1eda14cbcSMatt Macy /* 2eda14cbcSMatt Macy * CDDL HEADER START 3eda14cbcSMatt Macy * 4eda14cbcSMatt Macy * The contents of this file are subject to the terms of the 5eda14cbcSMatt Macy * Common Development and Distribution License (the "License"). 6eda14cbcSMatt Macy * You may not use this file except in compliance with the License. 7eda14cbcSMatt Macy * 8eda14cbcSMatt Macy * You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE 9271171e0SMartin Matuska * or https://opensource.org/licenses/CDDL-1.0. 10eda14cbcSMatt Macy * See the License for the specific language governing permissions 11eda14cbcSMatt Macy * and limitations under the License. 12eda14cbcSMatt Macy * 13eda14cbcSMatt Macy * When distributing Covered Code, include this CDDL HEADER in each 14eda14cbcSMatt Macy * file and include the License file at usr/src/OPENSOLARIS.LICENSE. 15eda14cbcSMatt Macy * If applicable, add the following below this CDDL HEADER, with the 16eda14cbcSMatt Macy * fields enclosed by brackets "[]" replaced with your own identifying 17eda14cbcSMatt Macy * information: Portions Copyright [yyyy] [name of copyright owner] 18eda14cbcSMatt Macy * 19eda14cbcSMatt Macy * CDDL HEADER END 20eda14cbcSMatt Macy */ 21eda14cbcSMatt Macy 22eda14cbcSMatt Macy /* 23eda14cbcSMatt Macy * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved. 24eda14cbcSMatt Macy */ 25eda14cbcSMatt Macy 26eda14cbcSMatt Macy /* 27eda14cbcSMatt Macy * We keep our own copy of this algorithm for 3 main reasons: 28eda14cbcSMatt Macy * 1. If we didn't, anyone modifying common/os/compress.c would 29eda14cbcSMatt Macy * directly break our on disk format 30eda14cbcSMatt Macy * 2. Our version of lzjb does not have a number of checks that the 31eda14cbcSMatt Macy * common/os version needs and uses 32eda14cbcSMatt Macy * 3. We initialize the lempel to ensure deterministic results, 33eda14cbcSMatt Macy * so that identical blocks can always be deduplicated. 34eda14cbcSMatt Macy * In particular, we are adding the "feature" that compress() can 35eda14cbcSMatt Macy * take a destination buffer size and returns the compressed length, or the 36eda14cbcSMatt Macy * source length if compression would overflow the destination buffer. 37eda14cbcSMatt Macy */ 38eda14cbcSMatt Macy 39eda14cbcSMatt Macy #include <sys/zfs_context.h> 40eda14cbcSMatt Macy #include <sys/zio_compress.h> 41eda14cbcSMatt Macy 42eda14cbcSMatt Macy #define MATCH_BITS 6 43eda14cbcSMatt Macy #define MATCH_MIN 3 44eda14cbcSMatt Macy #define MATCH_MAX ((1 << MATCH_BITS) + (MATCH_MIN - 1)) 45eda14cbcSMatt Macy #define OFFSET_MASK ((1 << (16 - MATCH_BITS)) - 1) 46eda14cbcSMatt Macy #define LEMPEL_SIZE 1024 47eda14cbcSMatt Macy 48*e2df9bb4SMartin Matuska static size_t 49*e2df9bb4SMartin Matuska zfs_lzjb_compress_buf(void *s_start, void *d_start, size_t s_len, 50*e2df9bb4SMartin Matuska size_t d_len, int n) 51eda14cbcSMatt Macy { 52e92ffd9bSMartin Matuska (void) n; 53eda14cbcSMatt Macy uchar_t *src = s_start; 54eda14cbcSMatt Macy uchar_t *dst = d_start; 55eda14cbcSMatt Macy uchar_t *cpy; 56eda14cbcSMatt Macy uchar_t *copymap = NULL; 57eda14cbcSMatt Macy int copymask = 1 << (NBBY - 1); 58eda14cbcSMatt Macy int mlen, offset, hash; 59eda14cbcSMatt Macy uint16_t *hp; 60eda14cbcSMatt Macy uint16_t *lempel; 61eda14cbcSMatt Macy 62eda14cbcSMatt Macy lempel = kmem_zalloc(LEMPEL_SIZE * sizeof (uint16_t), KM_SLEEP); 63eda14cbcSMatt Macy while (src < (uchar_t *)s_start + s_len) { 64eda14cbcSMatt Macy if ((copymask <<= 1) == (1 << NBBY)) { 65eda14cbcSMatt Macy if (dst >= (uchar_t *)d_start + d_len - 1 - 2 * NBBY) { 66eda14cbcSMatt Macy kmem_free(lempel, 67eda14cbcSMatt Macy LEMPEL_SIZE*sizeof (uint16_t)); 68eda14cbcSMatt Macy return (s_len); 69eda14cbcSMatt Macy } 70eda14cbcSMatt Macy copymask = 1; 71eda14cbcSMatt Macy copymap = dst; 72eda14cbcSMatt Macy *dst++ = 0; 73eda14cbcSMatt Macy } 74eda14cbcSMatt Macy if (src > (uchar_t *)s_start + s_len - MATCH_MAX) { 75eda14cbcSMatt Macy *dst++ = *src++; 76eda14cbcSMatt Macy continue; 77eda14cbcSMatt Macy } 78eda14cbcSMatt Macy hash = (src[0] << 16) + (src[1] << 8) + src[2]; 79eda14cbcSMatt Macy hash += hash >> 9; 80eda14cbcSMatt Macy hash += hash >> 5; 81eda14cbcSMatt Macy hp = &lempel[hash & (LEMPEL_SIZE - 1)]; 82eda14cbcSMatt Macy offset = (intptr_t)(src - *hp) & OFFSET_MASK; 83eda14cbcSMatt Macy *hp = (uint16_t)(uintptr_t)src; 84eda14cbcSMatt Macy cpy = src - offset; 85eda14cbcSMatt Macy if (cpy >= (uchar_t *)s_start && cpy != src && 86eda14cbcSMatt Macy src[0] == cpy[0] && src[1] == cpy[1] && src[2] == cpy[2]) { 87eda14cbcSMatt Macy *copymap |= copymask; 88eda14cbcSMatt Macy for (mlen = MATCH_MIN; mlen < MATCH_MAX; mlen++) 89eda14cbcSMatt Macy if (src[mlen] != cpy[mlen]) 90eda14cbcSMatt Macy break; 91eda14cbcSMatt Macy *dst++ = ((mlen - MATCH_MIN) << (NBBY - MATCH_BITS)) | 92eda14cbcSMatt Macy (offset >> NBBY); 93eda14cbcSMatt Macy *dst++ = (uchar_t)offset; 94eda14cbcSMatt Macy src += mlen; 95eda14cbcSMatt Macy } else { 96eda14cbcSMatt Macy *dst++ = *src++; 97eda14cbcSMatt Macy } 98eda14cbcSMatt Macy } 99eda14cbcSMatt Macy 100eda14cbcSMatt Macy kmem_free(lempel, LEMPEL_SIZE * sizeof (uint16_t)); 101eda14cbcSMatt Macy return (dst - (uchar_t *)d_start); 102eda14cbcSMatt Macy } 103eda14cbcSMatt Macy 104*e2df9bb4SMartin Matuska static int 105*e2df9bb4SMartin Matuska zfs_lzjb_decompress_buf(void *s_start, void *d_start, 106*e2df9bb4SMartin Matuska size_t s_len, size_t d_len, int n) 107eda14cbcSMatt Macy { 108e92ffd9bSMartin Matuska (void) s_len, (void) n; 109eda14cbcSMatt Macy uchar_t *src = s_start; 110eda14cbcSMatt Macy uchar_t *dst = d_start; 111eda14cbcSMatt Macy uchar_t *d_end = (uchar_t *)d_start + d_len; 112eda14cbcSMatt Macy uchar_t *cpy; 113eda14cbcSMatt Macy uchar_t copymap = 0; 114eda14cbcSMatt Macy int copymask = 1 << (NBBY - 1); 115eda14cbcSMatt Macy 116eda14cbcSMatt Macy while (dst < d_end) { 117eda14cbcSMatt Macy if ((copymask <<= 1) == (1 << NBBY)) { 118eda14cbcSMatt Macy copymask = 1; 119eda14cbcSMatt Macy copymap = *src++; 120eda14cbcSMatt Macy } 121eda14cbcSMatt Macy if (copymap & copymask) { 122eda14cbcSMatt Macy int mlen = (src[0] >> (NBBY - MATCH_BITS)) + MATCH_MIN; 123eda14cbcSMatt Macy int offset = ((src[0] << NBBY) | src[1]) & OFFSET_MASK; 124eda14cbcSMatt Macy src += 2; 125eda14cbcSMatt Macy if ((cpy = dst - offset) < (uchar_t *)d_start) 126eda14cbcSMatt Macy return (-1); 127eda14cbcSMatt Macy while (--mlen >= 0 && dst < d_end) 128eda14cbcSMatt Macy *dst++ = *cpy++; 129eda14cbcSMatt Macy } else { 130eda14cbcSMatt Macy *dst++ = *src++; 131eda14cbcSMatt Macy } 132eda14cbcSMatt Macy } 133eda14cbcSMatt Macy return (0); 134eda14cbcSMatt Macy } 135*e2df9bb4SMartin Matuska 136*e2df9bb4SMartin Matuska ZFS_COMPRESS_WRAP_DECL(zfs_lzjb_compress) 137*e2df9bb4SMartin Matuska ZFS_DECOMPRESS_WRAP_DECL(zfs_lzjb_decompress) 138