Commit f0c6eab5 authored by Andrea Righi's avatar Andrea Righi Committed by Tejun Heo
Browse files

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: d73249f8 ("sched_ext: idle: Make idle static keys private")
Signed-off-by: default avatarAndrea Righi <arighi@nvidia.com>
Reviewed-by: default avatarJoel Fernandes <joelagnelf@nvidia.com>
Signed-off-by: default avatarTejun Heo <tj@kernel.org>
parent a8897ed8

kernel/sched/ext.c

+2 −2
Original line number Diff line number Diff line
@@ -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.

kernel/sched/ext_idle.c

+4 −4
Original line number Diff line number Diff line
@@ -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);