bitops: use try_cmpxchg in set_mask_bits and bit_clear_unless

Use try_cmpxchg instead of cmpxchg (*ptr, old, new) == old in
set_mask_bits and bit_clear_unless.  x86 CMPXCHG instruction returns
success in ZF flag, so this change saves a compare after cmpxchg (and
related move instruction in front of cmpxchg).

Also, try_cmpxchg implicitly assigns old *ptr value to "old" when cmpxchg
fails, enabling further code simplifications.

Link: https://lkml.kernel.org/r/20220822143851.3290-1-ubizjak@gmail.com
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

include/linux/bitops.h

@@ -328,10 +328,10 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr,
 	const typeof(*(ptr)) mask__ = (mask), bits__ = (bits);	\
 	typeof(*(ptr)) old__, new__;				\
 								\
+	old__ = READ_ONCE(*(ptr));				\
 	do {							\
-		old__ = READ_ONCE(*(ptr));			\
 		new__ = (old__ & ~mask__) | bits__;		\
-	} while (cmpxchg(ptr, old__, new__) != old__);		\
+	} while (!try_cmpxchg(ptr, &old__, new__));		\
 								\
 	old__;							\
 })
@@ -343,11 +343,12 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr,
 	const typeof(*(ptr)) clear__ = (clear), test__ = (test);\
 	typeof(*(ptr)) old__, new__;				\
 								\
+	old__ = READ_ONCE(*(ptr));				\
 	do {							\
-		old__ = READ_ONCE(*(ptr));			\
+		if (old__ & test__)				\
+			break;					\
 		new__ = old__ & ~clear__;			\
-	} while (!(old__ & test__) &&				\
-		 cmpxchg(ptr, old__, new__) != old__);		\
+	} while (!try_cmpxchg(ptr, &old__, new__));		\
 								\
 	!(old__ & test__);					\
 })