From e31fda3063e3c88ca0b93a9fb5e6d6e32478e36b Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 15 Aug 2013 14:17:21 -0300 Subject: [PATCH] dwarves_reorganize: Fixup calculation of bytes needed for bitfield The changeset: commit f043528 Author: Arnaldo Carvalho de Melo Date: Sun Aug 16 12:26:33 2009 -0300 dwarves_reorganize: Fix class__demote_bitfields, we need power of two bytes Had a correct changeset description, but an incorrect implementation, it was not rouding up to the next power of two, but to the next multiple of 2, i.e. when a bitfield has 2 bits, it was deciding it needed 2 bytes, not 1. Fix it by copying the roundup_power_of_two code from the Linux kernel, mostly by David Howells . Signed-off-by: Arnaldo Carvalho de Melo --- dutil.h | 218 +++++++++++++++++++++++++++++++++++++++++++ dwarves_reorganize.c | 2 +- 2 files changed, 219 insertions(+), 1 deletion(-) diff --git a/dutil.h b/dutil.h index c6a1a79..6954243 100644 --- a/dutil.h +++ b/dutil.h @@ -15,8 +15,11 @@ #include #include #include +#include #include "rbtree.h" +#define BITS_PER_LONG __BITS_PER_LONG + #ifndef __unused #define __unused __attribute__ ((unused)) #endif @@ -32,6 +35,221 @@ static inline __attribute__((const)) bool is_power_of_2(unsigned long n) return (n != 0 && ((n & (n - 1)) == 0)); } +/** + * fls - find last (most-significant) bit set + * @x: the word to search + * + * This is defined the same way as ffs. + * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32. + */ +static __always_inline int fls(int x) +{ + return x ? sizeof(x) * 8 - __builtin_clz(x) : 0; +} + +/** + * fls64 - find last set bit in a 64-bit word + * @x: the word to search + * + * This is defined in a similar way as the libc and compiler builtin + * ffsll, but returns the position of the most significant set bit. + * + * fls64(value) returns 0 if value is 0 or the position of the last + * set bit if value is nonzero. The last (most significant) bit is + * at position 64. + */ +#if BITS_PER_LONG == 32 +static __always_inline int fls64(uint64_t x) +{ + uint32_t h = x >> 32; + if (h) + return fls(h) + 32; + return fls(x); +} +#elif BITS_PER_LONG == 64 +/** + * __fls - find last (most-significant) set bit in a long word + * @word: the word to search + * + * Undefined if no set bit exists, so code should check against 0 first. + */ +static __always_inline unsigned long __fls(unsigned long word) +{ + int num = BITS_PER_LONG - 1; + +#if BITS_PER_LONG == 64 + if (!(word & (~0ul << 32))) { + num -= 32; + word <<= 32; + } +#endif + if (!(word & (~0ul << (BITS_PER_LONG-16)))) { + num -= 16; + word <<= 16; + } + if (!(word & (~0ul << (BITS_PER_LONG-8)))) { + num -= 8; + word <<= 8; + } + if (!(word & (~0ul << (BITS_PER_LONG-4)))) { + num -= 4; + word <<= 4; + } + if (!(word & (~0ul << (BITS_PER_LONG-2)))) { + num -= 2; + word <<= 2; + } + if (!(word & (~0ul << (BITS_PER_LONG-1)))) + num -= 1; + return num; +} + +static __always_inline int fls64(uint64_t x) +{ + if (x == 0) + return 0; + return __fls(x) + 1; +} +#else +#error BITS_PER_LONG not 32 or 64 +#endif + +static inline unsigned fls_long(unsigned long l) +{ + if (sizeof(l) == 4) + return fls(l); + return fls64(l); +} + +/* + * round up to nearest power of two + */ +static inline __attribute__((const)) +unsigned long __roundup_pow_of_two(unsigned long n) +{ + return 1UL << fls_long(n - 1); +} + +/* + * 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 + */ +static inline __attribute__((const)) +int __ilog2_u32(uint32_t n) +{ + return fls(n) - 1; +} + +static inline __attribute__((const)) +int __ilog2_u64(uint64_t n) +{ + return fls64(n) - 1; +} + +/** + * 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) \ + ) + +/** + * roundup_pow_of_two - round the given value up to nearest power of two + * @n - parameter + * + * round the given value up to the nearest power of two + * - the result is undefined when n == 0 + * - this can be used to initialise global variables from constant data + */ +#define roundup_pow_of_two(n) \ +( \ + __builtin_constant_p(n) ? ( \ + (n == 1) ? 1 : \ + (1UL << (ilog2((n) - 1) + 1)) \ + ) : \ + __roundup_pow_of_two(n) \ + ) + /* We need define two variables, argp_program_version_hook and argp_program_bug_address, in all programs. argp.h declares these variables as non-const (which is correct in general). But we can diff --git a/dwarves_reorganize.c b/dwarves_reorganize.c index 75c0f02..61d8227 100644 --- a/dwarves_reorganize.c +++ b/dwarves_reorganize.c @@ -533,7 +533,7 @@ static int class__demote_bitfields(struct class *class, const struct cu *cu, size = member->byte_size; bytes_needed = (current_bitfield_size + 7) / 8; - bytes_needed = roundup(bytes_needed, 2); + bytes_needed = roundup_pow_of_two(bytes_needed); if (bytes_needed == size) continue;