danos/system/services/fat/fat.zig

//! system/services/fat — the FAT filesystem service. This is FAT's FAT-specific
//! half: it finds its block device, sets up the DMA bounce buffer, mounts the
//! FAT engine on it, and hands the mounted volume to the shared filesystem
//! harness (library/kernel/file-system-harness), which owns everything else —
//! the vfs-protocol serving, the open-node table, mount registration, the exit
//! sweep, durable-on-close. The engine (engine.zig) is the pure, host-testable
//! format code; on-disk.zig its byte layout. A second filesystem reuses the
//! harness and supplies its own engine
//! (docs/file-system-development/storage-architecture.md).
//!
//! The block data path never crosses IPC: a DMA bounce buffer is handed to the
//! block driver by physical address, and the engine copies sectors in and out.

const std = @import("std");
const channel = @import("channel");
const volume_manager_protocol = @import("volume-manager-protocol");
const ipc = @import("ipc");
const process = @import("process");
const block = @import("block");
const memory = @import("memory");
const logging = @import("logging");
const time = @import("time");
const engine = @import("engine.zig");
const envelope = @import("envelope");
const harness = @import("file-system-harness");

/// The serving harness, specialized for the FAT engine. One volume per process.
const Harness = harness.Server(engine.FileSystem);

// The engine's BlockDevice, backed by the `.block` driver plus a DMA bounce
// buffer the driver reads/writes by physical address.
const IpcBlock = struct {
    device: block.Device,
    bounce: memory.DmaRegion, // engine.max_transfer_sectors * 512 bytes

    fn readBlocks(context: *anyopaque, lba: u64, count: u32, buffer: []u8) bool {
        const self: *IpcBlock = @ptrCast(@alignCast(context));
        if (count == 0 or count > engine.max_transfer_sectors) return false;
        const len = count * 512;
        if (!self.device.read(lba, count, self.bounce.physical)) return false;
        const source: [*]const u8 = @ptrFromInt(self.bounce.virtual);
        @memcpy(buffer[0..len], source[0..len]);
        return true;
    }
    fn writeBlocks(context: *anyopaque, lba: u64, count: u32, buffer: []const u8) bool {
        const self: *IpcBlock = @ptrCast(@alignCast(context));
        if (count == 0 or count > engine.max_transfer_sectors) return false;
        const len = count * 512;
        const destination: [*]u8 = @ptrFromInt(self.bounce.virtual);
        @memcpy(destination[0..len], buffer[0..len]);
        if (!self.device.write(lba, count, self.bounce.physical)) return false;
        device_dirty = true; // a block reached the device; a close will flush it
        return true;
    }
};

var ipc_block: IpcBlock = undefined;
// Set whenever a block is written, cleared when the device cache is flushed on a
// file close — so writes are committed to stable media before a power-off.
var device_dirty: bool = false;
var filesystem: engine.FileSystem = undefined;
/// The volume this FAT process serves, its id given as argv[1] by the volume
/// manager that spawned it. The startup hello names it so the manager returns
/// the right volume's channel.
var my_volume_id: u64 = 0;

/// The volume's own mount path, handed in as argv[2] by the volume manager: the
/// volume's content id-path (e.g. /volumes/fat-12345678). Defaults to
/// /volumes/usb only for a bare launch with no argument; the manager always
/// passes it. The slice points into the entry block, valid for the process life.
var volume_mount_prefix: []const u8 = "/volumes/usb";

/// The mounts this volume installs: its own root, plus — only if it is the boot
/// volume (it resolves /system/configuration) — the two FHS rewrites, so the
/// logger's /system/logs stays decoupled from which volume backs it. Boot-volume
/// detection is by content, so it works no matter which volume carries /system.
/// bound: mounts one volume installs (its root + the two boot rewrites)
/// decided-by: ours
/// protects: the mount_specs array
/// at-limit: truncate - unreachable today (fixed at 3); more configured mounts
///   would need this raised, a deliberate change
/// observed-by: a mount silently missing from the harness's mount log
const maximum_mounts_per_volume = 4;
var mount_specs: [maximum_mounts_per_volume]harness.MountSpec = undefined;

/// Get this volume's block channel from the volume manager (establishment by
/// lineage, communication.md "Establishment: two planes" — `block` is not a
/// registry name). The manager spawned this process, confined it to its
/// partition, and answers the hello with the channel; the channel is
/// range-confined to this process's badge, so reads and writes are
/// volume-relative and cannot reach the neighbouring partition. Null until the
/// manager has the volume ready — this retries.
fn acquireVolume() ?block.Device {
    var attempts: u32 = 0;
    const vm = while (attempts < 500) : (attempts += 1) {
        if (channel.openEndpoint("volume-manager")) |handle| break handle;
        time.sleepMillis(20);
    } else return null;

    attempts = 0;
    while (attempts < 500) : (attempts += 1) {
        var packet: [volume_manager_protocol.message_maximum]u8 = undefined;
        const framed = volume_manager_protocol.Protocol.encodeRequest(.hello, my_volume_id, .{}, &.{}, &packet) orelse return null;
        var reply: [volume_manager_protocol.message_maximum]u8 = undefined;
        const answered = ipc.callCap(vm, framed, &reply, null) catch return null;
        const status = envelope.statusOf(reply[0..answered.len]) orelse return null;
        if (status.status != 0) {
            if (answered.cap) |stray| _ = ipc.close(stray);
            _ = logging.write("/system/services/fat: volume manager refused the hello\n");
            return null;
        }
        if (answered.cap) |bus| return .{ .endpoint = bus };
        // Acked with no channel: the volume is not ready yet — retry.
        time.sleepMillis(20);
    }
    return null;
}

/// Durable-on-close: commit the device write cache if any block reached it since
/// the last flush. The harness calls this on every close; the dirty check keeps
/// it cheap. `device_dirty` lives here because `IpcBlock.writeBlocks` sets it.
fn flushIfDirty() void {
    if (device_dirty) {
        _ = ipc_block.device.flush();
        device_dirty = false;
    }
}

/// FAT bring-up: find the block device, set up DMA, mount the engine, and hand
/// the volume to the harness — or null to retry on the harness's timer.
fn fatBringUp(endpoint: ipc.Handle) ?Harness.Volume {
    _ = endpoint;
    const device = acquireVolume() orelse return null;
    const geometry = device.geometry() orelse {
        _ = logging.write("/system/services/fat: block geometry unavailable\n");
        return null;
    };
    // Shareable so the buffer's capability can be attached down the chain (block
    // server -> controller), making its physical addresses reachable by the
    // device under an enforcing IOMMU. No-op binding otherwise.
    const bounce = memory.dmaAlloc(engine.max_transfer_sectors * 512, memory.dma_coherent | memory.dma_shareable) orelse return null;
    if (bounce.handle) |handle| {
        // Attach, detach, and attach again: the round trip exercises BOTH verbs
        // of the DMA-window lifecycle through the whole chain (fat -> storage ->
        // bus -> kernel) on every boot, so a broken detach fails every fat case
        // rather than lying dormant until the first buffer replacement.
        if (!device.attach(handle)) {
            _ = logging.write("/system/services/fat: could not attach the DMA bounce buffer\n");
            return null;
        }
        if (!device.detach(handle)) {
            _ = logging.write("/system/services/fat: could not detach the DMA bounce buffer\n");
            return null;
        }
        if (!device.attach(handle)) {
            _ = logging.write("/system/services/fat: could not re-attach the DMA bounce buffer\n");
            return null;
        }
        _ = ipc.close(handle); // the binding holds its own reference now
    }
    ipc_block = .{ .device = device, .bounce = bounce };

    const block_device = engine.BlockDevice{
        .context = &ipc_block,
        .block_size = geometry.block_size,
        .block_count = geometry.block_count,
        .readBlocksFn = IpcBlock.readBlocks,
        .writeBlocksFn = IpcBlock.writeBlocks,
    };
    filesystem = engine.FileSystem.mount(block_device) orelse {
        _ = logging.write("/system/services/fat: not a FAT filesystem\n");
        return null;
    };
    std.log.info("mounted FAT ({s}, {d} clusters, partition lba {d})", .{ @tagName(filesystem.geometry.fat_type), filesystem.geometry.cluster_count, filesystem.base_lba });

    // Every volume mounts at its own id-path (argv[2]). The boot/system volume —
    // the one carrying the /system tree — ADDITIONALLY installs the two FHS
    // rewrites, so hierarchy paths (config reads, the logger's persistent
    // /system/logs) stay decoupled from which volume backs them. Detection is by
    // CONTENT, not spawn order: a volume is the system volume iff /system/
    // configuration resolves on its own media. A data volume has no /system, so it
    // mounts only at its id-path and never shadows the running system's config or
    // logs with a dead mount.
    mount_specs[0] = .{ .prefix = volume_mount_prefix };
    var mount_count: usize = 1;
    if (filesystem.resolve("/system/configuration") != null) {
        std.log.info("volume {d} carries the system tree; backing /system/configuration and /system/logs", .{my_volume_id});
        mount_specs[1] = .{ .prefix = "/system/configuration", .rewrite = "/system/configuration" };
        mount_specs[2] = .{ .prefix = "/system/logs", .rewrite = "/system/logs" };
        mount_count = 3;
    } else {
        std.log.info("volume {d} is a data volume; mounted at {s}", .{ my_volume_id, volume_mount_prefix });
    }
    return .{ .engine = &filesystem, .mounts = mount_specs[0..mount_count], .flush = flushIfDirty };
}

pub fn main(init: process.Init) void {
    // The volume manager spawns this process with its volume id as argv[1] and
    // the volume's mount path (its id-path) as argv[2].
    if (init.arguments.get(1)) |id| {
        my_volume_id = std.fmt.parseInt(u64, id, 10) catch 0;
    }
    if (init.arguments.get(2)) |prefix| {
        volume_mount_prefix = prefix;
    }
    _ = logging.write("/system/services/fat: starting, waiting for a block device\n");
    Harness.run(.{ .bringUp = fatBringUp });
}