boot: the /system tree is the system image — loader-built ramdisk, spawn by path

Retire the build-time ramdisk packer and the packed initial-ramdisk.img.
make-fat-image.py now lays every user binary out at its FHS path on the
boot volume (system/services, system/drivers, system/tests), and the EFI
loader walks \system at boot, packing what it finds into an in-RAM v2
initial_ramdisk whose entry names are full FHS paths. init rides the
table like every other binary: its dedicated handoff fields are gone and
the kernel spawns PID 1 via the same lookup as everyone else
(process.spawnBundled).

system_spawn resolves names by exact path first, then unique basename,
and normalizes argv[0] to the stored path — so task names (and, next,
the tagged log ring's attribution) are honest binary paths everywhere.
initrd v2 rejects the old magic so a stale image fails loudly.

Groundwork for per-process logging (/var/log/<boot-stamp>/<binary-path>.log)
and the kernel-VFS /system mount.
This commit is contained in:
Daniel Samson
2026-07-21 14:47:26 +01:00
parent ec6e888076
commit 2d0858caf6
11 changed files with 413 additions and 324 deletions
+126 -43
View File
@@ -2,6 +2,7 @@ const std = @import("std");
const uefi = std.os.uefi;
const elf = std.elf;
const boot_handoff = @import("boot-handoff");
const initial_ramdisk = @import("initial-ramdisk");
const build_options = @import("build_options");
const BootInformation = boot_handoff.BootInformation;
const GraphicsOutput = uefi.protocol.GraphicsOutput;
@@ -15,11 +16,11 @@ const MemoryMapSlice = uefi.tables.MemoryMapSlice;
/// The kernel image: /system/kernel.
const kernel_file_name = std.unicode.utf8ToUtf16LeStringLiteral("system\\kernel");
/// The init program: /system/services/init.
const init_file_name = std.unicode.utf8ToUtf16LeStringLiteral("system\\services\\init");
/// The initial-ramdisk (the VFS server + drivers), in /boot.
const initial_ramdisk_file_name = std.unicode.utf8ToUtf16LeStringLiteral("boot\\initial-ramdisk.img");
/// The user binaries: everything under /system except the kernel itself. The
/// loader walks this tree and packs it into the in-RAM initial_ramdisk image —
/// the volume's file structure is the single source of truth (no packed image
/// artifact on disk).
const system_directory_name = std.unicode.utf8ToUtf16LeStringLiteral("system");
/// Physical page size, and the sentinel UEFI uses to seek to end-of-file.
const page_size = 4096;
@@ -64,20 +65,14 @@ fn boot() !noreturn {
const entry = try loadKernel(bs, &boot_information);
// Best effort: a volume without /system/services/init still boots (kernel-only).
loadInit(bs, &boot_information) catch |err| {
log("EFI: no /system/services/init (");
// Best effort: a volume without a /system tree of user binaries still boots
// (kernel-only). The tree — init included — becomes the initial_ramdisk.
loadSystemTree(bs, &boot_information) catch |err| {
log("EFI: no /system binaries (");
logBytes(@errorName(err));
log(") - booting without user space\r\n");
};
// Best effort: the initial_ramdisk (VFS server + drivers) is optional too.
loadInitialRamdisk(bs, &boot_information) catch |err| {
log("EFI: no initial_ramdisk (");
logBytes(@errorName(err));
log(")\r\n");
};
// Build the page tables the kernel starts life on: identity + a physmap of
// low RAM, plus the higher-half kernel image once it links high. Allocated
// now, while boot services (and the memory map) are still stable — nothing
@@ -369,11 +364,28 @@ fn handoff(cr3: u64, entry: usize, boot_information: *const BootInformation) nor
unreachable;
}
/// Read a whole file off the boot volume into a pool buffer that outlives the
/// loader. The buffer is deliberately NOT freed: it's LoaderData, which the
/// memory-map conversion classifies as reserved, so the kernel identity-maps it
/// and reads from there. Returns the buffer (pointer + length).
fn loadFile(bs: *uefi.tables.BootServices, name: [*:0]const u16) ![]u8 {
// --- the /system tree -> initial_ramdisk ------------------------------------
/// Cap on bundled binaries. Generous: the tree carries ~30 today.
const maximum_bundled = 64;
/// How deep the walk goes below /system ("/system/services/x" is depth 1).
const maximum_tree_depth = 3;
/// One binary discovered under /system: its FHS path (UTF-8, '/'-separated,
/// NUL-free) and its contents in a transient pool buffer.
const Bundled = struct {
path: [initial_ramdisk.maximum_name]u8,
path_len: usize,
data: []align(8) u8,
};
/// Walk the boot volume's /system tree and pack every regular file (except the
/// kernel image itself — the only top-level file) into an in-RAM v2
/// initial_ramdisk image, entries named by full FHS path. This is what makes the
/// volume's file structure the single source of truth: there is no packed
/// ramdisk artifact on disk, and init travels in the table like everything else.
fn loadSystemTree(bs: *uefi.tables.BootServices, boot_information: *BootInformation) !void {
const loaded = (try bs.handleProtocol(uefi.protocol.LoadedImage, uefi.handle)) orelse
return error.NoLoadedImage;
const device = loaded.device_handle orelse return error.NoBootDevice;
@@ -383,40 +395,111 @@ fn loadFile(bs: *uefi.tables.BootServices, name: [*:0]const u16) ![]u8 {
const root = try fs.openVolume();
defer _ = root.close() catch {};
const file = try root.open(name, .read, .{});
defer _ = file.close() catch {};
const system_directory = try root.open(system_directory_name, .read, .{});
defer _ = system_directory.close() catch {};
var list: [maximum_bundled]Bundled = undefined;
var count: usize = 0;
try walkDirectory(bs, system_directory, "/system", 0, &list, &count);
if (count == 0) return error.NoBinaries;
// Assemble the v2 image: header, entry table, then the blobs.
const table_end = @sizeOf(initial_ramdisk.Header) + count * @sizeOf(initial_ramdisk.Entry);
var total: usize = table_end;
for (list[0..count]) |e| total += e.data.len;
const image = try bs.allocatePool(.loader_data, total); // survives the handoff
std.mem.bytesAsValue(initial_ramdisk.Header, image[0..@sizeOf(initial_ramdisk.Header)]).* = .{
.magic = initial_ramdisk.magic,
.count = @intCast(count),
};
var offset: usize = table_end;
for (list[0..count], 0..) |e, i| {
var record = initial_ramdisk.Entry{ .name = @splat(0), .offset = offset, .len = e.data.len };
@memcpy(record.name[0..e.path_len], e.path[0..e.path_len]);
const slot = image[@sizeOf(initial_ramdisk.Header) + i * @sizeOf(initial_ramdisk.Entry) ..][0..@sizeOf(initial_ramdisk.Entry)];
std.mem.bytesAsValue(initial_ramdisk.Entry, slot).* = record;
@memcpy(image[offset..][0..e.data.len], e.data);
offset += e.data.len;
_ = bs.freePool(e.data.ptr) catch {};
}
boot_information.initial_ramdisk_base = @intFromPtr(image.ptr);
boot_information.initial_ramdisk_len = total;
progress("EFI: /system tree loaded\r\n");
}
/// Recursively collect the regular files below `directory` into `list`. Top-level
/// files (depth 0) are skipped: the only one is /system/kernel, which loadKernel
/// has already consumed and which is not a spawnable user binary.
fn walkDirectory(
bs: *uefi.tables.BootServices,
directory: *uefi.protocol.File,
prefix: []const u8,
depth: usize,
list: *[maximum_bundled]Bundled,
count: *usize,
) !void {
// Each read() on a directory yields one EFI_FILE_INFO; zero bytes means done.
var info_buffer: [1024]u8 align(8) = undefined;
while (true) {
const n = try directory.read(&info_buffer);
if (n == 0) return;
const info: *const uefi.protocol.File.Info.File = @ptrCast(@alignCast(&info_buffer));
const name16 = info.getFileName();
// Convert the (ASCII in practice) UTF-16 name; skip "." and "..".
var name_buffer: [initial_ramdisk.maximum_name]u8 = undefined;
var name_length: usize = 0;
while (name16[name_length] != 0) : (name_length += 1) {
if (name_length == name_buffer.len) return error.NameTooLong;
const c = name16[name_length];
if (c > 0x7F) return error.UnsupportedName;
name_buffer[name_length] = @intCast(c);
}
const name = name_buffer[0..name_length];
if (std.mem.eql(u8, name, ".") or std.mem.eql(u8, name, "..")) continue;
if (info.attribute.directory) {
if (depth == maximum_tree_depth) continue;
var child_prefix: [initial_ramdisk.maximum_name]u8 = undefined;
const child = try std.fmt.bufPrint(&child_prefix, "{s}/{s}", .{ prefix, name });
const child_directory = try directory.open(name16, .read, .{});
defer _ = child_directory.close() catch {};
try walkDirectory(bs, child_directory, child, depth + 1, list, count);
continue;
}
if (depth == 0) continue; // /system/kernel — already loaded, not bundled
if (count.* == maximum_bundled) return error.TooManyBinaries;
var entry: *Bundled = &list[count.*];
const path = try std.fmt.bufPrint(&entry.path, "{s}/{s}", .{ prefix, name });
entry.path_len = path.len;
const file = try directory.open(name16, .read, .{});
defer _ = file.close() catch {};
entry.data = try readWholeFile(bs, file);
count.* += 1;
}
}
/// Read an open file completely into a fresh pool buffer that survives the
/// handoff (LoaderData is classified reserved, so the kernel identity-maps it).
fn readWholeFile(bs: *uefi.tables.BootServices, file: *uefi.protocol.File) ![]align(8) u8 {
try file.setPosition(seek_end);
const size: usize = @intCast(try file.getPosition());
try file.setPosition(0);
if (size == 0) return error.EmptyFile;
const image = try bs.allocatePool(.loader_data, size); // survives the handoff
const buffer = try bs.allocatePool(.loader_data, size);
var read_total: usize = 0;
while (read_total < size) {
const n = try file.read(image[read_total..]);
const n = try file.read(buffer[read_total..]);
if (n == 0) return error.UnexpectedEof;
read_total += n;
}
return image[0..size];
}
/// Ferry the init program (/system/services/init) to the kernel. The kernel does the ELF
/// loading itself (into ring-3 mappings) — the loader just carries the bytes.
fn loadInit(bs: *uefi.tables.BootServices, boot_information: *BootInformation) !void {
const image = try loadFile(bs, init_file_name);
boot_information.init_base = @intFromPtr(image.ptr);
boot_information.init_len = image.len;
progress("EFI: /system/services/init loaded\r\n");
}
/// Ferry the initial_ramdisk (the VFS server + drivers) to the kernel, same as init.
fn loadInitialRamdisk(bs: *uefi.tables.BootServices, boot_information: *BootInformation) !void {
const image = try loadFile(bs, initial_ramdisk_file_name);
boot_information.initial_ramdisk_base = @intFromPtr(image.ptr);
boot_information.initial_ramdisk_len = image.len;
progress("EFI: initial_ramdisk loaded\r\n");
return buffer[0..size];
}
/// Validate the ELF, copy every PT_LOAD segment to its physical address, and