[PATCH v6 18/23] virt/steal_monitor: Provide default method to inc/dec preferred CPUs

[Shrikanth Hegde]

These methods will be used by the steal_monitor core in subsequent
patches. Default implementation are likely good enough for most archs.

decrease_preferred_cpus() - Called when there is high steal time. It needs
to decide which CPUs to mark as non-preferred and set that state.
increase_preferred_cpus() - Called when there is low steal time. It needs
to decide which CPUs to mark as preferred and set that state.

Default Implementations:
decrease_preferred_cpus()
- Get first housekeeping CPU and its core mask. Mark it as
  protected core. This helps to keep at least one core as preferred.
  This is to be safe under non-normal cases.
- Find the last CPU outside of this protected core mask. (target CPU)
  This works for cases where one may specify nohz_full= for last set of
  CPUs as well.
- If no such CPU exits, then only housekeeping core remains. Bail out.
- Based on that target CPU, get its sibling and mark them as
  non-preferred. If they are nohz_full, enable the tick.
  push mechanism relies on sched_tick.

increase_preferred_cpus()
- Get the first active non-preferred CPUs. This likely is the last
  set of CPUs being marked as non-preferred.
- If there is no such CPU, i.e preferred is same as active. Nothing
  todo further.
- If not, get the siblings of that core and mark them as preferred.
  Note that clearing the tick isn't needed as that would be handled via
  sched_can_stop_tick.

Using core instead of individual CPUs give better numbers as SMT is
quite common and some hypervisor such as powerVM does core scheduling.

Note: This doesn't do any NUMA splicing to keep the code simpler and
minimal overhead. current code expects CPUs spread unformly
across NUMA nodes.

Signed-off-by: Shrikanth Hegde <sshegde@xxxxxxxxxxxxx>
---
v5->v6:
- Make it work for all cases when nohz_full= may be specified.

 drivers/virt/steal_monitor/defaults.c | 74 +++++++++++++++++++++++++++
 drivers/virt/steal_monitor/sm_core.h  |  2 +
 2 files changed, 76 insertions(+)

diff --git a/drivers/virt/steal_monitor/defaults.c b/drivers/virt/steal_monitor/defaults.c
index 6681f9938f6a..4e2e5b233948 100644
--- a/drivers/virt/steal_monitor/defaults.c
+++ b/drivers/virt/steal_monitor/defaults.c
@@ -26,3 +26,77 @@ u64 __weak get_system_steal_time(void)
 
 	return total_steal;
 }
+
+/*
+ * Default implementation of decrementing the preferred CPUs based on steal
+ * time. This is simple logic and decrease the preferred CPUs by 1 core.
+ * It takes out the last core in the active & preferred.
+ *
+ * Ensure at least one housekeeping core is always kept as preferred
+ *
+ * Could be overwritten by arch specific handling. Arch must ensure
+ * preferred is always subset of active.
+ */
+
+#define get_core_mask(cpu) topology_sibling_cpumask(cpu)
+
+void __weak decrease_preferred_cpus(struct steal_monitor *ctx)
+{
+	int tmp_cpu, first_hk_cpu;
+	const struct cpumask *first_hk_core;
+	int target_cpu = nr_cpu_ids;
+
+	guard(cpus_read_lock)();
+
+	first_hk_cpu = cpumask_first_and(housekeeping_cpumask(HK_TYPE_KERNEL_NOISE),
+					 cpu_active_mask);
+
+	if (first_hk_cpu >= nr_cpu_ids)
+		return;
+
+	first_hk_core = get_core_mask(first_hk_cpu);
+
+	/* Always leave first housekeeping core as preferred. */
+	for_each_cpu_andnot(tmp_cpu, cpu_preferred_mask, first_hk_core)
+		target_cpu = tmp_cpu;
+
+	/* Only the first housekeeping core remains */
+	if (target_cpu >= nr_cpu_ids)
+		return;
+
+	/*
+	 * set tick bit for nohz_full CPU to push the task out. Once the tasks
+	 * are pushed out, bit will be cleared if there are no tasks.
+	 */
+
+	for_each_cpu_and(tmp_cpu, get_core_mask(target_cpu), cpu_active_mask) {
+		set_cpu_preferred(tmp_cpu, false);
+		if (tick_nohz_full_cpu(tmp_cpu))
+			tick_nohz_dep_set_cpu(tmp_cpu, TICK_DEP_BIT_SCHED);
+	}
+}
+
+/*
+ * Default implementation of incrementing preferred CPUs based on steal
+ * time. This is simple logic and increases the preferred CPUs by 1 core.
+ * It adds the first core in active & !preferred
+ *
+ * Nothing to do if active == preferred
+ *
+ * Could be overwritten by arch specific handling. Arch must ensure
+ * preferred is subset of active.
+ */
+void __weak increase_preferred_cpus(struct steal_monitor *ctx)
+{
+	int first_cpu, tmp_cpu;
+
+	guard(cpus_read_lock)();
+
+	first_cpu = cpumask_first_andnot(cpu_active_mask, cpu_preferred_mask);
+	/* All CPUs are preferred. Nothing to increase further */
+	if (first_cpu >= nr_cpu_ids)
+		return;
+
+	for_each_cpu_and(tmp_cpu, get_core_mask(first_cpu), cpu_active_mask)
+		set_cpu_preferred(tmp_cpu, true);
+}
diff --git a/drivers/virt/steal_monitor/sm_core.h b/drivers/virt/steal_monitor/sm_core.h
index 634c9f5a2610..030f6236c38e 100644
--- a/drivers/virt/steal_monitor/sm_core.h
+++ b/drivers/virt/steal_monitor/sm_core.h
@@ -26,5 +26,7 @@ struct steal_monitor {
 extern struct steal_monitor sm_core_ctx;
 
 u64 get_system_steal_time(void);
+void increase_preferred_cpus(struct steal_monitor *ctx);
+void decrease_preferred_cpus(struct steal_monitor *ctx);
 
 #endif /* __VIRT_STEAL_CORE_H */
-- 
2.47.3