With both gcc 4.7.2 and 4.9.2, 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,
set_buffer_foo(), clear_buffer_foo() and similar functions get deinlined
about 60 times. Examples of disassembly:
<set_buffer_mapped> (14 copies, 43 calls):
55 push %rbp
48 89 e5 mov %rsp,%rbp
f0 80 0f 20 lock orb $0x20,(%rdi)
5d pop %rbp
c3 retq
<buffer_mapped> (3 copies, 34 calls):
48 8b 07 mov (%rdi),%rax
55 push %rbp
48 89 e5 mov %rsp,%rbp
48 c1 e8 05 shr $0x5,%rax
83 e0 01 and $0x1,%eax
5d pop %rbp
c3 retq
<set_buffer_new> (5 copies, 13 calls):
55 push %rbp
48 89 e5 mov %rsp,%rbp
f0 80 0f 40 lock orb $0x40,(%rdi)
5d pop %rbp
c3 retq
This patch fixes this via s/inline/__always_inline/.
This decreases vmlinux by about 3 kbytes.
text data bss dec hex filename
88200439 19905208 36421632 144527279 89d4faf vmlinux2
88197239 19905240 36421632 144524111 89d434f vmlinux
Signed-off-by: Denys Vlasenko <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Thomas Graf <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: David Rientjes <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: [email protected]
---
Resending. Verified that the results are still valid on the current Linus tree:
savings are ~7k of code.
include/linux/buffer_head.h | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index e6797de..50ccd04 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -82,15 +82,15 @@ struct buffer_head {
* and buffer_foo() functions.
*/
#define BUFFER_FNS(bit, name) \
-static inline void set_buffer_##name(struct buffer_head *bh) \
+static __always_inline void set_buffer_##name(struct buffer_head *bh) \
{ \
set_bit(BH_##bit, &(bh)->b_state); \
} \
-static inline void clear_buffer_##name(struct buffer_head *bh) \
+static __always_inline void clear_buffer_##name(struct buffer_head *bh)
\
{ \
clear_bit(BH_##bit, &(bh)->b_state); \
} \
-static inline int buffer_##name(const struct buffer_head *bh) \
+static __always_inline int buffer_##name(const struct buffer_head *bh) \
{ \
return test_bit(BH_##bit, &(bh)->b_state); \
}
@@ -99,11 +99,11 @@ static inline int buffer_##name(const struct buffer_head
*bh) \
* test_set_buffer_foo() and test_clear_buffer_foo()
*/
#define TAS_BUFFER_FNS(bit, name) \
-static inline int test_set_buffer_##name(struct buffer_head *bh) \
+static __always_inline int test_set_buffer_##name(struct buffer_head *bh) \
{ \
return test_and_set_bit(BH_##bit, &(bh)->b_state); \
} \
-static inline int test_clear_buffer_##name(struct buffer_head *bh) \
+static __always_inline int test_clear_buffer_##name(struct buffer_head *bh) \
{ \
return test_and_clear_bit(BH_##bit, &(bh)->b_state); \
} \
--
1.8.1.4
