[PATCH v4 2/2] ACPI: CPPC: Add ospm_nominal_perf support

Expose the OSPM Nominal Performance register (ACPI 6.6, Section
8.4.6.1.2.6), which conveys the desired nominal performance level
at which the platform may run. Unlike the existing read-only
Nominal Performance register, it is writable and lets OSPM
request a lower nominal level than the platform-reported nominal.
The platform classifies performance above this level as boosted
and below as throttled for its power/thermal decisions.

It is exposed as a per-policy cpufreq sysfs attribute in kHz, to
match the cpufreq sysfs unit convention:

  /sys/devices/system/cpu/cpufreq/policyN/ospm_nominal_freq

The attribute is documented in
Documentation/ABI/testing/sysfs-devices-system-cpu.

Writes are converted to perf via cppc_khz_to_perf(), validated
against [Lowest Performance, Nominal Performance], and applied to
every CPU in policy->cpus.

The register is write-only; the kernel caches the last written
value in struct cppc_cpudata for sysfs readback (returns 0 until
userspace writes a value).

Signed-off-by: Sumit Gupta <[email protected]>
---
 .../ABI/testing/sysfs-devices-system-cpu      | 17 ++++++
 drivers/acpi/cppc_acpi.c                      | 35 +++++++++++
 drivers/cpufreq/cppc_cpufreq.c                | 60 +++++++++++++++++++
 include/acpi/cppc_acpi.h                      | 12 ++++
 4 files changed, 124 insertions(+)

diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 82d10d556cc8..ac1bf1b89ac4 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -346,6 +346,23 @@ Description:	Performance Limited
 
 		This file is only present if the cppc-cpufreq driver is in use.
 
+What:		/sys/devices/system/cpu/cpuX/cpufreq/ospm_nominal_freq
+Date:		May 2026
+Contact:	[email protected]
+Description:	OSPM Nominal Performance (kHz)
+
+		OSPM uses this attribute to request a nominal performance
+		level lower than the platform-reported nominal. The
+		platform treats performance above this level as boost
+		and below as throttle for power and thermal decisions.
+
+		Read returns the last written value in kHz, or 0 if no
+		value has been written. Write a kHz value in the range
+		[lowest_freq, nominal_freq].
+
+		This file is only present if the cppc-cpufreq driver is
+		in use.
+
 What:		/sys/devices/system/cpu/cpu*/cache/index3/cache_disable_{0,1}
 Date:		August 2008
 KernelVersion:	2.6.27
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index c76cfafa3589..ad6ece16c30d 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -1682,6 +1682,41 @@ int cppc_set_epp(int cpu, u64 epp_val)
 }
 EXPORT_SYMBOL_GPL(cppc_set_epp);
 
+/**
+ * cppc_set_ospm_nominal_perf() - Write OSPM Nominal Performance register.
+ * @cpu: CPU on which to write register.
+ * @ospm_nominal_perf: Value to write to the OSPM Nominal Performance register.
+ *
+ * OSPM Nominal Performance conveys the desired nominal performance level
+ * at which the platform may run. Per ACPI 6.6, s8.4.6.1.2.6, the value
+ * must lie within [Lowest Performance, Nominal Performance] and may be
+ * set independently of Minimum, Maximum and Desired performance.
+ *
+ * Return: 0 on success or negative error code.
+ */
+int cppc_set_ospm_nominal_perf(int cpu, u64 ospm_nominal_perf)
+{
+	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu);
+	struct cppc_perf_caps caps;
+	int ret;
+
+	if (!cpc_desc) {
+		pr_debug("No CPC descriptor for CPU:%d\n", cpu);
+		return -ENODEV;
+	}
+
+	ret = cppc_get_perf_caps(cpu, &caps);
+	if (ret)
+		return ret;
+
+	if (ospm_nominal_perf < caps.lowest_perf ||
+	    ospm_nominal_perf > caps.nominal_perf)
+		return -EINVAL;
+
+	return cppc_set_reg_val(cpu, OSPM_NOMINAL_PERF, ospm_nominal_perf);
+}
+EXPORT_SYMBOL_GPL(cppc_set_ospm_nominal_perf);
+
 /**
  * cppc_get_auto_act_window() - Read autonomous activity window register.
  * @cpu: CPU from which to read register.
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index 15a728dea911..5c54af1655b5 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -1139,11 +1139,70 @@ static int cppc_get_perf_limited_filtered(int cpu, u64 *perf_limited)
 CPPC_CPUFREQ_ATTR_RW_U64(perf_limited, cppc_get_perf_limited_filtered,
 			 cppc_set_perf_limited)
 
+static ssize_t show_ospm_nominal_freq(struct cpufreq_policy *policy, char *buf)
+{
+	struct cppc_cpudata *cpu_data = policy->driver_data;
+	unsigned int freq_khz;
+
+	if (!cpu_data->ospm_nominal_perf_set)
+		return sysfs_emit(buf, "0\n");
+
+	freq_khz = cppc_perf_to_khz(&cpu_data->perf_caps,
+				    cpu_data->ospm_nominal_perf);
+	return sysfs_emit(buf, "%u\n", freq_khz);
+}
+
+static ssize_t store_ospm_nominal_freq(struct cpufreq_policy *policy,
+				       const char *buf, size_t count)
+{
+	struct cppc_cpudata *cpu_data = policy->driver_data;
+	bool prev_set = cpu_data->ospm_nominal_perf_set;
+	u32 prev_perf = cpu_data->ospm_nominal_perf;
+	unsigned int sib, freq_khz, failing_cpu = 0;
+	u32 perf;
+	int ret;
+
+	ret = kstrtouint(buf, 0, &freq_khz);
+	if (ret)
+		return ret;
+
+	perf = cppc_khz_to_perf(&cpu_data->perf_caps, freq_khz);
+
+	for_each_cpu(sib, policy->cpus) {
+		ret = cppc_set_ospm_nominal_perf(sib, perf);
+		if (ret) {
+			failing_cpu = sib;
+			goto rollback;
+		}
+	}
+
+	cpu_data->ospm_nominal_perf = perf;
+	cpu_data->ospm_nominal_perf_set = true;
+	return count;
+
+rollback:
+	/*
+	 * Restore the previous value on siblings already updated.
+	 * for_each_cpu() iterates in CPU-id order, so siblings before
+	 * @failing_cpu were updated successfully. Skip restore when
+	 * there is no prior known-good value (first-ever write failed).
+	 */
+	if (prev_set) {
+		for_each_cpu(sib, policy->cpus) {
+			if (sib == failing_cpu)
+				break;
+			cppc_set_ospm_nominal_perf(sib, prev_perf);
+		}
+	}
+	return ret;
+}
+
 cpufreq_freq_attr_ro(freqdomain_cpus);
 cpufreq_freq_attr_rw(auto_select);
 cpufreq_freq_attr_rw(auto_act_window);
 cpufreq_freq_attr_rw(energy_performance_preference_val);
 cpufreq_freq_attr_rw(perf_limited);
+cpufreq_freq_attr_rw(ospm_nominal_freq);
 
 static struct freq_attr *cppc_cpufreq_attr[] = {
 	&freqdomain_cpus,
@@ -1151,6 +1210,7 @@ static struct freq_attr *cppc_cpufreq_attr[] = {
 	&auto_act_window,
 	&energy_performance_preference_val,
 	&perf_limited,
+	&ospm_nominal_freq,
 	NULL,
 };
 
diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
index 9b18fb9aab7c..14c6d5d0ac12 100644
--- a/include/acpi/cppc_acpi.h
+++ b/include/acpi/cppc_acpi.h
@@ -154,6 +154,13 @@ struct cppc_cpudata {
 	struct cppc_perf_fb_ctrs perf_fb_ctrs;
 	unsigned int shared_type;
 	cpumask_var_t shared_cpu_map;
+	/*
+	 * Cached OSPM Nominal Performance value (write-only register).
+	 * ospm_nominal_perf_set is true once userspace has written, so an
+	 * unwritten cache is distinguishable from a valid 0 perf write.
+	 */
+	u32 ospm_nominal_perf;
+	bool ospm_nominal_perf_set;
 };
 
 #ifdef CONFIG_ACPI_CPPC_LIB
@@ -181,6 +188,7 @@ extern int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val);
 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_set_epp(int cpu, u64 epp_val);
+extern int cppc_set_ospm_nominal_perf(int cpu, u64 ospm_nominal_perf);
 extern int cppc_get_auto_act_window(int cpu, u64 *auto_act_window);
 extern int cppc_set_auto_act_window(int cpu, u64 auto_act_window);
 extern int cppc_get_auto_sel(int cpu, bool *enable);
@@ -267,6 +275,10 @@ static inline int cppc_set_epp(int cpu, u64 epp_val)
 {
 	return -EOPNOTSUPP;
 }
+static inline int cppc_set_ospm_nominal_perf(int cpu, u64 ospm_nominal_perf)
+{
+	return -EOPNOTSUPP;
+}
 static inline int cppc_get_auto_act_window(int cpu, u64 *auto_act_window)
 {
 	return -EOPNOTSUPP;
-- 
2.34.1