diff options
| author | Andi Kleen <andi@firstfloor.org> | 2009-01-12 23:01:15 +0100 |
|---|---|---|
| committer | Ingo Molnar <mingo@elte.hu> | 2009-01-13 18:56:30 +0100 |
| commit | c8399943bdb70fef78798b97f975506ecc99e039 (patch) | |
| tree | 3d7cdf853bdfc012b9ea8513ab775238b94d6f75 /include/asm-generic | |
| parent | 4a922a969cb0190ce4580d4b064e2ac35f3ac9bf (diff) | |
| download | linux-c8399943bdb70fef78798b97f975506ecc99e039.tar.bz2 | |
x86, generic: mark complex bitops.h inlines as __always_inline
Impact: reduce kernel image size
Hugh Dickins noticed that older gcc versions when the kernel
is built for code size didn't inline some of the bitops.
Mark all complex x86 bitops that have more than a single
asm statement or two as always inline to avoid this problem.
Probably should be done for other architectures too.
Ingo then found a better fix that only requires
a single line change, but it unfortunately only
works on gcc 4.3.
On older gccs the original patch still makes a ~0.3% defconfig
difference with CONFIG_OPTIMIZE_INLINING=y.
With gcc 4.1 and a defconfig like build:
6116998 1138540 883788 8139326 7c323e vmlinux-oi-with-patch
6137043 1138540 883788 8159371 7c808b vmlinux-optimize-inlining
~20k / 0.3% difference.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'include/asm-generic')
| -rw-r--r-- | include/asm-generic/bitops/__ffs.h | 2 | ||||
| -rw-r--r-- | include/asm-generic/bitops/__fls.h | 2 | ||||
| -rw-r--r-- | include/asm-generic/bitops/fls.h | 2 | ||||
| -rw-r--r-- | include/asm-generic/bitops/fls64.h | 4 |
4 files changed, 5 insertions, 5 deletions
diff --git a/include/asm-generic/bitops/__ffs.h b/include/asm-generic/bitops/__ffs.h index 9a3274aecf83..937d7c435575 100644 --- a/include/asm-generic/bitops/__ffs.h +++ b/include/asm-generic/bitops/__ffs.h @@ -9,7 +9,7 @@ * * Undefined if no bit exists, so code should check against 0 first. */ -static inline unsigned long __ffs(unsigned long word) +static __always_inline unsigned long __ffs(unsigned long word) { int num = 0; diff --git a/include/asm-generic/bitops/__fls.h b/include/asm-generic/bitops/__fls.h index be24465403d6..a60a7ccb6782 100644 --- a/include/asm-generic/bitops/__fls.h +++ b/include/asm-generic/bitops/__fls.h @@ -9,7 +9,7 @@ * * Undefined if no set bit exists, so code should check against 0 first. */ -static inline unsigned long __fls(unsigned long word) +static __always_inline unsigned long __fls(unsigned long word) { int num = BITS_PER_LONG - 1; diff --git a/include/asm-generic/bitops/fls.h b/include/asm-generic/bitops/fls.h index 850859bc5069..0576d1f42f43 100644 --- a/include/asm-generic/bitops/fls.h +++ b/include/asm-generic/bitops/fls.h @@ -9,7 +9,7 @@ * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32. */ -static inline int fls(int x) +static __always_inline int fls(int x) { int r = 32; diff --git a/include/asm-generic/bitops/fls64.h b/include/asm-generic/bitops/fls64.h index 86d403f8b256..b097cf8444e3 100644 --- a/include/asm-generic/bitops/fls64.h +++ b/include/asm-generic/bitops/fls64.h @@ -15,7 +15,7 @@ * at position 64. */ #if BITS_PER_LONG == 32 -static inline int fls64(__u64 x) +static __always_inline int fls64(__u64 x) { __u32 h = x >> 32; if (h) @@ -23,7 +23,7 @@ static inline int fls64(__u64 x) return fls(x); } #elif BITS_PER_LONG == 64 -static inline int fls64(__u64 x) +static __always_inline int fls64(__u64 x) { if (x == 0) return 0; |