From a0180288cfed99a5663678db635700225aafb294 Mon Sep 17 00:00:00 2001 From: Anthony Minessale Date: Thu, 1 Dec 2016 18:11:01 -0600 Subject: [PATCH] FS-9803 #resolve [Add support for arbitrary data as hash keys] --- libs/libks/src/include/ks_hash.h | 350 ++++++++++++++++++++++++++- libs/libks/src/include/ks_platform.h | 16 ++ libs/libks/src/include/ks_types.h | 2 +- libs/libks/src/ks_hash.c | 52 +++- libs/libks/test/testhash.c | 42 +++- 5 files changed, 450 insertions(+), 12 deletions(-) diff --git a/libs/libks/src/include/ks_hash.h b/libs/libks/src/include/ks_hash.h index 2f6b9da1a7..09ff5dbb3a 100644 --- a/libs/libks/src/include/ks_hash.h +++ b/libs/libks/src/include/ks_hash.h @@ -106,7 +106,8 @@ typedef enum { KS_HASH_MODE_CASE_INSENSITIVE, KS_HASH_MODE_INT, KS_HASH_MODE_INT64, - KS_HASH_MODE_PTR + KS_HASH_MODE_PTR, + KS_HASH_MODE_ARBITRARY } ks_hash_mode_t; @@ -157,6 +158,7 @@ KS_DECLARE(int) ks_hash_insert_ex(ks_hash_t *h, void *k, void *v, ks_hash_flag_t KS_DECLARE(void) ks_hash_set_flags(ks_hash_t *h, ks_hash_flag_t flags); +KS_DECLARE(void) ks_hash_set_keysize(ks_hash_t *h, ks_size_t keysize); KS_DECLARE(void) ks_hash_set_destructor(ks_hash_t *h, ks_hash_destructor_t destructor); /***************************************************************************** @@ -318,6 +320,352 @@ static __inline uint32_t ks_hash_default_ci(void *ky) return hash; } +#define hashsize(n) ((uint32_t)1<<(n)) +#define hashmask(n) (hashsize(n)-1) +#define rot(x,k) (((x)<<(k)) | ((x)>>(32-(k)))) + +/* +------------------------------------------------------------------------------- +mix -- mix 3 32-bit values reversibly. + +This is reversible, so any information in (a,b,c) before mix() is +still in (a,b,c) after mix(). + +If four pairs of (a,b,c) inputs are run through mix(), or through +mix() in reverse, there are at least 32 bits of the output that +are sometimes the same for one pair and different for another pair. +This was tested for: +* pairs that differed by one bit, by two bits, in any combination + of top bits of (a,b,c), or in any combination of bottom bits of + (a,b,c). +* "differ" is defined as +, -, ^, or ~^. For + and -, I transformed + the output delta to a Gray code (a^(a>>1)) so a string of 1's (as + is commonly produced by subtraction) look like a single 1-bit + difference. +* the base values were pseudorandom, all zero but one bit set, or + all zero plus a counter that starts at zero. + +Some k values for my "a-=c; a^=rot(c,k); c+=b;" arrangement that +satisfy this are + 4 6 8 16 19 4 + 9 15 3 18 27 15 + 14 9 3 7 17 3 +Well, "9 15 3 18 27 15" didn't quite get 32 bits diffing +for "differ" defined as + with a one-bit base and a two-bit delta. I +used http://burtleburtle.net/bob/hash/avalanche.html to choose +the operations, constants, and arrangements of the variables. + +This does not achieve avalanche. There are input bits of (a,b,c) +that fail to affect some output bits of (a,b,c), especially of a. The +most thoroughly mixed value is c, but it doesn't really even achieve +avalanche in c. + +This allows some parallelism. Read-after-writes are good at doubling +the number of bits affected, so the goal of mixing pulls in the opposite +direction as the goal of parallelism. I did what I could. Rotates +seem to cost as much as shifts on every machine I could lay my hands +on, and rotates are much kinder to the top and bottom bits, so I used +rotates. +------------------------------------------------------------------------------- +*/ +#define mix(a,b,c) \ +{ \ + a -= c; a ^= rot(c, 4); c += b; \ + b -= a; b ^= rot(a, 6); a += c; \ + c -= b; c ^= rot(b, 8); b += a; \ + a -= c; a ^= rot(c,16); c += b; \ + b -= a; b ^= rot(a,19); a += c; \ + c -= b; c ^= rot(b, 4); b += a; \ +} + +/* +------------------------------------------------------------------------------- +mix -- mix 3 32-bit values reversibly. + +This is reversible, so any information in (a,b,c) before mix() is +still in (a,b,c) after mix(). + +If four pairs of (a,b,c) inputs are run through mix(), or through +mix() in reverse, there are at least 32 bits of the output that +are sometimes the same for one pair and different for another pair. +This was tested for: +* pairs that differed by one bit, by two bits, in any combination + of top bits of (a,b,c), or in any combination of bottom bits of + (a,b,c). +* "differ" is defined as +, -, ^, or ~^. For + and -, I transformed + the output delta to a Gray code (a^(a>>1)) so a string of 1's (as + is commonly produced by subtraction) look like a single 1-bit + difference. +* the base values were pseudorandom, all zero but one bit set, or + all zero plus a counter that starts at zero. + +Some k values for my "a-=c; a^=rot(c,k); c+=b;" arrangement that +satisfy this are + 4 6 8 16 19 4 + 9 15 3 18 27 15 + 14 9 3 7 17 3 +Well, "9 15 3 18 27 15" didn't quite get 32 bits diffing +for "differ" defined as + with a one-bit base and a two-bit delta. I +used http://burtleburtle.net/bob/hash/avalanche.html to choose +the operations, constants, and arrangements of the variables. + +This does not achieve avalanche. There are input bits of (a,b,c) +that fail to affect some output bits of (a,b,c), especially of a. The +most thoroughly mixed value is c, but it doesn't really even achieve +avalanche in c. + +This allows some parallelism. Read-after-writes are good at doubling +the number of bits affected, so the goal of mixing pulls in the opposite +direction as the goal of parallelism. I did what I could. Rotates +seem to cost as much as shifts on every machine I could lay my hands +on, and rotates are much kinder to the top and bottom bits, so I used +rotates. +------------------------------------------------------------------------------- +*/ +#define mix(a,b,c) \ +{ \ + a -= c; a ^= rot(c, 4); c += b; \ + b -= a; b ^= rot(a, 6); a += c; \ + c -= b; c ^= rot(b, 8); b += a; \ + a -= c; a ^= rot(c,16); c += b; \ + b -= a; b ^= rot(a,19); a += c; \ + c -= b; c ^= rot(b, 4); b += a; \ +} + +/* +------------------------------------------------------------------------------- +final -- final mixing of 3 32-bit values (a,b,c) into c + +Pairs of (a,b,c) values differing in only a few bits will usually +produce values of c that look totally different. This was tested for +* pairs that differed by one bit, by two bits, in any combination + of top bits of (a,b,c), or in any combination of bottom bits of + (a,b,c). +* "differ" is defined as +, -, ^, or ~^. For + and -, I transformed + the output delta to a Gray code (a^(a>>1)) so a string of 1's (as + is commonly produced by subtraction) look like a single 1-bit + difference. +* the base values were pseudorandom, all zero but one bit set, or + all zero plus a counter that starts at zero. + +These constants passed: + 14 11 25 16 4 14 24 + 12 14 25 16 4 14 24 +and these came close: + 4 8 15 26 3 22 24 + 10 8 15 26 3 22 24 + 11 8 15 26 3 22 24 +------------------------------------------------------------------------------- +*/ +#define final(a,b,c) \ +{ \ + c ^= b; c -= rot(b,14); \ + a ^= c; a -= rot(c,11); \ + b ^= a; b -= rot(a,25); \ + c ^= b; c -= rot(b,16); \ + a ^= c; a -= rot(c,4); \ + b ^= a; b -= rot(a,14); \ + c ^= b; c -= rot(b,24); \ +} + + + + +/* +------------------------------------------------------------------------------- +hashlittle() -- hash a variable-length key into a 32-bit value + k : the key (the unaligned variable-length array of bytes) + length : the length of the key, counting by bytes + initval : can be any 4-byte value +Returns a 32-bit value. Every bit of the key affects every bit of +the return value. Two keys differing by one or two bits will have +totally different hash values. + +The best hash table sizes are powers of 2. There is no need to do +mod a prime (mod is sooo slow!). If you need less than 32 bits, +use a bitmask. For example, if you need only 10 bits, do + h = (h & hashmask(10)); +In which case, the hash table should have hashsize(10) elements. + +If you are hashing n strings (uint8_t **)k, do it like this: + for (i=0, h=0; i 12) + { + a += k[0]; + b += k[1]; + c += k[2]; + mix(a,b,c); + length -= 12; + k += 3; + } + + /*----------------------------- handle the last (probably partial) block */ + /* + * "k[2]&0xffffff" actually reads beyond the end of the string, but + * then masks off the part it's not allowed to read. Because the + * string is aligned, the masked-off tail is in the same word as the + * rest of the string. Every machine with memory protection I've seen + * does it on word boundaries, so is OK with this. But VALGRIND will + * still catch it and complain. The masking trick does make the hash + * noticably faster for short strings (like English words). + */ +#ifndef VALGRIND + + switch(length) + { + case 12: c+=k[2]; b+=k[1]; a+=k[0]; break; + case 11: c+=k[2]&0xffffff; b+=k[1]; a+=k[0]; break; + case 10: c+=k[2]&0xffff; b+=k[1]; a+=k[0]; break; + case 9 : c+=k[2]&0xff; b+=k[1]; a+=k[0]; break; + case 8 : b+=k[1]; a+=k[0]; break; + case 7 : b+=k[1]&0xffffff; a+=k[0]; break; + case 6 : b+=k[1]&0xffff; a+=k[0]; break; + case 5 : b+=k[1]&0xff; a+=k[0]; break; + case 4 : a+=k[0]; break; + case 3 : a+=k[0]&0xffffff; break; + case 2 : a+=k[0]&0xffff; break; + case 1 : a+=k[0]&0xff; break; + case 0 : return c; /* zero length strings require no mixing */ + } + +#else /* make valgrind happy */ + + k8 = (const uint8_t *)k; + switch(length) + { + case 12: c+=k[2]; b+=k[1]; a+=k[0]; break; + case 11: c+=((uint32_t)k8[10])<<16; /* fall through */ + case 10: c+=((uint32_t)k8[9])<<8; /* fall through */ + case 9 : c+=k8[8]; /* fall through */ + case 8 : b+=k[1]; a+=k[0]; break; + case 7 : b+=((uint32_t)k8[6])<<16; /* fall through */ + case 6 : b+=((uint32_t)k8[5])<<8; /* fall through */ + case 5 : b+=k8[4]; /* fall through */ + case 4 : a+=k[0]; break; + case 3 : a+=((uint32_t)k8[2])<<16; /* fall through */ + case 2 : a+=((uint32_t)k8[1])<<8; /* fall through */ + case 1 : a+=k8[0]; break; + case 0 : return c; + } + +#endif /* !valgrind */ + + } else if (KS_LITTLE_ENDIAN && ((u.i & 0x1) == 0)) { + const uint16_t *k = (const uint16_t *)key; /* read 16-bit chunks */ + const uint8_t *k8; + + /*--------------- all but last block: aligned reads and different mixing */ + while (length > 12) + { + a += k[0] + (((uint32_t)k[1])<<16); + b += k[2] + (((uint32_t)k[3])<<16); + c += k[4] + (((uint32_t)k[5])<<16); + mix(a,b,c); + length -= 12; + k += 6; + } + + /*----------------------------- handle the last (probably partial) block */ + k8 = (const uint8_t *)k; + switch(length) + { + case 12: c+=k[4]+(((uint32_t)k[5])<<16); + b+=k[2]+(((uint32_t)k[3])<<16); + a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 11: c+=((uint32_t)k8[10])<<16; /* fall through */ + case 10: c+=k[4]; + b+=k[2]+(((uint32_t)k[3])<<16); + a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 9 : c+=k8[8]; /* fall through */ + case 8 : b+=k[2]+(((uint32_t)k[3])<<16); + a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 7 : b+=((uint32_t)k8[6])<<16; /* fall through */ + case 6 : b+=k[2]; + a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 5 : b+=k8[4]; /* fall through */ + case 4 : a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 3 : a+=((uint32_t)k8[2])<<16; /* fall through */ + case 2 : a+=k[0]; + break; + case 1 : a+=k8[0]; + break; + case 0 : return c; /* zero length requires no mixing */ + } + + } else { /* need to read the key one byte at a time */ + const uint8_t *k = (const uint8_t *)key; + + /*--------------- all but the last block: affect some 32 bits of (a,b,c) */ + while (length > 12) + { + a += k[0]; + a += ((uint32_t)k[1])<<8; + a += ((uint32_t)k[2])<<16; + a += ((uint32_t)k[3])<<24; + b += k[4]; + b += ((uint32_t)k[5])<<8; + b += ((uint32_t)k[6])<<16; + b += ((uint32_t)k[7])<<24; + c += k[8]; + c += ((uint32_t)k[9])<<8; + c += ((uint32_t)k[10])<<16; + c += ((uint32_t)k[11])<<24; + mix(a,b,c); + length -= 12; + k += 12; + } + + /*-------------------------------- last block: affect all 32 bits of (c) */ + switch(length) /* all the case statements fall through */ + { + case 12: c+=((uint32_t)k[11])<<24; + case 11: c+=((uint32_t)k[10])<<16; + case 10: c+=((uint32_t)k[9])<<8; + case 9 : c+=k[8]; + case 8 : b+=((uint32_t)k[7])<<24; + case 7 : b+=((uint32_t)k[6])<<16; + case 6 : b+=((uint32_t)k[5])<<8; + case 5 : b+=k[4]; + case 4 : a+=((uint32_t)k[3])<<24; + case 3 : a+=((uint32_t)k[2])<<16; + case 2 : a+=((uint32_t)k[1])<<8; + case 1 : a+=k[0]; + break; + case 0 : return c; + } + } + + final(a,b,c); + return c; +} + diff --git a/libs/libks/src/include/ks_platform.h b/libs/libks/src/include/ks_platform.h index f3028b9de2..741a904bd0 100644 --- a/libs/libks/src/include/ks_platform.h +++ b/libs/libks/src/include/ks_platform.h @@ -56,6 +56,22 @@ KS_BEGIN_EXTERN_C #define KS_64BIT 1 #endif +#if (defined(__BYTE_ORDER) && defined(__LITTLE_ENDIAN) && \ + __BYTE_ORDER == __LITTLE_ENDIAN) || \ + (defined(i386) || defined(__i386__) || defined(__i486__) || \ + defined(__i586__) || defined(__i686__) || defined(vax) || defined(MIPSEL)) +# define KS_LITTLE_ENDIAN 1 +# define KS_BIG_ENDIAN 0 +#elif (defined(__BYTE_ORDER) && defined(__BIG_ENDIAN) && \ + __BYTE_ORDER == __BIG_ENDIAN) || \ + (defined(sparc) || defined(POWERPC) || defined(mc68000) || defined(sel)) +# define KS_LITTLE_ENDIAN 0 +# define KS_BIG_ENDIAN 1 +#else +# define KS_LITTLE_ENDIAN 0 +# define KS_BIG_ENDIAN 0 +#endif + #include #include #include diff --git a/libs/libks/src/include/ks_types.h b/libs/libks/src/include/ks_types.h index ed5796b215..f10a0229a1 100644 --- a/libs/libks/src/include/ks_types.h +++ b/libs/libks/src/include/ks_types.h @@ -75,7 +75,7 @@ KS_BEGIN_EXTERN_C typedef uint16_t ks_port_t; typedef size_t ks_size_t; - + typedef unsigned char ks_byte_t; typedef enum { KS_STATUS_SUCCESS, KS_STATUS_FAIL, diff --git a/libs/libks/src/ks_hash.c b/libs/libks/src/ks_hash.c index b090e4d8cd..4fd611a1be 100644 --- a/libs/libks/src/ks_hash.c +++ b/libs/libks/src/ks_hash.c @@ -64,6 +64,8 @@ struct ks_hash { ks_rwl_t *rwl; ks_mutex_t *mutex; uint32_t readers; + ks_size_t keysize; + ks_hash_mode_t mode; }; /*****************************************************************************/ @@ -72,13 +74,22 @@ struct ks_hash { static inline unsigned int hash(ks_hash_t *h, void *k) { - /* Aim to protect against poor hash functions by adding logic here - * - logic taken from java 1.4 ks_hash source */ - unsigned int i = h->hashfn(k); - i += ~(i << 9); - i ^= ((i >> 14) | (i << 18)); /* >>> */ - i += (i << 4); - i ^= ((i >> 10) | (i << 22)); /* >>> */ + unsigned int i; + + if (h->mode == KS_HASH_MODE_ARBITRARY) { + i = ks_hash_default_arbitrary(k, h->keysize, 13); + } else { + i = h->hashfn(k); + } + + /* Aim to protect against poor hash functions by adding logic here + * - logic taken from java 1.4 hash source */ + + i += ~(i << 9); + i ^= ((i >> 14) | (i << 18)); /* >>> */ + i += (i << 4); + i ^= ((i >> 10) | (i << 22)); /* >>> */ + return i; } @@ -146,6 +157,11 @@ KS_DECLARE(void) ks_hash_set_flags(ks_hash_t *h, ks_hash_flag_t flags) h->flags = flags; } +KS_DECLARE(void) ks_hash_set_keysize(ks_hash_t *h, ks_size_t keysize) +{ + h->keysize = keysize; +} + KS_DECLARE(void) ks_hash_set_destructor(ks_hash_t *h, ks_hash_destructor_t destructor) { h->destructor = destructor; @@ -159,6 +175,7 @@ ks_hash_create_ex(ks_hash_t **hp, unsigned int minsize, { ks_hash_t *h; unsigned int pindex, size = primes[0]; + ks_size_t keysize = 0; switch(mode) { case KS_HASH_MODE_CASE_INSENSITIVE: @@ -170,18 +187,24 @@ ks_hash_create_ex(ks_hash_t **hp, unsigned int minsize, ks_assert(eqf == NULL); hashf = ks_hash_default_int; eqf = ks_hash_equalkeys_int; + keysize = 4; break; case KS_HASH_MODE_INT64: ks_assert(hashf == NULL); ks_assert(eqf == NULL); hashf = ks_hash_default_int64; eqf = ks_hash_equalkeys_int64; + keysize = 8; break; case KS_HASH_MODE_PTR: ks_assert(hashf == NULL); ks_assert(eqf == NULL); hashf = ks_hash_default_ptr; eqf = ks_hash_equalkeys_ptr; + keysize = sizeof(void *); + break; + case KS_HASH_MODE_ARBITRARY: + keysize = sizeof(void *); break; default: break; @@ -210,6 +233,8 @@ ks_hash_create_ex(ks_hash_t **hp, unsigned int minsize, h->pool = pool; h->flags = flags; h->destructor = destructor; + h->keysize = keysize; + h->mode = mode; if ((flags & KS_HASH_FLAG_RWLOCK)) { ks_rwl_create(&h->rwl, h->pool); @@ -303,6 +328,15 @@ ks_hash_count(ks_hash_t *h) return h->entrycount; } +static int key_equals(ks_hash_t *h, void *k1, void *k2) +{ + if (h->mode == KS_HASH_MODE_ARBITRARY) { + return !memcmp(k1, k2, h->keysize); + } else { + return h->eqfn(k1, k2); + } +} + static void * _ks_hash_remove(ks_hash_t *h, void *k, unsigned int hashvalue, unsigned int index) { /* TODO: consider compacting the table when the load factor drops enough, * or provide a 'compact' method. */ @@ -316,7 +350,7 @@ static void * _ks_hash_remove(ks_hash_t *h, void *k, unsigned int hashvalue, uns e = *pE; while (NULL != e) { /* Check hash value to short circuit heavier comparison */ - if ((hashvalue == e->h) && (h->eqfn(k, e->k))) { + if ((hashvalue == e->h) && (key_equals(h, k, e->k))) { *pE = e->next; h->entrycount--; v = e->v; @@ -457,7 +491,7 @@ ks_hash_search(ks_hash_t *h, void *k, ks_locked_t locked) e = h->table[index]; while (NULL != e) { /* Check hash value to short circuit heavier comparison */ - if ((hashvalue == e->h) && (h->eqfn(k, e->k))) { + if ((hashvalue == e->h) && (key_equals(h, k, e->k))) { v = e->v; break; } diff --git a/libs/libks/test/testhash.c b/libs/libks/test/testhash.c index e595a04164..220a6c6959 100644 --- a/libs/libks/test/testhash.c +++ b/libs/libks/test/testhash.c @@ -120,16 +120,56 @@ int test2(void) return 1; } +#include "sodium.h" +#define TEST3_SIZE 20 +int test3(void) +{ + ks_pool_t *pool; + ks_hash_t *hash; + ks_byte_t data[TEST3_SIZE]; + ks_byte_t data2[TEST3_SIZE]; + ks_byte_t data3[TEST3_SIZE]; + char *A, *B, *C; + + ks_pool_open(&pool); + ks_hash_create(&hash, KS_HASH_MODE_ARBITRARY, KS_HASH_FLAG_NONE, pool); + ks_hash_set_keysize(hash, TEST3_SIZE); + + randombytes_buf(data, sizeof(data)); + randombytes_buf(data2, sizeof(data2)); + + ks_hash_insert(hash, data, "FOO"); + ks_hash_insert(hash, data2, "BAR"); + ks_hash_insert(hash, data3, "BAZ"); + + + A = (char *)ks_hash_search(hash, data, KS_UNLOCKED); + B = (char *)ks_hash_search(hash, data2, KS_UNLOCKED); + C = (char *)ks_hash_search(hash, data3, KS_UNLOCKED); + + + printf("RESULT [%s][%s][%s]\n", A, B, C); + + ks_hash_destroy(&hash); + + ks_pool_close(&pool); + + return !strcmp(A, "FOO") && !strcmp(B, "BAR") && !strcmp(C, "BAZ"); + +} + + int main(int argc, char **argv) { ks_init(); srand((unsigned)(time(NULL) - (unsigned)(intptr_t)ks_thread_self())); - plan(2); + plan(3); ok(test1()); ok(test2()); + ok(test3()); ks_shutdown();