danos/system/services/vfs/vfs.zig

397 lines
17 KiB
Zig

//! system/services/vfs — the user-space VFS server. Shipped in the initial_ramdisk, spawned as a
//! ring-3 process, and reached by every other process through IPC (the `runtime`
//! file API marshals open/read/write/stat/close into calls to this server's
//! endpoint, published under the well-known `vfs` service id).
//!
//! Two namespaces meet here (M5):
//! - a small in-memory **ramfs** — opening a bare name creates it — enough to
//! prove the round trip and to back the existing tests;
//! - **mounted filesystems**: a mount table maps an absolute path prefix (e.g.
//! `/mnt/usb`) to a backend server's endpoint. An open of a path under a mount
//! is *forwarded* to that backend (which speaks this same protocol), and every
//! later read/write/status/readdir/close on the resulting handle is relayed to
//! it. The VFS is the router; a filesystem (FAT) is the backend.
//!
//! A path routes through a mount only when it is absolute and lies under a mount
//! prefix; bare names always resolve in the flat ramfs — the backward-compat
//! contract the `vfs` / `vfs-client-death` tests rely on.
const std = @import("std");
const runtime = @import("runtime");
const protocol = runtime.vfs_protocol;
const path = @import("path.zig");
const ipc = runtime.ipc;
const Node = struct {
used: bool = false,
name: [24]u8 = undefined,
name_len: usize = 0,
data: [512]u8 = undefined,
size: usize = 0,
};
const OpenFile = struct {
used: bool = false,
// For a local handle: an index into `nodes`. For a forwarding handle: the
// node id the backend returned. (usize == u64 here, so it holds either.)
node: usize = 0,
// Non-null for a handle that forwards to a mounted backend.
backend: ?ipc.Handle = null,
// The client (task id — an IPC badge is one) that opened this handle. What
// release-on-death sweeps by: a service must never depend on its clients
// cleaning up after themselves (docs/process-lifecycle.md).
owner: u32 = 0,
};
// One mounted filesystem: an absolute path prefix and the backend endpoint that
// serves everything under it.
const Mount = struct {
used: bool = false,
prefix: [64]u8 = undefined,
prefix_len: usize = 0,
backend: ipc.Handle = 0,
};
var nodes = [_]Node{.{}} ** 8;
var opens = [_]OpenFile{.{}} ** 16;
var mounts = [_]Mount{.{}} ** 8;
fn findNode(name: []const u8) ?usize {
for (&nodes, 0..) |*n, i| {
if (n.used and std.mem.eql(u8, n.name[0..n.name_len], name)) return i;
}
return null;
}
fn createNode(name: []const u8) ?usize {
for (&nodes, 0..) |*n, i| {
if (!n.used) {
const l = @min(name.len, n.name.len);
@memcpy(n.name[0..l], name[0..l]);
n.* = .{ .used = true, .name = n.name, .name_len = l, .size = 0 };
return i;
}
}
return null;
}
fn openAt(id: u64) ?*OpenFile {
if (id >= opens.len) return null;
const o = &opens[@intCast(id)];
return if (o.used) o else null;
}
/// The mount whose prefix most specifically contains `name`, and the path
/// relative to it. Only absolute paths route; bare names never match.
const MountMatch = struct { backend: ipc.Handle, relative: []const u8 };
fn longestMount(name: []const u8) ?MountMatch {
if (!path.isAbsolute(name)) return null;
var best: ?MountMatch = null;
var best_len: usize = 0;
for (&mounts) |*m| {
if (!m.used) continue;
const prefix = m.prefix[0..m.prefix_len];
if (path.underMount(name, prefix)) |relative| {
if (best == null or prefix.len >= best_len) {
best_len = prefix.len;
best = .{ .backend = m.backend, .relative = relative };
}
}
}
return best;
}
/// Serialise a reply header + payload into `out`; returns the total length.
fn writeReply(out: []u8, reply: protocol.Reply, payload: []const u8) usize {
@memcpy(out[0..protocol.reply_size], std.mem.asBytes(&reply));
const n = @min(payload.len, out.len - protocol.reply_size);
@memcpy(out[protocol.reply_size..][0..n], payload[0..n]);
return protocol.reply_size + n;
}
fn fail(out: []u8) usize {
return writeReply(out, .{ .status = -1 }, &.{});
}
/// Format one whole log line and emit it in a single `debug_write`, so lines from
/// concurrent processes can never land in the middle of it.
fn writeLine(comptime fmt: []const u8, arguments: anytype) void {
var line: [96]u8 = undefined;
_ = runtime.system.write(std.fmt.bufPrint(&line, fmt, arguments) catch return);
}
// --- mount routing ----------------------------------------------------------
/// Forward an open under a mount to its backend and, on success, allocate a local
/// forwarding handle that remembers the backend's node id.
fn forwardOpen(out: []u8, backend: ipc.Handle, relative: []const u8, flags: u32, sender: u32) usize {
const request = protocol.Request{ .operation = .open, .node = 0, .offset = 0, .len = @intCast(relative.len), .flags = flags };
var message: [protocol.message_maximum]u8 = undefined;
@memcpy(message[0..protocol.request_size], std.mem.asBytes(&request));
const rel = relative[0..@min(relative.len, protocol.maximum_payload)];
@memcpy(message[protocol.request_size..][0..rel.len], rel);
var reply: [protocol.message_maximum]u8 = undefined;
const n = ipc.call(backend, message[0 .. protocol.request_size + rel.len], &reply) catch return fail(out);
if (n < protocol.reply_size) return fail(out);
const backend_reply = std.mem.bytesToValue(protocol.Reply, reply[0..protocol.reply_size]);
if (backend_reply.status != 0) return writeReply(out, .{ .status = backend_reply.status }, &.{});
for (&opens, 0..) |*o, i| {
if (!o.used) {
o.* = .{ .used = true, .node = @intCast(backend_reply.node), .backend = backend, .owner = sender };
return writeReply(out, .{ .status = 0, .node = i }, &.{});
}
}
return fail(out);
}
/// Relay a read/write/status/readdir/close on a forwarding handle to the backend
/// (the node already rewritten to the backend's id) and copy its reply out.
fn forwardRequest(out: []u8, backend: ipc.Handle, request: protocol.Request, payload: []const u8) usize {
var message: [protocol.message_maximum]u8 = undefined;
@memcpy(message[0..protocol.request_size], std.mem.asBytes(&request));
const plen = @min(payload.len, protocol.maximum_payload);
@memcpy(message[protocol.request_size..][0..plen], payload[0..plen]);
var reply: [protocol.message_maximum]u8 = undefined;
const n = ipc.call(backend, message[0 .. protocol.request_size + plen], &reply) catch return fail(out);
const copy = @min(n, out.len);
@memcpy(out[0..copy], reply[0..copy]);
return copy;
}
/// Forward a path-based operation (mkdir, unlink) under a mount to its backend and
/// relay the reply. No handle is created — these operate by path and return only a
/// status.
fn forwardPath(out: []u8, backend: ipc.Handle, operation: protocol.Operation, relative: []const u8) usize {
const request = protocol.Request{ .operation = operation, .node = 0, .offset = 0, .len = @intCast(relative.len), .flags = 0 };
var message: [protocol.message_maximum]u8 = undefined;
@memcpy(message[0..protocol.request_size], std.mem.asBytes(&request));
const rel = relative[0..@min(relative.len, protocol.maximum_payload)];
@memcpy(message[protocol.request_size..][0..rel.len], rel);
var reply: [protocol.message_maximum]u8 = undefined;
const n = ipc.call(backend, message[0 .. protocol.request_size + rel.len], &reply) catch return fail(out);
const copy = @min(n, out.len);
@memcpy(out[0..copy], reply[0..copy]);
return copy;
}
/// Forward a rename to its backend: the payload is the mount-relative old path, a
/// 0x00 separator, then the mount-relative new path. Relays the backend's reply.
fn forwardRename(out: []u8, backend: ipc.Handle, old_relative: []const u8, new_relative: []const u8) usize {
const total = old_relative.len + 1 + new_relative.len;
var message: [protocol.message_maximum]u8 = undefined;
if (protocol.request_size + total > message.len) return fail(out);
const request = protocol.Request{ .operation = .rename, .node = 0, .offset = 0, .len = @intCast(total), .flags = 0 };
@memcpy(message[0..protocol.request_size], std.mem.asBytes(&request));
var p = protocol.request_size;
@memcpy(message[p..][0..old_relative.len], old_relative);
p += old_relative.len;
message[p] = 0;
p += 1;
@memcpy(message[p..][0..new_relative.len], new_relative);
p += new_relative.len;
var reply: [protocol.message_maximum]u8 = undefined;
const n = ipc.call(backend, message[0..p], &reply) catch return fail(out);
const copy = @min(n, out.len);
@memcpy(out[0..copy], reply[0..copy]);
return copy;
}
/// Best-effort close of a backend node (used when a dead client's forwarding
/// handles are swept — the backend must not leak the vfs's opens).
fn forwardClose(backend: ipc.Handle, backend_node: u64) void {
const request = protocol.Request{ .operation = .close, .node = backend_node, .offset = 0, .len = 0, .flags = 0 };
var reply: [protocol.message_maximum]u8 = undefined;
_ = ipc.call(backend, std.mem.asBytes(&request), &reply) catch {};
}
fn doMount(out: []u8, prefix: []const u8, backend: ipc.Handle) usize {
for (&mounts) |*m| {
if (m.used and std.mem.eql(u8, m.prefix[0..m.prefix_len], prefix)) {
m.backend = backend;
writeLine("/system/services/vfs: remounted {s}\n", .{prefix});
return writeReply(out, .{ .status = 0 }, &.{});
}
}
for (&mounts) |*m| {
if (!m.used) {
const l = @min(prefix.len, m.prefix.len);
m.used = true;
@memcpy(m.prefix[0..l], prefix[0..l]);
m.prefix_len = l;
m.backend = backend;
writeLine("/system/services/vfs: mounted {s}\n", .{prefix[0..l]});
return writeReply(out, .{ .status = 0 }, &.{});
}
}
return fail(out);
}
fn doUnmount(out: []u8, prefix: []const u8) usize {
for (&mounts) |*m| {
if (m.used and std.mem.eql(u8, m.prefix[0..m.prefix_len], prefix)) {
m.used = false;
writeLine("/system/services/vfs: unmounted {s}\n", .{prefix});
return writeReply(out, .{ .status = 0 }, &.{});
}
}
return fail(out);
}
/// Release every open handle `client` held — called on that client's published
/// exit event. Forwarding handles also tell their backend to release; local
/// nodes (the ramfs files) stay, since ramfs contents outlive their writers.
fn releaseClientHandles(client: u32) void {
var released: u32 = 0;
for (&opens) |*o| {
if (o.used and o.owner == client) {
if (o.backend) |backend| forwardClose(backend, o.node);
o.used = false;
released += 1;
}
}
if (released != 0) writeLine("/system/services/vfs: released {d} handle(s) for dead client {d}\n", .{ released, client });
}
/// Handle one request from `sender`; write the reply into `out`, return its length.
fn handle(message: []const u8, out: []u8, sender: u32, capability: ?ipc.Handle) usize {
if (message.len < protocol.request_size) return fail(out);
const request = std.mem.bytesToValue(protocol.Request, message[0..protocol.request_size]);
const payload = message[protocol.request_size..];
switch (request.operation) {
.mount => {
const prefix = payload[0..@min(payload.len, request.len)];
const backend = capability orelse return fail(out);
return doMount(out, prefix, backend);
},
.unmount => {
const prefix = payload[0..@min(payload.len, request.len)];
return doUnmount(out, prefix);
},
.open => {
const name = payload[0..@min(payload.len, request.len)];
if (longestMount(name)) |m| return forwardOpen(out, m.backend, m.relative, request.flags, sender);
// An absolute path with no matching mount is simply not found — only
// bare names live in the flat ramfs. (Else /mnt/usb would be silently
// created as a flat file when its filesystem is not yet mounted.)
if (path.isAbsolute(name)) return fail(out);
const ni = findNode(name) orelse createNode(name) orelse return fail(out);
for (&opens, 0..) |*o, i| {
if (!o.used) {
o.* = .{ .used = true, .node = ni, .backend = null, .owner = sender };
return writeReply(out, .{ .status = 0, .node = i }, &.{});
}
}
return fail(out);
},
.read => {
const of = openAt(request.node) orelse return fail(out);
if (of.backend) |backend| {
var forwarded = request;
forwarded.node = of.node;
return forwardRequest(out, backend, forwarded, payload);
}
const nd = &nodes[@intCast(of.node)];
const off: usize = @intCast(request.offset);
if (off >= nd.size) return writeReply(out, .{ .status = 0, .len = 0 }, &.{}); // EOF
const n = @min(@min(nd.size - off, request.len), protocol.maximum_payload);
return writeReply(out, .{ .status = 0, .len = @intCast(n) }, nd.data[off .. off + n]);
},
.write => {
const of = openAt(request.node) orelse return fail(out);
if (of.backend) |backend| {
var forwarded = request;
forwarded.node = of.node;
return forwardRequest(out, backend, forwarded, payload);
}
const nd = &nodes[@intCast(of.node)];
const off: usize = @intCast(request.offset);
if (off > nd.data.len) return fail(out);
const n = @min(@min(payload.len, request.len), nd.data.len - off);
@memcpy(nd.data[off .. off + n], payload[0..n]);
if (off + n > nd.size) nd.size = off + n;
return writeReply(out, .{ .status = 0, .len = @intCast(n) }, &.{});
},
.status => {
const of = openAt(request.node) orelse return fail(out);
if (of.backend) |backend| {
var forwarded = request;
forwarded.node = of.node;
return forwardRequest(out, backend, forwarded, payload);
}
const st = protocol.FileStatus{ .size = nodes[@intCast(of.node)].size, .kind = @intFromEnum(protocol.NodeKind.regular) };
return writeReply(out, .{ .status = 0, .len = @sizeOf(protocol.FileStatus) }, std.mem.asBytes(&st));
},
.readdir => {
const of = openAt(request.node) orelse return fail(out);
if (of.backend) |backend| {
var forwarded = request;
forwarded.node = of.node;
return forwardRequest(out, backend, forwarded, payload);
}
// The flat ramfs has no directories: report EOF.
return writeReply(out, .{ .status = 0, .len = 0 }, &.{});
},
.close => {
const of = openAt(request.node);
if (of) |o| {
if (o.backend) |backend| forwardClose(backend, o.node);
o.used = false;
}
return writeReply(out, .{ .status = 0 }, &.{});
},
.mkdir, .unlink => {
const name = payload[0..@min(payload.len, request.len)];
if (longestMount(name)) |m| return forwardPath(out, m.backend, request.operation, m.relative);
// Only a mounted backend has real directories; the flat ramfs cannot
// create or remove them (and a bare-name path is not a mount target).
return fail(out);
},
.rename => {
const both = payload[0..@min(payload.len, request.len)];
const sep = std.mem.indexOfScalar(u8, both, 0) orelse return fail(out);
const old_path = both[0..sep];
const new_path = both[sep + 1 ..];
const mo = longestMount(old_path) orelse return fail(out);
const mn = longestMount(new_path) orelse return fail(out);
// Both paths must live under the same mount — cross-filesystem rename is
// not supported.
if (mo.backend != mn.backend) return fail(out);
return forwardRename(out, mo.backend, mo.relative, mn.relative);
},
}
}
/// Startup, under the harness: subscribe to the published exit events — when a
/// client dies holding open handles, the exit notification is how the VFS learns
/// to release them (docs/process-lifecycle.md).
fn initialise(endpoint: ipc.Handle) bool {
if (!runtime.process.subscribeExits(endpoint)) {
_ = runtime.system.write("/system/services/vfs: exit subscription failed\n");
}
_ = runtime.system.write("/system/services/vfs: ready\n");
return true;
}
/// A non-signal notification: the only kind the VFS subscribes to is exit events.
fn onNotification(badge: u64) void {
if (badge & ipc.notify_exit_bit != 0) {
releaseClientHandles(@intCast(badge & ~(ipc.notify_badge_bit | ipc.notify_exit_bit)));
}
}
pub fn main() void {
// The harness owns the loop: requests dispatch to handle(), exit events to
// onNotification(), ping and terminate are answered for free — this service
// gained the whole lifecycle contract by deleting its hand-rolled loop.
runtime.service.run(protocol.message_maximum, .{
.service = .vfs,
.init = initialise,
.on_message = handle,
.on_notification = onNotification,
});
}