include/uapi/linux/byteorder, swab: force inlining of some byteswap operations

Sometimes gcc mysteriously doesn't inline
very small functions we expect to be inlined. See

    https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66122

With this .config:
http://busybox.net/~vda/kernel_config_OPTIMIZE_INLINING_and_Os,
the following functions get deinlined many times.
Examples of disassembly:

<get_unaligned_be16> (12 copies, 51 calls):
       66 8b 07                mov    (%rdi),%ax
       55                      push   %rbp
       48 89 e5                mov    %rsp,%rbp
       86 e0                   xchg   %ah,%al
       5d                      pop    %rbp
       c3                      retq

<get_unaligned_be32> (12 copies, 135 calls):
       8b 07                   mov    (%rdi),%eax
       55                      push   %rbp
       48 89 e5                mov    %rsp,%rbp
       0f c8                   bswap  %eax
       5d                      pop    %rbp
       c3                      retq

<get_unaligned_be64> (2 copies, 20 calls):
       48 8b 07                mov    (%rdi),%rax
       55                      push   %rbp
       48 89 e5                mov    %rsp,%rbp
       48 0f c8                bswap  %rax
       5d                      pop    %rbp
       c3                      retq

<__swab16p> (16 copies, 146 calls):
       55                      push   %rbp
       89 f8                   mov    %edi,%eax
       86 e0                   xchg   %ah,%al
       48 89 e5                mov    %rsp,%rbp
       5d                      pop    %rbp
       c3                      retq

<__swab32p> (43 copies, ~560 calls):
       55                      push   %rbp
       89 f8                   mov    %edi,%eax
       0f c8                   bswap  %eax
       48 89 e5                mov    %rsp,%rbp
       5d                      pop    %rbp
       c3                      retq

<__swab64p> (21 copies, 119 calls):
       55                      push   %rbp
       48 89 f8                mov    %rdi,%rax
       48 0f c8                bswap  %rax
       48 89 e5                mov    %rsp,%rbp
       5d                      pop    %rbp
       c3                      retq

<__swab32s> (6 copies, 47 calls):
       8b 07                   mov    (%rdi),%eax
       55                      push   %rbp
       48 89 e5                mov    %rsp,%rbp
       0f c8                   bswap  %eax
       89 07                   mov    %eax,(%rdi)
       5d                      pop    %rbp
       c3                      retq

This patch fixes this via s/inline/__always_inline/.
Code size decrease after the patch is ~4.5k:

    text     data      bss       dec     hex filename
92202377 20826112 36417536 149446025 8e85d89 vmlinux
92197848 20826112 36417536 149441496 8e84bd8 vmlinux5_swap_after

Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: Thomas Graf <tgraf@suug.ch>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/include/uapi/linux/swab.h b/include/uapi/linux/swab.h
index 0e011eb..3f10e53 100644
--- a/include/uapi/linux/swab.h
+++ b/include/uapi/linux/swab.h
@@ -151,7 +151,7 @@
  * __swab16p - return a byteswapped 16-bit value from a pointer
  * @p: pointer to a naturally-aligned 16-bit value
  */
-static inline __u16 __swab16p(const __u16 *p)
+static __always_inline __u16 __swab16p(const __u16 *p)
 {
 #ifdef __arch_swab16p
 	return __arch_swab16p(p);
@@ -164,7 +164,7 @@
  * __swab32p - return a byteswapped 32-bit value from a pointer
  * @p: pointer to a naturally-aligned 32-bit value
  */
-static inline __u32 __swab32p(const __u32 *p)
+static __always_inline __u32 __swab32p(const __u32 *p)
 {
 #ifdef __arch_swab32p
 	return __arch_swab32p(p);
@@ -177,7 +177,7 @@
  * __swab64p - return a byteswapped 64-bit value from a pointer
  * @p: pointer to a naturally-aligned 64-bit value
  */
-static inline __u64 __swab64p(const __u64 *p)
+static __always_inline __u64 __swab64p(const __u64 *p)
 {
 #ifdef __arch_swab64p
 	return __arch_swab64p(p);
@@ -232,7 +232,7 @@
  * __swab32s - byteswap a 32-bit value in-place
  * @p: pointer to a naturally-aligned 32-bit value
  */
-static inline void __swab32s(__u32 *p)
+static __always_inline void __swab32s(__u32 *p)
 {
 #ifdef __arch_swab32s
 	__arch_swab32s(p);
@@ -245,7 +245,7 @@
  * __swab64s - byteswap a 64-bit value in-place
  * @p: pointer to a naturally-aligned 64-bit value
  */
-static inline void __swab64s(__u64 *p)
+static __always_inline void __swab64s(__u64 *p)
 {
 #ifdef __arch_swab64s
 	__arch_swab64s(p);