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
  ...

8 files changed, 66 insertions, 53 deletions

diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
index 6126c977ece0..3a0995f8bce8 100644
--- a/include/acpi/cppc_acpi.h
+++ b/include/acpi/cppc_acpi.h
@@ -144,6 +144,8 @@ extern int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls);
 extern int cppc_set_enable(int cpu, bool enable);
 extern int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps);
 extern bool cppc_perf_ctrs_in_pcc(void);
+extern unsigned int cppc_perf_to_khz(struct cppc_perf_caps *caps, unsigned int perf);
+extern unsigned int cppc_khz_to_perf(struct cppc_perf_caps *caps, unsigned int freq);
 extern bool acpi_cpc_valid(void);
 extern bool cppc_allow_fast_switch(void);
 extern int acpi_get_psd_map(unsigned int cpu, struct cppc_cpudata *cpu_data);
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index a07b510e7dc5..a63d61ca55af 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -27,6 +27,13 @@ static inline unsigned long topology_get_cpu_scale(int cpu)
 
 void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity);
 
+DECLARE_PER_CPU(unsigned long, capacity_freq_ref);
+
+static inline unsigned long topology_get_freq_ref(int cpu)
+{
+	return per_cpu(capacity_freq_ref, cpu);
+}
+
 DECLARE_PER_CPU(unsigned long, arch_freq_scale);
 
 static inline unsigned long topology_get_freq_scale(int cpu)
@@ -92,6 +99,7 @@ void update_siblings_masks(unsigned int cpu);
 void remove_cpu_topology(unsigned int cpuid);
 void reset_cpu_topology(void);
 int parse_acpi_topology(void);
+void freq_inv_set_max_ratio(int cpu, u64 max_rate);
 #endif
 
 #endif /* _LINUX_ARCH_TOPOLOGY_H_ */
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 1c5ca92a0555..afda5f24d3dd 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -1203,6 +1203,7 @@ void arch_set_freq_scale(const struct cpumask *cpus,
 {
 }
 #endif
+
 /* the following are really really optional */
 extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs;
 extern struct freq_attr cpufreq_freq_attr_scaling_boost_freqs;
diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index b9caa01dfac4..88d91e087471 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -224,7 +224,7 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
 				unsigned long max_util, unsigned long sum_util,
 				unsigned long allowed_cpu_cap)
 {
-	unsigned long freq, scale_cpu;
+	unsigned long freq, ref_freq, scale_cpu;
 	struct em_perf_state *ps;
 	int cpu;
 
@@ -241,11 +241,10 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
 	 */
 	cpu = cpumask_first(to_cpumask(pd->cpus));
 	scale_cpu = arch_scale_cpu_capacity(cpu);
-	ps = &pd->table[pd->nr_perf_states - 1];
+	ref_freq = arch_scale_freq_ref(cpu);
 
-	max_util = map_util_perf(max_util);
 	max_util = min(max_util, allowed_cpu_cap);
-	freq = map_util_freq(max_util, ps->frequency, scale_cpu);
+	freq = map_util_freq(max_util, ref_freq, scale_cpu);
 
 	/*
 	 * Find the lowest performance state of the Energy Model above the
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 957ce38768b2..950df415d7de 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -600,6 +600,9 @@ struct vma_numab_state {
 	 */
 	unsigned long pids_active[2];
 
+	/* MM scan sequence ID when scan first started after VMA creation */
+	int start_scan_seq;
+
 	/*
 	 * MM scan sequence ID when the VMA was last completely scanned.
 	 * A VMA is not eligible for scanning if prev_scan_seq == numa_scan_seq
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 292c31697248..03bfe9ab2951 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -63,11 +63,13 @@ struct robust_list_head;
 struct root_domain;
 struct rq;
 struct sched_attr;
+struct sched_dl_entity;
 struct seq_file;
 struct sighand_struct;
 struct signal_struct;
 struct task_delay_info;
 struct task_group;
+struct task_struct;
 struct user_event_mm;
 
 /*
@@ -413,42 +415,6 @@ struct load_weight {
 	u32				inv_weight;
 };
 
-/**
- * struct util_est - Estimation utilization of FAIR tasks
- * @enqueued: instantaneous estimated utilization of a task/cpu
- * @ewma:     the Exponential Weighted Moving Average (EWMA)
- *            utilization of a task
- *
- * Support data structure to track an Exponential Weighted Moving Average
- * (EWMA) of a FAIR task's utilization. New samples are added to the moving
- * average each time a task completes an activation. Sample's weight is chosen
- * so that the EWMA will be relatively insensitive to transient changes to the
- * task's workload.
- *
- * The enqueued attribute has a slightly different meaning for tasks and cpus:
- * - task:   the task's util_avg at last task dequeue time
- * - cfs_rq: the sum of util_est.enqueued for each RUNNABLE task on that CPU
- * Thus, the util_est.enqueued of a task represents the contribution on the
- * estimated utilization of the CPU where that task is currently enqueued.
- *
- * Only for tasks we track a moving average of the past instantaneous
- * estimated utilization. This allows to absorb sporadic drops in utilization
- * of an otherwise almost periodic task.
- *
- * The UTIL_AVG_UNCHANGED flag is used to synchronize util_est with util_avg
- * updates. When a task is dequeued, its util_est should not be updated if its
- * util_avg has not been updated in the meantime.
- * This information is mapped into the MSB bit of util_est.enqueued at dequeue
- * time. Since max value of util_est.enqueued for a task is 1024 (PELT util_avg
- * for a task) it is safe to use MSB.
- */
-struct util_est {
-	unsigned int			enqueued;
-	unsigned int			ewma;
-#define UTIL_EST_WEIGHT_SHIFT		2
-#define UTIL_AVG_UNCHANGED		0x80000000
-} __attribute__((__aligned__(sizeof(u64))));
-
 /*
  * The load/runnable/util_avg accumulates an infinite geometric series
  * (see __update_load_avg_cfs_rq() in kernel/sched/pelt.c).
@@ -503,9 +469,20 @@ struct sched_avg {
 	unsigned long			load_avg;
 	unsigned long			runnable_avg;
 	unsigned long			util_avg;
-	struct util_est			util_est;
+	unsigned int			util_est;
 } ____cacheline_aligned;
 
+/*
+ * The UTIL_AVG_UNCHANGED flag is used to synchronize util_est with util_avg
+ * updates. When a task is dequeued, its util_est should not be updated if its
+ * util_avg has not been updated in the meantime.
+ * This information is mapped into the MSB bit of util_est at dequeue time.
+ * Since max value of util_est for a task is 1024 (PELT util_avg for a task)
+ * it is safe to use MSB.
+ */
+#define UTIL_EST_WEIGHT_SHIFT		2
+#define UTIL_AVG_UNCHANGED		0x80000000
+
 struct sched_statistics {
 #ifdef CONFIG_SCHEDSTATS
 	u64				wait_start;
@@ -523,7 +500,7 @@ struct sched_statistics {
 	u64				block_max;
 	s64				sum_block_runtime;
 
-	u64				exec_max;
+	s64				exec_max;
 	u64				slice_max;
 
 	u64				nr_migrations_cold;
@@ -553,7 +530,7 @@ struct sched_entity {
 	struct load_weight		load;
 	struct rb_node			run_node;
 	u64				deadline;
-	u64				min_deadline;
+	u64				min_vruntime;
 
 	struct list_head		group_node;
 	unsigned int			on_rq;
@@ -607,6 +584,9 @@ struct sched_rt_entity {
 #endif
 } __randomize_layout;
 
+typedef bool (*dl_server_has_tasks_f)(struct sched_dl_entity *);
+typedef struct task_struct *(*dl_server_pick_f)(struct sched_dl_entity *);
+
 struct sched_dl_entity {
 	struct rb_node			rb_node;
 
@@ -654,6 +634,7 @@ struct sched_dl_entity {
 	unsigned int			dl_yielded        : 1;
 	unsigned int			dl_non_contending : 1;
 	unsigned int			dl_overrun	  : 1;
+	unsigned int			dl_server         : 1;
 
 	/*
 	 * Bandwidth enforcement timer. Each -deadline task has its
@@ -668,7 +649,20 @@ struct sched_dl_entity {
 	 * timer is needed to decrease the active utilization at the correct
 	 * time.
 	 */
-	struct hrtimer inactive_timer;
+	struct hrtimer			inactive_timer;
+
+	/*
+	 * Bits for DL-server functionality. Also see the comment near
+	 * dl_server_update().
+	 *
+	 * @rq the runqueue this server is for
+	 *
+	 * @server_has_tasks() returns true if @server_pick return a
+	 * runnable task.
+	 */
+	struct rq			*rq;
+	dl_server_has_tasks_f		server_has_tasks;
+	dl_server_pick_f		server_pick;
 
 #ifdef CONFIG_RT_MUTEXES
 	/*
@@ -795,6 +789,7 @@ struct task_struct {
 	struct sched_entity		se;
 	struct sched_rt_entity		rt;
 	struct sched_dl_entity		dl;
+	struct sched_dl_entity		*dl_server;
 	const struct sched_class	*sched_class;
 
 #ifdef CONFIG_SCHED_CORE
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index de545ba85218..a6e04b4a21d7 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -279,6 +279,14 @@ void arch_update_thermal_pressure(const struct cpumask *cpus,
 { }
 #endif
 
+#ifndef arch_scale_freq_ref
+static __always_inline
+unsigned int arch_scale_freq_ref(int cpu)
+{
+	return 0;
+}
+#endif
+
 static inline int task_node(const struct task_struct *p)
 {
 	return cpu_to_node(task_cpu(p));
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 6188ad0d9e0d..dbb01b4b7451 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -493,33 +493,30 @@ DEFINE_EVENT_SCHEDSTAT(sched_stat_template, sched_stat_blocked,
  */
 DECLARE_EVENT_CLASS(sched_stat_runtime,
 
-	TP_PROTO(struct task_struct *tsk, u64 runtime, u64 vruntime),
+	TP_PROTO(struct task_struct *tsk, u64 runtime),
 
-	TP_ARGS(tsk, __perf_count(runtime), vruntime),
+	TP_ARGS(tsk, __perf_count(runtime)),
 
 	TP_STRUCT__entry(
 		__array( char,	comm,	TASK_COMM_LEN	)
 		__field( pid_t,	pid			)
 		__field( u64,	runtime			)
-		__field( u64,	vruntime			)
 	),
 
 	TP_fast_assign(
 		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
 		__entry->pid		= tsk->pid;
 		__entry->runtime	= runtime;
-		__entry->vruntime	= vruntime;
 	),
 
-	TP_printk("comm=%s pid=%d runtime=%Lu [ns] vruntime=%Lu [ns]",
+	TP_printk("comm=%s pid=%d runtime=%Lu [ns]",
 			__entry->comm, __entry->pid,
-			(unsigned long long)__entry->runtime,
-			(unsigned long long)__entry->vruntime)
+			(unsigned long long)__entry->runtime)
 );
 
 DEFINE_EVENT(sched_stat_runtime, sched_stat_runtime,
-	     TP_PROTO(struct task_struct *tsk, u64 runtime, u64 vruntime),
-	     TP_ARGS(tsk, runtime, vruntime));
+	     TP_PROTO(struct task_struct *tsk, u64 runtime),
+	     TP_ARGS(tsk, runtime));
 
 /*
  * Tracepoint for showing priority inheritance modifying a tasks