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
  ...

lib/cpumask.c

@@ -6,6 +6,7 @@
 #include <linux/export.h>
 #include <linux/memblock.h>
 #include <linux/numa.h>
+#include <linux/sched/isolation.h>
 
 /**
  * cpumask_next - get the next cpu in a cpumask
@@ -205,22 +206,27 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask)
  */
 unsigned int cpumask_local_spread(unsigned int i, int node)
 {
-	int cpu;
+	int cpu, hk_flags;
+	const struct cpumask *mask;
 
+	hk_flags = HK_FLAG_DOMAIN | HK_FLAG_MANAGED_IRQ;
+	mask = housekeeping_cpumask(hk_flags);
 	/* Wrap: we always want a cpu. */
-	i %= num_online_cpus();
+	i %= cpumask_weight(mask);
 
 	if (node == NUMA_NO_NODE) {
-		for_each_cpu(cpu, cpu_online_mask)
+		for_each_cpu(cpu, mask) {
 			if (i-- == 0)
 				return cpu;
+		}
 	} else {
 		/* NUMA first. */
-		for_each_cpu_and(cpu, cpumask_of_node(node), cpu_online_mask)
+		for_each_cpu_and(cpu, cpumask_of_node(node), mask) {
 			if (i-- == 0)
 				return cpu;
+		}
 
-		for_each_cpu(cpu, cpu_online_mask) {
+		for_each_cpu(cpu, mask) {
 			/* Skip NUMA nodes, done above. */
 			if (cpumask_test_cpu(cpu, cpumask_of_node(node)))
 				continue;

lib/math/div64.c

@@ -190,3 +190,44 @@ u32 iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder)
 	return __iter_div_u64_rem(dividend, divisor, remainder);
 }
 EXPORT_SYMBOL(iter_div_u64_rem);
+
+#ifndef mul_u64_u64_div_u64
+u64 mul_u64_u64_div_u64(u64 a, u64 b, u64 c)
+{
+	u64 res = 0, div, rem;
+	int shift;
+
+	/* can a * b overflow ? */
+	if (ilog2(a) + ilog2(b) > 62) {
+		/*
+		 * (b * a) / c is equal to
+		 *
+		 *      (b / c) * a +
+		 *      (b % c) * a / c
+		 *
+		 * if nothing overflows. Can the 1st multiplication
+		 * overflow? Yes, but we do not care: this can only
+		 * happen if the end result can't fit in u64 anyway.
+		 *
+		 * So the code below does
+		 *
+		 *      res = (b / c) * a;
+		 *      b = b % c;
+		 */
+		div = div64_u64_rem(b, c, &rem);
+		res = div * a;
+		b = rem;
+
+		shift = ilog2(a) + ilog2(b) - 62;
+		if (shift > 0) {
+			/* drop precision */
+			b >>= shift;
+			c >>= shift;
+			if (!c)
+				return res;
+		}
+	}
+
+	return res + div64_u64(a * b, c);
+}
+#endif