[PATCH v2] clockevents/drivers/arm_global_timer: Use writel_relaxed in gt_compare_set
From: Jisheng Zhang <hidden>
Date: 2015-11-26 12:24:54
Also in:
lkml
Subsystem:
arm/sti architecture, clocksource, clockevent drivers, the rest · Maintainers:
Patrice Chotard, Daniel Lezcano, Thomas Gleixner, Linus Torvalds
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 <redacted> --- since v1: - only use relaxed io in gt_compare_set(), this function is the remaining hot code path. - Add performance numbers in commit msg. drivers/clocksource/arm_global_timer.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/clocksource/arm_global_timer.c b/drivers/clocksource/arm_global_timer.c
index a2cb6fa..f99be6b 100644
--- 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)
--
2.6.2