Merge tag 'smp-urgent-2023-09-02' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull CPU hotplug fix from Ingo Molnar:
 "Fix a CPU hotplug related deadlock between the task which initiates
  and controls a CPU hot-unplug operation vs. the CFS bandwidth timer"

* tag 'smp-urgent-2023-09-02' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  cpu/hotplug: Prevent self deadlock on CPU hot-unplug

1 files changed, 23 insertions, 1 deletions

diff --git a/kernel/cpu.c b/kernel/cpu.c
index f6811c8571023..6de7c6bb74eee 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1487,8 +1487,22 @@ out:
 	return ret;
 }
 
+struct cpu_down_work {
+	unsigned int		cpu;
+	enum cpuhp_state	target;
+};
+
+static long __cpu_down_maps_locked(void *arg)
+{
+	struct cpu_down_work *work = arg;
+
+	return _cpu_down(work->cpu, 0, work->target);
+}
+
 static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target)
 {
+	struct cpu_down_work work = { .cpu = cpu, .target = target, };
+
 	/*
 	 * If the platform does not support hotplug, report it explicitly to
 	 * differentiate it from a transient offlining failure.
@@ -1497,7 +1511,15 @@ static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target)
 		return -EOPNOTSUPP;
 	if (cpu_hotplug_disabled)
 		return -EBUSY;
-	return _cpu_down(cpu, 0, target);
+
+	/*
+	 * Ensure that the control task does not run on the to be offlined
+	 * CPU to prevent a deadlock against cfs_b->period_timer.
+	 */
+	cpu = cpumask_any_but(cpu_online_mask, cpu);
+	if (cpu >= nr_cpu_ids)
+		return -EBUSY;
+	return work_on_cpu(cpu, __cpu_down_maps_locked, &work);
 }
 
 static int cpu_down(unsigned int cpu, enum cpuhp_state target)