-- A cgit auth filter that puts chosen repositories behind a login form and a
-- signed session cookie. cgit consults it on every request once cgitrc names
-- it with auth-filter=lua:/path/to/auth-file.lua, and it answers the
-- authenticate-cookie, authenticate-post and body actions the filter API
-- defines. This variant keeps the accounts, the groups and the per-repository
-- access lists in files on disk, which suits a user set that is large or
-- maintained by something else. The companion auth-inline.lua behaves
-- identically but carries the same lists inside the script.

-- The script runs on Lua 5.1, 5.2, 5.3, 5.4 and LuaJIT, and the runtime has to
-- be the same Lua that cgit was built against. Lua 5.5 will not do, because
-- luaossl has no 5.5 build.
--
-- Serve cgit over HTTPS and terminate TLS in the web server in front of it.
-- The session cookie is marked Secure by default, so a browser only sends it
-- back over HTTPS, and on an instance served over plain HTTP with no TLS
-- anywhere the cookie never comes back and login appears to loop until
-- cookie_insecure below is set.
--
-- Two libraries are needed. luaossl provides openssl.rand and openssl.hmac and
-- lives at <https://github.com/wahern/luaossl>, and luaposix provides
-- posix.sys.stat and posix.unistd and lives at
-- <https://github.com/luaposix/luaposix>. The reliable cross-platform way to
-- install them is LuaRocks matched to your Lua version, and luaossl also needs
-- the OpenSSL development headers present.
--
--     # Debian and Ubuntu
--     sudo apt install luarocks libssl-dev
--     sudo luarocks --lua-version 5.1 install luaossl
--     sudo luarocks --lua-version 5.1 install luaposix
--
--     # Fedora
--     sudo dnf install luarocks openssl-devel
--     sudo luarocks --lua-version 5.1 install luaossl luaposix
--
--     # Alpine
--     sudo apk add luarocks openssl-dev
--     sudo luarocks-5.1 install luaossl luaposix
--
--     # macOS with Homebrew
--     brew install luarocks openssl
--     luarocks install luaossl OPENSSL_DIR="$(brew --prefix openssl)"
--     luarocks install luaposix
--
-- Some distributions package both as well, for example lua-luaossl and
-- lua-posix on Debian, and such a package has to be built for the same Lua
-- version as cgit.
--
-- The cookie carries only a user name and there is no server-side session
-- store, so deleting an account does not revoke a cookie already issued until
-- it expires, and instances that share a secret file accept each other's
-- cookies. The login form carries no CSRF token. Both are acceptable for
-- gating read access to a git browser, so weigh them before guarding anything
-- more sensitive.

local sysstat = require("posix.sys.stat")
local unistd = require("posix.unistd")
local rand = require("openssl.rand")
local hmac = require("openssl.hmac")

-- The values that follow are the configuration and are meant to be edited.
-- Nothing below them needs changing for ordinary use.

-- Accounts live one per line as username:hash. Generate a hash with
--     mkpasswd -m sha-512 -R 300000
-- This file should not be world-readable.
local users_filename = "/etc/cgit-auth/users"

-- Group membership lives one per line as groupname:user1,user2,user3 and so
-- on.
local groups_filename = "/etc/cgit-auth/groups"

-- Per-repository access lives one per line as reponame:group1,group2 and so
-- on. A repository named here is protected and one that is not named is
-- public. The repository name has to match exactly, while group and user names
-- match whatever their case.
local repos_filename = "/etc/cgit-auth/repos"

-- Where the cookie-signing secret is stored, created on first use. It must be
-- persistent and writable by cgit, and it is worth keeping outside the cache
-- root, because pruning the cache would delete a secret kept inside it and
-- invalidate every live session. This file should not be world-readable.
local secret_filename = "/var/lib/cgit/auth-secret"

-- How long a login stays valid, in seconds. The default is one week.
local session_seconds = 7 * 24 * 60 * 60

local cookie_name = "cgitauth"

-- "/" covers the whole host. Set this to the cgit root to scope the cookie
-- more tightly.
local cookie_path = "/"

-- Leave this false so the cookie is marked Secure and only travels over HTTPS.
-- Set it true only if cgit is served over plain HTTP with no TLS anywhere.
local cookie_insecure = false

-- A throwaway hash of the documented shape, used only to spend the same work
-- on a missing account as on a present one, so a failed login does not reveal
-- by timing whether the user name exists.
local dummy_hash = "$6$rounds=300000$0000000000000000$"

-- One request reaches this script as an open, a write and a close, so what the
-- open decodes is kept here for the calls that follow.
local action, http, cgit, post

-- The two lookups below, account_hash and repo_userset, are the only part of
-- this script that differs from auth-inline.lua. Replacing them is all it
-- takes to keep accounts somewhere else.

local function trim(s)
	return (string.gsub(s, "^%s*(.-)%s*$", "%1"))
end

local function add_names(list, set)
	for name in string.gmatch(list, "([^,]+)") do
		set[trim(name):lower()] = true
	end
end

-- A missing or unreadable users file is not fatal, and neither is a line that
-- does not parse, so a broken file turns every login down rather than failing
-- the request outright.
--
-- The hash is trimmed as well as the name because reading by line strips the
-- newline but not a carriage return, so a users file saved with CRLF endings
-- would otherwise hand crypt a hash with a trailing \r and fail every login
-- with nothing in the log to say why.
function account_hash(user)
	if user == nil then
		return nil
	end
	local wanted = user:lower()
	local users_file = io.open(users_filename, "r")
	if users_file == nil then
		return nil
	end
	for line in users_file:lines() do
		local name, hash = string.match(line, "(.-):(.+)")
		if name ~= nil and trim(name):lower() == wanted then
			users_file:close()
			return trim(hash)
		end
	end
	users_file:close()
	return nil
end

-- The users allowed into a repository come back keyed by lowercased name, and
-- a repository the repos file does not name comes back as nil. A protected
-- repository whose groups resolve to nobody comes back as an empty table
-- instead, so it denies everyone rather than falling through to public.
function repo_userset(repo)
	if repo == nil then
		return nil
	end
	local groups = nil
	local repos_file = io.open(repos_filename, "r")
	if repos_file ~= nil then
		for line in repos_file:lines() do
			local name, list = string.match(line, "(.-):(.+)")
			if name ~= nil and trim(name) == repo then
				groups = {}
				add_names(list, groups)
				break
			end
		end
		repos_file:close()
	end
	if groups == nil then
		return nil
	end
	local users = {}
	local groups_file = io.open(groups_filename, "r")
	if groups_file ~= nil then
		for line in groups_file:lines() do
			local name, list = string.match(line, "(.-):(.+)")
			if name ~= nil and groups[trim(name):lower()] then
				add_names(list, users)
			end
		end
		groups_file:close()
	end
	return users
end

-- The URL helpers below are adapted from keplerproject/wsapi.

function url_decode(str)
	if not str then
		return ""
	end
	str = string.gsub(str, "+", " ")
	str = string.gsub(str, "%%(%x%x)", function(hex)
		return string.char(tonumber(hex, 16))
	end)
	str = string.gsub(str, "\r\n", "\n")
	return str
end

function url_encode(str)
	if not str then
		return ""
	end
	str = string.gsub(str, "\n", "\r\n")
	str = string.gsub(str, "([^%w ])", function(char)
		return string.format("%%%02X", string.byte(char))
	end)
	str = string.gsub(str, " ", "+")
	return str
end

-- Parse an application/x-www-form-urlencoded body. A value may itself contain
-- '=', for example a base64 password, so the value runs to the next '&'.
function parse_query(query)
	local params = {}
	for key, value in string.gmatch(query or "", "([^&=]+)=([^&]*)") do
		params[url_decode(key)] = url_decode(value)
	end
	return params
end

local function pattern_escape(s)
	return (string.gsub(s, "([%^%$%(%)%%%.%[%]%*%+%-%?])", "%%%1"))
end

-- The stored token was already URL encoded by secure_value, so it comes back
-- verbatim and the write path in set_cookie stays symmetric with this read
-- path. Decoding it here would break the signature check for any value
-- carrying a percent escape.
--
-- The name is escaped because it lands in a pattern. A cookie_name holding a
-- magic character, say "cgit-auth", would otherwise read as a pattern and stop
-- matching its own cookie while matching names nobody configured.
function get_cookie(cookies, name)
	cookies = string.gsub(";" .. (cookies or "") .. ";", "%s*;%s*", ";")
	return string.match(cookies, ";" .. pattern_escape(name) .. "=(.-);")
end

function tohex(bytes)
	local hex = ""
	for i = 1, #bytes do
		hex = hex .. string.format("%.2x", string.byte(bytes, i))
	end
	return hex
end

local secret = nil

-- Load the cookie-signing secret, creating it on first use. Failures raise,
-- which cgit turns into a request error, so a broken secret denies rather than
-- signs with nothing.
function get_secret()
	if secret ~= nil then
		return secret
	end
	local secret_file = io.open(secret_filename, "r")
	if secret_file == nil then
		-- The secret is written under a tightened mask so it is not
		-- created readable by anyone but the user cgit runs as, and
		-- the old mask goes back on every way out.
		local old_umask = sysstat.umask(63)
		local temporary_filename = secret_filename .. ".tmp." ..
			tohex(rand.bytes(16))
		local temporary_file = io.open(temporary_filename, "w")
		if temporary_file == nil then
			sysstat.umask(old_umask)
			error("cgit auth: cannot create secret file " ..
				secret_filename)
		end
		local wrote = temporary_file:write(tohex(rand.bytes(32)))
		local closed = temporary_file:close()
		if not wrote or not closed then
			os.remove(temporary_filename)
			sysstat.umask(old_umask)
			error("cgit auth: failed writing secret file " ..
				secret_filename)
		end
		-- The link is meant to fail when another worker won the race,
		-- which leaves that worker's secret in place rather than
		-- replacing it and invalidating the sessions it just signed.
		unistd.link(temporary_filename, secret_filename)
		unistd.unlink(temporary_filename)
		sysstat.umask(old_umask)
		secret_file = io.open(secret_filename, "r")
	end
	if secret_file == nil then
		error("cgit auth: cannot read secret file " .. secret_filename)
	end
	secret = secret_file:read("*l")
	secret_file:close()
	if secret == nil or secret:len() ~= 64 then
		secret = nil
		error("cgit auth: secret file " .. secret_filename ..
			" is malformed, expected 64 hex characters")
	end
	return secret
end

-- A redirect target is unsafe if a browser would read it as another origin.
-- The only such form cgit can be tricked into signing is a scheme-relative
-- "//host" or "/\host". Everything else stays on this host.
function is_safe_redirect(url)
	if type(url) ~= "string" then
		return false
	end
	local head = url:sub(1, 2)
	if head == "//" or head == "/\\" then
		return false
	end
	return true
end

-- Return the value carried by a signed cookie, or nil if it does not verify.
function validate_value(expected_field, cookie)
	local i = 0
	local value = ""
	local field = ""
	local expiration = 0
	local salt = ""
	local signature = ""

	if cookie == nil or cookie:len() < 3 or cookie:sub(1, 1) == "|" then
		return nil
	end

	for component in string.gmatch(cookie, "[^|]+") do
		if i == 0 then
			field = component
		elseif i == 1 then
			value = component
		elseif i == 2 then
			-- The expiration must be a plain integer, since
			-- tonumber and tostring of "1e9" or "100.0" differ
			-- across Lua versions and the signed bytes have to
			-- come back byte for byte.
			if not string.match(component, "^%d+$") then
				return nil
			end
			expiration = tonumber(component)
		elseif i == 3 then
			salt = component
		elseif i == 4 then
			signature = component
		else
			break
		end
		i = i + 1
	end

	if signature == nil or signature:len() == 0 then
		return nil
	end

	local payload = field .. "|" .. value .. "|" ..
		tostring(expiration) .. "|" .. salt
	local expected_signature =
		tohex(hmac.new(get_secret(), "sha256"):final(payload))
	if not constant_equals(signature, expected_signature) then
		return nil
	end

	-- An expiration of 0 never expires and is used for the redirect token.
	if expiration ~= 0 and expiration <= os.time() then
		return nil
	end

	if url_decode(field) ~= expected_field then
		return nil
	end

	local decoded = url_decode(value)
	-- Reject values carrying control characters so a signed value cannot
	-- smuggle CR or LF into a response header.
	if decoded:find("%c") then
		return nil
	end
	return decoded
end

-- The layout built here is what validate_value takes apart again, so the two
-- have to move together.
function secure_value(field, value, expiration)
	if value == nil or value:len() <= 0 then
		return ""
	end

	local salt = tohex(rand.bytes(16))
	value = url_encode(value)
	field = url_encode(field)
	local payload = field .. "|" .. value .. "|" ..
		tostring(expiration) .. "|" .. salt
	local signature = tohex(hmac.new(get_secret(), "sha256"):final(payload))
	return payload .. "|" .. signature
end

-- A control character in a header value would let that value split the
-- response, so it is dropped rather than escaped.
function strip_controls(s)
	return (string.gsub(s or "", "%c", ""))
end

-- Compare two strings in time that does not depend on how many leading bytes
-- match, so a mismatch position is not revealed by timing.
function constant_equals(a, b)
	if type(a) ~= "string" or type(b) ~= "string" or #a ~= #b then
		return false
	end
	local diff = 0
	for i = 1, #a do
		local delta = a:byte(i) - b:byte(i)
		diff = diff + delta * delta
	end
	return diff == 0
end

-- An empty value is how a login is cleared, since Max-Age=0 tells the browser
-- to drop the cookie it already holds.
function set_cookie(cookie, value)
	local attributes = "; HttpOnly; SameSite=Lax; Path=" .. cookie_path
	if not cookie_insecure then
		attributes = attributes .. "; Secure"
	end
	if value == "" then
		attributes = attributes .. "; Max-Age=0"
	elseif session_seconds > 0 then
		attributes = attributes ..
			"; Max-Age=" .. tostring(session_seconds)
	end
	html("Set-Cookie: " .. cookie .. "=" ..
		strip_controls(value) .. attributes .. "\n")
end

function redirect_to(url)
	html("Status: 302 Redirect\n")
	html("Cache-Control: no-cache, no-store\n")
	html("Location: " .. strip_controls(url) .. "\n")
end

function not_found()
	html("Status: 404 Not Found\n")
	html("Cache-Control: no-cache, no-store\n\n")
end

-- The three actions cgit can ask for follow, and they are the same in both
-- variants, so a change to one belongs in the other.

-- The redirect goes out before the password is checked, so a wrong password
-- and a right one answer with the same status and location and differ only in
-- the cookie.
function authenticate_post()
	local redirect = validate_value("redirect", post["redirect"])

	if redirect == nil or not is_safe_redirect(redirect) then
		not_found()
		return 0
	end

	redirect_to(redirect)

	local username = post["username"]
	local password = post["password"]
	local ok = false
	if username ~= nil and password ~= nil then
		local hash = account_hash(username)
		if hash == nil then
			-- Spend the work anyway, see dummy_hash.
			unistd.crypt(password, dummy_hash)
		elseif constant_equals(hash, unistd.crypt(password, hash)) then
			ok = true
		end
	end

	if ok then
		set_cookie(cookie_name, secure_value("username", username,
			os.time() + session_seconds))
	else
		set_cookie(cookie_name, "")
	end

	html("\n")
	return 0
end

-- cgit reads the answer, where 1 lets the request through and 0 sends it to
-- the login form.
function authenticate_cookie()
	local accepted_users = repo_userset(cgit["repo"])
	if accepted_users == nil then
		-- A repository nothing lists is public.
		return 1
	end

	local username = validate_value("username",
		get_cookie(http["cookie"], cookie_name))
	if username == nil or not accepted_users[username:lower()] then
		return 0
	end
	return 1
end

-- cgit calls this to fill the page body once the cookie has been turned down.
-- The form carries a signed redirect token, so the browser lands back on the
-- page that was asked for.
function body()
	local target = cgit["url"]
	if not is_safe_redirect(target) then
		target = cgit["login"]
	end

	html("<h2>Authentication Required</h2>")
	html("<form method='post' action='")
	html_attr(cgit["login"])
	html("'>")
	html("<input type='hidden' name='redirect' value='")
	html_attr(secure_value("redirect", target, 0))
	html("'>")
	html("<table>")
	html("<tr><td><label for='username'>Username:</label></td><td><input id='username' name='username' autocomplete='username' autofocus></td></tr>")
	html("<tr><td><label for='password'>Password:</label></td><td><input id='password' name='password' type='password' autocomplete='current-password'></td></tr>")
	html("<tr><td colspan='2'><input value='Login' type='submit'></td></tr>")
	html("</table></form>")

	return 0
end

-- cgit calls filter_open with the action name followed by the request fields
-- in a fixed order, so they are unpacked here into the tables the functions
-- above read. Only a post reaches filter_write, carrying the form body, and
-- filter_close is where the action finally runs and answers cgit.

local actions = {}
actions["authenticate-post"] = authenticate_post
actions["authenticate-cookie"] = authenticate_cookie
actions["body"] = body

function filter_open(...)
	action = actions[select(1, ...)]

	post = {}

	http = {}
	http["cookie"] = select(2, ...)
	http["method"] = select(3, ...)
	http["query"] = select(4, ...)
	http["referer"] = select(5, ...)
	http["path"] = select(6, ...)
	http["host"] = select(7, ...)
	http["https"] = select(8, ...)

	cgit = {}
	cgit["repo"] = select(9, ...)
	cgit["page"] = select(10, ...)
	cgit["url"] = select(11, ...)
	cgit["login"] = select(12, ...)
end

function filter_close()
	if action == nil then
		-- An unknown action denies rather than raising.
		return 0
	end
	return action()
end

function filter_write(str)
	post = parse_query(str)
end