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, 82 insertions, 5 deletions

diff --git a/include/linux/zstd.h b/include/linux/zstd.h
index b2c7cf310c8f..2f2a3c8b8a33 100644
--- a/include/linux/zstd.h
+++ b/include/linux/zstd.h
@@ -1,6 +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
@@ -160,7 +160,6 @@ typedef ZSTD_parameters zstd_parameters;
 zstd_parameters zstd_get_params(int level,
 	unsigned long long estimated_src_size);
 
-
 /**
  * zstd_get_cparams() - returns zstd_compression_parameters for selected level
  * @level:              The compression level
@@ -173,9 +172,20 @@ zstd_parameters zstd_get_params(int level,
 zstd_compression_parameters zstd_get_cparams(int level,
 	unsigned long long estimated_src_size, size_t dict_size);
 
-/* ======   Single-pass Compression   ====== */
-
 typedef ZSTD_CCtx zstd_cctx;
+typedef ZSTD_cParameter zstd_cparameter;
+
+/**
+ * zstd_cctx_set_param() - sets a compression parameter
+ * @cctx:         The context. Must have been initialized with zstd_init_cctx().
+ * @param:        The parameter to set.
+ * @value:        The value to set the parameter to.
+ *
+ * Return:        Zero or an error, which can be checked using zstd_is_error().
+ */
+size_t zstd_cctx_set_param(zstd_cctx *cctx, zstd_cparameter param, int value);
+
+/* ======   Single-pass Compression   ====== */
 
 /**
  * zstd_cctx_workspace_bound() - max memory needed to initialize a zstd_cctx
@@ -191,6 +201,20 @@ typedef ZSTD_CCtx zstd_cctx;
 size_t zstd_cctx_workspace_bound(const zstd_compression_parameters *parameters);
 
 /**
+ * zstd_cctx_workspace_bound_with_ext_seq_prod() - max memory needed to
+ * initialize a zstd_cctx when using the block-level external sequence
+ * producer API.
+ * @parameters: The compression parameters to be used.
+ *
+ * If multiple compression parameters might be used, the caller must call
+ * this function for each set of parameters and use the maximum size.
+ *
+ * Return:      A lower bound on the size of the workspace that is passed to
+ *              zstd_init_cctx().
+ */
+size_t zstd_cctx_workspace_bound_with_ext_seq_prod(const zstd_compression_parameters *parameters);
+
+/**
  * zstd_init_cctx() - initialize a zstd compression context
  * @workspace:      The workspace to emplace the context into. It must outlive
  *                  the returned context.
@@ -425,6 +449,16 @@ typedef ZSTD_CStream zstd_cstream;
 size_t zstd_cstream_workspace_bound(const zstd_compression_parameters *cparams);
 
 /**
+ * zstd_cstream_workspace_bound_with_ext_seq_prod() - memory needed to initialize
+ * a zstd_cstream when using the block-level external sequence producer API.
+ * @cparams: The compression parameters to be used for compression.
+ *
+ * Return:   A lower bound on the size of the workspace that is passed to
+ *           zstd_init_cstream().
+ */
+size_t zstd_cstream_workspace_bound_with_ext_seq_prod(const zstd_compression_parameters *cparams);
+
+/**
  * zstd_init_cstream() - initialize a zstd streaming compression context
  * @parameters        The zstd parameters to use for compression.
  * @pledged_src_size: If params.fParams.contentSizeFlag == 1 then the caller
@@ -584,6 +618,18 @@ size_t zstd_decompress_stream(zstd_dstream *dstream, zstd_out_buffer *output,
 size_t zstd_find_frame_compressed_size(const void *src, size_t src_size);
 
 /**
+ * zstd_register_sequence_producer() - exposes the zstd library function
+ * ZSTD_registerSequenceProducer(). This is used for the block-level external
+ * sequence producer API. See upstream zstd.h for detailed documentation.
+ */
+typedef ZSTD_sequenceProducer_F zstd_sequence_producer_f;
+void zstd_register_sequence_producer(
+  zstd_cctx *cctx,
+  void* sequence_producer_state,
+  zstd_sequence_producer_f sequence_producer
+);
+
+/**
  * struct zstd_frame_params - zstd frame parameters stored in the frame header
  * @frameContentSize: The frame content size, or ZSTD_CONTENTSIZE_UNKNOWN if not
  *                    present.
@@ -596,7 +642,7 @@ size_t zstd_find_frame_compressed_size(const void *src, size_t src_size);
  *
  * See zstd_lib.h.
  */
-typedef ZSTD_frameHeader zstd_frame_header;
+typedef ZSTD_FrameHeader zstd_frame_header;
 
 /**
  * zstd_get_frame_header() - extracts parameters from a zstd or skippable frame
@@ -611,4 +657,35 @@ typedef ZSTD_frameHeader zstd_frame_header;
 size_t zstd_get_frame_header(zstd_frame_header *params, const void *src,
 	size_t src_size);
 
+/**
+ * struct zstd_sequence - a sequence of literals or a match
+ *
+ * @offset: The offset of the match
+ * @litLength: The literal length of the sequence
+ * @matchLength: The match length of the sequence
+ * @rep: Represents which repeat offset is used
+ */
+typedef ZSTD_Sequence zstd_sequence;
+
+/**
+ * zstd_compress_sequences_and_literals() - compress an array of zstd_sequence and literals
+ *
+ * @cctx: The zstd compression context.
+ * @dst: The buffer to compress the data into.
+ * @dst_capacity: The size of the destination buffer.
+ * @in_seqs: The array of zstd_sequence to compress.
+ * @in_seqs_size: The number of sequences in in_seqs.
+ * @literals: The literals associated to the sequences to be compressed.
+ * @lit_size: The size of the literals in the literals buffer.
+ * @lit_capacity: The size of the literals buffer.
+ * @decompressed_size: The size of the input data
+ *
+ * Return: The compressed size or an error, which can be checked using
+ * 	   zstd_is_error().
+ */
+size_t zstd_compress_sequences_and_literals(zstd_cctx *cctx, void* dst, size_t dst_capacity,
+					    const zstd_sequence *in_seqs, size_t in_seqs_size,
+					    const void* literals, size_t lit_size, size_t lit_capacity,
+					    size_t decompressed_size);
+
 #endif  /* LINUX_ZSTD_H */