Messages in this thread Patch in this message | | | Date | Sat, 26 Apr 2008 18:11:19 +0200 | From | Ingo Molnar <> | Subject | [git pull] x86, generic: optimized inlining |
| |
Linus, please pull the "optimized inlining" feature from:
git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-x86-optimized-inlining.git for-linus
this is from x86.git but touches include/linux/compiler-gcc.h and can be enabled by other architectures as well. The motivation of this feature is a 2.3% kernel text size reduction on generic x86 distro kernel configs. (Perhaps gcc will also get smarter about inlining decisions if the kernel gives it leeway about it.)
This change makes __always_inline more meaningful (and more critical). Testing so far showed no ill effects.
Thanks,
Ingo
------------------> Ingo Molnar (2): x86: add optimized inlining generic: make optimized inlining arch-opt-in
arch/x86/Kconfig | 3 +++ arch/x86/Kconfig.debug | 13 +++++++++++++ arch/x86/configs/i386_defconfig | 1 + arch/x86/configs/x86_64_defconfig | 1 + include/linux/compiler-gcc.h | 13 ++++++++++--- 5 files changed, 28 insertions(+), 3 deletions(-)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 4d350b5..3b6ff3b 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -142,6 +142,9 @@ config AUDIT_ARCH config ARCH_SUPPORTS_AOUT def_bool y +config ARCH_SUPPORTS_OPTIMIZED_INLINING + def_bool y + # Use the generic interrupt handling code in kernel/irq/: config GENERIC_HARDIRQS bool diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 239fd9f..5b1979a 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -257,3 +257,16 @@ config CPA_DEBUG Do change_page_attr() self-tests every 30 seconds. endmenu + +config OPTIMIZE_INLINING + bool "Allow gcc to uninline functions marked 'inline'" + default y + help + This option determines if the kernel forces gcc to inline the functions + developers have marked 'inline'. Doing so takes away freedom from gcc to + do what it thinks is best, which is desirable for the gcc 3.x series of + compilers. The gcc 4.x series have a rewritten inlining algorithm and + disabling this option will generate a smaller kernel there. Hopefully + this algorithm is so good that allowing gcc4 to make the decision can + become the default in the future, until then this option is there to + test gcc for this. diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 3df340b..ad7ddaa 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -1421,6 +1421,7 @@ CONFIG_DEBUG_BUGVERBOSE=y # CONFIG_DEBUG_VM is not set # CONFIG_DEBUG_LIST is not set # CONFIG_FRAME_POINTER is not set +CONFIG_OPTIMIZE_INLINING=y # CONFIG_RCU_TORTURE_TEST is not set # CONFIG_LKDTM is not set # CONFIG_FAULT_INJECTION is not set diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index eef98cb..2d6f5b2 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -1346,6 +1346,7 @@ CONFIG_DEBUG_BUGVERBOSE=y # CONFIG_DEBUG_VM is not set # CONFIG_DEBUG_LIST is not set # CONFIG_FRAME_POINTER is not set +CONFIG_OPTIMIZE_INLINING=y # CONFIG_RCU_TORTURE_TEST is not set # CONFIG_LKDTM is not set # CONFIG_FAULT_INJECTION is not set diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index fe23792..b2fd754 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -28,9 +28,16 @@ #define __must_be_array(a) \ BUILD_BUG_ON_ZERO(__builtin_types_compatible_p(typeof(a), typeof(&a[0]))) -#define inline inline __attribute__((always_inline)) -#define __inline__ __inline__ __attribute__((always_inline)) -#define __inline __inline __attribute__((always_inline)) +/* + * Force always-inline if the user requests it so via the .config: + */ +#if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ + !defined(CONFIG_OPTIMIZE_INLINING) && (__GNUC__ >= 4) +# define inline inline __attribute__((always_inline)) +# define __inline__ __inline__ __attribute__((always_inline)) +# define __inline __inline __attribute__((always_inline)) +#endif + #define __deprecated __attribute__((deprecated)) #define __packed __attribute__((packed)) #define __weak __attribute__((weak))
| |