summary refs log tree commit diff stats
path: root/include/qemu/atomic.h
diff options
context:
space:
mode:
authorEmilio G. Cota <cota@braap.org>2016-05-24 16:06:14 -0400
committerPaolo Bonzini <pbonzini@redhat.com>2016-05-29 09:11:11 +0200
commit15487aa132109891482f79d78a30d6cfd465a391 (patch)
treec4f272a7dce759a217247f5e9a25b166a5977dd1 /include/qemu/atomic.h
parentc983895258a771f8a5e4a53950bfb7fd2216651c (diff)
downloadfocaccia-qemu-15487aa132109891482f79d78a30d6cfd465a391.tar.gz
focaccia-qemu-15487aa132109891482f79d78a30d6cfd465a391.zip
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

Signed-off-by: Emilio G. Cota <cota@braap.org>
Message-Id: <1464120374-8950-4-git-send-email-cota@braap.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Diffstat (limited to 'include/qemu/atomic.h')
-rw-r--r--include/qemu/atomic.h14
1 files changed, 12 insertions, 2 deletions
diff --git a/include/qemu/atomic.h b/include/qemu/atomic.h
index 96db6e9db5..7a590969b5 100644
--- a/include/qemu/atomic.h
+++ b/include/qemu/atomic.h
@@ -67,13 +67,23 @@
     __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)                          \
     ({                                                \
     QEMU_BUILD_BUG_ON(sizeof(*ptr) > sizeof(void *)); \
     typeof(*ptr) _val;                                \
-    __atomic_load(ptr, &_val, __ATOMIC_CONSUME);      \
+    atomic_rcu_read__nocheck(ptr, &_val);             \
     _val;                                             \
     })