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

Pull scheduler updates from Ingo Molnar:
 "The main changes in this cycle are:

   - Various NUMA scheduling updates: harmonize the load-balancer and
     NUMA placement logic to not work against each other. The intended
     result is better locality, better utilization and fewer migrations.

   - Introduce Thermal Pressure tracking and optimizations, to improve
     task placement on thermally overloaded systems.

   - Implement frequency invariant scheduler accounting on (some) x86
     CPUs. This is done by observing and sampling the 'recent' CPU
     frequency average at ~tick boundaries. The CPU provides this data
     via the APERF/MPERF MSRs. This hopefully makes our capacity
     estimates more precise and keeps tasks on the same CPU better even
     if it might seem overloaded at a lower momentary frequency. (As
     usual, turbo mode is a complication that we resolve by observing
     the maximum frequency and renormalizing to it.)

   - Add asymmetric CPU capacity wakeup scan to improve capacity
     utilization on asymmetric topologies. (big.LITTLE systems)

   - PSI fixes and optimizations.

   - RT scheduling capacity awareness fixes & improvements.

   - Optimize the CONFIG_RT_GROUP_SCHED constraints code.

   - Misc fixes, cleanups and optimizations - see the changelog for
     details"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (62 commits)
  threads: Update PID limit comment according to futex UAPI change
  sched/fair: Fix condition of avg_load calculation
  sched/rt: cpupri_find: Trigger a full search as fallback
  kthread: Do not preempt current task if it is going to call schedule()
  sched/fair: Improve spreading of utilization
  sched: Avoid scale real weight down to zero
  psi: Move PF_MEMSTALL out of task->flags
  MAINTAINERS: Add maintenance information for psi
  psi: Optimize switching tasks inside shared cgroups
  psi: Fix cpu.pressure for cpu.max and competing cgroups
  sched/core: Distribute tasks within affinity masks
  sched/fair: Fix enqueue_task_fair warning
  thermal/cpu-cooling, sched/core: Move the arch_set_thermal_pressure() API to generic scheduler code
  sched/rt: Remove unnecessary push for unfit tasks
  sched/rt: Allow pulling unfitting task
  sched/rt: Optimize cpupri_find() on non-heterogenous systems
  sched/rt: Re-instate old behavior in select_task_rq_rt()
  sched/rt: cpupri_find: Implement fallback mechanism for !fit case
  sched/fair: Fix reordering of enqueue/dequeue_task_fair()
  sched/fair: Fix runnable_avg for throttled cfs
  ...

1 files changed, 80 insertions, 31 deletions

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 028520702717..8f45cdb6463b 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -225,7 +225,7 @@ static bool test_state(unsigned int *tasks, enum psi_states state)
 	case PSI_MEM_FULL:
 		return tasks[NR_MEMSTALL] && !tasks[NR_RUNNING];
 	case PSI_CPU_SOME:
-		return tasks[NR_RUNNING] > 1;
+		return tasks[NR_RUNNING] > tasks[NR_ONCPU];
 	case PSI_NONIDLE:
 		return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] ||
 			tasks[NR_RUNNING];
@@ -669,13 +669,14 @@ static void record_times(struct psi_group_cpu *groupc, int cpu,
 		groupc->times[PSI_NONIDLE] += delta;
 }
 
-static u32 psi_group_change(struct psi_group *group, int cpu,
-			    unsigned int clear, unsigned int set)
+static void psi_group_change(struct psi_group *group, int cpu,
+			     unsigned int clear, unsigned int set,
+			     bool wake_clock)
 {
 	struct psi_group_cpu *groupc;
+	u32 state_mask = 0;
 	unsigned int t, m;
 	enum psi_states s;
-	u32 state_mask = 0;
 
 	groupc = per_cpu_ptr(group->pcpu, cpu);
 
@@ -695,10 +696,10 @@ static u32 psi_group_change(struct psi_group *group, int cpu,
 		if (!(m & (1 << t)))
 			continue;
 		if (groupc->tasks[t] == 0 && !psi_bug) {
-			printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u] clear=%x set=%x\n",
+			printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u %u] clear=%x set=%x\n",
 					cpu, t, groupc->tasks[0],
 					groupc->tasks[1], groupc->tasks[2],
-					clear, set);
+					groupc->tasks[3], clear, set);
 			psi_bug = 1;
 		}
 		groupc->tasks[t]--;
@@ -717,7 +718,11 @@ static u32 psi_group_change(struct psi_group *group, int cpu,
 
 	write_seqcount_end(&groupc->seq);
 
-	return state_mask;
+	if (state_mask & group->poll_states)
+		psi_schedule_poll_work(group, 1);
+
+	if (wake_clock && !delayed_work_pending(&group->avgs_work))
+		schedule_delayed_work(&group->avgs_work, PSI_FREQ);
 }
 
 static struct psi_group *iterate_groups(struct task_struct *task, void **iter)
@@ -744,27 +749,32 @@ static struct psi_group *iterate_groups(struct task_struct *task, void **iter)
 	return &psi_system;
 }
 
-void psi_task_change(struct task_struct *task, int clear, int set)
+static void psi_flags_change(struct task_struct *task, int clear, int set)
 {
-	int cpu = task_cpu(task);
-	struct psi_group *group;
-	bool wake_clock = true;
-	void *iter = NULL;
-
-	if (!task->pid)
-		return;
-
 	if (((task->psi_flags & set) ||
 	     (task->psi_flags & clear) != clear) &&
 	    !psi_bug) {
 		printk_deferred(KERN_ERR "psi: inconsistent task state! task=%d:%s cpu=%d psi_flags=%x clear=%x set=%x\n",
-				task->pid, task->comm, cpu,
+				task->pid, task->comm, task_cpu(task),
 				task->psi_flags, clear, set);
 		psi_bug = 1;
 	}
 
 	task->psi_flags &= ~clear;
 	task->psi_flags |= set;
+}
+
+void psi_task_change(struct task_struct *task, int clear, int set)
+{
+	int cpu = task_cpu(task);
+	struct psi_group *group;
+	bool wake_clock = true;
+	void *iter = NULL;
+
+	if (!task->pid)
+		return;
+
+	psi_flags_change(task, clear, set);
 
 	/*
 	 * Periodic aggregation shuts off if there is a period of no
@@ -777,14 +787,51 @@ void psi_task_change(struct task_struct *task, int clear, int set)
 		     wq_worker_last_func(task) == psi_avgs_work))
 		wake_clock = false;
 
-	while ((group = iterate_groups(task, &iter))) {
-		u32 state_mask = psi_group_change(group, cpu, clear, set);
+	while ((group = iterate_groups(task, &iter)))
+		psi_group_change(group, cpu, clear, set, wake_clock);
+}
+
+void psi_task_switch(struct task_struct *prev, struct task_struct *next,
+		     bool sleep)
+{
+	struct psi_group *group, *common = NULL;
+	int cpu = task_cpu(prev);
+	void *iter;
+
+	if (next->pid) {
+		psi_flags_change(next, 0, TSK_ONCPU);
+		/*
+		 * When moving state between tasks, the group that
+		 * contains them both does not change: we can stop
+		 * updating the tree once we reach the first common
+		 * ancestor. Iterate @next's ancestors until we
+		 * encounter @prev's state.
+		 */
+		iter = NULL;
+		while ((group = iterate_groups(next, &iter))) {
+			if (per_cpu_ptr(group->pcpu, cpu)->tasks[NR_ONCPU]) {
+				common = group;
+				break;
+			}
+
+			psi_group_change(group, cpu, 0, TSK_ONCPU, true);
+		}
+	}
+
+	/*
+	 * If this is a voluntary sleep, dequeue will have taken care
+	 * of the outgoing TSK_ONCPU alongside TSK_RUNNING already. We
+	 * only need to deal with it during preemption.
+	 */
+	if (sleep)
+		return;
 
-		if (state_mask & group->poll_states)
-			psi_schedule_poll_work(group, 1);
+	if (prev->pid) {
+		psi_flags_change(prev, TSK_ONCPU, 0);
 
-		if (wake_clock && !delayed_work_pending(&group->avgs_work))
-			schedule_delayed_work(&group->avgs_work, PSI_FREQ);
+		iter = NULL;
+		while ((group = iterate_groups(prev, &iter)) && group != common)
+			psi_group_change(group, cpu, TSK_ONCPU, 0, true);
 	}
 }
 
@@ -818,17 +865,17 @@ void psi_memstall_enter(unsigned long *flags)
 	if (static_branch_likely(&psi_disabled))
 		return;
 
-	*flags = current->flags & PF_MEMSTALL;
+	*flags = current->in_memstall;
 	if (*flags)
 		return;
 	/*
-	 * PF_MEMSTALL setting & accounting needs to be atomic wrt
+	 * in_memstall setting & accounting needs to be atomic wrt
 	 * changes to the task's scheduling state, otherwise we can
 	 * race with CPU migration.
 	 */
 	rq = this_rq_lock_irq(&rf);
 
-	current->flags |= PF_MEMSTALL;
+	current->in_memstall = 1;
 	psi_task_change(current, 0, TSK_MEMSTALL);
 
 	rq_unlock_irq(rq, &rf);
@@ -851,13 +898,13 @@ void psi_memstall_leave(unsigned long *flags)
 	if (*flags)
 		return;
 	/*
-	 * PF_MEMSTALL clearing & accounting needs to be atomic wrt
+	 * in_memstall clearing & accounting needs to be atomic wrt
 	 * changes to the task's scheduling state, otherwise we could
 	 * race with CPU migration.
 	 */
 	rq = this_rq_lock_irq(&rf);
 
-	current->flags &= ~PF_MEMSTALL;
+	current->in_memstall = 0;
 	psi_task_change(current, TSK_MEMSTALL, 0);
 
 	rq_unlock_irq(rq, &rf);
@@ -916,12 +963,14 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to)
 
 	rq = task_rq_lock(task, &rf);
 
-	if (task_on_rq_queued(task))
+	if (task_on_rq_queued(task)) {
 		task_flags = TSK_RUNNING;
-	else if (task->in_iowait)
+		if (task_current(rq, task))
+			task_flags |= TSK_ONCPU;
+	} else if (task->in_iowait)
 		task_flags = TSK_IOWAIT;
 
-	if (task->flags & PF_MEMSTALL)
+	if (task->in_memstall)
 		task_flags |= TSK_MEMSTALL;
 
 	if (task_flags)