STEP 3
>> +
>> +static int cpufreq_thermal_max_step = 3;
>
> __read_mostly I suppose?
>
Added in v3.
>> +
>> +/*
>> + * Minimum throttle percentage for processor_thermal cooling device.
>
> + *
>
>> + * The processor_thermal driver uses it to calculate the percentage amount by
>> + * which cpu frequency must be reduced for each cooling state. This is also used
>> + * to calculate the maximum number of throttling steps or cooling states.
>> + */
>> +static int cpufreq_thermal_pctg = 20;
>
> __read_mostly here too?
>
Added in v3.
>>
>> static DEFINE_PER_CPU(unsigned int, cpufreq_thermal_reduction_pctg);
>>
>> @@ -71,7 +80,7 @@ static int cpufreq_get_max_state(unsigned int cpu)
>> if (!cpu_has_cpufreq(cpu))
>> return 0;
>>
>> - return CPUFREQ_THERMAL_MAX_STEP;
>> + return cpufreq_thermal_max_step;
>> }
>>
>> static int cpufreq_get_cur_state(unsigned int cpu)
>> @@ -113,7 +122,8 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state)
>> if (!policy)
>> return -EINVAL;
>>
>> - max_freq = (policy->cpuinfo.max_freq * (100 - reduction_pctg(i) * 20)) / 100;
>> + max_freq = (policy->cpuinfo.max_freq *
>> + (100 - reduction_pctg(i) * cpufreq_thermal_pctg)) / 100;
>>
>> cpufreq_cpu_put(policy);
>>
>> @@ -126,10 +136,35 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state)
>> return 0;
>> }
>>
>
> #ifdef CONFIG_HAVE_ARM_SMCCC_DISCOVERY
>
>> +#define SMCCC_SOC_ID_T241 0x036b0241
>> +
>> +void acpi_thermal_cpufreq_config_nvidia(void)
>
> static void ?
>
Added in v3.
>> +{
>> +#ifdef CONFIG_HAVE_ARM_SMCCC_DISCOVERY
>> + s32 soc_id = arm_smccc_get_soc_id_version();
>> +
>> + /* Check JEP106 code for NVIDIA Tegra241 chip (036b:0241) */
>> + if ((soc_id < 0) || (soc_id != SMCCC_SOC_ID_T241))
>
> Inner parens are redundant.
>
Removed in v3.
>> + return;
>> +
>> + /* Reduce the CPUFREQ Thermal reduction percentage to 5% */
>> + cpufreq_thermal_pctg = 5;
>> +
>> + /*
>> + * Derive the MAX_STEP from minimum throttle percentage so that the reduction
>> + * percentage doesn't end up becoming negative. Also, cap the MAX_STEP so that
>> + * the CPU performance doesn't become 0.
>> + */
>> + cpufreq_thermal_max_step = ((100 / cpufreq_thermal_pctg) - 1);
>
> Outer parens are redundant.
>
ACK.
>> +#endif
>> +}
>
> #else
> static inline void void acpi_thermal_cpufreq_config_nvidia(void) {}
> #endif
>
>> +
>> void acpi_thermal_cpufreq_init(struct cpufreq_policy *policy)
>> {
>> unsigned int cpu;
>>
>> + acpi_thermal_cpufreq_config_nvidia();
>> +
>> for_each_cpu(cpu, policy->related_cpus) {
>> struct acpi_processor *pr = per_cpu(processors, cpu);
>> int ret;
>> --
>
> And patch [1/2] needs to be rebased on the current ACPI thermal
> material in linux-next.
>
Ok.
> Thanks!