From f0d1b0b30d250a07627ad8b9fbbb5c7cc08422e8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 8 Dec 2006 02:37:49 -0800 Subject: [PATCH] LOG2: Implement a general integer log2 facility in the kernel This facility provides three entry points: ilog2() Log base 2 of unsigned long ilog2_u32() Log base 2 of u32 ilog2_u64() Log base 2 of u64 These facilities can either be used inside functions on dynamic data: int do_something(long q) { ...; y = ilog2(x) ...; } Or can be used to statically initialise global variables with constant values: unsigned n = ilog2(27); When performing static initialisation, the compiler will report "error: initializer element is not constant" if asked to take a log of zero or of something not reducible to a constant. They treat negative numbers as unsigned. When not dealing with a constant, they fall back to using fls() which permits them to use arch-specific log calculation instructions - such as BSR on x86/x86_64 or SCAN on FRV - if available. [akpm@osdl.org: MMC fix] Signed-off-by: David Howells Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Herbert Xu Cc: David Howells Cc: Wojtek Kaniewski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-frv/bitops.h | 44 ++++++++++++++++ include/linux/kernel.h | 9 +--- include/linux/log2.h | 131 +++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 176 insertions(+), 8 deletions(-) create mode 100644 include/linux/log2.h (limited to 'include') diff --git a/include/asm-frv/bitops.h b/include/asm-frv/bitops.h index 1f70d47148b..f8560edf59f 100644 --- a/include/asm-frv/bitops.h +++ b/include/asm-frv/bitops.h @@ -256,6 +256,50 @@ int __ffs(unsigned long x) return 31 - bit; } +/* + * special slimline version of fls() for calculating ilog2_u32() + * - note: no protection against n == 0 + */ +#define ARCH_HAS_ILOG2_U32 +static inline __attribute__((const)) +int __ilog2_u32(u32 n) +{ + int bit; + asm("scan %1,gr0,%0" : "=r"(bit) : "r"(n)); + return 31 - bit; +} + +/* + * special slimline version of fls64() for calculating ilog2_u64() + * - note: no protection against n == 0 + */ +#define ARCH_HAS_ILOG2_U64 +static inline __attribute__((const)) +int __ilog2_u64(u64 n) +{ + union { + u64 ll; + struct { u32 h, l; }; + } _; + int bit, x, y; + + _.ll = n; + + asm(" subcc %3,gr0,gr0,icc0 \n" + " ckeq icc0,cc4 \n" + " cscan.p %3,gr0,%0 ,cc4,0 \n" + " setlos #63,%1 \n" + " cscan.p %4,gr0,%0 ,cc4,1 \n" + " setlos #31,%2 \n" + " csub.p %1,%0,%0 ,cc4,0 \n" + " csub %2,%0,%0 ,cc4,1 \n" + : "=&r"(bit), "=r"(x), "=r"(y) + : "0r"(_.h), "r"(_.l) + : "icc0", "cc4" + ); + return bit; +} + #include #include diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 6738283ac38..3710cce1664 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -157,14 +158,6 @@ static inline int printk(const char *s, ...) { return 0; } unsigned long int_sqrt(unsigned long); -static inline int __attribute_pure__ long_log2(unsigned long x) -{ - int r = 0; - for (x >>= 1; x > 0; x >>= 1) - r++; - return r; -} - static inline unsigned long __attribute_const__ roundup_pow_of_two(unsigned long x) { diff --git a/include/linux/log2.h b/include/linux/log2.h new file mode 100644 index 00000000000..3979c60325f --- /dev/null +++ b/include/linux/log2.h @@ -0,0 +1,131 @@ +/* Integer base 2 logarithm calculation + * + * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _LINUX_LOG2_H +#define _LINUX_LOG2_H + +#include +#include + +/* + * deal with unrepresentable constant logarithms + */ +extern __attribute__((const, noreturn)) +int ____ilog2_NaN(void); + +/* + * non-constant log of base 2 calculators + * - the arch may override these in asm/bitops.h if they can be implemented + * more efficiently than using fls() and fls64() + * - the arch is not required to handle n==0 if implementing the fallback + */ +#ifndef CONFIG_ARCH_HAS_ILOG2_U32 +static inline __attribute__((const)) +int __ilog2_u32(u32 n) +{ + return fls(n) - 1; +} +#endif + +#ifndef CONFIG_ARCH_HAS_ILOG2_U64 +static inline __attribute__((const)) +int __ilog2_u64(u64 n) +{ + return fls64(n) - 1; +} +#endif + +/** + * ilog2 - log of base 2 of 32-bit or a 64-bit unsigned value + * @n - parameter + * + * constant-capable log of base 2 calculation + * - this can be used to initialise global variables from constant data, hence + * the massive ternary operator construction + * + * selects the appropriately-sized optimised version depending on sizeof(n) + */ +#define ilog2(n) \ +( \ + __builtin_constant_p(n) ? ( \ + (n) < 1 ? ____ilog2_NaN() : \ + (n) & (1ULL << 63) ? 63 : \ + (n) & (1ULL << 62) ? 62 : \ + (n) & (1ULL << 61) ? 61 : \ + (n) & (1ULL << 60) ? 60 : \ + (n) & (1ULL << 59) ? 59 : \ + (n) & (1ULL << 58) ? 58 : \ + (n) & (1ULL << 57) ? 57 : \ + (n) & (1ULL << 56) ? 56 : \ + (n) & (1ULL << 55) ? 55 : \ + (n) & (1ULL << 54) ? 54 : \ + (n) & (1ULL << 53) ? 53 : \ + (n) & (1ULL << 52) ? 52 : \ + (n) & (1ULL << 51) ? 51 : \ + (n) & (1ULL << 50) ? 50 : \ + (n) & (1ULL << 49) ? 49 : \ + (n) & (1ULL << 48) ? 48 : \ + (n) & (1ULL << 47) ? 47 : \ + (n) & (1ULL << 46) ? 46 : \ + (n) & (1ULL << 45) ? 45 : \ + (n) & (1ULL << 44) ? 44 : \ + (n) & (1ULL << 43) ? 43 : \ + (n) & (1ULL << 42) ? 42 : \ + (n) & (1ULL << 41) ? 41 : \ + (n) & (1ULL << 40) ? 40 : \ + (n) & (1ULL << 39) ? 39 : \ + (n) & (1ULL << 38) ? 38 : \ + (n) & (1ULL << 37) ? 37 : \ + (n) & (1ULL << 36) ? 36 : \ + (n) & (1ULL << 35) ? 35 : \ + (n) & (1ULL << 34) ? 34 : \ + (n) & (1ULL << 33) ? 33 : \ + (n) & (1ULL << 32) ? 32 : \ + (n) & (1ULL << 31) ? 31 : \ + (n) & (1ULL << 30) ? 30 : \ + (n) & (1ULL << 29) ? 29 : \ + (n) & (1ULL << 28) ? 28 : \ + (n) & (1ULL << 27) ? 27 : \ + (n) & (1ULL << 26) ? 26 : \ + (n) & (1ULL << 25) ? 25 : \ + (n) & (1ULL << 24) ? 24 : \ + (n) & (1ULL << 23) ? 23 : \ + (n) & (1ULL << 22) ? 22 : \ + (n) & (1ULL << 21) ? 21 : \ + (n) & (1ULL << 20) ? 20 : \ + (n) & (1ULL << 19) ? 19 : \ + (n) & (1ULL << 18) ? 18 : \ + (n) & (1ULL << 17) ? 17 : \ + (n) & (1ULL << 16) ? 16 : \ + (n) & (1ULL << 15) ? 15 : \ + (n) & (1ULL << 14) ? 14 : \ + (n) & (1ULL << 13) ? 13 : \ + (n) & (1ULL << 12) ? 12 : \ + (n) & (1ULL << 11) ? 11 : \ + (n) & (1ULL << 10) ? 10 : \ + (n) & (1ULL << 9) ? 9 : \ + (n) & (1ULL << 8) ? 8 : \ + (n) & (1ULL << 7) ? 7 : \ + (n) & (1ULL << 6) ? 6 : \ + (n) & (1ULL << 5) ? 5 : \ + (n) & (1ULL << 4) ? 4 : \ + (n) & (1ULL << 3) ? 3 : \ + (n) & (1ULL << 2) ? 2 : \ + (n) & (1ULL << 1) ? 1 : \ + (n) & (1ULL << 0) ? 0 : \ + ____ilog2_NaN() \ + ) : \ + (sizeof(n) <= 4) ? \ + __ilog2_u32(n) : \ + __ilog2_u64(n) \ + ) + +#endif /* _LINUX_LOG2_H */ -- cgit v1.2.3