From 39df8c903d65303542a56d0be15f8c6039a75cdd Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Sun, 17 Mar 2024 16:55:09 +0100 Subject: [PATCH] MINOR: ring: it's not x86 but all non-ARMv8.1 which needs the read before OR Archs relying on CAS benefit from a read prior to FETCH_OR, so it's not just x86 that benefits from this. Let's just change the condition to only exclude __ARM_FEATURE_ATOMICS which is the only one faster without. --- src/ring.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/src/ring.c b/src/ring.c index 1dc4c06ee..7998f0905 100644 --- a/src/ring.c +++ b/src/ring.c @@ -280,10 +280,12 @@ ssize_t ring_write(struct ring *ring, size_t maxlen, const struct ist pfx[], siz goto wait_for_flush; __ha_cpu_relax_for_read(); -#if defined(__x86_64__) - /* x86 prefers a read first */ - if ((tail_ofs = HA_ATOMIC_LOAD(tail_ptr)) & RING_TAIL_LOCK) +#if !defined(__ARM_FEATURE_ATOMICS) + /* ARMv8.1-a has a true atomic OR and doesn't need the preliminary read */ + if ((tail_ofs = HA_ATOMIC_LOAD(tail_ptr)) & RING_TAIL_LOCK) { + __ha_cpu_relax_for_read(); continue; + } #endif /* OK the queue is locked, let's attempt to get the tail lock */ tail_ofs = HA_ATOMIC_FETCH_OR(tail_ptr, RING_TAIL_LOCK);