Merge tag 'sched_ext-for-7.3-rc3-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_extHEADmaster

Pull sched_ext fixes from Tejun Heo:

 - An error raised by a BPF program before the scheduler finished
   enabling was consumed by the disable path's pre-enable shortcut,
   leaving a running scheduler that couldn't be disabled and was later
   freed while in use.

 - Two compat kfuncs dereferenced a NULL scheduler when handed an exited
   or idle task, oopsing the kernel.

 - Keep-running decisions in the dispatch path used the root scheduler's
   flags for tasks belonging to a sub-scheduler, causing warnings and
   stalls.

 - Schedulers with their own CPU ID mapping had no way to learn which
   IDs are online. Add a kernel-maintained online mask to plug the hole.

 - Cgroup idle state: the initial cpu.idle state wasn't passed on cgroup
   init and same-value rewrites delivered spurious callbacks.

 - Example scheduler fixes for a reenqueue loop on attach, placements on
   CPUs without effective grants, stalled partition work and stale idle
   tracking.

* tag 'sched_ext-for-7.3-rc3-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext:
  sched_ext: Maintain an online cid mask in the scheduler arena
  sched_ext: scx_qmap: Restore unused idle claims from ops.dispatch()
  sched_ext: Close the pre-enable ops error claim window
  sched_ext: scx_qmap: Fix pending partition work handoff
  sched_ext: scx_qmap: Place only on cids whose caps are in effect
  sched_ext: scx_qmap: Do not add IMMED to rescue inserts
  sched_ext: Use @prev's scheduler for the keep decisions in dispatch_one()
  sched_ext: Rename sch to root_sch in dispatch_one()
  sched_ext: Fix NULL sched deref in kfunc sub-sched error paths
  sched_ext: Don't deliver duplicate ops.cgroup_set_idle() for same value
  sched_ext: Pass the initial cpu.idle state in scx_cgroup_init_args

1 files changed, 8 insertions, 4 deletions

diff --git a/kernel/sched/ext/sub.c b/kernel/sched/ext/sub.c
index 9e7040482bde..34e642a1a403 100644
--- a/kernel/sched/ext/sub.c
+++ b/kernel/sched/ext/sub.c
@@ -1361,6 +1361,7 @@ static s32 scx_cgroup_claim_subtree(struct scx_sched *sch)
 			.bw_period_us = tg->scx.bw_period_us,
 			.bw_quota_us = tg->scx.bw_quota_us,
 			.bw_burst_us = tg->scx.bw_burst_us,
+			.sched_idle = tg->scx.idle,
 		};
 
 		if (tg->scx.sched != parent ||
@@ -1464,6 +1465,7 @@ static void scx_cgroup_return_subtree(struct scx_sched *sch)
 			.bw_period_us = tg->scx.bw_period_us,
 			.bw_quota_us = tg->scx.bw_quota_us,
 			.bw_burst_us = tg->scx.bw_burst_us,
+			.sched_idle = tg->scx.idle,
 		};
 
 		/* the first pass must have transferred everything */
@@ -1803,6 +1805,12 @@ void scx_sub_enable_workfn(struct kthread_work *work)
 		goto err_disable;
 	}
 
+	scoped_guard(cpus_read_lock) {
+		ret = scx_alloc_kern_arena_objs(sch);
+		if (ret)
+			goto err_disable;
+	}
+
 	if (sch->ops.init) {
 		ret = SCX_CALL_OP_RET(sch, init, NULL);
 		if (ret) {
@@ -1813,10 +1821,6 @@ void scx_sub_enable_workfn(struct kthread_work *work)
 		sch->exit_info->flags |= SCX_EFLAG_INITIALIZED;
 	}
 
-	ret = scx_set_cmask_scratch_alloc(sch);
-	if (ret)
-		goto err_disable;
-
 	struct scx_sub_attach_args sub_attach_args = {
 		.ops = &sch->ops,
 		.cgroup_path = sch->cgrp_path,