From: Andrea Righi <arighi@nvidia.com>
Date: Tue, 25 Mar 2025 09:32:12 +0000 (+0100)
Subject: sched_ext: initialize built-in idle state before ops.init()
X-Git-Tag: v6.15-rc1~40^2~1
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=f0c6eab5e45c529f449fbc595873719e00de6d79;p=thirdparty%2Fkernel%2Flinux.git

sched_ext: initialize built-in idle state before ops.init()

A BPF scheduler may want to use the built-in idle cpumasks in ops.init()
before the scheduler is fully initialized, either directly or through a
BPF timer for example.

However, this would result in an error, since the idle state has not
been properly initialized yet.

This can be easily verified by modifying scx_simple to call
scx_bpf_get_idle_cpumask() in ops.init():

$ sudo scx_simple

DEBUG DUMP
===========================================================================

scx_simple[121] triggered exit kind 1024:
  runtime error (built-in idle tracking is disabled)
...

Fix this by properly initializing the idle state before ops.init() is
called. With this change applied:

$ sudo scx_simple
local=2 global=0
local=19 global=11
local=23 global=11
...

Fixes: d73249f88743d ("sched_ext: idle: Make idle static keys private")
Signed-off-by: Andrea Righi <arighi@nvidia.com>
Reviewed-by: Joel Fernandes <joelagnelf@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index b47be2729ece1..66bcd40a28ca1 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -5361,6 +5361,8 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 	 */
 	cpus_read_lock();
 
+	scx_idle_enable(ops);
+
 	if (scx_ops.init) {
 		ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init);
 		if (ret) {
@@ -5427,8 +5429,6 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 	if (scx_ops.cpu_acquire || scx_ops.cpu_release)
 		static_branch_enable(&scx_ops_cpu_preempt);
 
-	scx_idle_enable(ops);
-
 	/*
 	 * Lock out forks, cgroup on/offlining and moves before opening the
 	 * floodgate so that they don't wander into the operations prematurely.
diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c
index b5f451e616d48..cb343ca889e02 100644
--- a/kernel/sched/ext_idle.c
+++ b/kernel/sched/ext_idle.c
@@ -721,14 +721,14 @@ static void reset_idle_masks(struct sched_ext_ops *ops)
 void scx_idle_enable(struct sched_ext_ops *ops)
 {
 	if (!ops->update_idle || (ops->flags & SCX_OPS_KEEP_BUILTIN_IDLE))
-		static_branch_enable(&scx_builtin_idle_enabled);
+		static_branch_enable_cpuslocked(&scx_builtin_idle_enabled);
 	else
-		static_branch_disable(&scx_builtin_idle_enabled);
+		static_branch_disable_cpuslocked(&scx_builtin_idle_enabled);
 
 	if (ops->flags & SCX_OPS_BUILTIN_IDLE_PER_NODE)
-		static_branch_enable(&scx_builtin_idle_per_node);
+		static_branch_enable_cpuslocked(&scx_builtin_idle_per_node);
 	else
-		static_branch_disable(&scx_builtin_idle_per_node);
+		static_branch_disable_cpuslocked(&scx_builtin_idle_per_node);
 
 #ifdef CONFIG_SMP
 	reset_idle_masks(ops);