From 6fd92b63d0626a8fe7eb8e2e50d19ecaa18cb412 Mon Sep 17 00:00:00 2001 From: Alexander van Heukelum Date: Sun, 9 Mar 2008 21:01:04 +0100 Subject: x86: change x86 to use generic find_next_bit The versions with inline assembly are in fact slower on the machines I tested them on (in userspace) (Athlon XP 2800+, p4-like Xeon 2.8GHz, AMD Opteron 270). The i386-version needed a fix similar to 06024f21 to avoid crashing the benchmark. Benchmark using: gcc -fomit-frame-pointer -Os. For each bitmap size 1...512, for each possible bitmap with one bit set, for each possible offset: find the position of the first bit starting at offset. If you follow ;). Times include setup of the bitmap and checking of the results. Athlon Xeon Opteron 32/64bit x86-specific: 0m3.692s 0m2.820s 0m3.196s / 0m2.480s generic: 0m2.622s 0m1.662s 0m2.100s / 0m1.572s If the bitmap size is not a multiple of BITS_PER_LONG, and no set (cleared) bit is found, find_next_bit (find_next_zero_bit) returns a value outside of the range [0, size]. The generic version always returns exactly size. The generic version also uses unsigned long everywhere, while the x86 versions use a mishmash of int, unsigned (int), long and unsigned long. Using the generic version does give a slightly bigger kernel, though. defconfig: text data bss dec hex filename x86-specific: 4738555 481232 626688 5846475 5935cb vmlinux (32 bit) generic: 4738621 481232 626688 5846541 59360d vmlinux (32 bit) x86-specific: 5392395 846568 724424 6963387 6a40bb vmlinux (64 bit) generic: 5392458 846568 724424 6963450 6a40fa vmlinux (64 bit) Signed-off-by: Alexander van Heukelum Signed-off-by: Ingo Molnar --- include/asm-x86/bitops.h | 6 ++++++ include/asm-x86/bitops_32.h | 16 ---------------- include/asm-x86/bitops_64.h | 2 -- 3 files changed, 6 insertions(+), 18 deletions(-) (limited to 'include/asm-x86') diff --git a/include/asm-x86/bitops.h b/include/asm-x86/bitops.h index 1ae7b270a1e..31e408de90c 100644 --- a/include/asm-x86/bitops.h +++ b/include/asm-x86/bitops.h @@ -306,6 +306,12 @@ static int test_bit(int nr, const volatile unsigned long *addr); #undef BIT_ADDR #undef ADDR +unsigned long find_next_bit(const unsigned long *addr, + unsigned long size, unsigned long offset); +unsigned long find_next_zero_bit(const unsigned long *addr, + unsigned long size, unsigned long offset); + + #ifdef CONFIG_X86_32 # include "bitops_32.h" #else diff --git a/include/asm-x86/bitops_32.h b/include/asm-x86/bitops_32.h index 2513a81f82a..7c9ed759afb 100644 --- a/include/asm-x86/bitops_32.h +++ b/include/asm-x86/bitops_32.h @@ -39,14 +39,6 @@ static inline int find_first_zero_bit(const unsigned long *addr, unsigned size) return res; } -/** - * find_next_zero_bit - find the first zero bit in a memory region - * @addr: The address to base the search on - * @offset: The bit number to start searching at - * @size: The maximum size to search - */ -int find_next_zero_bit(const unsigned long *addr, int size, int offset); - /** * __ffs - find first bit in word. * @word: The word to search @@ -82,14 +74,6 @@ static inline unsigned find_first_bit(const unsigned long *addr, unsigned size) return x; } -/** - * find_next_bit - find the first set bit in a memory region - * @addr: The address to base the search on - * @offset: The bit number to start searching at - * @size: The maximum size to search - */ -int find_next_bit(const unsigned long *addr, int size, int offset); - /** * ffz - find first zero in word. * @word: The word to search diff --git a/include/asm-x86/bitops_64.h b/include/asm-x86/bitops_64.h index 365f8207ea5..65b20fb2ae7 100644 --- a/include/asm-x86/bitops_64.h +++ b/include/asm-x86/bitops_64.h @@ -6,9 +6,7 @@ */ extern long find_first_zero_bit(const unsigned long *addr, unsigned long size); -extern long find_next_zero_bit(const unsigned long *addr, long size, long offset); extern long find_first_bit(const unsigned long *addr, unsigned long size); -extern long find_next_bit(const unsigned long *addr, long size, long offset); /* return index of first bet set in val or max when no bit is set */ static inline long __scanbit(unsigned long val, unsigned long max) -- cgit v1.2.3