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/zfs_context.h>
40 #include <sys/types.h>
41 #include <sys/param.h>
42
43 #define MATCH_BITS 6
44 #define MATCH_MIN 3
45 #define MATCH_MAX ((1 << MATCH_BITS) + (MATCH_MIN - 1))
46 #define OFFSET_MASK ((1 << (16 - MATCH_BITS)) - 1)
47 #define LEMPEL_SIZE 1024
48
49 /*ARGSUSED*/
50 size_t
lzjb_compress(void * s_start,void * d_start,size_t s_len,size_t d_len,int n)51 lzjb_compress(void *s_start, void *d_start, size_t s_len, size_t d_len, int n)
52 {
53 uchar_t *src = s_start;
54 uchar_t *dst = d_start;
55 uchar_t *cpy;
56 uchar_t *copymap = NULL;
57 int copymask = 1 << (NBBY - 1);
58 int mlen, offset, hash;
59 uint16_t *hp;
60 uint16_t lempel[LEMPEL_SIZE] = { 0 };
61
62 while (src < (uchar_t *)s_start + s_len) {
63 if ((copymask <<= 1) == (1 << NBBY)) {
64 if (dst >= (uchar_t *)d_start + d_len - 1 - 2 * NBBY)
65 return (s_len);
66 copymask = 1;
67 copymap = dst;
68 *dst++ = 0;
69 }
70 if (src > (uchar_t *)s_start + s_len - MATCH_MAX) {
71 *dst++ = *src++;
72 continue;
73 }
74 hash = (src[0] << 16) + (src[1] << 8) + src[2];
75 hash += hash >> 9;
76 hash += hash >> 5;
77 hp = &lempel[hash & (LEMPEL_SIZE - 1)];
78 offset = (intptr_t)(src - *hp) & OFFSET_MASK;
79 *hp = (uint16_t)(uintptr_t)src;
80 cpy = src - offset;
81 if (cpy >= (uchar_t *)s_start && cpy != src &&
82 src[0] == cpy[0] && src[1] == cpy[1] && src[2] == cpy[2]) {
83 *copymap |= copymask;
84 for (mlen = MATCH_MIN; mlen < MATCH_MAX; mlen++)
85 if (src[mlen] != cpy[mlen])
86 break;
87 *dst++ = ((mlen - MATCH_MIN) << (NBBY - MATCH_BITS)) |
88 (offset >> NBBY);
89 *dst++ = (uchar_t)offset;
90 src += mlen;
91 } else {
92 *dst++ = *src++;
93 }
94 }
95 return (dst - (uchar_t *)d_start);
96 }
97
98 /*ARGSUSED*/
99 int
lzjb_decompress(void * s_start,void * d_start,size_t s_len,size_t d_len,int n)100 lzjb_decompress(void *s_start, void *d_start, size_t s_len, size_t d_len, int n)
101 {
102 uchar_t *src = s_start;
103 uchar_t *dst = d_start;
104 uchar_t *d_end = (uchar_t *)d_start + d_len;
105 uchar_t *cpy;
106 uchar_t copymap = 0;
107 int copymask = 1 << (NBBY - 1);
108
109 while (dst < d_end) {
110 if ((copymask <<= 1) == (1 << NBBY)) {
111 copymask = 1;
112 copymap = *src++;
113 }
114 if (copymap & copymask) {
115 int mlen = (src[0] >> (NBBY - MATCH_BITS)) + MATCH_MIN;
116 int offset = ((src[0] << NBBY) | src[1]) & OFFSET_MASK;
117 src += 2;
118 if ((cpy = dst - offset) < (uchar_t *)d_start)
119 return (-1);
120 if (mlen > (d_end - dst))
121 mlen = d_end - dst;
122 while (--mlen >= 0)
123 *dst++ = *cpy++;
124 } else {
125 *dst++ = *src++;
126 }
127 }
128 return (0);
129 }
130