Merge tag 'sched-core-2024-01-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Energy scheduling:

   - Consolidate how the max compute capacity is used in the scheduler
     and how we calculate the frequency for a level of utilization.

   - Rework interface between the scheduler and the schedutil governor

   - Simplify the util_est logic

  Deadline scheduler:

   - Work more towards reducing SCHED_DEADLINE starvation of low
     priority tasks (e.g., SCHED_OTHER) tasks when higher priority tasks
     monopolize CPU cycles, via the introduction of 'deadline servers'
     (nested/2-level scheduling).

     "Fair servers" to make use of this facility are not introduced yet.

  EEVDF:

   - Introduce O(1) fastpath for EEVDF task selection

  NUMA balancing:

   - Tune the NUMA-balancing vma scanning logic some more, to better
     distribute the probability of a particular vma getting scanned.

  Plus misc fixes, cleanups and updates"

* tag 'sched-core-2024-01-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (30 commits)
  sched/fair: Fix tg->load when offlining a CPU
  sched/fair: Remove unused 'next_buddy_marked' local variable in check_preempt_wakeup_fair()
  sched/fair: Use all little CPUs for CPU-bound workloads
  sched/fair: Simplify util_est
  sched/fair: Remove SCHED_FEAT(UTIL_EST_FASTUP, true)
  arm64/amu: Use capacity_ref_freq() to set AMU ratio
  cpufreq/cppc: Set the frequency used for computing the capacity
  cpufreq/cppc: Move and rename cppc_cpufreq_{perf_to_khz|khz_to_perf}()
  energy_model: Use a fixed reference frequency
  cpufreq/schedutil: Use a fixed reference frequency
  cpufreq: Use the fixed and coherent frequency for scaling capacity
  sched/topology: Add a new arch_scale_freq_ref() method
  freezer,sched: Clean saved_state when restoring it during thaw
  sched/fair: Update min_vruntime for reweight_entity() correctly
  sched/doc: Update documentation after renames and synchronize Chinese version
  sched/cpufreq: Rework iowait boost
  sched/cpufreq: Rework schedutil governor performance estimation
  sched/pelt: Avoid underestimation of task utilization
  sched/timers: Explain why idle task schedules out on remote timer enqueue
  sched/cpuidle: Comment about timers requirements VS idle handler
  ...

1 files changed, 17 insertions, 122 deletions

diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index fe08ca419b3dc..64420d9cfd1ed 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -16,7 +16,6 @@
 #include <linux/delay.h>
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
-#include <linux/dmi.h>
 #include <linux/irq_work.h>
 #include <linux/kthread.h>
 #include <linux/time.h>
@@ -27,12 +26,6 @@
 
 #include <acpi/cppc_acpi.h>
 
-/* Minimum struct length needed for the DMI processor entry we want */
-#define DMI_ENTRY_PROCESSOR_MIN_LENGTH	48
-
-/* Offset in the DMI processor structure for the max frequency */
-#define DMI_PROCESSOR_MAX_SPEED		0x14
-
 /*
  * This list contains information parsed from per CPU ACPI _CPC and _PSD
  * structures: e.g. the highest and lowest supported performance, capabilities,
@@ -291,97 +284,9 @@ static inline void cppc_freq_invariance_exit(void)
 }
 #endif /* CONFIG_ACPI_CPPC_CPUFREQ_FIE */
 
-/* Callback function used to retrieve the max frequency from DMI */
-static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private)
-{
-	const u8 *dmi_data = (const u8 *)dm;
-	u16 *mhz = (u16 *)private;
-
-	if (dm->type == DMI_ENTRY_PROCESSOR &&
-	    dm->length >= DMI_ENTRY_PROCESSOR_MIN_LENGTH) {
-		u16 val = (u16)get_unaligned((const u16 *)
-				(dmi_data + DMI_PROCESSOR_MAX_SPEED));
-		*mhz = val > *mhz ? val : *mhz;
-	}
-}
-
-/* Look up the max frequency in DMI */
-static u64 cppc_get_dmi_max_khz(void)
-{
-	u16 mhz = 0;
-
-	dmi_walk(cppc_find_dmi_mhz, &mhz);
-
-	/*
-	 * Real stupid fallback value, just in case there is no
-	 * actual value set.
-	 */
-	mhz = mhz ? mhz : 1;
-
-	return (1000 * mhz);
-}
-
-/*
- * If CPPC lowest_freq and nominal_freq registers are exposed then we can
- * use them to convert perf to freq and vice versa. The conversion is
- * extrapolated as an affine function passing by the 2 points:
- *  - (Low perf, Low freq)
- *  - (Nominal perf, Nominal perf)
- */
-static unsigned int cppc_cpufreq_perf_to_khz(struct cppc_cpudata *cpu_data,
-					     unsigned int perf)
-{
-	struct cppc_perf_caps *caps = &cpu_data->perf_caps;
-	s64 retval, offset = 0;
-	static u64 max_khz;
-	u64 mul, div;
-
-	if (caps->lowest_freq && caps->nominal_freq) {
-		mul = caps->nominal_freq - caps->lowest_freq;
-		div = caps->nominal_perf - caps->lowest_perf;
-		offset = caps->nominal_freq - div64_u64(caps->nominal_perf * mul, div);
-	} else {
-		if (!max_khz)
-			max_khz = cppc_get_dmi_max_khz();
-		mul = max_khz;
-		div = caps->highest_perf;
-	}
-
-	retval = offset + div64_u64(perf * mul, div);
-	if (retval >= 0)
-		return retval;
-	return 0;
-}
-
-static unsigned int cppc_cpufreq_khz_to_perf(struct cppc_cpudata *cpu_data,
-					     unsigned int freq)
-{
-	struct cppc_perf_caps *caps = &cpu_data->perf_caps;
-	s64 retval, offset = 0;
-	static u64 max_khz;
-	u64  mul, div;
-
-	if (caps->lowest_freq && caps->nominal_freq) {
-		mul = caps->nominal_perf - caps->lowest_perf;
-		div = caps->nominal_freq - caps->lowest_freq;
-		offset = caps->nominal_perf - div64_u64(caps->nominal_freq * mul, div);
-	} else {
-		if (!max_khz)
-			max_khz = cppc_get_dmi_max_khz();
-		mul = caps->highest_perf;
-		div = max_khz;
-	}
-
-	retval = offset + div64_u64(freq * mul, div);
-	if (retval >= 0)
-		return retval;
-	return 0;
-}
-
 static int cppc_cpufreq_set_target(struct cpufreq_policy *policy,
 				   unsigned int target_freq,
 				   unsigned int relation)
-
 {
 	struct cppc_cpudata *cpu_data = policy->driver_data;
 	unsigned int cpu = policy->cpu;
@@ -389,7 +294,7 @@ static int cppc_cpufreq_set_target(struct cpufreq_policy *policy,
 	u32 desired_perf;
 	int ret = 0;
 
-	desired_perf = cppc_cpufreq_khz_to_perf(cpu_data, target_freq);
+	desired_perf = cppc_khz_to_perf(&cpu_data->perf_caps, target_freq);
 	/* Return if it is exactly the same perf */
 	if (desired_perf == cpu_data->perf_ctrls.desired_perf)
 		return ret;
@@ -417,7 +322,7 @@ static unsigned int cppc_cpufreq_fast_switch(struct cpufreq_policy *policy,
 	u32 desired_perf;
 	int ret;
 
-	desired_perf = cppc_cpufreq_khz_to_perf(cpu_data, target_freq);
+	desired_perf = cppc_khz_to_perf(&cpu_data->perf_caps, target_freq);
 	cpu_data->perf_ctrls.desired_perf = desired_perf;
 	ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls);
 
@@ -530,7 +435,7 @@ static int cppc_get_cpu_power(struct device *cpu_dev,
 	min_step = min_cap / CPPC_EM_CAP_STEP;
 	max_step = max_cap / CPPC_EM_CAP_STEP;
 
-	perf_prev = cppc_cpufreq_khz_to_perf(cpu_data, *KHz);
+	perf_prev = cppc_khz_to_perf(perf_caps, *KHz);
 	step = perf_prev / perf_step;
 
 	if (step > max_step)
@@ -550,8 +455,8 @@ static int cppc_get_cpu_power(struct device *cpu_dev,
 			perf = step * perf_step;
 	}
 
-	*KHz = cppc_cpufreq_perf_to_khz(cpu_data, perf);
-	perf_check = cppc_cpufreq_khz_to_perf(cpu_data, *KHz);
+	*KHz = cppc_perf_to_khz(perf_caps, perf);
+	perf_check = cppc_khz_to_perf(perf_caps, *KHz);
 	step_check = perf_check / perf_step;
 
 	/*
@@ -561,8 +466,8 @@ static int cppc_get_cpu_power(struct device *cpu_dev,
 	 */
 	while ((*KHz == prev_freq) || (step_check != step)) {
 		perf++;
-		*KHz = cppc_cpufreq_perf_to_khz(cpu_data, perf);
-		perf_check = cppc_cpufreq_khz_to_perf(cpu_data, *KHz);
+		*KHz = cppc_perf_to_khz(perf_caps, perf);
+		perf_check = cppc_khz_to_perf(perf_caps, *KHz);
 		step_check = perf_check / perf_step;
 	}
 
@@ -591,7 +496,7 @@ static int cppc_get_cpu_cost(struct device *cpu_dev, unsigned long KHz,
 	perf_caps = &cpu_data->perf_caps;
 	max_cap = arch_scale_cpu_capacity(cpu_dev->id);
 
-	perf_prev = cppc_cpufreq_khz_to_perf(cpu_data, KHz);
+	perf_prev = cppc_khz_to_perf(perf_caps, KHz);
 	perf_step = CPPC_EM_CAP_STEP * perf_caps->highest_perf / max_cap;
 	step = perf_prev / perf_step;
 
@@ -679,10 +584,6 @@ static struct cppc_cpudata *cppc_cpufreq_get_cpu_data(unsigned int cpu)
 		goto free_mask;
 	}
 
-	/* Convert the lowest and nominal freq from MHz to KHz */
-	cpu_data->perf_caps.lowest_freq *= 1000;
-	cpu_data->perf_caps.nominal_freq *= 1000;
-
 	list_add(&cpu_data->node, &cpu_data_list);
 
 	return cpu_data;
@@ -724,20 +625,16 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	 * Set min to lowest nonlinear perf to avoid any efficiency penalty (see
 	 * Section 8.4.7.1.1.5 of ACPI 6.1 spec)
 	 */
-	policy->min = cppc_cpufreq_perf_to_khz(cpu_data,
-					       caps->lowest_nonlinear_perf);
-	policy->max = cppc_cpufreq_perf_to_khz(cpu_data,
-					       caps->nominal_perf);
+	policy->min = cppc_perf_to_khz(caps, caps->lowest_nonlinear_perf);
+	policy->max = cppc_perf_to_khz(caps, caps->nominal_perf);
 
 	/*
 	 * Set cpuinfo.min_freq to Lowest to make the full range of performance
 	 * available if userspace wants to use any perf between lowest & lowest
 	 * nonlinear perf
 	 */
-	policy->cpuinfo.min_freq = cppc_cpufreq_perf_to_khz(cpu_data,
-							    caps->lowest_perf);
-	policy->cpuinfo.max_freq = cppc_cpufreq_perf_to_khz(cpu_data,
-							    caps->nominal_perf);
+	policy->cpuinfo.min_freq = cppc_perf_to_khz(caps, caps->lowest_perf);
+	policy->cpuinfo.max_freq = cppc_perf_to_khz(caps, caps->nominal_perf);
 
 	policy->transition_delay_us = cppc_cpufreq_get_transition_delay_us(cpu);
 	policy->shared_type = cpu_data->shared_type;
@@ -773,7 +670,7 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		boost_supported = true;
 
 	/* Set policy->cur to max now. The governors will adjust later. */
-	policy->cur = cppc_cpufreq_perf_to_khz(cpu_data, caps->highest_perf);
+	policy->cur = cppc_perf_to_khz(caps, caps->highest_perf);
 	cpu_data->perf_ctrls.desired_perf =  caps->highest_perf;
 
 	ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls);
@@ -863,7 +760,7 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpu)
 	delivered_perf = cppc_perf_from_fbctrs(cpu_data, &fb_ctrs_t0,
 					       &fb_ctrs_t1);
 
-	return cppc_cpufreq_perf_to_khz(cpu_data, delivered_perf);
+	return cppc_perf_to_khz(&cpu_data->perf_caps, delivered_perf);
 }
 
 static int cppc_cpufreq_set_boost(struct cpufreq_policy *policy, int state)
@@ -878,11 +775,9 @@ static int cppc_cpufreq_set_boost(struct cpufreq_policy *policy, int state)
 	}
 
 	if (state)
-		policy->max = cppc_cpufreq_perf_to_khz(cpu_data,
-						       caps->highest_perf);
+		policy->max = cppc_perf_to_khz(caps, caps->highest_perf);
 	else
-		policy->max = cppc_cpufreq_perf_to_khz(cpu_data,
-						       caps->nominal_perf);
+		policy->max = cppc_perf_to_khz(caps, caps->nominal_perf);
 	policy->cpuinfo.max_freq = policy->max;
 
 	ret = freq_qos_update_request(policy->max_freq_req, policy->max);
@@ -937,7 +832,7 @@ static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu)
 	if (ret < 0)
 		return -EIO;
 
-	return cppc_cpufreq_perf_to_khz(cpu_data, desired_perf);
+	return cppc_perf_to_khz(&cpu_data->perf_caps, desired_perf);
 }
 
 static void cppc_check_hisi_workaround(void)