Updated to zstd 1.5.5 (#15)

zstd.mod/common.bmx

@@ -1,4 +1,4 @@
-' Copyright (c) 2022 Bruce A Henderson
+' Copyright (c) 2022-2023 Bruce A Henderson
 ' All rights reserved.
 '
 ' Redistribution and use in source and binary forms, with or without

zstd.mod/source.bmx

@@ -1,4 +1,4 @@
-' Copyright (c) 2022 Bruce A Henderson
+' Copyright (c) 2022-2023 Bruce A Henderson
 ' All rights reserved.
 '
 ' Redistribution and use in source and binary forms, with or without

zstd.mod/zstd.bmx

@@ -1,4 +1,4 @@
-' Copyright (c) 2022 Bruce A Henderson
+' Copyright (c) 2022-2023 Bruce A Henderson
 ' All rights reserved.
 '
 ' Redistribution and use in source and binary forms, with or without
@@ -24,11 +24,13 @@ SuperStrict
 
 Module Archive.Zstd
 
-ModuleInfo "Version: 1.00"
+ModuleInfo "Version: 1.01"
 ModuleInfo "License: BSD"
-ModuleInfo "Copyright: Wrapper - 2022 Bruce A Henderson"
-ModuleInfo "Copyright: ZStandard - 2016-present, Facebook, Inc"
+ModuleInfo "Copyright: Wrapper - 2022-2023 Bruce A Henderson"
+ModuleInfo "Copyright: ZStandard - Meta Platforms, Inc. and affiliates. All rights reserved."
 
+ModuleInfo "History: 1.01"
+ModuleInfo "History: Update to zstd 1.5.5"
 ModuleInfo "History: 1.00"
 ModuleInfo "History: Initial Release. zstd 1.5.2"
 

zstd.mod/zstd/CHANGELOG

@@ -1,3 +1,82 @@
+v1.5.5 (Apr 2023)
+fix: fix rare corruption bug affecting the high compression mode, reported by @danlark1 (#3517, @terrelln)
+perf: improve mid-level compression speed (#3529, #3533, #3543, @yoniko and #3552, @terrelln)
+lib: deprecated bufferless block-level API (#3534) by @terrelln
+cli: mmap large dictionaries to save memory, by @daniellerozenblit
+cli: improve speed of --patch-from mode (~+50%) (#3545) by @daniellerozenblit
+cli: improve i/o speed (~+10%) when processing lots of small files (#3479) by @felixhandte
+cli: zstd no longer crashes when requested to write into write-protected directory (#3541) by @felixhandte
+cli: fix decompression into block device using -o, reported by @georgmu (#3583)
+build: fix zstd CLI compiled with lzma support but not zlib support (#3494) by @Hello71
+build: fix cmake does no longer require 3.18 as minimum version (#3510) by @kou
+build: fix MSVC+ClangCL linking issue (#3569) by @tru
+build: fix zstd-dll, version of zstd CLI that links to the dynamic library (#3496) by @yoniko
+build: fix MSVC warnings (#3495) by @embg
+doc: updated zstd specification to clarify corner cases, by @Cyan4973
+doc: document how to create fat binaries for macos (#3568) by @rickmark
+misc: improve seekable format ingestion speed (~+100%) for very small chunk sizes (#3544) by @Cyan4973
+misc: tests/fullbench can benchmark multiple files (#3516) by @dloidolt
+
+v1.5.4 (Feb 2023)
+perf: +20% faster huffman decompression for targets that can't compile x64 assembly (#3449, @terrelln)
+perf: up to +10% faster streaming compression at levels 1-2 (#3114, @embg)
+perf: +4-13% for levels 5-12 by optimizing function generation (#3295, @terrelln)
+pref: +3-11% compression speed for `arm` target (#3199, #3164, #3145, #3141, #3138, @JunHe77 and #3139, #3160, @danlark1)
+perf: +5-30% faster dictionary compression at levels 1-4 (#3086, #3114, #3152, @embg)
+perf: +10-20% cold dict compression speed by prefetching CDict tables (#3177, @embg)
+perf: +1% faster compression by removing a branch in ZSTD_fast_noDict (#3129, @felixhandte)
+perf: Small compression ratio improvements in high compression mode (#2983, #3391, @Cyan4973 and #3285, #3302, @daniellerozenblit)
+perf: small speed improvement by better detecting `STATIC_BMI2` for `clang` (#3080, @TocarIP)
+perf: Improved streaming performance when `ZSTD_c_stableInBuffer` is set (#2974, @Cyan4973)
+cli: Asynchronous I/O for improved cli speed (#2975, #2985, #3021, #3022, @yoniko)
+cli: Change `zstdless` behavior to align with `zless` (#2909, @binhdvo)
+cli: Keep original file if `-c` or `--stdout` is given (#3052, @dirkmueller)
+cli: Keep original files when result is concatenated into a single output with `-o` (#3450, @Cyan4973)
+cli: Preserve Permissions and Ownership of regular files (#3432, @felixhandte)
+cli: Print zlib/lz4/lzma library versions with `-vv` (#3030, @terrelln)
+cli: Print checksum value for single frame files with `-lv`  (#3332, @Cyan4973)
+cli: Print `dictID` when present with `-lv` (#3184, @htnhan)
+cli: when `stderr` is *not* the console, disable status updates, but preserve final summary (#3458, @Cyan4973)
+cli: support `--best` and `--no-name` in `gzip` compatibility mode (#3059, @dirkmueller)
+cli: support for `posix` high resolution timer `clock_gettime()`, for improved benchmark accuracy (#3423, @Cyan4973)
+cli: improved help/usage (`-h`,  `-H`) formatting (#3094, @dirkmueller and #3385, @jonpalmisc)
+cli: Fix better handling of bogus numeric values (#3268, @ctkhanhly)
+cli: Fix input consists of multiple files _and_ `stdin` (#3222, @yoniko)
+cli: Fix tiny files passthrough (#3215, @cgbur)
+cli: Fix for `-r` on empty directory (#3027, @brailovich)
+cli: Fix empty string as argument for `--output-dir-*` (#3220, @embg)
+cli: Fix decompression memory usage reported by `-vv --long` (#3042, @u1f35c, and #3232, @zengyijing)
+cli: Fix infinite loop when empty input is passed to trainer (#3081, @terrelln)
+cli: Fix `--adapt` doesn't work when `--no-progress` is also set (#3354, @terrelln)
+api: Support for Block-Level Sequence Producer (#3333, @embg)
+api: Support for in-place decompression (#3432, @terrelln)
+api: New  `ZSTD_CCtx_setCParams()`  function, set all parameters defined in a  `ZSTD_compressionParameters`  structure (#3403, @Cyan4973)
+api: Streaming decompression detects incorrect header ID sooner (#3175, @Cyan4973)
+api: Window size resizing optimization for edge case (#3345, @daniellerozenblit)
+api: More accurate error codes for busy-loop scenarios (#3413, #3455, @Cyan4973)
+api: Fix limit overflow in `compressBound` and `decompressBound` (#3362, #3373, Cyan4973) reported by @nigeltao
+api: Deprecate several advanced experimental functions: streaming (#3408, @embg), copy (#3196, @mileshu)
+bug: Fix corruption that rarely occurs in 32-bit mode with wlog=25 (#3361, @terrelln)
+bug: Fix for block-splitter (#3033, @Cyan4973)
+bug: Fixes for Sequence Compression API (#3023, #3040, @Cyan4973)
+bug: Fix leaking thread handles on Windows (#3147, @animalize)
+bug: Fix timing issues with cmake/meson builds (#3166, #3167, #3170, @Cyan4973)
+build: Allow user to select legacy level for cmake (#3050, @shadchin)
+build: Enable legacy support by default in cmake (#3079, @niamster)
+build: Meson build script improvements (#3039, #3120, #3122, #3327, #3357, @eli-schwartz and #3276, @neheb)
+build: Add aarch64 to supported architectures for zstd_trace (#3054, @ooosssososos)
+build: support AIX architecture (#3219, @qiongsiwu)
+build: Fix `ZSTD_LIB_MINIFY` build macro, which now reduces static library size by half (#3366, @terrelln)
+build: Fix Windows issues with Multithreading translation layer (#3364, #3380, @yoniko) and ARM64 target (#3320, @cwoffenden)
+build: Fix `cmake` script (#3382, #3392, @terrelln and #3252 @Tachi107 and #3167 @Cyan4973)
+doc: Updated man page, providing more details for `--train` mode (#3112, @Cyan4973)
+doc: Add decompressor errata document (#3092, @terrelln)
+misc: Enable Intel CET (#2992, #2994, @hjl-tools)
+misc: Fix `contrib/` seekable format (#3058, @yhoogstrate and #3346, @daniellerozenblit)
+misc: Improve speed of the one-file library generator (#3241, @wahern and #3005, @cwoffenden)
+
+v1.5.3 (dev version, unpublished)
+
 v1.5.2 (Jan, 2022)
 perf: Regain Minimal memset()-ing During Reuse of Compression Contexts (@Cyan4973, #2969)
 build: Build Zstd with `noexecstack` on All Architectures (@felixhandte, #2964)

zstd.mod/zstd/CONTRIBUTING.md

@@ -7,7 +7,7 @@ New versions are being developed in the "dev" branch,
 or in their own feature branch.
 When they are deemed ready for a release, they are merged into "release".
 
-As a consequences, all contributions must stage first through "dev"
+As a consequence, all contributions must stage first through "dev"
 or their own feature branch.
 
 ## Pull Requests
@@ -68,8 +68,8 @@ Our contribution process works in three main stages:
             ```
 2. Code Review and CI tests
     * Ensure CI tests pass:
-        * Before sharing anything to the community, make sure that all CI tests pass on your local fork.
-        See our section on setting up your CI environment for more information on how to do this.
+        * Before sharing anything to the community, create a pull request in your own fork against the dev branch
+        and make sure that all GitHub Actions CI tests pass. See the Continuous Integration section below for more information.
         * Ensure that static analysis passes on your development machine. See the Static Analysis section
         below to see how to do this.
     * Create a pull request:
@@ -134,11 +134,47 @@ It can be useful to look at additional static analyzers once in a while (and we
 - Static analyzers are full of false positive. The signal to noise ratio is actually pretty low.
 - A good CI policy is "zero-warning tolerance". That means that all issues must be solved, including false positives. This quickly becomes a tedious workload.
 - Multiple static analyzers will feature multiple kind of false positives, sometimes applying to the same code but in different ways leading to :
-   + torteous code, trying to please multiple constraints, hurting readability and therefore maintenance. Sometimes, such complexity introduce other more subtle bugs, that are just out of scope of the analyzers.
+   + tortuous code, trying to please multiple constraints, hurting readability and therefore maintenance. Sometimes, such complexity introduce other more subtle bugs, that are just out of scope of the analyzers.
    + sometimes, these constraints are mutually exclusive : if one try to solve one, the other static analyzer will complain, they can't be both happy at the same time.
 - As if that was not enough, the list of false positives change with each version. It's hard enough to follow one static analyzer, but multiple ones with their own update agenda, this quickly becomes a massive velocity reducer.
 
-This is different from running a static analyzer once in a while, looking at the output, and __cherry picking__ a few warnings that seem helpful, either because they detected a genuine risk of bug, or because it helps expressing the code in a way which is more readable or more difficult to misuse. These kind of reports can be useful, and are accepted.
+This is different from running a static analyzer once in a while, looking at the output, and __cherry picking__ a few warnings that seem helpful, either because they detected a genuine risk of bug, or because it helps expressing the code in a way which is more readable or more difficult to misuse. These kinds of reports can be useful, and are accepted.
+
+## Continuous Integration
+CI tests run every time a pull request (PR) is created or updated. The exact tests
+that get run will depend on the destination branch you specify. Some tests take
+longer to run than others. Currently, our CI is set up to run a short
+series of tests when creating a PR to the dev branch and a longer series of tests
+when creating a PR to the release branch. You can look in the configuration files
+of the respective CI platform for more information on what gets run when.
+
+Most people will just want to create a PR with the destination set to their local dev
+branch of zstd. You can then find the status of the tests on the PR's page. You can also
+re-run tests and cancel running tests from the PR page or from the respective CI's dashboard.
+
+Almost all of zstd's CI runs on GitHub Actions (configured at `.github/workflows`), which will automatically run on PRs to your
+own fork. A small number of tests run on other services (e.g. Travis CI, Circle CI, Appveyor).
+These require work to set up on your local fork, and (at least for Travis CI) cost money.
+Therefore, if the PR on your local fork passes GitHub Actions, feel free to submit a PR
+against the main repo.
+
+### Third-party CI
+A small number of tests cannot run on GitHub Actions, or have yet to be migrated.
+For these, we use a variety of third-party services (listed below). It is not necessary to set
+these up on your fork in order to contribute to zstd; however, we do link to instructions for those
+who want earlier signal.
+
+| Service   | Purpose                                                                                                    | Setup Links                                                                                                                                            | Config Path            |
+|-----------|------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------|
+| Travis CI | Used for testing on non-x86 architectures such as PowerPC                                                  | https://docs.travis-ci.com/user/tutorial/#to-get-started-with-travis-ci-using-github <br> https://github.com/marketplace/travis-ci                     | `.travis.yml`          |
+| AppVeyor  | Used for some Windows testing (e.g. cygwin, mingw)                                                         | https://www.appveyor.com/blog/2018/10/02/github-apps-integration/ <br> https://github.com/marketplace/appveyor                                         | `appveyor.yml`         |
+| Cirrus CI | Used for testing on FreeBSD                                                                                | https://github.com/marketplace/cirrus-ci/                                                                                                              | `.cirrus.yml`          |
+| Circle CI | Historically was used to provide faster signal,<br/> but we may be able to migrate these to Github Actions | https://circleci.com/docs/2.0/getting-started/#setting-up-circleci <br> https://youtu.be/Js3hMUsSZ2c <br> https://circleci.com/docs/2.0/enable-checks/ | `.circleci/config.yml` |
+
+Note: the instructions linked above mostly cover how to set up a repository with CI from scratch. 
+The general idea should be the same for setting up CI on your fork of zstd, but you may have to 
+follow slightly different steps. In particular, please ignore any instructions related to setting up
+config files (since zstd already has configs for each of these services).
 
 ## Performance
 Performance is extremely important for zstd and we only merge pull requests whose performance
@@ -161,7 +197,7 @@ something subtle merged is extensive benchmarking. You will be doing us a great
 take the time to run extensive, long-duration, and potentially cross-(os, platform, process, etc)
 benchmarks on your end before submitting a PR. Of course, you will not be able to benchmark
 your changes on every single processor and os out there (and neither will we) but do that best
-you can:) We've adding some things to think about when benchmarking below in the Benchmarking
+you can:) We've added some things to think about when benchmarking below in the Benchmarking
 Performance section which might be helpful for you.
 3. Optimizing performance for a certain OS, processor vendor, compiler, or network system is a perfectly
 legitimate thing to do as long as it does not harm the overall performance health of Zstd.
@@ -237,7 +273,7 @@ for that options you have just provided. If you want to look at the internals of
 benchmarking script works, you can check out programs/benchzstd.c
 
 For example: say you have made a change that you believe improves the speed of zstd level 1. The
-very first thing you should use to asses whether you actually achieved any sort of improvement
+very first thing you should use to assess whether you actually achieved any sort of improvement
 is `zstd -b`. You might try to do something like this. Note: you can use the `-i` option to
 specify a running time for your benchmark in seconds (default is 3 seconds).
 Usually, the longer the running time, the more stable your results will be.
@@ -263,7 +299,7 @@ this method of evaluation will not be sufficient.
 ### Profiling
 There are a number of great profilers out there. We're going to briefly mention how you can
 profile your code using `instruments` on mac, `perf` on linux and `visual studio profiler`
-on windows.
+on Windows.
 
 Say you have an idea for a change that you think will provide some good performance gains
 for level 1 compression on Zstd. Typically this means, you have identified a section of
@@ -279,8 +315,8 @@ might be).
 
 Most profilers (including the profilers discussed below) will generate a call graph of
 functions for you. Your goal will be to find your function of interest in this call graph
-and then inspect the time spent inside of it. You might also want to to look at the
-annotated assembly which most profilers will provide you with.
+and then inspect the time spent inside of it. You might also want to look at the annotated
+assembly which most profilers will provide you with.
 
 #### Instruments
 We will once again consider the scenario where you think you've identified a piece of code
@@ -294,7 +330,7 @@ Instruments.
     * You will want a benchmark that runs for at least a few seconds (5 seconds will
     usually be long enough). This way the profiler will have something to work with
     and you will have ample time to attach your profiler to this process:)
-    * I will just use benchzstd as my bencharmking script for this example:
+    * I will just use benchzstd as my benchmarmking script for this example:
 ```
 $ zstd -b1 -i5 <my-data> # this will run for 5 seconds
 ```
@@ -339,57 +375,6 @@ counter `L1-dcache-load-misses`
 
 TODO
 
-
-## Setting up continuous integration (CI) on your fork
-Zstd uses a number of different continuous integration (CI) tools to ensure that new changes
-are well tested before they make it to an official release. Specifically, we use the platforms
-travis-ci, circle-ci, and appveyor.
-
-Changes cannot be merged into the main dev branch unless they pass all of our CI tests.
-The easiest way to run these CI tests on your own before submitting a PR to our dev branch
-is to configure your personal fork of zstd with each of the CI platforms. Below, you'll find
-instructions for doing this.
-
-### travis-ci
-Follow these steps to link travis-ci with your github fork of zstd
-
-1. Make sure you are logged into your github account
-2. Go to https://travis-ci.org/
-3. Click 'Sign in with Github' on the top right
-4. Click 'Authorize travis-ci'
-5. Click 'Activate all repositories using Github Apps'
-6. Select 'Only select repositories' and select your fork of zstd from the drop down
-7. Click 'Approve and Install'
-8. Click 'Sign in with Github' again. This time, it will be for travis-pro (which will let you view your tests on the web dashboard)
-9. Click 'Authorize travis-pro'
-10. You should have travis set up on your fork now.
-
-### circle-ci
-TODO
-
-### appveyor
-Follow these steps to link circle-ci with your github fork of zstd
-
-1. Make sure you are logged into your github account
-2. Go to https://www.appveyor.com/
-3. Click 'Sign in' on the top right
-4. Select 'Github' on the left panel
-5. Click 'Authorize appveyor'
-6. You might be asked to select which repositories you want to give appveyor permission to. Select your fork of zstd if you're prompted
-7. You should have appveyor set up on your fork now.
-
-### General notes on CI
-CI tests run every time a pull request (PR) is created or updated. The exact tests
-that get run will depend on the destination branch you specify. Some tests take
-longer to run than others. Currently, our CI is set up to run a short
-series of tests when creating a PR to the dev branch and a longer series of tests
-when creating a PR to the release branch. You can look in the configuration files
-of the respective CI platform for more information on what gets run when.
-
-Most people will just want to create a PR with the destination set to their local dev
-branch of zstd. You can then find the status of the tests on the PR's page. You can also
-re-run tests and cancel running tests from the PR page or from the respective CI's dashboard.
-
 ## Issues
 We use GitHub issues to track public bugs. Please ensure your description is
 clear and has sufficient instructions to be able to reproduce the issue.
@@ -470,7 +455,7 @@ This design requirement is fundamental to preserve the portability of the code b
   Any variable that can be `const` (aka. read-only) **must** be `const`.
   Any pointer which content will not be modified must be `const`.
   This property is then controlled at compiler level.
-  `const` variables are an important signal to readers that this variable isn’t modified.
+  `const` variables are an important signal to readers that this variable isn't modified.
   Conversely, non-const variables are a signal to readers to watch out for modifications later on in the function.
 * If a function must be inlined, mention it explicitly,
   using project's own portable macros, such as `FORCE_INLINE_ATTR`,

zstd.mod/zstd/LICENSE

@@ -2,7 +2,7 @@ BSD License
 
 For Zstandard software
 
-Copyright (c) 2016-present, Facebook, Inc. All rights reserved.
+Copyright (c) Meta Platforms, Inc. and affiliates. All rights reserved.
 
 Redistribution and use in source and binary forms, with or without modification,
 are permitted provided that the following conditions are met:
@@ -14,9 +14,9 @@ are permitted provided that the following conditions are met:
    this list of conditions and the following disclaimer in the documentation
    and/or other materials provided with the distribution.
 
- * Neither the name Facebook nor the names of its contributors may be used to
-   endorse or promote products derived from this software without specific
-   prior written permission.
+ * Neither the name Facebook, nor Meta, nor the names of its contributors may
+   be used to endorse or promote products derived from this software without
+   specific prior written permission.
 
 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
 ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED

zstd.mod/zstd/Makefile

@@ -1,5 +1,5 @@
 # ################################################################
-# Copyright (c) 2015-2021, 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
@@ -123,6 +123,7 @@ contrib: lib
 	$(MAKE) -C contrib/seekable_format/examples all
 	$(MAKE) -C contrib/seekable_format/tests test
 	$(MAKE) -C contrib/largeNbDicts all
+	$(MAKE) -C contrib/externalSequenceProducer all
 	cd build/single_file_libs/ ; ./build_decoder_test.sh
 	cd build/single_file_libs/ ; ./build_library_test.sh
 
@@ -142,6 +143,7 @@ clean:
 	$(Q)$(MAKE) -C contrib/seekable_format/examples $@ > $(VOID)
 	$(Q)$(MAKE) -C contrib/seekable_format/tests $@ > $(VOID)
 	$(Q)$(MAKE) -C contrib/largeNbDicts $@ > $(VOID)
+	$(Q)$(MAKE) -C contrib/externalSequenceProducer $@ > $(VOID)
 	$(Q)$(RM) zstd$(EXT) zstdmt$(EXT) tmp*
 	$(Q)$(RM) -r lz4
 	@echo Cleaning completed
@@ -157,7 +159,7 @@ MKDIR ?= mkdir -p
 
 HAVE_COLORNEVER = $(shell echo a | egrep --color=never a > /dev/null 2> /dev/null && echo 1 || echo 0)
 EGREP_OPTIONS ?=
-ifeq ($HAVE_COLORNEVER, 1)
+ifeq ($(HAVE_COLORNEVER), 1)
 EGREP_OPTIONS += --color=never
 endif
 EGREP = egrep $(EGREP_OPTIONS)
@@ -198,15 +200,15 @@ travis-install:
 .PHONY: gcc5build gcc6build gcc7build clangbuild m32build armbuild aarch64build ppcbuild ppc64build
 gcc5build: clean
 	gcc-5 -v
-	CC=gcc-5 $(MAKE) all MOREFLAGS="-Werror"
+	CC=gcc-5 $(MAKE) all MOREFLAGS="-Werror $(MOREFLAGS)"
 
 gcc6build: clean
 	gcc-6 -v
-	CC=gcc-6 $(MAKE) all MOREFLAGS="-Werror"
+	CC=gcc-6 $(MAKE) all MOREFLAGS="-Werror $(MOREFLAGS)"
 
 gcc7build: clean
 	gcc-7 -v
-	CC=gcc-7 $(MAKE) all MOREFLAGS="-Werror"
+	CC=gcc-7 $(MAKE) all MOREFLAGS="-Werror $(MOREFLAGS)"
 
 clangbuild: clean
 	clang -v
@@ -230,17 +232,17 @@ ppc64build: clean
 
 .PHONY: armfuzz aarch64fuzz ppcfuzz ppc64fuzz
 armfuzz: clean
-	CC=arm-linux-gnueabi-gcc QEMU_SYS=qemu-arm-static MOREFLAGS="-static" FUZZER_FLAGS=--no-big-tests $(MAKE) -C $(TESTDIR) fuzztest
+	CC=arm-linux-gnueabi-gcc QEMU_SYS=qemu-arm-static MOREFLAGS="-static $(MOREFLAGS)" FUZZER_FLAGS="--no-big-tests $(FUZZER_FLAGS)" $(MAKE) -C $(TESTDIR) fuzztest
 
 aarch64fuzz: clean
 	ld -v
-	CC=aarch64-linux-gnu-gcc QEMU_SYS=qemu-aarch64-static MOREFLAGS="-static" FUZZER_FLAGS=--no-big-tests $(MAKE) -C $(TESTDIR) fuzztest
+	CC=aarch64-linux-gnu-gcc QEMU_SYS=qemu-aarch64-static MOREFLAGS="-static $(MOREFLAGS)" FUZZER_FLAGS="--no-big-tests $(FUZZER_FLAGS)" $(MAKE) -C $(TESTDIR) fuzztest
 
 ppcfuzz: clean
-	CC=powerpc-linux-gnu-gcc QEMU_SYS=qemu-ppc-static MOREFLAGS="-static" FUZZER_FLAGS=--no-big-tests $(MAKE) -C $(TESTDIR) fuzztest
+	CC=powerpc-linux-gnu-gcc QEMU_SYS=qemu-ppc-static MOREFLAGS="-static $(MOREFLAGS)" FUZZER_FLAGS="--no-big-tests $(FUZZER_FLAGS)" $(MAKE) -C $(TESTDIR) fuzztest
 
 ppc64fuzz: clean
-	CC=powerpc-linux-gnu-gcc QEMU_SYS=qemu-ppc64-static MOREFLAGS="-m64 -static" FUZZER_FLAGS=--no-big-tests $(MAKE) -C $(TESTDIR) fuzztest
+	CC=powerpc-linux-gnu-gcc QEMU_SYS=qemu-ppc64-static MOREFLAGS="-m64 -static $(MOREFLAGS)" FUZZER_FLAGS="--no-big-tests $(FUZZER_FLAGS)" $(MAKE) -C $(TESTDIR) fuzztest
 
 .PHONY: cxxtest gcc5test gcc6test armtest aarch64test ppctest ppc64test
 cxxtest: CXXFLAGS += -Wall -Wextra -Wundef -Wshadow -Wcast-align -Werror
@@ -249,34 +251,34 @@ cxxtest: clean
 
 gcc5test: clean
 	gcc-5 -v
-	$(MAKE) all CC=gcc-5 MOREFLAGS="-Werror"
+	$(MAKE) all CC=gcc-5 MOREFLAGS="-Werror $(MOREFLAGS)"
 
 gcc6test: clean
 	gcc-6 -v
-	$(MAKE) all CC=gcc-6 MOREFLAGS="-Werror"
+	$(MAKE) all CC=gcc-6 MOREFLAGS="-Werror $(MOREFLAGS)"
 
 armtest: clean
 	$(MAKE) -C $(TESTDIR) datagen   # use native, faster
-	$(MAKE) -C $(TESTDIR) test CC=arm-linux-gnueabi-gcc QEMU_SYS=qemu-arm-static ZSTDRTTEST= MOREFLAGS="-Werror -static" FUZZER_FLAGS=--no-big-tests
+	$(MAKE) -C $(TESTDIR) test CC=arm-linux-gnueabi-gcc QEMU_SYS=qemu-arm-static ZSTDRTTEST= MOREFLAGS="-Werror -static $(MOREFLAGS)" FUZZER_FLAGS="--no-big-tests $(FUZZER_FLAGS)"
 
 aarch64test:
 	$(MAKE) -C $(TESTDIR) datagen   # use native, faster
-	$(MAKE) -C $(TESTDIR) test CC=aarch64-linux-gnu-gcc QEMU_SYS=qemu-aarch64-static ZSTDRTTEST= MOREFLAGS="-Werror -static" FUZZER_FLAGS=--no-big-tests
+	$(MAKE) -C $(TESTDIR) test CC=aarch64-linux-gnu-gcc QEMU_SYS=qemu-aarch64-static ZSTDRTTEST= MOREFLAGS="-Werror -static $(MOREFLAGS)" FUZZER_FLAGS="--no-big-tests $(FUZZER_FLAGS)"
 
 ppctest: clean
 	$(MAKE) -C $(TESTDIR) datagen   # use native, faster
-	$(MAKE) -C $(TESTDIR) test CC=powerpc-linux-gnu-gcc QEMU_SYS=qemu-ppc-static ZSTDRTTEST= MOREFLAGS="-Werror -Wno-attributes -static" FUZZER_FLAGS=--no-big-tests
+	$(MAKE) -C $(TESTDIR) test CC=powerpc-linux-gnu-gcc QEMU_SYS=qemu-ppc-static ZSTDRTTEST= MOREFLAGS="-Werror -Wno-attributes -static $(MOREFLAGS)" FUZZER_FLAGS="--no-big-tests $(FUZZER_FLAGS)"
 
 ppc64test: clean
 	$(MAKE) -C $(TESTDIR) datagen   # use native, faster
-	$(MAKE) -C $(TESTDIR) test CC=powerpc-linux-gnu-gcc QEMU_SYS=qemu-ppc64-static ZSTDRTTEST= MOREFLAGS="-m64 -static" FUZZER_FLAGS=--no-big-tests
+	$(MAKE) -C $(TESTDIR) test CC=powerpc-linux-gnu-gcc QEMU_SYS=qemu-ppc64-static ZSTDRTTEST= MOREFLAGS="-m64 -static $(MOREFLAGS)" FUZZER_FLAGS="--no-big-tests $(FUZZER_FLAGS)"
 
 .PHONY: arm-ppc-compilation
 arm-ppc-compilation:
-	$(MAKE) -C $(PRGDIR) clean zstd CC=arm-linux-gnueabi-gcc QEMU_SYS=qemu-arm-static ZSTDRTTEST= MOREFLAGS="-Werror -static"
-	$(MAKE) -C $(PRGDIR) clean zstd CC=aarch64-linux-gnu-gcc QEMU_SYS=qemu-aarch64-static ZSTDRTTEST= MOREFLAGS="-Werror -static"
-	$(MAKE) -C $(PRGDIR) clean zstd CC=powerpc-linux-gnu-gcc QEMU_SYS=qemu-ppc-static ZSTDRTTEST= MOREFLAGS="-Werror -Wno-attributes -static"
-	$(MAKE) -C $(PRGDIR) clean zstd CC=powerpc-linux-gnu-gcc QEMU_SYS=qemu-ppc64-static ZSTDRTTEST= MOREFLAGS="-m64 -static"
+	$(MAKE) -C $(PRGDIR) clean zstd CC=arm-linux-gnueabi-gcc QEMU_SYS=qemu-arm-static ZSTDRTTEST= MOREFLAGS="-Werror -static $(MOREFLAGS)"
+	$(MAKE) -C $(PRGDIR) clean zstd CC=aarch64-linux-gnu-gcc QEMU_SYS=qemu-aarch64-static ZSTDRTTEST= MOREFLAGS="-Werror -static $(MOREFLAGS)"
+	$(MAKE) -C $(PRGDIR) clean zstd CC=powerpc-linux-gnu-gcc QEMU_SYS=qemu-ppc-static ZSTDRTTEST= MOREFLAGS="-Werror -Wno-attributes -static $(MOREFLAGS)"
+	$(MAKE) -C $(PRGDIR) clean zstd CC=powerpc-linux-gnu-gcc QEMU_SYS=qemu-ppc64-static ZSTDRTTEST= MOREFLAGS="-m64 -static $(MOREFLAGS)"
 
 regressiontest:
 	$(MAKE) -C $(FUZZDIR) regressiontest
@@ -306,34 +308,36 @@ update_regressionResults:
 # run UBsan with -fsanitize-recover=pointer-overflow
 # this only works with recent compilers such as gcc 8+
 usan: clean
-	$(MAKE) test CC=clang MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize-recover=pointer-overflow -fsanitize=undefined -Werror"
+	$(MAKE) test CC=clang MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize-recover=pointer-overflow -fsanitize=undefined -Werror $(MOREFLAGS)"
 
 asan: clean
-	$(MAKE) test CC=clang MOREFLAGS="-g -fsanitize=address -Werror"
+	$(MAKE) test CC=clang MOREFLAGS="-g -fsanitize=address -Werror $(MOREFLAGS)"
 
 asan-%: clean
-	LDFLAGS=-fuse-ld=gold MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize=address -Werror" $(MAKE) -C $(TESTDIR) $*
+	LDFLAGS=-fuse-ld=gold MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize=address -Werror $(MOREFLAGS)" $(MAKE) -C $(TESTDIR) $*
 
 msan: clean
-	$(MAKE) test CC=clang MOREFLAGS="-g -fsanitize=memory -fno-omit-frame-pointer -Werror" HAVE_LZMA=0   # datagen.c fails this test for no obvious reason
+	$(MAKE) test CC=clang MOREFLAGS="-g -fsanitize=memory -fno-omit-frame-pointer -Werror $(MOREFLAGS)" HAVE_LZMA=0   # datagen.c fails this test for no obvious reason
 
 msan-%: clean
-	LDFLAGS=-fuse-ld=gold MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize=memory -fno-omit-frame-pointer -Werror" FUZZER_FLAGS=--no-big-tests $(MAKE) -C $(TESTDIR) HAVE_LZMA=0 $*
+	LDFLAGS=-fuse-ld=gold MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize=memory -fno-omit-frame-pointer -Werror $(MOREFLAGS)" FUZZER_FLAGS="--no-big-tests $(FUZZER_FLAGS)" $(MAKE) -C $(TESTDIR) HAVE_LZMA=0 $*
 
 asan32: clean
-	$(MAKE) -C $(TESTDIR) test32 CC=clang MOREFLAGS="-g -fsanitize=address"
+	$(MAKE) -C $(TESTDIR) test32 CC=clang MOREFLAGS="-g -fsanitize=address $(MOREFLAGS)"
 
 uasan: clean
-	$(MAKE) test CC=clang MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize-recover=pointer-overflow -fsanitize=address,undefined -Werror"
+	$(MAKE) test CC=clang MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize-recover=pointer-overflow -fsanitize=address,undefined -Werror $(MOREFLAGS)"
 
 uasan-%: clean
-	LDFLAGS=-fuse-ld=gold MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize-recover=pointer-overflow -fsanitize=address,undefined -Werror" $(MAKE) -C $(TESTDIR) $*
+	LDFLAGS=-fuse-ld=gold MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize-recover=pointer-overflow -fsanitize=address,undefined -Werror $(MOREFLAGS)" $(MAKE) -C $(TESTDIR) $*
 
 tsan-%: clean
-	LDFLAGS=-fuse-ld=gold MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize=thread -Werror" $(MAKE) -C $(TESTDIR) $* FUZZER_FLAGS=--no-big-tests
+	LDFLAGS=-fuse-ld=gold MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize=thread -Werror $(MOREFLAGS)" $(MAKE) -C $(TESTDIR) $* FUZZER_FLAGS="--no-big-tests $(FUZZER_FLAGS)"
 
 .PHONY: apt-install
 apt-install:
+	# TODO: uncomment once issue 3011 is resolved and remove hack from Github Actions .yml
+	# sudo apt-get update
 	sudo apt-get -yq --no-install-suggests --no-install-recommends --force-yes install $(APT_PACKAGES)
 
 .PHONY: apt-add-repo
@@ -400,7 +404,7 @@ cmakebuild:
 
 c89build: clean
 	$(CC) -v
-	CFLAGS="-std=c89 -Werror -O0" $(MAKE) allmost  # will fail, due to missing support for `long long`
+	CFLAGS="-std=c89 -Werror -Wno-attributes -Wpedantic -Wno-long-long -Wno-variadic-macros -O0" $(MAKE) lib zstd
 
 gnu90build: clean
 	$(CC) -v

zstd.mod/zstd/README.md

@@ -8,20 +8,17 @@ Zstandard's format is stable and documented in [RFC8878](https://datatracker.iet
 This repository represents the reference implementation, provided as an open-source dual [BSD](LICENSE) and [GPLv2](COPYING) licensed **C** library,
 and a command line utility producing and decoding `.zst`, `.gz`, `.xz` and `.lz4` files.
 Should your project require another programming language,
-a list of known ports and bindings is provided on [Zstandard homepage](http://www.zstd.net/#other-languages).
+a list of known ports and bindings is provided on [Zstandard homepage](https://facebook.github.io/zstd/#other-languages).
 
 **Development branch status:**
 
 [![Build Status][travisDevBadge]][travisLink]
-[![Build status][AppveyorDevBadge]][AppveyorLink]
 [![Build status][CircleDevBadge]][CircleLink]
 [![Build status][CirrusDevBadge]][CirrusLink]
 [![Fuzzing Status][OSSFuzzBadge]][OSSFuzzLink]
 
 [travisDevBadge]: https://api.travis-ci.com/facebook/zstd.svg?branch=dev "Continuous Integration test suite"
 [travisLink]: https://travis-ci.com/facebook/zstd
-[AppveyorDevBadge]: https://ci.appveyor.com/api/projects/status/xt38wbdxjk5mrbem/branch/dev?svg=true "Windows test suite"
-[AppveyorLink]: https://ci.appveyor.com/project/YannCollet/zstd-p0yf0
 [CircleDevBadge]: https://circleci.com/gh/facebook/zstd/tree/dev.svg?style=shield "Short test suite"
 [CircleLink]: https://circleci.com/gh/facebook/zstd
 [CirrusDevBadge]: https://api.cirrus-ci.com/github/facebook/zstd.svg?branch=dev
@@ -39,7 +36,7 @@ compiled with [gcc] 9.3.0,
 on the [Silesia compression corpus].
 
 [lzbench]: https://github.com/inikep/lzbench
-[Silesia compression corpus]: http://sun.aei.polsl.pl/~sdeor/index.php?page=silesia
+[Silesia compression corpus]: https://sun.aei.polsl.pl//~sdeor/index.php?page=silesia
 [gcc]: https://gcc.gnu.org/
 
 | Compressor name         | Ratio | Compression| Decompress.|
@@ -56,8 +53,8 @@ on the [Silesia compression corpus].
 | lzf 3.6 -1              | 2.077 |   410 MB/s |   830 MB/s |
 | snappy 1.1.9            | 2.073 |   550 MB/s |  1750 MB/s |
 
-[zlib]: http://www.zlib.net/
-[lz4]: http://www.lz4.org/
+[zlib]: https://www.zlib.net/
+[lz4]: https://lz4.github.io/lz4/
 
 The negative compression levels, specified with `--fast=#`,
 offer faster compression and decompression speed
@@ -124,14 +121,27 @@ Dictionary gains are mostly effective in the first few KB. Then, the compression
 
 ## Build instructions
 
+`make` is the officially maintained build system of this project.
+All other build systems are "compatible" and 3rd-party maintained,
+they may feature small differences in advanced options.
+When your system allows it, prefer using `make` to build `zstd` and `libzstd`.
+
 ### Makefile
 
 If your system is compatible with standard `make` (or `gmake`),
 invoking `make` in root directory will generate `zstd` cli in root directory.
+It will also create `libzstd` into `lib/`.
 
 Other available options include:
 - `make install` : create and install zstd cli, library and man pages
-- `make check` : create and run `zstd`, tests its behavior on local platform
+- `make check` : create and run `zstd`, test its behavior on local platform
+
+The `Makefile` follows the [GNU Standard Makefile conventions](https://www.gnu.org/prep/standards/html_node/Makefile-Conventions.html),
+allowing staged install, standard flags, directory variables and command variables.
+
+For advanced use cases, specialized compilation flags which control binary generation
+are documented in [`lib/README.md`](lib/README.md#modular-build) for the `libzstd` library
+and in [`programs/README.md`](programs/README.md#compilation-variables) for the `zstd` CLI.
 
 ### cmake
 
@@ -141,6 +151,18 @@ to create `zstd` binary, and `libzstd` dynamic and static libraries.
 
 By default, `CMAKE_BUILD_TYPE` is set to `Release`.
 
+#### Support for Fat (Universal2) Output
+
+`zstd` can be built and installed with support for both Apple Silicon (M1/M2) as well as Intel by using CMake's Universal2 support.
+To perform a Fat/Universal2 build and install use the following commands:
+
+```bash
+cmake -B build-cmake-debug -S build/cmake -G Ninja -DCMAKE_OSX_ARCHITECTURES="x86_64;x86_64h;arm64"
+cd build-cmake-debug
+ninja
+sudo ninja install
+```
+
 ### Meson
 
 A Meson project is provided within [`build/meson`](build/meson). Follow
@@ -178,13 +200,15 @@ The output binary will be in `buck-out/gen/programs/`.
 
 ## Testing
 
-You can run quick local smoke tests by executing the `playTest.sh` script from the `src/tests` directory.
-Two env variables `$ZSTD_BIN` and `$DATAGEN_BIN` are needed for the test script to locate the zstd and datagen binary.
-For information on CI testing, please refer to TESTING.md
+You can run quick local smoke tests by running `make check`.
+If you can't use `make`, execute the `playTest.sh` script from the `src/tests` directory.
+Two env variables `$ZSTD_BIN` and `$DATAGEN_BIN` are needed for the test script to locate the `zstd` and `datagen` binary.
+For information on CI testing, please refer to `TESTING.md`.
 
 ## Status
 
-Zstandard is currently deployed within Facebook. It is used continuously to compress large amounts of data in multiple formats and use cases.
+Zstandard is currently deployed within Facebook and many other large cloud infrastructures.
+It is run continuously to compress large amounts of data in multiple formats and use cases.
 Zstandard is considered safe for production environments.
 
 ## License

zstd.mod/zstd/TESTING.md

@@ -22,7 +22,7 @@ They consist of the following tests:
   - `tests/playTests.sh --test-large-data`
   - Fuzzer tests: `tests/fuzzer.c`, `tests/zstreamtest.c`, and `tests/decodecorpus.c`
 - `tests/zstreamtest.c` under Tsan (streaming mode, including multithreaded mode)
-- Valgrind Test (`make -C tests valgrindTest`) (testing CLI and fuzzer under valgrind)
+- Valgrind Test (`make -C tests test-valgrind`) (testing CLI and fuzzer under `valgrind`)
 - Fuzzer tests (see above) on ARM, AArch64, PowerPC, and PowerPC64
 
 Long Tests

zstd.mod/zstd/build/VS2008/zstd/zstd.vcproj

@@ -384,6 +384,10 @@
 				RelativePath="..\..\..\programs\fileio.c"
 				>
 			</File>
+			<File
+                RelativePath="..\..\..\programs\fileio_asyncio.c"
+                >
+            </File>
 			<File
 				RelativePath="..\..\..\lib\compress\fse_compress.c"
 				>

zstd.mod/zstd/build/VS2010/libzstd-dll/libzstd-dll.rc

@@ -32,11 +32,11 @@ BEGIN
     BEGIN
         BLOCK "040904B0"
         BEGIN
-            VALUE "CompanyName", "Yann Collet, Facebook, Inc."
+            VALUE "CompanyName", "Meta Platforms, Inc."
             VALUE "FileDescription", "Zstandard - Fast and efficient compression algorithm"
             VALUE "FileVersion", ZSTD_VERSION_STRING
             VALUE "InternalName", "libzstd.dll"
-            VALUE "LegalCopyright", "Copyright (c) 2013-present, Yann Collet, Facebook, Inc."
+            VALUE "LegalCopyright", "Copyright (c) Meta Platforms, Inc. and affiliates."
             VALUE "OriginalFilename", "libzstd.dll"
             VALUE "ProductName", "Zstandard"
             VALUE "ProductVersion", ZSTD_VERSION_STRING

zstd.mod/zstd/build/VS2010/libzstd-dll/libzstd-dll.vcxproj

@@ -169,7 +169,6 @@
       <WarningLevel>Level4</WarningLevel>
       <Optimization>Disabled</Optimization>
       <PreprocessorDefinitions>ZSTD_DLL_EXPORT=1;ZSTD_MULTITHREAD=1;ZSTD_LEGACY_SUPPORT=5;WIN32;_DEBUG;_CONSOLE;_CRT_SECURE_NO_WARNINGS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
-      <MinimalRebuild>true</MinimalRebuild>
       <BasicRuntimeChecks>EnableFastChecks</BasicRuntimeChecks>
       <RuntimeLibrary>MultiThreadedDebugDLL</RuntimeLibrary>
       <DebugInformationFormat>EditAndContinue</DebugInformationFormat>

zstd.mod/zstd/build/VS2010/libzstd/libzstd.vcxproj

@@ -162,7 +162,6 @@
       <WarningLevel>Level4</WarningLevel>
       <Optimization>Disabled</Optimization>
       <PreprocessorDefinitions>ZSTD_MULTITHREAD=1;ZSTD_LEGACY_SUPPORT=5;WIN32;_DEBUG;_CONSOLE;_CRT_SECURE_NO_WARNINGS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
-      <MinimalRebuild>true</MinimalRebuild>
       <BasicRuntimeChecks>EnableFastChecks</BasicRuntimeChecks>
       <RuntimeLibrary>MultiThreadedDebugDLL</RuntimeLibrary>
       <DebugInformationFormat>EditAndContinue</DebugInformationFormat>

zstd.mod/zstd/build/VS2010/zstd/zstd.rc

@@ -32,11 +32,11 @@ BEGIN
     BEGIN
         BLOCK "040904B0"
         BEGIN
-            VALUE "CompanyName", "Yann Collet, Facebook, Inc."
+            VALUE "CompanyName", "Meta Platforms, Inc."
             VALUE "FileDescription", "Zstandard - Fast and efficient compression algorithm"
             VALUE "FileVersion", ZSTD_VERSION_STRING
             VALUE "InternalName", "zstd.exe"
-            VALUE "LegalCopyright", "Copyright (c) 2013-present, Yann Collet, Facebook, Inc."
+            VALUE "LegalCopyright", "Copyright (c) Meta Platforms, Inc. and affiliates."
             VALUE "OriginalFilename", "zstd.exe"
             VALUE "ProductName", "Zstandard"
             VALUE "ProductVersion", ZSTD_VERSION_STRING

zstd.mod/zstd/build/VS2010/zstd/zstd.vcxproj

@@ -62,6 +62,7 @@
     <ClCompile Include="..\..\..\programs\datagen.c" />
     <ClCompile Include="..\..\..\programs\dibio.c" />
     <ClCompile Include="..\..\..\programs\fileio.c" />
+    <ClCompile Include="..\..\..\programs\fileio_asyncio.c" />
     <ClCompile Include="..\..\..\programs\zstdcli.c" />
     <ClCompile Include="..\..\..\programs\zstdcli_trace.c" />
   </ItemGroup>
@@ -113,6 +114,7 @@
     <RootNamespace>zstd</RootNamespace>
     <OutDir>$(SolutionDir)bin\$(Platform)_$(Configuration)\</OutDir>
     <IntDir>$(SolutionDir)bin\obj\$(RootNamespace)_$(Platform)_$(Configuration)\</IntDir>
+    <InstructionSet>NotSet</InstructionSet>
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
@@ -186,6 +188,7 @@
       <PreprocessorDefinitions>ZSTD_MULTITHREAD=1;ZSTD_LEGACY_SUPPORT=5;WIN32;_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
       <TreatWarningAsError>true</TreatWarningAsError>
       <EnablePREfast>false</EnablePREfast>
+      <EnableEnhancedInstructionSet>$(InstructionSet)</EnableEnhancedInstructionSet>
     </ClCompile>
     <Link>
       <SubSystem>Console</SubSystem>
@@ -202,6 +205,7 @@
       <PreprocessorDefinitions>ZSTD_MULTITHREAD=1;ZSTD_LEGACY_SUPPORT=5;WIN32;_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
       <TreatWarningAsError>true</TreatWarningAsError>
       <EnablePREfast>false</EnablePREfast>
+      <EnableEnhancedInstructionSet>$(InstructionSet)</EnableEnhancedInstructionSet>
     </ClCompile>
     <Link>
       <SubSystem>Console</SubSystem>
@@ -221,6 +225,7 @@
       <EnablePREfast>false</EnablePREfast>
       <TreatWarningAsError>false</TreatWarningAsError>
       <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
+      <EnableEnhancedInstructionSet>$(InstructionSet)</EnableEnhancedInstructionSet>
     </ClCompile>
     <Link>
       <SubSystem>Console</SubSystem>
@@ -243,6 +248,7 @@
       <EnablePREfast>false</EnablePREfast>
       <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
       <AdditionalOptions>/DZSTD_MULTITHREAD %(AdditionalOptions)</AdditionalOptions>
+      <EnableEnhancedInstructionSet>$(InstructionSet)</EnableEnhancedInstructionSet>
     </ClCompile>
     <Link>
       <SubSystem>Console</SubSystem>

zstd.mod/zstd/build/cmake/CMakeLists.txt

@@ -1,5 +1,5 @@
 # ################################################################
-# Copyright (c) 2016-present, 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
@@ -8,18 +8,18 @@
 # ################################################################
 
 cmake_minimum_required(VERSION 2.8.12 FATAL_ERROR)
-  
-# As of 2018-12-26 ZSTD has been validated to build with cmake version 3.13.2 new policies. 
-# Set and use the newest cmake policies that are validated to work 
-set(ZSTD_MAX_VALIDATED_CMAKE_MAJOR_VERSION "3") 
+
+# As of 2018-12-26 ZSTD has been validated to build with cmake version 3.13.2 new policies.
+# Set and use the newest cmake policies that are validated to work
+set(ZSTD_MAX_VALIDATED_CMAKE_MAJOR_VERSION "3")
 set(ZSTD_MAX_VALIDATED_CMAKE_MINOR_VERSION "13") #Policies never changed at PATCH level
 if("${CMAKE_MAJOR_VERSION}" LESS 3)
-  set(ZSTD_CMAKE_POLICY_VERSION "${CMAKE_VERSION}") 
-elseif( "${ZSTD_MAX_VALIDATED_CMAKE_MAJOR_VERSION}" EQUAL "${CMAKE_MAJOR_VERSION}" AND 
+  set(ZSTD_CMAKE_POLICY_VERSION "${CMAKE_VERSION}")
+elseif( "${ZSTD_MAX_VALIDATED_CMAKE_MAJOR_VERSION}" EQUAL "${CMAKE_MAJOR_VERSION}" AND
         "${ZSTD_MAX_VALIDATED_CMAKE_MINOR_VERSION}" GREATER "${CMAKE_MINOR_VERSION}")
-    set(ZSTD_CMAKE_POLICY_VERSION "${CMAKE_VERSION}") 
-else() 
-    set(ZSTD_CMAKE_POLICY_VERSION "${ZSTD_MAX_VALIDATED_CMAKE_MAJOR_VERSION}.${ZSTD_MAX_VALIDATED_CMAKE_MINOR_VERSION}.0") 
+    set(ZSTD_CMAKE_POLICY_VERSION "${CMAKE_VERSION}")
+else()
+    set(ZSTD_CMAKE_POLICY_VERSION "${ZSTD_MAX_VALIDATED_CMAKE_MAJOR_VERSION}.${ZSTD_MAX_VALIDATED_CMAKE_MINOR_VERSION}.0")
 endif()
 cmake_policy(VERSION ${ZSTD_CMAKE_POLICY_VERSION})
 
@@ -40,16 +40,18 @@ if( CMAKE_MAJOR_VERSION LESS 3 )
   set(PROJECT_VERSION_PATCH ${zstd_VERSION_PATCH})
   set(PROJECT_VERSION "${zstd_VERSION_MAJOR}.${zstd_VERSION_MINOR}.${zstd_VERSION_PATCH}")
   enable_language(C)   # Main library is in C
+  enable_language(ASM) # And ASM
   enable_language(CXX) # Testing contributed code also utilizes CXX
 else()
   project(zstd
     VERSION "${zstd_VERSION_MAJOR}.${zstd_VERSION_MINOR}.${zstd_VERSION_PATCH}"
     LANGUAGES C   # Main library is in C
+              ASM # And ASM
               CXX # Testing contributed code also utilizes CXX
     )
 endif()
 message(STATUS "ZSTD VERSION: ${zstd_VERSION}")
-set(zstd_HOMEPAGE_URL "http://www.zstd.net")
+set(zstd_HOMEPAGE_URL "https://facebook.github.io/zstd")
 set(zstd_DESCRIPTION  "Zstandard is a real-time compression algorithm, providing high compression ratios.")
 
 # Set a default build type if none was specified
@@ -82,11 +84,12 @@ message(STATUS "CMAKE_INSTALL_LIBDIR: ${CMAKE_INSTALL_LIBDIR}")
 #-----------------------------------------------------------------------------
 
 # Legacy support
-option(ZSTD_LEGACY_SUPPORT "LEGACY SUPPORT" OFF)
+option(ZSTD_LEGACY_SUPPORT "LEGACY SUPPORT" ON)
 
 if (ZSTD_LEGACY_SUPPORT)
     message(STATUS "ZSTD_LEGACY_SUPPORT defined!")
-    add_definitions(-DZSTD_LEGACY_SUPPORT=5)
+    set(ZSTD_LEGACY_LEVEL 5 CACHE STRING "")
+    add_definitions(-DZSTD_LEGACY_SUPPORT=${ZSTD_LEGACY_LEVEL})
 else ()
     message(STATUS "ZSTD_LEGACY_SUPPORT not defined!")
     add_definitions(-DZSTD_LEGACY_SUPPORT=0)

zstd.mod/zstd/build/cmake/CMakeModules/AddZstdCompilationFlags.cmake

@@ -1,7 +1,17 @@
 include(CheckCXXCompilerFlag)
 include(CheckCCompilerFlag)
+# VERSION_GREATER_EQUAL requires CMake 3.7 or later.
+# https://cmake.org/cmake/help/latest/command/if.html#version-greater-equal
+if (CMAKE_VERSION VERSION_LESS 3.18)
+    set(ZSTD_HAVE_CHECK_LINKER_FLAG false)
+else ()
+    set(ZSTD_HAVE_CHECK_LINKER_FLAG true)
+endif ()
+if (ZSTD_HAVE_CHECK_LINKER_FLAG)
+    include(CheckLinkerFlag)
+endif()
 
-function(EnableCompilerFlag _flag _C _CXX)
+function(EnableCompilerFlag _flag _C _CXX _LD)
     string(REGEX REPLACE "\\+" "PLUS" varname "${_flag}")
     string(REGEX REPLACE "[^A-Za-z0-9]+" "_" varname "${varname}")
     string(REGEX REPLACE "^_+" "" varname "${varname}")
@@ -18,43 +28,71 @@ function(EnableCompilerFlag _flag _C _CXX)
             set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${_flag}" PARENT_SCOPE)
         endif ()
     endif ()
+    if (_LD)
+        # We never add a linker flag with CMake < 3.18. We will
+        # implement CHECK_LINKER_FLAG() like feature for CMake < 3.18
+        # or require CMake >= 3.18 when we need to add a required
+        # linker flag in future.
+        #
+        # We also skip linker flags check for MSVC compilers (which includes
+        # clang-cl) since currently check_linker_flag() doesn't give correct
+        # results for this configuration,
+        # see: https://gitlab.kitware.com/cmake/cmake/-/issues/22023
+        if (ZSTD_HAVE_CHECK_LINKER_FLAG AND NOT MSVC)
+            CHECK_LINKER_FLAG(C ${_flag} LD_FLAG_${varname})
+        else ()
+            set(LD_FLAG_${varname} false)
+        endif ()
+        if (LD_FLAG_${varname})
+            set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} ${_flag}" PARENT_SCOPE)
+            set(CMAKE_SHARED_LINKER_FLAGS "${CMAKE_SHARED_LINKER_FLAGS} ${_flag}" PARENT_SCOPE)
+        endif ()
+    endif ()
 endfunction()
 
 macro(ADD_ZSTD_COMPILATION_FLAGS)
     if (CMAKE_CXX_COMPILER_ID MATCHES "GNU|Clang" OR MINGW) #Not only UNIX but also WIN32 for MinGW
-        #Set c++11 by default
-        EnableCompilerFlag("-std=c++11" false true)
-        #Set c99 by default
-        EnableCompilerFlag("-std=c99" true false)
+        # It's possible to select the exact standard used for compilation.
+        # It's not necessary, but can be employed for specific purposes.
+        # Note that zstd source code is compatible with both C++98 and above
+        # and C-gnu90 (c90 + long long + variadic macros ) and above
+        # EnableCompilerFlag("-std=c++11" false true) # Set C++ compilation to c++11 standard
+        # EnableCompilerFlag("-std=c99" true false)   # Set C compiation to c99 standard
         if (CMAKE_CXX_COMPILER_ID MATCHES "Clang" AND MSVC)
             # clang-cl normally maps -Wall to -Weverything.
-            EnableCompilerFlag("/clang:-Wall" true true)
+            EnableCompilerFlag("/clang:-Wall" true true false)
         else ()
-            EnableCompilerFlag("-Wall" true true)
+            EnableCompilerFlag("-Wall" true true false)
         endif ()
-        EnableCompilerFlag("-Wextra" true true)
-        EnableCompilerFlag("-Wundef" true true)
-        EnableCompilerFlag("-Wshadow" true true)
-        EnableCompilerFlag("-Wcast-align" true true)
-        EnableCompilerFlag("-Wcast-qual" true true)
-        EnableCompilerFlag("-Wstrict-prototypes" true false)
+        EnableCompilerFlag("-Wextra" true true false)
+        EnableCompilerFlag("-Wundef" true true false)
+        EnableCompilerFlag("-Wshadow" true true false)
+        EnableCompilerFlag("-Wcast-align" true true false)
+        EnableCompilerFlag("-Wcast-qual" true true false)
+        EnableCompilerFlag("-Wstrict-prototypes" true false false)
         # Enable asserts in Debug mode
         if (CMAKE_BUILD_TYPE MATCHES "Debug")
-            EnableCompilerFlag("-DDEBUGLEVEL=1" true true)
+            EnableCompilerFlag("-DDEBUGLEVEL=1" true true false)
         endif ()
+        # Add noexecstack flags
+        # LDFLAGS
+        EnableCompilerFlag("-z noexecstack" false false true)
+        # CFLAGS & CXXFLAGS
+        EnableCompilerFlag("-Qunused-arguments" true true false)
+        EnableCompilerFlag("-Wa,--noexecstack" true true false)
     elseif (MSVC) # Add specific compilation flags for Windows Visual
 
         set(ACTIVATE_MULTITHREADED_COMPILATION "ON" CACHE BOOL "activate multi-threaded compilation (/MP flag)")
         if (CMAKE_GENERATOR MATCHES "Visual Studio" AND ACTIVATE_MULTITHREADED_COMPILATION)
-            EnableCompilerFlag("/MP" true true)
+            EnableCompilerFlag("/MP" true true false)
         endif ()
-        
+
         # UNICODE SUPPORT
-        EnableCompilerFlag("/D_UNICODE" true true)
-        EnableCompilerFlag("/DUNICODE" true true)
+        EnableCompilerFlag("/D_UNICODE" true true false)
+        EnableCompilerFlag("/DUNICODE" true true false)
         # Enable asserts in Debug mode
         if (CMAKE_BUILD_TYPE MATCHES "Debug")
-            EnableCompilerFlag("/DDEBUGLEVEL=1" true true)
+            EnableCompilerFlag("/DDEBUGLEVEL=1" true true false)
         endif ()
     endif ()
 

zstd.mod/zstd/build/cmake/CMakeModules/JoinPaths.cmake

@@ -0,0 +1,23 @@
+# This module provides function for joining paths
+# known from most languages
+#
+# SPDX-License-Identifier: (MIT OR CC0-1.0)
+# Copyright 2020 Jan Tojnar
+# https://github.com/jtojnar/cmake-snips
+#
+# Modelled after Python’s os.path.join
+# https://docs.python.org/3.7/library/os.path.html#os.path.join
+# Windows not supported
+function(join_paths joined_path first_path_segment)
+    set(temp_path "${first_path_segment}")
+    foreach(current_segment IN LISTS ARGN)
+        if(NOT ("${current_segment}" STREQUAL ""))
+            if(IS_ABSOLUTE "${current_segment}")
+                set(temp_path "${current_segment}")
+            else()
+                set(temp_path "${temp_path}/${current_segment}")
+            endif()
+        endif()
+    endforeach()
+    set(${joined_path} "${temp_path}" PARENT_SCOPE)
+endfunction()

zstd.mod/zstd/build/cmake/README.md

@@ -1,13 +1,13 @@
 # Cmake contributions
 
 Contributions to the cmake build configurations are welcome. Please
-use case sensitivity that matches modern (ie. cmake version 2.6 and above)
+use case sensitivity that matches modern (i.e. cmake version 2.6 and above)
 conventions of using lower-case for commands, and upper-case for
 variables.
 
 ## How to build
 
-As cmake doesn't support command like `cmake clean`, it's recommended to perform a "out of source build".
+As cmake doesn't support command like `cmake clean`, it's recommended to perform an "out of source build".
 To do this, you can create a new directory and build in it:
 ```sh
 cd build/cmake
@@ -37,7 +37,7 @@ cmake -LH ..
 Bool options can be set to `ON/OFF` with `-D[option]=[ON/OFF]`. You can configure cmake options like this:
 ```sh
 cd build/cmake/builddir
-cmake -DZSTD_BUILD_TESTS=ON -DZSTD_LEGACY_SUPPORT=ON ..
+cmake -DZSTD_BUILD_TESTS=ON -DZSTD_LEGACY_SUPPORT=OFF ..
 make
 ```
 

zstd.mod/zstd/build/cmake/contrib/CMakeLists.txt

@@ -1,5 +1,5 @@
 # ################################################################
-# Copyright (c) 2016-present, 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

zstd.mod/zstd/build/cmake/contrib/gen_html/CMakeLists.txt

@@ -1,5 +1,5 @@
 # ################################################################
-# Copyright (c) 2015-present, 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

zstd.mod/zstd/build/cmake/contrib/pzstd/CMakeLists.txt

@@ -1,5 +1,5 @@
 # ################################################################
-# Copyright (c) 2016-present, 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

zstd.mod/zstd/build/cmake/lib/CMakeLists.txt

@@ -1,5 +1,5 @@
 # ################################################################
-# Copyright (c) 2015-present, 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
@@ -77,6 +77,12 @@ if (MSVC)
     set(PlatformDependResources ${MSVC_RESOURCE_DIR}/libzstd-dll.rc)
 endif ()
 
+# Explicitly set the language to C for all files, including ASM files.
+# Our assembly expects to be compiled by a C compiler, and is only enabled for
+# __GNUC__ compatible compilers. Otherwise all the ASM code is disabled by
+# macros.
+set_source_files_properties(${Sources} PROPERTIES LANGUAGE C)
+
 # Split project to static and shared libraries build
 set(library_targets)
 if (ZSTD_BUILD_SHARED)
@@ -135,30 +141,17 @@ if (ZSTD_BUILD_STATIC)
             OUTPUT_NAME ${STATIC_LIBRARY_BASE_NAME})
 endif ()
 
-if (UNIX OR MINGW)
-    # pkg-config
-    set(PREFIX "${CMAKE_INSTALL_PREFIX}")
-    set(EXEC_PREFIX "\${prefix}")
-    set(LIBDIR "${CMAKE_INSTALL_FULL_LIBDIR}")
-    set(INCLUDEDIR "${CMAKE_INSTALL_FULL_INCLUDEDIR}")
-    set(VERSION "${zstd_VERSION}")
-
-    string(LENGTH "${PREFIX}" PREFIX_LENGTH)
-    string(SUBSTRING "${LIBDIR}" 0 ${PREFIX_LENGTH} LIBDIR_PREFIX)
-    string(SUBSTRING "${LIBDIR}" ${PREFIX_LENGTH} -1 LIBDIR_SUFFIX)
-    string(SUBSTRING "${INCLUDEDIR}" 0 ${PREFIX_LENGTH} INCLUDEDIR_PREFIX)
-    string(SUBSTRING "${INCLUDEDIR}" ${PREFIX_LENGTH} -1 INCLUDEDIR_SUFFIX)
-
-    if ("${INCLUDEDIR_PREFIX}" STREQUAL "${PREFIX}")
-        set(INCLUDEDIR "\${prefix}${INCLUDEDIR_SUFFIX}")
-    endif()
-    if ("${LIBDIR_PREFIX}" STREQUAL "${PREFIX}")
-        set(LIBDIR "\${exec_prefix}${LIBDIR_SUFFIX}")
-    endif()
-
-    configure_file("${LIBRARY_DIR}/libzstd.pc.in" "${CMAKE_CURRENT_BINARY_DIR}/libzstd.pc" @ONLY)
-    install(FILES "${CMAKE_CURRENT_BINARY_DIR}/libzstd.pc" DESTINATION "${CMAKE_INSTALL_LIBDIR}/pkgconfig")
-endif ()
+# pkg-config
+include(JoinPaths) # can be replaced by cmake_path(APPEND) in CMake 3.20
+set(PREFIX "${CMAKE_INSTALL_PREFIX}")
+set(EXEC_PREFIX "\${prefix}")
+join_paths(LIBDIR "\${exec_prefix}" "${CMAKE_INSTALL_LIBDIR}")
+join_paths(INCLUDEDIR "\${prefix}" "${CMAKE_INSTALL_INCLUDEDIR}")
+set(LIBS_PRIVATE "${THREADS_LIBS}")
+set(VERSION "${zstd_VERSION}")
+
+configure_file("${LIBRARY_DIR}/libzstd.pc.in" "${CMAKE_CURRENT_BINARY_DIR}/libzstd.pc" @ONLY)
+install(FILES "${CMAKE_CURRENT_BINARY_DIR}/libzstd.pc" DESTINATION "${CMAKE_INSTALL_LIBDIR}/pkgconfig")
 
 # install target
 install(FILES

zstd.mod/zstd/build/cmake/programs/CMakeLists.txt

@@ -1,5 +1,5 @@
 # ################################################################
-# Copyright (c) 2015-present, 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
@@ -32,7 +32,7 @@ if (MSVC)
     set(PlatformDependResources ${MSVC_RESOURCE_DIR}/zstd.rc)
 endif ()
 
-add_executable(zstd ${PROGRAMS_DIR}/zstdcli.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/timefn.c ${PROGRAMS_DIR}/fileio.c ${PROGRAMS_DIR}/benchfn.c ${PROGRAMS_DIR}/benchzstd.c ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/dibio.c ${PROGRAMS_DIR}/zstdcli_trace.c ${PlatformDependResources})
+add_executable(zstd ${PROGRAMS_DIR}/zstdcli.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/timefn.c ${PROGRAMS_DIR}/fileio.c ${PROGRAMS_DIR}/fileio_asyncio.c ${PROGRAMS_DIR}/benchfn.c ${PROGRAMS_DIR}/benchzstd.c ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/dibio.c ${PROGRAMS_DIR}/zstdcli_trace.c ${PlatformDependResources})
 target_link_libraries(zstd ${PROGRAMS_ZSTD_LINK_TARGET})
 if (CMAKE_SYSTEM_NAME MATCHES "(Solaris|SunOS)")
     target_link_libraries(zstd rt)
@@ -75,7 +75,7 @@ if (UNIX)
         ${CMAKE_CURRENT_BINARY_DIR}/zstdless.1
         DESTINATION "${MAN_INSTALL_DIR}")
 
-    add_executable(zstd-frugal ${PROGRAMS_DIR}/zstdcli.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/timefn.c ${PROGRAMS_DIR}/fileio.c)
+    add_executable(zstd-frugal ${PROGRAMS_DIR}/zstdcli.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/timefn.c ${PROGRAMS_DIR}/fileio.c ${PROGRAMS_DIR}/fileio_asyncio.c)
     target_link_libraries(zstd-frugal ${PROGRAMS_ZSTD_LINK_TARGET})
     set_property(TARGET zstd-frugal APPEND PROPERTY COMPILE_DEFINITIONS "ZSTD_NOBENCH;ZSTD_NODICT;ZSTD_NOTRACE")
 endif ()

zstd.mod/zstd/build/cmake/tests/CMakeLists.txt

@@ -1,6 +1,6 @@
 # ################################################################
 # zstd - Makefile
-# Copyright (C) Yann Collet 2014-present
+# Copyright (c) Meta Platforms, Inc. and affiliates.
 # All rights reserved.
 #
 # BSD license
@@ -27,7 +27,7 @@
 # SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #
 # You can contact the author at :
-#  - zstd homepage : http://www.zstd.net/
+#  - zstd homepage : https://facebook.github.io/zstd/
 # ################################################################
 
 project(tests)
@@ -57,7 +57,9 @@ target_link_libraries(datagen libzstd_static)
 # fullbench
 #
 add_executable(fullbench ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/timefn.c ${PROGRAMS_DIR}/benchfn.c ${PROGRAMS_DIR}/benchzstd.c ${TESTS_DIR}/fullbench.c)
-set_property(TARGET fullbench APPEND PROPERTY COMPILE_OPTIONS "-Wno-deprecated-declarations")
+if (NOT MSVC)
+    target_compile_options(fullbench PRIVATE "-Wno-deprecated-declarations")
+endif()
 target_link_libraries(fullbench libzstd_static)
 add_test(NAME fullbench COMMAND fullbench ${ZSTD_FULLBENCH_FLAGS})
 
@@ -65,7 +67,9 @@ add_test(NAME fullbench COMMAND fullbench ${ZSTD_FULLBENCH_FLAGS})
 # fuzzer
 #
 add_executable(fuzzer ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/timefn.c ${TESTS_DIR}/fuzzer.c)
-set_property(TARGET fuzzer APPEND PROPERTY COMPILE_OPTIONS "-Wno-deprecated-declarations")
+if (NOT MSVC)
+    target_compile_options(fuzzer PRIVATE "-Wno-deprecated-declarations")
+endif()
 target_link_libraries(fuzzer libzstd_static)
 AddTestFlagsOption(ZSTD_FUZZER_FLAGS "$ENV{FUZZERTEST} $ENV{FUZZER_FLAGS}"
     "Semicolon-separated list of flags to pass to the fuzzer test (see `fuzzer -h` for usage)")
@@ -77,8 +81,10 @@ add_test(NAME fuzzer COMMAND fuzzer ${ZSTD_FUZZER_FLAGS})
 #
 # zstreamtest
 #
-add_executable(zstreamtest ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/timefn.c ${TESTS_DIR}/seqgen.c ${TESTS_DIR}/zstreamtest.c)
-set_property(TARGET zstreamtest APPEND PROPERTY COMPILE_OPTIONS "-Wno-deprecated-declarations")
+add_executable(zstreamtest ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/timefn.c ${TESTS_DIR}/seqgen.c ${TESTS_DIR}/zstreamtest.c ${TESTS_DIR}/external_matchfinder.c)
+if (NOT MSVC)
+    target_compile_options(zstreamtest PRIVATE "-Wno-deprecated-declarations")
+endif()
 target_link_libraries(zstreamtest libzstd_static)
 AddTestFlagsOption(ZSTD_ZSTREAM_FLAGS "$ENV{ZSTREAM_TESTTIME} $ENV{FUZZER_FLAGS}"
     "Semicolon-separated list of flags to pass to the zstreamtest test (see `zstreamtest -h` for usage)")
@@ -90,13 +96,14 @@ add_test(NAME zstreamtest COMMAND zstreamtest ${ZSTD_ZSTREAM_FLAGS})
 AddTestFlagsOption(ZSTD_PLAYTESTS_FLAGS "$ENV{PLAYTESTS_FLAGS}"
     "Semicolon-separated list of flags to pass to the playTests.sh test")
 add_test(NAME playTests COMMAND sh -c "\"${TESTS_DIR}/playTests.sh\" ${ZSTD_PLAYTESTS_FLAGS}")
-if (ZSTD_BUILD_PROGRAMS)
+find_program(UNAME uname) # Run script only in unix shell environments
+if (ZSTD_BUILD_PROGRAMS AND UNAME)
     set_property(TEST playTests APPEND PROPERTY ENVIRONMENT
         "ZSTD_BIN=$<TARGET_FILE:zstd>"
         "DATAGEN_BIN=$<TARGET_FILE:datagen>"
         )
 else()
-    message(STATUS "Disabling playTests.sh test because ZSTD_BUILD_PROGRAMS is not enabled")
+    message(STATUS "Disabling playTests.sh test because requirements not met")
     set_tests_properties(playTests PROPERTIES DISABLED YES)
 endif()
 

zstd.mod/zstd/build/meson/contrib/pzstd/meson.build

@@ -18,7 +18,8 @@ pzstd_sources = [join_paths(zstd_rootdir, 'programs/util.c'),
   join_paths(zstd_rootdir, 'contrib/pzstd/SkippableFrame.cpp')]
 pzstd = executable('pzstd',
   pzstd_sources,
-  cpp_args: [ '-DNDEBUG', '-Wno-shadow', '-Wno-deprecated-declarations' ],
+  cpp_args: pzstd_warning_flags,
   include_directories: pzstd_includes,
   dependencies: [ libzstd_dep, thread_dep ],
+  override_options: ['b_ndebug=true'],
   install: true)

zstd.mod/zstd/build/meson/lib/meson.build

@@ -47,7 +47,7 @@ libzstd_sources = [join_paths(zstd_rootdir, 'lib/common/entropy_common.c'),
 
 # really we need anything that defines __GNUC__ as that is what ZSTD_ASM_SUPPORTED is gated on
 # but these are the two compilers that are supported in tree and actually handle this correctly
-# Otherwise, explicitly disable assmebly.
+# Otherwise, explicitly disable assembly.
 if [compiler_gcc, compiler_clang].contains(cc_id)
   libzstd_sources += join_paths(zstd_rootdir, 'lib/decompress/huf_decompress_amd64.S')
 else
@@ -83,7 +83,8 @@ libzstd_c_args = []
 if cc_id == compiler_msvc
   if default_library_type != 'static'
     libzstd_sources += [windows_mod.compile_resources(
-      join_paths(zstd_rootdir, 'build/VS2010/libzstd-dll/libzstd-dll.rc'))]
+      join_paths(zstd_rootdir, 'build/VS2010/libzstd-dll/libzstd-dll.rc'),
+      include_directories: libzstd_includes)]
     libzstd_c_args += ['-DZSTD_DLL_EXPORT=1',
       '-DZSTD_HEAPMODE=0',
       '-D_CONSOLE',
@@ -125,12 +126,41 @@ libzstd = library('zstd',
 libzstd_dep = declare_dependency(link_with: libzstd,
   include_directories: libzstd_includes)
 
+# we link to both:
+# - the shared library (for public symbols)
+# - the static library (for private symbols)
+#
+# this is needed because internally private symbols are used all the time, and
+# -fvisibility=hidden means those cannot be found
+if get_option('default_library') == 'static'
+  libzstd_static = libzstd
+  libzstd_internal_dep = libzstd_dep
+else
+  if get_option('default_library') == 'shared'
+    libzstd_static = static_library('zstd_objlib',
+      objects: libzstd.extract_all_objects(recursive: true),
+      build_by_default: false)
+  else
+    libzstd_static = libzstd.get_static_lib()
+  endif
+
+  if cc_id == compiler_msvc
+    # msvc does not actually support linking to both, but errors out with:
+    #   error LNK2005: ZSTD_<foo> already defined in zstd.lib(zstd-1.dll)
+    libzstd_internal_dep = declare_dependency(link_with: libzstd_static)
+  else
+    libzstd_internal_dep = declare_dependency(link_with: libzstd,
+      # the static library must be linked after the shared one
+      dependencies: declare_dependency(link_with: libzstd_static))
+  endif
+endif
+
 pkgconfig.generate(libzstd,
   name: 'libzstd',
   filebase: 'libzstd',
   description: 'fast lossless compression algorithm library',
   version: zstd_libversion,
-  url: 'http://www.zstd.net/')
+  url: 'https://facebook.github.io/zstd/')
 
 install_headers(join_paths(zstd_rootdir, 'lib/zstd.h'),
   join_paths(zstd_rootdir, 'lib/zdict.h'),

zstd.mod/zstd/build/meson/meson.build

@@ -12,7 +12,10 @@ project('zstd',
   ['c', 'cpp'],
   license: ['BSD', 'GPLv2'],
   default_options : [
-    'c_std=gnu99',
+    # There shouldn't be any need to force a C standard convention for zstd
+    # but in case one would want that anyway, this can be done here.
+    # 'c_std=gnu99',
+    # c++11 standard is useful for pzstd
     'cpp_std=c++11',
     'buildtype=release',
     'warning_level=3',
@@ -20,8 +23,10 @@ project('zstd',
     # so this isn't safe
     #'werror=true'
   ],
-  version: 'DUMMY',
-  meson_version: '>=0.48.0')
+  version: run_command(
+    find_program('GetZstdLibraryVersion.py'), '../../lib/zstd.h',
+    check: true).stdout().strip(),
+  meson_version: '>=0.50.0')
 
 cc = meson.get_compiler('c')
 cxx = meson.get_compiler('cpp')
@@ -42,16 +47,6 @@ compiler_msvc = 'msvc'
 
 zstd_version = meson.project_version()
 
-zstd_h_file = join_paths(meson.current_source_dir(), '../../lib/zstd.h')
-GetZstdLibraryVersion_py = find_program('GetZstdLibraryVersion.py', native : true)
-r = run_command(GetZstdLibraryVersion_py, zstd_h_file)
-if r.returncode() == 0
-  zstd_version = r.stdout().strip()
-  message('Project version is now: @0@'.format(zstd_version))
-else
-  error('Cannot find project version in @0@'.format(zstd_h_file))
-endif
-
 zstd_libversion = zstd_version
 
 # =============================================================================
@@ -92,7 +87,7 @@ feature_lz4 = get_option('lz4')
 # Dependencies
 # =============================================================================
 
-libm_dep = cc.find_library('m', required: bin_tests)
+libm_dep = cc.find_library('m', required: false)
 thread_dep = dependency('threads', required: feature_multi_thread)
 use_multi_thread = thread_dep.found()
 # Arguments in dependency should be equivalent to those passed to pkg-config
@@ -109,8 +104,10 @@ use_lz4 = lz4_dep.found()
 
 add_project_arguments('-DXXH_NAMESPACE=ZSTD_', language: ['c'])
 
+pzstd_warning_flags = []
 if [compiler_gcc, compiler_clang].contains(cc_id)
   common_warning_flags = [ '-Wundef', '-Wshadow', '-Wcast-align', '-Wcast-qual' ]
+  pzstd_warning_flags = ['-Wno-shadow', '-Wno-deprecated-declarations']
   if cc_id == compiler_clang
     common_warning_flags += ['-Wconversion', '-Wno-sign-conversion', '-Wdocumentation']
   endif
@@ -135,7 +132,7 @@ endif
 
 subdir('lib')
 
-if bin_programs
+if bin_programs or bin_tests
   subdir('programs')
 endif
 

zstd.mod/zstd/build/meson/meson_options.txt

@@ -14,7 +14,7 @@ option('legacy_level', type: 'integer', min: 0, max: 7, value: 5,
   description: 'Support any legacy format: 7 to 1 for v0.7+ to v0.1+')
 option('debug_level', type: 'integer', min: 0, max: 9, value: 1,
   description: 'Enable run-time debug. See lib/common/debug.h')
-option('backtrace', type: 'boolean', value: false,
+option('backtrace', type: 'feature', value: 'disabled',
   description: 'Display a stack backtrace when execution generates a runtime exception')
 option('static_runtime', type: 'boolean', value: false,
   description: 'Link to static run-time libraries on MSVC')

zstd.mod/zstd/build/meson/programs/meson.build

@@ -14,20 +14,26 @@ zstd_programs_sources = [join_paths(zstd_rootdir, 'programs/zstdcli.c'),
   join_paths(zstd_rootdir, 'programs/util.c'),
   join_paths(zstd_rootdir, 'programs/timefn.c'),
   join_paths(zstd_rootdir, 'programs/fileio.c'),
+  join_paths(zstd_rootdir, 'programs/fileio_asyncio.c'),
   join_paths(zstd_rootdir, 'programs/benchfn.c'),
   join_paths(zstd_rootdir, 'programs/benchzstd.c'),
   join_paths(zstd_rootdir, 'programs/datagen.c'),
   join_paths(zstd_rootdir, 'programs/dibio.c'),
-  join_paths(zstd_rootdir, 'programs/zstdcli_trace.c'),
-  # needed due to use of private symbol + -fvisibility=hidden
-  join_paths(zstd_rootdir, 'lib/common/xxhash.c')]
+  join_paths(zstd_rootdir, 'programs/zstdcli_trace.c')]
 
+zstd_deps = [ libzstd_internal_dep ]
 zstd_c_args = libzstd_debug_cflags
+
+zstd_frugal_deps = [ libzstd_internal_dep ]
+zstd_frugal_c_args = [ '-DZSTD_NOBENCH', '-DZSTD_NODICT', '-DZSTD_NOTRACE' ]
+
 if use_multi_thread
+  zstd_deps += [ thread_dep ]
   zstd_c_args += [ '-DZSTD_MULTITHREAD' ]
+  zstd_frugal_deps += [ thread_dep ]
+  zstd_frugal_c_args += [ '-DZSTD_MULTITHREAD' ]
 endif
 
-zstd_deps = [ libzstd_dep ]
 if use_zlib
   zstd_deps += [ zlib_dep ]
   zstd_c_args += [ '-DZSTD_GZCOMPRESS', '-DZSTD_GZDECOMPRESS' ]
@@ -45,7 +51,8 @@ endif
 
 export_dynamic_on_windows = false
 # explicit backtrace enable/disable for Linux & Darwin
-if not use_backtrace
+have_execinfo = cc.has_header('execinfo.h', required: use_backtrace)
+if not have_execinfo
   zstd_c_args += '-DBACKTRACE_ENABLE=0'
 elif use_debug and host_machine_os == os_windows  # MinGW target
   zstd_c_args += '-DBACKTRACE_ENABLE=1'
@@ -55,7 +62,8 @@ endif
 if cc_id == compiler_msvc
   if default_library_type != 'static'
     zstd_programs_sources += [windows_mod.compile_resources(
-      join_paths(zstd_rootdir, 'build/VS2010/zstd/zstd.rc'))]
+      join_paths(zstd_rootdir, 'build/VS2010/zstd/zstd.rc'),
+      include_directories: libzstd_includes)]
   endif
 endif
 
@@ -64,19 +72,27 @@ zstd = executable('zstd',
   c_args: zstd_c_args,
   dependencies: zstd_deps,
   export_dynamic: export_dynamic_on_windows, # Since Meson 0.45.0
-  install: true)
+  build_by_default: bin_programs,
+  install: bin_programs)
+
+if not bin_programs
+  # we generate rules to build the programs, but don't install anything
+  # so do not continue to installing scripts and manpages
+  subdir_done()
+endif
 
 zstd_frugal_sources = [join_paths(zstd_rootdir, 'programs/zstdcli.c'),
   join_paths(zstd_rootdir, 'programs/timefn.c'),
   join_paths(zstd_rootdir, 'programs/util.c'),
-  join_paths(zstd_rootdir, 'programs/fileio.c')]
+  join_paths(zstd_rootdir, 'programs/fileio.c'),
+  join_paths(zstd_rootdir, 'programs/fileio_asyncio.c')]
 
 # Minimal target, with only zstd compression and decompression.
 # No bench. No legacy.
 executable('zstd-frugal',
   zstd_frugal_sources,
-  dependencies: libzstd_dep,
-  c_args: [ '-DZSTD_NOBENCH', '-DZSTD_NODICT', '-DZSTD_NOTRACE' ],
+  dependencies: zstd_frugal_deps,
+  c_args: zstd_frugal_c_args,
   install: true)
 
 install_data(join_paths(zstd_rootdir, 'programs/zstdgrep'),

zstd.mod/zstd/build/meson/tests/meson.build

@@ -21,7 +21,6 @@ FUZZER_FLAGS = ['--no-big-tests']
 FUZZERTEST = '-T200s'
 ZSTREAM_TESTTIME = '-T90s'
 DECODECORPUS_TESTTIME = '-T30'
-ZSTDRTTEST = ['--test-large-data']
 
 # =============================================================================
 # Executables
@@ -38,7 +37,7 @@ testcommon_sources = [join_paths(zstd_rootdir, 'programs/datagen.c'),
 testcommon = static_library('testcommon',
   testcommon_sources,
   # needed due to use of private symbol + -fvisibility=hidden
-  objects: libzstd.extract_all_objects(recursive: false))
+  link_with: libzstd_static)
 
 testcommon_dep = declare_dependency(link_with: testcommon,
   dependencies: libzstd_deps,
@@ -66,8 +65,10 @@ fuzzer = executable('fuzzer',
   dependencies: [ testcommon_dep, thread_dep ],
   install: false)
 
-zstreamtest_sources = [join_paths(zstd_rootdir, 'tests/seqgen.c'),
-  join_paths(zstd_rootdir, 'tests/zstreamtest.c')]
+zstreamtest_sources = [
+  join_paths(zstd_rootdir, 'tests/seqgen.c'),
+  join_paths(zstd_rootdir, 'tests/zstreamtest.c'),
+  join_paths(zstd_rootdir, 'tests/external_matchfinder.c')]
 zstreamtest = executable('zstreamtest',
   zstreamtest_sources,
   include_directories: test_includes,
@@ -116,11 +117,7 @@ decodecorpus = executable('decodecorpus',
   dependencies: [ testcommon_dep, libm_dep ],
   install: false)
 
-poolTests_sources = [join_paths(zstd_rootdir, 'tests/poolTests.c'),
-  join_paths(zstd_rootdir, 'lib/common/pool.c'),
-  join_paths(zstd_rootdir, 'lib/common/threading.c'),
-  join_paths(zstd_rootdir, 'lib/common/zstd_common.c'),
-  join_paths(zstd_rootdir, 'lib/common/error_private.c')]
+poolTests_sources = [join_paths(zstd_rootdir, 'tests/poolTests.c')]
 poolTests = executable('poolTests',
   poolTests_sources,
   include_directories: test_includes,
@@ -138,24 +135,38 @@ checkTag = executable('checkTag',
 # =============================================================================
 
 if tests_supported_oses.contains(host_machine_os)
-  valgrind_prog = find_program('valgrind', ['/usr/bin/valgrind'], required: true)
+  valgrind_prog = find_program('valgrind', ['/usr/bin/valgrind'], required: false)
   valgrindTest_py = files('valgrindTest.py')
-  test('valgrindTest',
-    valgrindTest_py,
-    args: [valgrind_prog.path(), zstd, datagen, fuzzer, fullbench],
-    depends: [zstd, datagen, fuzzer, fullbench],
-    timeout: 600) # Timeout should work on HDD drive
+  if valgrind_prog.found()
+    test('valgrindTest',
+      valgrindTest_py,
+      args: [valgrind_prog.path(), zstd, datagen, fuzzer, fullbench],
+      depends: [zstd, datagen, fuzzer, fullbench],
+      timeout: 600) # Timeout should work on HDD drive
+  endif
 endif
 
 if host_machine_os != os_windows
   playTests_sh = find_program(join_paths(zstd_rootdir, 'tests/playTests.sh'), required: true)
-  test('test-zstd',
-    playTests_sh,
-    args: ZSTDRTTEST,
-    env: ['ZSTD_BIN=' + zstd.full_path(), 'DATAGEN_BIN=./datagen'],
-    depends: [datagen],
-    workdir: meson.current_build_dir(),
-    timeout: 2800) # Timeout should work on HDD drive
+
+  # add slow tests only if the meson version is new enough to support
+  # test setups with default-excluded suites
+  if meson.version().version_compare('>=0.57.0')
+    matrix = {'fast': [], 'slow': ['--test-large-data']}
+  else
+    matrix = {'fast': []}
+  endif
+
+  foreach suite, opt: matrix
+    test('test-zstd-'+suite,
+      playTests_sh,
+      args: opt,
+      env: ['ZSTD_BIN=' + zstd.full_path(), 'DATAGEN_BIN=./datagen'],
+      depends: [datagen, zstd],
+      suite: suite,
+      workdir: meson.current_build_dir(),
+      timeout: 2800) # Timeout should work on HDD drive
+  endforeach
 endif
 
 test('test-fullbench-1',
@@ -194,3 +205,11 @@ test('test-decodecorpus',
   args: ['-t', DECODECORPUS_TESTTIME],
   timeout: 60)
 test('test-poolTests', poolTests) # should be fast
+
+if meson.version().version_compare('>=0.57.0')
+  add_test_setup('fast',
+    is_default: true,
+    exclude_suites: ['slow'])
+  add_test_setup('slow',
+    exclude_suites: ['fast'])
+endif

zstd.mod/zstd/build/meson/tests/valgrindTest.py

@@ -21,7 +21,7 @@ def valgrindTest(valgrind, datagen, fuzzer, zstd, fullbench):
 
   if subprocess.call([*VALGRIND_ARGS, zstd],
                      stdout=subprocess.DEVNULL) == 0:
-    raise subprocess.CalledProcessError('zstd without argument should have failed')
+    raise subprocess.SubprocessError('zstd without argument should have failed')
 
   with subprocess.Popen([datagen, '-g80'], stdout=subprocess.PIPE) as p1, \
        subprocess.Popen([*VALGRIND_ARGS, zstd, '-', '-c'],
@@ -30,7 +30,7 @@ def valgrindTest(valgrind, datagen, fuzzer, zstd, fullbench):
     p1.stdout.close()  # Allow p1 to receive a SIGPIPE if p2 exits.
     p2.communicate()
     if p2.returncode != 0:
-      raise subprocess.CalledProcessError()
+      raise subprocess.SubprocessError()
 
   with subprocess.Popen([datagen, '-g16KB'], stdout=subprocess.PIPE) as p1, \
        subprocess.Popen([*VALGRIND_ARGS, zstd, '-vf', '-', '-c'],
@@ -39,7 +39,7 @@ def valgrindTest(valgrind, datagen, fuzzer, zstd, fullbench):
     p1.stdout.close()
     p2.communicate()
     if p2.returncode != 0:
-      raise subprocess.CalledProcessError()
+      raise subprocess.SubprocessError()
 
   with tempfile.NamedTemporaryFile() as tmp_fd:
     with subprocess.Popen([datagen, '-g2930KB'], stdout=subprocess.PIPE) as p1, \
@@ -48,7 +48,7 @@ def valgrindTest(valgrind, datagen, fuzzer, zstd, fullbench):
       p1.stdout.close()
       p2.communicate()
       if p2.returncode != 0:
-        raise subprocess.CalledProcessError()
+        raise subprocess.SubprocessError()
 
     subprocess.check_call([*VALGRIND_ARGS, zstd, '-vdf', tmp_fd.name, '-c'],
                           stdout=subprocess.DEVNULL)
@@ -60,7 +60,7 @@ def valgrindTest(valgrind, datagen, fuzzer, zstd, fullbench):
       p1.stdout.close()
       p2.communicate()
       if p2.returncode != 0:
-        raise subprocess.CalledProcessError()
+        raise subprocess.SubprocessError()
 
   subprocess.check_call([*VALGRIND_ARGS, fuzzer, '-T1mn', '-t1'])
   subprocess.check_call([*VALGRIND_ARGS, fullbench, '-i1'])

zstd.mod/zstd/build/single_file_libs/README.md

@@ -12,7 +12,7 @@ This is the most common use case. The decompression library is small, adding, fo
 Create `zstddeclib.c` from the Zstd source using:
 ```
 cd zstd/build/single_file_libs
-./combine.sh -r ../../lib -o zstddeclib.c zstddeclib-in.c
+python3 combine.py -r ../../lib -x legacy/zstd_legacy.h -o zstddeclib.c zstddeclib-in.c
 ```
 Then add the resulting file to your project (see the [example files](examples)).
 
@@ -26,7 +26,7 @@ The same tool can amalgamate the entire Zstd library for ease of adding both com
 Create `zstd.c` from the Zstd source using:
 ```
 cd zstd/build/single_file_libs
-./combine.sh -r ../../lib -o zstd.c zstd-in.c
+python3 combine.py -r ../../lib -x legacy/zstd_legacy.h -k zstd.h -o zstd.c zstd-in.c
 ```
 It's possible to create a compressor-only library but since the decompressor is so small in comparison this doesn't bring much of a gain (but for the curious, simply remove the files in the _decompress_ section at the end of `zstd-in.c`).
 

zstd.mod/zstd/build/single_file_libs/build_decoder_test.sh

@@ -11,7 +11,7 @@ IN_FILES="examples/emscripten.c"
 
 # Emscripten build using emcc.
 emscripten_emcc_build() {
-  # Compile the the same example as above
+  # Compile the same example as above
   CC_FLAGS="-Wall -Wextra -Wshadow -Werror -Os -g0 -flto"
   emcc $CC_FLAGS -s WASM=1 -I. -o $OUT_WASM $IN_FILES
   # Did compilation work?

zstd.mod/zstd/build/single_file_libs/build_library_test.sh

@@ -14,7 +14,7 @@ IN_FILES="zstd.c examples/roundtrip.c"
 
 # Emscripten build using emcc.
 emscripten_emcc_build() {
-  # Compile the the same example as above
+  # Compile the same example as above
   CC_FLAGS="-Wall -Wextra -Wshadow -Werror -Os -g0 -flto"
   emcc $CC_FLAGS -s WASM=1 -I. -o $OUT_WASM $IN_FILES
   # Did compilation work?
@@ -69,7 +69,7 @@ fi
 echo "Single file library creation script: PASSED"
 
 # Copy the header to here (for the tests)
-cp "$ZSTD_SRC_ROOT/zstd.h" zstd.h
+cp "$ZSTD_SRC_ROOT/zstd.h" examples/zstd.h
 
 # Compile the generated output
 cc -Wall -Wextra -Werror -Wshadow -pthread -I. -Os -g0 -o $OUT_FILE zstd.c examples/roundtrip.c

zstd.mod/zstd/build/single_file_libs/combine.py

@@ -0,0 +1,234 @@
+#!/usr/bin/env python3
+
+# Tool to bundle multiple C/C++ source files, inlining any includes.
+# 
+# Note: there are two types of exclusion options: the '-x' flag, which besides
+# excluding a file also adds an #error directive in place of the #include, and
+# the '-k' flag, which keeps the #include and doesn't inline the file. The
+# intended use cases are: '-x' for files that would normally be #if'd out, so
+# features that 100% won't be used in the amalgamated file, for which every
+# occurrence adds the error, and '-k' for headers that we wish to manually
+# include, such as a project's public API, for which occurrences after the first
+# are removed.
+# 
+# Todo: the error handling could be better, which currently throws and halts
+# (which is functional just not very friendly).
+# 
+# Author: Carl Woffenden, Numfum GmbH (this script is released under a CC0 license/Public Domain)
+
+import argparse, re, sys
+
+from pathlib import Path
+from typing import Any, List, Optional, Pattern, Set, TextIO
+
+# Set of file roots when searching (equivalent to -I paths for the compiler).
+roots: Set[Path] = set()
+
+# Set of (canonical) file Path objects to exclude from inlining (and not only
+# exclude but to add a compiler error directive when they're encountered).
+excludes: Set[Path] = set()
+
+# Set of (canonical) file Path objects to keep as include directives.
+keeps: Set[Path] = set()
+
+# Whether to keep the #pragma once directives (unlikely, since this will result
+# in a warning, but the option is there).
+keep_pragma: bool = False
+
+# Destination file object (or stdout if no output file was supplied).
+destn: TextIO = sys.stdout
+
+# Set of file Path objects previously inlined (and to ignore if reencountering).
+found: Set[Path] = set()
+
+# Compiled regex Pattern to handle "#pragma once" in various formats:
+# 
+#   #pragma once
+#     #pragma once
+#   #  pragma once
+#   #pragma   once
+#   #pragma once // comment
+# 
+# Ignoring commented versions, same as include_regex.
+# 
+pragma_regex: Pattern = re.compile(r'^\s*#\s*pragma\s*once\s*')
+
+# Compiled regex Pattern to handle the following type of file includes:
+# 
+#   #include "file"
+#     #include "file"
+#   #  include "file"
+#   #include   "file"
+#   #include "file" // comment
+#   #include "file" // comment with quote "
+# 
+# And all combinations of, as well as ignoring the following:
+# 
+#   #include <file>
+#   //#include "file"
+#   /*#include "file"*/
+# 
+# We don't try to catch errors since the compiler will do this (and the code is
+# expected to be valid before processing) and we don't care what follows the
+# file (whether it's a valid comment or not, since anything after the quoted
+# string is ignored)
+# 
+include_regex: Pattern = re.compile(r'^\s*#\s*include\s*"(.+?)"')
+
+# Simple tests to prove include_regex's cases.
+# 
+def test_match_include() -> bool:
+    if (include_regex.match('#include "file"')   and
+        include_regex.match('  #include "file"') and
+        include_regex.match('#  include "file"') and
+        include_regex.match('#include   "file"') and
+        include_regex.match('#include "file" // comment')):
+            if (not include_regex.match('#include <file>')   and
+                not include_regex.match('//#include "file"') and
+                not include_regex.match('/*#include "file"*/')):
+                    found = include_regex.match('#include "file" // "')
+                    if (found and found.group(1) == 'file'):
+                        print('#include match valid')
+                        return True
+    return False
+
+# Simple tests to prove pragma_regex's cases.
+# 
+def test_match_pragma() -> bool:
+    if (pragma_regex.match('#pragma once')   and
+        pragma_regex.match('  #pragma once') and
+        pragma_regex.match('#  pragma once') and
+        pragma_regex.match('#pragma   once') and
+        pragma_regex.match('#pragma once // comment')):
+            if (not pragma_regex.match('//#pragma once') and
+                not pragma_regex.match('/*#pragma once*/')):
+                    print('#pragma once match valid')
+                    return True
+    return False
+
+# Finds 'file'. First the list of 'root' paths are searched, followed by the
+# currently processing file's 'parent' path, returning a valid Path in
+# canonical form. If no match is found None is returned.
+# 
+def resolve_include(file: str, parent: Optional[Path] = None) -> Optional[Path]:
+    for root in roots:
+        found = root.joinpath(file).resolve()
+        if (found.is_file()):
+            return found
+    if (parent):
+        found = parent.joinpath(file).resolve();
+    else:
+        found = Path(file)
+    if (found.is_file()):
+        return found
+    return None
+
+# Helper to resolve lists of files. 'file_list' is passed in from the arguments
+# and each entry resolved to its canonical path (like any include entry, either
+# from the list of root paths or the owning file's 'parent', which in this case
+# is case is the input file). The results are stored in 'resolved'.
+# 
+def resolve_excluded_files(file_list: Optional[List[str]], resolved: Set[Path], parent: Optional[Path] = None) -> None:
+    if (file_list):
+        for filename in file_list:
+            found = resolve_include(filename, parent)
+            if (found):
+                resolved.add(found)
+            else:
+                error_line(f'Warning: excluded file not found: {filename}')
+
+# Writes 'line' to the open 'destn' (or stdout).
+# 
+def write_line(line: str) -> None:
+    print(line, file=destn)
+
+# Logs 'line' to stderr. This is also used for general notifications that we
+# don't want to go to stdout (so the source can be piped).
+# 
+def error_line(line: Any) -> None:
+    print(line, file=sys.stderr)
+
+# Inline the contents of 'file' (with any of its includes also inlined, etc.).
+# 
+# Note: text encoding errors are ignored and replaced with ? when reading the
+# input files. This isn't ideal, but it's more than likely in the comments than
+# code and a) the text editor has probably also failed to read the same content,
+# and b) the compiler probably did too.
+# 
+def add_file(file: Path, file_name: str = None) -> None:
+    if (file.is_file()):
+        if (not file_name):
+            file_name = file.name
+        error_line(f'Processing: {file_name}')
+        with file.open('r', errors='replace') as opened:
+            for line in opened:
+                line = line.rstrip('\n')
+                match_include = include_regex.match(line);
+                if (match_include):
+                    # We have a quoted include directive so grab the file
+                    inc_name = match_include.group(1)
+                    resolved = resolve_include(inc_name, file.parent)
+                    if (resolved):
+                        if (resolved in excludes):
+                            # The file was excluded so error if the compiler uses it
+                            write_line(f'#error Using excluded file: {inc_name} (re-amalgamate source to fix)')
+                            error_line(f'Excluding: {inc_name}')
+                        else:
+                            if (resolved not in found):
+                                # The file was not previously encountered
+                                found.add(resolved)
+                                if (resolved in keeps):
+                                    # But the include was flagged to keep as included
+                                    write_line(f'/**** *NOT* inlining {inc_name} ****/')
+                                    write_line(line)
+                                    error_line(f'Not inlining: {inc_name}')
+                                else:
+                                    # The file was neither excluded nor seen before so inline it
+                                    write_line(f'/**** start inlining {inc_name} ****/')
+                                    add_file(resolved, inc_name)
+                                    write_line(f'/**** ended inlining {inc_name} ****/')
+                            else:
+                                write_line(f'/**** skipping file: {inc_name} ****/')
+                    else:
+                        # The include file didn't resolve to a file
+                        write_line(f'#error Unable to find: {inc_name}')
+                        error_line(f'Error: Unable to find: {inc_name}')
+                else:
+                    # Skip any 'pragma once' directives, otherwise write the source line
+                    if (keep_pragma or not pragma_regex.match(line)):
+                        write_line(line)
+    else:
+        error_line(f'Error: Invalid file: {file}')
+
+# Start here
+parser = argparse.ArgumentParser(description='Amalgamate Tool', epilog=f'example: {sys.argv[0]} -r ../my/path -r ../other/path -o out.c in.c')
+parser.add_argument('-r', '--root', action='append', type=Path, help='file root search path')
+parser.add_argument('-x', '--exclude',  action='append', help='file to completely exclude from inlining')
+parser.add_argument('-k', '--keep', action='append', help='file to exclude from inlining but keep the include directive')
+parser.add_argument('-p', '--pragma', action='store_true', default=False, help='keep any "#pragma once" directives (removed by default)')
+parser.add_argument('-o', '--output', type=argparse.FileType('w'), help='output file (otherwise stdout)')
+parser.add_argument('input', type=Path, help='input file')
+args = parser.parse_args()
+
+# Fail early on an invalid input (and store it so we don't recurse)
+args.input = args.input.resolve(strict=True)
+found.add(args.input)
+
+# Resolve all of the root paths upfront (we'll halt here on invalid roots)
+if (args.root):
+    for path in args.root:
+        roots.add(path.resolve(strict=True))
+
+# The remaining params: so resolve the excluded files and #pragma once directive
+resolve_excluded_files(args.exclude, excludes, args.input.parent)
+resolve_excluded_files(args.keep,    keeps,    args.input.parent)
+keep_pragma = args.pragma;
+
+# Then recursively process the input file
+try:
+    if (args.output):
+        destn = args.output
+    add_file(args.input)
+finally:
+    if (destn):
+        destn.close()

zstd.mod/zstd/build/single_file_libs/combine.sh

@@ -2,11 +2,7 @@
 
 # Tool to bundle multiple C/C++ source files, inlining any includes.
 # 
-# Note: this POSIX-compliant script is many times slower than the original bash
-# implementation (due to the grep calls) but it runs and works everywhere.
-# 
 # TODO: ROOTS, FOUND, etc., as arrays (since they fail on paths with spaces)
-# TODO: revert to Bash-only regex (the grep ones being too slow)
 # 
 # Author: Carl Woffenden, Numfum GmbH (this script is released under a CC0 license/Public Domain)
 
@@ -52,13 +48,54 @@ test_deps() {
   fi
 }
 
+# Test if glob pattern $1 matches subject $2 (see fnmatch(3))
+fnmatch() {
+  case "$2" in
+  $1)
+    return 0
+    ;;
+  esac
+  return 1
+}
+
+# Test if line $1 is local include directive
+is_include_line() {
+  fnmatch "*#*include*" "$1" || return 1
+  printf "%s\n" "$1" | grep -Eq '^\s*#\s*include\s*".+"'
+}
+
+# Test if line $1 is pragma once directive
+is_pragma_once_line() {
+  fnmatch "*#*pragma*once*" "$1" || return 1
+  printf "%s\n" "$1" | grep -Eq '^\s*#\s*pragma\s*once\s*'
+}
+
 # Tests if list $1 has item $2 (returning zero on a match)
+# (originally used grep -Eq "(^|\s*)$2(\$|\s*))
+readonly list_FS="$IFS"
 list_has_item() {
-  if echo "$1" | grep -Eq "(^|\s*)$2(\$|\s*)"; then
-    return 0
-  else
-    return 1
+  # Re: escaping glob pattern special characters in item string:
+  #
+  # bash (tested 3.2.57, 5.1.4), dash (tested 0.5.10.2), NetBSD /bin/sh
+  # (tested 8.2), and Solaris /bin/sh (tested 11.4) require escaping
+  # backslashes in a bracket expression despite POSIX specifying that
+  # backslash loses significance in a bracket expression.
+  #
+  # Conversely, neither FreeBSD /bin/sh (tested 12.2) nor OpenBSD /bin/sh
+  # (tested 7.1) obey backslash-escaping in case statement patterns even
+  # outside bracket expressions, so escape special characters using bracket
+  # expressions.
+  #
+  # Solaris /bin/sh (tested 11.4) requires vertical bar (|) to be escaped.
+  #
+  # All accommodations should behave as expected under strict POSIX semantics.
+  if fnmatch "*[\\*?[|]*" "$2"; then
+    set -- "$1" "$(printf '%s\n' "$2" | sed -e 's/[*?[|]/[&]/g; s/[\]/[\\&]/g')"
   fi
+  for item_P in "*[$list_FS]$2[$list_FS]*" "*[$list_FS]$2" "$2[$list_FS]*" "$2"; do
+    fnmatch "${item_P}" "$1" && return 0
+  done
+  return 1
 }
 
 # Adds a new line with the supplied arguments to $DESTN (or stdout)
@@ -124,13 +161,13 @@ add_file() {
     # Read the file
     local line=
     while IFS= read -r line; do
-      if echo "$line" | grep -Eq '^\s*#\s*include\s*".+"'; then
+      if is_include_line "$line"; then
         # We have an include directive so strip the (first) file
         local inc=$(echo "$line" | grep -Eo '".*"' | sed -E 's/"([^"]+)"/\1/' | head -1)
         local res_inc="$(resolve_include "$srcdir" "$inc")"
         if list_has_item "$XINCS" "$inc"; then
           # The file was excluded so error if the source attempts to use it
-          write_line "#error Using excluded file: $inc"
+          write_line "#error Using excluded file: $inc (re-amalgamate source to fix)"
           log_line "Excluding: $inc"
         else
           if ! list_has_item "$FOUND" "$res_inc"; then
@@ -155,7 +192,7 @@ add_file() {
         # Skip any 'pragma once' directives, otherwise write the source line
         local write=$PONCE
         if [ $write -eq 0 ]; then
-          if echo "$line" | grep -Eqv '^\s*#\s*pragma\s*once\s*'; then
+          if ! is_pragma_once_line "$line"; then
             write=1
           fi
         fi
@@ -200,6 +237,7 @@ if [ -n "$1" ]; then
       printf "" > "$DESTN"
     fi
     test_deps
+    log_line "Processing using the slower shell script; this might take a while"
     add_file "$1"
   else
     echo "Input file not found: \"$1\""

zstd.mod/zstd/build/single_file_libs/create_single_file_decoder.sh

@@ -4,8 +4,13 @@
 ZSTD_SRC_ROOT="../../lib"
 
 # Amalgamate the sources
-echo "Amalgamating files... this can take a while"
-./combine.sh -r "$ZSTD_SRC_ROOT" -o zstddeclib.c zstddeclib-in.c
+echo "Amalgamating files..."
+# Using the faster Python script if we have 3.8 or higher
+if python3 -c 'import sys; assert sys.version_info >= (3,8)' 2>/dev/null; then
+  ./combine.py -r "$ZSTD_SRC_ROOT" -x legacy/zstd_legacy.h -o zstddeclib.c zstddeclib-in.c
+else
+  ./combine.sh -r "$ZSTD_SRC_ROOT" -x legacy/zstd_legacy.h -o zstddeclib.c zstddeclib-in.c
+fi
 # Did combining work?
 if [ $? -ne 0 ]; then
   echo "Combine script: FAILED"

zstd.mod/zstd/build/single_file_libs/create_single_file_library.sh

@@ -4,8 +4,13 @@
 ZSTD_SRC_ROOT="../../lib"
 
 # Amalgamate the sources
-echo "Amalgamating files... this can take a while"
-./combine.sh -r "$ZSTD_SRC_ROOT" -o zstd.c zstd-in.c
+echo "Amalgamating files..."
+# Using the faster Python script if we have 3.8 or higher
+if python3 -c 'import sys; assert sys.version_info >= (3,8)' 2>/dev/null; then
+  ./combine.py -r "$ZSTD_SRC_ROOT" -x legacy/zstd_legacy.h -o zstd.c zstd-in.c
+else
+  ./combine.sh -r "$ZSTD_SRC_ROOT" -x legacy/zstd_legacy.h -o zstd.c zstd-in.c
+fi
 # Did combining work?
 if [ $? -ne 0 ]; then
   echo "Combine script: FAILED"

zstd.mod/zstd/build/single_file_libs/zstd-in.c

@@ -4,11 +4,11 @@
  *
  * Generate using:
  * \code
- *	combine.sh -r ../../lib -o zstd.c zstd-in.c
+ *	python combine.py -r ../../lib -x legacy/zstd_legacy.h -o zstd.c zstd-in.c
  * \endcode
  */
 /*
- * Copyright (c) 2016-2021, 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
@@ -25,9 +25,13 @@
  * Note: MEM_MODULE stops xxhash redefining BYTE, U16, etc., which are also
  * defined in mem.h (breaking C99 compatibility).
  *
- * Note: the undefs for xxHash allow Zstd's implementation to coincide with with
+ * Note: the undefs for xxHash allow Zstd's implementation to coincide with
  * standalone xxHash usage (with global defines).
  *
+ * Note: if you enable ZSTD_LEGACY_SUPPORT the combine.py script will need
+ * re-running without the "-x legacy/zstd_legacy.h" option (it excludes the
+ * legacy support at the source level).
+ *
  * Note: multithreading is enabled for all platforms apart from Emscripten.
  */
 #define DEBUGLEVEL 0

zstd.mod/zstd/build/single_file_libs/zstddeclib-in.c

@@ -4,11 +4,11 @@
  *
  * Generate using:
  * \code
- *	combine.sh -r ../../lib -o zstddeclib.c zstddeclib-in.c
+ *	python combine.py -r ../../lib -x legacy/zstd_legacy.h -o zstddeclib.c zstddeclib-in.c
  * \endcode
  */
 /*
- * Copyright (c) 2016-2021, 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
@@ -25,8 +25,12 @@
  * Note: MEM_MODULE stops xxhash redefining BYTE, U16, etc., which are also
  * defined in mem.h (breaking C99 compatibility).
  *
- * Note: the undefs for xxHash allow Zstd's implementation to coincide with with
+ * Note: the undefs for xxHash allow Zstd's implementation to coincide with
  * standalone xxHash usage (with global defines).
+ *
+ * Note: if you enable ZSTD_LEGACY_SUPPORT the combine.py script will need
+ * re-running without the "-x legacy/zstd_legacy.h" option (it excludes the
+ * legacy support at the source level).
  */
 #define DEBUGLEVEL 0
 #define MEM_MODULE

zstd.mod/zstd/contrib/VS2005/zstd/zstd.vcproj

@@ -363,6 +363,10 @@
 				RelativePath="..\..\..\programs\fileio.c"
 				>
 			</File>
+			<File
+                RelativePath="..\..\..\programs\fileio_asyncio.c"
+                >
+            </File>
 			<File
 				RelativePath="..\..\..\lib\compress\fse_compress.c"
 				>

zstd.mod/zstd/contrib/diagnose_corruption/Makefile

@@ -1,5 +1,5 @@
 # ################################################################
-# Copyright (c) 2019-present, 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

zstd.mod/zstd/contrib/diagnose_corruption/check_flipped_bits.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-present, 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

zstd.mod/zstd/contrib/docker/Dockerfile

@@ -1,13 +1,13 @@
 # Dockerfile
 # First image to build the binary
-FROM alpine as builder
+FROM alpine@sha256:69665d02cb32192e52e07644d76bc6f25abeb5410edc1c7a81a10ba3f0efb90a as builder
 
 RUN apk --no-cache add make gcc libc-dev
 COPY . /src
 RUN mkdir /pkg && cd /src && make && make DESTDIR=/pkg install
 
 # Second minimal image to only keep the built binary
-FROM alpine
+FROM alpine@sha256:69665d02cb32192e52e07644d76bc6f25abeb5410edc1c7a81a10ba3f0efb90a
 
 # Copy the built files
 COPY --from=builder /pkg /

zstd.mod/zstd/contrib/externalSequenceProducer/.gitignore

@@ -0,0 +1,2 @@
+# build artifacts
+externalSequenceProducer

zstd.mod/zstd/contrib/externalSequenceProducer/Makefile

@@ -0,0 +1,40 @@
+# ################################################################
+# Copyright (c) Yann Collet, Meta Platforms, 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).
+# ################################################################
+
+PROGDIR = ../../programs
+LIBDIR  = ../../lib
+
+LIBZSTD = $(LIBDIR)/libzstd.a
+
+CPPFLAGS+= -I$(LIBDIR) -I$(LIBDIR)/compress -I$(LIBDIR)/common
+
+CFLAGS  ?= -O3
+CFLAGS  += -std=gnu99
+DEBUGFLAGS= -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \
+            -Wstrict-aliasing=1 -Wswitch-enum \
+            -Wstrict-prototypes -Wundef -Wpointer-arith \
+            -Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings \
+            -Wredundant-decls
+CFLAGS  += $(DEBUGFLAGS) $(MOREFLAGS)
+
+default: externalSequenceProducer
+
+all: externalSequenceProducer
+
+externalSequenceProducer: sequence_producer.c main.c $(LIBZSTD)
+	$(CC) $(CPPFLAGS) $(CFLAGS) $^ $(LDFLAGS) -o $@
+
+.PHONY: $(LIBZSTD)
+$(LIBZSTD):
+	$(MAKE) -C $(LIBDIR) libzstd.a CFLAGS="$(CFLAGS)"
+
+clean:
+	$(RM) *.o
+	$(MAKE) -C $(LIBDIR) clean > /dev/null
+	$(RM) externalSequenceProducer

zstd.mod/zstd/contrib/externalSequenceProducer/README.md

@@ -0,0 +1,14 @@
+externalSequenceProducer
+=====================
+
+`externalSequenceProducer` is a test tool for the Block-Level Sequence Producer API.
+It demonstrates how to use the API to perform a simple round-trip test.
+
+A sample sequence producer is provided in sequence_producer.c, but the user can swap
+this out with a different one if desired. The sample sequence producer implements
+LZ parsing with a 1KB hashtable. Dictionary-based parsing is not currently supported.
+
+Command line :
+```
+externalSequenceProducer filename
+```

zstd.mod/zstd/contrib/externalSequenceProducer/main.c

@@ -0,0 +1,107 @@
+/*
+ * Copyright (c) Yann Collet, Meta Platforms, 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.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <assert.h>
+
+#define ZSTD_STATIC_LINKING_ONLY
+#include "zstd.h"
+#include "zstd_errors.h"
+#include "sequence_producer.h" // simpleSequenceProducer
+
+#define CHECK(res)                                      \
+do {                                                    \
+    if (ZSTD_isError(res)) {                            \
+        printf("ERROR: %s\n", ZSTD_getErrorName(res));  \
+        return 1;                                       \
+    }                                                   \
+} while (0)                                             \
+
+int main(int argc, char *argv[]) {
+    if (argc != 2) {
+        printf("Usage: externalSequenceProducer <file>\n");
+        return 1;
+    }
+
+    ZSTD_CCtx* const zc = ZSTD_createCCtx();
+
+    int simpleSequenceProducerState = 0xdeadbeef;
+
+    // Here is the crucial bit of code!
+    ZSTD_registerSequenceProducer(
+        zc,
+        &simpleSequenceProducerState,
+        simpleSequenceProducer
+    );
+
+    {
+        size_t const res = ZSTD_CCtx_setParameter(zc, ZSTD_c_enableSeqProducerFallback, 1);
+        CHECK(res);
+    }
+
+    FILE *f = fopen(argv[1], "rb");
+    assert(f);
+    {
+        int const ret = fseek(f, 0, SEEK_END);
+        assert(ret == 0);
+    }
+    size_t const srcSize = ftell(f);
+    {
+        int const ret = fseek(f, 0, SEEK_SET);
+        assert(ret == 0);
+    }
+
+    char* const src = malloc(srcSize + 1);
+    assert(src);
+    {
+        size_t const ret = fread(src, srcSize, 1, f);
+        assert(ret == 1);
+        int const ret2 = fclose(f);
+        assert(ret2 == 0);
+    }
+
+    size_t const dstSize = ZSTD_compressBound(srcSize);
+    char* const dst = malloc(dstSize);
+    assert(dst);
+
+    size_t const cSize = ZSTD_compress2(zc, dst, dstSize, src, srcSize);
+    CHECK(cSize);
+
+    char* const val = malloc(srcSize);
+    assert(val);
+
+    {
+        size_t const res = ZSTD_decompress(val, srcSize, dst, cSize);
+        CHECK(res);
+    }
+
+    if (memcmp(src, val, srcSize) == 0) {
+        printf("Compression and decompression were successful!\n");
+        printf("Original size: %lu\n", srcSize);
+        printf("Compressed size: %lu\n", cSize);
+    } else {
+        printf("ERROR: input and validation buffers don't match!\n");
+        for (size_t i = 0; i < srcSize; i++) {
+            if (src[i] != val[i]) {
+                printf("First bad index: %zu\n", i);
+                break;
+            }
+        }
+        return 1;
+    }
+
+    ZSTD_freeCCtx(zc);
+    free(src);
+    free(dst);
+    free(val);
+    return 0;
+}

zstd.mod/zstd/contrib/externalSequenceProducer/sequence_producer.c

@@ -0,0 +1,80 @@
+/*
+ * Copyright (c) Yann Collet, Meta Platforms, 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.
+ */
+
+#include "zstd_compress_internal.h"
+#include "sequence_producer.h"
+
+#define HSIZE 1024
+static U32 const HLOG = 10;
+static U32 const MLS = 4;
+static U32 const BADIDX = 0xffffffff;
+
+size_t simpleSequenceProducer(
+  void* sequenceProducerState,
+  ZSTD_Sequence* outSeqs, size_t outSeqsCapacity,
+  const void* src, size_t srcSize,
+  const void* dict, size_t dictSize,
+  int compressionLevel,
+  size_t windowSize
+) {
+    const BYTE* const istart = (const BYTE*)src;
+    const BYTE* const iend = istart + srcSize;
+    const BYTE* ip = istart;
+    const BYTE* anchor = istart;
+    size_t seqCount = 0;
+    U32 hashTable[HSIZE];
+
+    (void)sequenceProducerState;
+    (void)dict;
+    (void)dictSize;
+    (void)outSeqsCapacity;
+    (void)compressionLevel;
+
+    {   int i;
+        for (i=0; i < HSIZE; i++) {
+            hashTable[i] = BADIDX;
+    }   }
+
+    while (ip + MLS < iend) {
+        size_t const hash = ZSTD_hashPtr(ip, HLOG, MLS);
+        U32 const matchIndex = hashTable[hash];
+        hashTable[hash] = (U32)(ip - istart);
+
+        if (matchIndex != BADIDX) {
+            const BYTE* const match = istart + matchIndex;
+            U32 const matchLen = (U32)ZSTD_count(ip, match, iend);
+            if (matchLen >= ZSTD_MINMATCH_MIN) {
+                U32 const litLen = (U32)(ip - anchor);
+                U32 const offset = (U32)(ip - match);
+                ZSTD_Sequence const seq = {
+                    offset, litLen, matchLen, 0
+                };
+
+                /* Note: it's crucial to stay within the window size! */
+                if (offset <= windowSize) {
+                    outSeqs[seqCount++] = seq;
+                    ip += matchLen;
+                    anchor = ip;
+                    continue;
+                }
+            }
+        }
+
+        ip++;
+    }
+
+    {   ZSTD_Sequence const finalSeq = {
+            0, (U32)(iend - anchor), 0, 0
+        };
+        outSeqs[seqCount++] = finalSeq;
+    }
+
+    return seqCount;
+}

zstd.mod/zstd/contrib/externalSequenceProducer/sequence_producer.h

@@ -0,0 +1,26 @@
+/*
+ * Copyright (c) Yann Collet, Meta Platforms, 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 MATCHFINDER_H
+#define MATCHFINDER_H
+
+#define ZSTD_STATIC_LINKING_ONLY
+#include "zstd.h"
+
+size_t simpleSequenceProducer(
+  void* sequenceProducerState,
+  ZSTD_Sequence* outSeqs, size_t outSeqsCapacity,
+  const void* src, size_t srcSize,
+  const void* dict, size_t dictSize,
+  int compressionLevel,
+  size_t windowSize
+);
+
+#endif

zstd.mod/zstd/contrib/freestanding_lib/freestanding.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 # ################################################################
-# Copyright (c) 2021-2021, 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
@@ -340,7 +340,7 @@ class PartialPreprocessor(object):
 
                 if macro2 is not None and not resolved:
                     assert ifdef and defined and op == '&&' and cmp is not None
-                    # If the statment is true, but we have a single value check, then
+                    # If the statement is true, but we have a single value check, then
                     # check the value.
                     defined_value = self._defs[macro]
                     are_ints = True
@@ -431,7 +431,7 @@ class Freestanding(object):
             external_xxhash: bool, xxh64_state: Optional[str],
             xxh64_prefix: Optional[str], rewritten_includes: [(str, str)],
             defs: [(str, Optional[str])], replaces: [(str, str)],
-            undefs: [str], excludes: [str], seds: [str],
+            undefs: [str], excludes: [str], seds: [str], spdx: bool,
     ):
         self._zstd_deps = zstd_deps
         self._mem = mem
@@ -446,6 +446,7 @@ class Freestanding(object):
         self._undefs = undefs
         self._excludes = excludes
         self._seds = seds
+        self._spdx = spdx
 
     def _dst_lib_file_paths(self):
         """
@@ -640,6 +641,27 @@ class Freestanding(object):
         for sed in self._seds:
             self._process_sed(sed)
 
+    def _process_spdx(self):
+        if not self._spdx:
+            return
+        self._log("Processing spdx")
+        SPDX_C = "// SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause\n"
+        SPDX_H_S = "/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */\n"
+        for filepath in self._dst_lib_file_paths():
+            file = FileLines(filepath)
+            if file.lines[0] == SPDX_C or file.lines[0] == SPDX_H_S:
+                continue
+            for line in file.lines:
+                if "SPDX-License-Identifier" in line:
+                    raise RuntimeError(f"Unexpected SPDX license identifier: {file.filename} {repr(line)}")
+            if file.filename.endswith(".c"):
+                file.lines.insert(0, SPDX_C)
+            elif file.filename.endswith(".h") or file.filename.endswith(".S"):
+                file.lines.insert(0, SPDX_H_S)
+            else:
+                raise RuntimeError(f"Unexpected file extension: {file.filename}")
+            file.write()
+
 
 
     def go(self):
@@ -651,6 +673,7 @@ class Freestanding(object):
         self._rewrite_includes()
         self._replace_xxh64_prefix()
         self._process_seds()
+        self._process_spdx()
 
 
 def parse_optional_pair(defines: [str]) -> [(str, Optional[str])]:
@@ -689,8 +712,9 @@ def main(name, args):
     parser.add_argument("--xxh64-prefix", default=None, help="Alternate XXH64 function prefix (excluding _) e.g. --xxh64-prefix=xxh64")
     parser.add_argument("--rewrite-include", default=[], dest="rewritten_includes", action="append", help="Rewrite an include REGEX=NEW (e.g. '<stddef\\.h>=<linux/types.h>')")
     parser.add_argument("--sed", default=[], dest="seds", action="append", help="Apply a sed replacement. Format: `s/REGEX/FORMAT/[g]`. REGEX is a Python regex. FORMAT is a Python format string formatted by the regex dict.")
+    parser.add_argument("--spdx", action="store_true", help="Add SPDX License Identifiers")
     parser.add_argument("-D", "--define", default=[], dest="defs", action="append", help="Pre-define this macro (can be passed multiple times)")
-    parser.add_argument("-U", "--undefine", default=[], dest="undefs", action="append", help="Pre-undefine this macro (can be passed mutliple times)")
+    parser.add_argument("-U", "--undefine", default=[], dest="undefs", action="append", help="Pre-undefine this macro (can be passed multiple times)")
     parser.add_argument("-R", "--replace", default=[], dest="replaces", action="append", help="Pre-define this macro and replace the first ifndef block with its definition")
     parser.add_argument("-E", "--exclude", default=[], dest="excludes", action="append", help="Exclude all lines between 'BEGIN <EXCLUDE>' and 'END <EXCLUDE>'")
     args = parser.parse_args(args)
@@ -743,6 +767,7 @@ def main(name, args):
         args.undefs,
         args.excludes,
         args.seds,
+        args.spdx,
     ).go()
 
 if __name__ == "__main__":

zstd.mod/zstd/contrib/gen_html/Makefile

@@ -1,5 +1,5 @@
 # ################################################################
-# Copyright (c) 2016-present, 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

zstd.mod/zstd/contrib/gen_html/gen_html.cpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-present, Przemyslaw Skibinski, 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

zstd.mod/zstd/contrib/largeNbDicts/Makefile

@@ -1,5 +1,5 @@
 # ################################################################
-# Copyright (c) 2018-present, 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

zstd.mod/zstd/contrib/largeNbDicts/README.md

@@ -14,12 +14,20 @@ Command line :
 ```
 largeNbDicts [Options] filename(s)
 
-Options :
--r           : recursively load all files in subdirectories (default: off)
--B#          : split input into blocks of size # (default: no split)
--#           : use compression level # (default: 3)
--D #         : use # as a dictionary (default: create one)
--i#          : nb benchmark rounds (default: 6)
---nbDicts=#  : set nb of dictionaries to # (default: one per block)
--h           : help (this text)
+Options : 
+-z          : benchmark compression (default) 
+-d          : benchmark decompression 
+-r          : recursively load all files in subdirectories (default: off) 
+-B#         : split input into blocks of size # (default: no split) 
+-#          : use compression level # (default: 3) 
+-D #        : use # as a dictionary (default: create one) 
+-i#         : nb benchmark rounds (default: 6) 
+--nbBlocks=#: use # blocks for bench (default: one per file) 
+--nbDicts=# : create # dictionaries for bench (default: one per block) 
+-h          : help (this text) 
+ 
+Advanced Options (see zstd.h for documentation) : 
+--dedicated-dict-search
+--dict-content-type=#
+--dict-attach-pref=#
 ```

zstd.mod/zstd/contrib/largeNbDicts/largeNbDicts.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2018-present, 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
@@ -19,7 +19,7 @@
 /*---  Dependencies  ---*/
 
 #include <stddef.h>   /* size_t */
-#include <stdlib.h>   /* malloc, free, abort */
+#include <stdlib.h>   /* malloc, free, abort, qsort*/
 #include <stdio.h>    /* fprintf */
 #include <limits.h>   /* UINT_MAX */
 #include <assert.h>   /* assert */
@@ -39,6 +39,7 @@
 #define BLOCKSIZE_DEFAULT 0  /* no slicing into blocks */
 #define DICTSIZE  (4 KB)
 #define CLEVEL_DEFAULT 3
+#define DICT_LOAD_METHOD ZSTD_dlm_byCopy
 
 #define BENCH_TIME_DEFAULT_S   6
 #define RUN_TIME_DEFAULT_MS    1000
@@ -156,19 +157,6 @@ createDictionaryBuffer(const char* dictionaryName,
     }
 }
 
-static ZSTD_CDict* createCDictForDedicatedDictSearch(const void* dict, size_t dictSize, int compressionLevel)
-{
-    ZSTD_CCtx_params* params = ZSTD_createCCtxParams();
-    ZSTD_CCtxParams_init(params, compressionLevel);
-    ZSTD_CCtxParams_setParameter(params, ZSTD_c_enableDedicatedDictSearch, 1);
-    ZSTD_CCtxParams_setParameter(params, ZSTD_c_compressionLevel, compressionLevel);
-
-    ZSTD_CDict* cdict = ZSTD_createCDict_advanced2(dict, dictSize, ZSTD_dlm_byCopy, ZSTD_dct_auto, params, ZSTD_defaultCMem);
-
-    ZSTD_freeCCtxParams(params);
-    return cdict;
-}
-
 /*! BMK_loadFiles() :
  *  Loads `buffer`, with content from files listed within `fileNamesTable`.
  *  Fills `buffer` entirely.
@@ -461,14 +449,12 @@ static void freeCDictCollection(cdict_collection_t cdictc)
 }
 
 /* returns .buffers=NULL if operation fails */
-static cdict_collection_t createCDictCollection(const void* dictBuffer, size_t dictSize, size_t nbCDict, int cLevel, int dedicatedDictSearch)
+static cdict_collection_t createCDictCollection(const void* dictBuffer, size_t dictSize, size_t nbCDict, ZSTD_dictContentType_e dictContentType, ZSTD_CCtx_params* cctxParams)
 {
     ZSTD_CDict** const cdicts = malloc(nbCDict * sizeof(ZSTD_CDict*));
     if (cdicts==NULL) return kNullCDictCollection;
     for (size_t dictNb=0; dictNb < nbCDict; dictNb++) {
-        cdicts[dictNb] = dedicatedDictSearch ?
-            createCDictForDedicatedDictSearch(dictBuffer, dictSize, cLevel) :
-            ZSTD_createCDict(dictBuffer, dictSize, cLevel);
+        cdicts[dictNb] = ZSTD_createCDict_advanced2(dictBuffer, dictSize, DICT_LOAD_METHOD, dictContentType, cctxParams, ZSTD_defaultCMem);
         CONTROL(cdicts[dictNb] != NULL);
     }
     cdict_collection_t cdictc;
@@ -591,11 +577,13 @@ typedef struct {
     cdict_collection_t dictionaries;
 } compressInstructions;
 
-compressInstructions createCompressInstructions(cdict_collection_t dictionaries)
+compressInstructions createCompressInstructions(cdict_collection_t dictionaries, ZSTD_CCtx_params* cctxParams)
 {
     compressInstructions ci;
     ci.cctx = ZSTD_createCCtx();
     CONTROL(ci.cctx != NULL);
+    if (cctxParams)
+      ZSTD_CCtx_setParametersUsingCCtxParams(ci.cctx, cctxParams);
     ci.nbDicts = dictionaries.nbCDict;
     ci.dictNb = 0;
     ci.dictionaries = dictionaries;
@@ -636,10 +624,10 @@ size_t compress(const void* src, size_t srcSize, void* dst, size_t dstCapacity,
     compressInstructions* const ci = (compressInstructions*) payload;
     (void)dstCapacity;
 
-    ZSTD_compress_usingCDict(ci->cctx,
-                    dst, srcSize,
-                    src, srcSize,
-                    ci->dictionaries.cdicts[ci->dictNb]);
+    ZSTD_CCtx_refCDict(ci->cctx, ci->dictionaries.cdicts[ci->dictNb]);
+    ZSTD_compress2(ci->cctx,
+            dst, srcSize,
+            src, srcSize);
 
     ci->dictNb = ci->dictNb + 1;
     if (ci->dictNb >= ci->nbDicts) ci->dictNb = 0;
@@ -663,25 +651,55 @@ size_t decompress(const void* src, size_t srcSize, void* dst, size_t dstCapacity
     return result;
 }
 
+typedef enum {
+  fastest = 0,
+  median = 1,
+} metricAggregatePref_e;
 
-static int benchMem(slice_collection_t dstBlocks,
-                    slice_collection_t srcBlocks,
+/* compareFunction() :
+ * Sort input in decreasing order when used with qsort() */
+int compareFunction(const void *a, const void *b)
+{
+  double x = *(const double *)a;
+  double y = *(const double *)b;
+  if (x < y)
+    return 1;
+  else if (x > y)
+    return -1;
+  return 0;
+}
+
+double aggregateData(double *data, size_t size,
+                     metricAggregatePref_e metricAggregatePref)
+{
+  qsort(data, size, sizeof(*data), compareFunction);
+  if (metricAggregatePref == fastest)
+    return data[0];
+  else /* median */
+    return (data[(size - 1) / 2] + data[size / 2]) / 2;
+}
+
+static int benchMem(slice_collection_t dstBlocks, slice_collection_t srcBlocks,
                     ddict_collection_t ddictionaries,
-                    cdict_collection_t cdictionaries,
-                    unsigned nbRounds, int benchCompression)
+                    cdict_collection_t cdictionaries, unsigned nbRounds,
+                    int benchCompression, const char *exeName,
+                    ZSTD_CCtx_params *cctxParams,
+                    metricAggregatePref_e metricAggregatePref)
 {
     assert(dstBlocks.nbSlices == srcBlocks.nbSlices);
+    if (benchCompression) assert(cctxParams);
 
     unsigned const ms_per_round = RUN_TIME_DEFAULT_MS;
     unsigned const total_time_ms = nbRounds * ms_per_round;
 
-    double bestSpeed = 0.;
+    double *const speedPerRound = (double *)malloc(nbRounds * sizeof(double));
 
     BMK_timedFnState_t* const benchState =
             BMK_createTimedFnState(total_time_ms, ms_per_round);
 
     decompressInstructions di = createDecompressInstructions(ddictionaries);
-    compressInstructions ci = createCompressInstructions(cdictionaries);
+    compressInstructions ci =
+        createCompressInstructions(cdictionaries, cctxParams);
     void* payload = benchCompression ? (void*)&ci : (void*)&di;
     BMK_benchParams_t const bp = {
         .benchFn = benchCompression ? compress : decompress,
@@ -697,6 +715,7 @@ static int benchMem(slice_collection_t dstBlocks,
         .blockResults = NULL
     };
 
+    size_t roundNb = 0;
     for (;;) {
         BMK_runOutcome_t const outcome = BMK_benchTimedFn(benchState, bp);
         CONTROL(BMK_isSuccessful_runOutcome(outcome));
@@ -706,16 +725,57 @@ static int benchMem(slice_collection_t dstBlocks,
         double const dTime_sec = (double)dTime_ns / 1000000000;
         size_t const srcSize = result.sumOfReturn;
         double const speed_MBps = (double)srcSize / dTime_sec / (1 MB);
-        if (speed_MBps > bestSpeed) bestSpeed = speed_MBps;
+        speedPerRound[roundNb] = speed_MBps;
         if (benchCompression)
-            DISPLAY("Compression Speed : %.1f MB/s \r", bestSpeed);
+            DISPLAY("Compression Speed : %.1f MB/s \r", speed_MBps);
         else
-            DISPLAY("Decompression Speed : %.1f MB/s \r", bestSpeed);
+            DISPLAY("Decompression Speed : %.1f MB/s \r", speed_MBps);
 
         fflush(stdout);
         if (BMK_isCompleted_TimedFn(benchState)) break;
+        roundNb++;
     }
     DISPLAY("\n");
+    /* BMK_benchTimedFn may not run exactly nbRounds iterations */
+    double speedAggregated =
+        aggregateData(speedPerRound, roundNb + 1, metricAggregatePref);
+    if (metricAggregatePref == fastest)
+      DISPLAY("Fastest Speed : %.1f MB/s \n", speedAggregated);
+    else
+      DISPLAY("Median Speed : %.1f MB/s \n", speedAggregated);
+
+    char* csvFileName = malloc(strlen(exeName) + 5);
+    strcpy(csvFileName, exeName);
+    strcat(csvFileName, ".csv");
+    FILE* csvFile = fopen(csvFileName, "r");
+    if (!csvFile) {
+        csvFile = fopen(csvFileName, "wt");
+        assert(csvFile);
+        fprintf(csvFile, "%s\n", exeName);
+        /* Print table headers */
+        fprintf(
+            csvFile,
+            "Compression/Decompression,Level,nbDicts,dictAttachPref,metricAggregatePref,Speed\n");
+    } else {
+        fclose(csvFile);
+        csvFile = fopen(csvFileName, "at");
+        assert(csvFile);
+    }
+
+    int cLevel = -1;
+    int dictAttachPref = -1;
+    if (benchCompression) {
+      ZSTD_CCtxParams_getParameter(cctxParams, ZSTD_c_compressionLevel,
+                                   &cLevel);
+      ZSTD_CCtxParams_getParameter(cctxParams, ZSTD_c_forceAttachDict,
+                                   &dictAttachPref);
+    }
+    fprintf(csvFile, "%s,%d,%ld,%d,%d,%.1f\n",
+            benchCompression ? "Compression" : "Decompression", cLevel,
+            benchCompression ? ci.nbDicts : di.nbDicts, dictAttachPref,
+            metricAggregatePref, speedAggregated);
+    fclose(csvFile);
+    free(csvFileName);
 
     freeDecompressInstructions(di);
     freeCompressInstructions(ci);
@@ -730,12 +790,11 @@ static int benchMem(slice_collection_t dstBlocks,
  *  dictionary : optional (can be NULL), file to load as dictionary,
  *              if none provided : will be calculated on the fly by the program.
  * @return : 0 is success, 1+ otherwise */
-int bench(const char** fileNameTable, unsigned nbFiles,
-          const char* dictionary,
-          size_t blockSize, int clevel,
-          unsigned nbDictMax, unsigned nbBlocks,
+int bench(const char **fileNameTable, unsigned nbFiles, const char *dictionary,
+          size_t blockSize, int clevel, unsigned nbDictMax, unsigned nbBlocks,
           unsigned nbRounds, int benchCompression,
-          int dedicatedDictSearch)
+          ZSTD_dictContentType_e dictContentType, ZSTD_CCtx_params *cctxParams,
+          const char *exeName, metricAggregatePref_e metricAggregatePref)
 {
     int result = 0;
 
@@ -786,20 +845,18 @@ int bench(const char** fileNameTable, unsigned nbFiles,
     /* dictionary determination */
     buffer_t const dictBuffer = createDictionaryBuffer(dictionary,
                                 srcs.buffer.ptr,
-                                srcs.slices.capacities, srcs.slices.nbSlices,
+                                srcSlices.capacities, srcSlices.nbSlices,
                                 DICTSIZE);
     CONTROL(dictBuffer.ptr != NULL);
 
-    ZSTD_CDict* const cdict = dedicatedDictSearch ?
-        createCDictForDedicatedDictSearch(dictBuffer.ptr, dictBuffer.size, clevel) :
-        ZSTD_createCDict(dictBuffer.ptr, dictBuffer.size, clevel);
+    ZSTD_CDict* const cdict = ZSTD_createCDict_advanced2(dictBuffer.ptr, dictBuffer.size, DICT_LOAD_METHOD, dictContentType, cctxParams, ZSTD_defaultCMem);
     CONTROL(cdict != NULL);
 
     size_t const cTotalSizeNoDict = compressBlocks(NULL, dstSlices, srcSlices, NULL, clevel);
     CONTROL(cTotalSizeNoDict != 0);
     DISPLAYLEVEL(3, "compressing at level %u without dictionary : Ratio=%.2f  (%u bytes) \n",
                     clevel,
-                    (double)totalSrcSlicesSize / cTotalSizeNoDict, (unsigned)cTotalSizeNoDict);
+                    (double)totalSrcSlicesSize / (double)cTotalSizeNoDict, (unsigned)cTotalSizeNoDict);
 
     size_t* const cSizes = malloc(nbBlocks * sizeof(size_t));
     CONTROL(cSizes != NULL);
@@ -808,21 +865,21 @@ int bench(const char** fileNameTable, unsigned nbFiles,
     CONTROL(cTotalSize != 0);
     DISPLAYLEVEL(3, "compressed using a %u bytes dictionary : Ratio=%.2f  (%u bytes) \n",
                     (unsigned)dictBuffer.size,
-                    (double)totalSrcSlicesSize / cTotalSize, (unsigned)cTotalSize);
+                    (double)totalSrcSlicesSize / (double)cTotalSize, (unsigned)cTotalSize);
 
     /* now dstSlices contain the real compressed size of each block, instead of the maximum capacity */
     shrinkSizes(dstSlices, cSizes);
 
     unsigned const nbDicts = nbDictMax ? nbDictMax : nbBlocks;
 
-    cdict_collection_t const cdictionaries = createCDictCollection(dictBuffer.ptr, dictBuffer.size, nbDicts, clevel, dedicatedDictSearch);
+    cdict_collection_t const cdictionaries = createCDictCollection(dictBuffer.ptr, dictBuffer.size, nbDicts, dictContentType, cctxParams);
     CONTROL(cdictionaries.cdicts != NULL);
 
     ddict_collection_t const ddictionaries = createDDictCollection(dictBuffer.ptr, dictBuffer.size, nbDicts);
     CONTROL(ddictionaries.ddicts != NULL);
 
     if (benchCompression) {
-        size_t const dictMem = ZSTD_estimateCDictSize(dictBuffer.size, ZSTD_dlm_byCopy);
+        size_t const dictMem = ZSTD_sizeof_CDict(cdictionaries.cdicts[0]);
         size_t const allDictMem = dictMem * nbDicts;
         DISPLAYLEVEL(3, "generating %u dictionaries, using %.1f MB of memory \n",
                         nbDicts, (double)allDictMem / (1 MB));
@@ -832,11 +889,13 @@ int bench(const char** fileNameTable, unsigned nbFiles,
         buffer_collection_t resultCollection = createBufferCollection_fromSliceCollection(srcSlices);
         CONTROL(resultCollection.buffer.ptr != NULL);
 
-        result = benchMem(dstSlices, resultCollection.slices, ddictionaries, cdictionaries, nbRounds, benchCompression);
+        result = benchMem(dstSlices, resultCollection.slices, ddictionaries,
+                          cdictionaries, nbRounds, benchCompression, exeName,
+                          cctxParams, metricAggregatePref);
 
         freeBufferCollection(resultCollection);
     } else {
-        size_t const dictMem = ZSTD_estimateDDictSize(dictBuffer.size, ZSTD_dlm_byCopy);
+        size_t const dictMem = ZSTD_estimateDDictSize(dictBuffer.size, DICT_LOAD_METHOD);
         size_t const allDictMem = dictMem * nbDicts;
         DISPLAYLEVEL(3, "generating %u dictionaries, using %.1f MB of memory \n",
                         nbDicts, (double)allDictMem / (1 MB));
@@ -846,7 +905,9 @@ int bench(const char** fileNameTable, unsigned nbFiles,
         buffer_collection_t resultCollection = createBufferCollection_fromSliceCollectionSizes(srcSlices);
         CONTROL(resultCollection.buffer.ptr != NULL);
 
-        result = benchMem(resultCollection.slices, dstSlices, ddictionaries, cdictionaries, nbRounds, benchCompression);
+        result = benchMem(resultCollection.slices, dstSlices, ddictionaries,
+                          cdictionaries, nbRounds, benchCompression, exeName,
+                          NULL, metricAggregatePref);
 
         freeBufferCollection(resultCollection);
     }
@@ -924,9 +985,15 @@ int usage(const char* exeName)
     DISPLAY ("-#          : use compression level # (default: %u) \n", CLEVEL_DEFAULT);
     DISPLAY ("-D #        : use # as a dictionary (default: create one) \n");
     DISPLAY ("-i#         : nb benchmark rounds (default: %u) \n", BENCH_TIME_DEFAULT_S);
+    DISPLAY ("-p#         : print speed for all rounds 0=fastest 1=median (default: 0) \n");
     DISPLAY ("--nbBlocks=#: use # blocks for bench (default: one per file) \n");
     DISPLAY ("--nbDicts=# : create # dictionaries for bench (default: one per block) \n");
     DISPLAY ("-h          : help (this text) \n");
+    DISPLAY (" \n");
+    DISPLAY ("Advanced Options (see zstd.h for documentation) : \n");
+    DISPLAY ("--dedicated-dict-search\n");
+    DISPLAY ("--dict-content-type=#\n");
+    DISPLAY ("--dict-attach-pref=#\n");
     return 0;
 }
 
@@ -956,6 +1023,10 @@ int main (int argc, const char** argv)
     size_t blockSize = BLOCKSIZE_DEFAULT;
     unsigned nbDicts = 0;  /* determine nbDicts automatically: 1 dictionary per block */
     unsigned nbBlocks = 0; /* determine nbBlocks automatically, from source and blockSize */
+    ZSTD_dictContentType_e dictContentType = ZSTD_dct_auto;
+    ZSTD_dictAttachPref_e dictAttachPref = ZSTD_dictDefaultAttach;
+    ZSTD_paramSwitch_e prefetchCDictTables = ZSTD_ps_auto;
+    metricAggregatePref_e metricAggregatePref = fastest;
 
     for (int argNb = 1; argNb < argc ; argNb++) {
         const char* argument = argv[argNb];
@@ -965,6 +1036,7 @@ int main (int argc, const char** argv)
         if (!strcmp(argument, "-r")) { recursiveMode = 1; continue; }
         if (!strcmp(argument, "-D")) { argNb++; assert(argNb < argc); dictionary = argv[argNb]; continue; }
         if (longCommandWArg(&argument, "-i")) { nbRounds = readU32FromChar(&argument); continue; }
+        if (longCommandWArg(&argument, "-p")) { metricAggregatePref = (int)readU32FromChar(&argument); continue;}
         if (longCommandWArg(&argument, "--dictionary=")) { dictionary = argument; continue; }
         if (longCommandWArg(&argument, "-B")) { blockSize = readU32FromChar(&argument); continue; }
         if (longCommandWArg(&argument, "--blockSize=")) { blockSize = readU32FromChar(&argument); continue; }
@@ -972,6 +1044,9 @@ int main (int argc, const char** argv)
         if (longCommandWArg(&argument, "--nbBlocks=")) { nbBlocks = readU32FromChar(&argument); continue; }
         if (longCommandWArg(&argument, "--clevel=")) { cLevel = (int)readU32FromChar(&argument); continue; }
         if (longCommandWArg(&argument, "--dedicated-dict-search")) { dedicatedDictSearch = 1; continue; }
+        if (longCommandWArg(&argument, "--dict-content-type=")) { dictContentType = (int)readU32FromChar(&argument); continue; }
+        if (longCommandWArg(&argument, "--dict-attach-pref=")) { dictAttachPref = (int)readU32FromChar(&argument); continue; }
+        if (longCommandWArg(&argument, "--prefetch-cdict-tables=")) { prefetchCDictTables = (int)readU32FromChar(&argument); continue; }
         if (longCommandWArg(&argument, "-")) { cLevel = (int)readU32FromChar(&argument); continue; }
         /* anything that's not a command is a filename */
         nameTable[nameIdx++] = argument;
@@ -989,10 +1064,22 @@ int main (int argc, const char** argv)
         nameTable = NULL;  /* UTIL_createFileNamesTable() takes ownership of nameTable */
     }
 
-    int result = bench(filenameTable->fileNames, (unsigned)filenameTable->tableSize, dictionary, blockSize, cLevel, nbDicts, nbBlocks, nbRounds, benchCompression, dedicatedDictSearch);
+    ZSTD_CCtx_params* cctxParams = ZSTD_createCCtxParams();
+    ZSTD_CCtxParams_init(cctxParams, cLevel);
+    ZSTD_CCtxParams_setParameter(cctxParams, ZSTD_c_enableDedicatedDictSearch, dedicatedDictSearch);
+    ZSTD_CCtxParams_setParameter(cctxParams, ZSTD_c_nbWorkers, 0);
+    ZSTD_CCtxParams_setParameter(cctxParams, ZSTD_c_forceAttachDict, dictAttachPref);
+    ZSTD_CCtxParams_setParameter(cctxParams, ZSTD_c_prefetchCDictTables, prefetchCDictTables);
+
+    int result =
+        bench(filenameTable->fileNames, (unsigned)filenameTable->tableSize,
+              dictionary, blockSize, cLevel, nbDicts, nbBlocks, nbRounds,
+              benchCompression, dictContentType, cctxParams, exeName,
+              metricAggregatePref);
 
     UTIL_freeFileNamesTable(filenameTable);
     free(nameTable);
+    ZSTD_freeCCtxParams(cctxParams);
 
     return result;
 }

zstd.mod/zstd/contrib/linux-kernel/Makefile

@@ -1,5 +1,5 @@
 # ################################################################
-# Copyright (c) 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
@@ -26,14 +26,13 @@ libzstd:
 		--rewrite-include '"(\.\./)?zstd_errors.h"=<linux/zstd_errors.h>' \
 		--sed 's,/\*\*\*,/* *,g' \
 		--sed 's,/\*\*,/*,g' \
+		--spdx \
 		-DZSTD_NO_INTRINSICS \
 		-DZSTD_NO_UNUSED_FUNCTIONS \
 		-DZSTD_LEGACY_SUPPORT=0 \
 		-DZSTD_STATIC_LINKING_ONLY \
 		-DFSE_STATIC_LINKING_ONLY \
-		-DHUF_STATIC_LINKING_ONLY \
 		-DXXH_STATIC_LINKING_ONLY \
-		-DMEM_FORCE_MEMORY_ACCESS=0 \
 		-D__GNUC__ \
 		-D__linux__=1 \
 		-DSTATIC_BMI2=0 \
@@ -49,16 +48,19 @@ libzstd:
 		-UZSTD_MULTITHREAD \
 		-U_MSC_VER \
 		-U_WIN32 \
-		-RZSTDLIB_VISIBILITY= \
-		-RZSTDERRORLIB_VISIBILITY= \
+		-RZSTDLIB_VISIBLE= \
+		-RZSTDERRORLIB_VISIBLE= \
 		-RZSTD_FALLTHROUGH=fallthrough \
 		-DZSTD_HAVE_WEAK_SYMBOLS=0 \
 		-DZSTD_TRACE=0 \
 		-DZSTD_NO_TRACE \
+		-DZSTD_DISABLE_ASM \
 		-DZSTD_LINUX_KERNEL
+	rm linux/lib/zstd/decompress/huf_decompress_amd64.S
 	mv linux/lib/zstd/zstd.h linux/include/linux/zstd_lib.h
 	mv linux/lib/zstd/zstd_errors.h linux/include/linux/
 	cp linux_zstd.h linux/include/linux/zstd.h
+	cp zstd_common_module.c linux/lib/zstd
 	cp zstd_compress_module.c linux/lib/zstd
 	cp zstd_decompress_module.c linux/lib/zstd
 	cp decompress_sources.h linux/lib/zstd
@@ -102,4 +104,5 @@ test: libzstd
 
 .PHONY: clean
 clean:
-	$(RM) -rf linux test/test test/static_test
+	$(RM) -rf linux
+	$(MAKE) -C test clean

zstd.mod/zstd/contrib/linux-kernel/decompress_sources.h

@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */
 /*
- * Copyright (c) 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

zstd.mod/zstd/contrib/linux-kernel/linux.mk

@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause
 # ################################################################
-# Copyright (c) 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
@@ -10,16 +10,10 @@
 # ################################################################
 obj-$(CONFIG_ZSTD_COMPRESS) += zstd_compress.o
 obj-$(CONFIG_ZSTD_DECOMPRESS) += zstd_decompress.o
-
-ccflags-y += -Wno-error=deprecated-declarations
+obj-$(CONFIG_ZSTD_COMMON) += zstd_common.o
 
 zstd_compress-y := \
 		zstd_compress_module.o \
-		common/debug.o \
-		common/entropy_common.o \
-		common/error_private.o \
-		common/fse_decompress.o \
-		common/zstd_common.o \
 		compress/fse_compress.o \
 		compress/hist.o \
 		compress/huf_compress.o \
@@ -35,13 +29,15 @@ zstd_compress-y := \
 
 zstd_decompress-y := \
 		zstd_decompress_module.o \
+		decompress/huf_decompress.o \
+		decompress/zstd_ddict.o \
+		decompress/zstd_decompress.o \
+		decompress/zstd_decompress_block.o \
+
+zstd_common-y := \
+		zstd_common_module.o \
 		common/debug.o \
 		common/entropy_common.o \
 		common/error_private.o \
 		common/fse_decompress.o \
 		common/zstd_common.o \
-		decompress/huf_decompress.o \
-		decompress/huf_decompress_amd64.o \
-		decompress/zstd_ddict.o \
-		decompress/zstd_decompress.o \
-		decompress/zstd_decompress_block.o \

zstd.mod/zstd/contrib/linux-kernel/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

zstd.mod/zstd/contrib/linux-kernel/mem.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

zstd.mod/zstd/contrib/linux-kernel/test/Makefile

@@ -1,5 +1,5 @@
 # ################################################################
-# Copyright (c) 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
@@ -24,7 +24,7 @@ LINUX_ZSTD_OBJECTS0   := $(LINUX_ZSTD_FILES:.c=.o)
 LINUX_ZSTD_OBJECTS    := $(LINUX_ZSTD_OBJECTS0:.S=.o)
 
 %.o: %.S
-	$(CC) -c $(CPPFLAGS) $(CFLAGS) $^ -o $@
+	$(COMPILE.S) $(OUTPUT_OPTION) $<
 
 liblinuxzstd.a: $(LINUX_ZSTD_OBJECTS)
 	$(AR) $(ARFLAGS) $@ $^
@@ -45,4 +45,5 @@ clean:
 	$(RM) -f $(LINUX_ZSTDLIB)/*.o
 	$(RM) -f $(LINUX_ZSTDLIB)/**/*.o
 	$(RM) -f *.o *.a
+	$(RM) -f static_test
 	$(RM) -f test

zstd.mod/zstd/contrib/linux-kernel/test/include/linux/compiler.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-2021, 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

zstd.mod/zstd/contrib/linux-kernel/test/include/linux/errno.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-2021, 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

zstd.mod/zstd/contrib/linux-kernel/test/include/linux/kernel.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-2021, 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

zstd.mod/zstd/contrib/linux-kernel/test/include/linux/limits.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-2021, 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

zstd.mod/zstd/contrib/linux-kernel/test/include/linux/math64.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-2021, 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

zstd.mod/zstd/contrib/linux-kernel/test/include/linux/module.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-2021, 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
@@ -12,6 +12,8 @@
 
 #define EXPORT_SYMBOL(symbol)                                                  \
   void* __##symbol = symbol
+#define EXPORT_SYMBOL_GPL(symbol)                                              \
+  void* __##symbol = symbol
 #define MODULE_LICENSE(license)
 #define MODULE_DESCRIPTION(description)
 

zstd.mod/zstd/contrib/linux-kernel/test/include/linux/printk.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-2021, 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

zstd.mod/zstd/contrib/linux-kernel/test/include/linux/stddef.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-2021, 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

zstd.mod/zstd/contrib/linux-kernel/test/include/linux/swab.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-2021, 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

zstd.mod/zstd/contrib/linux-kernel/test/include/linux/types.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-2021, 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

zstd.mod/zstd/contrib/linux-kernel/test/include/linux/xxhash.h

@@ -2,7 +2,7 @@
  * xxHash - Extremely Fast Hash algorithm
  * Copyright (C) 2012-2016, Yann Collet.
  *
- * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+ * BSD 2-Clause License (https://opensource.org/licenses/bsd-license.php)
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are
@@ -260,7 +260,7 @@ XXH_API void xxh64_copy_state(struct xxh64_state *dst, const struct xxh64_state
  * xxHash - Extremely Fast Hash algorithm
  * Copyright (C) 2012-2016, Yann Collet.
  *
- * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+ * BSD 2-Clause License (https://opensource.org/licenses/bsd-license.php)
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are

zstd.mod/zstd/contrib/linux-kernel/test/static_test.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 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

zstd.mod/zstd/contrib/linux-kernel/test/test.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 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
@@ -186,11 +186,14 @@ static void __attribute__((noinline)) use(void *x) {
   asm volatile("" : "+r"(x));
 }
 
+static void __attribute__((noinline)) fill_stack(void) {
+  memset(g_stack, 0x33, 8192);
+}
+
 static void __attribute__((noinline)) set_stack(void) {
 
   char stack[8192];
   g_stack = stack;
-  memset(g_stack, 0x33, 8192);
   use(g_stack);
 }
 
@@ -208,6 +211,7 @@ static void __attribute__((noinline)) check_stack(void) {
 
 static void test_stack_usage(test_data_t const *data) {
   set_stack();
+  fill_stack();
   test_f2fs();
   test_btrfs(data);
   test_decompress_unzstd(data);

zstd.mod/zstd/contrib/linux-kernel/zstd_common_module.c

@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause
+/*
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
+ * 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.
+ */
+
+#include <linux/module.h>
+
+#include "common/huf.h"
+#include "common/fse.h"
+#include "common/zstd_internal.h"
+
+// Export symbols shared by compress and decompress into a common module
+
+#undef ZSTD_isError   /* defined within zstd_internal.h */
+EXPORT_SYMBOL_GPL(FSE_readNCount);
+EXPORT_SYMBOL_GPL(HUF_readStats);
+EXPORT_SYMBOL_GPL(HUF_readStats_wksp);
+EXPORT_SYMBOL_GPL(ZSTD_isError);
+EXPORT_SYMBOL_GPL(ZSTD_getErrorName);
+EXPORT_SYMBOL_GPL(ZSTD_getErrorCode);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("Zstd Common");

zstd.mod/zstd/contrib/linux-kernel/zstd_compress_module.c

@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause
 /*
- * Copyright (c) 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
@@ -133,7 +133,11 @@ EXPORT_SYMBOL(zstd_init_cstream);
 size_t zstd_reset_cstream(zstd_cstream *cstream,
 	unsigned long long pledged_src_size)
 {
-	return ZSTD_resetCStream(cstream, pledged_src_size);
+	if (pledged_src_size == 0)
+		pledged_src_size = ZSTD_CONTENTSIZE_UNKNOWN;
+	ZSTD_FORWARD_IF_ERR( ZSTD_CCtx_reset(cstream, ZSTD_reset_session_only) );
+	ZSTD_FORWARD_IF_ERR( ZSTD_CCtx_setPledgedSrcSize(cstream, pledged_src_size) );
+	return 0;
 }
 EXPORT_SYMBOL(zstd_reset_cstream);
 

zstd.mod/zstd/contrib/linux-kernel/zstd_decompress_module.c

@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause
 /*
- * Copyright (c) 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

zstd.mod/zstd/contrib/linux-kernel/zstd_deps.h

@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */
 /*
- * Copyright (c) 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
@@ -84,7 +84,7 @@ static uint64_t ZSTD_div64(uint64_t dividend, uint32_t divisor) {
 
 #include <linux/kernel.h>
 
-#define assert(x) WARN_ON((x))
+#define assert(x) WARN_ON(!(x))
 
 #endif /* ZSTD_DEPS_ASSERT */
 #endif /* ZSTD_DEPS_NEED_ASSERT */

zstd.mod/zstd/contrib/match_finders/README.md

@@ -14,7 +14,7 @@
  * files would be small relative to the size of the file. 
  * 
  * Various 'diffing' algorithms utilize this notion of edit distance and 
- * the corrensponding concept of a minimal edit script between two 
+ * the corresponding concept of a minimal edit script between two 
  * sequences to identify the regions within two files where they differ. 
  * The core algorithm used in this match finder is described in: 
  * 
@@ -28,12 +28,12 @@
  * 
  * Note: after some experimentation, this approach proved to not provide enough 
  * utility to justify the additional CPU used in finding matches. The one area
- * where this approach consistenly outperforms Zstandard even on level 19 is 
- * when compressing small files (<10 KB) using a equally small dictionary that 
+ * where this approach consistently outperforms Zstandard even on level 19 is 
+ * when compressing small files (<10 KB) using an equally small dictionary that 
  * is very similar to the source file. For the use case that this was intended,
  * (large similar files) this approach by itself took 5-10X longer than zstd-19 and 
  * generally resulted in 2-3X larger files. The core advantage that zstd-19 has 
- * over this appraoch for match finding is the overlapping matches. This approach 
+ * over this approach for match finding is the overlapping matches. This approach 
  * cannot find any. 
  * 
  * I'm leaving this in the contrib section in case this ever becomes interesting 

zstd.mod/zstd/contrib/match_finders/zstd_edist.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-present, 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
@@ -12,7 +12,7 @@
 *  Dependencies
 ***************************************/
 
-/* Currently relies on qsort when combining contiguous matches. This can probabily 
+/* Currently relies on qsort when combining contiguous matches. This can probably 
  * be avoided but would require changes to the algorithm. The qsort is far from 
  * the bottleneck in this algorithm even for medium sized files so it's probably 
  * not worth trying to address */ 
@@ -26,7 +26,7 @@
 *  Constants
 ***************************************/
 
-/* Just a sential for the entires of the diagnomal matrix */
+/* Just a sential for the entries of the diagonal matrix */
 #define ZSTD_EDIST_DIAG_MAX (S32)(1 << 30)
 
 /* How large should a snake be to be considered a 'big' snake. 
@@ -39,7 +39,7 @@
 #define ZSTD_EDIST_SNAKE_ITER_THRESH 200
 
 /* After how many iterations should be just give up and take 
- * the best availabe edit script for this round */ 
+ * the best available edit script for this round */ 
 #define ZSTD_EDIST_EXPENSIVE_THRESH 1024
 
 /*-*************************************
@@ -57,10 +57,10 @@ typedef struct {
     const BYTE* src;
     size_t dictSize;
     size_t srcSize;
-    S32* forwardDiag;            /* Entires of the forward diagonal stored here */ 
-    S32* backwardDiag;           /* Entires of the backward diagonal stored here.
+    S32* forwardDiag;            /* Entries of the forward diagonal stored here */
+    S32* backwardDiag;           /* Entries of the backward diagonal stored here.
                                   *   Note: this buffer and the 'forwardDiag' buffer 
-                                  *   are contiguous. See the ZSTD_eDist_genSequences */ 
+                                  *   are contiguous. See the ZSTD_eDist_genSequences */
     ZSTD_eDist_match* matches;   /* Accumulate matches of length 1 in this buffer. 
                                   *   In a subsequence post-processing step, we combine 
                                   *   contiguous matches. */
@@ -192,7 +192,7 @@ static void ZSTD_eDist_diag(ZSTD_eDist_state* state,
         if (!useHeuristics)
             continue;
 
-        /* Everything under this point is a heuritic. Using these will 
+        /* Everything under this point is a heuristic. Using these will 
          * substantially speed up the match finding. In some cases, taking 
          * the total match finding time from several minutes to seconds.
          * Of course, the caveat is that the edit script found may no longer 
@@ -366,8 +366,8 @@ static int ZSTD_eDist_compare(ZSTD_eDist_state* state,
         }
     } else if (srcLow == srcHigh) {
         while (dictLow < dictHigh) {
-            /* Reaching this point means deleteing dict[dictLow] from 
-             * the current positino of dict */ 
+            /* Reaching this point means deleting dict[dictLow] from 
+             * the current position of dict */ 
             dictLow++;
         }
     } else {
@@ -395,7 +395,7 @@ static int ZSTD_eDist_matchComp(const void* p, const void* q)
 }
 
 /* The matches from the approach above will all be of the form 
- * (dictIdx, srcIdx, 1). this method combines contiguous matches 
+ * (dictIdx, srcIdx, 1). This method combines contiguous matches 
  * of length MINMATCH or greater. Matches less than MINMATCH 
  * are discarded */ 
 static void ZSTD_eDist_combineMatches(ZSTD_eDist_state* state)
@@ -460,7 +460,7 @@ static size_t ZSTD_eDist_convertMatchesToSequences(ZSTD_Sequence* sequences,
 }
 
 /*-*************************************
-*  Interal utils
+*  Internal utils
 ***************************************/
 
 static size_t ZSTD_eDist_hamingDist(const BYTE* const a,

zstd.mod/zstd/contrib/match_finders/zstd_edist.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-present, 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
@@ -21,7 +21,7 @@
  * files would be small relative to the size of the file. 
  * 
  * Various 'diffing' algorithms utilize this notion of edit distance and 
- * the corrensponding concept of a minimal edit script between two 
+ * the corresponding concept of a minimal edit script between two 
  * sequences to identify the regions within two files where they differ. 
  * The core algorithm used in this match finder is described in: 
  * 
@@ -35,12 +35,12 @@
  * 
  * Note: after some experimentation, this approach proved to not provide enough 
  * utility to justify the additional CPU used in finding matches. The one area
- * where this approach consistenly outperforms Zstandard even on level 19 is 
- * when compressing small files (<10 KB) using a equally small dictionary that 
+ * where this approach consistently outperforms Zstandard even on level 19 is 
+ * when compressing small files (<10 KB) using an equally small dictionary that 
  * is very similar to the source file. For the use case that this was intended,
  * (large similar files) this approach by itself took 5-10X longer than zstd-19 and 
  * generally resulted in 2-3X larger files. The core advantage that zstd-19 has 
- * over this appraoch for match finding is the overlapping matches. This approach 
+ * over this approach for match finding is the overlapping matches. This approach 
  * cannot find any. 
  * 
  * I'm leaving this in the contrib section in case this ever becomes interesting 

zstd.mod/zstd/contrib/pzstd/ErrorHolder.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-present, 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

zstd.mod/zstd/contrib/pzstd/Logging.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-present, 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

zstd.mod/zstd/contrib/pzstd/Makefile

@@ -1,5 +1,5 @@
 # ################################################################
-# Copyright (c) 2016-present, 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
@@ -37,10 +37,16 @@ CFLAGS   += -Wno-deprecated-declarations
 PZSTD_INC  = -I$(ZSTDDIR) -I$(ZSTDDIR)/common -I$(PROGDIR) -I.
 GTEST_INC  = -isystem googletest/googletest/include
 
+# If default C++ version is older than C++11, explicitly set C++11, which is the
+# minimum required by the code.
+ifeq ($(shell echo "\043if __cplusplus < 201103L\n\043error\n\043endif" | $(CXX) -x c++ -Werror -c - -o /dev/null 2>/dev/null && echo 1 || echo 0),0)
+PZSTD_CXX_STD := -std=c++11
+endif
+
 PZSTD_CPPFLAGS  = $(PZSTD_INC)
 PZSTD_CCXXFLAGS =
 PZSTD_CFLAGS    = $(PZSTD_CCXXFLAGS)
-PZSTD_CXXFLAGS  = $(PZSTD_CCXXFLAGS) -std=c++11
+PZSTD_CXXFLAGS  = $(PZSTD_CCXXFLAGS) $(PZSTD_CXX_STD)
 PZSTD_LDFLAGS   =
 EXTRA_FLAGS     =
 ALL_CFLAGS      = $(EXTRA_FLAGS) $(CPPFLAGS) $(PZSTD_CPPFLAGS) $(CFLAGS)   $(PZSTD_CFLAGS)

zstd.mod/zstd/contrib/pzstd/Options.cpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-present, 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

zstd.mod/zstd/contrib/pzstd/Options.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-present, 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

zstd.mod/zstd/contrib/pzstd/Pzstd.cpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-present, 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
@@ -10,11 +10,13 @@
 #include "Pzstd.h"
 #include "SkippableFrame.h"
 #include "utils/FileSystem.h"
+#include "utils/Portability.h"
 #include "utils/Range.h"
 #include "utils/ScopeGuard.h"
 #include "utils/ThreadPool.h"
 #include "utils/WorkQueue.h"
 
+#include <algorithm>
 #include <chrono>
 #include <cinttypes>
 #include <cstddef>
@@ -336,6 +338,10 @@ static size_t calculateStep(
     const ZSTD_parameters &params) {
   (void)size;
   (void)numThreads;
+  // Not validated to work correctly for window logs > 23.
+  // It will definitely fail if windowLog + 2 is >= 4GB because
+  // the skippable frame can only store sizes up to 4GB.
+  assert(params.cParams.windowLog <= 23);
   return size_t{1} << (params.cParams.windowLog + 2);
 }
 
@@ -587,7 +593,8 @@ std::uint64_t writeFile(
       // start writing before compression is done because we need to know the
       // compressed size.
       // Wait for the compressed size to be available and write skippable frame
-      SkippableFrame frame(out->size());
+      assert(uint64_t(out->size()) < uint64_t(1) << 32);
+      SkippableFrame frame(uint32_t(out->size()));
       if (!writeData(frame.data(), outputFd)) {
         errorHolder.setError("Failed to write output");
         return bytesWritten;

zstd.mod/zstd/contrib/pzstd/Pzstd.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-present, 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

zstd.mod/zstd/contrib/pzstd/README.md

@@ -31,7 +31,7 @@ If this number is not suitable, during compilation you can define `PZSTD_NUM_THR
 
 ## Benchmarks
 
-As a reference, PZstandard and Pigz were compared on an Intel Core i7 @ 3.1 GHz, each using 4 threads, with the [Silesia compression corpus](http://sun.aei.polsl.pl/~sdeor/index.php?page=silesia).
+As a reference, PZstandard and Pigz were compared on an Intel Core i7 @ 3.1 GHz, each using 4 threads, with the [Silesia compression corpus](https://sun.aei.polsl.pl//~sdeor/index.php?page=silesia).
 
 Compression Speed vs Ratio with 4 Threads | Decompression Speed with 4 Threads
 ------------------------------------------|-----------------------------------

zstd.mod/zstd/contrib/pzstd/SkippableFrame.cpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-present, 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

zstd.mod/zstd/contrib/pzstd/SkippableFrame.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-present, 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

zstd.mod/zstd/contrib/pzstd/main.cpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-present, 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

zstd.mod/zstd/contrib/pzstd/test/OptionsTest.cpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-present, 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

zstd.mod/zstd/contrib/pzstd/test/PzstdTest.cpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-present, 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

zstd.mod/zstd/contrib/pzstd/test/RoundTrip.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-present, 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

zstd.mod/zstd/contrib/pzstd/test/RoundTripTest.cpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-present, 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

zstd.mod/zstd/contrib/pzstd/utils/Buffer.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-present, 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

zstd.mod/zstd/contrib/pzstd/utils/FileSystem.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-present, 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
@@ -8,16 +8,18 @@
  */
 #pragma once
 
+#include "utils/Portability.h"
 #include "utils/Range.h"
 
 #include <sys/stat.h>
 #include <cerrno>
 #include <cstdint>
+#include <limits>
 #include <system_error>
 
 // A small subset of `std::filesystem`.
 // `std::filesystem` should be a drop in replacement.
-// See http://en.cppreference.com/w/cpp/filesystem for documentation.
+// See https://en.cppreference.com/w/cpp/filesystem for documentation.
 
 namespace pzstd {
 
@@ -28,7 +30,7 @@ typedef struct ::_stat64 file_status;
 typedef struct ::stat file_status;
 #endif
 
-/// http://en.cppreference.com/w/cpp/filesystem/status
+/// https://en.cppreference.com/w/cpp/filesystem/status
 inline file_status status(StringPiece path, std::error_code& ec) noexcept {
   file_status status;
 #if defined(_MSC_VER)
@@ -44,7 +46,7 @@ inline file_status status(StringPiece path, std::error_code& ec) noexcept {
   return status;
 }
 
-/// http://en.cppreference.com/w/cpp/filesystem/is_regular_file
+/// https://en.cppreference.com/w/cpp/filesystem/is_regular_file
 inline bool is_regular_file(file_status status) noexcept {
 #if defined(S_ISREG)
   return S_ISREG(status.st_mode);
@@ -55,12 +57,12 @@ inline bool is_regular_file(file_status status) noexcept {
 #endif
 }
 
-/// http://en.cppreference.com/w/cpp/filesystem/is_regular_file
+/// https://en.cppreference.com/w/cpp/filesystem/is_regular_file
 inline bool is_regular_file(StringPiece path, std::error_code& ec) noexcept {
   return is_regular_file(status(path, ec));
 }
 
-/// http://en.cppreference.com/w/cpp/filesystem/is_directory
+/// https://en.cppreference.com/w/cpp/filesystem/is_directory
 inline bool is_directory(file_status status) noexcept {
 #if defined(S_ISDIR)
   return S_ISDIR(status.st_mode);
@@ -71,22 +73,22 @@ inline bool is_directory(file_status status) noexcept {
 #endif
 }
 
-/// http://en.cppreference.com/w/cpp/filesystem/is_directory
+/// https://en.cppreference.com/w/cpp/filesystem/is_directory
 inline bool is_directory(StringPiece path, std::error_code& ec) noexcept {
   return is_directory(status(path, ec));
 }
 
-/// http://en.cppreference.com/w/cpp/filesystem/file_size
+/// https://en.cppreference.com/w/cpp/filesystem/file_size
 inline std::uintmax_t file_size(
     StringPiece path,
     std::error_code& ec) noexcept {
   auto stat = status(path, ec);
   if (ec) {
-    return -1;
+    return std::numeric_limits<uintmax_t>::max();
   }
   if (!is_regular_file(stat)) {
     ec.assign(ENOTSUP, std::generic_category());
-    return -1;
+    return std::numeric_limits<uintmax_t>::max();
   }
   ec.clear();
   return stat.st_size;