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
  ...

5 files changed, 58 insertions, 14 deletions

diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index 435aba289fc5..e0593cf095d0 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -16,8 +16,9 @@
 /* Enable topology flag updates */
 #define arch_update_cpu_topology topology_update_cpu_topology
 
-/* Replace task scheduler's default thermal pressure retrieve API */
+/* Replace task scheduler's default thermal pressure API */
 #define arch_scale_thermal_pressure topology_get_thermal_pressure
+#define arch_set_thermal_pressure   topology_set_thermal_pressure
 
 #else
 
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index 0cc835ddfcd1..e042f6527981 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -34,8 +34,9 @@ void topology_scale_freq_tick(void);
 /* Enable topology flag updates */
 #define arch_update_cpu_topology topology_update_cpu_topology
 
-/* Replace task scheduler's default thermal pressure retrieve API */
+/* Replace task scheduler's default thermal pressure API */
 #define arch_scale_thermal_pressure topology_get_thermal_pressure
+#define arch_set_thermal_pressure   topology_set_thermal_pressure
 
 #include <asm-generic/topology.h>
 
diff --git a/arch/x86/include/asm/div64.h b/arch/x86/include/asm/div64.h
index 9b8cb50768c2..b8f1dc0761e4 100644
--- a/arch/x86/include/asm/div64.h
+++ b/arch/x86/include/asm/div64.h
@@ -74,16 +74,26 @@ static inline u64 mul_u32_u32(u32 a, u32 b)
 #else
 # include <asm-generic/div64.h>
 
-static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 div)
+/*
+ * Will generate an #DE when the result doesn't fit u64, could fix with an
+ * __ex_table[] entry when it becomes an issue.
+ */
+static inline u64 mul_u64_u64_div_u64(u64 a, u64 mul, u64 div)
 {
 	u64 q;
 
 	asm ("mulq %2; divq %3" : "=a" (q)
-				: "a" (a), "rm" ((u64)mul), "rm" ((u64)div)
+				: "a" (a), "rm" (mul), "rm" (div)
 				: "rdx");
 
 	return q;
 }
+#define mul_u64_u64_div_u64 mul_u64_u64_div_u64
+
+static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 div)
+{
+	return mul_u64_u64_div_u64(a, mul, div);
+}
 #define mul_u64_u32_div	mul_u64_u32_div
 
 #endif /* CONFIG_X86_32 */
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 79d8d5496330..f4234575f3fd 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -193,7 +193,7 @@ static inline void sched_clear_itmt_support(void)
 }
 #endif /* CONFIG_SCHED_MC_PRIO */
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && defined(CONFIG_X86_64)
 #include <asm/cpufeature.h>
 
 DECLARE_STATIC_KEY_FALSE(arch_scale_freq_key);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index ffbd9a3d78d8..518ac6bf752e 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -56,6 +56,7 @@
 #include <linux/cpuidle.h>
 #include <linux/numa.h>
 #include <linux/pgtable.h>
+#include <linux/overflow.h>
 
 #include <asm/acpi.h>
 #include <asm/desc.h>
@@ -1777,6 +1778,7 @@ void native_play_dead(void)
 
 #endif
 
+#ifdef CONFIG_X86_64
 /*
  * APERF/MPERF frequency ratio computation.
  *
@@ -1975,6 +1977,7 @@ static bool core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
 static bool intel_set_max_freq_ratio(void)
 {
 	u64 base_freq, turbo_freq;
+	u64 turbo_ratio;
 
 	if (slv_set_max_freq_ratio(&base_freq, &turbo_freq))
 		goto out;
@@ -2000,15 +2003,23 @@ out:
 	/*
 	 * Some hypervisors advertise X86_FEATURE_APERFMPERF
 	 * but then fill all MSR's with zeroes.
+	 * Some CPUs have turbo boost but don't declare any turbo ratio
+	 * in MSR_TURBO_RATIO_LIMIT.
 	 */
-	if (!base_freq) {
-		pr_debug("Couldn't determine cpu base frequency, necessary for scale-invariant accounting.\n");
+	if (!base_freq || !turbo_freq) {
+		pr_debug("Couldn't determine cpu base or turbo frequency, necessary for scale-invariant accounting.\n");
 		return false;
 	}
 
-	arch_turbo_freq_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE,
-					base_freq);
+	turbo_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE, base_freq);
+	if (!turbo_ratio) {
+		pr_debug("Non-zero turbo and base frequencies led to a 0 ratio.\n");
+		return false;
+	}
+
+	arch_turbo_freq_ratio = turbo_ratio;
 	arch_set_max_freq_ratio(turbo_disabled());
+
 	return true;
 }
 
@@ -2048,11 +2059,19 @@ static void init_freq_invariance(bool secondary)
 	}
 }
 
+static void disable_freq_invariance_workfn(struct work_struct *work)
+{
+	static_branch_disable(&arch_scale_freq_key);
+}
+
+static DECLARE_WORK(disable_freq_invariance_work,
+		    disable_freq_invariance_workfn);
+
 DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE;
 
 void arch_scale_freq_tick(void)
 {
-	u64 freq_scale;
+	u64 freq_scale = SCHED_CAPACITY_SCALE;
 	u64 aperf, mperf;
 	u64 acnt, mcnt;
 
@@ -2064,19 +2083,32 @@ void arch_scale_freq_tick(void)
 
 	acnt = aperf - this_cpu_read(arch_prev_aperf);
 	mcnt = mperf - this_cpu_read(arch_prev_mperf);
-	if (!mcnt)
-		return;
 
 	this_cpu_write(arch_prev_aperf, aperf);
 	this_cpu_write(arch_prev_mperf, mperf);
 
-	acnt <<= 2*SCHED_CAPACITY_SHIFT;
-	mcnt *= arch_max_freq_ratio;
+	if (check_shl_overflow(acnt, 2*SCHED_CAPACITY_SHIFT, &acnt))
+		goto error;
+
+	if (check_mul_overflow(mcnt, arch_max_freq_ratio, &mcnt) || !mcnt)
+		goto error;
 
 	freq_scale = div64_u64(acnt, mcnt);
+	if (!freq_scale)
+		goto error;
 
 	if (freq_scale > SCHED_CAPACITY_SCALE)
 		freq_scale = SCHED_CAPACITY_SCALE;
 
 	this_cpu_write(arch_freq_scale, freq_scale);
+	return;
+
+error:
+	pr_warn("Scheduler frequency invariance went wobbly, disabling!\n");
+	schedule_work(&disable_freq_invariance_work);
+}
+#else
+static inline void init_freq_invariance(bool secondary)
+{
 }
+#endif /* CONFIG_X86_64 */