Optimize atomic64_read() as a special open-coded
cmpxchg8b variant. This generates nicer code:
arch/x86/lib/atomic64_32.o:
text data bss dec hex filename
435 0 0 435 1b3 atomic64_32.o.before
431 0 0 431 1af atomic64_32.o.after
md5:
bd8ab95e69c93518578bfaf0ea3be4d9 atomic64_32.o.before.asm
2bdfd4bd1f6b7b61b7fc127aef90ce3b atomic64_32.o.after.asm
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Arnd Bergmann <arnd@arndb.de>
LKML-Reference: <alpine.LFD.2.01.
0907021653030.3210@localhost.localdomain>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
*/
u64 atomic64_read(atomic64_t *ptr)
{
- u64 old = 1LL << 32;
+ u64 res;
- return cmpxchg8b(&ptr->counter, old, old);
+ asm volatile(
+ "mov %%ebx, %%eax\n\t"
+ "mov %%ecx, %%edx\n\t"
+ LOCK_PREFIX "cmpxchg8b %1\n"
+ : "+A" (res)
+ : "m" (*ptr)
+ );
+
+ return res;
}
/**