[PATCH 1/4] sched_ext: idle: Honor idle flags in the built-in idle selection policy

[Andrea Righi]

Enable passing idle flags (%SCX_PICK_IDLE_*) to scx_select_cpu_dfl(),
to enforce strict selection criteria, such as selecting an idle CPU
strictly within @prev_cpu's node or choosing only a fully idle SMT core.

This functionality will be exposed through a dedicated kfunc in a
separate patch.

Signed-off-by: Andrea Righi <arighi@xxxxxxxxxx>
---
 kernel/sched/ext.c      |  2 +-
 kernel/sched/ext_idle.c | 41 ++++++++++++++++++++++++++++++-----------
 kernel/sched/ext_idle.h |  2 +-
 3 files changed, 32 insertions(+), 13 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index debcd1cf2de9b..5cd878bbd0e39 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -3396,7 +3396,7 @@ static int select_task_rq_scx(struct task_struct *p, int prev_cpu, int wake_flag
 		bool found;
 		s32 cpu;
 
-		cpu = scx_select_cpu_dfl(p, prev_cpu, wake_flags, &found);
+		cpu = scx_select_cpu_dfl(p, prev_cpu, wake_flags, 0, &found);
 		p->scx.selected_cpu = cpu;
 		if (found) {
 			p->scx.slice = SCX_SLICE_DFL;
diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c
index 15e9d1c8b2815..16981456ec1ed 100644
--- a/kernel/sched/ext_idle.c
+++ b/kernel/sched/ext_idle.c
@@ -418,7 +418,7 @@ void scx_idle_update_selcpu_topology(struct sched_ext_ops *ops)
  * NOTE: tasks that can only run on 1 CPU are excluded by this logic, because
  * we never call ops.select_cpu() for them, see select_task_rq().
  */
-s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, bool *found)
+s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, u64 flags, bool *found)
 {
 	const struct cpumask *llc_cpus = NULL;
 	const struct cpumask *numa_cpus = NULL;
@@ -455,12 +455,13 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, bool
 	 * If WAKE_SYNC, try to migrate the wakee to the waker's CPU.
 	 */
 	if (wake_flags & SCX_WAKE_SYNC) {
-		cpu = smp_processor_id();
+		int waker_node;
 
 		/*
 		 * If the waker's CPU is cache affine and prev_cpu is idle,
 		 * then avoid a migration.
 		 */
+		cpu = smp_processor_id();
 		if (cpus_share_cache(cpu, prev_cpu) &&
 		    scx_idle_test_and_clear_cpu(prev_cpu)) {
 			cpu = prev_cpu;
@@ -480,9 +481,11 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, bool
 		 * piled up on it even if there is an idle core elsewhere on
 		 * the system.
 		 */
+		waker_node = cpu_to_node(cpu);
 		if (!(current->flags & PF_EXITING) &&
 		    cpu_rq(cpu)->scx.local_dsq.nr == 0 &&
-		    !cpumask_empty(idle_cpumask(cpu_to_node(cpu))->cpu)) {
+		    (!(flags & SCX_PICK_IDLE_IN_NODE) || (waker_node == node)) &&
+		    !cpumask_empty(idle_cpumask(waker_node)->cpu)) {
 			if (cpumask_test_cpu(cpu, p->cpus_ptr))
 				goto cpu_found;
 		}
@@ -521,15 +524,25 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, bool
 		}
 
 		/*
-		 * Search for any full idle core usable by the task.
+		 * Search for any full-idle core usable by the task.
 		 *
-		 * If NUMA aware idle selection is enabled, the search will
+		 * If the node-aware idle CPU selection policy is enabled
+		 * (%SCX_OPS_BUILTIN_IDLE_PER_NODE), the search will always
 		 * begin in prev_cpu's node and proceed to other nodes in
 		 * order of increasing distance.
 		 */
-		cpu = scx_pick_idle_cpu(p->cpus_ptr, node, SCX_PICK_IDLE_CORE);
+		cpu = scx_pick_idle_cpu(p->cpus_ptr, node, flags | SCX_PICK_IDLE_CORE);
 		if (cpu >= 0)
 			goto cpu_found;
+
+		/*
+		 * Give up if we're strictly looking for a full-idle SMT
+		 * core.
+		 */
+		if (flags & SCX_PICK_IDLE_CORE) {
+			cpu = prev_cpu;
+			goto out_unlock;
+		}
 	}
 
 	/*
@@ -560,18 +573,24 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, bool
 
 	/*
 	 * Search for any idle CPU usable by the task.
+	 *
+	 * If the node-aware idle CPU selection policy is enabled
+	 * (%SCX_OPS_BUILTIN_IDLE_PER_NODE), the search will always begin
+	 * in prev_cpu's node and proceed to other nodes in order of
+	 * increasing distance.
 	 */
-	cpu = scx_pick_idle_cpu(p->cpus_ptr, node, 0);
+	cpu = scx_pick_idle_cpu(p->cpus_ptr, node, flags);
 	if (cpu >= 0)
 		goto cpu_found;
 
-	rcu_read_unlock();
-	return prev_cpu;
+	cpu = prev_cpu;
+	goto out_unlock;
 
 cpu_found:
+	*found = true;
+out_unlock:
 	rcu_read_unlock();
 
-	*found = true;
 	return cpu;
 }
 
@@ -810,7 +829,7 @@ __bpf_kfunc s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu,
 		goto prev_cpu;
 
 #ifdef CONFIG_SMP
-	return scx_select_cpu_dfl(p, prev_cpu, wake_flags, is_idle);
+	return scx_select_cpu_dfl(p, prev_cpu, wake_flags, 0, is_idle);
 #endif
 
 prev_cpu:
diff --git a/kernel/sched/ext_idle.h b/kernel/sched/ext_idle.h
index 68c4307ce4f6f..5c1db6b315f7a 100644
--- a/kernel/sched/ext_idle.h
+++ b/kernel/sched/ext_idle.h
@@ -27,7 +27,7 @@ static inline s32 scx_pick_idle_cpu(const struct cpumask *cpus_allowed, int node
 }
 #endif /* CONFIG_SMP */
 
-s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, bool *found);
+s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, u64 flags, bool *found);
 void scx_idle_enable(struct sched_ext_ops *ops);
 void scx_idle_disable(void);
 int scx_idle_init(void);
-- 
2.48.1