Merge tag 'v5.0-rc6' into sched/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

3 files changed, 34 insertions, 7 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ec1b67a195cc..e86e2b8f6922 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -398,6 +398,18 @@ static bool set_nr_if_polling(struct task_struct *p)
 #endif
 #endif
 
+/**
+ * wake_q_add() - queue a wakeup for 'later' waking.
+ * @head: the wake_q_head to add @task to
+ * @task: the task to queue for 'later' wakeup
+ *
+ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
+ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
+ * instantly.
+ *
+ * This function must be used as-if it were wake_up_process(); IOW the task
+ * must be ready to be woken at this location.
+ */
 void wake_q_add(struct wake_q_head *head, struct task_struct *task)
 {
 	struct wake_q_node *node = &task->wake_q;
@@ -407,10 +419,11 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task)
 	 * its already queued (either by us or someone else) and will get the
 	 * wakeup due to that.
 	 *
-	 * This cmpxchg() executes a full barrier, which pairs with the full
-	 * barrier executed by the wakeup in wake_up_q().
+	 * In order to ensure that a pending wakeup will observe our pending
+	 * state, even in the failed case, an explicit smp_mb() must be used.
 	 */
-	if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL))
+	smp_mb__before_atomic();
+	if (cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL))
 		return;
 
 	get_task_struct(task);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ffd1ae7237e7..38d4669aa2ef 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6009,6 +6009,7 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p
 
 #ifdef CONFIG_SCHED_SMT
 DEFINE_STATIC_KEY_FALSE(sched_smt_present);
+EXPORT_SYMBOL_GPL(sched_smt_present);
 
 static inline void set_idle_cores(int cpu, int val)
 {
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index fe24de3fbc93..c3484785b179 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -124,6 +124,7 @@
  * sampling of the aggregate task states would be.
  */
 
+#include "../workqueue_internal.h"
 #include <linux/sched/loadavg.h>
 #include <linux/seq_file.h>
 #include <linux/proc_fs.h>
@@ -480,9 +481,6 @@ static void psi_group_change(struct psi_group *group, int cpu,
 			groupc->tasks[t]++;
 
 	write_seqcount_end(&groupc->seq);
-
-	if (!delayed_work_pending(&group->clock_work))
-		schedule_delayed_work(&group->clock_work, PSI_FREQ);
 }
 
 static struct psi_group *iterate_groups(struct task_struct *task, void **iter)
@@ -513,6 +511,7 @@ 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)
@@ -530,8 +529,22 @@ void psi_task_change(struct task_struct *task, int clear, int set)
 	task->psi_flags &= ~clear;
 	task->psi_flags |= set;
 
-	while ((group = iterate_groups(task, &iter)))
+	/*
+	 * Periodic aggregation shuts off if there is a period of no
+	 * task changes, so we wake it back up if necessary. However,
+	 * don't do this if the task change is the aggregation worker
+	 * itself going to sleep, or we'll ping-pong forever.
+	 */
+	if (unlikely((clear & TSK_RUNNING) &&
+		     (task->flags & PF_WQ_WORKER) &&
+		     wq_worker_last_func(task) == psi_update_work))
+		wake_clock = false;
+
+	while ((group = iterate_groups(task, &iter))) {
 		psi_group_change(group, cpu, clear, set);
+		if (wake_clock && !delayed_work_pending(&group->clock_work))
+			schedule_delayed_work(&group->clock_work, PSI_FREQ);
+	}
 }
 
 void psi_memstall_tick(struct task_struct *task, int cpu)