Merge tag 'sched-core-2021-02-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Core scheduler updates:

   - Add CONFIG_PREEMPT_DYNAMIC: this in its current form adds the
     preempt=none/voluntary/full boot options (default: full), to allow
     distros to build a PREEMPT kernel but fall back to close to
     PREEMPT_VOLUNTARY (or PREEMPT_NONE) runtime scheduling behavior via
     a boot time selection.

     There's also the /debug/sched_debug switch to do this runtime.

     This feature is implemented via runtime patching (a new variant of
     static calls).

     The scope of the runtime patching can be best reviewed by looking
     at the sched_dynamic_update() function in kernel/sched/core.c.

     ( Note that the dynamic none/voluntary mode isn't 100% identical,
       for example preempt-RCU is available in all cases, plus the
       preempt count is maintained in all models, which has runtime
       overhead even with the code patching. )

     The PREEMPT_VOLUNTARY/PREEMPT_NONE models, used by the vast
     majority of distributions, are supposed to be unaffected.

   - Fix ignored rescheduling after rcu_eqs_enter(). This is a bug that
     was found via rcutorture triggering a hang. The bug is that
     rcu_idle_enter() may wake up a NOCB kthread, but this happens after
     the last generic need_resched() check. Some cpuidle drivers fix it
     by chance but many others don't.

     In true 2020 fashion the original bug fix has grown into a 5-patch
     scheduler/RCU fix series plus another 16 RCU patches to address the
     underlying issue of missed preemption events. These are the initial
     fixes that should fix current incarnations of the bug.

   - Clean up rbtree usage in the scheduler, by providing & using the
     following consistent set of rbtree APIs:

       partial-order; less() based:
         - rb_add(): add a new entry to the rbtree
         - rb_add_cached(): like rb_add(), but for a rb_root_cached

       total-order; cmp() based:
         - rb_find(): find an entry in an rbtree
         - rb_find_add(): find an entry, and add if not found

         - rb_find_first(): find the first (leftmost) matching entry
         - rb_next_match(): continue from rb_find_first()
         - rb_for_each(): iterate a sub-tree using the previous two

   - Improve the SMP/NUMA load-balancer: scan for an idle sibling in a
     single pass. This is a 4-commit series where each commit improves
     one aspect of the idle sibling scan logic.

   - Improve the cpufreq cooling driver by getting the effective CPU
     utilization metrics from the scheduler

   - Improve the fair scheduler's active load-balancing logic by
     reducing the number of active LB attempts & lengthen the
     load-balancing interval. This improves stress-ng mmapfork
     performance.

   - Fix CFS's estimated utilization (util_est) calculation bug that can
     result in too high utilization values

  Misc updates & fixes:

   - Fix the HRTICK reprogramming & optimization feature

   - Fix SCHED_SOFTIRQ raising race & warning in the CPU offlining code

   - Reduce dl_add_task_root_domain() overhead

   - Fix uprobes refcount bug

   - Process pending softirqs in flush_smp_call_function_from_idle()

   - Clean up task priority related defines, remove *USER_*PRIO and
     USER_PRIO()

   - Simplify the sched_init_numa() deduplication sort

   - Documentation updates

   - Fix EAS bug in update_misfit_status(), which degraded the quality
     of energy-balancing

   - Smaller cleanups"

* tag 'sched-core-2021-02-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (51 commits)
  sched,x86: Allow !PREEMPT_DYNAMIC
  entry/kvm: Explicitly flush pending rcuog wakeup before last rescheduling point
  entry: Explicitly flush pending rcuog wakeup before last rescheduling point
  rcu/nocb: Trigger self-IPI on late deferred wake up before user resume
  rcu/nocb: Perform deferred wake up before last idle's need_resched() check
  rcu: Pull deferred rcuog wake up to rcu_eqs_enter() callers
  sched/features: Distinguish between NORMAL and DEADLINE hrtick
  sched/features: Fix hrtick reprogramming
  sched/deadline: Reduce rq lock contention in dl_add_task_root_domain()
  uprobes: (Re)add missing get_uprobe() in __find_uprobe()
  smp: Process pending softirqs in flush_smp_call_function_from_idle()
  sched: Harden PREEMPT_DYNAMIC
  static_call: Allow module use without exposing static_call_key
  sched: Add /debug/sched_preempt
  preempt/dynamic: Support dynamic preempt with preempt= boot option
  preempt/dynamic: Provide irqentry_exit_cond_resched() static call
  preempt/dynamic: Provide preempt_schedule[_notrace]() static calls
  preempt/dynamic: Provide cond_resched() and might_resched() static calls
  preempt: Introduce CONFIG_PREEMPT_DYNAMIC
  static_call: Provide DEFINE_STATIC_CALL_RET0()
  ...

1 files changed, 55 insertions, 14 deletions

diff --git a/drivers/thermal/cpufreq_cooling.c b/drivers/thermal/cpufreq_cooling.c
index 612f063c1cfc..f5af2571f9b7 100644
--- a/drivers/thermal/cpufreq_cooling.c
+++ b/drivers/thermal/cpufreq_cooling.c
@@ -76,7 +76,9 @@ struct cpufreq_cooling_device {
 	struct em_perf_domain *em;
 	struct cpufreq_policy *policy;
 	struct list_head node;
+#ifndef CONFIG_SMP
 	struct time_in_idle *idle_time;
+#endif
 	struct freq_qos_request qos_req;
 };
 
@@ -132,14 +134,25 @@ static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_cdev,
 }
 
 /**
- * get_load() - get load for a cpu since last updated
- * @cpufreq_cdev:	&struct cpufreq_cooling_device for this cpu
- * @cpu:	cpu number
- * @cpu_idx:	index of the cpu in time_in_idle*
+ * get_load() - get load for a cpu
+ * @cpufreq_cdev: struct cpufreq_cooling_device for the cpu
+ * @cpu: cpu number
+ * @cpu_idx: index of the cpu in time_in_idle array
  *
  * Return: The average load of cpu @cpu in percentage since this
  * function was last called.
  */
+#ifdef CONFIG_SMP
+static u32 get_load(struct cpufreq_cooling_device *cpufreq_cdev, int cpu,
+		    int cpu_idx)
+{
+	unsigned long max = arch_scale_cpu_capacity(cpu);
+	unsigned long util;
+
+	util = sched_cpu_util(cpu, max);
+	return (util * 100) / max;
+}
+#else /* !CONFIG_SMP */
 static u32 get_load(struct cpufreq_cooling_device *cpufreq_cdev, int cpu,
 		    int cpu_idx)
 {
@@ -161,6 +174,7 @@ static u32 get_load(struct cpufreq_cooling_device *cpufreq_cdev, int cpu,
 
 	return load;
 }
+#endif /* CONFIG_SMP */
 
 /**
  * get_dynamic_power() - calculate the dynamic power
@@ -346,6 +360,36 @@ static inline bool em_is_sane(struct cpufreq_cooling_device *cpufreq_cdev,
 }
 #endif /* CONFIG_THERMAL_GOV_POWER_ALLOCATOR */
 
+#ifdef CONFIG_SMP
+static inline int allocate_idle_time(struct cpufreq_cooling_device *cpufreq_cdev)
+{
+	return 0;
+}
+
+static inline void free_idle_time(struct cpufreq_cooling_device *cpufreq_cdev)
+{
+}
+#else
+static int allocate_idle_time(struct cpufreq_cooling_device *cpufreq_cdev)
+{
+	unsigned int num_cpus = cpumask_weight(cpufreq_cdev->policy->related_cpus);
+
+	cpufreq_cdev->idle_time = kcalloc(num_cpus,
+					  sizeof(*cpufreq_cdev->idle_time),
+					  GFP_KERNEL);
+	if (!cpufreq_cdev->idle_time)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void free_idle_time(struct cpufreq_cooling_device *cpufreq_cdev)
+{
+	kfree(cpufreq_cdev->idle_time);
+	cpufreq_cdev->idle_time = NULL;
+}
+#endif /* CONFIG_SMP */
+
 static unsigned int get_state_freq(struct cpufreq_cooling_device *cpufreq_cdev,
 				   unsigned long state)
 {
@@ -485,7 +529,7 @@ __cpufreq_cooling_register(struct device_node *np,
 	struct thermal_cooling_device *cdev;
 	struct cpufreq_cooling_device *cpufreq_cdev;
 	char dev_name[THERMAL_NAME_LENGTH];
-	unsigned int i, num_cpus;
+	unsigned int i;
 	struct device *dev;
 	int ret;
 	struct thermal_cooling_device_ops *cooling_ops;
@@ -496,7 +540,6 @@ __cpufreq_cooling_register(struct device_node *np,
 		return ERR_PTR(-ENODEV);
 	}
 
-
 	if (IS_ERR_OR_NULL(policy)) {
 		pr_err("%s: cpufreq policy isn't valid: %p\n", __func__, policy);
 		return ERR_PTR(-EINVAL);
@@ -514,12 +557,10 @@ __cpufreq_cooling_register(struct device_node *np,
 		return ERR_PTR(-ENOMEM);
 
 	cpufreq_cdev->policy = policy;
-	num_cpus = cpumask_weight(policy->related_cpus);
-	cpufreq_cdev->idle_time = kcalloc(num_cpus,
-					 sizeof(*cpufreq_cdev->idle_time),
-					 GFP_KERNEL);
-	if (!cpufreq_cdev->idle_time) {
-		cdev = ERR_PTR(-ENOMEM);
+
+	ret = allocate_idle_time(cpufreq_cdev);
+	if (ret) {
+		cdev = ERR_PTR(ret);
 		goto free_cdev;
 	}
 
@@ -579,7 +620,7 @@ remove_qos_req:
 remove_ida:
 	ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id);
 free_idle_time:
-	kfree(cpufreq_cdev->idle_time);
+	free_idle_time(cpufreq_cdev);
 free_cdev:
 	kfree(cpufreq_cdev);
 	return cdev;
@@ -672,7 +713,7 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 	thermal_cooling_device_unregister(cdev);
 	freq_qos_remove_request(&cpufreq_cdev->qos_req);
 	ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id);
-	kfree(cpufreq_cdev->idle_time);
+	free_idle_time(cpufreq_cdev);
 	kfree(cpufreq_cdev);
 }
 EXPORT_SYMBOL_GPL(cpufreq_cooling_unregister);