73f3d1b48f
Add zstd compression and decompression kernel modules. zstd offers a wide varity of compression speed and quality trade-offs. It can compress at speeds approaching lz4, and quality approaching lzma. zstd decompressions at speeds more than twice as fast as zlib, and decompression speed remains roughly the same across all compression levels. The code was ported from the upstream zstd source repository. The `linux/zstd.h` header was modified to match linux kernel style. The cross-platform and allocation code was stripped out. Instead zstd requires the caller to pass a preallocated workspace. The source files were clang-formatted [1] to match the Linux Kernel style as much as possible. Otherwise, the code was unmodified. We would like to avoid as much further manual modification to the source code as possible, so it will be easier to keep the kernel zstd up to date. I benchmarked zstd compression as a special character device. I ran zstd and zlib compression at several levels, as well as performing no compression, which measure the time spent copying the data to kernel space. Data is passed to the compresser 4096 B at a time. The benchmark file is located in the upstream zstd source repository under `contrib/linux-kernel/zstd_compress_test.c` [2]. 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 `silesia.tar` [3], which is 211,988,480 B large. Run the following commands for the benchmark: sudo modprobe zstd_compress_test sudo mknod zstd_compress_test c 245 0 sudo cp silesia.tar zstd_compress_test The time is reported by the time of the userland `cp`. The MB/s is computed with 1,536,217,008 B / time(buffer size, hash) which includes the time to copy from userland. The Adjusted MB/s is computed with 1,536,217,088 B / (time(buffer size, hash) - time(buffer size, none)). The memory reported is the amount of memory the compressor requests. | Method | Size (B) | Time (s) | Ratio | MB/s | Adj MB/s | Mem (MB) | |----------|----------|----------|-------|---------|----------|----------| | none | 11988480 | 0.100 | 1 | 2119.88 | - | - | | zstd -1 | 73645762 | 1.044 | 2.878 | 203.05 | 224.56 | 1.23 | | zstd -3 | 66988878 | 1.761 | 3.165 | 120.38 | 127.63 | 2.47 | | zstd -5 | 65001259 | 2.563 | 3.261 | 82.71 | 86.07 | 2.86 | | zstd -10 | 60165346 | 13.242 | 3.523 | 16.01 | 16.13 | 13.22 | | zstd -15 | 58009756 | 47.601 | 3.654 | 4.45 | 4.46 | 21.61 | | zstd -19 | 54014593 | 102.835 | 3.925 | 2.06 | 2.06 | 60.15 | | zlib -1 | 77260026 | 2.895 | 2.744 | 73.23 | 75.85 | 0.27 | | zlib -3 | 72972206 | 4.116 | 2.905 | 51.50 | 52.79 | 0.27 | | zlib -6 | 68190360 | 9.633 | 3.109 | 22.01 | 22.24 | 0.27 | | zlib -9 | 67613382 | 22.554 | 3.135 | 9.40 | 9.44 | 0.27 | I benchmarked zstd decompression using the same method on the same machine. The benchmark file is located in the upstream zstd repo under `contrib/linux-kernel/zstd_decompress_test.c` [4]. The memory reported is the amount of memory required to decompress data compressed with the given compression level. If you know the maximum size of your input, you can reduce the memory usage of decompression irrespective of the compression level. | Method | Time (s) | MB/s | Adjusted MB/s | Memory (MB) | |----------|----------|---------|---------------|-------------| | none | 0.025 | 8479.54 | - | - | | zstd -1 | 0.358 | 592.15 | 636.60 | 0.84 | | zstd -3 | 0.396 | 535.32 | 571.40 | 1.46 | | zstd -5 | 0.396 | 535.32 | 571.40 | 1.46 | | zstd -10 | 0.374 | 566.81 | 607.42 | 2.51 | | zstd -15 | 0.379 | 559.34 | 598.84 | 4.61 | | zstd -19 | 0.412 | 514.54 | 547.77 | 8.80 | | zlib -1 | 0.940 | 225.52 | 231.68 | 0.04 | | zlib -3 | 0.883 | 240.08 | 247.07 | 0.04 | | zlib -6 | 0.844 | 251.17 | 258.84 | 0.04 | | zlib -9 | 0.837 | 253.27 | 287.64 | 0.04 | Tested in userland using the test-suite in the zstd repo under `contrib/linux-kernel/test/UserlandTest.cpp` [5] by mocking the kernel functions. Fuzz tested using libfuzzer [6] with the fuzz harnesses under `contrib/linux-kernel/test/{RoundTripCrash.c,DecompressCrash.c}` [7] [8] with ASAN, UBSAN, and MSAN. Additionaly, it was tested while testing the BtrFS and SquashFS patches coming next. [1] https://clang.llvm.org/docs/ClangFormat.html [2] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/zstd_compress_test.c [3] http://sun.aei.polsl.pl/~sdeor/index.php?page=silesia [4] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/zstd_decompress_test.c [5] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/test/UserlandTest.cpp [6] http://llvm.org/docs/LibFuzzer.html [7] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/test/RoundTripCrash.c [8] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/test/DecompressCrash.c zstd source repository: https://github.com/facebook/zstd Signed-off-by: Nick Terrell <terrelln@fb.com> Signed-off-by: Chris Mason <clm@fb.com>
76 lines
2.5 KiB
C
76 lines
2.5 KiB
C
/**
|
|
* Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
|
|
* All rights reserved.
|
|
*
|
|
* This source code is licensed under the BSD-style license found in the
|
|
* LICENSE file in the root directory of https://github.com/facebook/zstd.
|
|
* An additional grant of patent rights can be found in the PATENTS file in the
|
|
* same directory.
|
|
*
|
|
* 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").
|
|
*/
|
|
|
|
/*-*************************************
|
|
* Dependencies
|
|
***************************************/
|
|
#include "error_private.h"
|
|
#include "zstd_internal.h" /* declaration of ZSTD_isError, ZSTD_getErrorName, ZSTD_getErrorCode, ZSTD_getErrorString, ZSTD_versionNumber */
|
|
#include <linux/kernel.h>
|
|
|
|
/*=**************************************************************
|
|
* Custom allocator
|
|
****************************************************************/
|
|
|
|
#define stack_push(stack, size) \
|
|
({ \
|
|
void *const ptr = ZSTD_PTR_ALIGN((stack)->ptr); \
|
|
(stack)->ptr = (char *)ptr + (size); \
|
|
(stack)->ptr <= (stack)->end ? ptr : NULL; \
|
|
})
|
|
|
|
ZSTD_customMem ZSTD_initStack(void *workspace, size_t workspaceSize)
|
|
{
|
|
ZSTD_customMem stackMem = {ZSTD_stackAlloc, ZSTD_stackFree, workspace};
|
|
ZSTD_stack *stack = (ZSTD_stack *)workspace;
|
|
/* Verify preconditions */
|
|
if (!workspace || workspaceSize < sizeof(ZSTD_stack) || workspace != ZSTD_PTR_ALIGN(workspace)) {
|
|
ZSTD_customMem error = {NULL, NULL, NULL};
|
|
return error;
|
|
}
|
|
/* Initialize the stack */
|
|
stack->ptr = workspace;
|
|
stack->end = (char *)workspace + workspaceSize;
|
|
stack_push(stack, sizeof(ZSTD_stack));
|
|
return stackMem;
|
|
}
|
|
|
|
void *ZSTD_stackAllocAll(void *opaque, size_t *size)
|
|
{
|
|
ZSTD_stack *stack = (ZSTD_stack *)opaque;
|
|
*size = (BYTE const *)stack->end - (BYTE *)ZSTD_PTR_ALIGN(stack->ptr);
|
|
return stack_push(stack, *size);
|
|
}
|
|
|
|
void *ZSTD_stackAlloc(void *opaque, size_t size)
|
|
{
|
|
ZSTD_stack *stack = (ZSTD_stack *)opaque;
|
|
return stack_push(stack, size);
|
|
}
|
|
void ZSTD_stackFree(void *opaque, void *address)
|
|
{
|
|
(void)opaque;
|
|
(void)address;
|
|
}
|
|
|
|
void *ZSTD_malloc(size_t size, ZSTD_customMem customMem) { return customMem.customAlloc(customMem.opaque, size); }
|
|
|
|
void ZSTD_free(void *ptr, ZSTD_customMem customMem)
|
|
{
|
|
if (ptr != NULL)
|
|
customMem.customFree(customMem.opaque, ptr);
|
|
}
|