//! pardes, as ESP32-P4 firmware.
//!
//! There is no operating system under this. `_start` is the reset entry the second-stage bootloader
//! jumps to, and this file is the entire platform: a heap, a millisecond clock, and UART0.
//!
//! ## Where the editor is
//!
//! Not in this package. `../02-pardes-code` compiles its core for riscv32-freestanding and emits
//! ONE object exporting the six C functions declared below; `-Dpardes` links it. The seam is a file
//! rather than a package dependency for a reason recorded at length in `build.zig`: declaring the
//! editor as a `build.zig.zon` path dependency nested its ~30-package graph under this one and
//! broke every build in this repo, including the ones that have nothing to do with it.
//!
//! The seam is deliberately **bytes in, bytes out**. Everything that needs to know what a cell is -
//! vaxis, the ANSI encoder, the input parser, the capability handshake - lives on the far side,
//! next to the vaxis it is built against. What crosses is a byte stream in each direction, which is
//! exactly what a serial line is, so this file has no opinion about terminals at all.
//!
//! ## Where the memory is
//!
//! Measured on this die by `examples/memprobe.zig`, not read off a datasheet:
//!
//!     0x4FF02000..0x4FF3F000   244 KiB  .data/.bss/.stack live at the bottom of this
//!     0x4FF3F000..0x4FF40000     4 KiB  mask ROM .data/.bss - untouchable, ets_printf needs it
//!     0x4FF40000..0x4FFC0000   512 KiB  handed to the editor as its entire heap
//!
//! The 512 KiB arrives as `__heap_start`/`__heap_end` from the generated linker script, so those
//! addresses are written down in exactly one place. The editor owns that span outright: it is
//! passed in at init and this file never allocates from it.
//!
//! PSRAM is not used. The board has 32 MB fitted and it would make all of this comfortable, but
//! ESP-IDF's own ESP32-P4 implementation runs past a thousand lines - MPLL, MSPI clocking, pin
//! drive and DQS, CS timing, mode registers, a connectivity check, and an entire timing-calibration
//! subsystem - and the mask ROM offers only MMU mapping, no device init. Touching it untrained
//! faults and hangs the core, which `examples/memprobe.zig` demonstrates on purpose.

const std = @import("std");
const soc = @import("soc");
const config = @import("config");

/// `-Dprof`: time the two phases of a keystroke on the board and print the cycle counts. A
/// diagnostic, not a feature - see the loop.
const prof = config.prof;
const hal = @import("hal");
const heapmod = @import("heap");
const uart = @import("uart.zig");

// ------------------------------------------------------------------------------------- the ABI
// Seven functions, all `callconv(.c)`, all implemented in the linked object. This is the complete
// interface between this board and the editor, and it is deliberately bytes-and-memory only: the
// editor never learns what a UART is, and this file never learns what a cell is.

/// How the editor emits bytes. Called with finished runs of ANSI, many times per frame.
const WriteFn = *const fn (ctx: ?*anyopaque, ptr: [*]const u8, len: usize) callconv(.c) void;

/// This board's allocator, handed across as plain function pointers. `log2_align` is a log2 value,
/// which is exactly how `std.mem.Alignment` represents itself, so neither side needs a conversion
/// table.
///
/// The memory belongs to THIS side: only the firmware knows that the heap is the 384 KiB at
/// 0x4FF40000, that the 128 KiB above it is L2 cache, and that PSRAM is untrained. The editor gets
/// an allocator, not an address range.
const Allocator = extern struct {
    ctx: ?*anyopaque,
    alloc: *const fn (ctx: ?*anyopaque, len: usize, log2_align: u8) callconv(.c) ?[*]u8,
    resize: *const fn (ctx: ?*anyopaque, ptr: [*]u8, len: usize, log2_align: u8, new_len: usize) callconv(.c) bool,
    free: *const fn (ctx: ?*anyopaque, ptr: [*]u8, len: usize, log2_align: u8) callconv(.c) void,
};

/// The one number both sides must agree on. Linkers do not type-check C symbols, so a signature
/// that drifts on one side of this seam links cleanly and then corrupts the stack; checking this
/// before calling anything else turns that into a refusal to boot.
const abi_version: u32 = 1;
extern fn pardes_p4_abi_version() callconv(.c) u32;

/// Hand over the allocator and the output sink, and state the initial window size. Returns 0, or a
/// small non-zero code this file can only report.
extern fn pardes_p4_init(
    alloc: *const Allocator,
    write: WriteFn,
    ctx: ?*anyopaque,
    cols: u16,
    rows: u16,
) callconv(.c) u32;

/// Raw bytes off the wire: keystrokes, capability-query replies, and the host bridge's in-band
/// resize reports. The editor parses all three; this file distinguishes none of them.
extern fn pardes_p4_input(ptr: [*]const u8, len: usize) callconv(.c) void;

/// Advance time. Separate from `input` because animations and timeouts must progress on a wire
/// where nothing is arriving.
extern fn pardes_p4_tick(now_ms: u64) callconv(.c) void;

/// Emit one frame through the write callback. Returns 0 or an error code.
extern fn pardes_p4_render() callconv(.c) u32;

/// Is there anything to draw - a dirty surface or a running animation? Asked every iteration so a
/// quiet editor costs no bytes on a 115200-baud link.
extern fn pardes_p4_wants_frame() callconv(.c) bool;

/// Has the user asked to leave? There is nowhere to go, so this only stops the loop.
extern fn pardes_p4_quit() callconv(.c) bool;

/// The last frame's three stages in CPU cycles: the copy of pardes's Surface into vaxis's grid,
/// vaxis's own diff-and-emit, and the push into the UART. Only meaningful under `-Dprof`; the
/// editor object always exports it, and it costs two CSR reads per stage.
extern fn pardes_p4_frame_prof(copy: *u64, render: *u64, flush: *u64) callconv(.c) void;

// ------------------------------------------------------------------------------------ the sink

/// The write callback handed to `pardes_p4_init`. No context is needed - there is one UART.
fn writeOut(_: ?*anyopaque, ptr: [*]const u8, len: usize) callconv(.c) void {
    uart.write(ptr[0..len]);
}

// ------------------------------------------------------------------------------------- the heap

/// The span the linker script hands over, from `l2high`'s ORIGIN and LENGTH.
///
/// Reached with `@extern`, NOT with `extern const __heap_start: anyopaque` plus
/// `@intFromPtr`/`@ptrFromInt`. That spelling was here first and it was silently wrong: declaring a
/// linker symbol as an `anyopaque` OBJECT gives the optimiser a zero-sized object, so a pointer
/// derived from its address carries provenance for zero bytes, and ordinary (non-volatile) stores
/// through it are dead code it may drop. `examples/heapcheck.zig` caught it on the die - the
/// allocator's first block header read back as `size=2988759312 next=0xffffffff`-not, and the free
/// list walk never terminated. A `[*]u8` from `@extern` has no size to lose.
const heap_start = @extern([*]align(heapmod.Heap.granule) u8, .{ .name = "__heap_start" });
const heap_end = @extern([*]align(heapmod.Heap.granule) u8, .{ .name = "__heap_end" });

fn heapSpan() []align(heapmod.Heap.granule) u8 {
    return heap_start[0 .. @intFromPtr(heap_end) - @intFromPtr(heap_start)];
}

/// The one heap. A K&R coalescing free list over that span, validated on this die by
/// `examples/heapcheck.zig`: 512 blocks fill and free back to a single 393,216-byte block, a holed
/// arena still satisfies a 4 KiB request, and 20,000 random operations drain back to one block.
var gpa_heap: heapmod.Heap = undefined;

// The four C forwarders the editor is handed. `log2_align` round-trips through
// `std.mem.Alignment`, whose representation IS the log2 value.

fn cAlloc(_: ?*anyopaque, len: usize, log2_align: u8) callconv(.c) ?[*]u8 {
    const a = gpa_heap.allocator();
    return a.vtable.alloc(a.ptr, len, @enumFromInt(log2_align), @returnAddress());
}

fn cResize(_: ?*anyopaque, ptr: [*]u8, len: usize, log2_align: u8, new_len: usize) callconv(.c) bool {
    const a = gpa_heap.allocator();
    return a.vtable.resize(a.ptr, ptr[0..len], @enumFromInt(log2_align), new_len, @returnAddress());
}

fn cFree(_: ?*anyopaque, ptr: [*]u8, len: usize, log2_align: u8) callconv(.c) void {
    const a = gpa_heap.allocator();
    a.vtable.free(a.ptr, ptr[0..len], @enumFromInt(log2_align), @returnAddress());
}

const editor_allocator: Allocator = .{
    .ctx = null,
    .alloc = cAlloc,
    .resize = cResize,
    .free = cFree,
};

// ------------------------------------------------------------------------------------ the clock

/// Milliseconds since boot, off the systimer - a 16 MHz counter (`hal/systimer.zig:31`), which is
/// the cheapest trustworthy clock on this chip. `read` returns null if the unit is not running, in
/// which case time simply does not advance and the editor stops animating; that is a better failure
/// than a clock that jumps.
fn nowMs() u64 {
    const us = hal.systimer.micros(.unit0) orelse return 0;
    return us / 1000;
}

// ------------------------------------------------------------------------------------- the loop

export fn zig_main() noreturn {
    // FIRST, before a single byte of `.rodata` is touched - which means before the marker below,
    // because that marker IS a string literal in flash and would read as machine code without this.
    soc.flushFlashCache();
    const heap = heapSpan();
    soc.rom.print("\r\nMARK B3 rom.print heap 0x%08x..0x%08x %u KiB\r\n", .{
        @as(u32, @intFromPtr(heap.ptr)),
        @as(u32, @intFromPtr(heap.ptr)) + @as(u32, @intCast(heap.len)),
        @as(u32, @intCast(heap.len / 1024)),
    });

    // The CPU clock, before anything is timed against it. The bootloader leaves 90 MHz and the
    // CPLL is already at 360, so this is a divider change that disturbs neither UART0 (XTAL) nor
    // the systimer (XTAL/2.5) nor the flash interface (SPLL). See hal/clkrst.zig:setCpuFreq.
    if (config.cpu_mhz != 90) hal.clkrst.setCpuFreq(switch (config.cpu_mhz) {
        180 => .mhz180,
        360 => .mhz360,
        else => .mhz90,
    });

    const rwdt_was_armed = hal.rwdt.disable();
    hal.systimer.init();
    _ = rwdt_was_armed;

    const their_abi = pardes_p4_abi_version();
    if (their_abi != abi_version) {
        uart.write("MARK PARDES_ABI_MISMATCH\r\n");
        while (true) {}
    }

    gpa_heap = heapmod.Heap.init(heap);
    _ = uart.drainInput();

    const rc = pardes_p4_init(&editor_allocator, writeOut, null, 80, 24);

    if (rc != 0) {
        soc.rom.print("MARK PARDES_INIT_FAIL rc=%u\r\n", .{rc});
        const s = gpa_heap.stats();
        soc.rom.print("MARK PARDES_HEAP free=%u largest=%u blocks=%u\r\n", .{
            s.free, s.largest_free, s.free_blocks,
        });
        while (true) {}
    }

    // The CPU clock, measured rather than assumed. Every cycle count this firmware reports is
    // divided by it somewhere, and `src/io/chip.zig` records it as "a measured ~90 MHz" that
    // nothing here reconfigures - so it is worth printing rather than remembering. The systimer is
    // XTAL/2.5 = 16 MHz and is NOT derived from the CPU clock (`hal/systimer.zig:31`,
    // `clk_tree_defs.h:196-198`), which is exactly what makes it a valid reference for measuring it.
    if (prof) {
        const t_start = hal.systimer.micros(.unit0) orelse 0;
        const c_start = soc.cycles();
        // 50 ms is long enough that the systimer's 16 MHz granularity and the loop's own overhead
        // are both noise, and short enough to be invisible in a boot.
        while ((hal.systimer.micros(.unit0) orelse 0) -% t_start < 50_000) {}
        const elapsed_us = (hal.systimer.micros(.unit0) orelse 0) -% t_start;
        const elapsed_cy = soc.cycles() - c_start;
        soc.rom.print("MARK CPU_HZ cycles=%u us=%u khz=%u\r\n", .{
            @as(u32, @intCast(elapsed_cy)),
            @as(u32, @intCast(elapsed_us)),
            @as(u32, @intCast(if (elapsed_us > 0) elapsed_cy * 1000 / elapsed_us else 0)),
        });
    }
    soc.rom.print("MARK PARDES_READY\r\n", .{});

    var in: [256]u8 = undefined;
    while (!pardes_p4_quit()) {
        // ATTRIBUTION. The host can time a keystroke's round trip but cannot see what the firmware
        // spent it on, and the two candidates - parsing and editing, versus rendering - want
        // opposite fixes. `soc.cycles()` is the unprivileged cycle counter, so this costs two CSR
        // reads per phase and quantises at one cycle, which is four orders of magnitude below the
        // milliseconds being attributed. Gated on `prof` so the shipping build carries none of it.
        const n = uart.read(&in);
        var input_cy: u64 = 0;
        if (n > 0) {
            const t0 = if (prof) soc.cycles() else 0;
            pardes_p4_input(&in, n);
            if (prof) input_cy = soc.cycles() - t0;
        }

        pardes_p4_tick(nowMs());

        // Only when there is something to show. On a link this slow an unconditional repaint per
        // iteration would saturate the wire and starve input.
        if (pardes_p4_wants_frame()) {
            const t0 = if (prof) soc.cycles() else 0;
            const err = pardes_p4_render();
            if (err != 0) soc.rom.print("MARK PARDES_RENDER_FAIL rc=%u\r\n", .{err});
            if (prof) {
                const render_cy = soc.cycles() - t0;
                // A SECOND render with nothing changed since the first. It splits the cost in two:
                // whatever this still costs is the price of walking and diffing the whole editor
                // state, paid regardless of output, while the difference between the two is the
                // price of the change itself. `wants_frame` is false now, so this only happens
                // under -Dprof and never on a shipping build.
                const t1 = soc.cycles();
                _ = pardes_p4_render();
                const idle_cy = soc.cycles() - t1;
                // Reported in cycles, not microseconds: the divisor is the CPU clock, which this
                // firmware does not set and has only ever measured, so converting here would bake a
                // guess into the data. `experiments/` divides by the clock it measured.
                var copy_cy: u64 = 0;
                var vx_cy: u64 = 0;
                var flush_cy: u64 = 0;
                pardes_p4_frame_prof(&copy_cy, &vx_cy, &flush_cy);
                soc.rom.print("PROF in=%u render=%u idle=%u copy=%u vaxis=%u flush=%u\r\n", .{
                    @as(u32, @intCast(input_cy)),
                    @as(u32, @intCast(render_cy)),
                    @as(u32, @intCast(idle_cy)),
                    @as(u32, @intCast(copy_cy)),
                    @as(u32, @intCast(vx_cy)),
                    @as(u32, @intCast(flush_cy)),
                });
            }
        }
    }

    soc.rom.print("\r\nMARK PARDES_QUIT\r\n", .{});
    while (true) {}
}

// ------------------------------------------------------------------------------------ the trap

/// A trap handler, because the absence of one is why this port has been guessing.
///
/// The mask ROM prints "Guru Meditation" for a trap only while ITS handler is still installed;
/// anything this image does that replaces or outgrows that path fails silently instead, and a silent
/// fault is indistinguishable from an infinite loop over a serial line. This one reports the three
/// registers that name the fault and then stops, using the direct-FIFO writer so it shares nothing
/// with the editor's buffered output.
///
/// `mtvec` is set in DIRECT mode (low two bits zero), so every trap and every interrupt lands on
/// `trapEntry` regardless of cause - which is what a diagnostic wants.
export fn trapEntry() linksection(".text.entry") callconv(.naked) noreturn {
    asm volatile ("j trapReport");
}

export fn trapReport() noreturn {
    const mcause = asm volatile ("csrr %[o], mcause"
        : [o] "=r" (-> u32),
    );
    const mepc = asm volatile ("csrr %[o], mepc"
        : [o] "=r" (-> u32),
    );
    const mtval = asm volatile ("csrr %[o], mtval"
        : [o] "=r" (-> u32),
    );
    uart.write("\r\nMARK TRAP mcause=");
    uart.dumpWord(mcause);
    uart.write("MARK TRAP mepc=");
    uart.dumpWord(mepc);
    uart.write("MARK TRAP mtval=");
    uart.dumpWord(mtval);
    uart.write("MARK TRAP dropped=");
    uart.dumpWord(uart.dropped);
    while (true) {}
}

// --------------------------------------------------------------------------- the root's own duties

/// `page_size_min`/`max`: the board has no MMU and no pages, but std derives allocator alignment
/// from these. 4 KiB is the ESP32-P4's cache and DMA granularity.
///
/// `logFn` is not cosmetic. std's default log implementation reaches `std.debug_io`, which
/// instantiates `std.Io.Threaded` - a thread pool, `getrandom`, `IOV_MAX`, `mremap` - none of which
/// exist here, and one `log.warn` from anywhere is enough to drag all of it into the image.
pub const std_options: std.Options = .{
    .page_size_min = 4096,
    .page_size_max = 4096,
    .logFn = logFn,
};

fn logFn(
    comptime level: std.log.Level,
    comptime scope: @EnumLiteral(),
    comptime fmt: []const u8,
    args: anytype,
) void {
    var buf: [256]u8 = undefined;
    const line = std.fmt.bufPrint(&buf, "\r\n[" ++ level.asText() ++ "/" ++ @tagName(scope) ++ "] " ++ fmt ++ "\r\n", args) catch
        "\r\n[log overflow]\r\n";
    uart.write(line);
}

pub const panic = std.debug.FullPanic(panicImpl);

fn panicImpl(msg: []const u8, _: ?usize) noreturn {
    // The ROM path deliberately: a panic may BE the console writer failing, and `ets_printf` shares
    // nothing with `uart.write` except the FIFO itself.
    soc.rom.print("\r\nMARK PARDES_PANIC %s\r\n", .{msg.ptr});
    while (true) {}
}

/// Reset entry. The bootloader hands over with an unspecified stack pointer and the FPU off, so:
/// enable the F extension (`mstatus.FS`, which ESP-IDF only ever turns on lazily from a trap handler
/// this image does not have), establish a stack, clear `.bss`, and call into Zig.
///
/// The cache invalidate that this image also needs is the FIRST thing `zig_main` does, not something
/// done here. Hand-written `la t0, Cache_Invalidate_All` against an absolute linker symbol computed
/// a PC-relative target and jumped into nowhere (measured: PC=0x88b5d788 with the argument stranded
/// in a2); Zig generates the addressing for an `extern fn` correctly, and `zig_main` runs before any
/// `.rodata` is touched anyway.
export fn _start() linksection(".text.entry") callconv(.naked) noreturn {
    asm volatile (
        \\ li t0, 1 << 13
        \\ csrs mstatus, t0
        \\ la sp, __stack_top
        \\ mv fp, sp
        \\ la t0, trapEntry
        \\ csrw mtvec, t0
        \\ la t0, __bss_start
        \\ la t1, __bss_end
        \\ bgeu t0, t1, 2f
        \\1:
        \\ sw zero, 0(t0)
        \\ addi t0, t0, 4
        \\ bltu t0, t1, 1b
        \\2:
        \\ j zig_main
    );
}