From ab569f5cdeeac023b8e2c6783e321b64db380a45 Mon Sep 17 00:00:00 2001 From: "Emilio G. Cota" Date: Sat, 24 Feb 2018 03:28:09 -0500 Subject: [PATCH] atomics: do not emit consume barrier for atomic_rcu_read Currently we emit a consume-load in atomic_rcu_read. Because of limitations in current compilers, this is overkill for non-Alpha hosts and it is only useful to make Thread Sanitizer work. This patch leaves the consume-load in atomic_rcu_read when compiling with Thread Sanitizer enabled, and resorts to a relaxed load + smp_read_barrier_depends otherwise. On an RMO host architecture, such as aarch64, the performance improvement of this change is easily measurable. For instance, qht-bench performs an atomic_rcu_read on every lookup. Performance before and after applying this patch: $ tests/qht-bench -d 5 -n 1 Before: 9.78 MT/s After: 10.96 MT/s Backports commit 15487aa132109891482f79d78a30d6cfd465a391 from qemu --- qemu/include/qemu/atomic.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/qemu/include/qemu/atomic.h b/qemu/include/qemu/atomic.h index 17f38ba9..4bcce927 100644 --- a/qemu/include/qemu/atomic.h +++ b/qemu/include/qemu/atomic.h @@ -70,12 +70,22 @@ void _ReadWriteBarrier(void); __atomic_store(ptr, &_val, __ATOMIC_RELAXED); \ } while(0) -/* Atomic RCU operations imply weak memory barriers */ +/* See above: most compilers currently treat consume and acquire the + * same, but this slows down atomic_rcu_read unnecessarily. + */ +#ifdef __SANITIZE_THREAD__ +#define atomic_rcu_read__nocheck(ptr, valptr) \ + __atomic_load(ptr, valptr, __ATOMIC_CONSUME); +#else +#define atomic_rcu_read__nocheck(ptr, valptr) \ + __atomic_load(ptr, valptr, __ATOMIC_RELAXED); \ + smp_read_barrier_depends(); +#endif #define atomic_rcu_read(ptr) \ ({ \ typeof(*ptr) _val; \ - __atomic_load(ptr, &_val, __ATOMIC_CONSUME); \ + atomic_rcu_read__nocheck(ptr, &_val); \ _val; \ })