Merge tag 'sched-core-2020-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Improve uclamp performance by using a static key for the fast path

 - Add the "sched_util_clamp_min_rt_default" sysctl, to optimize for
   better power efficiency of RT tasks on battery powered devices.
   (The default is to maximize performance & reduce RT latencies.)

 - Improve utime and stime tracking accuracy, which had a fixed boundary
   of error, which created larger and larger relative errors as the
   values become larger. This is now replaced with more precise
   arithmetics, using the new mul_u64_u64_div_u64() helper in math64.h.

 - Improve the deadline scheduler, such as making it capacity aware

 - Improve frequency-invariant scheduling

 - Misc cleanups in energy/power aware scheduling

 - Add sched_update_nr_running tracepoint to track changes to nr_running

 - Documentation additions and updates

 - Misc cleanups and smaller fixes

* tag 'sched-core-2020-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (54 commits)
  sched/doc: Factorize bits between sched-energy.rst & sched-capacity.rst
  sched/doc: Document capacity aware scheduling
  sched: Document arch_scale_*_capacity()
  arm, arm64: Fix selection of CONFIG_SCHED_THERMAL_PRESSURE
  Documentation/sysctl: Document uclamp sysctl knobs
  sched/uclamp: Add a new sysctl to control RT default boost value
  sched/uclamp: Fix a deadlock when enabling uclamp static key
  sched: Remove duplicated tick_nohz_full_enabled() check
  sched: Fix a typo in a comment
  sched/uclamp: Remove unnecessary mutex_init()
  arm, arm64: Select CONFIG_SCHED_THERMAL_PRESSURE
  sched: Cleanup SCHED_THERMAL_PRESSURE kconfig entry
  arch_topology, sched/core: Cleanup thermal pressure definition
  trace/events/sched.h: fix duplicated word
  linux/sched/mm.h: drop duplicated words in comments
  smp: Fix a potential usage of stale nr_cpus
  sched/fair: update_pick_idlest() Select group with lowest group_util when idle_cpus are equal
  sched: nohz: stop passing around unused "ticks" parameter.
  sched: Better document ttwu()
  sched: Add a tracepoint to track rq->nr_running
  ...

10 files changed, 51 insertions, 20 deletions

diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index 0566cb3314ef..69b1dabe39dc 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -39,8 +39,8 @@ static inline unsigned long topology_get_thermal_pressure(int cpu)
 	return per_cpu(thermal_pressure, cpu);
 }
 
-void arch_set_thermal_pressure(struct cpumask *cpus,
-			       unsigned long th_pressure);
+void topology_set_thermal_pressure(const struct cpumask *cpus,
+				   unsigned long th_pressure);
 
 struct cpu_topology {
 	int thread_id;
diff --git a/include/linux/math64.h b/include/linux/math64.h
index 11a267413e8e..d097119419e6 100644
--- a/include/linux/math64.h
+++ b/include/linux/math64.h
@@ -263,6 +263,8 @@ static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor)
 }
 #endif /* mul_u64_u32_div */
 
+u64 mul_u64_u64_div_u64(u64 a, u64 mul, u64 div);
+
 #define DIV64_U64_ROUND_UP(ll, d)	\
 	({ u64 _tmp = (d); div64_u64((ll) + _tmp - 1, _tmp); })
 
diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
index 4b7258495a04..b95f3211566a 100644
--- a/include/linux/psi_types.h
+++ b/include/linux/psi_types.h
@@ -153,9 +153,10 @@ struct psi_group {
 	unsigned long avg[NR_PSI_STATES - 1][3];
 
 	/* Monitor work control */
-	atomic_t poll_scheduled;
-	struct kthread_worker __rcu *poll_kworker;
-	struct kthread_delayed_work poll_work;
+	struct task_struct __rcu *poll_task;
+	struct timer_list poll_timer;
+	wait_queue_head_t poll_wait;
+	atomic_t poll_wakeup;
 
 	/* Protects data used by the monitor */
 	struct mutex trigger_lock;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 060e9214c8b5..6d6683b48c2a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -155,24 +155,24 @@ struct task_group;
  *
  *   for (;;) {
  *	set_current_state(TASK_UNINTERRUPTIBLE);
- *	if (!need_sleep)
- *		break;
+ *	if (CONDITION)
+ *	   break;
  *
  *	schedule();
  *   }
  *   __set_current_state(TASK_RUNNING);
  *
  * If the caller does not need such serialisation (because, for instance, the
- * condition test and condition change and wakeup are under the same lock) then
+ * CONDITION test and condition change and wakeup are under the same lock) then
  * use __set_current_state().
  *
  * The above is typically ordered against the wakeup, which does:
  *
- *   need_sleep = false;
+ *   CONDITION = 1;
  *   wake_up_state(p, TASK_UNINTERRUPTIBLE);
  *
- * where wake_up_state() executes a full memory barrier before accessing the
- * task state.
+ * where wake_up_state()/try_to_wake_up() executes a full memory barrier before
+ * accessing p->state.
  *
  * Wakeup will do: if (@state & p->state) p->state = TASK_RUNNING, that is,
  * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a
@@ -375,7 +375,7 @@ struct util_est {
  * For cfs_rq, they are the aggregated values of all runnable and blocked
  * sched_entities.
  *
- * The load/runnable/util_avg doesn't direcly factor frequency scaling and CPU
+ * The load/runnable/util_avg doesn't directly factor frequency scaling and CPU
  * capacity scaling. The scaling is done through the rq_clock_pelt that is used
  * for computing those signals (see update_rq_clock_pelt())
  *
@@ -687,9 +687,15 @@ struct task_struct {
 	struct sched_dl_entity		dl;
 
 #ifdef CONFIG_UCLAMP_TASK
-	/* Clamp values requested for a scheduling entity */
+	/*
+	 * Clamp values requested for a scheduling entity.
+	 * Must be updated with task_rq_lock() held.
+	 */
 	struct uclamp_se		uclamp_req[UCLAMP_CNT];
-	/* Effective clamp values used for a scheduling entity */
+	/*
+	 * Effective clamp values used for a scheduling entity.
+	 * Must be updated with task_rq_lock() held.
+	 */
 	struct uclamp_se		uclamp[UCLAMP_CNT];
 #endif
 
@@ -2039,6 +2045,7 @@ const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq);
 const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq);
 
 int sched_trace_rq_cpu(struct rq *rq);
+int sched_trace_rq_nr_running(struct rq *rq);
 
 const struct cpumask *sched_trace_rd_span(struct root_domain *rd);
 
diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index 0fbcbacd1b29..cc9f393e2a70 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -14,6 +14,7 @@ enum hk_flags {
 	HK_FLAG_DOMAIN		= (1 << 5),
 	HK_FLAG_WQ		= (1 << 6),
 	HK_FLAG_MANAGED_IRQ	= (1 << 7),
+	HK_FLAG_KTHREAD		= (1 << 8),
 };
 
 #ifdef CONFIG_CPU_ISOLATION
diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h
index 4859bea47a7b..83ec54b65e79 100644
--- a/include/linux/sched/loadavg.h
+++ b/include/linux/sched/loadavg.h
@@ -43,6 +43,6 @@ extern unsigned long calc_load_n(unsigned long load, unsigned long exp,
 #define LOAD_INT(x) ((x) >> FSHIFT)
 #define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
 
-extern void calc_global_load(unsigned long ticks);
+extern void calc_global_load(void);
 
 #endif /* _LINUX_SCHED_LOADAVG_H */
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 480a4d1b7dd8..6be66f52a2ad 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -23,7 +23,7 @@ extern struct mm_struct *mm_alloc(void);
  * will still exist later on and mmget_not_zero() has to be used before
  * accessing it.
  *
- * This is a preferred way to to pin @mm for a longer/unbounded amount
+ * This is a preferred way to pin @mm for a longer/unbounded amount
  * of time.
  *
  * Use mmdrop() to release the reference acquired by mmgrab().
@@ -49,8 +49,6 @@ static inline void mmdrop(struct mm_struct *mm)
 		__mmdrop(mm);
 }
 
-void mmdrop(struct mm_struct *mm);
-
 /*
  * This has to be called after a get_task_mm()/mmget_not_zero()
  * followed by taking the mmap_lock for writing before modifying the
@@ -234,7 +232,7 @@ static inline unsigned int memalloc_noio_save(void)
  * @flags: Flags to restore.
  *
  * Ends the implicit GFP_NOIO scope started by memalloc_noio_save function.
- * Always make sure that that the given flags is the return value from the
+ * Always make sure that the given flags is the return value from the
  * pairing memalloc_noio_save call.
  */
 static inline void memalloc_noio_restore(unsigned int flags)
@@ -265,7 +263,7 @@ static inline unsigned int memalloc_nofs_save(void)
  * @flags: Flags to restore.
  *
  * Ends the implicit GFP_NOFS scope started by memalloc_nofs_save function.
- * Always make sure that that the given flags is the return value from the
+ * Always make sure that the given flags is the return value from the
  * pairing memalloc_nofs_save call.
  */
 static inline void memalloc_nofs_restore(unsigned int flags)
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 660ac49f2b53..3c31ba88aca5 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -61,9 +61,13 @@ int sched_proc_update_handler(struct ctl_table *table, int write,
 extern unsigned int sysctl_sched_rt_period;
 extern int sysctl_sched_rt_runtime;
 
+extern unsigned int sysctl_sched_dl_period_max;
+extern unsigned int sysctl_sched_dl_period_min;
+
 #ifdef CONFIG_UCLAMP_TASK
 extern unsigned int sysctl_sched_uclamp_util_min;
 extern unsigned int sysctl_sched_uclamp_util_max;
+extern unsigned int sysctl_sched_uclamp_util_min_rt_default;
 #endif
 
 #ifdef CONFIG_CFS_BANDWIDTH
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 1301077f9c24..27b4fa454c80 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -55,6 +55,7 @@ extern asmlinkage void schedule_tail(struct task_struct *prev);
 extern void init_idle(struct task_struct *idle, int cpu);
 
 extern int sched_fork(unsigned long clone_flags, struct task_struct *p);
+extern void sched_post_fork(struct task_struct *p);
 extern void sched_dead(struct task_struct *p);
 
 void __noreturn do_task_dead(void);
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index fb11091129b3..820511289857 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -217,6 +217,16 @@ static inline bool cpus_share_cache(int this_cpu, int that_cpu)
 #endif	/* !CONFIG_SMP */
 
 #ifndef arch_scale_cpu_capacity
+/**
+ * arch_scale_cpu_capacity - get the capacity scale factor of a given CPU.
+ * @cpu: the CPU in question.
+ *
+ * Return: the CPU scale factor normalized against SCHED_CAPACITY_SCALE, i.e.
+ *
+ *             max_perf(cpu)
+ *      ----------------------------- * SCHED_CAPACITY_SCALE
+ *      max(max_perf(c) : c \in CPUs)
+ */
 static __always_inline
 unsigned long arch_scale_cpu_capacity(int cpu)
 {
@@ -232,6 +242,13 @@ unsigned long arch_scale_thermal_pressure(int cpu)
 }
 #endif
 
+#ifndef arch_set_thermal_pressure
+static __always_inline
+void arch_set_thermal_pressure(const struct cpumask *cpus,
+			       unsigned long th_pressure)
+{ }
+#endif
+
 static inline int task_node(const struct task_struct *p)
 {
 	return cpu_to_node(task_cpu(p));