s390/cpum_sf: Convert to cmpxchg128()

Now that there is a cross arch u128 and cmpxchg128(), use those
instead of the custom CDSG helper.

Signed-off-by: Peter Zijlstra (Intel) <[e-mail]>
Reviewed-by: Arnd Bergmann <[e-mail]>
Reviewed-by: Mark Rutland <[e-mail]>
Acked-by: Heiko Carstens <[e-mail]>
Tested-by: Mark Rutland <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]

arch/s390/include/asm/cpu_mf.h

···
 		unsigned int dsdes:16;	/* 48-63: size of diagnostic SDE */
 		unsigned long long overflow; /* 64 - Overflow Count   */
 	};
-	__uint128_t val;
+	u128 val;
 };
 
 struct hws_trailer_entry {

arch/s390/kernel/perf_cpum_sf.c

···
 	}
 }
 
-static inline __uint128_t __cdsg(__uint128_t *ptr, __uint128_t old, __uint128_t new)
-{
-	asm volatile(
-		"	cdsg	%[old],%[new],%[ptr]\n"
-		: [old] "+d" (old), [ptr] "+QS" (*ptr)
-		: [new] "d" (new)
-		: "memory", "cc");
-	return old;
-}
-
 /* hw_perf_event_update() - Process sampling buffer
  * @event:	The perf event
  * @flush_all:	Flag to also flush partially filled sample-data-blocks
···
 			new.f = 0;
 			new.a = 1;
 			new.overflow = 0;
-			prev.val = __cdsg(&te->header.val, old.val, new.val);
+			prev.val = cmpxchg128(&te->header.val, old.val, new.val);
 		} while (prev.val != old.val);
 
 		/* Advance to next sample-data-block */
···
 		}
 		new.a = 1;
 		new.overflow = 0;
-		prev.val = __cdsg(&te->header.val, old.val, new.val);
+		prev.val = cmpxchg128(&te->header.val, old.val, new.val);
 	} while (prev.val != old.val);
 	return true;
 }
···
 				new.a = 1;
 			else
 				new.a = 0;
-			prev.val = __cdsg(&te->header.val, old.val, new.val);
+			prev.val = cmpxchg128(&te->header.val, old.val, new.val);
 		} while (prev.val != old.val);
 		*overflow += orig_overflow;
 	}