asm-generic/atomic: Use __always_inline for pure wrappers

Prefer __always_inline for atomic wrappers. When building for size
(CC_OPTIMIZE_FOR_SIZE), some compilers appear to be less inclined to
inline even relatively small static inline functions that are assumed to
be inlinable such as atomic ops. This can cause problems, for example in
UACCESS regions.

By using __always_inline, we let the real implementation and not the
wrapper determine the final inlining preference.

For x86 tinyconfig we observe:
- vmlinux baseline: 1316204
- vmlinux with patch: 1315988 (-216 bytes)

This came up when addressing UACCESS warnings with CC_OPTIMIZE_FOR_SIZE
in the KCSAN runtime:
http://lkml.kernel.org/r/[email protected]

Reported-by: Randy Dunlap <[email protected]>
Signed-off-by: Marco Elver <[email protected]>
Acked-by: Mark Rutland <[email protected]>
Signed-off-by: Paul E. McKenney <[email protected]>

scripts/atomic/gen-atomic-instrumented.sh

@@ -84,7 +84,7 @@ gen_proto_order_variant()
 	[ ! -z "${guard}" ] && printf "#if ${guard}\n"
 
 cat <<EOF
-static inline ${ret}
+static __always_inline ${ret}
 ${atomicname}(${params})
 {
 ${checks}
@@ -147,16 +147,17 @@ cat << EOF
 #define _ASM_GENERIC_ATOMIC_INSTRUMENTED_H
 
 #include <linux/build_bug.h>
+#include <linux/compiler.h>
 #include <linux/kasan-checks.h>
 #include <linux/kcsan-checks.h>
 
-static inline void __atomic_check_read(const volatile void *v, size_t size)
+static __always_inline void __atomic_check_read(const volatile void *v, size_t size)
 {
 	kasan_check_read(v, size);
 	kcsan_check_atomic_read(v, size);
 }
 
-static inline void __atomic_check_write(const volatile void *v, size_t size)
+static __always_inline void __atomic_check_write(const volatile void *v, size_t size)
 {
 	kasan_check_write(v, size);
 	kcsan_check_atomic_write(v, size);

scripts/atomic/gen-atomic-long.sh

@@ -46,7 +46,7 @@ gen_proto_order_variant()
 	local retstmt="$(gen_ret_stmt "${meta}")"
 
 cat <<EOF
-static inline ${ret}
+static __always_inline ${ret}
 atomic_long_${name}(${params})
 {
 	${retstmt}${atomic}_${name}(${argscast});
@@ -64,6 +64,7 @@ cat << EOF
 #ifndef _ASM_GENERIC_ATOMIC_LONG_H
 #define _ASM_GENERIC_ATOMIC_LONG_H
 
+#include <linux/compiler.h>
 #include <asm/types.h>
 
 #ifdef CONFIG_64BIT