From 819dc7d4c4198fb19ec2124e3d5cd3b6a7c0fb28 Mon Sep 17 00:00:00 2001 From: David Goulet Date: Thu, 27 Oct 2011 14:50:45 +0200 Subject: [PATCH] Import hashtable files from URCU upstream git Signed-off-by: David Goulet --- hashtable/hash.c | 453 +++++++++++++++++++++++++++++++++++++++ hashtable/hash.h | 31 +++ ltt-sessiond/hashtable.c | 108 ++++++++++ ltt-sessiond/hashtable.h | 40 ++++ 4 files changed, 632 insertions(+) create mode 100644 hashtable/hash.c create mode 100644 hashtable/hash.h create mode 100644 ltt-sessiond/hashtable.c create mode 100644 ltt-sessiond/hashtable.h diff --git a/hashtable/hash.c b/hashtable/hash.c new file mode 100644 index 000000000..a3a3152dc --- /dev/null +++ b/hashtable/hash.c @@ -0,0 +1,453 @@ +/* + * Copyright (C) - Bob Jenkins, May 2006, Public Domain. + * Copyright (C) 2011 - David Goulet + * + * These are functions for producing 32-bit hashes for hash table lookup. + * hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final() are + * externally useful functions. Routines to test the hash are included if + * SELF_TEST is defined. You can use this free for any purpose. It's in the + * public domain. It has no warranty. + * + * You probably want to use hashlittle(). hashlittle() and hashbig() hash byte + * arrays. hashlittle() is is faster than hashbig() on little-endian machines. + * Intel and AMD are little-endian machines. On second thought, you probably + * want hashlittle2(), which is identical to hashlittle() except it returns two + * 32-bit hashes for the price of one. You could implement hashbig2() if you + * wanted but I haven't bothered here. + * + * If you want to find a hash of, say, exactly 7 integers, do + * a = i1; b = i2; c = i3; + * mix(a,b,c); + * a += i4; b += i5; c += i6; + * mix(a,b,c); + * a += i7; + * final(a,b,c); + * then use c as the hash value. If you have a variable length array of + * 4-byte integers to hash, use hashword(). If you have a byte array (like + * a character string), use hashlittle(). If you have several byte arrays, or + * a mix of things, see the comments above hashlittle(). + * + * Why is this so big? I read 12 bytes at a time into 3 4-byte integers, then + * mix those integers. This is fast (you can do a lot more thorough mixing + * with 12*3 instructions on 3 integers than you can with 3 instructions on 1 + * byte), but shoehorning those bytes into integers efficiently is messy. + */ + +#include /* defines printf for tests */ +#include /* defines time_t for timings in the test */ +#include /* defines uint32_t etc */ +#include /* attempt to define endianness */ +#include /* attempt to define endianness */ +#include +#include + +/* + * My best guess at if you are big-endian or little-endian. This may + * need adjustment. + */ +#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 HASH_LITTLE_ENDIAN 1 +# define HASH_BIG_ENDIAN 0 +#elif (defined(__BYTE_ORDER) && defined(__BIG_ENDIAN) && \ + __BYTE_ORDER == __BIG_ENDIAN) || \ + (defined(sparc) || defined(POWERPC) || defined(mc68000) || defined(sel)) +# define HASH_LITTLE_ENDIAN 0 +# define HASH_BIG_ENDIAN 1 +#else +# define HASH_LITTLE_ENDIAN 0 +# define HASH_BIG_ENDIAN 0 +#endif + +#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; \ +} + +/* + * 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); \ +} + +/* + * hashword2() -- same as hashword(), but take two seeds and return two 32-bit + * values. pc and pb must both be nonnull, and *pc and *pb must both be + * initialized with seeds. If you pass in (*pb)==0, the output (*pc) will be + * the same as the return value from hashword(). + */ +static void hashword2(const uint32_t *k, size_t length, + uint32_t *pc, uint32_t *pb) +{ + uint32_t a, b, c; + + /* Set up the internal state */ + a = b = c = 0xdeadbeef + ((uint32_t) (length << 2)) + *pc; + c += *pb; + + while (length > 3) { + a += k[0]; + b += k[1]; + c += k[2]; + mix(a, b, c); + length -= 3; + k += 3; + } + + switch (length) { + case 3 : + c += k[2]; + case 2 : + b += k[1]; + case 1 : + a += k[0]; + final(a, b, c); + case 0: /* case 0: nothing left to add */ + break; + } + + *pc = c; + *pb = b; +} + +/* + * 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; + } + + /* + * "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 */ + const uint8_t *k8; + + 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 (HASH_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; + } + + 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; + + 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; + } + + 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; +} + +/* + * Hash function for number value. + */ +unsigned long hash_key(void *_key, size_t length, unsigned long seed) +{ + union { + uint64_t v64; + uint32_t v32[2]; + } v; + union { + uint64_t v64; + uint32_t v32[2]; + } key; + + assert(length == sizeof(unsigned long)); + v.v64 = (uint64_t) seed; + key.v64 = (uint64_t) _key; + hashword2(key.v32, 2, &v.v32[0], &v.v32[1]); + return v.v64; +} + +/* + * Hash function for string. + */ +unsigned long hash_key_str(void *key, size_t length, unsigned long seed) +{ + return hashlittle(key, length, seed); +} + +/* + * Hash function compare for number value. + */ +unsigned long hash_compare_key(void *key1, size_t key1_len, + void *key2, size_t key2_len) +{ + if (key1_len != key2_len) { + return -1; + } + + if (key1 == key2) { + return 0; + } + + return 1; +} + +/* + * Hash compare function for string. + */ +unsigned long hash_compare_key_str(void *key1, size_t key1_len, + void *key2, size_t key2_len) +{ + if (key1_len != key2_len) { + return -1; + } + + if (strncmp(key1, key2, key1_len) == 0) { + return 0; + } + + return 1; +} diff --git a/hashtable/hash.h b/hashtable/hash.h new file mode 100644 index 000000000..796920e5c --- /dev/null +++ b/hashtable/hash.h @@ -0,0 +1,31 @@ +/* + * Copyright (C) 2011 - David Goulet + * + * 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; only version 2 of the License. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., 59 Temple + * Place - Suite 330, Boston, MA 02111-1307, USA. + */ + +#ifndef _LTT_HASH_H +#define _LTT_HASH_H + +unsigned long hash_key(void *_key, size_t length, unsigned long seed); + +unsigned long hash_key_str(void *_key, size_t length, unsigned long seed); + +unsigned long hash_compare_key(void *key1, size_t key1_len, + void *key2, size_t key2_len); + +unsigned long hash_compare_key_str(void *key1, size_t key1_len, + void *key2, size_t key2_len); + +#endif /* _LTT_HASH_H */ diff --git a/ltt-sessiond/hashtable.c b/ltt-sessiond/hashtable.c new file mode 100644 index 000000000..37dc01c9e --- /dev/null +++ b/ltt-sessiond/hashtable.c @@ -0,0 +1,108 @@ +/* + * Copyright (C) 2011 - David Goulet + * + * 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; only version 2 of the License. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., 59 Temple + * Place - Suite 330, Boston, MA 02111-1307, USA. + */ + +#include + +#include + +#include "hashtable.h" +#include "../hashtable/rculfhash.h" +#include "../hashtable/hash.h" + +struct cds_lfht *hashtable_new(unsigned long size) +{ + if (size == 0) { + size = DEFAULT_HT_SIZE; + } + + return cds_lfht_new(hash_key, hash_compare_key, 0x42UL, + CDS_LFHT_AUTO_RESIZE, size, NULL); +} + +struct cds_lfht *hashtable_new_str(unsigned long size) +{ + if (size == 0) { + size = DEFAULT_HT_SIZE; + } + + return cds_lfht_new(hash_key_str, hash_compare_key_str, 0x42UL, + CDS_LFHT_AUTO_RESIZE, size, NULL); +} + +struct cds_lfht_node *hashtable_iter_get_node(struct cds_lfht_iter *iter) +{ + /* Safety net */ + if (iter == NULL) { + return NULL; + } + + return cds_lfht_iter_get_node(iter); +} + +struct cds_lfht_node *hashtable_lookup(struct cds_lfht *ht, void *key, + size_t key_len, struct cds_lfht_iter *iter) +{ + /* Safety net */ + if (ht == NULL || iter == NULL || key == NULL) { + return NULL; + } + + cds_lfht_lookup(ht, key, key_len, iter); + + return hashtable_iter_get_node(iter); +} + +void hashtable_get_first(struct cds_lfht *ht, struct cds_lfht_iter *iter) +{ + cds_lfht_first(ht, iter); +} + +void hashtable_get_next(struct cds_lfht *ht, struct cds_lfht_iter *iter) +{ + cds_lfht_next(ht, iter); +} + +void hashtable_add_unique(struct cds_lfht *ht, struct cds_lfht_node *node) +{ + cds_lfht_add_unique(ht, node); +} + +void hashtable_node_init(struct cds_lfht_node *node, void *key, + size_t key_len) +{ + cds_lfht_node_init(node, key, key_len); +} + +int hashtable_del(struct cds_lfht *ht, struct cds_lfht_iter *iter) +{ + /* Safety net */ + if (ht == NULL || iter == NULL) { + return -1; + } + + return cds_lfht_del(ht, iter); +} + +unsigned long hashtable_get_count(struct cds_lfht *ht) +{ + long ab, aa; + unsigned long count, removed; + + cds_lfht_count_nodes(ht, &ab, &count, &removed, &aa); + + return count; +} diff --git a/ltt-sessiond/hashtable.h b/ltt-sessiond/hashtable.h new file mode 100644 index 000000000..5174eed75 --- /dev/null +++ b/ltt-sessiond/hashtable.h @@ -0,0 +1,40 @@ +/* + * Copyright (C) 2011 - David Goulet + * + * 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; only version 2 of the License. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., 59 Temple + * Place - Suite 330, Boston, MA 02111-1307, USA. + */ + +#ifndef _LTT_HASHTABLE_H +#define _LTT_HASHTABLE_H + +#include +#include "../hashtable/rculfhash.h" + +struct cds_lfht *hashtable_new(unsigned long size); +struct cds_lfht *hashtable_new_str(unsigned long size); + +struct cds_lfht_node *hashtable_iter_get_node(struct cds_lfht_iter *iter); +struct cds_lfht_node *hashtable_lookup(struct cds_lfht *ht, void *key, + size_t key_len, struct cds_lfht_iter *iter); + +void hashtable_get_first(struct cds_lfht *ht, struct cds_lfht_iter *iter); +void hashtable_get_next(struct cds_lfht *ht, struct cds_lfht_iter *iter); +void hashtable_add_unique(struct cds_lfht *ht, struct cds_lfht_node *node); +void hashtable_node_init(struct cds_lfht_node *node, + void *key, size_t key_len); + +int hashtable_del(struct cds_lfht *ht, struct cds_lfht_iter *iter); +unsigned long hashtable_get_count(struct cds_lfht *ht); + +#endif /* _LTT_HASHTABLE_H */ -- 2.34.1