powerpc: Fix races with irq_work

If we set irq_work on a processor and immediately afterward, before the
irq work has a chance to be processed, we change the decrementer value,
we can seriously delay the handling of that irq_work.

Fix it by checking in a few places for pending irq work, first before
changing the decrementer in decrementer_set_next_event() and after
changing it in the same function and in timer_interrupt().

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

1 files changed, 11 insertions, 0 deletions

diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index afb1b56..b3dab20 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -536,6 +536,9 @@ void timer_interrupt(struct pt_regs * regs)
 		now = *next_tb - now;
 		if (now <= DECREMENTER_MAX)
 			set_dec((int)now);
+		/* We may have raced with new irq work */
+		if (test_irq_work_pending())
+			set_dec(1);
 		__get_cpu_var(irq_stat).timer_irqs_others++;
 	}
 
@@ -802,8 +805,16 @@ static void __init clocksource_init(void)
 static int decrementer_set_next_event(unsigned long evt,
 				      struct clock_event_device *dev)
 {
+	/* Don't adjust the decrementer if some irq work is pending */
+	if (test_irq_work_pending())
+		return 0;
 	__get_cpu_var(decrementers_next_tb) = get_tb_or_rtc() + evt;
 	set_dec(evt);
+
+	/* We may have raced with new irq work */
+	if (test_irq_work_pending())
+		set_dec(1);
+
 	return 0;
 }