summaryrefslogtreecommitdiff
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
parentfe7582f4f92152ab60e9523bf146fe28ceae51f6 (diff)
downloadmusl-3c43c0761e1725fd5f89a9c028cbf43250abb913.tar.gz
musl-3c43c0761e1725fd5f89a9c028cbf43250abb913.tar.bz2
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.
-rw-r--r--arch/i386/atomic.h2
-rw-r--r--arch/x32/atomic.h2
-rw-r--r--arch/x86_64/atomic.h2
3 files changed, 3 insertions, 3 deletions
diff --git a/arch/i386/atomic.h b/arch/i386/atomic.h
index 95fecbdc..25441df2 100644
--- a/arch/i386/atomic.h
+++ b/arch/i386/atomic.h
@@ -88,7 +88,7 @@ static inline void a_dec(volatile int *x)
static inline void a_store(volatile int *p, int x)
{
- __asm__( "movl %1, %0" : "=m"(*p) : "r"(x) : "memory" );
+ __asm__( "movl %1, %0 ; lock ; orl $0,(%%esp)" : "=m"(*p) : "r"(x) : "memory" );
}
static inline void a_spin()
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()
diff --git a/arch/x86_64/atomic.h b/arch/x86_64/atomic.h
index b2014cc0..2ab1f7a2 100644
--- a/arch/x86_64/atomic.h
+++ b/arch/x86_64/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()