summaryrefslogtreecommitdiffstats
path: root/lib/zstd/compress/zstd_lazy.h
diff options
context:
space:
mode:
authorNick Terrell <terrelln@meta.com>2025-03-08 12:09:33 -0800
committerNick Terrell <terrelln@meta.com>2025-03-13 13:25:58 -0700
commit65d1f5507ed2c78c64fce40e44e5574a9419eb09 (patch)
tree4a1b819db2ea7f2a322e9bcc7582d946d0a4ea29 /lib/zstd/compress/zstd_lazy.h
parent7eb172143d5508b4da468ed59ee857c6e5e01da6 (diff)
downloadlinux-65d1f5507ed2c78c64fce40e44e5574a9419eb09.tar.gz
linux-65d1f5507ed2c78c64fce40e44e5574a9419eb09.tar.bz2
linux-65d1f5507ed2c78c64fce40e44e5574a9419eb09.zip
zstd: Import upstream v1.5.7
In addition to keeping the kernel's copy of zstd up to date, this update was requested by Intel to expose upstream's APIs that allow QAT to accelerate the LZ match finding stage of Zstd. This patch is imported from the upstream tag v1.5.7-kernel [0], which is signed with upstream's signing key EF8FE99528B52FFD [1]. It was imported from upstream using this command: export ZSTD=/path/to/repo/zstd/ export LINUX=/path/to/repo/linux/ cd "$ZSTD/contrib/linux-kernel" git checkout v1.5.7-kernel make import LINUX="$LINUX" This patch has been tested on x86-64, and has been boot tested with a zstd compressed kernel & initramfs on i386 and aarch64. I benchmarked the patch on x86-64 with gcc-14.2.1 on an Intel i9-9900K by measruing the performance of compressed filesystem reads and writes. Component, Level, Size delta, C. time delta, D. time delta Btrfs , 1, +0.00%, -6.1%, +1.4% Btrfs , 3, +0.00%, -9.8%, +3.0% Btrfs , 5, +0.00%, +1.7%, +1.4% Btrfs , 7, +0.00%, -1.9%, +2.7% Btrfs , 9, +0.00%, -3.4%, +3.7% Btrfs , 15, +0.00%, -0.3%, +3.6% SquashFS , 1, +0.00%, N/A, +1.9% The major changes that impact the kernel use cases for each version are: v1.5.7: https://github.com/facebook/zstd/releases/tag/v1.5.7 * Add zstd_compress_sequences_and_literals() for use by Intel's QAT driver to implement Zstd compression acceleration in the kernel. * Fix an underflow bug in 32-bit builds that can cause data corruption when processing more than 4GB of data with a single `ZSTD_CCtx` object, when an input crosses the 4GB boundry. I don't believe this impacts any current kernel use cases, because the `ZSTD_CCtx` is typically reconstructed between compressions. * Levels 1-4 see 5-10% compression speed improvements for inputs smaller than 128KB. v1.5.6: https://github.com/facebook/zstd/releases/tag/v1.5.6 * Improved compression ratio for the highest compression levels. I don't expect these see much use however, due to their slow speeds. v1.5.5: https://github.com/facebook/zstd/releases/tag/v1.5.5 * Fix a rare corruption bug that can trigger on levels 13 and above. * Improve compression speed of levels 5-11 on incompressible data. v1.5.4: https://github.com/facebook/zstd/releases/tag/v1.5.4 * Improve copmression speed of levels 5-11 on ARM. * Improve dictionary compression speed. Signed-off-by: Nick Terrell <terrelln@fb.com>
Diffstat (limited to 'lib/zstd/compress/zstd_lazy.h')
-rw-r--r--lib/zstd/compress/zstd_lazy.h195
1 files changed, 135 insertions, 60 deletions
diff --git a/lib/zstd/compress/zstd_lazy.h b/lib/zstd/compress/zstd_lazy.h
index e5bdf4df8dde..987a036d8bde 100644
--- a/lib/zstd/compress/zstd_lazy.h
+++ b/lib/zstd/compress/zstd_lazy.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */
/*
- * Copyright (c) Yann Collet, Facebook, Inc.
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
* All rights reserved.
*
* This source code is licensed under both the BSD-style license (found in the
@@ -11,7 +12,6 @@
#ifndef ZSTD_LAZY_H
#define ZSTD_LAZY_H
-
#include "zstd_compress_internal.h"
/*
@@ -22,98 +22,173 @@
*/
#define ZSTD_LAZY_DDSS_BUCKET_LOG 2
-U32 ZSTD_insertAndFindFirstIndex(ZSTD_matchState_t* ms, const BYTE* ip);
-void ZSTD_row_update(ZSTD_matchState_t* const ms, const BYTE* ip);
+#define ZSTD_ROW_HASH_TAG_BITS 8 /* nb bits to use for the tag */
+
+#if !defined(ZSTD_EXCLUDE_GREEDY_BLOCK_COMPRESSOR) \
+ || !defined(ZSTD_EXCLUDE_LAZY_BLOCK_COMPRESSOR) \
+ || !defined(ZSTD_EXCLUDE_LAZY2_BLOCK_COMPRESSOR) \
+ || !defined(ZSTD_EXCLUDE_BTLAZY2_BLOCK_COMPRESSOR)
+U32 ZSTD_insertAndFindFirstIndex(ZSTD_MatchState_t* ms, const BYTE* ip);
+void ZSTD_row_update(ZSTD_MatchState_t* const ms, const BYTE* ip);
-void ZSTD_dedicatedDictSearch_lazy_loadDictionary(ZSTD_matchState_t* ms, const BYTE* const ip);
+void ZSTD_dedicatedDictSearch_lazy_loadDictionary(ZSTD_MatchState_t* ms, const BYTE* const ip);
void ZSTD_preserveUnsortedMark (U32* const table, U32 const size, U32 const reducerValue); /*! used in ZSTD_reduceIndex(). preemptively increase value of ZSTD_DUBT_UNSORTED_MARK */
+#endif
-size_t ZSTD_compressBlock_btlazy2(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+#ifndef ZSTD_EXCLUDE_GREEDY_BLOCK_COMPRESSOR
+size_t ZSTD_compressBlock_greedy(
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
-size_t ZSTD_compressBlock_lazy2(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+size_t ZSTD_compressBlock_greedy_row(
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
-size_t ZSTD_compressBlock_lazy(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+size_t ZSTD_compressBlock_greedy_dictMatchState(
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
-size_t ZSTD_compressBlock_greedy(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+size_t ZSTD_compressBlock_greedy_dictMatchState_row(
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
-size_t ZSTD_compressBlock_lazy2_row(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+size_t ZSTD_compressBlock_greedy_dedicatedDictSearch(
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
-size_t ZSTD_compressBlock_lazy_row(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+size_t ZSTD_compressBlock_greedy_dedicatedDictSearch_row(
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
-size_t ZSTD_compressBlock_greedy_row(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+size_t ZSTD_compressBlock_greedy_extDict(
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+ void const* src, size_t srcSize);
+size_t ZSTD_compressBlock_greedy_extDict_row(
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
-size_t ZSTD_compressBlock_btlazy2_dictMatchState(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+#define ZSTD_COMPRESSBLOCK_GREEDY ZSTD_compressBlock_greedy
+#define ZSTD_COMPRESSBLOCK_GREEDY_ROW ZSTD_compressBlock_greedy_row
+#define ZSTD_COMPRESSBLOCK_GREEDY_DICTMATCHSTATE ZSTD_compressBlock_greedy_dictMatchState
+#define ZSTD_COMPRESSBLOCK_GREEDY_DICTMATCHSTATE_ROW ZSTD_compressBlock_greedy_dictMatchState_row
+#define ZSTD_COMPRESSBLOCK_GREEDY_DEDICATEDDICTSEARCH ZSTD_compressBlock_greedy_dedicatedDictSearch
+#define ZSTD_COMPRESSBLOCK_GREEDY_DEDICATEDDICTSEARCH_ROW ZSTD_compressBlock_greedy_dedicatedDictSearch_row
+#define ZSTD_COMPRESSBLOCK_GREEDY_EXTDICT ZSTD_compressBlock_greedy_extDict
+#define ZSTD_COMPRESSBLOCK_GREEDY_EXTDICT_ROW ZSTD_compressBlock_greedy_extDict_row
+#else
+#define ZSTD_COMPRESSBLOCK_GREEDY NULL
+#define ZSTD_COMPRESSBLOCK_GREEDY_ROW NULL
+#define ZSTD_COMPRESSBLOCK_GREEDY_DICTMATCHSTATE NULL
+#define ZSTD_COMPRESSBLOCK_GREEDY_DICTMATCHSTATE_ROW NULL
+#define ZSTD_COMPRESSBLOCK_GREEDY_DEDICATEDDICTSEARCH NULL
+#define ZSTD_COMPRESSBLOCK_GREEDY_DEDICATEDDICTSEARCH_ROW NULL
+#define ZSTD_COMPRESSBLOCK_GREEDY_EXTDICT NULL
+#define ZSTD_COMPRESSBLOCK_GREEDY_EXTDICT_ROW NULL
+#endif
+
+#ifndef ZSTD_EXCLUDE_LAZY_BLOCK_COMPRESSOR
+size_t ZSTD_compressBlock_lazy(
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
-size_t ZSTD_compressBlock_lazy2_dictMatchState(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+size_t ZSTD_compressBlock_lazy_row(
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
size_t ZSTD_compressBlock_lazy_dictMatchState(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
- void const* src, size_t srcSize);
-size_t ZSTD_compressBlock_greedy_dictMatchState(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
- void const* src, size_t srcSize);
-size_t ZSTD_compressBlock_lazy2_dictMatchState_row(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
size_t ZSTD_compressBlock_lazy_dictMatchState_row(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
-size_t ZSTD_compressBlock_greedy_dictMatchState_row(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+size_t ZSTD_compressBlock_lazy_dedicatedDictSearch(
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
-
-size_t ZSTD_compressBlock_lazy2_dedicatedDictSearch(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+size_t ZSTD_compressBlock_lazy_dedicatedDictSearch_row(
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
-size_t ZSTD_compressBlock_lazy_dedicatedDictSearch(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+size_t ZSTD_compressBlock_lazy_extDict(
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
-size_t ZSTD_compressBlock_greedy_dedicatedDictSearch(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+size_t ZSTD_compressBlock_lazy_extDict_row(
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
-size_t ZSTD_compressBlock_lazy2_dedicatedDictSearch_row(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+
+#define ZSTD_COMPRESSBLOCK_LAZY ZSTD_compressBlock_lazy
+#define ZSTD_COMPRESSBLOCK_LAZY_ROW ZSTD_compressBlock_lazy_row
+#define ZSTD_COMPRESSBLOCK_LAZY_DICTMATCHSTATE ZSTD_compressBlock_lazy_dictMatchState
+#define ZSTD_COMPRESSBLOCK_LAZY_DICTMATCHSTATE_ROW ZSTD_compressBlock_lazy_dictMatchState_row
+#define ZSTD_COMPRESSBLOCK_LAZY_DEDICATEDDICTSEARCH ZSTD_compressBlock_lazy_dedicatedDictSearch
+#define ZSTD_COMPRESSBLOCK_LAZY_DEDICATEDDICTSEARCH_ROW ZSTD_compressBlock_lazy_dedicatedDictSearch_row
+#define ZSTD_COMPRESSBLOCK_LAZY_EXTDICT ZSTD_compressBlock_lazy_extDict
+#define ZSTD_COMPRESSBLOCK_LAZY_EXTDICT_ROW ZSTD_compressBlock_lazy_extDict_row
+#else
+#define ZSTD_COMPRESSBLOCK_LAZY NULL
+#define ZSTD_COMPRESSBLOCK_LAZY_ROW NULL
+#define ZSTD_COMPRESSBLOCK_LAZY_DICTMATCHSTATE NULL
+#define ZSTD_COMPRESSBLOCK_LAZY_DICTMATCHSTATE_ROW NULL
+#define ZSTD_COMPRESSBLOCK_LAZY_DEDICATEDDICTSEARCH NULL
+#define ZSTD_COMPRESSBLOCK_LAZY_DEDICATEDDICTSEARCH_ROW NULL
+#define ZSTD_COMPRESSBLOCK_LAZY_EXTDICT NULL
+#define ZSTD_COMPRESSBLOCK_LAZY_EXTDICT_ROW NULL
+#endif
+
+#ifndef ZSTD_EXCLUDE_LAZY2_BLOCK_COMPRESSOR
+size_t ZSTD_compressBlock_lazy2(
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
-size_t ZSTD_compressBlock_lazy_dedicatedDictSearch_row(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+size_t ZSTD_compressBlock_lazy2_row(
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
-size_t ZSTD_compressBlock_greedy_dedicatedDictSearch_row(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+size_t ZSTD_compressBlock_lazy2_dictMatchState(
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
-
-size_t ZSTD_compressBlock_greedy_extDict(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+size_t ZSTD_compressBlock_lazy2_dictMatchState_row(
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
-size_t ZSTD_compressBlock_lazy_extDict(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+size_t ZSTD_compressBlock_lazy2_dedicatedDictSearch(
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+ void const* src, size_t srcSize);
+size_t ZSTD_compressBlock_lazy2_dedicatedDictSearch_row(
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
size_t ZSTD_compressBlock_lazy2_extDict(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
-size_t ZSTD_compressBlock_greedy_extDict_row(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+size_t ZSTD_compressBlock_lazy2_extDict_row(
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
-size_t ZSTD_compressBlock_lazy_extDict_row(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+
+#define ZSTD_COMPRESSBLOCK_LAZY2 ZSTD_compressBlock_lazy2
+#define ZSTD_COMPRESSBLOCK_LAZY2_ROW ZSTD_compressBlock_lazy2_row
+#define ZSTD_COMPRESSBLOCK_LAZY2_DICTMATCHSTATE ZSTD_compressBlock_lazy2_dictMatchState
+#define ZSTD_COMPRESSBLOCK_LAZY2_DICTMATCHSTATE_ROW ZSTD_compressBlock_lazy2_dictMatchState_row
+#define ZSTD_COMPRESSBLOCK_LAZY2_DEDICATEDDICTSEARCH ZSTD_compressBlock_lazy2_dedicatedDictSearch
+#define ZSTD_COMPRESSBLOCK_LAZY2_DEDICATEDDICTSEARCH_ROW ZSTD_compressBlock_lazy2_dedicatedDictSearch_row
+#define ZSTD_COMPRESSBLOCK_LAZY2_EXTDICT ZSTD_compressBlock_lazy2_extDict
+#define ZSTD_COMPRESSBLOCK_LAZY2_EXTDICT_ROW ZSTD_compressBlock_lazy2_extDict_row
+#else
+#define ZSTD_COMPRESSBLOCK_LAZY2 NULL
+#define ZSTD_COMPRESSBLOCK_LAZY2_ROW NULL
+#define ZSTD_COMPRESSBLOCK_LAZY2_DICTMATCHSTATE NULL
+#define ZSTD_COMPRESSBLOCK_LAZY2_DICTMATCHSTATE_ROW NULL
+#define ZSTD_COMPRESSBLOCK_LAZY2_DEDICATEDDICTSEARCH NULL
+#define ZSTD_COMPRESSBLOCK_LAZY2_DEDICATEDDICTSEARCH_ROW NULL
+#define ZSTD_COMPRESSBLOCK_LAZY2_EXTDICT NULL
+#define ZSTD_COMPRESSBLOCK_LAZY2_EXTDICT_ROW NULL
+#endif
+
+#ifndef ZSTD_EXCLUDE_BTLAZY2_BLOCK_COMPRESSOR
+size_t ZSTD_compressBlock_btlazy2(
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
-size_t ZSTD_compressBlock_lazy2_extDict_row(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+size_t ZSTD_compressBlock_btlazy2_dictMatchState(
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
size_t ZSTD_compressBlock_btlazy2_extDict(
- ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+ ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize);
-
+#define ZSTD_COMPRESSBLOCK_BTLAZY2 ZSTD_compressBlock_btlazy2
+#define ZSTD_COMPRESSBLOCK_BTLAZY2_DICTMATCHSTATE ZSTD_compressBlock_btlazy2_dictMatchState
+#define ZSTD_COMPRESSBLOCK_BTLAZY2_EXTDICT ZSTD_compressBlock_btlazy2_extDict
+#else
+#define ZSTD_COMPRESSBLOCK_BTLAZY2 NULL
+#define ZSTD_COMPRESSBLOCK_BTLAZY2_DICTMATCHSTATE NULL
+#define ZSTD_COMPRESSBLOCK_BTLAZY2_EXTDICT NULL
+#endif
#endif /* ZSTD_LAZY_H */