1 /* 2 * CDDL HEADER START 3 * 4 * The contents of this file are subject to the terms of the 5 * Common Development and Distribution License (the "License"). 6 * You may not use this file except in compliance with the License. 7 * 8 * You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE 9 * or http://www.opensolaris.org/os/licensing. 10 * See the License for the specific language governing permissions 11 * and limitations under the License. 12 * 13 * When distributing Covered Code, include this CDDL HEADER in each 14 * file and include the License file at usr/src/OPENSOLARIS.LICENSE. 15 * If applicable, add the following below this CDDL HEADER, with the 16 * fields enclosed by brackets "[]" replaced with your own identifying 17 * information: Portions Copyright [yyyy] [name of copyright owner] 18 * 19 * CDDL HEADER END 20 */ 21 22 /* 23 * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved. 24 */ 25 26 /* 27 * We keep our own copy of this algorithm for 3 main reasons: 28 * 1. If we didn't, anyone modifying common/os/compress.c would 29 * directly break our on disk format 30 * 2. Our version of lzjb does not have a number of checks that the 31 * common/os version needs and uses 32 * 3. We initialize the lempel to ensure deterministic results, 33 * so that identical blocks can always be deduplicated. 34 * In particular, we are adding the "feature" that compress() can 35 * take a destination buffer size and returns the compressed length, or the 36 * source length if compression would overflow the destination buffer. 37 */ 38 39 #include <sys/types.h> 40 #include <sys/param.h> 41 42 #define MATCH_BITS 6 43 #define MATCH_MIN 3 44 #define MATCH_MAX ((1 << MATCH_BITS) + (MATCH_MIN - 1)) 45 #define OFFSET_MASK ((1 << (16 - MATCH_BITS)) - 1) 46 #define LEMPEL_SIZE 1024 47 48 /*ARGSUSED*/ 49 size_t 50 lzjb_compress(void *s_start, void *d_start, size_t s_len, size_t d_len, int n) 51 { 52 uchar_t *src = s_start; 53 uchar_t *dst = d_start; 54 uchar_t *cpy; 55 uchar_t *copymap = NULL; 56 int copymask = 1 << (NBBY - 1); 57 int mlen, offset, hash; 58 uint16_t *hp; 59 uint16_t lempel[LEMPEL_SIZE] = { 0 }; 60 61 while (src < (uchar_t *)s_start + s_len) { 62 if ((copymask <<= 1) == (1 << NBBY)) { 63 if (dst >= (uchar_t *)d_start + d_len - 1 - 2 * NBBY) 64 return (s_len); 65 copymask = 1; 66 copymap = dst; 67 *dst++ = 0; 68 } 69 if (src > (uchar_t *)s_start + s_len - MATCH_MAX) { 70 *dst++ = *src++; 71 continue; 72 } 73 hash = (src[0] << 16) + (src[1] << 8) + src[2]; 74 hash += hash >> 9; 75 hash += hash >> 5; 76 hp = &lempel[hash & (LEMPEL_SIZE - 1)]; 77 offset = (intptr_t)(src - *hp) & OFFSET_MASK; 78 *hp = (uint16_t)(uintptr_t)src; 79 cpy = src - offset; 80 if (cpy >= (uchar_t *)s_start && cpy != src && 81 src[0] == cpy[0] && src[1] == cpy[1] && src[2] == cpy[2]) { 82 *copymap |= copymask; 83 for (mlen = MATCH_MIN; mlen < MATCH_MAX; mlen++) 84 if (src[mlen] != cpy[mlen]) 85 break; 86 *dst++ = ((mlen - MATCH_MIN) << (NBBY - MATCH_BITS)) | 87 (offset >> NBBY); 88 *dst++ = (uchar_t)offset; 89 src += mlen; 90 } else { 91 *dst++ = *src++; 92 } 93 } 94 return (dst - (uchar_t *)d_start); 95 } 96 97 /*ARGSUSED*/ 98 int 99 lzjb_decompress(void *s_start, void *d_start, size_t s_len, size_t d_len, int n) 100 { 101 uchar_t *src = s_start; 102 uchar_t *dst = d_start; 103 uchar_t *d_end = (uchar_t *)d_start + d_len; 104 uchar_t *cpy; 105 uchar_t copymap = 0; 106 int copymask = 1 << (NBBY - 1); 107 108 while (dst < d_end) { 109 if ((copymask <<= 1) == (1 << NBBY)) { 110 copymask = 1; 111 copymap = *src++; 112 } 113 if (copymap & copymask) { 114 int mlen = (src[0] >> (NBBY - MATCH_BITS)) + MATCH_MIN; 115 int offset = ((src[0] << NBBY) | src[1]) & OFFSET_MASK; 116 src += 2; 117 if ((cpy = dst - offset) < (uchar_t *)d_start) 118 return (-1); 119 while (--mlen >= 0 && dst < d_end) 120 *dst++ = *cpy++; 121 } else { 122 *dst++ = *src++; 123 } 124 } 125 return (0); 126 } 127