]>
Commit | Line | Data |
---|---|---|
34dc7c2f BB |
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 | /* | |
572e2857 | 23 | * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved. |
34dc7c2f BB |
24 | */ |
25 | ||
34dc7c2f | 26 | /* |
572e2857 | 27 | * We keep our own copy of this algorithm for 3 main reasons: |
428870ff | 28 | * 1. If we didn't, anyone modifying common/os/compress.c would |
34dc7c2f | 29 | * directly break our on disk format |
428870ff | 30 | * 2. Our version of lzjb does not have a number of checks that the |
34dc7c2f | 31 | * common/os version needs and uses |
428870ff BB |
32 | * 3. We initialize the lempel to ensure deterministic results, |
33 | * so that identical blocks can always be deduplicated. | |
34dc7c2f | 34 | * In particular, we are adding the "feature" that compress() can |
572e2857 BB |
35 | * take a destination buffer size and returns the compressed length, or the |
36 | * source length if compression would overflow the destination buffer. | |
34dc7c2f BB |
37 | */ |
38 | ||
18a89ba4 | 39 | #include <sys/zfs_context.h> |
34dc7c2f BB |
40 | |
41 | #define MATCH_BITS 6 | |
42 | #define MATCH_MIN 3 | |
43 | #define MATCH_MAX ((1 << MATCH_BITS) + (MATCH_MIN - 1)) | |
44 | #define OFFSET_MASK ((1 << (16 - MATCH_BITS)) - 1) | |
428870ff | 45 | #define LEMPEL_SIZE 1024 |
34dc7c2f BB |
46 | |
47 | /*ARGSUSED*/ | |
48 | size_t | |
49 | lzjb_compress(void *s_start, void *d_start, size_t s_len, size_t d_len, int n) | |
50 | { | |
51 | uchar_t *src = s_start; | |
52 | uchar_t *dst = d_start; | |
a117a6d6 GW |
53 | uchar_t *cpy; |
54 | uchar_t *copymap = NULL; | |
34dc7c2f | 55 | int copymask = 1 << (NBBY - 1); |
428870ff | 56 | int mlen, offset, hash; |
34dc7c2f | 57 | uint16_t *hp; |
18a89ba4 | 58 | uint16_t *lempel; |
34dc7c2f | 59 | |
79c76d5b | 60 | lempel = kmem_zalloc(LEMPEL_SIZE * sizeof (uint16_t), KM_SLEEP); |
34dc7c2f BB |
61 | while (src < (uchar_t *)s_start + s_len) { |
62 | if ((copymask <<= 1) == (1 << NBBY)) { | |
18a89ba4 | 63 | if (dst >= (uchar_t *)d_start + d_len - 1 - 2 * NBBY) { |
d1d7e268 MK |
64 | kmem_free(lempel, |
65 | LEMPEL_SIZE*sizeof (uint16_t)); | |
34dc7c2f | 66 | return (s_len); |
18a89ba4 | 67 | } |
34dc7c2f BB |
68 | copymask = 1; |
69 | copymap = dst; | |
70 | *dst++ = 0; | |
71 | } | |
72 | if (src > (uchar_t *)s_start + s_len - MATCH_MAX) { | |
73 | *dst++ = *src++; | |
74 | continue; | |
75 | } | |
428870ff BB |
76 | hash = (src[0] << 16) + (src[1] << 8) + src[2]; |
77 | hash += hash >> 9; | |
78 | hash += hash >> 5; | |
79 | hp = &lempel[hash & (LEMPEL_SIZE - 1)]; | |
34dc7c2f BB |
80 | offset = (intptr_t)(src - *hp) & OFFSET_MASK; |
81 | *hp = (uint16_t)(uintptr_t)src; | |
82 | cpy = src - offset; | |
83 | if (cpy >= (uchar_t *)s_start && cpy != src && | |
84 | src[0] == cpy[0] && src[1] == cpy[1] && src[2] == cpy[2]) { | |
85 | *copymap |= copymask; | |
86 | for (mlen = MATCH_MIN; mlen < MATCH_MAX; mlen++) | |
87 | if (src[mlen] != cpy[mlen]) | |
88 | break; | |
89 | *dst++ = ((mlen - MATCH_MIN) << (NBBY - MATCH_BITS)) | | |
90 | (offset >> NBBY); | |
91 | *dst++ = (uchar_t)offset; | |
92 | src += mlen; | |
93 | } else { | |
94 | *dst++ = *src++; | |
95 | } | |
96 | } | |
18a89ba4 BB |
97 | |
98 | kmem_free(lempel, LEMPEL_SIZE * sizeof (uint16_t)); | |
34dc7c2f BB |
99 | return (dst - (uchar_t *)d_start); |
100 | } | |
101 | ||
102 | /*ARGSUSED*/ | |
103 | int | |
104 | lzjb_decompress(void *s_start, void *d_start, size_t s_len, size_t d_len, int n) | |
105 | { | |
106 | uchar_t *src = s_start; | |
107 | uchar_t *dst = d_start; | |
108 | uchar_t *d_end = (uchar_t *)d_start + d_len; | |
a117a6d6 GW |
109 | uchar_t *cpy; |
110 | uchar_t copymap = 0; | |
34dc7c2f BB |
111 | int copymask = 1 << (NBBY - 1); |
112 | ||
113 | while (dst < d_end) { | |
114 | if ((copymask <<= 1) == (1 << NBBY)) { | |
115 | copymask = 1; | |
116 | copymap = *src++; | |
117 | } | |
118 | if (copymap & copymask) { | |
119 | int mlen = (src[0] >> (NBBY - MATCH_BITS)) + MATCH_MIN; | |
120 | int offset = ((src[0] << NBBY) | src[1]) & OFFSET_MASK; | |
121 | src += 2; | |
122 | if ((cpy = dst - offset) < (uchar_t *)d_start) | |
123 | return (-1); | |
124 | while (--mlen >= 0 && dst < d_end) | |
125 | *dst++ = *cpy++; | |
126 | } else { | |
127 | *dst++ = *src++; | |
128 | } | |
129 | } | |
130 | return (0); | |
131 | } |