diff options
author | Nick Terrell <terrelln@fb.com> | 2017-08-04 23:19:17 +0300 |
---|---|---|
committer | Chris Mason <clm@fb.com> | 2017-08-15 19:02:07 +0300 |
commit | 5d2405227a9eaea48e8cc95756a06d407b11f141 (patch) | |
tree | e277dff5d00014f32ab1810eacdeaab97f53cf67 /include/linux | |
parent | ef954844c7ace62f773f4f23e28d2d915adc419f (diff) | |
download | linux-5d2405227a9eaea48e8cc95756a06d407b11f141.tar.xz |
lib: Add xxhash module
Adds xxhash kernel module with xxh32 and xxh64 hashes. xxhash is an
extremely fast non-cryptographic hash algorithm for checksumming.
The zstd compression and decompression modules added in the next patch
require xxhash. I extracted it out from zstd since it is useful on its
own. I copied the code from the upstream XXHash source repository and
translated it into kernel style. I ran benchmarks and tests in the kernel
and tests in userland.
I benchmarked xxhash as a special character device. I ran in four modes,
no-op, xxh32, xxh64, and crc32. The no-op mode simply copies the data to
kernel space and ignores it. The xxh32, xxh64, and crc32 modes compute
hashes on the copied data. I also ran it with four different buffer sizes.
The benchmark file is located in the upstream zstd source repository under
`contrib/linux-kernel/xxhash_test.c` [1].
I ran the benchmarks on a Ubuntu 14.04 VM with 2 cores and 4 GiB of RAM.
The VM is running on a MacBook Pro with a 3.1 GHz Intel Core i7 processor,
16 GB of RAM, and a SSD. I benchmarked using the file `filesystem.squashfs`
from `ubuntu-16.10-desktop-amd64.iso`, which is 1,536,217,088 B large.
Run the following commands for the benchmark:
modprobe xxhash_test
mknod xxhash_test c 245 0
time cp filesystem.squashfs xxhash_test
The time is reported by the time of the userland `cp`.
The GB/s is computed with
1,536,217,008 B / time(buffer size, hash)
which includes the time to copy from userland.
The Normalized GB/s is computed with
1,536,217,088 B / (time(buffer size, hash) - time(buffer size, none)).
| Buffer Size (B) | Hash | Time (s) | GB/s | Adjusted GB/s |
|-----------------|-------|----------|------|---------------|
| 1024 | none | 0.408 | 3.77 | - |
| 1024 | xxh32 | 0.649 | 2.37 | 6.37 |
| 1024 | xxh64 | 0.542 | 2.83 | 11.46 |
| 1024 | crc32 | 1.290 | 1.19 | 1.74 |
| 4096 | none | 0.380 | 4.04 | - |
| 4096 | xxh32 | 0.645 | 2.38 | 5.79 |
| 4096 | xxh64 | 0.500 | 3.07 | 12.80 |
| 4096 | crc32 | 1.168 | 1.32 | 1.95 |
| 8192 | none | 0.351 | 4.38 | - |
| 8192 | xxh32 | 0.614 | 2.50 | 5.84 |
| 8192 | xxh64 | 0.464 | 3.31 | 13.60 |
| 8192 | crc32 | 1.163 | 1.32 | 1.89 |
| 16384 | none | 0.346 | 4.43 | - |
| 16384 | xxh32 | 0.590 | 2.60 | 6.30 |
| 16384 | xxh64 | 0.466 | 3.30 | 12.80 |
| 16384 | crc32 | 1.183 | 1.30 | 1.84 |
Tested in userland using the test-suite in the zstd repo under
`contrib/linux-kernel/test/XXHashUserlandTest.cpp` [2] by mocking the
kernel functions. A line in each branch of every function in `xxhash.c`
was commented out to ensure that the test-suite fails. Additionally
tested while testing zstd and with SMHasher [3].
[1] https://phabricator.intern.facebook.com/P57526246
[2] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/test/XXHashUserlandTest.cpp
[3] https://github.com/aappleby/smhasher
zstd source repository: https://github.com/facebook/zstd
XXHash source repository: https://github.com/cyan4973/xxhash
Signed-off-by: Nick Terrell <terrelln@fb.com>
Signed-off-by: Chris Mason <clm@fb.com>
Diffstat (limited to 'include/linux')
-rw-r--r-- | include/linux/xxhash.h | 236 |
1 files changed, 236 insertions, 0 deletions
diff --git a/include/linux/xxhash.h b/include/linux/xxhash.h new file mode 100644 index 000000000000..9e1f42cb57e9 --- /dev/null +++ b/include/linux/xxhash.h @@ -0,0 +1,236 @@ +/* + * xxHash - Extremely Fast Hash algorithm + * Copyright (C) 2012-2016, Yann Collet. + * + * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are + * met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following disclaimer + * in the documentation and/or other materials provided with the + * distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + * This program is free software; you can redistribute it and/or modify it under + * the terms of the GNU General Public License version 2 as published by the + * Free Software Foundation. This program is dual-licensed; you may select + * either version 2 of the GNU General Public License ("GPL") or BSD license + * ("BSD"). + * + * You can contact the author at: + * - xxHash homepage: http://cyan4973.github.io/xxHash/ + * - xxHash source repository: https://github.com/Cyan4973/xxHash + */ + +/* + * Notice extracted from xxHash homepage: + * + * xxHash is an extremely fast Hash algorithm, running at RAM speed limits. + * It also successfully passes all tests from the SMHasher suite. + * + * Comparison (single thread, Windows Seven 32 bits, using SMHasher on a Core 2 + * Duo @3GHz) + * + * Name Speed Q.Score Author + * xxHash 5.4 GB/s 10 + * CrapWow 3.2 GB/s 2 Andrew + * MumurHash 3a 2.7 GB/s 10 Austin Appleby + * SpookyHash 2.0 GB/s 10 Bob Jenkins + * SBox 1.4 GB/s 9 Bret Mulvey + * Lookup3 1.2 GB/s 9 Bob Jenkins + * SuperFastHash 1.2 GB/s 1 Paul Hsieh + * CityHash64 1.05 GB/s 10 Pike & Alakuijala + * FNV 0.55 GB/s 5 Fowler, Noll, Vo + * CRC32 0.43 GB/s 9 + * MD5-32 0.33 GB/s 10 Ronald L. Rivest + * SHA1-32 0.28 GB/s 10 + * + * Q.Score is a measure of quality of the hash function. + * It depends on successfully passing SMHasher test set. + * 10 is a perfect score. + * + * A 64-bits version, named xxh64 offers much better speed, + * but for 64-bits applications only. + * Name Speed on 64 bits Speed on 32 bits + * xxh64 13.8 GB/s 1.9 GB/s + * xxh32 6.8 GB/s 6.0 GB/s + */ + +#ifndef XXHASH_H +#define XXHASH_H + +#include <linux/types.h> + +/*-**************************** + * Simple Hash Functions + *****************************/ + +/** + * xxh32() - calculate the 32-bit hash of the input with a given seed. + * + * @input: The data to hash. + * @length: The length of the data to hash. + * @seed: The seed can be used to alter the result predictably. + * + * Speed on Core 2 Duo @ 3 GHz (single thread, SMHasher benchmark) : 5.4 GB/s + * + * Return: The 32-bit hash of the data. + */ +uint32_t xxh32(const void *input, size_t length, uint32_t seed); + +/** + * xxh64() - calculate the 64-bit hash of the input with a given seed. + * + * @input: The data to hash. + * @length: The length of the data to hash. + * @seed: The seed can be used to alter the result predictably. + * + * This function runs 2x faster on 64-bit systems, but slower on 32-bit systems. + * + * Return: The 64-bit hash of the data. + */ +uint64_t xxh64(const void *input, size_t length, uint64_t seed); + +/*-**************************** + * Streaming Hash Functions + *****************************/ + +/* + * These definitions are only meant to allow allocation of XXH state + * statically, on stack, or in a struct for example. + * Do not use members directly. + */ + +/** + * struct xxh32_state - private xxh32 state, do not use members directly + */ +struct xxh32_state { + uint32_t total_len_32; + uint32_t large_len; + uint32_t v1; + uint32_t v2; + uint32_t v3; + uint32_t v4; + uint32_t mem32[4]; + uint32_t memsize; +}; + +/** + * struct xxh32_state - private xxh64 state, do not use members directly + */ +struct xxh64_state { + uint64_t total_len; + uint64_t v1; + uint64_t v2; + uint64_t v3; + uint64_t v4; + uint64_t mem64[4]; + uint32_t memsize; +}; + +/** + * xxh32_reset() - reset the xxh32 state to start a new hashing operation + * + * @state: The xxh32 state to reset. + * @seed: Initialize the hash state with this seed. + * + * Call this function on any xxh32_state to prepare for a new hashing operation. + */ +void xxh32_reset(struct xxh32_state *state, uint32_t seed); + +/** + * xxh32_update() - hash the data given and update the xxh32 state + * + * @state: The xxh32 state to update. + * @input: The data to hash. + * @length: The length of the data to hash. + * + * After calling xxh32_reset() call xxh32_update() as many times as necessary. + * + * Return: Zero on success, otherwise an error code. + */ +int xxh32_update(struct xxh32_state *state, const void *input, size_t length); + +/** + * xxh32_digest() - produce the current xxh32 hash + * + * @state: Produce the current xxh32 hash of this state. + * + * A hash value can be produced at any time. It is still possible to continue + * inserting input into the hash state after a call to xxh32_digest(), and + * generate new hashes later on, by calling xxh32_digest() again. + * + * Return: The xxh32 hash stored in the state. + */ +uint32_t xxh32_digest(const struct xxh32_state *state); + +/** + * xxh64_reset() - reset the xxh64 state to start a new hashing operation + * + * @state: The xxh64 state to reset. + * @seed: Initialize the hash state with this seed. + */ +void xxh64_reset(struct xxh64_state *state, uint64_t seed); + +/** + * xxh64_update() - hash the data given and update the xxh64 state + * @state: The xxh64 state to update. + * @input: The data to hash. + * @length: The length of the data to hash. + * + * After calling xxh64_reset() call xxh64_update() as many times as necessary. + * + * Return: Zero on success, otherwise an error code. + */ +int xxh64_update(struct xxh64_state *state, const void *input, size_t length); + +/** + * xxh64_digest() - produce the current xxh64 hash + * + * @state: Produce the current xxh64 hash of this state. + * + * A hash value can be produced at any time. It is still possible to continue + * inserting input into the hash state after a call to xxh64_digest(), and + * generate new hashes later on, by calling xxh64_digest() again. + * + * Return: The xxh64 hash stored in the state. + */ +uint64_t xxh64_digest(const struct xxh64_state *state); + +/*-************************** + * Utils + ***************************/ + +/** + * xxh32_copy_state() - copy the source state into the destination state + * + * @src: The source xxh32 state. + * @dst: The destination xxh32 state. + */ +void xxh32_copy_state(struct xxh32_state *dst, const struct xxh32_state *src); + +/** + * xxh64_copy_state() - copy the source state into the destination state + * + * @src: The source xxh64 state. + * @dst: The destination xxh64 state. + */ +void xxh64_copy_state(struct xxh64_state *dst, const struct xxh64_state *src); + +#endif /* XXHASH_H */ |