include/linux/unaligned: force inlining of 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> (24 copies, 108 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> (25 copies, 181 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> (23 copies, 94 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

<put_unaligned_be16> (2 copies, 11 calls):
       89 f8                   mov    %edi,%eax
       55                      push   %rbp
       c1 ef 08                shr    $0x8,%edi
       c1 e0 08                shl    $0x8,%eax
       09 c7                   or     %eax,%edi
       48 89 e5                mov    %rsp,%rbp
       66 89 3e                mov    %di,(%rsi)

<put_unaligned_be32> (8 copies, 43 calls):
       55                      push   %rbp
       0f cf                   bswap  %edi
       89 3e                   mov    %edi,(%rsi)
       48 89 e5                mov    %rsp,%rbp
       5d                      pop    %rbp
       c3                      retq

<put_unaligned_be64> (26 copies, 157 calls):
       55                      push   %rbp
       48 0f cf                bswap  %rdi
       48 89 3e                mov    %rdi,(%rsi)
       48 89 e5                mov    %rsp,%rbp
       5d                      pop    %rbp
       c3                      retq

This patch fixes this via s/inline/__always_inline/.

It only affects arches with efficient unaligned access insns, such as x86.
(arched which lack such ops do not include linux/unaligned/access_ok.h)

Code size decrease after the patch is ~8.5k:

    text     data      bss       dec     hex filename
92197848 20826112 36417536 149441496 8e84bd8 vmlinux
92189231 20826144 36417536 149432911 8e82a4f vmlinux6_unaligned_be_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/linux/unaligned/access_ok.h b/include/linux/unaligned/access_ok.h
index 99c1b4d20b0ff22012d4b59b53b3e9f9be6b4236..33383ca23837e4c386407d7f8966056a34618962 100644 (file)
--- a/include/linux/unaligned/access_ok.h
+++ b/include/linux/unaligned/access_ok.h
@@ -4,62 +4,62 @@
 #include <linux/kernel.h>
 #include <asm/byteorder.h>
 
-static inline u16 get_unaligned_le16(const void *p)
+static __always_inline u16 get_unaligned_le16(const void *p)
 {
        return le16_to_cpup((__le16 *)p);
 }
 
-static inline u32 get_unaligned_le32(const void *p)
+static __always_inline u32 get_unaligned_le32(const void *p)
 {
        return le32_to_cpup((__le32 *)p);
 }
 
-static inline u64 get_unaligned_le64(const void *p)
+static __always_inline u64 get_unaligned_le64(const void *p)
 {
        return le64_to_cpup((__le64 *)p);
 }
 
-static inline u16 get_unaligned_be16(const void *p)
+static __always_inline u16 get_unaligned_be16(const void *p)
 {
        return be16_to_cpup((__be16 *)p);
 }
 
-static inline u32 get_unaligned_be32(const void *p)
+static __always_inline u32 get_unaligned_be32(const void *p)
 {
        return be32_to_cpup((__be32 *)p);
 }
 
-static inline u64 get_unaligned_be64(const void *p)
+static __always_inline u64 get_unaligned_be64(const void *p)
 {
        return be64_to_cpup((__be64 *)p);
 }
 
-static inline void put_unaligned_le16(u16 val, void *p)
+static __always_inline void put_unaligned_le16(u16 val, void *p)
 {
        *((__le16 *)p) = cpu_to_le16(val);
 }
 
-static inline void put_unaligned_le32(u32 val, void *p)
+static __always_inline void put_unaligned_le32(u32 val, void *p)
 {
        *((__le32 *)p) = cpu_to_le32(val);
 }
 
-static inline void put_unaligned_le64(u64 val, void *p)
+static __always_inline void put_unaligned_le64(u64 val, void *p)
 {
        *((__le64 *)p) = cpu_to_le64(val);
 }
 
-static inline void put_unaligned_be16(u16 val, void *p)
+static __always_inline void put_unaligned_be16(u16 val, void *p)
 {
        *((__be16 *)p) = cpu_to_be16(val);
 }
 
-static inline void put_unaligned_be32(u32 val, void *p)
+static __always_inline void put_unaligned_be32(u32 val, void *p)
 {
        *((__be32 *)p) = cpu_to_be32(val);
 }
 
-static inline void put_unaligned_be64(u64 val, void *p)
+static __always_inline void put_unaligned_be64(u64 val, void *p)
 {
        *((__be64 *)p) = cpu_to_be64(val);
 }