Merge tag 'pm-6.10-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management fixes from Rafael Wysocki:
 "These fix the intel_pstate and amd-pstate cpufreq drivers and the
  cpupower utility.

  Specifics:

   - Fix a recently introduced unchecked HWP MSR access in the
     intel_pstate driver (Srinivas Pandruvada)

   - Add missing conversion from MHz to KHz to amd_pstate_set_boost() to
     address sysfs inteface inconsistency and fix P-state frequency
     reporting on AMD Family 1Ah CPUs in the cpupower utility (Dhananjay
     Ugwekar)

   - Get rid of an excess global header file used by the amd-pstate
     cpufreq driver (Arnd Bergmann)"

* tag 'pm-6.10-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  cpufreq: intel_pstate: Fix unchecked HWP MSR access
  cpufreq: amd-pstate: Fix the inconsistency in max frequency units
  cpufreq: amd-pstate: remove global header file
  tools/power/cpupower: Fix Pstate frequency reporting on AMD Family 1Ah CPUs

4 files changed, 142 insertions, 4 deletions

diff --git a/drivers/cpufreq/amd-pstate-ut.c b/drivers/cpufreq/amd-pstate-ut.c
index f04ae67dda37..fc275d41d51e 100644
--- a/drivers/cpufreq/amd-pstate-ut.c
+++ b/drivers/cpufreq/amd-pstate-ut.c
@@ -26,10 +26,11 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/fs.h>
-#include <linux/amd-pstate.h>
 
 #include <acpi/cppc_acpi.h>
 
+#include "amd-pstate.h"
+
 /*
  * Abbreviations:
  * amd_pstate_ut: used as a shortform for AMD P-State unit test.
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 1b7e82a0ad2e..9ad62dbe8bfb 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -36,7 +36,6 @@
 #include <linux/delay.h>
 #include <linux/uaccess.h>
 #include <linux/static_call.h>
-#include <linux/amd-pstate.h>
 #include <linux/topology.h>
 
 #include <acpi/processor.h>
@@ -46,6 +45,8 @@
 #include <asm/processor.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu_device_id.h>
+
+#include "amd-pstate.h"
 #include "amd-pstate-trace.h"
 
 #define AMD_PSTATE_TRANSITION_LATENCY	20000
@@ -53,6 +54,37 @@
 #define CPPC_HIGHEST_PERF_PERFORMANCE	196
 #define CPPC_HIGHEST_PERF_DEFAULT	166
 
+#define AMD_CPPC_EPP_PERFORMANCE		0x00
+#define AMD_CPPC_EPP_BALANCE_PERFORMANCE	0x80
+#define AMD_CPPC_EPP_BALANCE_POWERSAVE		0xBF
+#define AMD_CPPC_EPP_POWERSAVE			0xFF
+
+/*
+ * enum amd_pstate_mode - driver working mode of amd pstate
+ */
+enum amd_pstate_mode {
+	AMD_PSTATE_UNDEFINED = 0,
+	AMD_PSTATE_DISABLE,
+	AMD_PSTATE_PASSIVE,
+	AMD_PSTATE_ACTIVE,
+	AMD_PSTATE_GUIDED,
+	AMD_PSTATE_MAX,
+};
+
+static const char * const amd_pstate_mode_string[] = {
+	[AMD_PSTATE_UNDEFINED]   = "undefined",
+	[AMD_PSTATE_DISABLE]     = "disable",
+	[AMD_PSTATE_PASSIVE]     = "passive",
+	[AMD_PSTATE_ACTIVE]      = "active",
+	[AMD_PSTATE_GUIDED]      = "guided",
+	NULL,
+};
+
+struct quirk_entry {
+	u32 nominal_freq;
+	u32 lowest_freq;
+};
+
 /*
  * TODO: We need more time to fine tune processors with shared memory solution
  * with community together.
@@ -669,7 +701,7 @@ static int amd_pstate_set_boost(struct cpufreq_policy *policy, int state)
 	if (state)
 		policy->cpuinfo.max_freq = cpudata->max_freq;
 	else
-		policy->cpuinfo.max_freq = cpudata->nominal_freq;
+		policy->cpuinfo.max_freq = cpudata->nominal_freq * 1000;
 
 	policy->max = policy->cpuinfo.max_freq;
 
diff --git a/drivers/cpufreq/amd-pstate.h b/drivers/cpufreq/amd-pstate.h
new file mode 100644
index 000000000000..e6a28e7f4dbf
--- /dev/null
+++ b/drivers/cpufreq/amd-pstate.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2022 Advanced Micro Devices, Inc.
+ *
+ * Author: Meng Li <li.meng@amd.com>
+ */
+
+#ifndef _LINUX_AMD_PSTATE_H
+#define _LINUX_AMD_PSTATE_H
+
+#include <linux/pm_qos.h>
+
+/*********************************************************************
+ *                        AMD P-state INTERFACE                       *
+ *********************************************************************/
+/**
+ * struct  amd_aperf_mperf
+ * @aperf: actual performance frequency clock count
+ * @mperf: maximum performance frequency clock count
+ * @tsc:   time stamp counter
+ */
+struct amd_aperf_mperf {
+	u64 aperf;
+	u64 mperf;
+	u64 tsc;
+};
+
+/**
+ * struct amd_cpudata - private CPU data for AMD P-State
+ * @cpu: CPU number
+ * @req: constraint request to apply
+ * @cppc_req_cached: cached performance request hints
+ * @highest_perf: the maximum performance an individual processor may reach,
+ *		  assuming ideal conditions
+ *		  For platforms that do not support the preferred core feature, the
+ *		  highest_pef may be configured with 166 or 255, to avoid max frequency
+ *		  calculated wrongly. we take the fixed value as the highest_perf.
+ * @nominal_perf: the maximum sustained performance level of the processor,
+ *		  assuming ideal operating conditions
+ * @lowest_nonlinear_perf: the lowest performance level at which nonlinear power
+ *			   savings are achieved
+ * @lowest_perf: the absolute lowest performance level of the processor
+ * @prefcore_ranking: the preferred core ranking, the higher value indicates a higher
+ * 		  priority.
+ * @min_limit_perf: Cached value of the performance corresponding to policy->min
+ * @max_limit_perf: Cached value of the performance corresponding to policy->max
+ * @min_limit_freq: Cached value of policy->min (in khz)
+ * @max_limit_freq: Cached value of policy->max (in khz)
+ * @max_freq: the frequency (in khz) that mapped to highest_perf
+ * @min_freq: the frequency (in khz) that mapped to lowest_perf
+ * @nominal_freq: the frequency (in khz) that mapped to nominal_perf
+ * @lowest_nonlinear_freq: the frequency (in khz) that mapped to lowest_nonlinear_perf
+ * @cur: Difference of Aperf/Mperf/tsc count between last and current sample
+ * @prev: Last Aperf/Mperf/tsc count value read from register
+ * @freq: current cpu frequency value (in khz)
+ * @boost_supported: check whether the Processor or SBIOS supports boost mode
+ * @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
+ *
+ * The amd_cpudata is key private data for each CPU thread in AMD P-State, and
+ * represents all the attributes and goals that AMD P-State requests at runtime.
+ */
+struct amd_cpudata {
+	int	cpu;
+
+	struct	freq_qos_request req[2];
+	u64	cppc_req_cached;
+
+	u32	highest_perf;
+	u32	nominal_perf;
+	u32	lowest_nonlinear_perf;
+	u32	lowest_perf;
+	u32     prefcore_ranking;
+	u32     min_limit_perf;
+	u32     max_limit_perf;
+	u32     min_limit_freq;
+	u32     max_limit_freq;
+
+	u32	max_freq;
+	u32	min_freq;
+	u32	nominal_freq;
+	u32	lowest_nonlinear_freq;
+
+	struct amd_aperf_mperf cur;
+	struct amd_aperf_mperf prev;
+
+	u64	freq;
+	bool	boost_supported;
+	bool	hw_prefcore;
+
+	/* EPP feature related attributes*/
+	s16	epp_policy;
+	s16	epp_cached;
+	u32	policy;
+	u64	cppc_cap1_cached;
+	bool	suspended;
+};
+
+#endif /* _LINUX_AMD_PSTATE_H */
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 4b986c044741..65d3f79104bd 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1153,7 +1153,8 @@ static void intel_pstate_update_policies(void)
 static void __intel_pstate_update_max_freq(struct cpudata *cpudata,
 					   struct cpufreq_policy *policy)
 {
-	intel_pstate_get_hwp_cap(cpudata);
+	if (hwp_active)
+		intel_pstate_get_hwp_cap(cpudata);
 
 	policy->cpuinfo.max_freq = READ_ONCE(global.no_turbo) ?
 			cpudata->pstate.max_freq : cpudata->pstate.turbo_freq;