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>

1 files changed, 39 insertions, 16 deletions

diff --git a/lib/zstd/compress/zstd_opt.h b/lib/zstd/compress/zstd_opt.h
index 22b862858ba7..fbdc540ec9d1 100644
--- a/lib/zstd/compress/zstd_opt.h
+++ b/lib/zstd/compress/zstd_opt.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
@@ -11,40 +12,62 @@
 #ifndef ZSTD_OPT_H
 #define ZSTD_OPT_H
 
-
 #include "zstd_compress_internal.h"
 
+#if !defined(ZSTD_EXCLUDE_BTLAZY2_BLOCK_COMPRESSOR) \
+ || !defined(ZSTD_EXCLUDE_BTOPT_BLOCK_COMPRESSOR) \
+ || !defined(ZSTD_EXCLUDE_BTULTRA_BLOCK_COMPRESSOR)
 /* used in ZSTD_loadDictionaryContent() */
-void ZSTD_updateTree(ZSTD_matchState_t* ms, const BYTE* ip, const BYTE* iend);
+void ZSTD_updateTree(ZSTD_MatchState_t* ms, const BYTE* ip, const BYTE* iend);
+#endif
 
+#ifndef ZSTD_EXCLUDE_BTOPT_BLOCK_COMPRESSOR
 size_t ZSTD_compressBlock_btopt(
-        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_btultra(
-        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+size_t ZSTD_compressBlock_btopt_dictMatchState(
+        ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
         void const* src, size_t srcSize);
-size_t ZSTD_compressBlock_btultra2(
-        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+size_t ZSTD_compressBlock_btopt_extDict(
+        ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
         void const* src, size_t srcSize);
 
+#define ZSTD_COMPRESSBLOCK_BTOPT ZSTD_compressBlock_btopt
+#define ZSTD_COMPRESSBLOCK_BTOPT_DICTMATCHSTATE ZSTD_compressBlock_btopt_dictMatchState
+#define ZSTD_COMPRESSBLOCK_BTOPT_EXTDICT ZSTD_compressBlock_btopt_extDict
+#else
+#define ZSTD_COMPRESSBLOCK_BTOPT NULL
+#define ZSTD_COMPRESSBLOCK_BTOPT_DICTMATCHSTATE NULL
+#define ZSTD_COMPRESSBLOCK_BTOPT_EXTDICT NULL
+#endif
 
-size_t ZSTD_compressBlock_btopt_dictMatchState(
-        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+#ifndef ZSTD_EXCLUDE_BTULTRA_BLOCK_COMPRESSOR
+size_t ZSTD_compressBlock_btultra(
+        ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
         void const* src, size_t srcSize);
 size_t ZSTD_compressBlock_btultra_dictMatchState(
-        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
-        void const* src, size_t srcSize);
-
-size_t ZSTD_compressBlock_btopt_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_btultra_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);
 
         /* note : no btultra2 variant for extDict nor dictMatchState,
          * because btultra2 is not meant to work with dictionaries
          * and is only specific for the first block (no prefix) */
+size_t ZSTD_compressBlock_btultra2(
+        ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
 
+#define ZSTD_COMPRESSBLOCK_BTULTRA ZSTD_compressBlock_btultra
+#define ZSTD_COMPRESSBLOCK_BTULTRA_DICTMATCHSTATE ZSTD_compressBlock_btultra_dictMatchState
+#define ZSTD_COMPRESSBLOCK_BTULTRA_EXTDICT ZSTD_compressBlock_btultra_extDict
+#define ZSTD_COMPRESSBLOCK_BTULTRA2 ZSTD_compressBlock_btultra2
+#else
+#define ZSTD_COMPRESSBLOCK_BTULTRA NULL
+#define ZSTD_COMPRESSBLOCK_BTULTRA_DICTMATCHSTATE NULL
+#define ZSTD_COMPRESSBLOCK_BTULTRA_EXTDICT NULL
+#define ZSTD_COMPRESSBLOCK_BTULTRA2 NULL
+#endif
 
 #endif /* ZSTD_OPT_H */