[PATCH 08/17] sched/core: Implement CPU soft offline/online

[Srikar Dronamraju <srikar@linux.ibm.com>]

Scheduler already supports CPU online/offline. However for cases where
scheduler has to offline a CPU temporarily, the online/offline cost is
too high. Hence here is an attempt to come-up with soft-offline that
almost looks similar to offline without actually having to do the
full-offline. Since CPUs are not to be used temporarily for a short
duration, they will continue to be part of the CPU topology.

In the soft-offline, CPU will be marked as inactive, i.e removed from
the cpu_active_mask, CPUs capacity would be reduced and non-pinned tasks
would be migrated out of the CPU's runqueue.

Similarly when onlined, CPU will be remarked as active, i.e. added to
cpu_active_mask, CPUs capacity would be restored.

Soft-offline is almost similar as 1st step of offline except rebuilding
the sched-domains. Since the other steps are not done including
rebuilding the sched-domain, the overhead of soft-offline would be less
compared to regular offline. A new cpumask is used to indicate
soft-offline is in progress and hence skips rebuilding the
sched-domains.

To push tasks out of the CPU, balance_push is modified to push tasks out
till there are runnable tasks on the runqueue or till the CPU is in dying
state.

Signed-off-by: Srikar Dronamraju <srikar@linux.ibm.com>
---
 include/linux/sched/topology.h |  1 +
 kernel/sched/core.c            | 44 ++++++++++++++++++++++++++++++----
 2 files changed, 40 insertions(+), 5 deletions(-)

diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index bbcfdf12aa6e..ed45d7db3e76 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -241,4 +241,5 @@ static inline int task_node(const struct task_struct *p)
 	return cpu_to_node(task_cpu(p));
 }
 
+extern void set_cpu_softoffline(int cpu, bool soft_offline);
 #endif /* _LINUX_SCHED_TOPOLOGY_H */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 89efff1e1ead..f66fd1e925b0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8177,13 +8177,16 @@ static void balance_push(struct rq *rq)
 	 * Only active while going offline and when invoked on the outgoing
 	 * CPU.
 	 */
-	if (!cpu_dying(rq->cpu) || rq != this_rq())
+	if (cpu_active(rq->cpu) || rq != this_rq())
 		return;
 
 	/*
-	 * Ensure the thing is persistent until balance_push_set(.on = false);
+	 * Unless soft-offline, Ensure the thing is persistent until
+	 * balance_push_set(.on = false); In case of soft-offline, just
+	 * enough to push current non-pinned tasks out.
 	 */
-	rq->balance_callback = &balance_push_callback;
+	if (cpu_dying(rq->cpu) || rq->nr_running)
+		rq->balance_callback = &balance_push_callback;
 
 	/*
 	 * Both the cpu-hotplug and stop task are in this case and are
@@ -8392,6 +8395,8 @@ static inline void sched_smt_present_dec(int cpu)
 #endif
 }
 
+static struct cpumask cpu_softoffline_mask;
+
 int sched_cpu_activate(unsigned int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
@@ -8411,7 +8416,10 @@ int sched_cpu_activate(unsigned int cpu)
 	if (sched_smp_initialized) {
 		sched_update_numa(cpu, true);
 		sched_domains_numa_masks_set(cpu);
-		cpuset_cpu_active();
+
+		/* For CPU soft-offline, dont need to rebuild sched-domains */
+		if (!cpumask_test_cpu(cpu, &cpu_softoffline_mask))
+			cpuset_cpu_active();
 	}
 
 	scx_rq_activate(rq);
@@ -8485,7 +8493,11 @@ int sched_cpu_deactivate(unsigned int cpu)
 		return 0;
 
 	sched_update_numa(cpu, false);
-	cpuset_cpu_inactive(cpu);
+
+	/* For CPU soft-offline, dont need to rebuild sched-domains */
+	if (!cpumask_test_cpu(cpu, &cpu_softoffline_mask))
+		cpuset_cpu_inactive(cpu);
+
 	sched_domains_numa_masks_clear(cpu);
 	return 0;
 }
@@ -10928,3 +10940,25 @@ void sched_enq_and_set_task(struct sched_enq_and_set_ctx *ctx)
 		set_next_task(rq, ctx->p);
 }
 #endif /* CONFIG_SCHED_CLASS_EXT */
+
+void set_cpu_softoffline(int cpu, bool soft_offline)
+{
+	struct sched_domain *sd;
+
+	if (!cpu_online(cpu))
+		return;
+
+	cpumask_set_cpu(cpu, &cpu_softoffline_mask);
+
+	rcu_read_lock();
+	for_each_domain(cpu, sd)
+		update_group_capacity(sd, cpu);
+	rcu_read_unlock();
+
+	if (soft_offline)
+		sched_cpu_deactivate(cpu);
+	else
+		sched_cpu_activate(cpu);
+
+	cpumask_clear_cpu(cpu, &cpu_softoffline_mask);
+}
-- 
2.43.7