-- loader.lua -- debugger-assisted COFF loader acceptance harness.
--
-- Boots the firmware with VT1200_SKIP_LEVEL1=1 (the documented divergence) to
-- the OS, then at frame LOADER_AT pokes:
--   * the loader payload at bit 0x01880000 (raw dwt/loader/build/loader.bin)
--   * a GSPLNK COFF image at LOADER_BUF (default bit 0x01900000)
--   * the loader descriptor at 0x01882C00
-- and sets PC = 0x01880000.  It does not use the network, the rdebug service
-- or any firmware transport: this is the debugger-assisted milestone.
--
-- The loader itself copies the COFF sections to their linked bit addresses and
-- calls create_process(entry, "LOADER", 0x6000, 1, 0).  This script only pokes
-- the input and reads the result; it never writes the app's code or markers.
--
-- Env:
--   LOADER_BIN   loader payload (default dwt/loader/build/loader.bin)
--   LOADER_COFF  app COFF (default dwt/loader/build/marker.coff)
--   LOADER_BUF   COFF buffer bit address (default 0x01900000)
--   LOADER_AT    injection frame (default 2500)
--   LOADER_END   inspection/exit frame (default 2700)
--   LOADER_OUT   evidence directory (default dwt/loader/evidence)
--   LOADER_SNAP  1 = write a PNG at LOADER_END (default 0)
--   LOADER_VERBOSE 1 = print the result block every 25 frames

local function hex(v, w) return string.format("%0" .. (w or 8) .. "X", v) end

local machine = manager.machine
local cpu = machine.devices[':maincpu']
local dbg = machine.debugger
local prog = cpu.spaces['program']

if not dbg then
	print("LOADER: debugger not enabled; pass -debug")
	machine:exit()
	return
end

local AT      = tonumber(os.getenv("LOADER_AT") or "2500")
local ENDF    = tonumber(os.getenv("LOADER_END") or "2700")
local BIN     = os.getenv("LOADER_BIN") or "dwt/loader/build/loader.bin"
local COFF    = os.getenv("LOADER_COFF") or "dwt/loader/build/marker.coff"
local BUF     = tonumber(os.getenv("LOADER_BUF") or "0x01900000")
local OUT     = os.getenv("LOADER_OUT") or "dwt/loader/evidence"
local SNAP    = os.getenv("LOADER_SNAP") == "1"
local MODE    = tonumber(os.getenv("LOADER_MODE") or "0")
local A8DESC  = os.getenv("LOADER_A8_DESC") == "1"
local VERBOSE = os.getenv("LOADER_VERBOSE") == "1"

local LOADER_BASE = 0x01880000
local DESC        = 0x01882C00
local RESULT      = 0x01882D00
local RETURN_STUB = 0x01883100
local RETURN_SP   = 0x01883110

local function rd(p) return io.open(p, "rb") end
local function slurp(p)
	local f, err = rd(p)
	if not f then error("cannot open " .. p .. ": " .. tostring(err)) end
	local s = f:read("*a")
	f:close()
	return s
end

local function u16(s, o)
	return s:byte(o + 1) + s:byte(o + 2) * 256
end

local function u32(s, o)
	return s:byte(o + 1) + s:byte(o + 2) * 256
		+ s:byte(o + 3) * 65536 + s:byte(o + 4) * 16777216
end

local function parse_coff(d)
	local c = { data = d }
	c.magic = u16(d, 0)
	c.nscns = u16(d, 2)
	c.opthdr = u16(d, 16)
	c.sections = {}
	if c.opthdr > 0 then
		c.optmagic = u16(d, 20)
		c.entry = u32(d, 20 + 16)
		c.textstart = u32(d, 20 + 20)
		c.datastart = u32(d, 20 + 24)
	end
	local base = 20 + c.opthdr
	for i = 0, c.nscns - 1 do
		local o = base + i * 40
		local name = d:sub(o + 1, o + 8):gsub("%z", "")
		c.sections[#c.sections + 1] = {
			name = name,
			paddr = u32(d, o + 8),
			size = u32(d, o + 16),	-- bits
			scnptr = u32(d, o + 20),
			flags = u32(d, o + 36),
		}
	end
	return c
end

local function poke_bytes(bitaddr, data)
	local n = math.floor((#data + 1) / 2)
	for i = 0, n - 1 do
		local lo = data:byte(i * 2 + 1) or 0
		local hi = data:byte(i * 2 + 2) or 0
		prog:write_u16(bitaddr + i * 16, lo + hi * 256)
	end
	return n
end

local function verify_bytes(bitaddr, data)
	local n = math.floor((#data + 1) / 2)
	local bad = 0
	for i = 0, n - 1 do
		local lo = data:byte(i * 2 + 1) or 0
		local hi = data:byte(i * 2 + 2) or 0
		if prog:read_u16(bitaddr + i * 16) ~= lo + hi * 256 then
			bad = bad + 1
		end
	end
	return n, bad
end

local function w32(a, v) prog:write_u32(a, v) end
local function r32(a)
	local ok, v = pcall(function() return prog:read_u32(a) end)
	if ok then return v end
	return 0xDEADBEEF
end

local loader = slurp(BIN)
local coff = slurp(COFF)
local app = parse_coff(coff)

print(string.format("LOADER: payload %s (%d B) -> bit %s", BIN, #loader, hex(LOADER_BASE)))
print(string.format("LOADER: COFF %s (%d B) -> bit %s", COFF, #coff, hex(BUF)))
print(string.format("LOADER: file magic=%04X nscns=%d opthdr=%d optmagic=%s entry=%s textstart=%s",
	app.magic, app.nscns, app.opthdr,
	app.optmagic and string.format("%04X", app.optmagic) or "none",
	hex(app.entry or 0), hex(app.textstart or 0)))
for _, s in ipairs(app.sections) do
	print(string.format("LOADER:   sec %-8s paddr=%s size=%d bits (%d B) scnptr=%#x flags=%#x",
		s.name, hex(s.paddr), s.size, math.floor(s.size / 8), s.scnptr, s.flags))
end

local TRACE = os.getenv("LOADER_TRACE") == "1"

local frames = 0
local injected = false
local done = false
local last_count = -1

local function status_name(v)
	local t = {
		[0] = "OK",
		[1] = "bad descriptor",
		[2] = "truncated COFF / section headers",
		[3] = "bad COFF magic",
		[4] = "section size not whole words",
		[5] = "target outside RAM",
		[6] = "target overlaps loader page or COFF buffer",
		[7] = "relocation records present (unsupported)",
		[8] = "target not in a free-list block",
		[9] = "no entry point",
	}
	return t[v] or ("error " .. tostring(v))
end

local function result_dump()
	local st = r32(RESULT + 0x000)
	print(string.format(
		"LOADER: result status=%d (%s) entry=%s text=%s/%d bits data=%s/%d bits bss=%s/%d bits relocs=%d pcb=%s nscns=%d len=%d",
		st, status_name(st), hex(r32(RESULT + 0x020)),
		hex(r32(RESULT + 0x040)), r32(RESULT + 0x060),
		hex(r32(RESULT + 0x080)), r32(RESULT + 0x0A0),
		hex(r32(RESULT + 0x0C0)), r32(RESULT + 0x0E0),
		r32(RESULT + 0x100), hex(r32(RESULT + 0x120)),
		r32(RESULT + 0x140), r32(RESULT + 0x160)))
end

local function inject()
	-- 1. loader itself
	local n, bad = 0, 0
	poke_bytes(LOADER_BASE, loader)
	n, bad = verify_bytes(LOADER_BASE, loader)
	print(string.format("LOADER: loader poked %d words, readback %d bad at %s",
		n, bad, hex(LOADER_BASE)))

	-- 2. COFF image
	poke_bytes(BUF, coff)
	n, bad = verify_bytes(BUF, coff)
	print(string.format("LOADER: COFF poked %d words, readback %d bad at %s",
		n, bad, hex(BUF)))

	-- 3. pre-fill every .bss section with A5A5, so a loaded zero is meaningful
	for _, s in ipairs(app.sections) do
		if s.flags & 0x80 ~= 0 then
			for i = 0, math.floor(s.size / 16) - 1 do
				prog:write_u16(s.paddr + i * 16, 0xA5A5)
			end
			print(string.format("LOADER: pre-filled .bss %s..%s with A5A5",
				hex(s.paddr), hex(s.paddr + s.size)))
		end
	end

	-- 4. descriptor: magic "LD" "R1", buf, len, mode=0 (spin)
	w32(DESC + 0x00, 0)
	prog:write_u16(DESC + 0x00, 0x4C44)
	prog:write_u16(DESC + 0x10, 0x5231)
	w32(DESC + 0x20, BUF)
	w32(DESC + 0x40, #coff)
	w32(DESC + 0x60, MODE)
	print(string.format("LOADER: descriptor @%s magic=%04X/%04X buf=%s len=%d mode=%d",
		hex(DESC), prog:read_u16(DESC + 0x00), prog:read_u16(DESC + 0x10),
		hex(r32(DESC + 0x20)), r32(DESC + 0x40), r32(DESC + 0x60)))

	-- 5. return stub.  mode 0 ignores it (the loader jumps to ORIG_PC
	-- itself); mode 1 returns here, and the stub resumes the interrupted
	-- PC so the caller yields and the scheduler can run the child.
	local orig_pc = cpu.state['PC'].value
	if MODE == 1 then
		prog:write_u16(RETURN_STUB, 0xC080)		-- jauc <orig_pc>
		prog:write_u16(RETURN_STUB + 0x10, orig_pc & 0xFFFF)
		prog:write_u16(RETURN_STUB + 0x20, math.floor(orig_pc / 0x10000) & 0xFFFF)
	else
		prog:write_u16(RETURN_STUB, 0xC0FF)		-- jruc self
	end

	-- 6. enter the loader.  A8=0 selects the fixed descriptor; SP points at
	-- the return slot so mode=1 would return to the spin stub.
	-- Leave SP alone for mode 0: the loader pushes onto the current
	-- process stack, then restores it and resumes at ORIG_PC.  (mode 1
	-- would use the return stub.)
	w32(0x01882A20, orig_pc)  -- LD_ORIG_PC
	print(string.format("LOADER: will resume at %s after create_process", hex(orig_pc)))
	cpu.state['A8'].value = A8DESC and DESC or 0
	if MODE == 1 then
		-- Simulate a CALLA from the current process: push the return
		-- address on the *firmware* stack (a real transport would do this).
		local sp = cpu.state['SP'].value - 0x20
		w32(sp, RETURN_STUB)
		cpu.state['SP'].value = sp
	end
	cpu.state['PC'].value = LOADER_BASE
	injected = true
	print(string.format("LOADER: frame %d: entered loader at %s (caller SP=%s)",
		frames, hex(LOADER_BASE), hex(cpu.state['SP'].value)))
end

local function inspect()
	result_dump()

	-- Verify the placement from RAM: .text/.data must equal the file bytes.
	for _, s in ipairs(app.sections) do
		if s.scnptr ~= 0 and s.size > 0 then
			local nb = math.floor(s.size / 8)
			local bytes = coff:sub(s.scnptr + 1, s.scnptr + nb)
			local _, bad = verify_bytes(s.paddr, bytes)
			print(string.format("LOADER: placed %s at %s: %d bytes, %d differing",
				s.name, hex(s.paddr), nb, bad))
		end
	end

	local base = COFF:match("([^/]+)$") or COFF
	if base:find("marker") then
		print(string.format("LOADER: marker app: start=%s data=%s data2=%s bss=%s count=%d",
			hex(r32(0x018E0000)), hex(r32(0x018E0020)), hex(r32(0x018E0040)),
			hex(r32(0x018E0060)), r32(0x018E0080)))
	elseif base:find("xhello") then
		print(string.format("LOADER: xhello: stage=%d strlen=%d display=%s root=%s window=%s sync=%s",
			r32(0x01890140), r32(0x01890160), hex(r32(0x01890100)),
			hex(r32(0x01890110)), hex(r32(0x01890120)), hex(r32(0x01890130))))
	elseif base:find("xtext") then
		print(string.format("LOADER: xtext: stage=%d strlen=%d display=%s font=%s window=%s gc=%s draw1=%s draw2=%s",
			r32(0x01842000), r32(0x01842160), hex(r32(0x01842020)),
			hex(r32(0x01842040)), hex(r32(0x01842060)), hex(r32(0x01842080)),
			hex(r32(0x01842100)), hex(r32(0x01842120))))
	end
	print(string.format("LOADER: PC at inspection = %s", hex(cpu.state['PC'].value)))
end

emu.register_frame_done(function()
	frames = frames + 1
	if frames % 50 == 0 then
		print(string.format("XTEXT f=%d pc=%s st=%d str=%d disp=%s font=%s win=%s gc=%s d1=%s d2=%s sp0=%s a140=%s wpc=%s wa=%s wd=%s",
			frames, hex(cpu.state['PC'].value), r32(0x01842000), r32(0x01842160),
			hex(r32(0x01842020)), hex(r32(0x01842040)), hex(r32(0x01842060)),
			hex(r32(0x01842080)), hex(r32(0x01842100)), hex(r32(0x01842120)),
			hex(r32(0x018420A0)), hex(r32(0x018420C0)),
			hex(r32(0x01896000)), hex(r32(0x01896020)), hex(r32(0x01896040))))
	end
	if injected and frames >= AT and frames <= AT + 8 then
		print(string.format("XTSP f=%d pc=%s sp=%s a14=%s sp0=%s a140=%s st=%d",
			frames, hex(cpu.state['PC'].value), hex(cpu.state['SP'].value),
			hex(cpu.state['A14'].value), hex(r32(0x01894500)), hex(r32(0x01894520)), r32(0x01895000)))
	end
	if frames == AT and not injected then
		inject()
		if TRACE then dbg:command("trace dwt/loader/evidence/real-unit-xtext/xtrace.tr") end
	end
	if injected and TRACE and frames == AT + 80 then
		dbg:command("trace off")
		print("LOADER: trace written to dwt/loader/evidence/real-unit-xtext/xtrace.tr")
	end
	if injected and not done then
		if TRACE and frames <= AT + 40 then
			print(string.format("LOADER: trace f=%d PC=%s SP=%s A14=%s status=%s entry=%s",
				frames, hex(cpu.state['PC'].value), hex(cpu.state['SP'].value),
				hex(cpu.state['A14'].value), hex(r32(RESULT + 0x000)),
				hex(r32(RESULT + 0x020))))
		end
		local st = r32(RESULT + 0x000)
		-- status 0 means OK; nonzero is final too once parsing has begun
		if st ~= 0xFFFFFFFF and not done then
			-- The loader writes 0 on success.  A nonzero status is final
			-- only after it has been written once (it is 0 from power-on,
			-- so require the loader to have run: PC no longer at entry or
			-- the app counter moved).
		end
		if VERBOSE and frames % 25 == 0 then
			result_dump()
		end
		if base_contains_marker then
			local c = r32(0x018E0080)
			if c ~= last_count then
				if last_count ~= -1 then
					print(string.format("LOADER: marker counter %d -> %d (child running)",
						last_count, c))
				end
				last_count = c
			end
		end
	end
	if frames >= ENDF then
		if injected then
			done = true
			inspect()
			if SNAP then
				local screen = nil
				for _, s in pairs(machine.screens) do screen = s break end
				if screen then
					local out = OUT .. "/loader_frame" .. frames .. ".png"
					local ok, err = pcall(function() return screen:snapshot(out) end)
					print(string.format("LOADER: snapshot %s ok=%s %s",
						out, tostring(ok), tostring(err or "")))
				end
			end
		end
		machine:exit()
	end
end, "vt1200-loader")

-- (Lua has no forward use of a name defined later; set a small flag here.)
base_contains_marker = (COFF:match("([^/]+)$") or ""):find("marker") ~= nil

-- (no debugger breakpoints; the app is observed through its marker cells.)

dbg.visible_cpu = cpu
dbg.execution_state = 'run'