Dave Korn wrote:
> The attached patch implements ilockexch and ilockcmpexch, using the inline
> asm definition from __arch_compare_and_exchange_val_32_acq in
> glibc-2.10.1/sysdeps/i386/i486/bits/atomic.h, trivially expanded inline rather
> than in its original preprocessor macro form.
The attached patch does likewise, but adds a "memory" clobber. It generates
correct code:
L186:
.loc 3 127 0
movl __ZN13pthread_mutex7mutexesE+8, %eax # mutexes.head, D.28599
movl %eax, 36(%ebx) # D.28599, <variable>.next
.loc 2 60 0
/APP
# 60 "/gnu/winsup/src/winsup/cygwin/winbase.h" 1
lock cmpxchgl %ebx, __ZN13pthread_mutex7mutexesE+8 # this,
# 0 "" 2
/NO_APP
movl %eax, -12(%ebp) # tmp68, ret
.loc 2 61 0
movl -12(%ebp), %eax # ret, D.28596
.loc 3 126 0
cmpl %eax, 36(%ebx) # D.28596, <variable>.next
jne L186 #,
although as you see it has some needless register motion as it stores %eax to
the stack slot for ret and reloads it. Still, this is now almost as good as
the code generated by my original patch.
winsup/cygwin/ChangeLog
* winbase.h (ilockexch): Fix asm constraints.
(ilockcmpexch): Likewise.
Ok-ish?
cheers,
DaveK
Index: winsup/cygwin/winbase.h
===================================================================
RCS file: /cvs/src/src/winsup/cygwin/winbase.h,v
retrieving revision 1.14
diff -p -u -r1.14 winbase.h
--- winsup/cygwin/winbase.h 12 Jul 2008 18:09:17 -0000 1.14
+++ winsup/cygwin/winbase.h 3 Jun 2009 23:28:02 -0000
@@ -38,22 +38,28 @@ ilockdecr (volatile long *m)
extern __inline__ long
ilockexch (volatile long *t, long v)
{
- register int __res;
- __asm__ __volatile__ ("\n\
-1: lock cmpxchgl %3,(%1)\n\
- jne 1b\n\
- ": "=a" (__res), "=q" (t): "1" (t), "q" (v), "0" (*t): "cc");
- return __res;
+ return ({
+ __typeof (*t) ret;
+ __asm __volatile ("1: lock cmpxchgl %2, %1\n"
+ " jne 1b\n"
+ : "=a" (ret), "=m" (*t)
+ : "r" (v), "m" (*t), "0" (*t)
+ : "memory");
+ ret;
+ });
}
extern __inline__ long
ilockcmpexch (volatile long *t, long v, long c)
{
- register int __res;
- __asm__ __volatile__ ("\n\
- lock cmpxchgl %3,(%1)\n\
- ": "=a" (__res), "=q" (t) : "1" (t), "q" (v), "0" (c): "cc");
- return __res;
+ return ({
+ __typeof (*t) ret;
+ __asm __volatile ("lock cmpxchgl %2, %1"
+ : "=a" (ret), "=m" (*t)
+ : "r" (v), "m" (*t), "0" (c)
+ : "memory");
+ ret;
+ });
}
#undef InterlockedIncrement
