clockevents/drivers/arm_global_timer: Use writel_relaxed in gt_compare_set

Use the relaxed version to improve performance. we measured time of
4096 rounds of gt_compare_set() spent on Marvell BG2Q:

before the patch: 3690648ns on average
after the patch: 1083023ns on average

improved by 70%!

Signed-off-by: Jisheng Zhang <jszhang@marvell.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>

diff --git a/drivers/clocksource/arm_global_timer.c b/drivers/clocksource/arm_global_timer.c
index a2cb6fa..f99be6b 100644 (file)
--- a/drivers/clocksource/arm_global_timer.c
+++ b/drivers/clocksource/arm_global_timer.c
@@ -99,17 +99,17 @@ static void gt_compare_set(unsigned long delta, int periodic)
 
        counter += delta;
        ctrl = GT_CONTROL_TIMER_ENABLE;
-       writel(ctrl, gt_base + GT_CONTROL);
-       writel(lower_32_bits(counter), gt_base + GT_COMP0);
-       writel(upper_32_bits(counter), gt_base + GT_COMP1);
+       writel_relaxed(ctrl, gt_base + GT_CONTROL);
+       writel_relaxed(lower_32_bits(counter), gt_base + GT_COMP0);
+       writel_relaxed(upper_32_bits(counter), gt_base + GT_COMP1);
 
        if (periodic) {
-               writel(delta, gt_base + GT_AUTO_INC);
+               writel_relaxed(delta, gt_base + GT_AUTO_INC);
                ctrl |= GT_CONTROL_AUTO_INC;
        }
 
        ctrl |= GT_CONTROL_COMP_ENABLE | GT_CONTROL_IRQ_ENABLE;
-       writel(ctrl, gt_base + GT_CONTROL);
+       writel_relaxed(ctrl, gt_base + GT_CONTROL);
 }
 
 static int gt_clockevent_shutdown(struct clock_event_device *evt)