[PATCH v5 11/24] sched/core: Push current task from non preferred CPU

[Shrikanth Hegde <sshegde@linux.ibm.com>]

Actively push out task running on a non-preferred CPU. Since the task is
running on the CPU, need to stop the cpu and push the task out.
However, if the task in pinned only to non-preferred CPUs, it will continue
running there. This will help in maintaining the userspace affinities
unlike CPU hotplug or isolated cpusets.

Though code is almost same as __balance_push_cpu_stop and quite close to
push_cpu_stop, it is being kept separate as it provides a cleaner
implementation w.r.t CONFIG_HOTPLUG_CPU.

Add push_task_work_done flag to protect work buffer.
Works only with FAIR class.

Signed-off-by: Shrikanth Hegde <sshegde@linux.ibm.com>
---
v4->v5:
- Move select_fallback_rq outside of rq_lock (Sashiko)
- Add context_unsafe_alias (K Prateek Nayak)
- Cleanup properly on early exit.

 kernel/sched/core.c  | 87 ++++++++++++++++++++++++++++++++++++++++++++
 kernel/sched/sched.h |  8 ++++
 2 files changed, 95 insertions(+)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c0391e7897f5..1e42078251d5 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5794,6 +5794,9 @@ void sched_tick(void)
 	unsigned long hw_pressure;
 	u64 resched_latency;
 
+	if (!cpu_preferred(cpu))
+		sched_push_current_non_preferred_cpu(rq);
+
 	if (housekeeping_cpu(cpu, HK_TYPE_KERNEL_NOISE))
 		arch_scale_freq_tick();
 
@@ -11303,3 +11306,87 @@ void sched_change_end(struct sched_change_ctx *ctx)
 		p->sched_class->prio_changed(rq, p, ctx->prio);
 	}
 }
+
+#ifdef CONFIG_PREFERRED_CPU
+/* npc - non preferred CPU */
+static DEFINE_PER_CPU(struct cpu_stop_work, npc_push_task_work);
+
+static int sched_non_preferred_cpu_push_stop(void *arg)
+{
+	struct task_struct *p = arg;
+	struct rq *rq = this_rq();
+	struct rq_flags rf;
+	int cpu;
+
+	/* sanity check and clear */
+	if (cpu_preferred(rq->cpu)) {
+		scoped_guard (rq_lock, rq)
+			rq->push_task_work_done = 0;
+		put_task_struct(p);
+		return 0;
+	}
+
+	raw_spin_lock_irq(&p->pi_lock);
+
+	/* This could take rq lock. So call it before rq lock is taken */
+	cpu = select_fallback_rq(rq->cpu, p);
+	rq_lock(rq, &rf);
+	rq->push_task_work_done = 0;
+	update_rq_clock(rq);
+
+	context_unsafe_alias(rq);
+
+	if (task_rq(p) == rq && task_on_rq_queued(p))
+		rq = __migrate_task(rq, &rf, p, cpu);
+
+	rq_unlock(rq, &rf);
+	raw_spin_unlock_irq(&p->pi_lock);
+	put_task_struct(p);
+
+	return 0;
+}
+
+/*
+ * Push the current task running on non-preferred CPU.
+ * Using this non preferred CPU will lead to more vCPU preemptions
+ * in the host. So it is better not to use this CPU.
+ *
+ * Since task is running, call a stopper to push the task out. This is
+ * similar to how task moves during hotplug. In select_fallback_rq a
+ * preferred CPU will be chosen and henceforth task shouldn't come back to
+ * this CPU again.
+ *
+ * Works for FAIR class only
+ *
+ * If task is affined only non-preferred CPUs, it can't be moved out
+ */
+void sched_push_current_non_preferred_cpu(struct rq *rq)
+{
+	struct task_struct *push_task = rq->curr;
+
+	/* Push only if it is FAIR class */
+	if (push_task->sched_class != &fair_sched_class)
+		return;
+
+	if (kthread_is_per_cpu(push_task) ||
+	    is_migration_disabled(push_task))
+		return;
+
+	/* Is there any preferred CPU in the affinity list */
+	if (!task_has_preferred_cpus(push_task))
+		return;
+
+	/* There is already a stopper thread for this. Dont race with it */
+	if (rq->push_task_work_done == 1)
+		return;
+
+	/* sched_tick runs with interrupts disabled. Don't disable again */
+	get_task_struct(push_task);
+
+	scoped_guard (rq_lock, rq)
+		rq->push_task_work_done = 1;
+
+	stop_one_cpu_nowait(rq->cpu, sched_non_preferred_cpu_push_stop,
+			    push_task, this_cpu_ptr(&npc_push_task_work));
+}
+#endif
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 148fe6145f1a..316d3ccefc48 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1274,6 +1274,8 @@ struct rq {
 
 	struct list_head cfs_tasks;
 
+	bool			push_task_work_done;
+
 	struct sched_avg	avg_rt;
 	struct sched_avg	avg_dl;
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
@@ -4241,4 +4243,10 @@ static inline bool task_has_preferred_cpus(struct task_struct *p)
 	else
 		return cpumask_intersects(p->cpus_ptr, cpu_preferred_mask);
 }
+
+#ifdef CONFIG_PREFERRED_CPU
+void sched_push_current_non_preferred_cpu(struct rq *rq);
+#else	/* !CONFIG_PREFERRED_CPU */
+static inline void sched_push_current_non_preferred_cpu(struct rq *rq) { }
+#endif
 #endif /* _KERNEL_SCHED_SCHED_H */
-- 
2.47.3