Marginally optimise __delay() by using a WFIT/WFET sequence.
It probably is a win if no interrupt fires during the delay.
Signed-off-by: Marc Zyngier <maz@xxxxxxxxxx>
---
arch/arm64/lib/delay.c | 12 +++++++++++-
1 file changed, 11 insertions(+), 1 deletion(-)
diff --git a/arch/arm64/lib/delay.c b/arch/arm64/lib/delay.c
index 1688af0a4c97..5b7890139bc2 100644
--- a/arch/arm64/lib/delay.c
+++ b/arch/arm64/lib/delay.c
@@ -27,7 +27,17 @@ void __delay(unsigned long cycles)
{
cycles_t start = get_cycles();
- if (arch_timer_evtstrm_available()) {
+ if (cpus_have_const_cap(ARM64_HAS_WFXT)) {
+ u64 end = start + cycles;
+
+ /*
+ * Start with WFIT. If an interrupt makes us resume
+ * early, use a WFET loop to complete the delay.
+ */
+ wfit(end);
+ while ((get_cycles() - start) < cycles)
+ wfet(end);
+ } else if (arch_timer_evtstrm_available()) {
const cycles_t timer_evt_period =
USECS_TO_CYCLES(ARCH_TIMER_EVT_STREAM_PERIOD_US);
--
2.34.1
