We can now use the `git_process` class to invoke OpenSSH and use it as
an SSH transport. This may be preferred over libssh2 for a variety of
callers.

We may want to support SSH but with a different provider that is not
libssh2. Add GIT_SSH to indicate that we have some inbuilt SSH support
and GIT_SSH_LIBSSH2 to indicate that support is via libssh2. This is
similar to how we support GIT_HTTPS and GIT_OPENSSL, for example.

ci: update to macOS 12

ci: retry flaky online tests

cmake: fix openssl build on win32

since f15c8ac7 libgit unconditionally depends on secur32 on Windows
but only added it in cmake for the winhttp and schannel variants.
In case libgit is built against openssl it would fail to link.

This moves secur32 out of the https backend selection code into
the global win32 condition (and while at it also adds ws2_32 to the .pc file)

cli: add a `git config` command

config: provide an "origin" for config entries

README.md: Fix link to conan packages

Revert "CMake: Search for ssh2 instead of libssh2."

proxy: Return an error for invalid proxy URLs instead of crashing.

Test proxies specified by both host:port format in configuration
options, environment variables, and `http.proxy` configuration.

The common format for specifying proxy URLs is just 'host:port'. Handle
the common case.

Introduce a url parser that defaults to treating poorly specified URLs
as http URLs. For example: `localhost:8080` is treated as
`http://localhost:8080/` by the http-biased url parsing, instead of a
URL with a scheme `localhost` and a path of `8080`..

Refactor url parsing to simplify the state-passing (introducing a
struct) and add a path parser for future reusability.

ssh: fix known_hosts leak in _git_ssh_setup_conn

stransport: macOS: replace errSSLNetworkTimeout, with hard-coded value

Instead of special casing `--help`, reorder the arguments for
subcommands so that it can handle "global" arguments like `--help`,
`-c key=value`, etc.

Introduce `cli_repository_open` which will reparse command-line options
looking for `-c` or `--config-env`. Add those values to an in-memory
configuration database and configure the opened repository with that.

Add a `config` command with `--list` and `--get`.

Provide two memory-backed configuration backends -- one that takes a
string in config file format `[section] key=value` and one that takes a
list of strings in `section.key=value` format.

A git_config_entry now knows the type of the origin for the entry
("file", "memory", etc) and the path details (for files, the path on
disk). This is propagated through snapshots.

The opaque `payload` on an entry is unnecessary and distracting; config
entries should follow the patterns of other objects and use space
elsewhere in the structure with a "base" config entry struct embedded.

Don't set entry data when we "get" an entry from the collection, add the
data to the entry before it's put into the collection. This keeps the
entry creation logic in a single place.