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 /arch/x86 | |
parent | 4a922a969cb0190ce4580d4b064e2ac35f3ac9bf (diff) | |
download | blackbird-op-linux-c8399943bdb70fef78798b97f975506ecc99e039.tar.gz blackbird-op-linux-c8399943bdb70fef78798b97f975506ecc99e039.zip |
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 'arch/x86')
-rw-r--r-- | arch/x86/include/asm/bitops.h | 14 |
1 files changed, 10 insertions, 4 deletions
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index e02a359d2aa5..02b47a603fc8 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -3,6 +3,9 @@ /* * Copyright 1992, Linus Torvalds. + * + * Note: inlines with more than a single statement should be marked + * __always_inline to avoid problems with older gcc's inlining heuristics. */ #ifndef _LINUX_BITOPS_H @@ -53,7 +56,8 @@ * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ -static inline void set_bit(unsigned int nr, volatile unsigned long *addr) +static __always_inline void +set_bit(unsigned int nr, volatile unsigned long *addr) { if (IS_IMMEDIATE(nr)) { asm volatile(LOCK_PREFIX "orb %1,%0" @@ -90,7 +94,8 @@ static inline void __set_bit(int nr, volatile unsigned long *addr) * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit() * in order to ensure changes are visible on other processors. */ -static inline void clear_bit(int nr, volatile unsigned long *addr) +static __always_inline void +clear_bit(int nr, volatile unsigned long *addr) { if (IS_IMMEDIATE(nr)) { asm volatile(LOCK_PREFIX "andb %1,%0" @@ -204,7 +209,8 @@ static inline int test_and_set_bit(int nr, volatile unsigned long *addr) * * This is the same as test_and_set_bit on x86. */ -static inline int test_and_set_bit_lock(int nr, volatile unsigned long *addr) +static __always_inline int +test_and_set_bit_lock(int nr, volatile unsigned long *addr) { return test_and_set_bit(nr, addr); } @@ -300,7 +306,7 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr) return oldbit; } -static inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr) +static __always_inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr) { return ((1UL << (nr % BITS_PER_LONG)) & (((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0; |