[PATCH 5/6] powerpc/qspinlock: Propagate sleepy if previous waiter is preempted

Nicholas Piggin npiggin at gmail.com
Mon Oct 16 23:43:04 AEDT 2023


The sleepy (aka lock-owner-is-preempted) condition is propagated down
the queue by each waiter. If a waiter becomes preempted, it can no
longer propagate sleepy. To allow subsequent waiters to yield to the
lock owner, also check the lock owner in this case.

Signed-off-by: Nicholas Piggin <npiggin at gmail.com>
---
 arch/powerpc/lib/qspinlock.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/lib/qspinlock.c b/arch/powerpc/lib/qspinlock.c
index 6bb627e90a32..c68c2bd7b853 100644
--- a/arch/powerpc/lib/qspinlock.c
+++ b/arch/powerpc/lib/qspinlock.c
@@ -384,7 +384,11 @@ static __always_inline bool yield_to_prev(struct qspinlock *lock, struct qnode *
 	if (!pv_yield_propagate_owner)
 		goto yield_prev;
 
-	if (node->sleepy) {
+	/*
+	 * If the previous waiter was preempted it might not be able to
+	 * propagate sleepy to us, so check the lock in that case too.
+	 */
+	if (node->sleepy || vcpu_is_preempted(prev_cpu)) {
 		u32 val = READ_ONCE(lock->val);
 
 		if (val & _Q_LOCKED_VAL) {
-- 
2.42.0



More information about the Linuxppc-dev mailing list