Including the `include/git2` build path is a seemingly unnecessary
oversight to include the generated `experimental.h` file.

xdiff is a dependency (from git core) and more properly belongs in the
'deps' directory. Move it there, and add a stub for cmake to resolve
xdiff from the system location in the future. (At present, bundled xdiff
remains hardcoded.)

The library name is correctly libgit2 (not git2) or libgit2-experimental
depending on configuration.

libgit2 can be built with optional, experimental sha256 support. This
allows consumers to begin testing and providing feedback for our sha256
support while we continue to develop it, and allows us to make API
breaking changes while we iterate on a final sha256 implementation.

The results will be `git2-experimental.dll` and installed as
`git2-experimental.h` to avoid confusion with a production libgit2.

Linux has a /usr/include/features.h, which gets confusing; update this
to `git2_features.h` and move it into the `util` directory.

The `git2internal` target is actually the git library; call it such so
that IDE users have visibility into it.

Instead of simply including the utility files directly, make them a
cmake object library for easy reusability between other projects within
libgit2.

Now the top-level `src` is responsible for platform selection, while the
next-level `libgit2` and `util` configurations are responsible for
identifying what objects they include.

Introduce `git_rand`, a PRNG based on xoroshiro256**, a fast,
all-purpose pseudo-random number generator: https://prng.di.unimi.it

The PRNG will be seeded by the system's entropy store when possible,
falling back to current time and system data (pid, uptime, etc).
Inspiration for this was taken from libressl, but since our PRNG is
not used for cryptographic purposes (and indeed currently only generates
a unique temp file name that is written in a protected directory),
this should be more than sufficient.

Our implementation of xoroshiro256** was taken almost strictly from
the original author's sources, but was tested against PractRand to
ensure that there were no foolish mistranslations:

```
RNG_test using PractRand version 0.94
RNG = RNG_stdin64, seed = unknown
test set = core, folding = standard (64 bit)

rng=RNG_stdin64, seed=unknown
length= 256 megabytes (2^28 bytes), time= 2.9 seconds
  no anomalies in 210 test result(s)

rng=RNG_stdin64, seed=unknown
length= 512 megabytes (2^29 bytes), time= 6.2 seconds
  no anomalies in 226 test result(s)

rng=RNG_stdin64, seed=unknown
length= 1 gigabyte (2^30 bytes), time= 12.7 seconds
  no anomalies in 243 test result(s)

rng=RNG_stdin64, seed=unknown
length= 2 gigabytes (2^31 bytes), time= 25.4 seconds
  no anomalies in 261 test result(s)

rng=RNG_stdin64, seed=unknown
length= 4 gigabytes (2^32 bytes), time= 50.6 seconds
  no anomalies in 277 test result(s)

rng=RNG_stdin64, seed=unknown
length= 8 gigabytes (2^33 bytes), time= 104 seconds
  no anomalies in 294 test result(s)
```

Update to the xdiff used in git v2.35.0, with updates to our build
configuration to ignore the sort of warnings that we normally care
about (signed/unsigned mismatch, unused, etc.)

Any git-specific abstraction bits are now redefined for our use in
`git-xdiff.h`.  It is a (wildly optimistic) hope that we can use that
indirection layer to standardize on a shared xdiff implementation.

Also applies to *_BINARY_DIR.

This effectively reverts 84083dcc,
which broke all users of libgit2 that use it as a CMake subdirectory
(via `add_subdirectory()`). This is because CMAKE_SOURCE_DIR refers
to the root-most CMake directory, which in the case of
`add_subdirectory()` is a parent project to libgit2 and thus the paths
don't make any sense to the configuration files. Corollary,
CMAKE_SOURCE_DIR only makes sense if the CMake project is always the
root project - which can rarely be guaranteed.

In all honesty, CMake should deprecate and eventually remove
CMAKE_SOURCE_DIR and CMAKE_BINARY_DIR. It's been the source of headaches
and confusion for years, they're rarely useful over
CMAKE_CURRENT_(SOURCE|BINARY)_DIR or PROJECT_(SOURCE|BINARY)_DIR,
and they cause a lot of confusing configuration and source
code layouts to boot.

Any time they are used, they break `add_subdirectory()` almost 100% of
the time, cause confusing error messages, and hide subtle bugs.

Instead of using the project-specific `libgit2_SOURCE_DIR` and
`libgit2_BINARY_DIR` variables, use `CMAKE_SOURCE_DIR` and
`CMAKE_BINARY_DIR`.

The select hashes module selects the hash; the CMakeLists.txt selects
the files to implement it.

Update the global variables `LIBGIT2_OBJECTS` to
`LIBGIT2_DEPENDENCY_OBJECTS` for clarity and consistency.

We should enforce declarations throughout the code-base, including
examples, fuzzers and tests, not just in the `src` tree.

Move zlib selection into its own cmake module.

Move WinHTTP selection into its own cmake module.

Move SSH selection into its own cmake module.

Move regex selection into its own cmake module.

Move http_parser selection into its own cmake module.

There's no need to add the deprecation at the top-level.  Our tests add
deprecation explicitly.

WinHTTP can now be disabled with `USE_WINHTTP=OFF` instead of
`WINHTTP=OFF` to better support the other cmake semantics.

Threading can now be disabled with `USE_THREADS=OFF` instead of
`THREADSAFE=OFF` to better support the other cmake semantics.

Nanosecond support is the default _if_ we can detect it.  This should be
our default always - like threads - and people can opt out explicitly.

Ensure that we always use lowercase function names, and that we do not
have spaces preceding open parentheses, for consistency.

There's no need to make tracing opt-in; it should always be included.

Co-authored-by: Edward Thomson <ethomson@github.com>

Add `GIT_DEBUG_STRICT_ALLOC` to help identify problematic callers of
allocation code that pass a `0` size to the allocators and then expect a
non-`NULL` return.

When given a 0-size allocation, `malloc` _may_ return either a `NULL`
_or_ a pointer that is not writeable.  Most systems return a non-`NULL`
pointer; AIX is an outlier.  We should be able to cope with this AIXy
behavior, so this adds an option to emulate it.

Now `USE_BUNDLED_ZLIB` can be set to the string `Chromium` to enable the
Chromium implementation of zlib.

This change builds libgit2 using Chromium's zlib implementation by
invoking cmake with `-DUSE_BUNDLED_ZLIB=ON -DUSE_CHROMIUM_ZLIB=ON`,
which is ~10% faster than the bundled zlib for the core::zstream suite.

This version of zlib has some optimizations:

a) Decompression (Intel+ARM): inflate_fast, adler32, crc32, etc.
b) Compression (Intel): fill_window, longest_match, hash function, etc.

Due to the introduction of SIMD optimizations, and to get the maximum
performance out of this fork of zlib, this requires an x86_64 processor
with SSE4.2 and CLMUL (anything Westmere or later, ~2010). The Chromium
zlib implementation also supports ARM with NEON, but it has not been
enabled in this patch.

Performance
===========

TL;DR: Running just `./libgit2_clar -score::zstream` 100 times in a loop
took 0:56.30 before and 0:50.67 after (~10% reduction!).

The bundled and system zlib implementations on an Ubuntu Focal system
perform relatively similar (the bundled one is marginally better due to
the compiler being able to inline some functions), so only the bundled
and Chromium zlibs were compared.

For a more balanced comparison (to ensure that nothing regressed
overall), `libgit2_clar` under `perf` was also run, and the zlib-related
functions were compared.

Bundled
-------

```shell
cmake \
  -DUSE_BUNDLED_ZLIB=ON \
  -DUSE_CHROMIUM_ZLIB=OFF \
  -DCMAKE_BUILD_TYPE="RelWithDebInfo" \
  -DCMAKE_C_FLAGS="-fPIC -fno-omit-frame-pointer" \
  -GNinja \
  ..
ninja
perf record --call-graph=dwarf ./libgit2_clar
perf report --children
```

```
Samples: 87K of event 'cycles', Event count (approx.): 75923450603
  Children      Self  Command       Shared Objec  Symbol
+    4.14%     0.01%  libgit2_clar  libgit2_clar  [.] git_zstream_get_output_chunk
+    2.91%     0.00%  libgit2_clar  libgit2_clar  [.] git_zstream_get_output
+    0.69%     0.00%  libgit2_clar  libgit2_clar  [.] git_zstream_get_output (inlined)
     0.17%     0.00%  libgit2_clar  libgit2_clar  [.] git_zstream_init
     0.02%     0.00%  libgit2_clar  libgit2_clar  [.] git_zstream_reset
     0.00%     0.00%  libgit2_clar  libgit2_clar  [.] git_zstream_eos
     0.00%     0.00%  libgit2_clar  libgit2_clar  [.] git_zstream_done
     0.00%     0.00%  libgit2_clar  libgit2_clar  [.] git_zstream_free (inlined)

Samples: 87K of event 'cycles', Event count (approx.): 75923450603
  Children      Self  Command       Shared Objec  Symbol
+    3.12%     0.01%  libgit2_clar  libgit2_clar  [.] deflate
+    2.65%     1.48%  libgit2_clar  libgit2_clar  [.] deflate_slow
+    1.60%     0.55%  libgit2_clar  libgit2_clar  [.] inflate
+    0.53%     0.00%  libgit2_clar  libgit2_clar  [.] write_deflate
     0.49%     0.36%  libgit2_clar  libgit2_clar  [.] inflate_fast
     0.46%     0.02%  libgit2_clar  libgit2_clar  [.] deflate_fast
     0.19%     0.19%  libgit2_clar  libgit2_clar  [.] inflate_table
     0.16%     0.01%  libgit2_clar  libgit2_clar  [.] inflateInit_
     0.15%     0.00%  libgit2_clar  libgit2_clar  [.] inflateInit2_ (inlined)
     0.10%     0.00%  libgit2_clar  libgit2_clar  [.] deflateInit_
     0.10%     0.00%  libgit2_clar  libgit2_clar  [.] deflateInit2_
     0.03%     0.00%  libgit2_clar  libgit2_clar  [.] deflateReset (inlined)
     0.02%     0.00%  libgit2_clar  libgit2_clar  [.] deflateReset
     0.02%     0.00%  libgit2_clar  libgit2_clar  [.] inflateEnd
     0.02%     0.00%  libgit2_clar  libgit2_clar  [.] deflateEnd
     0.01%     0.00%  libgit2_clar  libgit2_clar  [.] deflateResetKeep
     0.01%     0.01%  libgit2_clar  libgit2_clar  [.] inflateReset2
     0.01%     0.00%  libgit2_clar  libgit2_clar  [.] deflateReset (inlined)
     0.00%     0.00%  libgit2_clar  libgit2_clar  [.] inflateStateCheck (inlined)
     0.00%     0.00%  libgit2_clar  libgit2_clar  [.] inflateReset (inlined)
     0.00%     0.00%  libgit2_clar  libgit2_clar  [.] inflateStateCheck (inlined)
     0.00%     0.00%  libgit2_clar  libgit2_clar  [.] deflateStateCheck (inlined)
     0.00%     0.00%  libgit2_clar  libgit2_clar  [.] inflateResetKeep (inlined)
```

Chromium
--------

```shell
cmake \
  -DUSE_BUNDLED_ZLIB=ON \
  -DUSE_CHROMIUM_ZLIB=ON \
  -DCMAKE_BUILD_TYPE="RelWithDebInfo" \
  -DCMAKE_C_FLAGS="-fPIC -fno-omit-frame-pointer" \
  -GNinja \
  ..
ninja
perf record --call-graph=dwarf ./libgit2_clar
perf report --children
```

```
Samples: 97K of event 'cycles', Event count (approx.): 80862210917
  Children      Self  Command       Shared Objec  Symbol
+    3.31%     0.00%  libgit2_clar  libgit2_clar  [.] git_zstream_get_output_chunk
+    2.27%     0.01%  libgit2_clar  libgit2_clar  [.] git_zstream_get_output
+    0.55%     0.00%  libgit2_clar  libgit2_clar  [.] git_zstream_get_output (inlined)
     0.18%     0.00%  libgit2_clar  libgit2_clar  [.] git_zstream_init
     0.02%     0.00%  libgit2_clar  libgit2_clar  [.] git_zstream_reset
     0.00%     0.00%  libgit2_clar  libgit2_clar  [.] git_zstream_free (inlined)
     0.00%     0.00%  libgit2_clar  libgit2_clar  [.] git_zstream_done
     0.00%     0.00%  libgit2_clar  libgit2_clar  [.] git_zstream_free

Samples: 97K of event 'cycles', Event count (approx.): 80862210917
  Children      Self  Command       Shared Objec  Symbol
+    2.55%     0.01%  libgit2_clar  libgit2_clar  [.] deflate
+    2.25%     1.41%  libgit2_clar  libgit2_clar  [.] deflate_slow
+    1.10%     0.52%  libgit2_clar  libgit2_clar  [.] inflate
     0.36%     0.00%  libgit2_clar  libgit2_clar  [.] write_deflate
     0.30%     0.03%  libgit2_clar  libgit2_clar  [.] deflate_fast
     0.28%     0.15%  libgit2_clar  libgit2_clar  [.] inflate_fast_chunk_
     0.19%     0.19%  libgit2_clar  libgit2_clar  [.] inflate_table
     0.17%     0.01%  libgit2_clar  libgit2_clar  [.] inflateInit_
     0.16%     0.00%  libgit2_clar  libgit2_clar  [.] inflateInit2_ (inlined)
     0.15%     0.00%  libgit2_clar  libgit2_clar  [.] deflateInit_
     0.15%     0.00%  libgit2_clar  libgit2_clar  [.] deflateInit2_
     0.11%     0.01%  libgit2_clar  libgit2_clar  [.] adler32_z
     0.09%     0.09%  libgit2_clar  libgit2_clar  [.] adler32_simd_
     0.05%     0.00%  libgit2_clar  libgit2_clar  [.] deflateReset (inlined)
     0.05%     0.00%  libgit2_clar  libgit2_clar  [.] deflate_read_buf
     0.03%     0.00%  libgit2_clar  libgit2_clar  [.] inflateEnd
     0.02%     0.00%  libgit2_clar  libgit2_clar  [.] deflateReset
     0.01%     0.00%  libgit2_clar  libgit2_clar  [.] deflateEnd
     0.01%     0.01%  libgit2_clar  libgit2_clar  [.] inflateReset2
     0.01%     0.00%  libgit2_clar  libgit2_clar  [.] inflateReset (inlined)
     0.00%     0.00%  libgit2_clar  libgit2_clar  [.] adler32
     0.00%     0.00%  libgit2_clar  libgit2_clar  [.] inflateResetKeep (inlined)
     0.00%     0.00%  libgit2_clar  libgit2_clar  [.] deflateResetKeep
     0.00%     0.00%  libgit2_clar  libgit2_clar  [.] inflateStateCheck (inlined)
     0.00%     0.00%  libgit2_clar  libgit2_clar  [.] inflateStateCheck (inlined)
     0.00%     0.00%  libgit2_clar  libgit2_clar  [.] inflateStateCheck (inlined)
     0.00%     0.00%  libgit2_clar  libgit2_clar  [.] deflateStateCheck (inlined)
```

We set up some compile definitions as part of our src/CMakeLists.txt.
While the definitions are global, we really only need them as part of
the git2internal target which compiles all the objects. Let's thus use
`target_compile_definitions` instead of `add_definitions`.