linux/lib/zstd/common/mem.h

262 lines
6.3 KiB
C
Raw Normal View History

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every upstream release, so the kernel gets the latest bug fixes and performance improvements, and doesn't get 3 years out of date again.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] https://github.com/facebook/zstd/commit/20821a46f4122f9abd7c7b245d28162dde8129c9 [1] https://github.com/terrelln/linux/commit/e0fa481d0e3df26918da0a13749740a1f6777574 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>
2020-09-11 23:37:08 +00:00
/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */
/*
* 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.
*/
#ifndef MEM_H_MODULE
#define MEM_H_MODULE
/*-****************************************
* Dependencies
******************************************/
#include <linux/unaligned.h> /* get_unaligned, put_unaligned* */
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] https://github.com/facebook/zstd/commit/20821a46f4122f9abd7c7b245d28162dde8129c9 [1] https://github.com/terrelln/linux/commit/e0fa481d0e3df26918da0a13749740a1f6777574 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>
2020-09-11 23:37:08 +00:00
#include <linux/compiler.h> /* inline */
#include <linux/swab.h> /* swab32, swab64 */
#include <linux/types.h> /* size_t, ptrdiff_t */
#include "debug.h" /* DEBUG_STATIC_ASSERT */
/*-****************************************
* Compiler specifics
******************************************/
#define MEM_STATIC static inline
/*-**************************************************************
* Basic Types
*****************************************************************/
typedef uint8_t BYTE;
typedef uint8_t U8;
typedef int8_t S8;
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] https://github.com/facebook/zstd/commit/20821a46f4122f9abd7c7b245d28162dde8129c9 [1] https://github.com/terrelln/linux/commit/e0fa481d0e3df26918da0a13749740a1f6777574 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>
2020-09-11 23:37:08 +00:00
typedef uint16_t U16;
typedef int16_t S16;
typedef uint32_t U32;
typedef int32_t S32;
typedef uint64_t U64;
typedef int64_t S64;
/*-**************************************************************
* Memory I/O API
*****************************************************************/
/*=== Static platform detection ===*/
MEM_STATIC unsigned MEM_32bits(void);
MEM_STATIC unsigned MEM_64bits(void);
MEM_STATIC unsigned MEM_isLittleEndian(void);
/*=== Native unaligned read/write ===*/
MEM_STATIC U16 MEM_read16(const void* memPtr);
MEM_STATIC U32 MEM_read32(const void* memPtr);
MEM_STATIC U64 MEM_read64(const void* memPtr);
MEM_STATIC size_t MEM_readST(const void* memPtr);
MEM_STATIC void MEM_write16(void* memPtr, U16 value);
MEM_STATIC void MEM_write32(void* memPtr, U32 value);
MEM_STATIC void MEM_write64(void* memPtr, U64 value);
/*=== Little endian unaligned read/write ===*/
MEM_STATIC U16 MEM_readLE16(const void* memPtr);
MEM_STATIC U32 MEM_readLE24(const void* memPtr);
MEM_STATIC U32 MEM_readLE32(const void* memPtr);
MEM_STATIC U64 MEM_readLE64(const void* memPtr);
MEM_STATIC size_t MEM_readLEST(const void* memPtr);
MEM_STATIC void MEM_writeLE16(void* memPtr, U16 val);
MEM_STATIC void MEM_writeLE24(void* memPtr, U32 val);
MEM_STATIC void MEM_writeLE32(void* memPtr, U32 val32);
MEM_STATIC void MEM_writeLE64(void* memPtr, U64 val64);
MEM_STATIC void MEM_writeLEST(void* memPtr, size_t val);
/*=== Big endian unaligned read/write ===*/
MEM_STATIC U32 MEM_readBE32(const void* memPtr);
MEM_STATIC U64 MEM_readBE64(const void* memPtr);
MEM_STATIC size_t MEM_readBEST(const void* memPtr);
MEM_STATIC void MEM_writeBE32(void* memPtr, U32 val32);
MEM_STATIC void MEM_writeBE64(void* memPtr, U64 val64);
MEM_STATIC void MEM_writeBEST(void* memPtr, size_t val);
/*=== Byteswap ===*/
MEM_STATIC U32 MEM_swap32(U32 in);
MEM_STATIC U64 MEM_swap64(U64 in);
MEM_STATIC size_t MEM_swapST(size_t in);
/*-**************************************************************
* Memory I/O Implementation
*****************************************************************/
MEM_STATIC unsigned MEM_32bits(void)
{
return sizeof(size_t) == 4;
}
MEM_STATIC unsigned MEM_64bits(void)
{
return sizeof(size_t) == 8;
}
#if defined(__LITTLE_ENDIAN)
#define MEM_LITTLE_ENDIAN 1
#else
#define MEM_LITTLE_ENDIAN 0
#endif
MEM_STATIC unsigned MEM_isLittleEndian(void)
{
return MEM_LITTLE_ENDIAN;
}
MEM_STATIC U16 MEM_read16(const void *memPtr)
{
return get_unaligned((const U16 *)memPtr);
}
MEM_STATIC U32 MEM_read32(const void *memPtr)
{
return get_unaligned((const U32 *)memPtr);
}
MEM_STATIC U64 MEM_read64(const void *memPtr)
{
return get_unaligned((const U64 *)memPtr);
}
MEM_STATIC size_t MEM_readST(const void *memPtr)
{
return get_unaligned((const size_t *)memPtr);
}
MEM_STATIC void MEM_write16(void *memPtr, U16 value)
{
put_unaligned(value, (U16 *)memPtr);
}
MEM_STATIC void MEM_write32(void *memPtr, U32 value)
{
put_unaligned(value, (U32 *)memPtr);
}
MEM_STATIC void MEM_write64(void *memPtr, U64 value)
{
put_unaligned(value, (U64 *)memPtr);
}
/*=== Little endian r/w ===*/
MEM_STATIC U16 MEM_readLE16(const void *memPtr)
{
return get_unaligned_le16(memPtr);
}
MEM_STATIC void MEM_writeLE16(void *memPtr, U16 val)
{
put_unaligned_le16(val, memPtr);
}
MEM_STATIC U32 MEM_readLE24(const void *memPtr)
{
return MEM_readLE16(memPtr) + (((const BYTE *)memPtr)[2] << 16);
}
MEM_STATIC void MEM_writeLE24(void *memPtr, U32 val)
{
MEM_writeLE16(memPtr, (U16)val);
((BYTE *)memPtr)[2] = (BYTE)(val >> 16);
}
MEM_STATIC U32 MEM_readLE32(const void *memPtr)
{
return get_unaligned_le32(memPtr);
}
MEM_STATIC void MEM_writeLE32(void *memPtr, U32 val32)
{
put_unaligned_le32(val32, memPtr);
}
MEM_STATIC U64 MEM_readLE64(const void *memPtr)
{
return get_unaligned_le64(memPtr);
}
MEM_STATIC void MEM_writeLE64(void *memPtr, U64 val64)
{
put_unaligned_le64(val64, memPtr);
}
MEM_STATIC size_t MEM_readLEST(const void *memPtr)
{
if (MEM_32bits())
return (size_t)MEM_readLE32(memPtr);
else
return (size_t)MEM_readLE64(memPtr);
}
MEM_STATIC void MEM_writeLEST(void *memPtr, size_t val)
{
if (MEM_32bits())
MEM_writeLE32(memPtr, (U32)val);
else
MEM_writeLE64(memPtr, (U64)val);
}
/*=== Big endian r/w ===*/
MEM_STATIC U32 MEM_readBE32(const void *memPtr)
{
return get_unaligned_be32(memPtr);
}
MEM_STATIC void MEM_writeBE32(void *memPtr, U32 val32)
{
put_unaligned_be32(val32, memPtr);
}
MEM_STATIC U64 MEM_readBE64(const void *memPtr)
{
return get_unaligned_be64(memPtr);
}
MEM_STATIC void MEM_writeBE64(void *memPtr, U64 val64)
{
put_unaligned_be64(val64, memPtr);
}
MEM_STATIC size_t MEM_readBEST(const void *memPtr)
{
if (MEM_32bits())
return (size_t)MEM_readBE32(memPtr);
else
return (size_t)MEM_readBE64(memPtr);
}
MEM_STATIC void MEM_writeBEST(void *memPtr, size_t val)
{
if (MEM_32bits())
MEM_writeBE32(memPtr, (U32)val);
else
MEM_writeBE64(memPtr, (U64)val);
}
MEM_STATIC U32 MEM_swap32(U32 in)
{
return swab32(in);
}
MEM_STATIC U64 MEM_swap64(U64 in)
{
return swab64(in);
}
MEM_STATIC size_t MEM_swapST(size_t in)
{
if (MEM_32bits())
return (size_t)MEM_swap32((U32)in);
else
return (size_t)MEM_swap64((U64)in);
}
#endif /* MEM_H_MODULE */