Merge branch 'pm-cpufreq'

Merge cpufreq updates for 7.1-rc1:

 - Update qcom-hw DT bindings to include Eliza hardware (Abel Vesa)

 - Update cpufreq-dt-platdev blocklist (Faruque Ansari)

 - Minor updates to driver and dt-bindings for Tegra (Thierry Reding,
   Rosen Penev)

 - Add MAINTAINERS entry for CPPC driver (Viresh Kumar)

 - Add support for new features: CPPC performance priority, Dynamic EPP,
   Raw EPP, and new unit tests for them to amd-pstate (Gautham Shenoy,
   Mario Limonciello)

 - Fix sysfs files being present when HW missing and broken/outdated
   documentation in the amd-pstate driver (Ninad Naik, Gautham Shenoy)

 - Pass the policy to cpufreq_driver->adjust_perf() to avoid using
   cpufreq_cpu_get() in the .adjust_perf() callback in amd-pstate which
   leads to a scheduling-while-atomic bug (K Prateek Nayak)

 - Clean up dead code in Kconfig for cpufreq (Julian Braha)

 - Remove max_freq_req update for pre-existing cpufreq policy and add a
   boost_freq_req QoS request to save the boost constraint instead of
   overwriting the last scaling_max_freq constraint (Pierre Gondois)

 - Embed cpufreq QoS freq_req objects in cpufreq policy so they all
   are allocated in one go along with the policy to simplify lifetime
   rules and avoid error handling issues (Viresh Kumar)

 - Use DMI max speed when CPPC is unavailable in the acpi-cpufreq
   scaling driver (Henry Tseng)

 - Switch policy_is_shared() in cpufreq to using cpumask_nth() instead
   of cpumask_weight() because the former is more efficient (Yury Norov)

 - Use sysfs_emit() in sysfs show functions for cpufreq governor
   attributes (Thorsten Blum)

 - Update intel_pstate to stop returning an error when "off" is written
   to its status sysfs attribute while the driver is already off (Fabio
   De Francesco)

 - Include current frequency in the debug message printed by
   __cpufreq_driver_target() (Pengjie Zhang)

* pm-cpufreq: (38 commits)
  cpufreq/amd-pstate: Add POWER_SUPPLY select for dynamic EPP
  MAINTAINERS: amd-pstate: Step down as maintainer, add Prateek as reviewer
  cpufreq: Pass the policy to cpufreq_driver->adjust_perf()
  cpufreq/amd-pstate: Pass the policy to amd_pstate_update()
  cpufreq/amd-pstate-ut: Add a unit test for raw EPP
  cpufreq/amd-pstate: Add support for raw EPP writes
  cpufreq/amd-pstate: Add support for platform profile class
  cpufreq/amd-pstate: add kernel command line to override dynamic epp
  cpufreq/amd-pstate: Add dynamic energy performance preference
  Documentation: amd-pstate: fix dead links in the reference section
  cpufreq/amd-pstate: Cache the max frequency in cpudata
  Documentation/amd-pstate: Add documentation for amd_pstate_floor_{freq,count}
  Documentation/amd-pstate: List amd_pstate_prefcore_ranking sysfs file
  Documentation/amd-pstate: List amd_pstate_hw_prefcore sysfs file
  amd-pstate-ut: Add a testcase to validate the visibility of driver attributes
  amd-pstate-ut: Add module parameter to select testcases
  amd-pstate: Introduce a tracepoint trace_amd_pstate_cppc_req2()
  amd-pstate: Add sysfs support for floor_freq and floor_count
  amd-pstate: Add support for CPPC_REQ2 and FLOOR_PERF
  x86/cpufeatures: Add AMD CPPC Performance Priority feature.
  ...

Author: rafaeljw

Documentation/admin-guide/kernel-parameters.txt

@@ -493,6 +493,13 @@ Kernel parameters
 			disable
 			  Disable amd-pstate preferred core.
 
+	amd_dynamic_epp=
+			[X86]
+			disable
+			  Disable amd-pstate dynamic EPP.
+			enable
+			  Enable amd-pstate dynamic EPP.
+
 	amijoy.map=	[HW,JOY] Amiga joystick support
 			Map of devices attached to JOY0DAT and JOY1DAT
 			Format: <a>,<b>

Documentation/admin-guide/pm/amd-pstate.rst

@@ -239,8 +239,12 @@ control its functionality at the system level. They are located in the
 
  root@hr-test1:/home/ray# ls /sys/devices/system/cpu/cpufreq/policy0/*amd*
  /sys/devices/system/cpu/cpufreq/policy0/amd_pstate_highest_perf
+ /sys/devices/system/cpu/cpufreq/policy0/amd_pstate_hw_prefcore
  /sys/devices/system/cpu/cpufreq/policy0/amd_pstate_lowest_nonlinear_freq
  /sys/devices/system/cpu/cpufreq/policy0/amd_pstate_max_freq
+ /sys/devices/system/cpu/cpufreq/policy0/amd_pstate_floor_freq
+ /sys/devices/system/cpu/cpufreq/policy0/amd_pstate_floor_count
+ /sys/devices/system/cpu/cpufreq/policy0/amd_pstate_prefcore_ranking
 
 
 ``amd_pstate_highest_perf / amd_pstate_max_freq``
@@ -264,14 +268,46 @@ This attribute is read-only.
 
 ``amd_pstate_hw_prefcore``
 
-Whether the platform supports the preferred core feature and it has been
-enabled. This attribute is read-only.
+Whether the platform supports the preferred core feature and it has
+been enabled. This attribute is read-only. This file is only visible
+on platforms which support the preferred core feature.
 
 ``amd_pstate_prefcore_ranking``
 
 The performance ranking of the core. This number doesn't have any unit, but
 larger numbers are preferred at the time of reading. This can change at
-runtime based on platform conditions. This attribute is read-only.
+runtime based on platform conditions. This attribute is read-only. This file
+is only visible on platforms which support the preferred core feature.
+
+``amd_pstate_floor_freq``
+
+The floor frequency associated with each CPU. Userspace can write any
+value between ``cpuinfo_min_freq`` and ``scaling_max_freq`` into this
+file. When the system is under power or thermal constraints, the
+platform firmware will attempt to throttle the CPU frequency to the
+value specified in ``amd_pstate_floor_freq`` before throttling it
+further. This allows userspace to specify different floor frequencies
+to different CPUs. For optimal results, threads of the same core
+should have the same floor frequency value. This file is only visible
+on platforms that support the CPPC Performance Priority feature.
+
+
+``amd_pstate_floor_count``
+
+The number of distinct Floor Performance levels supported by the
+platform. For example, if this value is 2, then the number of unique
+values obtained from the command ``cat
+/sys/devices/system/cpu/cpufreq/policy*/amd_pstate_floor_freq |
+sort -n | uniq`` should be at most this number for the behavior
+described in ``amd_pstate_floor_freq`` to take effect. A zero value
+implies that the platform supports unlimited floor performance levels.
+This file is only visible on platforms that support the CPPC
+Performance Priority feature.
+
+**Note**: When ``amd_pstate_floor_count`` is non-zero, the frequency to
+which the CPU is throttled under power or thermal constraints is
+undefined when the number of unique values of ``amd_pstate_floor_freq``
+across all CPUs in the system exceeds ``amd_pstate_floor_count``.
 
 ``energy_performance_available_preferences``
 
@@ -280,16 +316,22 @@ A list of all the supported EPP preferences that could be used for
 These profiles represent different hints that are provided
 to the low-level firmware about the user's desired energy vs efficiency
 tradeoff.  ``default`` represents the epp value is set by platform
-firmware. This attribute is read-only.
+firmware. ``custom`` designates that integer values 0-255 may be written
+as well.  This attribute is read-only.
 
 ``energy_performance_preference``
 
 The current energy performance preference can be read from this attribute.
 and user can change current preference according to energy or performance needs
-Please get all support profiles list from
-``energy_performance_available_preferences`` attribute, all the profiles are
-integer values defined between 0 to 255 when EPP feature is enabled by platform
-firmware, if EPP feature is disabled, driver will ignore the written value
+Coarse named profiles are available in the attribute
+``energy_performance_available_preferences``.
+Users can also write individual integer values between 0 to 255.
+When dynamic EPP is enabled, writes to energy_performance_preference are blocked
+even when EPP feature is enabled by platform firmware. Lower epp values shift the bias
+towards improved performance while a higher epp value shifts the bias towards
+power-savings. The exact impact can change from one platform to the other.
+If a valid integer was last written, then a number will be returned on future reads.
+If a valid string was last written then a string will be returned on future reads.
 This attribute is read-write.
 
 ``boost``
@@ -311,6 +353,24 @@ boost or `1` to enable it, for the respective CPU using the sysfs path
 Other performance and frequency values can be read back from
 ``/sys/devices/system/cpu/cpuX/acpi_cppc/``, see :ref:`cppc_sysfs`.
 
+Dynamic energy performance profile
+==================================
+The amd-pstate driver supports dynamically selecting the energy performance
+profile based on whether the machine is running on AC or DC power.
+
+Whether this behavior is enabled by default depends on the kernel
+config option `CONFIG_X86_AMD_PSTATE_DYNAMIC_EPP`. This behavior can also be overridden
+at runtime by the sysfs file ``/sys/devices/system/cpu/cpufreq/policyX/dynamic_epp``.
+
+When set to enabled, the driver will select a different energy performance
+profile when the machine is running on battery or AC power. The driver will
+also register with the platform profile handler to receive notifications of
+user desired power state and react to those.
+When set to disabled, the driver will not change the energy performance profile
+based on the power source and will not react to user desired power state.
+
+Attempting to manually write to the ``energy_performance_preference`` sysfs
+file will fail when ``dynamic_epp`` is enabled.
 
 ``amd-pstate`` vs ``acpi-cpufreq``
 ======================================
@@ -422,6 +482,13 @@ For systems that support ``amd-pstate`` preferred core, the core rankings will
 always be advertised by the platform. But OS can choose to ignore that via the
 kernel parameter ``amd_prefcore=disable``.
 
+``amd_dynamic_epp``
+
+When AMD pstate is in auto mode, dynamic EPP will control whether the kernel
+autonomously changes the EPP mode. The default is configured by
+``CONFIG_X86_AMD_PSTATE_DYNAMIC_EPP`` but can be explicitly enabled with
+``amd_dynamic_epp=enable`` or disabled with ``amd_dynamic_epp=disable``.
+
 User Space Interface in ``sysfs`` - General
 ===========================================
 
@@ -790,13 +857,13 @@ Reference
 ===========
 
 .. [1] AMD64 Architecture Programmer's Manual Volume 2: System Programming,
-       https://www.amd.com/system/files/TechDocs/24593.pdf
+       https://docs.amd.com/v/u/en-US/24593_3.44_APM_Vol2
 
 .. [2] Advanced Configuration and Power Interface Specification,
        https://uefi.org/sites/default/files/resources/ACPI_Spec_6_4_Jan22.pdf
 
 .. [3] Processor Programming Reference (PPR) for AMD Family 19h Model 51h, Revision A1 Processors
-       https://www.amd.com/system/files/TechDocs/56569-A1-PUB.zip
+       https://docs.amd.com/v/u/en-US/56569-A1-PUB_3.03
 
 .. [4] Linux Kernel Selftests,
        https://www.kernel.org/doc/html/latest/dev-tools/kselftest.html

Documentation/devicetree/bindings/arm/tegra/nvidia,tegra-ccplex-cluster.yaml

@@ -24,6 +24,7 @@ properties:
     enum:
       - nvidia,tegra186-ccplex-cluster
       - nvidia,tegra234-ccplex-cluster
+      - nvidia,tegra238-ccplex-cluster
 
   reg:
     maxItems: 1

Documentation/devicetree/bindings/cpufreq/cpufreq-qcom-hw.yaml

@@ -35,6 +35,7 @@ properties:
       - description: v2 of CPUFREQ HW (EPSS)
         items:
           - enum:
+              - qcom,eliza-cpufreq-epss
               - qcom,milos-cpufreq-epss
               - qcom,qcs8300-cpufreq-epss
               - qcom,qdu1000-cpufreq-epss

MAINTAINERS

@@ -1234,9 +1234,9 @@ F:	drivers/gpu/drm/amd/pm/
 
 AMD PSTATE DRIVER
 M:	Huang Rui <ray.huang@amd.com>
-M:	Gautham R. Shenoy <gautham.shenoy@amd.com>
 M:	Mario Limonciello <mario.limonciello@amd.com>
 R:	Perry Yuan <perry.yuan@amd.com>
+R:	K Prateek Nayak <kprateek.nayak@amd.com>
 L:	linux-pm@vger.kernel.org
 S:	Supported
 F:	Documentation/admin-guide/pm/amd-pstate.rst
@@ -6616,6 +6616,17 @@ M:	Bence Csókás <bence98@sch.bme.hu>
 S:	Maintained
 F:	drivers/i2c/busses/i2c-cp2615.c
 
+CPU FREQUENCY DRIVERS - CPPC CPUFREQ
+M:	"Rafael J. Wysocki" <rafael@kernel.org>
+M:	Viresh Kumar <viresh.kumar@linaro.org>
+R:	Jie Zhan <zhanjie9@hisilicon.com>
+R:	Lifeng Zheng <zhenglifeng1@huawei.com>
+R:	Pierre Gondois <pierre.gondois@arm.com>
+R:	Sumit Gupta <sumitg@nvidia.com>
+L:	linux-pm@vger.kernel.org
+S:	Maintained
+F:	drivers/cpufreq/cppc_cpufreq.c
+
 CPU FREQUENCY DRIVERS - VEXPRESS SPC ARM BIG LITTLE
 M:	Viresh Kumar <viresh.kumar@linaro.org>
 M:	Sudeep Holla <sudeep.holla@kernel.org>
@@ -6624,6 +6635,12 @@ S:	Maintained
 W:	http://www.arm.com/products/processors/technologies/biglittleprocessing.php
 F:	drivers/cpufreq/vexpress-spc-cpufreq.c
 
+CPU FREQUENCY DRIVERS - VIRTUAL MACHINE CPUFREQ
+M:	Saravana Kannan <saravanak@kernel.org>
+L:	linux-pm@vger.kernel.org
+S:	Maintained
+F:	drivers/cpufreq/virtual-cpufreq.c
+
 CPU FREQUENCY SCALING FRAMEWORK
 M:	"Rafael J. Wysocki" <rafael@kernel.org>
 M:	Viresh Kumar <viresh.kumar@linaro.org>
@@ -6643,12 +6660,6 @@ F:	kernel/sched/cpufreq*.c
 F:	rust/kernel/cpufreq.rs
 F:	tools/testing/selftests/cpufreq/
 
-CPU FREQUENCY DRIVERS - VIRTUAL MACHINE CPUFREQ
-M:	Saravana Kannan <saravanak@kernel.org>
-L:	linux-pm@vger.kernel.org
-S:	Maintained
-F:	drivers/cpufreq/virtual-cpufreq.c
-
 CPU HOTPLUG
 M:	Thomas Gleixner <tglx@kernel.org>
 M:	Peter Zijlstra <peterz@infradead.org>

arch/x86/include/asm/cpufeatures.h

@@ -415,7 +415,7 @@
  */
 #define X86_FEATURE_OVERFLOW_RECOV	(17*32+ 0) /* "overflow_recov" MCA overflow recovery support */
 #define X86_FEATURE_SUCCOR		(17*32+ 1) /* "succor" Uncorrectable error containment and recovery */
-
+#define X86_FEATURE_CPPC_PERF_PRIO	(17*32+ 2) /* CPPC Floor Perf support */
 #define X86_FEATURE_SMCA		(17*32+ 3) /* "smca" Scalable MCA */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */

arch/x86/include/asm/msr-index.h

@@ -765,19 +765,24 @@
 #define MSR_AMD_CPPC_CAP2		0xc00102b2
 #define MSR_AMD_CPPC_REQ		0xc00102b3
 #define MSR_AMD_CPPC_STATUS		0xc00102b4
+#define MSR_AMD_CPPC_REQ2		0xc00102b5
 
 /* Masks for use with MSR_AMD_CPPC_CAP1 */
 #define AMD_CPPC_LOWEST_PERF_MASK	GENMASK(7, 0)
 #define AMD_CPPC_LOWNONLIN_PERF_MASK	GENMASK(15, 8)
 #define AMD_CPPC_NOMINAL_PERF_MASK	GENMASK(23, 16)
 #define AMD_CPPC_HIGHEST_PERF_MASK	GENMASK(31, 24)
+#define AMD_CPPC_FLOOR_PERF_CNT_MASK	GENMASK_ULL(39, 32)
 
 /* Masks for use with MSR_AMD_CPPC_REQ */
 #define AMD_CPPC_MAX_PERF_MASK		GENMASK(7, 0)
 #define AMD_CPPC_MIN_PERF_MASK		GENMASK(15, 8)
 #define AMD_CPPC_DES_PERF_MASK		GENMASK(23, 16)
 #define AMD_CPPC_EPP_PERF_MASK		GENMASK(31, 24)
 
+/* Masks for use with MSR_AMD_CPPC_REQ2 */
+#define AMD_CPPC_FLOOR_PERF_MASK	GENMASK(7, 0)
+
 /* AMD Performance Counter Global Status and Control MSRs */
 #define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS	0xc0000300
 #define MSR_AMD64_PERF_CNTR_GLOBAL_CTL		0xc0000301

arch/x86/kernel/cpu/scattered.c

@@ -52,6 +52,7 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_CPB,			CPUID_EDX,  9, 0x80000007, 0 },
 	{ X86_FEATURE_PROC_FEEDBACK,		CPUID_EDX, 11, 0x80000007, 0 },
 	{ X86_FEATURE_AMD_FAST_CPPC,		CPUID_EDX, 15, 0x80000007, 0 },
+	{ X86_FEATURE_CPPC_PERF_PRIO,		CPUID_EDX, 16, 0x80000007, 0 },
 	{ X86_FEATURE_MBA,			CPUID_EBX,  6, 0x80000008, 0 },
 	{ X86_FEATURE_X2AVIC_EXT,		CPUID_ECX,  6, 0x8000000a, 0 },
 	{ X86_FEATURE_COHERENCY_SFW_NO,		CPUID_EBX, 31, 0x8000001f, 0 },

drivers/acpi/cppc_acpi.c

@@ -1944,7 +1944,7 @@ static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private)
 }
 
 /* Look up the max frequency in DMI */
-static u64 cppc_get_dmi_max_khz(void)
+u64 cppc_get_dmi_max_khz(void)
 {
 	u16 mhz = 0;
 
@@ -1958,6 +1958,7 @@ static u64 cppc_get_dmi_max_khz(void)
 
 	return KHZ_PER_MHZ * mhz;
 }
+EXPORT_SYMBOL_GPL(cppc_get_dmi_max_khz);
 
 /*
  * If CPPC lowest_freq and nominal_freq registers are exposed then we can

drivers/cpufreq/Kconfig

@@ -163,7 +163,6 @@ config CPU_FREQ_GOV_ONDEMAND
 
 config CPU_FREQ_GOV_CONSERVATIVE
 	tristate "'conservative' cpufreq governor"
-	depends on CPU_FREQ
 	select CPU_FREQ_GOV_COMMON
 	help
 	  'conservative' - this driver is rather similar to the 'ondemand'
@@ -188,7 +187,7 @@ config CPU_FREQ_GOV_CONSERVATIVE
 
 config CPU_FREQ_GOV_SCHEDUTIL
 	bool "'schedutil' cpufreq policy governor"
-	depends on CPU_FREQ && SMP
+	depends on SMP
 	select CPU_FREQ_GOV_ATTR_SET
 	select IRQ_WORK
 	help
@@ -365,6 +364,6 @@ config ACPI_CPPC_CPUFREQ_FIE
 
 	  If in doubt, say N.
 
-endif
+endif # CPU_FREQ
 
 endmenu