linux-stable/lib/zstd/compress/zstd_compress_literals.c
Nick Terrell e0c1b49f5b lib: zstd: Upgrade to latest upstream zstd version 1.4.10
Upgrade to the latest upstream zstd version 1.4.10.

This patch is 100% generated from upstream zstd commit 20821a46f412 [0].

This patch is very large because it is transitioning from the custom
kernel zstd to using upstream directly. The new zstd follows upstreams
file structure which is different. Future update patches will be much
smaller because they will only contain the changes from one upstream
zstd release.

As an aid for review I've created a commit [1] that shows the diff
between upstream zstd as-is (which doesn't compile), and the zstd
code imported in this patch. The verion of zstd in this patch is
generated from upstream with changes applied by automation to replace
upstreams libc dependencies, remove unnecessary portability macros,
replace `/**` comments with `/*` comments, and use the kernel's xxhash
instead of bundling it.

The benefits of this patch are as follows:
1. Using upstream directly with automated script to generate kernel
   code. This allows us to update the kernel every upstream release, so
   the kernel gets the latest bug fixes and performance improvements,
   and doesn't get 3 years out of date again. The automation and the
   translated code are tested every upstream commit to ensure it
   continues to work.
2. Upgrades from a custom zstd based on 1.3.1 to 1.4.10, getting 3 years
   of performance improvements and bug fixes. On x86_64 I've measured
   15% faster BtrFS and SquashFS decompression+read speeds, 35% faster
   kernel decompression, and 30% faster ZRAM decompression+read speeds.
3. Zstd-1.4.10 supports negative compression levels, which allow zstd to
   match or subsume lzo's performance.
4. Maintains the same kernel-specific wrapper API, so no callers have to
   be modified with zstd version updates.

One concern that was brought up was stack usage. Upstream zstd had
already removed most of its heavy stack usage functions, but I just
removed the last functions that allocate arrays on the stack. I've
measured the high water mark for both compression and decompression
before and after this patch. Decompression is approximately neutral,
using about 1.2KB of stack space. Compression levels up to 3 regressed
from 1.4KB -> 1.6KB, and higher compression levels regressed from 1.5KB
-> 2KB. We've added unit tests upstream to prevent further regression.
I believe that this is a reasonable increase, and if it does end up
causing problems, this commit can be cleanly reverted, because it only
touches zstd.

I chose the bulk update instead of replaying upstream commits because
there have been ~3500 upstream commits since the 1.3.1 release, zstd
wasn't ready to be used in the kernel as-is before a month ago, and not
all upstream zstd commits build. The bulk update preserves bisectablity
because bugs can be bisected to the zstd version update. At that point
the update can be reverted, and we can work with upstream to find and
fix the bug.

Note that upstream zstd release 1.4.10 doesn't exist yet. I have cut a
staging branch at 20821a46f412 [0] and will apply any changes requested
to the staging branch. Once we're ready to merge this update I will cut
a zstd release at the commit we merge, so we have a known zstd release
in the kernel.

The implementation of the kernel API is contained in
zstd_compress_module.c and zstd_decompress_module.c.

[0] 20821a46f4
[1] e0fa481d0e

Signed-off-by: Nick Terrell <terrelln@fb.com>
Tested By: Paul Jones <paul@pauljones.id.au>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com> # LLVM/Clang v13.0.0 on x86-64
Tested-by: Jean-Denis Girard <jd.girard@sysnux.pf>
2021-11-08 16:55:32 -08:00

158 lines
6.1 KiB
C

/*
* Copyright (c) Yann Collet, Facebook, Inc.
* All rights reserved.
*
* This source code is licensed under both the BSD-style license (found in the
* LICENSE file in the root directory of this source tree) and the GPLv2 (found
* in the COPYING file in the root directory of this source tree).
* You may select, at your option, one of the above-listed licenses.
*/
/*-*************************************
* Dependencies
***************************************/
#include "zstd_compress_literals.h"
size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
{
BYTE* const ostart = (BYTE*)dst;
U32 const flSize = 1 + (srcSize>31) + (srcSize>4095);
RETURN_ERROR_IF(srcSize + flSize > dstCapacity, dstSize_tooSmall, "");
switch(flSize)
{
case 1: /* 2 - 1 - 5 */
ostart[0] = (BYTE)((U32)set_basic + (srcSize<<3));
break;
case 2: /* 2 - 2 - 12 */
MEM_writeLE16(ostart, (U16)((U32)set_basic + (1<<2) + (srcSize<<4)));
break;
case 3: /* 2 - 2 - 20 */
MEM_writeLE32(ostart, (U32)((U32)set_basic + (3<<2) + (srcSize<<4)));
break;
default: /* not necessary : flSize is {1,2,3} */
assert(0);
}
ZSTD_memcpy(ostart + flSize, src, srcSize);
DEBUGLOG(5, "Raw literals: %u -> %u", (U32)srcSize, (U32)(srcSize + flSize));
return srcSize + flSize;
}
size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
{
BYTE* const ostart = (BYTE*)dst;
U32 const flSize = 1 + (srcSize>31) + (srcSize>4095);
(void)dstCapacity; /* dstCapacity already guaranteed to be >=4, hence large enough */
switch(flSize)
{
case 1: /* 2 - 1 - 5 */
ostart[0] = (BYTE)((U32)set_rle + (srcSize<<3));
break;
case 2: /* 2 - 2 - 12 */
MEM_writeLE16(ostart, (U16)((U32)set_rle + (1<<2) + (srcSize<<4)));
break;
case 3: /* 2 - 2 - 20 */
MEM_writeLE32(ostart, (U32)((U32)set_rle + (3<<2) + (srcSize<<4)));
break;
default: /* not necessary : flSize is {1,2,3} */
assert(0);
}
ostart[flSize] = *(const BYTE*)src;
DEBUGLOG(5, "RLE literals: %u -> %u", (U32)srcSize, (U32)flSize + 1);
return flSize+1;
}
size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf,
ZSTD_hufCTables_t* nextHuf,
ZSTD_strategy strategy, int disableLiteralCompression,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
void* entropyWorkspace, size_t entropyWorkspaceSize,
const int bmi2)
{
size_t const minGain = ZSTD_minGain(srcSize, strategy);
size_t const lhSize = 3 + (srcSize >= 1 KB) + (srcSize >= 16 KB);
BYTE* const ostart = (BYTE*)dst;
U32 singleStream = srcSize < 256;
symbolEncodingType_e hType = set_compressed;
size_t cLitSize;
DEBUGLOG(5,"ZSTD_compressLiterals (disableLiteralCompression=%i srcSize=%u)",
disableLiteralCompression, (U32)srcSize);
/* Prepare nextEntropy assuming reusing the existing table */
ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
if (disableLiteralCompression)
return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
/* small ? don't even attempt compression (speed opt) */
# define COMPRESS_LITERALS_SIZE_MIN 63
{ size_t const minLitSize = (prevHuf->repeatMode == HUF_repeat_valid) ? 6 : COMPRESS_LITERALS_SIZE_MIN;
if (srcSize <= minLitSize) return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
}
RETURN_ERROR_IF(dstCapacity < lhSize+1, dstSize_tooSmall, "not enough space for compression");
{ HUF_repeat repeat = prevHuf->repeatMode;
int const preferRepeat = strategy < ZSTD_lazy ? srcSize <= 1024 : 0;
if (repeat == HUF_repeat_valid && lhSize == 3) singleStream = 1;
cLitSize = singleStream ?
HUF_compress1X_repeat(
ostart+lhSize, dstCapacity-lhSize, src, srcSize,
HUF_SYMBOLVALUE_MAX, HUF_TABLELOG_DEFAULT, entropyWorkspace, entropyWorkspaceSize,
(HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2) :
HUF_compress4X_repeat(
ostart+lhSize, dstCapacity-lhSize, src, srcSize,
HUF_SYMBOLVALUE_MAX, HUF_TABLELOG_DEFAULT, entropyWorkspace, entropyWorkspaceSize,
(HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2);
if (repeat != HUF_repeat_none) {
/* reused the existing table */
DEBUGLOG(5, "Reusing previous huffman table");
hType = set_repeat;
}
}
if ((cLitSize==0) | (cLitSize >= srcSize - minGain) | ERR_isError(cLitSize)) {
ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
}
if (cLitSize==1) {
ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
return ZSTD_compressRleLiteralsBlock(dst, dstCapacity, src, srcSize);
}
if (hType == set_compressed) {
/* using a newly constructed table */
nextHuf->repeatMode = HUF_repeat_check;
}
/* Build header */
switch(lhSize)
{
case 3: /* 2 - 2 - 10 - 10 */
{ U32 const lhc = hType + ((!singleStream) << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<14);
MEM_writeLE24(ostart, lhc);
break;
}
case 4: /* 2 - 2 - 14 - 14 */
{ U32 const lhc = hType + (2 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<18);
MEM_writeLE32(ostart, lhc);
break;
}
case 5: /* 2 - 2 - 18 - 18 */
{ U32 const lhc = hType + (3 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<22);
MEM_writeLE32(ostart, lhc);
ostart[4] = (BYTE)(cLitSize >> 10);
break;
}
default: /* not possible : lhSize is {3,4,5} */
assert(0);
}
DEBUGLOG(5, "Compressed literals: %u -> %u", (U32)srcSize, (U32)(lhSize+cLitSize));
return lhSize+cLitSize;
}