[PATCH v2 00/11] Adjustments for preferred core detection

[PATCH v2 00/11] Adjustments for preferred core detection

[Mario Limonciello]

From: Mario Limonciello <mario.limonciello@amd.com>

Preferred core detection is fragile in that any CPU that reports
less than 255 for any core is assumed to be a preferred core design.
This might not always be true, so it's better to check all CPUs and
see that varying values are actually reported.

Furthermore, preferred core detection isn't used by acpi-cpufreq. So
incorrect frequencies are used unless amd-pstate is active.

This series moves preferred core detection out of amd-pstate in a more
robust fashion.  It also removes some tech debt of hardcoded values for
platforms that are actually preferred core platforms.

This branch is based off v6.11-rc6.

v1->v2:
 * Add patches for documentation
 * Add patch for existing wrong return code in header
 * Individual changes described in individual patches

Mario Limonciello (10):
  x86/amd: Move amd_get_highest_perf() from amd.c to cppc.c
  x86/amd: Rename amd_get_highest_perf() to
    amd_get_boost_ratio_numerator()
  ACPI: CPPC: Drop check for non zero perf ratio
  ACPI: CPPC: Adjust debug messages in amd_set_max_freq_ratio() to warn
  x86/amd: Move amd_get_highest_perf() out of amd-pstate
  x86/amd: Detect preferred cores in amd_get_boost_ratio_numerator()
  cpufreq: amd-pstate: Merge amd_pstate_highest_perf_set() into
    amd_get_boost_ratio_numerator()
  cpufreq: amd-pstate: Optimize amd_pstate_update_limits()
  cpufreq: amd-pstate: Add documentation for `amd_pstate_hw_prefcore`
  amd-pstate: Add missing documentation for
    `amd_pstate_prefcore_ranking`

 Documentation/admin-guide/pm/amd-pstate.rst |  15 +-
 arch/x86/include/asm/processor.h            |   3 -
 arch/x86/kernel/acpi/cppc.c                 | 172 ++++++++++++++++++--
 arch/x86/kernel/cpu/amd.c                   |  16 --
 drivers/cpufreq/acpi-cpufreq.c              |  12 +-
 drivers/cpufreq/amd-pstate.c                | 128 ++++-----------
 include/acpi/cppc_acpi.h                    |  17 ++
 7 files changed, 230 insertions(+), 133 deletions(-)

-- 
2.43.0

[PATCH v2 01/11] x86/amd: Move amd_get_highest_perf() from amd.c to cppc.c

[Mario Limonciello]

From: Mario Limonciello <mario.limonciello@amd.com>

To prepare to let amd_get_highest_perf() detect preferred cores
it will require CPPC functions. Move amd_get_highest_perf() to
cppc.c to prepare for 'preferred core detection' rework.

No functional changes intended.

Reviewed-by: Perry Yuan <perry.yuan@amd.com>
Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 arch/x86/kernel/acpi/cppc.c | 16 ++++++++++++++++
 arch/x86/kernel/cpu/amd.c   | 16 ----------------
 2 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c
index ff8f25faca3dd..7ec8f2ce859c8 100644
--- a/arch/x86/kernel/acpi/cppc.c
+++ b/arch/x86/kernel/acpi/cppc.c
@@ -116,3 +116,19 @@ void init_freq_invariance_cppc(void)
 	init_done = true;
 	mutex_unlock(&freq_invariance_lock);
 }
+
+u32 amd_get_highest_perf(void)
+{
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+
+	if (c->x86 == 0x17 && ((c->x86_model >= 0x30 && c->x86_model < 0x40) ||
+			       (c->x86_model >= 0x70 && c->x86_model < 0x80)))
+		return 166;
+
+	if (c->x86 == 0x19 && ((c->x86_model >= 0x20 && c->x86_model < 0x30) ||
+			       (c->x86_model >= 0x40 && c->x86_model < 0x70)))
+		return 166;
+
+	return 255;
+}
+EXPORT_SYMBOL_GPL(amd_get_highest_perf);
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 1e0fe5f8ab84e..015971adadfc7 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1190,22 +1190,6 @@ unsigned long amd_get_dr_addr_mask(unsigned int dr)
 }
 EXPORT_SYMBOL_GPL(amd_get_dr_addr_mask);
 
-u32 amd_get_highest_perf(void)
-{
-	struct cpuinfo_x86 *c = &boot_cpu_data;
-
-	if (c->x86 == 0x17 && ((c->x86_model >= 0x30 && c->x86_model < 0x40) ||
-			       (c->x86_model >= 0x70 && c->x86_model < 0x80)))
-		return 166;
-
-	if (c->x86 == 0x19 && ((c->x86_model >= 0x20 && c->x86_model < 0x30) ||
-			       (c->x86_model >= 0x40 && c->x86_model < 0x70)))
-		return 166;
-
-	return 255;
-}
-EXPORT_SYMBOL_GPL(amd_get_highest_perf);
-
 static void zenbleed_check_cpu(void *unused)
 {
 	struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
-- 
2.43.0

[PATCH v2 02/11] ACPI: CPPC: Adjust return code for inline functions in !CONFIG_ACPI_CPPC_LIB

[Mario Limonciello]

From: Mario Limonciello <mario.limonciello@amd.com>

Checkpath emits the following warning:
```
WARNING: ENOTSUPP is not a SUSV4 error code, prefer EOPNOTSUPP
```

Adjust the code accordingly.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 include/acpi/cppc_acpi.h | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
index 930b6afba6f4d..409a7190a4a86 100644
--- a/include/acpi/cppc_acpi.h
+++ b/include/acpi/cppc_acpi.h
@@ -162,31 +162,31 @@ extern int cppc_set_auto_sel(int cpu, bool enable);
 #else /* !CONFIG_ACPI_CPPC_LIB */
 static inline int cppc_get_desired_perf(int cpunum, u64 *desired_perf)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 static inline int cppc_get_nominal_perf(int cpunum, u64 *nominal_perf)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 static inline int cppc_get_highest_perf(int cpunum, u64 *highest_perf)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 static inline int cppc_get_perf_ctrs(int cpu, struct cppc_perf_fb_ctrs *perf_fb_ctrs)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 static inline int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 static inline int cppc_set_enable(int cpu, bool enable)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 static inline int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 static inline bool cppc_perf_ctrs_in_pcc(void)
 {
@@ -210,27 +210,27 @@ static inline bool cpc_ffh_supported(void)
 }
 static inline int cpc_read_ffh(int cpunum, struct cpc_reg *reg, u64 *val)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 static inline int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 static inline int cppc_set_epp_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls, bool enable)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 static inline int cppc_get_epp_perf(int cpunum, u64 *epp_perf)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 static inline int cppc_set_auto_sel(int cpu, bool enable)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 static inline int cppc_get_auto_sel_caps(int cpunum, struct cppc_perf_caps *perf_caps)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 #endif /* !CONFIG_ACPI_CPPC_LIB */
 
-- 
2.43.0

[PATCH v2 03/11] x86/amd: Rename amd_get_highest_perf() to amd_get_boost_ratio_numerator()

[Mario Limonciello]

From: Mario Limonciello <mario.limonciello@amd.com>

The function name is ambiguous because it returns an intermediate value
for calculating maximum frequency rather than the CPPC 'Highest Perf'
register.

Rename the function to clarify its use and allow the function to return
errors. Adjust the consumer in acpi-cpufreq to catch errors.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
v1->v2:
 * Rename variable from `highest_perf` to `numerator`
 * Fail when unable to return boost numerator
 * Move prototype behind CONFIG_ACPI_CPPC_LIB (lkp robot)
---
 arch/x86/include/asm/processor.h |  3 ---
 arch/x86/kernel/acpi/cppc.c      | 44 +++++++++++++++++++++++---------
 drivers/cpufreq/acpi-cpufreq.c   | 12 ++++++---
 include/acpi/cppc_acpi.h         |  5 ++++
 4 files changed, 46 insertions(+), 18 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index a75a07f4931fd..775acbdea1a96 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -691,8 +691,6 @@ static inline u32 per_cpu_l2c_id(unsigned int cpu)
 }
 
 #ifdef CONFIG_CPU_SUP_AMD
-extern u32 amd_get_highest_perf(void);
-
 /*
  * Issue a DIV 0/1 insn to clear any division data from previous DIV
  * operations.
@@ -705,7 +703,6 @@ static __always_inline void amd_clear_divider(void)
 
 extern void amd_check_microcode(void);
 #else
-static inline u32 amd_get_highest_perf(void)		{ return 0; }
 static inline void amd_clear_divider(void)		{ }
 static inline void amd_check_microcode(void)		{ }
 #endif
diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c
index 7ec8f2ce859c8..660cfeb6384ba 100644
--- a/arch/x86/kernel/acpi/cppc.c
+++ b/arch/x86/kernel/acpi/cppc.c
@@ -69,7 +69,7 @@ int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val)
 static void amd_set_max_freq_ratio(void)
 {
 	struct cppc_perf_caps perf_caps;
-	u64 highest_perf, nominal_perf;
+	u64 numerator, nominal_perf;
 	u64 perf_ratio;
 	int rc;
 
@@ -79,15 +79,19 @@ static void amd_set_max_freq_ratio(void)
 		return;
 	}
 
-	highest_perf = amd_get_highest_perf();
+	rc = amd_get_boost_ratio_numerator(0, &numerator);
+	if (rc) {
+		pr_debug("Could not retrieve highest performance (%d)\n", rc);
+		return;
+	}
 	nominal_perf = perf_caps.nominal_perf;
 
-	if (!highest_perf || !nominal_perf) {
-		pr_debug("Could not retrieve highest or nominal performance\n");
+	if (!nominal_perf) {
+		pr_debug("Could not retrieve nominal performance\n");
 		return;
 	}
 
-	perf_ratio = div_u64(highest_perf * SCHED_CAPACITY_SCALE, nominal_perf);
+	perf_ratio = div_u64(numerator * SCHED_CAPACITY_SCALE, nominal_perf);
 	/* midpoint between max_boost and max_P */
 	perf_ratio = (perf_ratio + SCHED_CAPACITY_SCALE) >> 1;
 	if (!perf_ratio) {
@@ -117,18 +121,34 @@ void init_freq_invariance_cppc(void)
 	mutex_unlock(&freq_invariance_lock);
 }
 
-u32 amd_get_highest_perf(void)
+/**
+ * amd_get_boost_ratio_numerator: Get the numerator to use for boost ratio calculation
+ * @cpu: CPU to get numerator for.
+ * @numerator: Output variable for numerator.
+ *
+ * Determine the numerator to use for calculating the boost ratio on
+ * a CPU. On systems that support preferred cores, this will be a hardcoded
+ * value. On other systems this will the highest performance register value.
+ *
+ * Return: 0 for success, negative error code otherwise.
+ */
+int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator)
 {
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 
 	if (c->x86 == 0x17 && ((c->x86_model >= 0x30 && c->x86_model < 0x40) ||
-			       (c->x86_model >= 0x70 && c->x86_model < 0x80)))
-		return 166;
+			       (c->x86_model >= 0x70 && c->x86_model < 0x80))) {
+		*numerator = 166;
+		return 0;
+	}
 
 	if (c->x86 == 0x19 && ((c->x86_model >= 0x20 && c->x86_model < 0x30) ||
-			       (c->x86_model >= 0x40 && c->x86_model < 0x70)))
-		return 166;
+			       (c->x86_model >= 0x40 && c->x86_model < 0x70))) {
+		*numerator = 166;
+		return 0;
+	}
+	*numerator = 255;
 
-	return 255;
+	return 0;
 }
-EXPORT_SYMBOL_GPL(amd_get_highest_perf);
+EXPORT_SYMBOL_GPL(amd_get_boost_ratio_numerator);
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index a8ca625a98b89..0f04feb6cafaf 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -642,10 +642,16 @@ static u64 get_max_boost_ratio(unsigned int cpu)
 		return 0;
 	}
 
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
-		highest_perf = amd_get_highest_perf();
-	else
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
+		ret = amd_get_boost_ratio_numerator(cpu, &highest_perf);
+		if (ret) {
+			pr_debug("CPU%d: Unable to get boost ratio numerator (%d)\n",
+				 cpu, ret);
+			return 0;
+		}
+	} else {
 		highest_perf = perf_caps.highest_perf;
+	}
 
 	nominal_perf = perf_caps.nominal_perf;
 
diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
index 409a7190a4a86..97861abc5f5b8 100644
--- a/include/acpi/cppc_acpi.h
+++ b/include/acpi/cppc_acpi.h
@@ -159,6 +159,7 @@ extern int cppc_get_epp_perf(int cpunum, u64 *epp_perf);
 extern int cppc_set_epp_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls, bool enable);
 extern int cppc_get_auto_sel_caps(int cpunum, struct cppc_perf_caps *perf_caps);
 extern int cppc_set_auto_sel(int cpu, bool enable);
+extern int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator);
 #else /* !CONFIG_ACPI_CPPC_LIB */
 static inline int cppc_get_desired_perf(int cpunum, u64 *desired_perf)
 {
@@ -232,6 +233,10 @@ static inline int cppc_get_auto_sel_caps(int cpunum, struct cppc_perf_caps *perf
 {
 	return -EOPNOTSUPP;
 }
+static inline int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator)
+{
+	return -EOPNOTSUPP;
+}
 #endif /* !CONFIG_ACPI_CPPC_LIB */
 
 #endif /* _CPPC_ACPI_H*/
-- 
2.43.0

[PATCH v2 04/11] ACPI: CPPC: Drop check for non zero perf ratio

[Mario Limonciello]

From: Mario Limonciello <mario.limonciello@amd.com>

perf_ratio is a u64 and SCHED_CAPACITY_SCALE is a larg number.
Shifting by one will never have a zero value.

Drop the check.

Suggested-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 arch/x86/kernel/acpi/cppc.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c
index 660cfeb6384ba..e65c77afab318 100644
--- a/arch/x86/kernel/acpi/cppc.c
+++ b/arch/x86/kernel/acpi/cppc.c
@@ -91,13 +91,8 @@ static void amd_set_max_freq_ratio(void)
 		return;
 	}
 
-	perf_ratio = div_u64(numerator * SCHED_CAPACITY_SCALE, nominal_perf);
 	/* midpoint between max_boost and max_P */
-	perf_ratio = (perf_ratio + SCHED_CAPACITY_SCALE) >> 1;
-	if (!perf_ratio) {
-		pr_debug("Non-zero highest/nominal perf values led to a 0 ratio\n");
-		return;
-	}
+	perf_ratio = (div_u64(numerator * SCHED_CAPACITY_SCALE, nominal_perf) + SCHED_CAPACITY_SCALE) >> 1;
 
 	freq_invariance_set_perf_ratio(perf_ratio, false);
 }
-- 
2.43.0

[PATCH v2 05/11] ACPI: CPPC: Adjust debug messages in amd_set_max_freq_ratio() to warn

[Mario Limonciello]

From: Mario Limonciello <mario.limonciello@amd.com>

If the boost ratio isn't calculated properly for the system for any
reason this can cause other problems that are non-obvious.

Raise all messages to warn instead.

Suggested-by: Perry Yuan <Perry.Yuan@amd.com>
Reviewed-by: Perry Yuan <perry.yuan@amd.com>
Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 arch/x86/kernel/acpi/cppc.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c
index e65c77afab318..f0328ce98a8fe 100644
--- a/arch/x86/kernel/acpi/cppc.c
+++ b/arch/x86/kernel/acpi/cppc.c
@@ -75,19 +75,19 @@ static void amd_set_max_freq_ratio(void)
 
 	rc = cppc_get_perf_caps(0, &perf_caps);
 	if (rc) {
-		pr_debug("Could not retrieve perf counters (%d)\n", rc);
+		pr_warn("Could not retrieve perf counters (%d)\n", rc);
 		return;
 	}
 
 	rc = amd_get_boost_ratio_numerator(0, &numerator);
 	if (rc) {
-		pr_debug("Could not retrieve highest performance (%d)\n", rc);
+		pr_warn("Could not retrieve highest performance (%d)\n", rc);
 		return;
 	}
 	nominal_perf = perf_caps.nominal_perf;
 
 	if (!nominal_perf) {
-		pr_debug("Could not retrieve nominal performance\n");
+		pr_warn("Could not retrieve nominal performance\n");
 		return;
 	}
 
-- 
2.43.0

[PATCH v2 06/11] x86/amd: Move amd_get_highest_perf() out of amd-pstate

[Mario Limonciello]

From: Mario Limonciello <mario.limonciello@amd.com>

amd_pstate_get_highest_perf() is a helper used to get the highest perf
value on AMD systems.  It's used in amd-pstate as part of preferred
core handling, but applicable for acpi-cpufreq as well.

Move it out to cppc handling code as amd_get_highest_perf().

Reviewed-by: Perry Yuan <perry.yuan@amd.com>
Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
v1->v2:
 * Update commit message (Gautham)
---
 arch/x86/kernel/acpi/cppc.c  | 30 ++++++++++++++++++++++++++++++
 drivers/cpufreq/amd-pstate.c | 34 ++--------------------------------
 include/acpi/cppc_acpi.h     |  5 +++++
 3 files changed, 37 insertions(+), 32 deletions(-)

diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c
index f0328ce98a8fe..a75dcb382c786 100644
--- a/arch/x86/kernel/acpi/cppc.c
+++ b/arch/x86/kernel/acpi/cppc.c
@@ -116,6 +116,36 @@ void init_freq_invariance_cppc(void)
 	mutex_unlock(&freq_invariance_lock);
 }
 
+/*
+ * Get the highest performance register value.
+ * @cpu: CPU from which to get highest performance.
+ * @highest_perf: Return address for highest performance value.
+ *
+ * Return: 0 for success, negative error code otherwise.
+ */
+int amd_get_highest_perf(unsigned int cpu, u32 *highest_perf)
+{
+	u64 val;
+	int ret;
+
+	if (cpu_feature_enabled(X86_FEATURE_CPPC)) {
+		ret = rdmsrl_safe_on_cpu(cpu, MSR_AMD_CPPC_CAP1, &val);
+		if (ret)
+			goto out;
+
+		val = AMD_CPPC_HIGHEST_PERF(val);
+	} else {
+		ret = cppc_get_highest_perf(cpu, &val);
+		if (ret)
+			goto out;
+	}
+
+	WRITE_ONCE(*highest_perf, (u32)val);
+out:
+	return ret;
+}
+EXPORT_SYMBOL_GPL(amd_get_highest_perf);
+
 /**
  * amd_get_boost_ratio_numerator: Get the numerator to use for boost ratio calculation
  * @cpu: CPU to get numerator for.
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index db4f747f128f1..44df6ef66b5fa 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -803,36 +803,6 @@ static void amd_pstste_sched_prefcore_workfn(struct work_struct *work)
 }
 static DECLARE_WORK(sched_prefcore_work, amd_pstste_sched_prefcore_workfn);
 
-/*
- * Get the highest performance register value.
- * @cpu: CPU from which to get highest performance.
- * @highest_perf: Return address.
- *
- * Return: 0 for success, -EIO otherwise.
- */
-static int amd_pstate_get_highest_perf(int cpu, u32 *highest_perf)
-{
-	int ret;
-
-	if (cpu_feature_enabled(X86_FEATURE_CPPC)) {
-		u64 cap1;
-
-		ret = rdmsrl_safe_on_cpu(cpu, MSR_AMD_CPPC_CAP1, &cap1);
-		if (ret)
-			return ret;
-		WRITE_ONCE(*highest_perf, AMD_CPPC_HIGHEST_PERF(cap1));
-	} else {
-		u64 cppc_highest_perf;
-
-		ret = cppc_get_highest_perf(cpu, &cppc_highest_perf);
-		if (ret)
-			return ret;
-		WRITE_ONCE(*highest_perf, cppc_highest_perf);
-	}
-
-	return (ret);
-}
-
 #define CPPC_MAX_PERF	U8_MAX
 
 static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata)
@@ -840,7 +810,7 @@ static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata)
 	int ret, prio;
 	u32 highest_perf;
 
-	ret = amd_pstate_get_highest_perf(cpudata->cpu, &highest_perf);
+	ret = amd_get_highest_perf(cpudata->cpu, &highest_perf);
 	if (ret)
 		return;
 
@@ -879,7 +849,7 @@ static void amd_pstate_update_limits(unsigned int cpu)
 	if ((!amd_pstate_prefcore) || (!cpudata->hw_prefcore))
 		goto free_cpufreq_put;
 
-	ret = amd_pstate_get_highest_perf(cpu, &cur_high);
+	ret = amd_get_highest_perf(cpu, &cur_high);
 	if (ret)
 		goto free_cpufreq_put;
 
diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
index 97861abc5f5b8..f7c7abf2a95e9 100644
--- a/include/acpi/cppc_acpi.h
+++ b/include/acpi/cppc_acpi.h
@@ -159,6 +159,7 @@ extern int cppc_get_epp_perf(int cpunum, u64 *epp_perf);
 extern int cppc_set_epp_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls, bool enable);
 extern int cppc_get_auto_sel_caps(int cpunum, struct cppc_perf_caps *perf_caps);
 extern int cppc_set_auto_sel(int cpu, bool enable);
+extern int amd_get_highest_perf(unsigned int cpu, u32 *highest_perf);
 extern int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator);
 #else /* !CONFIG_ACPI_CPPC_LIB */
 static inline int cppc_get_desired_perf(int cpunum, u64 *desired_perf)
@@ -233,6 +234,10 @@ static inline int cppc_get_auto_sel_caps(int cpunum, struct cppc_perf_caps *perf
 {
 	return -EOPNOTSUPP;
 }
+static inline int amd_get_highest_perf(unsigned int cpu, u32 *highest_perf)
+{
+	return -ENODEV;
+}
 static inline int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator)
 {
 	return -EOPNOTSUPP;
-- 
2.43.0

[PATCH v2 07/11] x86/amd: Detect preferred cores in amd_get_boost_ratio_numerator()

[Mario Limonciello]

From: Mario Limonciello <mario.limonciello@amd.com>

AMD systems that support preferred cores will use "166" as their
numerator for max frequency calculations instead of "255".

Add a function for detecting preferred cores by looking at the
highest perf value on all cores.

If preferred cores are enabled return 166 and if disabled the
value in the highest perf register. As the function will be called
multiple times, cache the values for the boost numerator and if
preferred cores will be enabled in global variables.

Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
v1->v2:
 * Add a comment into amd_get_boost_ratio_numerator() as well
---
 arch/x86/kernel/acpi/cppc.c  | 93 ++++++++++++++++++++++++++++++++----
 drivers/cpufreq/amd-pstate.c | 34 +++++--------
 include/acpi/cppc_acpi.h     |  7 +++
 3 files changed, 103 insertions(+), 31 deletions(-)

diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c
index a75dcb382c786..df367bc359308 100644
--- a/arch/x86/kernel/acpi/cppc.c
+++ b/arch/x86/kernel/acpi/cppc.c
@@ -9,6 +9,16 @@
 #include <asm/processor.h>
 #include <asm/topology.h>
 
+#define CPPC_HIGHEST_PERF_PREFCORE	166
+
+enum amd_pref_core {
+	AMD_PREF_CORE_UNKNOWN = 0,
+	AMD_PREF_CORE_SUPPORTED,
+	AMD_PREF_CORE_UNSUPPORTED,
+};
+static enum amd_pref_core amd_pref_core_detected;
+static u64 boost_numerator;
+
 /* Refer to drivers/acpi/cppc_acpi.c for the description of functions */
 
 bool cpc_supported_by_cpu(void)
@@ -146,6 +156,66 @@ int amd_get_highest_perf(unsigned int cpu, u32 *highest_perf)
 }
 EXPORT_SYMBOL_GPL(amd_get_highest_perf);
 
+/**
+ * amd_detect_prefcore: Detect if CPUs in the system support preferred cores
+ * @detected: Output variable for the result of the detection.
+ *
+ * Determine whether CPUs in the system support preferred cores. On systems
+ * that support preferred cores, different highest perf values will be found
+ * on different cores. On other systems, the highest perf value will be the
+ * same on all cores.
+ *
+ * The result of the detection will be stored in the 'detected' parameter.
+ *
+ * Return: 0 for success, negative error code otherwise
+ */
+int amd_detect_prefcore(bool *detected)
+{
+	int cpu, count = 0;
+	u64 highest_perf[2] = {0};
+
+	if (WARN_ON(!detected))
+		return -EINVAL;
+
+	switch (amd_pref_core_detected) {
+	case AMD_PREF_CORE_SUPPORTED:
+		*detected = true;
+		return 0;
+	case AMD_PREF_CORE_UNSUPPORTED:
+		*detected = false;
+		return 0;
+	default:
+		break;
+	}
+
+	for_each_present_cpu(cpu) {
+		u32 tmp;
+		int ret;
+
+		ret = amd_get_highest_perf(cpu, &tmp);
+		if (ret)
+			return ret;
+
+		if (!count || (count == 1 && tmp != highest_perf[0]))
+			highest_perf[count++] = tmp;
+
+		if (count == 2)
+			break;
+	}
+
+	*detected = (count == 2);
+	boost_numerator = highest_perf[0];
+
+	amd_pref_core_detected = *detected ? AMD_PREF_CORE_SUPPORTED :
+					     AMD_PREF_CORE_UNSUPPORTED;
+
+	pr_debug("AMD CPPC preferred core is %ssupported (highest perf: 0x%llx)\n",
+		 *detected ? "" : "un", highest_perf[0]);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(amd_detect_prefcore);
+
 /**
  * amd_get_boost_ratio_numerator: Get the numerator to use for boost ratio calculation
  * @cpu: CPU to get numerator for.
@@ -155,24 +225,27 @@ EXPORT_SYMBOL_GPL(amd_get_highest_perf);
  * a CPU. On systems that support preferred cores, this will be a hardcoded
  * value. On other systems this will the highest performance register value.
  *
+ * If booting the system with amd-pstate enabled but preferred cores disabled then
+ * the correct boost numerator will be returned to match hardware capabilities
+ * even if the preferred cores scheduling hints are not enabled.
+ *
  * Return: 0 for success, negative error code otherwise.
  */
 int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator)
 {
-	struct cpuinfo_x86 *c = &boot_cpu_data;
+	bool prefcore;
+	int ret;
 
-	if (c->x86 == 0x17 && ((c->x86_model >= 0x30 && c->x86_model < 0x40) ||
-			       (c->x86_model >= 0x70 && c->x86_model < 0x80))) {
-		*numerator = 166;
-		return 0;
-	}
+	ret = amd_detect_prefcore(&prefcore);
+	if (ret)
+		return ret;
 
-	if (c->x86 == 0x19 && ((c->x86_model >= 0x20 && c->x86_model < 0x30) ||
-			       (c->x86_model >= 0x40 && c->x86_model < 0x70))) {
-		*numerator = 166;
+	/* without preferred cores, return the highest perf register value */
+	if (!prefcore) {
+		*numerator = boost_numerator;
 		return 0;
 	}
-	*numerator = 255;
+	*numerator = CPPC_HIGHEST_PERF_PREFCORE;
 
 	return 0;
 }
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 44df6ef66b5fa..c29cdf2d3882c 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -807,32 +807,18 @@ static DECLARE_WORK(sched_prefcore_work, amd_pstste_sched_prefcore_workfn);
 
 static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata)
 {
-	int ret, prio;
-	u32 highest_perf;
-
-	ret = amd_get_highest_perf(cpudata->cpu, &highest_perf);
-	if (ret)
+	/* user disabled or not detected */
+	if (!amd_pstate_prefcore)
 		return;
 
 	cpudata->hw_prefcore = true;
-	/* check if CPPC preferred core feature is enabled*/
-	if (highest_perf < CPPC_MAX_PERF)
-		prio = (int)highest_perf;
-	else {
-		pr_debug("AMD CPPC preferred core is unsupported!\n");
-		cpudata->hw_prefcore = false;
-		return;
-	}
-
-	if (!amd_pstate_prefcore)
-		return;
 
 	/*
 	 * The priorities can be set regardless of whether or not
 	 * sched_set_itmt_support(true) has been called and it is valid to
 	 * update them at any time after it has been called.
 	 */
-	sched_set_itmt_core_prio(prio, cpudata->cpu);
+	sched_set_itmt_core_prio((int)READ_ONCE(cpudata->highest_perf), cpudata->cpu);
 
 	schedule_work(&sched_prefcore_work);
 }
@@ -998,12 +984,12 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 
 	cpudata->cpu = policy->cpu;
 
-	amd_pstate_init_prefcore(cpudata);
-
 	ret = amd_pstate_init_perf(cpudata);
 	if (ret)
 		goto free_cpudata1;
 
+	amd_pstate_init_prefcore(cpudata);
+
 	ret = amd_pstate_init_freq(cpudata);
 	if (ret)
 		goto free_cpudata1;
@@ -1453,12 +1439,12 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 	cpudata->cpu = policy->cpu;
 	cpudata->epp_policy = 0;
 
-	amd_pstate_init_prefcore(cpudata);
-
 	ret = amd_pstate_init_perf(cpudata);
 	if (ret)
 		goto free_cpudata1;
 
+	amd_pstate_init_prefcore(cpudata);
+
 	ret = amd_pstate_init_freq(cpudata);
 	if (ret)
 		goto free_cpudata1;
@@ -1920,6 +1906,12 @@ static int __init amd_pstate_init(void)
 		static_call_update(amd_pstate_update_perf, cppc_update_perf);
 	}
 
+	if (amd_pstate_prefcore) {
+		ret = amd_detect_prefcore(&amd_pstate_prefcore);
+		if (ret)
+			return ret;
+	}
+
 	/* enable amd pstate feature */
 	ret = amd_pstate_enable(true);
 	if (ret) {
diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
index f7c7abf2a95e9..67325a9294ba1 100644
--- a/include/acpi/cppc_acpi.h
+++ b/include/acpi/cppc_acpi.h
@@ -136,6 +136,8 @@ struct cppc_cpudata {
 	cpumask_var_t shared_cpu_map;
 };
 
+extern int amd_get_highest_perf(unsigned int cpu, u32 *highest_perf);
+extern int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator);
 #ifdef CONFIG_ACPI_CPPC_LIB
 extern int cppc_get_desired_perf(int cpunum, u64 *desired_perf);
 extern int cppc_get_nominal_perf(int cpunum, u64 *nominal_perf);
@@ -161,6 +163,7 @@ extern int cppc_get_auto_sel_caps(int cpunum, struct cppc_perf_caps *perf_caps);
 extern int cppc_set_auto_sel(int cpu, bool enable);
 extern int amd_get_highest_perf(unsigned int cpu, u32 *highest_perf);
 extern int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator);
+extern int amd_detect_prefcore(bool *detected);
 #else /* !CONFIG_ACPI_CPPC_LIB */
 static inline int cppc_get_desired_perf(int cpunum, u64 *desired_perf)
 {
@@ -242,6 +245,10 @@ static inline int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator
 {
 	return -EOPNOTSUPP;
 }
+static inline int amd_detect_prefcore(bool *detected)
+{
+	return -ENODEV;
+}
 #endif /* !CONFIG_ACPI_CPPC_LIB */
 
 #endif /* _CPPC_ACPI_H*/
-- 
2.43.0

[PATCH v2 08/11] cpufreq: amd-pstate: Merge amd_pstate_highest_perf_set() into amd_get_boost_ratio_numerator()

[Mario Limonciello]

From: Mario Limonciello <mario.limonciello@amd.com>

The special case in amd_pstate_highest_perf_set() is the value used
for calculating the boost numerator.  Merge this into
amd_get_boost_ratio_numerator() and then use that to calculate boost
ratio.

This allows dropping more special casing of the highest perf value.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
v1->v2:
 * Document that preferred cores will have different values for highest
   perf.
 * Fix an uninitialized variable caused by merge
---
 Documentation/admin-guide/pm/amd-pstate.rst |  3 +-
 arch/x86/kernel/acpi/cppc.c                 | 16 +++++++
 drivers/cpufreq/amd-pstate.c                | 52 ++++-----------------
 3 files changed, 28 insertions(+), 43 deletions(-)

diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst
index d0324d44f5482..e13915c540648 100644
--- a/Documentation/admin-guide/pm/amd-pstate.rst
+++ b/Documentation/admin-guide/pm/amd-pstate.rst
@@ -251,7 +251,8 @@ 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``.
+``cpuinfo``. On systems that support preferred core, the driver will have
+different values for some cores than others.
 This attribute is read-only.
 
 ``amd_pstate_lowest_nonlinear_freq``
diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c
index df367bc359308..956984054bf30 100644
--- a/arch/x86/kernel/acpi/cppc.c
+++ b/arch/x86/kernel/acpi/cppc.c
@@ -9,6 +9,7 @@
 #include <asm/processor.h>
 #include <asm/topology.h>
 
+#define CPPC_HIGHEST_PERF_PERFORMANCE	196
 #define CPPC_HIGHEST_PERF_PREFCORE	166
 
 enum amd_pref_core {
@@ -245,6 +246,21 @@ int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator)
 		*numerator = boost_numerator;
 		return 0;
 	}
+
+	/*
+	 * For AMD CPUs with Family ID 19H and Model ID range 0x70 to 0x7f,
+	 * the highest performance level is set to 196.
+	 * https://bugzilla.kernel.org/show_bug.cgi?id=218759
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_ZEN4)) {
+		switch (boot_cpu_data.x86_model) {
+		case 0x70 ... 0x7f:
+			*numerator = CPPC_HIGHEST_PERF_PERFORMANCE;
+			return 0;
+		default:
+			break;
+		}
+	}
 	*numerator = CPPC_HIGHEST_PERF_PREFCORE;
 
 	return 0;
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index c29cdf2d3882c..3ae41af6f041e 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -52,8 +52,6 @@
 #define AMD_PSTATE_TRANSITION_LATENCY	20000
 #define AMD_PSTATE_TRANSITION_DELAY	1000
 #define AMD_PSTATE_FAST_CPPC_TRANSITION_DELAY 600
-#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
@@ -372,43 +370,17 @@ static inline int amd_pstate_enable(bool enable)
 	return static_call(amd_pstate_enable)(enable);
 }
 
-static u32 amd_pstate_highest_perf_set(struct amd_cpudata *cpudata)
-{
-	struct cpuinfo_x86 *c = &cpu_data(0);
-
-	/*
-	 * For AMD CPUs with Family ID 19H and Model ID range 0x70 to 0x7f,
-	 * the highest performance level is set to 196.
-	 * https://bugzilla.kernel.org/show_bug.cgi?id=218759
-	 */
-	if (c->x86 == 0x19 && (c->x86_model >= 0x70 && c->x86_model <= 0x7f))
-		return CPPC_HIGHEST_PERF_PERFORMANCE;
-
-	return CPPC_HIGHEST_PERF_DEFAULT;
-}
-
 static int pstate_init_perf(struct amd_cpudata *cpudata)
 {
 	u64 cap1;
-	u32 highest_perf;
 
 	int ret = rdmsrl_safe_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1,
 				     &cap1);
 	if (ret)
 		return ret;
 
-	/* 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 AMD_CPPC_HIGHEST_PERF(cap1) value as
-	 * the default max perf.
-	 */
-	if (cpudata->hw_prefcore)
-		highest_perf = amd_pstate_highest_perf_set(cpudata);
-	else
-		highest_perf = AMD_CPPC_HIGHEST_PERF(cap1);
-
-	WRITE_ONCE(cpudata->highest_perf, highest_perf);
-	WRITE_ONCE(cpudata->max_limit_perf, highest_perf);
+	WRITE_ONCE(cpudata->highest_perf, AMD_CPPC_HIGHEST_PERF(cap1));
+	WRITE_ONCE(cpudata->max_limit_perf, AMD_CPPC_HIGHEST_PERF(cap1));
 	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));
@@ -420,19 +392,13 @@ static int pstate_init_perf(struct amd_cpudata *cpudata)
 static int cppc_init_perf(struct amd_cpudata *cpudata)
 {
 	struct cppc_perf_caps cppc_perf;
-	u32 highest_perf;
 
 	int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf);
 	if (ret)
 		return ret;
 
-	if (cpudata->hw_prefcore)
-		highest_perf = amd_pstate_highest_perf_set(cpudata);
-	else
-		highest_perf = cppc_perf.highest_perf;
-
-	WRITE_ONCE(cpudata->highest_perf, highest_perf);
-	WRITE_ONCE(cpudata->max_limit_perf, highest_perf);
+	WRITE_ONCE(cpudata->highest_perf, cppc_perf.highest_perf);
+	WRITE_ONCE(cpudata->max_limit_perf, cppc_perf.highest_perf);
 	WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf);
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf,
 		   cppc_perf.lowest_nonlinear_perf);
@@ -905,8 +871,8 @@ static u32 amd_pstate_get_transition_latency(unsigned int cpu)
 static int amd_pstate_init_freq(struct amd_cpudata *cpudata)
 {
 	int ret;
-	u32 min_freq;
-	u32 highest_perf, max_freq;
+	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;
@@ -928,8 +894,10 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata)
 
 	nominal_perf = READ_ONCE(cpudata->nominal_perf);
 
-	highest_perf = READ_ONCE(cpudata->highest_perf);
-	boost_ratio = div_u64(highest_perf << SCHED_CAPACITY_SHIFT, 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);
 	max_freq = (nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT) * 1000;
 
 	lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf);
-- 
2.43.0

[PATCH v2 09/11] cpufreq: amd-pstate: Optimize amd_pstate_update_limits()

[Mario Limonciello]

From: Mario Limonciello <mario.limonciello@amd.com>

Don't take and release the mutex when prefcore isn't present and
avoid initialization of variables that will be initially set
in the function.

Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
Reviewed-by: Perry Yuan <perry.yuan@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 drivers/cpufreq/amd-pstate.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 3ae41af6f041e..9312d4e40994f 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -797,17 +797,17 @@ static void amd_pstate_update_limits(unsigned int cpu)
 	int ret;
 	bool highest_perf_changed = false;
 
-	mutex_lock(&amd_pstate_driver_lock);
-	if ((!amd_pstate_prefcore) || (!cpudata->hw_prefcore))
-		goto free_cpufreq_put;
+	if (!amd_pstate_prefcore)
+		return;
 
+	mutex_lock(&amd_pstate_driver_lock);
 	ret = amd_get_highest_perf(cpu, &cur_high);
 	if (ret)
 		goto free_cpufreq_put;
 
 	prev_high = READ_ONCE(cpudata->prefcore_ranking);
-	if (prev_high != cur_high) {
-		highest_perf_changed = true;
+	highest_perf_changed = (prev_high != cur_high);
+	if (highest_perf_changed) {
 		WRITE_ONCE(cpudata->prefcore_ranking, cur_high);
 
 		if (cur_high < CPPC_MAX_PERF)
-- 
2.43.0

[PATCH v2 10/11] cpufreq: amd-pstate: Add documentation for `amd_pstate_hw_prefcore`

[Mario Limonciello]

From: Mario Limonciello <mario.limonciello@amd.com>

Explain that the sysfs file represents both preferred core being
enabled by the user and supported by the hardware.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 Documentation/admin-guide/pm/amd-pstate.rst | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst
index e13915c540648..d5c050ea390dc 100644
--- a/Documentation/admin-guide/pm/amd-pstate.rst
+++ b/Documentation/admin-guide/pm/amd-pstate.rst
@@ -263,6 +263,11 @@ lowest non-linear performance in `AMD CPPC Performance Capability
 <perf_cap_>`_.)
 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.
+
 ``energy_performance_available_preferences``
 
 A list of all the supported EPP preferences that could be used for
-- 
2.43.0

[PATCH v2 11/11] amd-pstate: Add missing documentation for `amd_pstate_prefcore_ranking`

[Mario Limonciello]

From: Mario Limonciello <mario.limonciello@amd.com>

`amd_pstate_prefcore_ranking` reflects the dynamic rankings of a CPU
core based on platform conditions.  Explicitly include it in the
documentation.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 Documentation/admin-guide/pm/amd-pstate.rst | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst
index d5c050ea390dc..210a808b74ec2 100644
--- a/Documentation/admin-guide/pm/amd-pstate.rst
+++ b/Documentation/admin-guide/pm/amd-pstate.rst
@@ -252,7 +252,8 @@ 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.
+different values for some cores than others and this will reflect the values
+advertised by the platform at bootup.
 This attribute is read-only.
 
 ``amd_pstate_lowest_nonlinear_freq``
@@ -268,6 +269,12 @@ This attribute is read-only.
 Whether the platform supports the preferred core feature and it has been
 enabled. This attribute is read-only.
 
+``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.
+
 ``energy_performance_available_preferences``
 
 A list of all the supported EPP preferences that could be used for
-- 
2.43.0

Re: [PATCH v2 07/11] x86/amd: Detect preferred cores in amd_get_boost_ratio_numerator()

[kernel test robot]

Hi Mario,

kernel test robot noticed the following build errors:

[auto build test ERROR on rafael-pm/linux-next]
[also build test ERROR on rafael-pm/bleeding-edge tip/x86/core tip/master linus/master v6.11-rc6 next-20240904]
[cannot apply to tip/auto-latest]
[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/Mario-Limonciello/x86-amd-Move-amd_get_highest_perf-from-amd-c-to-cppc-c/20240904-044140
base:   https://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git linux-next
patch link:    https://lore.kernel.org/r/20240903203701.2695040-8-superm1%40kernel.org
patch subject: [PATCH v2 07/11] x86/amd: Detect preferred cores in amd_get_boost_ratio_numerator()
config: i386-allmodconfig (https://download.01.org/0day-ci/archive/20240905/202409050432.AoAbkkyJ-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/20240905/202409050432.AoAbkkyJ-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/202409050432.AoAbkkyJ-lkp@intel.com/

All errors (new ones prefixed by >>):

   In file included from drivers/cpufreq/amd-pstate.c:42:
>> include/acpi/cppc_acpi.h:242:19: error: static declaration of 'amd_get_highest_perf' follows non-static declaration
     242 | static inline int amd_get_highest_perf(unsigned int cpu, u32 *highest_perf)
         |                   ^~~~~~~~~~~~~~~~~~~~
   include/acpi/cppc_acpi.h:141:12: note: previous declaration of 'amd_get_highest_perf' with type 'int(unsigned int,  u32 *)' {aka 'int(unsigned int,  unsigned int *)'}
     141 | extern int amd_get_highest_perf(unsigned int cpu, u32 *highest_perf);
         |            ^~~~~~~~~~~~~~~~~~~~
>> include/acpi/cppc_acpi.h:246:19: error: static declaration of 'amd_get_boost_ratio_numerator' follows non-static declaration
     246 | static inline int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator)
         |                   ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   include/acpi/cppc_acpi.h:142:12: note: previous declaration of 'amd_get_boost_ratio_numerator' with type 'int(unsigned int,  u64 *)' {aka 'int(unsigned int,  long long unsigned int *)'}
     142 | extern int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator);
         |            ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~


vim +/amd_get_highest_perf +242 include/acpi/cppc_acpi.h

337aadff8e4567 Ashwin Chaugule    2015-10-02  140  
7885bc49834406 Mario Limonciello  2024-09-03  141  extern int amd_get_highest_perf(unsigned int cpu, u32 *highest_perf);
7885bc49834406 Mario Limonciello  2024-09-03  142  extern int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator);
8a02d99876362f Rafael J. Wysocki  2021-03-16  143  #ifdef CONFIG_ACPI_CPPC_LIB
1757d05f3112ac Xiongfeng Wang     2019-02-17  144  extern int cppc_get_desired_perf(int cpunum, u64 *desired_perf);
0654cf05d17bc4 Rafael J. Wysocki  2021-09-04  145  extern int cppc_get_nominal_perf(int cpunum, u64 *nominal_perf);
12753d71e8c5c3 Meng Li            2024-01-19  146  extern int cppc_get_highest_perf(int cpunum, u64 *highest_perf);
337aadff8e4567 Ashwin Chaugule    2015-10-02  147  extern int cppc_get_perf_ctrs(int cpu, struct cppc_perf_fb_ctrs *perf_fb_ctrs);
337aadff8e4567 Ashwin Chaugule    2015-10-02  148  extern int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls);
fb0b00af04d083 Jinzhou Su         2021-12-24  149  extern int cppc_set_enable(int cpu, bool enable);
337aadff8e4567 Ashwin Chaugule    2015-10-02  150  extern int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps);
ae2df912d1a557 Jeremy Linton      2022-09-12  151  extern bool cppc_perf_ctrs_in_pcc(void);
50b813b147e9eb Vincent Guittot    2023-12-11  152  extern unsigned int cppc_perf_to_khz(struct cppc_perf_caps *caps, unsigned int perf);
50b813b147e9eb Vincent Guittot    2023-12-11  153  extern unsigned int cppc_khz_to_perf(struct cppc_perf_caps *caps, unsigned int freq);
a28b2bfc099c6b Ionela Voinescu    2020-12-14  154  extern bool acpi_cpc_valid(void);
3cc30dd00a580c Pierre Gondois     2022-05-18  155  extern bool cppc_allow_fast_switch(void);
a28b2bfc099c6b Ionela Voinescu    2020-12-14  156  extern int acpi_get_psd_map(unsigned int cpu, struct cppc_cpudata *cpu_data);
be8b88d7d98771 Prakash, Prashanth 2016-08-16  157  extern unsigned int cppc_get_transition_latency(int cpu);
ad3bc25a320742 Borislav Petkov    2018-12-05  158  extern bool cpc_ffh_supported(void);
8b356e536e69f3 Mario Limonciello  2022-07-05  159  extern bool cpc_supported_by_cpu(void);
ad3bc25a320742 Borislav Petkov    2018-12-05  160  extern int cpc_read_ffh(int cpunum, struct cpc_reg *reg, u64 *val);
ad3bc25a320742 Borislav Petkov    2018-12-05  161  extern int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val);
7bc1fcd3990182 Perry Yuan         2023-01-31  162  extern int cppc_get_epp_perf(int cpunum, u64 *epp_perf);
7bc1fcd3990182 Perry Yuan         2023-01-31  163  extern int cppc_set_epp_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls, bool enable);
c984f5d5d45bd5 Wyes Karny         2023-03-07  164  extern int cppc_get_auto_sel_caps(int cpunum, struct cppc_perf_caps *perf_caps);
c984f5d5d45bd5 Wyes Karny         2023-03-07  165  extern int cppc_set_auto_sel(int cpu, bool enable);
cfa6630658f7de Mario Limonciello  2024-09-03  166  extern int amd_get_highest_perf(unsigned int cpu, u32 *highest_perf);
402eea79aece78 Mario Limonciello  2024-09-03  167  extern int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator);
7885bc49834406 Mario Limonciello  2024-09-03  168  extern int amd_detect_prefcore(bool *detected);
8a02d99876362f Rafael J. Wysocki  2021-03-16  169  #else /* !CONFIG_ACPI_CPPC_LIB */
8a02d99876362f Rafael J. Wysocki  2021-03-16  170  static inline int cppc_get_desired_perf(int cpunum, u64 *desired_perf)
8a02d99876362f Rafael J. Wysocki  2021-03-16  171  {
e224a868e488cf Mario Limonciello  2024-09-03  172  	return -EOPNOTSUPP;
8a02d99876362f Rafael J. Wysocki  2021-03-16  173  }
0654cf05d17bc4 Rafael J. Wysocki  2021-09-04  174  static inline int cppc_get_nominal_perf(int cpunum, u64 *nominal_perf)
0654cf05d17bc4 Rafael J. Wysocki  2021-09-04  175  {
e224a868e488cf Mario Limonciello  2024-09-03  176  	return -EOPNOTSUPP;
0654cf05d17bc4 Rafael J. Wysocki  2021-09-04  177  }
12753d71e8c5c3 Meng Li            2024-01-19  178  static inline int cppc_get_highest_perf(int cpunum, u64 *highest_perf)
12753d71e8c5c3 Meng Li            2024-01-19  179  {
e224a868e488cf Mario Limonciello  2024-09-03  180  	return -EOPNOTSUPP;
12753d71e8c5c3 Meng Li            2024-01-19  181  }
8a02d99876362f Rafael J. Wysocki  2021-03-16  182  static inline int cppc_get_perf_ctrs(int cpu, struct cppc_perf_fb_ctrs *perf_fb_ctrs)
8a02d99876362f Rafael J. Wysocki  2021-03-16  183  {
e224a868e488cf Mario Limonciello  2024-09-03  184  	return -EOPNOTSUPP;
8a02d99876362f Rafael J. Wysocki  2021-03-16  185  }
8a02d99876362f Rafael J. Wysocki  2021-03-16  186  static inline int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
8a02d99876362f Rafael J. Wysocki  2021-03-16  187  {
e224a868e488cf Mario Limonciello  2024-09-03  188  	return -EOPNOTSUPP;
8a02d99876362f Rafael J. Wysocki  2021-03-16  189  }
fb0b00af04d083 Jinzhou Su         2021-12-24  190  static inline int cppc_set_enable(int cpu, bool enable)
fb0b00af04d083 Jinzhou Su         2021-12-24  191  {
e224a868e488cf Mario Limonciello  2024-09-03  192  	return -EOPNOTSUPP;
fb0b00af04d083 Jinzhou Su         2021-12-24  193  }
8a02d99876362f Rafael J. Wysocki  2021-03-16  194  static inline int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps)
8a02d99876362f Rafael J. Wysocki  2021-03-16  195  {
e224a868e488cf Mario Limonciello  2024-09-03  196  	return -EOPNOTSUPP;
8a02d99876362f Rafael J. Wysocki  2021-03-16  197  }
ae2df912d1a557 Jeremy Linton      2022-09-12  198  static inline bool cppc_perf_ctrs_in_pcc(void)
ae2df912d1a557 Jeremy Linton      2022-09-12  199  {
ae2df912d1a557 Jeremy Linton      2022-09-12  200  	return false;
ae2df912d1a557 Jeremy Linton      2022-09-12  201  }
8a02d99876362f Rafael J. Wysocki  2021-03-16  202  static inline bool acpi_cpc_valid(void)
8a02d99876362f Rafael J. Wysocki  2021-03-16  203  {
8a02d99876362f Rafael J. Wysocki  2021-03-16  204  	return false;
8a02d99876362f Rafael J. Wysocki  2021-03-16  205  }
3cc30dd00a580c Pierre Gondois     2022-05-18  206  static inline bool cppc_allow_fast_switch(void)
3cc30dd00a580c Pierre Gondois     2022-05-18  207  {
3cc30dd00a580c Pierre Gondois     2022-05-18  208  	return false;
3cc30dd00a580c Pierre Gondois     2022-05-18  209  }
8a02d99876362f Rafael J. Wysocki  2021-03-16  210  static inline unsigned int cppc_get_transition_latency(int cpu)
8a02d99876362f Rafael J. Wysocki  2021-03-16  211  {
8a02d99876362f Rafael J. Wysocki  2021-03-16  212  	return CPUFREQ_ETERNAL;
8a02d99876362f Rafael J. Wysocki  2021-03-16  213  }
8a02d99876362f Rafael J. Wysocki  2021-03-16  214  static inline bool cpc_ffh_supported(void)
8a02d99876362f Rafael J. Wysocki  2021-03-16  215  {
8a02d99876362f Rafael J. Wysocki  2021-03-16  216  	return false;
8a02d99876362f Rafael J. Wysocki  2021-03-16  217  }
8a02d99876362f Rafael J. Wysocki  2021-03-16  218  static inline int cpc_read_ffh(int cpunum, struct cpc_reg *reg, u64 *val)
8a02d99876362f Rafael J. Wysocki  2021-03-16  219  {
e224a868e488cf Mario Limonciello  2024-09-03  220  	return -EOPNOTSUPP;
8a02d99876362f Rafael J. Wysocki  2021-03-16  221  }
8a02d99876362f Rafael J. Wysocki  2021-03-16  222  static inline int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val)
8a02d99876362f Rafael J. Wysocki  2021-03-16  223  {
e224a868e488cf Mario Limonciello  2024-09-03  224  	return -EOPNOTSUPP;
8a02d99876362f Rafael J. Wysocki  2021-03-16  225  }
7bc1fcd3990182 Perry Yuan         2023-01-31  226  static inline int cppc_set_epp_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls, bool enable)
7bc1fcd3990182 Perry Yuan         2023-01-31  227  {
e224a868e488cf Mario Limonciello  2024-09-03  228  	return -EOPNOTSUPP;
7bc1fcd3990182 Perry Yuan         2023-01-31  229  }
7bc1fcd3990182 Perry Yuan         2023-01-31  230  static inline int cppc_get_epp_perf(int cpunum, u64 *epp_perf)
7bc1fcd3990182 Perry Yuan         2023-01-31  231  {
e224a868e488cf Mario Limonciello  2024-09-03  232  	return -EOPNOTSUPP;
7bc1fcd3990182 Perry Yuan         2023-01-31  233  }
c984f5d5d45bd5 Wyes Karny         2023-03-07  234  static inline int cppc_set_auto_sel(int cpu, bool enable)
c984f5d5d45bd5 Wyes Karny         2023-03-07  235  {
e224a868e488cf Mario Limonciello  2024-09-03  236  	return -EOPNOTSUPP;
c984f5d5d45bd5 Wyes Karny         2023-03-07  237  }
c984f5d5d45bd5 Wyes Karny         2023-03-07  238  static inline int cppc_get_auto_sel_caps(int cpunum, struct cppc_perf_caps *perf_caps)
c984f5d5d45bd5 Wyes Karny         2023-03-07  239  {
e224a868e488cf Mario Limonciello  2024-09-03  240  	return -EOPNOTSUPP;
c984f5d5d45bd5 Wyes Karny         2023-03-07  241  }
cfa6630658f7de Mario Limonciello  2024-09-03 @242  static inline int amd_get_highest_perf(unsigned int cpu, u32 *highest_perf)
cfa6630658f7de Mario Limonciello  2024-09-03  243  {
cfa6630658f7de Mario Limonciello  2024-09-03  244  	return -ENODEV;
cfa6630658f7de Mario Limonciello  2024-09-03  245  }
402eea79aece78 Mario Limonciello  2024-09-03 @246  static inline int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator)
402eea79aece78 Mario Limonciello  2024-09-03  247  {
402eea79aece78 Mario Limonciello  2024-09-03  248  	return -EOPNOTSUPP;
402eea79aece78 Mario Limonciello  2024-09-03  249  }
7885bc49834406 Mario Limonciello  2024-09-03  250  static inline int amd_detect_prefcore(bool *detected)
7885bc49834406 Mario Limonciello  2024-09-03  251  {
7885bc49834406 Mario Limonciello  2024-09-03  252  	return -ENODEV;
7885bc49834406 Mario Limonciello  2024-09-03  253  }
8a02d99876362f Rafael J. Wysocki  2021-03-16  254  #endif /* !CONFIG_ACPI_CPPC_LIB */
337aadff8e4567 Ashwin Chaugule    2015-10-02  255  

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

Re: [PATCH v2 02/11] ACPI: CPPC: Adjust return code for inline functions in !CONFIG_ACPI_CPPC_LIB

[Gautham R. Shenoy]

On Tue, Sep 03, 2024 at 03:36:52PM -0500, Mario Limonciello wrote:
> From: Mario Limonciello <mario.limonciello@amd.com>
> 
> Checkpath emits the following warning:
> ```
> WARNING: ENOTSUPP is not a SUSV4 error code, prefer EOPNOTSUPP
> ```
> 
> Adjust the code accordingly.
> 
> Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>

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


> ---
>  include/acpi/cppc_acpi.h | 26 +++++++++++++-------------
>  1 file changed, 13 insertions(+), 13 deletions(-)
> 
> diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
> index 930b6afba6f4d..409a7190a4a86 100644
> --- a/include/acpi/cppc_acpi.h
> +++ b/include/acpi/cppc_acpi.h
> @@ -162,31 +162,31 @@ extern int cppc_set_auto_sel(int cpu, bool enable);
>  #else /* !CONFIG_ACPI_CPPC_LIB */
>  static inline int cppc_get_desired_perf(int cpunum, u64 *desired_perf)
>  {
> -	return -ENOTSUPP;
> +	return -EOPNOTSUPP;
>  }
>  static inline int cppc_get_nominal_perf(int cpunum, u64 *nominal_perf)
>  {
> -	return -ENOTSUPP;
> +	return -EOPNOTSUPP;
>  }
>  static inline int cppc_get_highest_perf(int cpunum, u64 *highest_perf)
>  {
> -	return -ENOTSUPP;
> +	return -EOPNOTSUPP;
>  }
>  static inline int cppc_get_perf_ctrs(int cpu, struct cppc_perf_fb_ctrs *perf_fb_ctrs)
>  {
> -	return -ENOTSUPP;
> +	return -EOPNOTSUPP;
>  }
>  static inline int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
>  {
> -	return -ENOTSUPP;
> +	return -EOPNOTSUPP;
>  }
>  static inline int cppc_set_enable(int cpu, bool enable)
>  {
> -	return -ENOTSUPP;
> +	return -EOPNOTSUPP;
>  }
>  static inline int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps)
>  {
> -	return -ENOTSUPP;
> +	return -EOPNOTSUPP;
>  }
>  static inline bool cppc_perf_ctrs_in_pcc(void)
>  {
> @@ -210,27 +210,27 @@ static inline bool cpc_ffh_supported(void)
>  }
>  static inline int cpc_read_ffh(int cpunum, struct cpc_reg *reg, u64 *val)
>  {
> -	return -ENOTSUPP;
> +	return -EOPNOTSUPP;
>  }
>  static inline int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val)
>  {
> -	return -ENOTSUPP;
> +	return -EOPNOTSUPP;
>  }
>  static inline int cppc_set_epp_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls, bool enable)
>  {
> -	return -ENOTSUPP;
> +	return -EOPNOTSUPP;
>  }
>  static inline int cppc_get_epp_perf(int cpunum, u64 *epp_perf)
>  {
> -	return -ENOTSUPP;
> +	return -EOPNOTSUPP;
>  }
>  static inline int cppc_set_auto_sel(int cpu, bool enable)
>  {
> -	return -ENOTSUPP;
> +	return -EOPNOTSUPP;
>  }
>  static inline int cppc_get_auto_sel_caps(int cpunum, struct cppc_perf_caps *perf_caps)
>  {
> -	return -ENOTSUPP;
> +	return -EOPNOTSUPP;
>  }
>  #endif /* !CONFIG_ACPI_CPPC_LIB */
>  
> -- 
> 2.43.0
> 

Re: [PATCH v2 03/11] x86/amd: Rename amd_get_highest_perf() to amd_get_boost_ratio_numerator()

[Gautham R. Shenoy]

On Tue, Sep 03, 2024 at 03:36:53PM -0500, Mario Limonciello wrote:
> From: Mario Limonciello <mario.limonciello@amd.com>
> 
> The function name is ambiguous because it returns an intermediate value
> for calculating maximum frequency rather than the CPPC 'Highest Perf'
> register.
> 
> Rename the function to clarify its use and allow the function to return
> errors. Adjust the consumer in acpi-cpufreq to catch errors.
> 
> Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>

LGTM

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

--
Thanks and Regards
gautham.

> ---
> v1->v2:
>  * Rename variable from `highest_perf` to `numerator`
>  * Fail when unable to return boost numerator
>  * Move prototype behind CONFIG_ACPI_CPPC_LIB (lkp robot)
> ---
>  arch/x86/include/asm/processor.h |  3 ---
>  arch/x86/kernel/acpi/cppc.c      | 44 +++++++++++++++++++++++---------
>  drivers/cpufreq/acpi-cpufreq.c   | 12 ++++++---
>  include/acpi/cppc_acpi.h         |  5 ++++
>  4 files changed, 46 insertions(+), 18 deletions(-)
> 
> diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
> index a75a07f4931fd..775acbdea1a96 100644
> --- a/arch/x86/include/asm/processor.h
> +++ b/arch/x86/include/asm/processor.h
> @@ -691,8 +691,6 @@ static inline u32 per_cpu_l2c_id(unsigned int cpu)
>  }
>  
>  #ifdef CONFIG_CPU_SUP_AMD
> -extern u32 amd_get_highest_perf(void);
> -
>  /*
>   * Issue a DIV 0/1 insn to clear any division data from previous DIV
>   * operations.
> @@ -705,7 +703,6 @@ static __always_inline void amd_clear_divider(void)
>  
>  extern void amd_check_microcode(void);
>  #else
> -static inline u32 amd_get_highest_perf(void)		{ return 0; }
>  static inline void amd_clear_divider(void)		{ }
>  static inline void amd_check_microcode(void)		{ }
>  #endif
> diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c
> index 7ec8f2ce859c8..660cfeb6384ba 100644
> --- a/arch/x86/kernel/acpi/cppc.c
> +++ b/arch/x86/kernel/acpi/cppc.c
> @@ -69,7 +69,7 @@ int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val)
>  static void amd_set_max_freq_ratio(void)
>  {
>  	struct cppc_perf_caps perf_caps;
> -	u64 highest_perf, nominal_perf;
> +	u64 numerator, nominal_perf;
>  	u64 perf_ratio;
>  	int rc;
>  
> @@ -79,15 +79,19 @@ static void amd_set_max_freq_ratio(void)
>  		return;
>  	}
>  
> -	highest_perf = amd_get_highest_perf();
> +	rc = amd_get_boost_ratio_numerator(0, &numerator);
> +	if (rc) {
> +		pr_debug("Could not retrieve highest performance (%d)\n", rc);
> +		return;
> +	}
>  	nominal_perf = perf_caps.nominal_perf;
>  
> -	if (!highest_perf || !nominal_perf) {
> -		pr_debug("Could not retrieve highest or nominal performance\n");
> +	if (!nominal_perf) {
> +		pr_debug("Could not retrieve nominal performance\n");
>  		return;
>  	}
>  
> -	perf_ratio = div_u64(highest_perf * SCHED_CAPACITY_SCALE, nominal_perf);
> +	perf_ratio = div_u64(numerator * SCHED_CAPACITY_SCALE, nominal_perf);
>  	/* midpoint between max_boost and max_P */
>  	perf_ratio = (perf_ratio + SCHED_CAPACITY_SCALE) >> 1;
>  	if (!perf_ratio) {
> @@ -117,18 +121,34 @@ void init_freq_invariance_cppc(void)
>  	mutex_unlock(&freq_invariance_lock);
>  }
>  
> -u32 amd_get_highest_perf(void)
> +/**
> + * amd_get_boost_ratio_numerator: Get the numerator to use for boost ratio calculation
> + * @cpu: CPU to get numerator for.
> + * @numerator: Output variable for numerator.
> + *
> + * Determine the numerator to use for calculating the boost ratio on
> + * a CPU. On systems that support preferred cores, this will be a hardcoded
> + * value. On other systems this will the highest performance register value.
> + *
> + * Return: 0 for success, negative error code otherwise.
> + */
> +int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator)
>  {
>  	struct cpuinfo_x86 *c = &boot_cpu_data;
>  
>  	if (c->x86 == 0x17 && ((c->x86_model >= 0x30 && c->x86_model < 0x40) ||
> -			       (c->x86_model >= 0x70 && c->x86_model < 0x80)))
> -		return 166;
> +			       (c->x86_model >= 0x70 && c->x86_model < 0x80))) {
> +		*numerator = 166;
> +		return 0;
> +	}
>  
>  	if (c->x86 == 0x19 && ((c->x86_model >= 0x20 && c->x86_model < 0x30) ||
> -			       (c->x86_model >= 0x40 && c->x86_model < 0x70)))
> -		return 166;
> +			       (c->x86_model >= 0x40 && c->x86_model < 0x70))) {
> +		*numerator = 166;
> +		return 0;
> +	}
> +	*numerator = 255;
>  
> -	return 255;
> +	return 0;
>  }
> -EXPORT_SYMBOL_GPL(amd_get_highest_perf);
> +EXPORT_SYMBOL_GPL(amd_get_boost_ratio_numerator);
> diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
> index a8ca625a98b89..0f04feb6cafaf 100644
> --- a/drivers/cpufreq/acpi-cpufreq.c
> +++ b/drivers/cpufreq/acpi-cpufreq.c
> @@ -642,10 +642,16 @@ static u64 get_max_boost_ratio(unsigned int cpu)
>  		return 0;
>  	}
>  
> -	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
> -		highest_perf = amd_get_highest_perf();
> -	else
> +	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
> +		ret = amd_get_boost_ratio_numerator(cpu, &highest_perf);
> +		if (ret) {
> +			pr_debug("CPU%d: Unable to get boost ratio numerator (%d)\n",
> +				 cpu, ret);
> +			return 0;
> +		}
> +	} else {
>  		highest_perf = perf_caps.highest_perf;
> +	}
>  
>  	nominal_perf = perf_caps.nominal_perf;
>  
> diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
> index 409a7190a4a86..97861abc5f5b8 100644
> --- a/include/acpi/cppc_acpi.h
> +++ b/include/acpi/cppc_acpi.h
> @@ -159,6 +159,7 @@ extern int cppc_get_epp_perf(int cpunum, u64 *epp_perf);
>  extern int cppc_set_epp_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls, bool enable);
>  extern int cppc_get_auto_sel_caps(int cpunum, struct cppc_perf_caps *perf_caps);
>  extern int cppc_set_auto_sel(int cpu, bool enable);
> +extern int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator);
>  #else /* !CONFIG_ACPI_CPPC_LIB */
>  static inline int cppc_get_desired_perf(int cpunum, u64 *desired_perf)
>  {
> @@ -232,6 +233,10 @@ static inline int cppc_get_auto_sel_caps(int cpunum, struct cppc_perf_caps *perf
>  {
>  	return -EOPNOTSUPP;
>  }
> +static inline int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator)
> +{
> +	return -EOPNOTSUPP;
> +}
>  #endif /* !CONFIG_ACPI_CPPC_LIB */
>  
>  #endif /* _CPPC_ACPI_H*/
> -- 
> 2.43.0
> 

Re: [PATCH v2 04/11] ACPI: CPPC: Drop check for non zero perf ratio

[Gautham R. Shenoy]

On Tue, Sep 03, 2024 at 03:36:54PM -0500, Mario Limonciello wrote:
> From: Mario Limonciello <mario.limonciello@amd.com>
> 
> perf_ratio is a u64 and SCHED_CAPACITY_SCALE is a larg number.

s/larg/large

> Shifting by one will never have a zero value.
> 
> Drop the check.
> 
> Suggested-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
> Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>

Other than that, LGTM

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

--
Thanks and Regards
gautham

> ---
>  arch/x86/kernel/acpi/cppc.c | 7 +------
>  1 file changed, 1 insertion(+), 6 deletions(-)
> 
> diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c
> index 660cfeb6384ba..e65c77afab318 100644
> --- a/arch/x86/kernel/acpi/cppc.c
> +++ b/arch/x86/kernel/acpi/cppc.c
> @@ -91,13 +91,8 @@ static void amd_set_max_freq_ratio(void)
>  		return;
>  	}
>  
> -	perf_ratio = div_u64(numerator * SCHED_CAPACITY_SCALE, nominal_perf);
>  	/* midpoint between max_boost and max_P */
> -	perf_ratio = (perf_ratio + SCHED_CAPACITY_SCALE) >> 1;
> -	if (!perf_ratio) {
> -		pr_debug("Non-zero highest/nominal perf values led to a 0 ratio\n");
> -		return;
> -	}
> +	perf_ratio = (div_u64(numerator * SCHED_CAPACITY_SCALE, nominal_perf) + SCHED_CAPACITY_SCALE) >> 1;
>  
>  	freq_invariance_set_perf_ratio(perf_ratio, false);
>  }
> -- 
> 2.43.0
> 

Re: [PATCH v2 08/11] cpufreq: amd-pstate: Merge amd_pstate_highest_perf_set() into amd_get_boost_ratio_numerator()

[Gautham R. Shenoy]

On Tue, Sep 03, 2024 at 03:36:58PM -0500, Mario Limonciello wrote:
> From: Mario Limonciello <mario.limonciello@amd.com>
> 
> The special case in amd_pstate_highest_perf_set() is the value used
> for calculating the boost numerator.  Merge this into
> amd_get_boost_ratio_numerator() and then use that to calculate boost
> ratio.
> 
> This allows dropping more special casing of the highest perf value.
> 
> Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>

> ---
> v1->v2:
>  * Document that preferred cores will have different values for highest
>    perf.
>  * Fix an uninitialized variable caused by merge
> ---
>  Documentation/admin-guide/pm/amd-pstate.rst |  3 +-
>  arch/x86/kernel/acpi/cppc.c                 | 16 +++++++
>  drivers/cpufreq/amd-pstate.c                | 52 ++++-----------------
>  3 files changed, 28 insertions(+), 43 deletions(-)
> 
> diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst
> index d0324d44f5482..e13915c540648 100644
> --- a/Documentation/admin-guide/pm/amd-pstate.rst
> +++ b/Documentation/admin-guide/pm/amd-pstate.rst
> @@ -251,7 +251,8 @@ 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``.
> +``cpuinfo``. On systems that support preferred core, the driver will have
> +different values for some cores than others.

Thanks for documenting this.

The patch looks good to me.

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


--
Thanks and Regards
gautham.

>  This attribute is read-only.
>  
>  ``amd_pstate_lowest_nonlinear_freq``
> diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c
> index df367bc359308..956984054bf30 100644
> --- a/arch/x86/kernel/acpi/cppc.c
> +++ b/arch/x86/kernel/acpi/cppc.c
> @@ -9,6 +9,7 @@
>  #include <asm/processor.h>
>  #include <asm/topology.h>
>  
> +#define CPPC_HIGHEST_PERF_PERFORMANCE	196
>  #define CPPC_HIGHEST_PERF_PREFCORE	166
>  
>  enum amd_pref_core {
> @@ -245,6 +246,21 @@ int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator)
>  		*numerator = boost_numerator;
>  		return 0;
>  	}
> +
> +	/*
> +	 * For AMD CPUs with Family ID 19H and Model ID range 0x70 to 0x7f,
> +	 * the highest performance level is set to 196.
> +	 * https://bugzilla.kernel.org/show_bug.cgi?id=218759
> +	 */
> +	if (cpu_feature_enabled(X86_FEATURE_ZEN4)) {
> +		switch (boot_cpu_data.x86_model) {
> +		case 0x70 ... 0x7f:
> +			*numerator = CPPC_HIGHEST_PERF_PERFORMANCE;
> +			return 0;
> +		default:
> +			break;
> +		}
> +	}
>  	*numerator = CPPC_HIGHEST_PERF_PREFCORE;
>  
>  	return 0;
> diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
> index c29cdf2d3882c..3ae41af6f041e 100644
> --- a/drivers/cpufreq/amd-pstate.c
> +++ b/drivers/cpufreq/amd-pstate.c
> @@ -52,8 +52,6 @@
>  #define AMD_PSTATE_TRANSITION_LATENCY	20000
>  #define AMD_PSTATE_TRANSITION_DELAY	1000
>  #define AMD_PSTATE_FAST_CPPC_TRANSITION_DELAY 600
> -#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
> @@ -372,43 +370,17 @@ static inline int amd_pstate_enable(bool enable)
>  	return static_call(amd_pstate_enable)(enable);
>  }
>  
> -static u32 amd_pstate_highest_perf_set(struct amd_cpudata *cpudata)
> -{
> -	struct cpuinfo_x86 *c = &cpu_data(0);
> -
> -	/*
> -	 * For AMD CPUs with Family ID 19H and Model ID range 0x70 to 0x7f,
> -	 * the highest performance level is set to 196.
> -	 * https://bugzilla.kernel.org/show_bug.cgi?id=218759
> -	 */
> -	if (c->x86 == 0x19 && (c->x86_model >= 0x70 && c->x86_model <= 0x7f))
> -		return CPPC_HIGHEST_PERF_PERFORMANCE;
> -
> -	return CPPC_HIGHEST_PERF_DEFAULT;
> -}
> -
>  static int pstate_init_perf(struct amd_cpudata *cpudata)
>  {
>  	u64 cap1;
> -	u32 highest_perf;
>  
>  	int ret = rdmsrl_safe_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1,
>  				     &cap1);
>  	if (ret)
>  		return ret;
>  
> -	/* 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 AMD_CPPC_HIGHEST_PERF(cap1) value as
> -	 * the default max perf.
> -	 */
> -	if (cpudata->hw_prefcore)
> -		highest_perf = amd_pstate_highest_perf_set(cpudata);
> -	else
> -		highest_perf = AMD_CPPC_HIGHEST_PERF(cap1);
> -
> -	WRITE_ONCE(cpudata->highest_perf, highest_perf);
> -	WRITE_ONCE(cpudata->max_limit_perf, highest_perf);
> +	WRITE_ONCE(cpudata->highest_perf, AMD_CPPC_HIGHEST_PERF(cap1));
> +	WRITE_ONCE(cpudata->max_limit_perf, AMD_CPPC_HIGHEST_PERF(cap1));
>  	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));
> @@ -420,19 +392,13 @@ static int pstate_init_perf(struct amd_cpudata *cpudata)
>  static int cppc_init_perf(struct amd_cpudata *cpudata)
>  {
>  	struct cppc_perf_caps cppc_perf;
> -	u32 highest_perf;
>  
>  	int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf);
>  	if (ret)
>  		return ret;
>  
> -	if (cpudata->hw_prefcore)
> -		highest_perf = amd_pstate_highest_perf_set(cpudata);
> -	else
> -		highest_perf = cppc_perf.highest_perf;
> -
> -	WRITE_ONCE(cpudata->highest_perf, highest_perf);
> -	WRITE_ONCE(cpudata->max_limit_perf, highest_perf);
> +	WRITE_ONCE(cpudata->highest_perf, cppc_perf.highest_perf);
> +	WRITE_ONCE(cpudata->max_limit_perf, cppc_perf.highest_perf);
>  	WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf);
>  	WRITE_ONCE(cpudata->lowest_nonlinear_perf,
>  		   cppc_perf.lowest_nonlinear_perf);
> @@ -905,8 +871,8 @@ static u32 amd_pstate_get_transition_latency(unsigned int cpu)
>  static int amd_pstate_init_freq(struct amd_cpudata *cpudata)
>  {
>  	int ret;
> -	u32 min_freq;
> -	u32 highest_perf, max_freq;
> +	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;
> @@ -928,8 +894,10 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata)
>  
>  	nominal_perf = READ_ONCE(cpudata->nominal_perf);
>  
> -	highest_perf = READ_ONCE(cpudata->highest_perf);
> -	boost_ratio = div_u64(highest_perf << SCHED_CAPACITY_SHIFT, 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);
>  	max_freq = (nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT) * 1000;
>  
>  	lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf);
> -- 
> 2.43.0
> 

Re: [PATCH v2 10/11] cpufreq: amd-pstate: Add documentation for `amd_pstate_hw_prefcore`

[Gautham R. Shenoy]

On Tue, Sep 03, 2024 at 03:37:00PM -0500, Mario Limonciello wrote:
> From: Mario Limonciello <mario.limonciello@amd.com>
> 
> Explain that the sysfs file represents both preferred core being
> enabled by the user and supported by the hardware.
> 
> Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>

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

> ---
>  Documentation/admin-guide/pm/amd-pstate.rst | 5 +++++
>  1 file changed, 5 insertions(+)
> 
> diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst
> index e13915c540648..d5c050ea390dc 100644
> --- a/Documentation/admin-guide/pm/amd-pstate.rst
> +++ b/Documentation/admin-guide/pm/amd-pstate.rst
> @@ -263,6 +263,11 @@ lowest non-linear performance in `AMD CPPC Performance Capability
>  <perf_cap_>`_.)
>  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.
> +
>  ``energy_performance_available_preferences``
>  
>  A list of all the supported EPP preferences that could be used for
> -- 
> 2.43.0
> 

Re: [PATCH v2 11/11] amd-pstate: Add missing documentation for `amd_pstate_prefcore_ranking`

[Gautham R. Shenoy]

On Tue, Sep 03, 2024 at 03:37:01PM -0500, Mario Limonciello wrote:
> From: Mario Limonciello <mario.limonciello@amd.com>
> 
> `amd_pstate_prefcore_ranking` reflects the dynamic rankings of a CPU
> core based on platform conditions.  Explicitly include it in the
> documentation.

Thanks for adding this.

> 
> Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>

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

> ---
>  Documentation/admin-guide/pm/amd-pstate.rst | 9 ++++++++-
>  1 file changed, 8 insertions(+), 1 deletion(-)
> 
> diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst
> index d5c050ea390dc..210a808b74ec2 100644
> --- a/Documentation/admin-guide/pm/amd-pstate.rst
> +++ b/Documentation/admin-guide/pm/amd-pstate.rst
> @@ -252,7 +252,8 @@ 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.
> +different values for some cores than others and this will reflect the values
> +advertised by the platform at bootup.
>  This attribute is read-only.
>  
>  ``amd_pstate_lowest_nonlinear_freq``
> @@ -268,6 +269,12 @@ This attribute is read-only.
>  Whether the platform supports the preferred core feature and it has been
>  enabled. This attribute is read-only.
>  
> +``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.
> +
>  ``energy_performance_available_preferences``
>  
>  A list of all the supported EPP preferences that could be used for
> -- 
> 2.43.0
>