diff mbox series

[v4,1/3] spinlock: use wfe to reduce contention on aarch64

Message ID 20210707054341.1607419-2-ruifeng.wang@arm.com (mailing list archive)
State Superseded, archived
Headers show
Series Use WFE for spinlock and ring | expand


Context Check Description
ci/checkpatch success coding style OK

Commit Message

Ruifeng Wang July 7, 2021, 5:43 a.m. UTC
From: Gavin Hu <gavin.hu@arm.com>

In acquiring a spinlock, cores repeatedly poll the lock variable.
This is replaced by rte_wait_until_equal API.

Running the micro benchmarking and the testpmd and l3fwd traffic tests
on ThunderX2, Ampere eMAG80 and Arm N1SDP, everything went well and no
notable performance gain nor degradation was measured.

Signed-off-by: Gavin Hu <gavin.hu@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Phil Yang <phil.yang@arm.com>
Reviewed-by: Steve Capper <steve.capper@arm.com>
Reviewed-by: Ola Liljedahl <ola.liljedahl@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Tested-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
 lib/eal/include/generic/rte_spinlock.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
diff mbox series


diff --git a/lib/eal/include/generic/rte_spinlock.h b/lib/eal/include/generic/rte_spinlock.h
index 87ae7a4f18..40fe49d5ad 100644
--- a/lib/eal/include/generic/rte_spinlock.h
+++ b/lib/eal/include/generic/rte_spinlock.h
@@ -65,8 +65,8 @@  rte_spinlock_lock(rte_spinlock_t *sl)
 	while (!__atomic_compare_exchange_n(&sl->locked, &exp, 1, 0,
-		while (__atomic_load_n(&sl->locked, __ATOMIC_RELAXED))
-			rte_pause();
+		rte_wait_until_equal_32((volatile uint32_t *)&sl->locked,
+			       0, __ATOMIC_RELAXED);
 		exp = 0;