s390/rwonce: add READ_ONCE_ALIGNED_128() macro

Add an s390 specific READ_ONCE_ALIGNED_128() helper, which can be used for
fast block concurrent (atomic) 128-bit accesses.

The used lpq instruction requires 128-bit alignment. This is also the
reason why the compiler doesn't emit this instruction if __READ_ONCE() is
used for 128-bit accesses.

Link: https://lore.kernel.org/r/20230224100237.3247871-2-hca@linux.ibm.com
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>

arch/s390/include/asm/rwonce.h

@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_S390_RWONCE_H
+#define __ASM_S390_RWONCE_H
+
+#include <linux/compiler_types.h>
+
+/*
+ * Use READ_ONCE_ALIGNED_128() for 128-bit block concurrent (atomic) read
+ * accesses. Note that x must be 128-bit aligned, otherwise a specification
+ * exception is generated.
+ */
+#define READ_ONCE_ALIGNED_128(x)			\
+({							\
+	union {						\
+		typeof(x) __x;				\
+		__uint128_t val;			\
+	} __u;						\
+							\
+	BUILD_BUG_ON(sizeof(x) != 16);			\
+	asm volatile(					\
+		"	lpq	%[val],%[_x]\n"		\
+		: [val] "=d" (__u.val)			\
+		: [_x] "QS" (x)				\
+		: "memory");				\
+	__u.__x;					\
+})
+
+#include <asm-generic/rwonce.h>
+
+#endif	/* __ASM_S390_RWONCE_H */