Files
danos/system/services/fat/fat.zig
T
Daniel Samson d63a008148 file-system: extract the serving harness from fat — V1
fat was one binary doing four jobs; the three that are not FAT-specific move
to library/kernel/file-system-harness, a Server(comptime Engine) generic over
the engine type: the badge-scoped open-node table, the nine vfs handlers, the
not-mounted politeness, the exit sweep, mount registration, and durable-on-
close. A filesystem is now an engine plus a main that hands the harness a
mounted volume; a second engine reuses the harness wholesale.

Placement note: the plan said library/file-system, but the harness is a
specialization of `service` (its sibling) and needs nothing from the device
domain, so it lives beside service in library/kernel and stays block-free —
durability rides a caller closure (Volume.flush), no backwards kernel->device
dependency, no new-domain scaffolding. The engine type is inferred from
resolve()'s return, so engine.zig is untouched (its Node stays module-scope).

fat keeps only its FAT-specific bring-up (acquireVolume, DMA, engine.mount,
the attach/detach round trip) and the three mount prefixes as data. Behavior-
neutral: 13/13 across the fat/vfs/logger/IOMMU surface, nothing observable
changed. This lands first so every later phase touches the harness once.
2026-08-09 16:55:48 +01:00

186 lines
9.2 KiB
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 device_manager_protocol = @import("device-manager-protocol");
const driver = @import("driver");
const ipc = @import("ipc");
const block = @import("block");
const memory = @import("memory");
const logging = @import("logging");
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 one channel to the device manager, opened on first need and kept — the
/// poll retries on it, never spending a handle-table slot per attempt.
var manager_handle: ?ipc.Handle = null;
/// The prefixes this volume installs: /volumes/usb from the volume root, plus
/// the two hierarchy subtrees the boot volume carries (rewrite == prefix), so
/// hierarchy paths (the logger's /system/logs) stay decoupled from which volume
/// backs them.
const fat_mounts = [_]harness.MountSpec{
.{ .prefix = "/volumes/usb" },
.{ .prefix = "/system/configuration", .rewrite = "/system/configuration" },
.{ .prefix = "/system/logs", .rewrite = "/system/logs" },
};
/// Find the volume's provider through the device manager (establishment by
/// lineage, communication.md "Establishment: two planes" — `block` is not a
/// registry name; one storage process serves each stick): enumerate the
/// manager's tree, take the FIRST usb mass-storage child by enumeration order
/// (deterministic within a boot; single-volume by construction, and choosing
/// the BOOT volume by content when two sticks are present is the volume-manager
/// track), and consumer-hello for the channel of the driver bound to it.
/// Null until the chain is up — the harness's poll retries.
fn acquireVolume() ?block.Device {
const manager = manager_handle orelse opened: {
const handle = channel.openEndpoint("device-manager") orelse return null;
manager_handle = handle;
break :opened handle;
};
// The envelope's reserved `enumerate` verb, PAGED: one reply carries only
// a handful of entries and a real tree (a dozen ACPI nodes before the
// first USB child) is bigger, so `Header.target` is the start cursor and
// a short page is the end. Identity is the bus's native triple, for USB
// (base << 16) | (class << 8) | protocol — mass storage is base 0x08,
// subclass 0x06 (SCSI transparent), the same key devices.csv matches on.
const Entry = device_manager_protocol.ChildEntry;
var start: u64 = 0;
while (true) {
const enumerate = envelope.Header{ .operation = envelope.operation_enumerate, .target = start };
var reply: [device_manager_protocol.message_maximum]u8 = undefined;
const length = ipc.call(manager, std.mem.asBytes(&enumerate), &reply) catch return null;
const status = envelope.statusOf(reply[0..length]) orelse return null;
if (status.status != 0) return null;
const carried = @min(@as(usize, status.len), length -| envelope.prefix_size);
const tail = reply[envelope.prefix_size..][0..carried];
const count = tail.len / @sizeOf(Entry);
if (count == 0) return null; // the tree is exhausted; no volume yet
var index: usize = 0;
while (index < count) : (index += 1) {
const entry = std.mem.bytesToValue(Entry, tail[index * @sizeOf(Entry) ..][0..@sizeOf(Entry)]);
if (entry.device_id == device_manager_protocol.no_device) continue;
if ((entry.identity >> 16) & 0xff != 0x08 or (entry.identity >> 8) & 0xff != 0x06) continue;
const exchanged = driver.helloOn(manager, .consumer, entry.device_id, null, true) orelse return null;
const provider = exchanged.channel orelse continue; // its driver not up yet — next tick
return .{ .endpoint = provider };
}
start += count;
}
}
/// 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 });
return .{ .engine = &filesystem, .mounts = &fat_mounts, .flush = flushIfDirty };
}
pub fn main() void {
_ = logging.write("/system/services/fat: starting, waiting for a block device\n");
Harness.run(.{ .bringUp = fatBringUp });
}