about summary refs log tree commit diff
path: root/arch/x32/atomic.h
diff options
context:
space:
mode:
authorRich Felker <dalias@aerifal.cx>2015-07-28 18:40:18 +0000
committerRich Felker <dalias@aerifal.cx>2015-07-28 18:40:18 +0000
commit3c43c0761e1725fd5f89a9c028cbf43250abb913 (patch)
treef8f504aaafc22502a8aec0a4ba58c60856096495 /arch/x32/atomic.h
parentfe7582f4f92152ab60e9523bf146fe28ceae51f6 (diff)
downloadmusl-3c43c0761e1725fd5f89a9c028cbf43250abb913.tar.gz
musl-3c43c0761e1725fd5f89a9c028cbf43250abb913.tar.xz
musl-3c43c0761e1725fd5f89a9c028cbf43250abb913.zip
fix missing synchronization in atomic store on i386 and x86_64
despite being strongly ordered, the x86 memory model does not preclude
reordering of loads across earlier stores. while a plain store
suffices as a release barrier, we actually need a full barrier, since
users of a_store subsequently load a waiter count to determine whether
to issue a futex wait, and using a stale count will result in soft
(fail-to-wake) deadlocks. these deadlocks were observed in malloc and
possible with stdio locks and other libc-internal locking.

on i386, an atomic operation on the caller's stack is used as the
barrier rather than performing the store itself using xchg; this
avoids the need to read the cache line on which the store is being
performed. mfence is used on x86_64 where it's always available, and
could be used on i386 with the appropriate cpu model checks if it's
shown to perform better.
Diffstat (limited to 'arch/x32/atomic.h')
-rw-r--r--arch/x32/atomic.h2
1 files changed, 1 insertions, 1 deletions
diff --git a/arch/x32/atomic.h b/arch/x32/atomic.h
index b2014cc0..2ab1f7a2 100644
--- a/arch/x32/atomic.h
+++ b/arch/x32/atomic.h
@@ -83,7 +83,7 @@ static inline void a_dec(volatile int *x)
 
 static inline void a_store(volatile int *p, int x)
 {
-	__asm__( "mov %1, %0" : "=m"(*p) : "r"(x) : "memory" );
+	__asm__( "mov %1, %0 ; mfence" : "=m"(*p) : "r"(x) : "memory" );
 }
 
 static inline void a_spin()