lib/irq_poll: Prevent softirq pending leak in irq_poll_cpu_dead()

irq_poll_cpu_dead() pulls the blk_cpu_iopoll backlog from the dead CPU and
raises the POLL softirq with __raise_softirq_irqoff() on the CPU it is
running on. That just sets the bit in the pending softirq mask.

This means the handling of the softirq is delayed until the next interrupt
or a local_bh_disable/enable() pair. As a consequence the CPU on which this
code runs can reach idle with the POLL softirq pending, which triggers a
warning in the NOHZ idle code.

Add a local_bh_disable/enable() pair around the interrupts disabled section
in irq_poll_cpu_dead(). local_bh_enable will handle the pending softirq.

[tglx: Massaged changelog and comment]

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/87k0bxgl27.ffs@tglx

1 files changed, 6 insertions, 2 deletions

diff --git a/lib/irq_poll.c b/lib/irq_poll.c
index 2f17b488d58e..2d5329a42105 100644
--- a/lib/irq_poll.c
+++ b/lib/irq_poll.c
@@ -188,14 +188,18 @@ EXPORT_SYMBOL(irq_poll_init);
 static int irq_poll_cpu_dead(unsigned int cpu)
 {
 	/*
-	 * If a CPU goes away, splice its entries to the current CPU
-	 * and trigger a run of the softirq
+	 * If a CPU goes away, splice its entries to the current CPU and
+	 * set the POLL softirq bit. The local_bh_disable()/enable() pair
+	 * ensures that it is handled. Otherwise the current CPU could
+	 * reach idle with the POLL softirq pending.
 	 */
+	local_bh_disable();
 	local_irq_disable();
 	list_splice_init(&per_cpu(blk_cpu_iopoll, cpu),
 			 this_cpu_ptr(&blk_cpu_iopoll));
 	__raise_softirq_irqoff(IRQ_POLL_SOFTIRQ);
 	local_irq_enable();
+	local_bh_enable();
 
 	return 0;
 }