From: Andrea Righi <arighi@nvidia.com>
Date: Sat, 5 Apr 2025 13:39:22 +0000 (+0200)
Subject: sched_ext: idle: Explicitly pass allowed cpumask to scx_select_cpu_dfl()
X-Git-Url: https://www.infradead.org/git/?a=commitdiff_plain;h=23c63a965275ce5d6268075bbfe7ce8b6ffe9a35;p=users%2Fwilly%2Fxarray.git

sched_ext: idle: Explicitly pass allowed cpumask to scx_select_cpu_dfl()

Modify scx_select_cpu_dfl() to take the allowed cpumask as an explicit
argument, instead of implicitly using @p->cpus_ptr.

This prepares for future changes where arbitrary cpumasks may be passed
to the built-in idle CPU selection policy.

This is a pure refactoring with no functional changes.

Signed-off-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 6781e6da059b..ac3fd7a409e9 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -3392,7 +3392,7 @@ static int select_task_rq_scx(struct task_struct *p, int prev_cpu, int wake_flag
 	} else {
 		s32 cpu;
 
-		cpu = scx_select_cpu_dfl(p, prev_cpu, wake_flags, 0);
+		cpu = scx_select_cpu_dfl(p, prev_cpu, wake_flags, NULL, 0);
 		if (cpu >= 0) {
 			p->scx.slice = SCX_SLICE_DFL;
 			p->scx.ddsp_dsq_id = SCX_DSQ_LOCAL;
diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c
index ed37fb8e4518..5d6253c6ed90 100644
--- a/kernel/sched/ext_idle.c
+++ b/kernel/sched/ext_idle.c
@@ -438,9 +438,11 @@ static inline bool task_affinity_all(const struct task_struct *p)
  * 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, u64 flags)
+s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags,
+		       const struct cpumask *cpus_allowed, u64 flags)
 {
 	const struct cpumask *llc_cpus = NULL, *numa_cpus = NULL;
+	const struct cpumask *allowed = cpus_allowed ?: p->cpus_ptr;
 	int node = scx_cpu_node_if_enabled(prev_cpu);
 	s32 cpu;
 
@@ -460,9 +462,9 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, u64
 		struct cpumask *local_cpus = this_cpu_cpumask_var_ptr(local_numa_idle_cpumask);
 		const struct cpumask *cpus = numa_span(prev_cpu);
 
-		if (task_affinity_all(p))
+		if (allowed == p->cpus_ptr && task_affinity_all(p))
 			numa_cpus = cpus;
-		else if (cpus && cpumask_and(local_cpus, p->cpus_ptr, cpus))
+		else if (cpus && cpumask_and(local_cpus, allowed, cpus))
 			numa_cpus = local_cpus;
 	}
 
@@ -470,9 +472,9 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, u64
 		struct cpumask *local_cpus = this_cpu_cpumask_var_ptr(local_llc_idle_cpumask);
 		const struct cpumask *cpus = llc_span(prev_cpu);
 
-		if (task_affinity_all(p))
+		if (allowed == p->cpus_ptr && task_affinity_all(p))
 			llc_cpus = cpus;
-		else if (cpus && cpumask_and(local_cpus, p->cpus_ptr, cpus))
+		else if (cpus && cpumask_and(local_cpus, allowed, cpus))
 			llc_cpus = local_cpus;
 	}
 
@@ -511,7 +513,7 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, u64
 		    cpu_rq(cpu)->scx.local_dsq.nr == 0 &&
 		    (!(flags & SCX_PICK_IDLE_IN_NODE) || (waker_node == node)) &&
 		    !cpumask_empty(idle_cpumask(waker_node)->cpu)) {
-			if (cpumask_test_cpu(cpu, p->cpus_ptr))
+			if (cpumask_test_cpu(cpu, allowed))
 				goto out_unlock;
 		}
 	}
@@ -556,7 +558,7 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, u64
 		 * 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, flags | SCX_PICK_IDLE_CORE);
+		cpu = scx_pick_idle_cpu(allowed, node, flags | SCX_PICK_IDLE_CORE);
 		if (cpu >= 0)
 			goto out_unlock;
 
@@ -604,7 +606,7 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, u64
 	 * in prev_cpu's node and proceed to other nodes in order of
 	 * increasing distance.
 	 */
-	cpu = scx_pick_idle_cpu(p->cpus_ptr, node, flags);
+	cpu = scx_pick_idle_cpu(allowed, node, flags);
 
 out_unlock:
 	rcu_read_unlock();
@@ -858,7 +860,7 @@ __bpf_kfunc s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu,
 		goto prev_cpu;
 
 #ifdef CONFIG_SMP
-	cpu = scx_select_cpu_dfl(p, prev_cpu, wake_flags, 0);
+	cpu = scx_select_cpu_dfl(p, prev_cpu, wake_flags, NULL, 0);
 	if (cpu >= 0) {
 		*is_idle = true;
 		return cpu;
diff --git a/kernel/sched/ext_idle.h b/kernel/sched/ext_idle.h
index 511cc2221f7a..37be78a7502b 100644
--- a/kernel/sched/ext_idle.h
+++ b/kernel/sched/ext_idle.h
@@ -27,7 +27,8 @@ 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, u64 flags);
+s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags,
+		       const struct cpumask *cpus_allowed, u64 flags);
 void scx_idle_enable(struct sched_ext_ops *ops);
 void scx_idle_disable(void);
 int scx_idle_init(void);