Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "These were the main changes in this cycle:

   - More -rt motivated separation of CONFIG_PREEMPT and
     CONFIG_PREEMPTION.

   - Add more low level scheduling topology sanity checks and warnings
     to filter out nonsensical topologies that break scheduling.

   - Extend uclamp constraints to influence wakeup CPU placement

   - Make the RT scheduler more aware of asymmetric topologies and CPU
     capacities, via uclamp metrics, if CONFIG_UCLAMP_TASK=y

   - Make idle CPU selection more consistent

   - Various fixes, smaller cleanups, updates and enhancements - please
     see the git log for details"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (58 commits)
  sched/fair: Define sched_idle_cpu() only for SMP configurations
  sched/topology: Assert non-NUMA topology masks don't (partially) overlap
  idle: fix spelling mistake "iterrupts" -> "interrupts"
  sched/fair: Remove redundant call to cpufreq_update_util()
  sched/psi: create /proc/pressure and /proc/pressure/{io|memory|cpu} only when psi enabled
  sched/fair: Fix sgc->{min,max}_capacity calculation for SD_OVERLAP
  sched/fair: calculate delta runnable load only when it's needed
  sched/cputime: move rq parameter in irqtime_account_process_tick
  stop_machine: Make stop_cpus() static
  sched/debug: Reset watchdog on all CPUs while processing sysrq-t
  sched/core: Fix size of rq::uclamp initialization
  sched/uclamp: Fix a bug in propagating uclamp value in new cgroups
  sched/fair: Load balance aggressively for SCHED_IDLE CPUs
  sched/fair : Improve update_sd_pick_busiest for spare capacity case
  watchdog: Remove soft_lockup_hrtimer_cnt and related code
  sched/rt: Make RT capacity-aware
  sched/fair: Make EAS wakeup placement consider uclamp restrictions
  sched/fair: Make task_fits_capacity() consider uclamp restrictions
  sched/uclamp: Rename uclamp_util_with() into uclamp_rq_util_with()
  sched/uclamp: Make uclamp util helpers use and return UL values
  ...

1 files changed, 23 insertions, 2 deletions

diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index b7abca987d94..1a2719e1350a 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -46,6 +46,8 @@ static int convert_prio(int prio)
  * @cp: The cpupri context
  * @p: The task
  * @lowest_mask: A mask to fill in with selected CPUs (or NULL)
+ * @fitness_fn: A pointer to a function to do custom checks whether the CPU
+ *              fits a specific criteria so that we only return those CPUs.
  *
  * Note: This function returns the recommended CPUs as calculated during the
  * current invocation.  By the time the call returns, the CPUs may have in
@@ -57,7 +59,8 @@ static int convert_prio(int prio)
  * Return: (int)bool - CPUs were found
  */
 int cpupri_find(struct cpupri *cp, struct task_struct *p,
-		struct cpumask *lowest_mask)
+		struct cpumask *lowest_mask,
+		bool (*fitness_fn)(struct task_struct *p, int cpu))
 {
 	int idx = 0;
 	int task_pri = convert_prio(p->prio);
@@ -98,6 +101,8 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p,
 			continue;
 
 		if (lowest_mask) {
+			int cpu;
+
 			cpumask_and(lowest_mask, p->cpus_ptr, vec->mask);
 
 			/*
@@ -108,7 +113,23 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p,
 			 * condition, simply act as though we never hit this
 			 * priority level and continue on.
 			 */
-			if (cpumask_any(lowest_mask) >= nr_cpu_ids)
+			if (cpumask_empty(lowest_mask))
+				continue;
+
+			if (!fitness_fn)
+				return 1;
+
+			/* Ensure the capacity of the CPUs fit the task */
+			for_each_cpu(cpu, lowest_mask) {
+				if (!fitness_fn(p, cpu))
+					cpumask_clear_cpu(cpu, lowest_mask);
+			}
+
+			/*
+			 * If no CPU at the current priority can fit the task
+			 * continue looking
+			 */
+			if (cpumask_empty(lowest_mask))
 				continue;
 		}