module/zfs/lzjb.c

   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 https://opensource.org/licenses/CDDL-1.0.
  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/zio_compress.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 size_t
  49 lzjb_compress(void *s_start, void *d_start, size_t s_len, size_t d_len, int n)
  50 {
  51         (void) n;
  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;
  60
  61         lempel = kmem_zalloc(LEMPEL_SIZE * sizeof (uint16_t), KM_SLEEP);
  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                                 kmem_free(lempel,
  66                                     LEMPEL_SIZE*sizeof (uint16_t));
  67                                 return (s_len);
  68                         }
  69                         copymask = 1;
  70                         copymap = dst;
  71                         *dst++ = 0;
  72                 }
  73                 if (src > (uchar_t *)s_start + s_len - MATCH_MAX) {
  74                         *dst++ = *src++;
  75                         continue;
  76                 }
  77                 hash = (src[0] << 16) + (src[1] << 8) + src[2];
  78                 hash += hash >> 9;
  79                 hash += hash >> 5;
  80                 hp = &lempel[hash & (LEMPEL_SIZE - 1)];
  81                 offset = (intptr_t)(src - *hp) & OFFSET_MASK;
  82                 *hp = (uint16_t)(uintptr_t)src;
  83                 cpy = src - offset;
  84                 if (cpy >= (uchar_t *)s_start && cpy != src &&
  85                     src[0] == cpy[0] && src[1] == cpy[1] && src[2] == cpy[2]) {
  86                         *copymap |= copymask;
  87                         for (mlen = MATCH_MIN; mlen < MATCH_MAX; mlen++)
  88                                 if (src[mlen] != cpy[mlen])
  89                                         break;
  90                         *dst++ = ((mlen - MATCH_MIN) << (NBBY - MATCH_BITS)) |
  91                             (offset >> NBBY);
  92                         *dst++ = (uchar_t)offset;
  93                         src += mlen;
  94                 } else {
  95                         *dst++ = *src++;
  96                 }
  97         }
  98
  99         kmem_free(lempel, LEMPEL_SIZE * sizeof (uint16_t));
 100         return (dst - (uchar_t *)d_start);
 101 }
 102
 103 int
 104 lzjb_decompress(void *s_start, void *d_start, size_t s_len, size_t d_len, int n)
 105 {
 106         (void) s_len, (void) n;
 107         uchar_t *src = s_start;
 108         uchar_t *dst = d_start;
 109         uchar_t *d_end = (uchar_t *)d_start + d_len;
 110         uchar_t *cpy;
 111         uchar_t copymap = 0;
 112         int copymask = 1 << (NBBY - 1);
 113
 114         while (dst < d_end) {
 115                 if ((copymask <<= 1) == (1 << NBBY)) {
 116                         copymask = 1;
 117                         copymap = *src++;
 118                 }
 119                 if (copymap & copymask) {
 120                         int mlen = (src[0] >> (NBBY - MATCH_BITS)) + MATCH_MIN;
 121                         int offset = ((src[0] << NBBY) | src[1]) & OFFSET_MASK;
 122                         src += 2;
 123                         if ((cpy = dst - offset) < (uchar_t *)d_start)
 124                                 return (-1);
 125                         while (--mlen >= 0 && dst < d_end)
 126                                 *dst++ = *cpy++;
 127                 } else {
 128                         *dst++ = *src++;
 129                 }
 130         }
 131         return (0);
 132 }