From 3c4b38064937a761ebbf85b1649e812db85eb59e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 27 Jul 2026 11:20:32 -1000 Subject: [PATCH] sched_ext: Abort directly from the hardlockup handler scx_hardlockup() defers the abort to an irq_work because exit claiming used to take scx_sched_lock and couldn't run from NMI. The deferral is now unnecessary - claiming is NMI-safe and asserting ->aborting is exactly what breaks the live-locks that hard-lock CPUs. Call handle_lockup() directly and drop the irq_work. This also makes the self-detected case recoverable: the perf watchdog fires on the hard-locked CPU itself, where a queued irq_work never runs with IRQs off. Also fix the return value: %true used to be returned whenever sched_ext was loaded, suppressing the kernel's hardlockup report even when the abort was refused. Return %true only when this call initiated the abort. Fixes: bd2d76455b65 ("sched_ext: Defer scx_hardlockup() out of NMI") Signed-off-by: Tejun Heo Reviewed-by: Andrea Righi --- kernel/sched/ext/ext.c | 35 +++++++++-------------------------- 1 file changed, 9 insertions(+), 26 deletions(-) diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c index cff55fa3d58f..f99c2b8557e6 100644 --- a/kernel/sched/ext/ext.c +++ b/kernel/sched/ext/ext.c @@ -5390,25 +5390,6 @@ void scx_softlockup(u32 dur_s) cpu, dur_s); } -/* - * scx_hardlockup() runs from NMI and eventually calls scx_claim_exit(), - * which takes scx_sched_lock. scx_sched_lock isn't NMI-safe and grabbing - * it from NMI context can lead to deadlocks. Defer via irq_work; the - * disable path runs off irq_work anyway. - */ -static atomic_t scx_hardlockup_cpu = ATOMIC_INIT(-1); - -static void scx_hardlockup_irq_workfn(struct irq_work *work) -{ - int cpu = atomic_xchg(&scx_hardlockup_cpu, -1); - - if (cpu >= 0 && handle_lockup(cpu, "hard lockup - CPU %d", cpu)) - printk_deferred(KERN_ERR "sched_ext: Hard lockup - CPU %d, disabling BPF scheduler\n", - cpu); -} - -static DEFINE_IRQ_WORK(scx_hardlockup_irq_work, scx_hardlockup_irq_workfn); - /** * scx_hardlockup - sched_ext hardlockup handler * @cpu: the target CPU @@ -5418,19 +5399,21 @@ static DEFINE_IRQ_WORK(scx_hardlockup_irq_work, scx_hardlockup_irq_workfn); * Try kicking out the current scheduler in an attempt to recover the system to * a good state before taking more drastic actions. * - * Queues an irq_work; the handle_lockup() call happens in IRQ context (see - * scx_hardlockup_irq_workfn). + * Called from NMI. Aborting the scheduler sets ->aborting throughout the + * hierarchy before returning, which is what breaks the dispatch-path live-locks + * that can hard-lock CPUs. * - * Returns %true if sched_ext is enabled and the work was queued, %false - * otherwise. + * Returns %true if sched_ext is enabled and abort was initiated, which may + * resolve the lockup. %false if sched_ext is not enabled or abort was already + * initiated by someone else. */ bool scx_hardlockup(int cpu) { - if (!rcu_access_pointer(scx_root)) + if (!handle_lockup(cpu, "hard lockup - CPU %d", cpu)) return false; - atomic_cmpxchg(&scx_hardlockup_cpu, -1, cpu); - irq_work_queue(&scx_hardlockup_irq_work); + printk_deferred(KERN_ERR "sched_ext: Hard lockup - CPU %d, disabling BPF scheduler\n", + cpu); return true; }