vfs: the root moves into the kernel — resolve + redirect cutover

runtime.fs now routes every path through fs_resolve: kernel-served
/system nodes are read via fs_node (tokens, no open state); everything
under a userspace mount goes straight to the owning backend's endpoint
with the kernel-rewritten mount-relative path — one syscall of naming,
then the unchanged vfs-protocol rendezvous, public API untouched. mkdir/
unlink/rename resolve-then-forward (rename checks both paths land on
the SAME backend); mount is the fs_mount syscall.

The fat server mounts twice — /mnt/usb from the volume root and /var
from its /var subtree — so the logger now writes the FHS path
/var/log/<boot-stamp>/... and swapping the persistent medium later
touches only fat's two mount calls. With clients holding fat's node ids
directly, fat records each handle's owner, checks it, and sweeps a dead
client's handles via the published exit events (the old router's
pattern, now where the state actually lives).

The userspace vfs server and its router die; ServiceId.vfs=1 stays
reserved-retired; protocol.zig moves to system/vfs-protocol.zig (the
wire contract is backend-only now). vfs-test becomes the ring-3 proof
of the kernel VFS (own-binary ELF magic through /system, read-only
refusals, listing); vfs-client-death becomes the fat sweep test over
the full storage chain, with a ring-scanning check (the last-write
buffer is too racy under a chattering tree).

build.zig

@@ -364,7 +364,7 @@ pub fn build(b: *std.Build) void {
     // is the first "protocol module" (see docs/driver-model.md); usb/block will
     // expose theirs the same way.
     const vfs_protocol_module = b.addModule("vfs-protocol", .{
-        .root_source_file = b.path("system/services/vfs/protocol.zig"),
+        .root_source_file = b.path("system/vfs-protocol.zig"),
     });
 
     // The input wire protocol: the input service's public interface, exposed as its own
@@ -511,8 +511,7 @@ pub fn build(b: *std.Build) void {
     // Each is built by the same user-binary recipe and laid out at its FHS path on
     // the boot volume (see `bundled` below). The EFI loader walks the tree at boot
     // and hands the kernel an in-RAM initial_ramdisk of it (system/initial-ramdisk.zig).
-    const vfs_exe = addUserBinary(b, kernel_target, runtime_module, mmio_module, xkeyboard_config_module, acpi_ids_module, "vfs", "system/services/vfs/vfs.zig");
+    const vfstest_exe = addUserBinary(b, kernel_target, runtime_module, mmio_module, xkeyboard_config_module, acpi_ids_module, "vfs-test", "system/services/vfs-test/vfs-test.zig");
-    const vfstest_exe = addUserBinary(b, kernel_target, runtime_module, mmio_module, xkeyboard_config_module, acpi_ids_module, "vfs-test", "system/services/vfs/vfs-test.zig");
     const ps2_bus_exe = addUserBinary(b, kernel_target, runtime_module, mmio_module, xkeyboard_config_module, acpi_ids_module, "ps2-bus", "system/drivers/ps2-bus/ps2-bus.zig");
     const ps2_keyboard_exe = addUserBinary(b, kernel_target, runtime_module, mmio_module, xkeyboard_config_module, acpi_ids_module, "ps2-keyboard", "system/drivers/ps2-bus/keyboard.zig");
     const ps2_mouse_exe = addUserBinary(b, kernel_target, runtime_module, mmio_module, xkeyboard_config_module, acpi_ids_module, "ps2-mouse", "system/drivers/ps2-bus/mouse.zig");
@@ -594,7 +593,6 @@ pub fn build(b: *std.Build) void {
     // are these paths with a leading slash.
     const bundled = [_]BundledBinary{
         .{ .path = "system/services/init", .binary = init_exe.getEmittedBin() },
-        .{ .path = "system/services/vfs", .binary = vfs_exe.getEmittedBin() },
         .{ .path = "system/services/fat", .binary = fat_exe.getEmittedBin() },
         .{ .path = "system/services/display", .binary = display_exe.getEmittedBin() },
         .{ .path = "system/services/display-demo", .binary = display_demo_exe.getEmittedBin() },
@@ -888,8 +886,7 @@ pub fn build(b: *std.Build) void {
         "system/drivers/usb-hid/hid-report.zig", // HID boot-report keyboard/mouse decode
         "system/drivers/usb-storage/bulk-only-transport.zig", // CBW/CSW wrapper sizes
         "system/drivers/usb-storage/scsi.zig", // SCSI CDB encodings (big-endian)
-        "system/services/vfs/path.zig", // mount-prefix path matching
+        "system/vfs-protocol.zig", // NodeKind / DirectoryEntry sizes + op values
-        "system/services/vfs/protocol.zig", // NodeKind / DirectoryEntry sizes + op values
         "system/services/fat/on-disk.zig", // FAT on-disk struct sizes + type detection
         "system/services/fat/engine.zig", // FAT read/write over a RAM-backed image
         "system/services/display/compositor.zig", // Rect math + fill/composite/blit-tile

library/runtime/fs.zig

@@ -1,5 +1,5 @@
 //! runtime.fs — the danos-native file API. A program opens, reads, writes, and
-//! lists files served by the user-space VFS (system/services/vfs), each call
+//! lists files through the kernel VFS root (resolve + redirect), each call
 //! marshalling a vfs-protocol request over IPC. This is the danos-native layer
 //! danos programs use directly; it is also where the file operations that later
 //! become `std.os.danos` are staged (see docs/zig-self-hosting.md). It replaces
@@ -12,6 +12,7 @@
 
 const std = @import("std");
 const ipc = @import("ipc.zig");
+const system = @import("system.zig");
 const protocol = @import("vfs-protocol");
 
 /// The kind of a filesystem node — re-exported so a caller need not import the
@@ -60,23 +61,37 @@ pub const OpenOptions = struct {
     }
 };
 
-// The VFS server endpoint, looked up once by well-known id and cached.
+// The route to a path: the kernel resolves (fs_resolve) and either serves the
-var vfs_handle: ipc.Handle = 0;
+// node itself (the initrd at /system — a permanent token) or redirects us to
-var vfs_resolved = false;
+// the owning filesystem backend's endpoint, to which we speak the vfs-protocol
-fn vfs() ?ipc.Handle {
+// rendezvous directly with the rewritten mount-relative path.
-    if (!vfs_resolved) {
+const Route = union(enum) {
-        vfs_handle = ipc.lookup(.vfs) orelse return null;
+    kernel: u64,
-        vfs_resolved = true;
+    backend: struct { handle: ipc.Handle, path: [224]u8, path_len: usize },
+
+    fn backendPath(self: *const Route) []const u8 {
+        return self.backend.path[0..self.backend.path_len];
+    }
+};
+
+fn resolve(path: []const u8, flags: usize) ?Route {
+    var out: [224]u8 = undefined;
+    const route = system.fsResolve(path, flags, &out) orelse return null;
+    switch (route) {
+        .kernel => |token| return .{ .kernel = token },
+        .backend => |b| {
+            var r: Route = .{ .backend = .{ .handle = b.handle, .path = undefined, .path_len = b.path_len } };
+            @memcpy(r.backend.path[0..b.path_len], out[0..b.path_len]);
+            return r;
+        },
     }
-    return vfs_handle;
 }
 
 const Result = struct { reply: protocol.Reply, payload: []u8 };
 
-// One request/reply round trip: [Request header][send payload] -> VFS ->
+// One request/reply round trip: [Request header][send payload] -> backend ->
 // [Reply header][receive payload]. The receive payload lands in `out`.
-fn transact(request: protocol.Request, send: []const u8, out: []u8) ?Result {
+fn transact(h: ipc.Handle, request: protocol.Request, send: []const u8, out: []u8) ?Result {
-    const h = vfs() orelse return null;
     var message: [protocol.message_maximum]u8 = undefined;
     @memcpy(message[0..protocol.request_size], std.mem.asBytes(&request));
     const slen = @min(send.len, protocol.maximum_payload);
@@ -95,13 +110,21 @@ fn transact(request: protocol.Request, send: []const u8, out: []u8) ?Result {
 pub const File = struct {
     node: u64,
     offset: u64 = 0,
+    /// The owning backend's endpoint, or null for a kernel-served node (the
+    /// read-only /system tree), whose `node` is a permanent fs_node token.
+    backend: ?ipc.Handle = null,
 
     /// Read up to `buffer.len` bytes at the current offset; returns the count, or
     /// null on error.
     pub fn read(self: *File, buffer: []u8) ?usize {
+        const h = self.backend orelse {
+            const n = system.fsNodeRead(self.node, self.offset, buffer) orelse return null;
+            self.offset += n;
+            return n;
+        };
         const want: u32 = @intCast(@min(buffer.len, protocol.maximum_payload));
         const request = protocol.Request{ .operation = .read, .node = self.node, .offset = self.offset, .len = want, .flags = 0 };
-        const r = transact(request, &.{}, buffer) orelse return null;
+        const r = transact(h, request, &.{}, buffer) orelse return null;
         if (r.reply.status != 0) return null;
         self.offset += r.reply.len;
         return r.reply.len;
@@ -109,11 +132,13 @@ pub const File = struct {
 
     /// Write `data` at the current offset; returns the count written. A single
     /// call is capped at the VFS payload size, so the return may be short — use
-    /// `writeAll` to write the whole slice. Null on error.
+    /// `writeAll` to write the whole slice. Null on error (kernel-served nodes
+    /// are read-only).
     pub fn write(self: *File, data: []const u8) ?usize {
+        const h = self.backend orelse return null;
         const want: u32 = @intCast(@min(data.len, protocol.maximum_payload));
         const request = protocol.Request{ .operation = .write, .node = self.node, .offset = self.offset, .len = want, .flags = 0 };
-        const r = transact(request, data[0..want], &.{}) orelse return null;
+        const r = transact(h, request, data[0..want], &.{}) orelse return null;
         if (r.reply.status != 0) return null;
         self.offset += r.reply.len;
         return r.reply.len;
@@ -138,27 +163,40 @@ pub const File = struct {
 
     /// This file's metadata.
     pub fn attributes(self: *File) ?Attributes {
+        const h = self.backend orelse {
+            const a = system.fsNodeStatus(self.node) orelse return null;
+            return .{ .size = a.size, .kind = if (a.kind == system.file_kind_directory) .directory else .regular, .mtime = a.mtime };
+        };
         const request = protocol.Request{ .operation = .status, .node = self.node, .offset = 0, .len = 0, .flags = 0 };
         var buffer: [@sizeOf(protocol.FileStatus)]u8 = undefined;
-        const r = transact(request, &.{}, &buffer) orelse return null;
+        const r = transact(h, request, &.{}, &buffer) orelse return null;
         if (r.reply.status != 0 or r.payload.len < @sizeOf(protocol.FileStatus)) return null;
         const status = std.mem.bytesToValue(protocol.FileStatus, buffer[0..@sizeOf(protocol.FileStatus)]);
         return .{ .size = status.size, .kind = kindFromWire(status.kind), .mtime = status.mtime };
     }
 
-    /// Release the VFS's open handle for this file.
+    /// Release the backend's open handle for this file. Kernel-served node
+    /// tokens are permanent — nothing to release.
     pub fn close(self: *File) void {
+        const h = self.backend orelse return;
         const request = protocol.Request{ .operation = .close, .node = self.node, .offset = 0, .len = 0, .flags = 0 };
-        _ = transact(request, &.{}, &.{});
+        _ = transact(h, request, &.{}, &.{});
     }
 };
 
 /// Open (or create, with `.create`) `path`. Returns the open file, or null.
 pub fn open(path: []const u8, options: OpenOptions) ?File {
-    const request = protocol.Request{ .operation = .open, .node = 0, .offset = 0, .len = @intCast(path.len), .flags = options.wireFlags() };
+    const route = resolve(path, options.wireFlags()) orelse return null;
-    const r = transact(request, path, &.{}) orelse return null;
+    switch (route) {
+        .kernel => |token| return .{ .node = token, .backend = null },
+        .backend => |b| {
+            const relative = route.backendPath();
+            const request = protocol.Request{ .operation = .open, .node = 0, .offset = 0, .len = @intCast(relative.len), .flags = options.wireFlags() };
+            const r = transact(b.handle, request, relative, &.{}) orelse return null;
             if (r.reply.status != 0) return null;
-    return .{ .node = r.reply.node };
+            return .{ .node = r.reply.node, .backend = b.handle };
+        },
+    }
 }
 
 /// A path's metadata without keeping it open (open -> status -> close).
@@ -190,13 +228,27 @@ pub const Entry = struct {
 pub const Directory = struct {
     node: u64,
     cursor: u64 = 0,
+    backend: ?ipc.Handle = null,
 
     /// Fill `entry` with the next directory entry; false at end of directory or
     /// on error.
     pub fn next(self: *Directory, entry: *Entry) bool {
+        const h = self.backend orelse {
+            var buffer: [@sizeOf(system.DirectoryEntryHeader) + 64]u8 = undefined;
+            const n = system.fsNodeReaddir(self.node, self.cursor, &buffer) orelse return false;
+            if (n < @sizeOf(system.DirectoryEntryHeader)) return false; // end
+            const header = std.mem.bytesToValue(system.DirectoryEntryHeader, buffer[0..@sizeOf(system.DirectoryEntryHeader)]);
+            entry.kind = if (header.kind == system.file_kind_directory) .directory else .regular;
+            entry.size = header.size;
+            const nlen = @min(@as(usize, header.name_len), entry.name_buffer.len);
+            @memcpy(entry.name_buffer[0..nlen], buffer[@sizeOf(system.DirectoryEntryHeader)..][0..nlen]);
+            entry.name_len = nlen;
+            self.cursor += 1;
+            return true;
+        };
         const request = protocol.Request{ .operation = .readdir, .node = self.node, .offset = self.cursor, .len = 0, .flags = 0 };
         var buffer: [protocol.message_maximum]u8 = undefined;
-        const r = transact(request, &.{}, &buffer) orelse return false;
+        const r = transact(h, request, &.{}, &buffer) orelse return false;
         if (r.reply.status != 0 or r.reply.len == 0) return false; // error or EOF
         if (r.payload.len < protocol.directory_entry_size) return false;
         const header = std.mem.bytesToValue(protocol.DirectoryEntry, r.payload[0..protocol.directory_entry_size]);
@@ -210,9 +262,9 @@ pub const Directory = struct {
         return true;
     }
 
-    /// Release the VFS's open handle for this directory.
+    /// Release the backend's open handle for this directory.
     pub fn close(self: *Directory) void {
-        var f = File{ .node = self.node };
+        var f = File{ .node = self.node, .backend = self.backend };
         f.close();
     }
 };
@@ -220,13 +272,18 @@ pub const Directory = struct {
 /// Open `path` as a directory for listing. Returns null if it isn't one / on error.
 pub fn openDirectory(path: []const u8) ?Directory {
     const file = open(path, .{ .directory = true }) orelse return null;
-    return .{ .node = file.node };
+    return .{ .node = file.node, .backend = file.backend };
 }
 
-// A path-based request that returns only a status (mkdir, unlink).
+// A path-based request that returns only a status (mkdir, unlink). Kernel-served
+// paths (the read-only /system) refuse mutation by construction: the resolve
+// must land on a backend.
 fn pathOperation(operation: protocol.Operation, path: []const u8) bool {
-    const request = protocol.Request{ .operation = operation, .node = 0, .offset = 0, .len = @intCast(path.len), .flags = 0 };
+    const route = resolve(path, 0) orelse return false;
-    const r = transact(request, path, &.{}) orelse return false;
+    if (route != .backend) return false;
+    const relative = route.backendPath();
+    const request = protocol.Request{ .operation = operation, .node = 0, .offset = 0, .len = @intCast(relative.len), .flags = 0 };
+    const r = transact(route.backend.handle, request, relative, &.{}) orelse return false;
     return r.reply.status == 0;
 }
 
@@ -261,33 +318,37 @@ pub fn remove(path: []const u8) bool {
     return pathOperation(.unlink, path);
 }
 
-/// Rename `old_path` to `new_path`. Both must be in the same directory (same-
+/// Rename `old_path` to `new_path`. Both must resolve to the SAME filesystem
-/// directory, 8.3-name rename only for now). Returns true on success.
+/// backend (same-directory, 8.3-name rename only for now). Returns true on
+/// success.
 pub fn rename(old_path: []const u8, new_path: []const u8) bool {
-    const total = old_path.len + 1 + new_path.len;
+    const old_route = resolve(old_path, 0) orelse return false;
+    const new_route = resolve(new_path, 0) orelse return false;
+    if (old_route != .backend or new_route != .backend) return false;
+    if (old_route.backend.handle != new_route.backend.handle) return false; // cross-filesystem
+    const old_relative = old_route.backendPath();
+    const new_relative = new_route.backendPath();
+    const total = old_relative.len + 1 + new_relative.len;
     if (total > protocol.maximum_payload) return false;
     var payload: [protocol.maximum_payload]u8 = undefined;
-    @memcpy(payload[0..old_path.len], old_path);
+    @memcpy(payload[0..old_relative.len], old_relative);
-    payload[old_path.len] = 0;
+    payload[old_relative.len] = 0;
-    @memcpy(payload[old_path.len + 1 ..][0..new_path.len], new_path);
+    @memcpy(payload[old_relative.len + 1 ..][0..new_relative.len], new_relative);
     const request = protocol.Request{ .operation = .rename, .node = 0, .offset = 0, .len = @intCast(total), .flags = 0 };
-    const r = transact(request, payload[0..total], &.{}) orelse return false;
+    const r = transact(old_route.backend.handle, request, payload[0..total], &.{}) orelse return false;
     return r.reply.status == 0;
 }
 
 /// Mount a filesystem backend (its server endpoint) at absolute path `target`;
-/// the VFS then routes everything under `target` to that backend. This is the one
+/// the kernel VFS then routes everything under `target` to that backend.
-/// call that hands the VFS a capability (the backend endpoint). Returns true on
+/// Possession of the endpoint handle is the capability. Returns true on success.
-/// success.
 pub fn mount(target: []const u8, backend: ipc.Handle) bool {
-    const h = vfs() orelse return false;
+    return system.fsMount(target, backend, "");
-    const request = protocol.Request{ .operation = .mount, .node = 0, .offset = 0, .len = @intCast(target.len), .flags = 0 };
+}
-    var message: [protocol.message_maximum]u8 = undefined;
+
-    @memcpy(message[0..protocol.request_size], std.mem.asBytes(&request));
+/// As `mount`, with a backend-side rewrite prefix: a path under `target` reaches
-    const tlen = @min(target.len, protocol.maximum_payload);
+/// the backend as `rewrite` + the mount-relative tail. How one volume serves two
-    @memcpy(message[protocol.request_size..][0..tlen], target[0..tlen]);
+/// mounts ("/mnt/usb" from its root, "/var" from its /var subtree).
-    var rbuf: [protocol.message_maximum]u8 = undefined;
+pub fn mountRewritten(target: []const u8, backend: ipc.Handle, rewrite: []const u8) bool {
-    const result = ipc.callCap(h, message[0 .. protocol.request_size + tlen], &rbuf, backend) catch return false;
+    return system.fsMount(target, backend, rewrite);
-    if (result.len < protocol.reply_size) return false;
-    return std.mem.bytesToValue(protocol.Reply, rbuf[0..protocol.reply_size]).status == 0;
 }

library/runtime/system.zig

@@ -32,6 +32,10 @@ pub const klog_record_magic = abi.klog_record_magic;
 pub const klog_flag_truncated = abi.klog_flag_truncated;
 pub const klog_maximum_message = abi.klog_maximum_message;
 pub const maximum_process_name = abi.maximum_process_name;
+pub const FileAttributes = abi.FileAttributes;
+pub const DirectoryEntryHeader = abi.DirectoryEntryHeader;
+pub const file_kind_regular = abi.file_kind_regular;
+pub const file_kind_directory = abi.file_kind_directory;
 
 /// Write raw bytes to the kernel log (bring-up/panic diagnostics; ordinary
 /// output goes through std.log -> writeRecord). The kernel stamps the record
@@ -100,6 +104,72 @@ pub fn klogStatus() ?KlogStatus {
     return status;
 }
 
+/// Where fs_resolve routed a path: served by the kernel (a permanent node
+/// token for fs_node) or by a userspace filesystem backend (an endpoint handle
+/// plus the rewritten mount-relative path, returned in the caller's buffer).
+pub const FsRoute = union(enum) {
+    kernel: u64,
+    backend: struct { handle: usize, path_len: usize },
+};
+
+/// Route `path` through the kernel VFS. For a backend route the rewritten
+/// mount-relative path lands in `out` (behind a kernel-written length prefix,
+/// already stripped here: out[0..path_len] is the path).
+pub fn fsResolve(path: []const u8, flags: usize, out: []u8) ?FsRoute {
+    var rax: usize = undefined;
+    var rdx: usize = flags; // in: flags (arg #3); out: node token / backend handle
+    asm volatile ("syscall"
+        : [rax] "={rax}" (rax),
+          [rdx] "+{rdx}" (rdx),
+        : [n] "{rax}" (@intFromEnum(abi.SystemCall.fs_resolve)),
+          [a0] "{rdi}" (@intFromPtr(path.ptr)),
+          [a1] "{rsi}" (path.len),
+          [a3] "{r10}" (@intFromPtr(out.ptr)),
+          [a4] "{r8}" (out.len),
+        : .{ .rcx = true, .r11 = true, .memory = true });
+    if (@as(isize, @bitCast(rax)) < 0) return null;
+    if (rax == abi.fs_route_kernel) return .{ .kernel = rdx };
+    if (rax != abi.fs_route_backend) return null;
+    const path_len = @as(usize, out[0]) | (@as(usize, out[1]) << 8);
+    if (path_len + 2 > out.len) return null;
+    std.mem.copyForwards(u8, out[0..path_len], out[2..][0..path_len]);
+    return .{ .backend = .{ .handle = rdx, .path_len = path_len } };
+}
+
+/// Read `out.len` bytes of a kernel-served node at `offset` (fs_node read).
+pub fn fsNodeRead(node_token: u64, offset: u64, out: []u8) ?usize {
+    const r = sc.systemCall5(.fs_node, abi.fs_node_read, node_token, offset, @intFromPtr(out.ptr), out.len);
+    if (@as(isize, @bitCast(r)) < 0) return null;
+    return r;
+}
+
+/// A kernel-served node's metadata (fs_node status).
+pub fn fsNodeStatus(node_token: u64) ?abi.FileAttributes {
+    var attributes: abi.FileAttributes = undefined;
+    const r = sc.systemCall5(.fs_node, abi.fs_node_status, node_token, 0, @intFromPtr(&attributes), @sizeOf(abi.FileAttributes));
+    if (@as(isize, @bitCast(r)) < 0) return null;
+    return attributes;
+}
+
+/// The `cursor`th child of a kernel-served directory (fs_node readdir): fills
+/// `out` with [DirectoryEntryHeader][name]; returns total bytes (0 = end).
+pub fn fsNodeReaddir(node_token: u64, cursor: u64, out: []u8) ?usize {
+    const r = sc.systemCall5(.fs_node, abi.fs_node_readdir, node_token, cursor, @intFromPtr(out.ptr), out.len);
+    if (@as(isize, @bitCast(r)) < 0) return null;
+    return r;
+}
+
+/// Mount a userspace filesystem's endpoint at `prefix`, with an optional
+/// backend-side `rewrite` prefix ("" = none). Possession of the endpoint
+/// handle is the capability.
+pub fn fsMount(prefix: []const u8, backend: usize, rewrite: []const u8) bool {
+    return sc.systemCall5(.fs_mount, @intFromPtr(prefix.ptr), prefix.len, backend, @intFromPtr(rewrite.ptr), rewrite.len) == 0;
+}
+
+pub fn fsUnmount(prefix: []const u8) bool {
+    return sc.systemCall2(.fs_unmount, @intFromPtr(prefix.ptr), prefix.len) == 0;
+}
+
 /// End the process. Never returns.
 pub fn exit(code: usize) noreturn {
     _ = sc.systemCall1(.exit, code);

system/abi.zig

@@ -282,7 +282,7 @@ pub const KlogStatus = extern struct {
 /// ipc_register/ipc_lookup). Small integers, so no string interning is needed
 /// during bring-up. The VFS server registers under `vfs`; clients look it up.
 pub const ServiceId = enum(u32) {
-    vfs = 1,
+    vfs = 1, // RETIRED: the router moved into the kernel (fs_resolve); the slot stays reserved
     input = 2,
     ps2_bus = 3, // the 8042 owner; child device drivers attach here for raw bytes
     device_manager = 4, // the tree, the matcher, the supervisor (docs/device-manager.md)

system/kernel/process.zig

@@ -1309,8 +1309,7 @@ fn systemKlogStatus(state: *architecture.CpuState) void {
 /// through the kernel mount table (docs/vfs-protocol.md). Kernel-served ->
 /// rax=fs_route_kernel, rdx=node token. Backend-served -> rax=fs_route_backend,
 /// rdx=an endpoint handle in the caller's table (deduplicated), and the
-/// rewritten mount-relative path copied to `out` with its length in the third
+/// rewritten mount-relative path copied into `out` behind a u16 length prefix. Fails for unknown paths, create-intent on /system, or an
-/// result register. Fails for unknown paths, create-intent on /system, or an
 /// undersized out buffer.
 fn systemFsResolve(state: *architecture.CpuState) void {
     const path_ptr = architecture.systemCallArg(state, 0);
@@ -1331,14 +1330,18 @@ fn systemFsResolve(state: *architecture.CpuState) void {
             architecture.setSystemCallResult2(state, node_token);
         },
         .backend => |*backend| {
-            if (backend.path_len > out_cap) return fail(state);
+            // The rewritten path goes back in the out buffer behind a u16
+            // length prefix (a third result register would collide with r8's
+            // argument role in the userspace stub).
+            if (backend.path_len + 2 > out_cap) return fail(state);
             const handle = ipc.installHandleDeduped(t, backend.endpoint);
             if (handle < 0) return fail(state);
             const destination: [*]u8 = @ptrFromInt(out_ptr);
-            @memcpy(destination[0..backend.path_len], backend.path[0..backend.path_len]);
+            destination[0] = @intCast(backend.path_len & 0xFF);
+            destination[1] = @intCast(backend.path_len >> 8);
+            @memcpy(destination[2..][0..backend.path_len], backend.path[0..backend.path_len]);
             architecture.setSystemCallResult(state, abi.fs_route_backend);
             architecture.setSystemCallResult2(state, @intCast(handle));
-            architecture.setSystemCallResult3(state, backend.path_len);
         },
         .not_found => fail(state),
     }

system/kernel/tests.zig

@@ -265,6 +265,31 @@ fn bufferHas(needle: []const u8) bool {
     return std.mem.indexOf(u8, process.write_buffer[0..process.write_len], needle) != null;
 }
 
+/// Substring search across the whole retained log ring (record payloads are
+/// contiguous in the stream, so a one-line needle always matches if present).
+/// Unlike `bufferHas` (the single LAST write), this survives busy-tree chatter.
+fn ringHas(needle: []const u8) bool {
+    var chunk: [1024]u8 = undefined;
+    var overlap: [128]u8 = undefined;
+    var overlap_len: usize = 0;
+    var offset = kernel_log.status().tail;
+    while (true) {
+        const n = kernel_log.readAt(offset, &chunk) orelse return false;
+        if (n == 0) return false;
+        offset += n;
+        // Search the previous tail glued to this chunk, then the chunk itself.
+        if (overlap_len != 0) {
+            var glued: [1152]u8 = undefined;
+            @memcpy(glued[0..overlap_len], overlap[0..overlap_len]);
+            const m = @min(n, glued.len - overlap_len);
+            @memcpy(glued[overlap_len..][0..m], chunk[0..m]);
+            if (std.mem.indexOf(u8, glued[0 .. overlap_len + m], needle) != null) return true;
+        } else if (std.mem.indexOf(u8, chunk[0..n], needle) != null) return true;
+        overlap_len = @min(n, @min(overlap.len, needle.len));
+        @memcpy(overlap[0..overlap_len], chunk[n - overlap_len ..][0..overlap_len]);
+    }
+}
+
 /// How many `pci_device` functions the devices broker currently holds. A durable
 /// snapshot, unlike a `bufferHas` poll of the single-latest write_buffer line, so a
 /// test can wait on it without racing transient log output. `scratch` is
@@ -2120,11 +2145,11 @@ fn claimReleaseTest(boot_information: *const BootInformation) void {
     result();
 }
 
-/// M17.3: the published exit events, proven by their first subscriber. The VFS
+/// M17.3: the published exit events, proven by a stateful server. The fat
-/// subscribes at startup; a client opens a file and parks holding the handle;
+/// server subscribes at startup; a client opens a file on the volume and parks
-/// the kill posts the exit event to the VFS's endpoint; the VFS releases the
+/// holding the handle; the kill posts the exit event to fat's endpoint; fat
-/// dead client's handle and says so — the service-side mirror of iron rule 1
+/// releases the dead client's handle and says so — the service-side mirror of
-/// (a service must never depend on clients cleaning up after themselves).
+/// iron rule 1 (a service must never depend on clients cleaning up).
 fn vfsClientDeathTest(boot_information: *const BootInformation) void {
     log("DANOS-TEST-BEGIN: vfs-client-death\n", .{});
     if (boot_information.initial_ramdisk_len == 0) {
@@ -2140,7 +2165,11 @@ fn vfsClientDeathTest(boot_information: *const BootInformation) void {
     };
 
     process.write_count = 0;
-    check("vfs spawned", spawnNamed(rd, "vfs"));
+    // The full tree: the storage chain must come up for /mnt/usb to exist —
+    // the fat server (not a router) now owns client file state and its sweep.
+    process.setInitialRamdisk(image);
+    const init_ok = if (process.spawnBundled("/system/services/init")) true else |_| false;
+    check("init spawned (boots the storage chain)", init_ok);
 
     const me = scheduler.currentId();
     const endpoint = ipcsync.createIpcEndpoint() orelse {
@@ -2158,16 +2187,18 @@ fn vfsClientDeathTest(boot_information: *const BootInformation) void {
     }
     check("parked client spawned (supervised)", client != 0);
 
-    // Its heartbeat is the fence: once it beats, the handle is open.
+    // Its heartbeat is the fence: once it beats, the handle is open. The park
+    // waits out the whole USB->block->fat chain, so give it room; with the full
+    // tree chattering, the ring (not the last-write buffer) is the evidence.
     const parked = "vfstest: parked";
     scheduler.setPriority(1);
-    var deadline = architecture.millis() + 10000;
+    var deadline = architecture.millis() + 30000;
     while (architecture.millis() < deadline) {
-        if (bufferHas(parked)) break;
+        if (ringHas(parked)) break;
         scheduler.yield();
     }
     scheduler.setPriority(4);
-    check("client parked holding an open handle", bufferHas(parked));
+    check("client parked holding an open handle", ringHas(parked));
 
     check("the kill is accepted", process.killProcess(me, client) == 0);
     var badge: u64 = 0;
@@ -2175,16 +2206,17 @@ fn vfsClientDeathTest(boot_information: *const BootInformation) void {
     _ = ipcsync.replyWait(endpoint, 0, 0, 0, 0, abi.no_cap, &badge, &received_cap);
     check("the exit notification arrived", badge == abi.notify_badge_bit | abi.notify_exit_bit | client);
 
-    // The VFS heard the same published event; its release line is the proof.
+    // The fat server heard the same published event; its release line in the
+    // ring is the proof.
     const released = "released 1 handle(s) for dead client";
     scheduler.setPriority(1);
     deadline = architecture.millis() + 10000;
     while (architecture.millis() < deadline) {
-        if (bufferHas(released)) break;
+        if (ringHas(released)) break;
         scheduler.yield();
     }
     scheduler.setPriority(4);
-    check("the VFS released the dead client's handle", bufferHas(released));
+    check("the fat server released the dead client's handle", ringHas(released));
     result();
 }
 
@@ -2683,9 +2715,10 @@ fn vfsTest(boot_information: *const BootInformation) void {
 
     process.write_count = 0;
     process.write_from_user = false;
-    // Spawn just the server and its client (other initial_ramdisk binaries would write to
+    // Seed the kernel VFS (/system) — the router the client exercises.
-    // the shared evidence buffer and confuse the marker check).
+    process.setInitialRamdisk(image);
-    _ = spawnNamed(rd, "vfs");
+    // Spawn just the client: the kernel itself is the VFS root it exercises
+    // (resolve + fs_node over /system through the plain runtime.fs API).
     _ = spawnNamed(rd, "vfs-test");
 
     // Wait for the client's success heartbeat (it round-trips, then beats ~1/s).

system/services/fat/fat.zig

@@ -101,18 +101,42 @@ fn initialise(endpoint: runtime.ipc.Handle) bool {
     };
     std.log.info("mounted FAT ({s}, {d} clusters, partition lba {d})", .{ @tagName(filesystem.geometry.fat_type), filesystem.geometry.cluster_count, filesystem.base_lba });
 
-    // Mount ourselves into the VFS namespace at /mnt/usb (retry while the VFS
+    // With the router in the kernel, clients hold OUR node ids directly; sweep
-    // comes up). From here the VFS routes /mnt/usb/... to this server.
+    // a dead client's open handles via the published exit events (the pattern
-    var tries: u32 = 0;
+    // the old userspace router used for its own table).
-    while (tries < 100) : (tries += 1) {
+    _ = runtime.process.subscribeExits(endpoint);
+
+    // Mount ourselves into the kernel VFS at /mnt/usb — and serve /var from the
+    // volume's /var subtree, so FHS paths (the logger's /var/log) stay decoupled
+    // from which volume carries them. A mount is one syscall now; no retry
+    // needed (the kernel's table exists before any service).
     if (runtime.fs.mount(mount_point, endpoint)) {
         std.log.info("mounted {s}", .{mount_point});
+    } else {
+        _ = runtime.system.write("/system/services/fat: could not mount /mnt/usb\n");
+    }
+    if (runtime.fs.mountRewritten("/var", endpoint, "/var")) {
+        std.log.info("mounted /var", .{});
+    } else {
+        _ = runtime.system.write("/system/services/fat: could not mount /var\n");
+    }
     return true;
+}
+
+/// A subscribed process-exit event: release every open handle the dead client
+/// held, so a crashed reader can't pin table slots (or, later, locks).
+fn onNotification(badge: u64) void {
+    const got = runtime.ipc.Received{ .len = 0, .badge = badge, .cap = null };
+    if (!got.isChildExit()) return;
+    const dead = got.childProcessId();
+    var released: u32 = 0;
+    for (&open_nodes) |*o| {
+        if (o.used and o.owner == dead) {
+            o.* = .{};
+            released += 1;
         }
-        runtime.system.sleep(50);
     }
-    _ = runtime.system.write("/system/services/fat: could not mount into the VFS\n");
+    if (released != 0) std.log.info("released {d} handle(s) for dead client {d}", .{ released, dead });
-    return true; // still serve directly, even if the namespace mount didn't take
 }
 
 const ParentLeaf = struct { parent: []const u8, leaf: []const u8 };
@@ -127,7 +151,7 @@ fn splitParent(path: []const u8) ParentLeaf {
     };
 }
 
-fn handleOpen(out: []u8, path: []const u8, flags: u32) usize {
+fn handleOpen(out: []u8, path: []const u8, flags: u32, sender: u32) usize {
     var node = filesystem.resolve(path);
     if (node == null and flags & protocol.create != 0) {
         const split = splitParent(path);
@@ -141,13 +165,12 @@ fn handleOpen(out: []u8, path: []const u8, flags: u32) usize {
         filesystem.truncate(&resolved);
     }
     const index = allocOpen() orelse return fail(out);
-    open_nodes[index] = .{ .used = true, .node = resolved };
+    open_nodes[index] = .{ .used = true, .node = resolved, .owner = sender };
     return writeReply(out, .{ .status = 0, .node = index }, &.{});
 }
 
 fn onMessage(message: []const u8, out: []u8, sender: u32, capability: ?runtime.ipc.Handle) usize {
     _ = capability;
-    _ = sender;
     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..];
@@ -157,7 +180,7 @@ fn onMessage(message: []const u8, out: []u8, sender: u32, capability: ?runtime.i
     filesystem.current_time_epoch = runtime.system.wallClock();
 
     switch (request.operation) {
-        .open => return handleOpen(out, payload[0..@min(payload.len, request.len)], request.flags),
+        .open => return handleOpen(out, payload[0..@min(payload.len, request.len)], request.flags, sender),
         .read => {
             const o = openAt(request.node) orelse return fail(out);
             var buffer: [protocol.maximum_payload]u8 = undefined;
@@ -237,5 +260,6 @@ pub fn main() void {
         .service = .fat,
         .init = initialise,
         .on_message = onMessage,
+        .on_notification = onNotification,
     });
 }

system/services/init/init.zig

@@ -28,7 +28,6 @@ const build_options = @import("build_options");
 /// future init reads this from a manifest under /system/services instead of a
 /// hardcoded list.)
 const boot_services = [_][]const u8{
-    "/system/services/vfs",
     "/system/services/input",
     "/system/services/device-manager",
     "/system/services/fat",

system/services/logger/logger.zig

@@ -35,9 +35,11 @@ const runtime = @import("runtime");
 const system = runtime.system;
 const fs = runtime.fs;
 
-/// Where log trees live. Flips to "/var/log" when the kernel VFS routes /var
+/// Where log trees live: the FHS path. The kernel VFS routes /var to whatever
-/// to the flash volume (M-G); today the FAT service mounts at /mnt/usb only.
+/// volume the fat server mounted there (today: the /var subtree of the USB
-const base = "/mnt/usb/var/log";
+/// flash volume) — swapping the persistent medium later touches fat's two
+/// mount calls, never this constant.
+const base = "/var/log";
 
 /// Drain cadence and the quiet period after which files are closed (flushed).
 const tick_ms = 250;
@@ -119,9 +121,9 @@ fn onTerminate() void {
 
 fn tick() void {
     if (!storage_ready) {
-        // Probe the mount; the ring buffers until it appears. `exists` on the
+        // makePath doubles as the readiness probe: while /var is unmounted the
-        // mount root is the documented readiness check.
+        // resolve fails fast (no storage round trip) and the ring buffers; the
-        if (!fs.exists("/mnt/usb")) return;
+        // first success creates the whole per-boot tree.
         if (!fs.makePath(boot_directory[0..boot_directory_len])) return;
         storage_ready = true;
         if (!announced) {

system/services/vfs-test/vfs-test.zig

@@ -0,0 +1,89 @@
+//! /system/tests/vfs-test — a ring-3 client that proves the kernel VFS end to
+//! end through the plain `runtime.fs` API: resolve its OWN binary under the
+//! kernel-served /system mount, check its metadata, read its ELF magic, and
+//! list /system/services. On success it heartbeats "vfstest: ok" so the kernel
+//! test can observe it; on failure it reports what went wrong.
+//!
+//! The "park" role (the fat-client-death test): open a file on the FAT volume,
+//! then hold the handle forever without closing — the kill and the fat
+//! server's release-on-death sweep are the point.
+
+const std = @import("std");
+const runtime = @import("runtime");
+const fs = runtime.fs;
+
+pub fn main(init: runtime.process.Init) void {
+    if (init.arguments.count > 1) {
+        park();
+        return;
+    }
+
+    // Our own binary, resolved through the kernel mount table.
+    const self_path = "/system/tests/vfs-test";
+    var file = fs.open(self_path, .{}) orelse {
+        _ = runtime.system.write("vfstest: open of own binary failed\n");
+        return;
+    };
+    defer file.close();
+
+    const attributes = file.attributes() orelse {
+        _ = runtime.system.write("vfstest: attributes failed\n");
+        return;
+    };
+    if (attributes.kind != .regular or attributes.size == 0) {
+        _ = runtime.system.write("vfstest: bad attributes\n");
+        return;
+    }
+
+    var header: [4]u8 = undefined;
+    const n = file.read(&header) orelse 0;
+    if (n != 4 or header[0] != 0x7f or header[1] != 'E' or header[2] != 'L' or header[3] != 'F') {
+        _ = runtime.system.write("vfstest: ELF magic mismatch\n");
+        return;
+    }
+
+    // The write refusal: /system is read-only by construction.
+    if (file.write("x") != null or fs.open("/system/tests/new-file", .{ .create = true }) != null) {
+        _ = runtime.system.write("vfstest: /system accepted a write\n");
+        return;
+    }
+
+    // Listing: /system/services contains init.
+    var saw_init = false;
+    if (fs.openDirectory("/system/services")) |listing| {
+        var directory = listing;
+        defer directory.close();
+        var entry: fs.Entry = .{};
+        while (directory.next(&entry)) {
+            if (std.mem.eql(u8, entry.name(), "init")) saw_init = true;
+        }
+    }
+    if (!saw_init) {
+        _ = runtime.system.write("vfstest: /system/services listing missed init\n");
+        return;
+    }
+
+    while (true) {
+        _ = runtime.system.write("vfstest: ok\n");
+        runtime.system.sleep(1000);
+    }
+}
+
+fn park() void {
+    // The storage chain (usb -> block -> fat -> mounts) takes a few seconds;
+    // retry until the volume appears.
+    var parked: ?fs.File = null;
+    var tries: u32 = 0;
+    while (parked == null and tries < 1000) : (tries += 1) {
+        parked = fs.open("/mnt/usb/parked", .{ .create = true });
+        if (parked == null) runtime.system.sleep(20);
+    }
+    if (parked == null) {
+        _ = runtime.system.write("vfstest: park open failed\n");
+        return;
+    }
+    while (true) {
+        _ = runtime.system.write("vfstest: parked\n");
+        runtime.system.sleep(500);
+    }
+}

system/services/vfs/path.zig

@@ -1,39 +0,0 @@
-//! Pure path utilities for the VFS mount router — no IPC, no state, so they are
-//! host-testable in isolation. The router uses these to decide whether an opened
-//! path lies under a mount point and, if so, what it looks like relative to that
-//! mount.
-
-const std = @import("std");
-
-/// If `path` lies under `mount_prefix` — equal to it, or the prefix followed by a
-/// path separator — return the path relative to the mount ("/" for an exact
-/// match, otherwise the tail beginning with '/'). Returns null when `path` is not
-/// under the mount, so a prefix like "/mnt/usb" never captures "/mnt/usbextra".
-pub fn underMount(path: []const u8, mount_prefix: []const u8) ?[]const u8 {
-    if (path.len < mount_prefix.len) return null;
-    if (!std.mem.eql(u8, path[0..mount_prefix.len], mount_prefix)) return null;
-    if (path.len == mount_prefix.len) return "/";
-    if (path[mount_prefix.len] != '/') return null;
-    return path[mount_prefix.len..];
-}
-
-/// Whether `path` is absolute (rooted at '/'). Bare names — what the flat ramfs
-/// uses — are relative and never route through a mount.
-pub fn isAbsolute(path: []const u8) bool {
-    return path.len > 0 and path[0] == '/';
-}
-
-test "underMount matches only at path boundaries" {
-    try std.testing.expectEqualStrings("/", underMount("/mnt/usb", "/mnt/usb").?);
-    try std.testing.expectEqualStrings("/system/kernel", underMount("/mnt/usb/system/kernel", "/mnt/usb").?);
-    try std.testing.expect(underMount("/mnt/usbextra", "/mnt/usb") == null); // not a boundary
-    try std.testing.expect(underMount("/mnt", "/mnt/usb") == null); // shorter than the prefix
-    try std.testing.expect(underMount("/other", "/mnt/usb") == null);
-    try std.testing.expect(underMount("greeting", "/mnt/usb") == null); // a bare name
-}
-
-test "isAbsolute distinguishes paths from bare names" {
-    try std.testing.expect(isAbsolute("/mnt/usb"));
-    try std.testing.expect(!isAbsolute("greeting"));
-    try std.testing.expect(!isAbsolute(""));
-}

system/services/vfs/vfs-test.zig

@@ -1,62 +0,0 @@
-//! /system/services/vfs/vfs-test — a client that proves the VFS round trip end to end: open a
-//! file through the `runtime.fs` file API, write to it, seek back, read it, and compare.
-//! On success it heartbeats "vfstest: ok" so the kernel test can observe it;
-//! on failure it reports what went wrong. Shipped in the initial_ramdisk alongside vfs.
-
-const std = @import("std");
-const runtime = @import("runtime");
-const fs = runtime.fs;
-
-pub fn main(init: runtime.process.Init) void {
-    const payload = "hello-vfs";
-
-    // The "park" role (the vfs-client-death test): open a file, then hold the
-    // handle forever without closing — the kill and the VFS's release-on-death
-    // are the point.
-    if (init.arguments.count > 1) {
-        var parked: ?fs.File = null;
-        var tries: u32 = 0;
-        while (parked == null and tries < 200) : (tries += 1) {
-            parked = fs.open("parked", .{ .create = true });
-            if (parked == null) runtime.system.sleep(20);
-        }
-        if (parked == null) {
-            _ = runtime.system.write("vfstest: park open failed\n");
-            return;
-        }
-        while (true) {
-            _ = runtime.system.write("vfstest: parked\n");
-            runtime.system.sleep(500);
-        }
-    }
-
-    // The VFS server may not have registered yet — retry open until it's up.
-    var opened: ?fs.File = null;
-    var tries: u32 = 0;
-    while (opened == null and tries < 200) : (tries += 1) {
-        opened = fs.open("greeting", .{ .create = true });
-        if (opened == null) runtime.system.sleep(20);
-    }
-    var greeting = opened orelse {
-        _ = runtime.system.write("vfstest: open failed\n");
-        return;
-    };
-
-    if ((greeting.write(payload) orelse 0) != payload.len) {
-        _ = runtime.system.write("vfstest: write failed\n");
-        return;
-    }
-    greeting.seekTo(0);
-
-    var buffer: [32]u8 = undefined;
-    const n = greeting.read(&buffer) orelse 0;
-    greeting.close();
-
-    if (n == payload.len and std.mem.eql(u8, buffer[0..n], payload)) {
-        while (true) {
-            _ = runtime.system.write("vfstest: ok\n");
-            runtime.system.sleep(1000);
-        }
-    }
-    _ = runtime.system.write("vfstest: mismatch\n");
-}

system/services/vfs/vfs.zig

@@ -1,389 +0,0 @@
-//! 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 }, &.{});
-}
-
-// --- 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;
-            std.log.info("remounted {s}", .{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;
-            std.log.info("mounted {s}", .{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;
-            std.log.info("unmounted {s}", .{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) std.log.info("released {d} handle(s) for dead client {d}", .{ 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,
-    });
-}

test/qemu_test.py

@@ -427,6 +427,7 @@ CASES = [
     # open handle, and the VFS releases it (process-lifecycle.md "Who learns of a death").
     {"name": "vfs-client-death",
      "smp":    4,
+     "timeout": 90,  # the park client waits out the whole USB->block->fat chain
      "expect": r"DANOS-TEST-RESULT: PASS",
      "fail":   r"DANOS-TEST-RESULT: FAIL"},
     # M17.4: signals over IPC — ping, reload, terminate (clean exit), the one-shot
@@ -562,7 +563,7 @@ CASES = [
      "smp":    4,
      "timeout": 150,
      "qmp_after": {"delay": 8, "command": "system_powerdown"},
-     "expect": r"logger: logging to /mnt/usb/var/log/\d{4}-\d{2}-\d{2}T\d{6}Z[\s\S]*"
+     "expect": r"logger: logging to /var/log/\d{4}-\d{2}-\d{2}T\d{6}Z[\s\S]*"
                r"init: shutting down[\s\S]*"
                r"logger: flushed through sequence \d+[\s\S]*"
                r"power: entering S5",