cpufreq: intel_pstate: Adjust the .adjust_perf() driver callback

In some cases, the processor may not actually stick to the "desired"
performance level programmed through the driver's .adjust_perf()
callback and may go above it, which may not be desirable (for instance,
there may be a UCLAMP_MAX limit set for the task currently running on
the given CPU which should be respected).

Address that by adjusting the .adjust_perf() callback to take an
additional argument, max_perf, representing the maximum allowed
performance level of the CPU and update the intel_pstate driver to
take that argument into account as appropriate.

Accordingly, adjust cpufreq_driver_adjust_perf() and the other existing
user of .adjust_perf(), which is the amd-pstate driver (but the behavior
of that driver is not changed).

While at it, also update the cpufreq_driver_adjust_perf()
documentation to reflect this change and some previous code
changes that have not been taken into account in it.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Zhongqiu Han <zhongqiu.han@oss.qualcomm.com>
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Link: https://patch.msgid.link/6277654.lOV4Wx5bFT@rafael.j.wysocki
[ rjw: Adjusted Rust function formatting ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

6 files changed, 32 insertions, 9 deletions

diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index a74a4cf99d22..f8d8288d644f 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -782,6 +782,7 @@ static unsigned int amd_pstate_fast_switch(struct cpufreq_policy *policy,
 static void amd_pstate_adjust_perf(struct cpufreq_policy *policy,
 				   unsigned long _min_perf,
 				   unsigned long target_perf,
+				   unsigned long _max_perf,
 				   unsigned long capacity)
 {
 	u8 max_perf, min_perf, des_perf, cap_perf;
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 507224c9ecd3..f07b73694cec 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2225,14 +2225,17 @@ EXPORT_SYMBOL_GPL(cpufreq_driver_fast_switch);
  * @policy: cpufreq policy object of the target CPU.
  * @min_perf: Minimum (required) performance level (units of @capacity).
  * @target_perf: Target (desired) performance level (units of @capacity).
+ * @max_perf: Maximum (allowed) performance level (units of @capacity).
  * @capacity: Capacity of the target CPU.
  *
- * Carry out a fast performance level switch of @cpu without sleeping.
+ * Carry out a fast performance level adjustment for the CPU represented by
+ * @policy without sleeping.
  *
  * The driver's ->adjust_perf() callback invoked by this function must be
- * suitable for being called from within RCU-sched read-side critical sections
- * and it is expected to select a suitable performance level equal to or above
- * @min_perf and preferably equal to or below @target_perf.
+ * suitable for calling from within RCU-sched read-side critical sections and
+ * it is expected to program the processor to select suitable performance
+ * levels between @min_perf and @max_perf inclusive and preferably close to
+ * @target_perf going forward for the CPU represented by @policy.
  *
  * This function must not be called if policy->fast_switch_enabled is unset.
  *
@@ -2244,9 +2247,10 @@ EXPORT_SYMBOL_GPL(cpufreq_driver_fast_switch);
 void cpufreq_driver_adjust_perf(struct cpufreq_policy *policy,
 				 unsigned long min_perf,
 				 unsigned long target_perf,
+				 unsigned long max_perf,
 				 unsigned long capacity)
 {
-	cpufreq_driver->adjust_perf(policy, min_perf, target_perf, capacity);
+	cpufreq_driver->adjust_perf(policy, min_perf, target_perf, max_perf, capacity);
 }
 
 /**
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index fd524d0267a3..fe3e6accd9a5 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -3239,6 +3239,7 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy,
 static void intel_cpufreq_adjust_perf(struct cpufreq_policy *policy,
 				      unsigned long min_perf,
 				      unsigned long target_perf,
+				      unsigned long max_perf,
 				      unsigned long capacity)
 {
 	struct cpudata *cpu = all_cpu_data[policy->cpu];
@@ -3269,7 +3270,13 @@ static void intel_cpufreq_adjust_perf(struct cpufreq_policy *policy,
 	if (min_pstate > cpu->max_perf_ratio)
 		min_pstate = cpu->max_perf_ratio;
 
-	max_pstate = min(cap_pstate, cpu->max_perf_ratio);
+	max_pstate = cap_pstate;
+	if (max_perf < capacity)
+		max_pstate = DIV_ROUND_UP(cap_pstate * max_perf, capacity);
+
+	if (max_pstate > cpu->max_perf_ratio)
+		max_pstate = cpu->max_perf_ratio;
+
 	if (max_pstate < min_pstate)
 		max_pstate = min_pstate;
 
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index ae9d1ce4f49c..35ce665edfd8 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -379,6 +379,7 @@ struct cpufreq_driver {
 	void		(*adjust_perf)(struct cpufreq_policy *policy,
 				       unsigned long min_perf,
 				       unsigned long target_perf,
+				       unsigned long max_perf,
 				       unsigned long capacity);
 
 	/*
@@ -624,6 +625,7 @@ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
 void cpufreq_driver_adjust_perf(struct cpufreq_policy *policy,
 				unsigned long min_perf,
 				unsigned long target_perf,
+				unsigned long max_perf,
 				unsigned long capacity);
 bool cpufreq_driver_has_adjust_perf(void);
 int cpufreq_driver_target(struct cpufreq_policy *policy,
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index a4e689eefdfb..7271cf24879d 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -50,6 +50,7 @@ struct sugov_cpu {
 
 	unsigned long		util;
 	unsigned long		bw_min;
+	unsigned long		bw_max;
 
 	/* The field below is for single-CPU policies only: */
 #ifdef CONFIG_NO_HZ_COMMON
@@ -232,6 +233,7 @@ static void sugov_get_util(struct sugov_cpu *sg_cpu, unsigned long boost)
 	util = effective_cpu_util(sg_cpu->cpu, util, &min, &max);
 	util = max(util, boost);
 	sg_cpu->bw_min = min;
+	sg_cpu->bw_max = max;
 	sg_cpu->util = sugov_effective_cpu_perf(sg_cpu->cpu, util, min, max);
 }
 
@@ -484,7 +486,7 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
 		sg_cpu->util = prev_util;
 
 	cpufreq_driver_adjust_perf(sg_policy->policy, sg_cpu->bw_min,
-				   sg_cpu->util, max_cap);
+				   sg_cpu->util, sg_cpu->bw_max, max_cap);
 
 	sg_policy->need_freq_update = false;
 	sg_policy->last_freq_update_time = time;
diff --git a/rust/kernel/cpufreq.rs b/rust/kernel/cpufreq.rs
index 58ac04c650a1..d624cccb6540 100644
--- a/rust/kernel/cpufreq.rs
+++ b/rust/kernel/cpufreq.rs
@@ -792,7 +792,13 @@ pub trait Driver {
     }
 
     /// Driver's `adjust_perf` callback.
-    fn adjust_perf(_policy: &mut Policy, _min_perf: usize, _target_perf: usize, _capacity: usize) {
+    fn adjust_perf(
+        _policy: &mut Policy,
+        _min_perf: usize,
+        _target_perf: usize,
+        _max_perf: usize,
+        _capacity: usize,
+    ) {
         build_error!(VTABLE_DEFAULT_ERROR)
     }
 
@@ -1263,12 +1269,13 @@ impl<T: Driver> Registration<T> {
         ptr: *mut bindings::cpufreq_policy,
         min_perf: c_ulong,
         target_perf: c_ulong,
+        max_perf: c_ulong,
         capacity: c_ulong,
     ) {
         // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
         // lifetime of `policy`.
         let policy = unsafe { Policy::from_raw_mut(ptr) };
-        T::adjust_perf(policy, min_perf, target_perf, capacity);
+        T::adjust_perf(policy, min_perf, target_perf, max_perf, capacity);
     }
 
     /// Driver's `get_intermediate` callback.