Files
danos/system/kernel/devices-broker.zig
T
Daniel Samson 452080e997 Add runtime.time, drop demo drivers, harden TSC timekeeping
Time is a kernel concern in danos: the kernel owns the scheduling timer and
already exposes monotonic time via the clock/sleep/timer_bind syscalls, so a
userspace time service would be a redundant, slower path. This adds the generic
runtime.time module over those syscalls, retires the two demonstration drivers,
reorganizes the milestone docs, and makes the monotonic clock correct on Intel,
AMD, and inside any VM.

runtime.time (library/runtime/time.zig)
- Instant/Duration interface: now, sleep, spin, after, monotonicNanos, available
- a thin layer over system.clock/sleep/timerOnce; unit-tested arithmetic

Remove the demo drivers hpet and bus (a teaching example belongs in the docs,
not shipped in the tree)
- system/drivers/ now holds only real drivers: pci-bus, ps2-bus, usb-xhci-bus
- device-manager end-to-end test repointed to pci-bus (asserts on kernel state:
  the process table and the device tree, not a racy serial marker)
- device_register containment moved to a new in-kernel `containment` test
- the driver-model worked example moved inline into docs/drivers.md

Reorganize milestone docs into topic docs
- m17-m18 / m19-m20 / m21 plans dissolved into process-lifecycle, device-manager,
  discovery, and acpi docs; new docs/power.md and docs/timers.md; ~20 citations
  repointed; plan docs deleted

TSC reliability (apic.zig, smp.zig, cpu.zig, kernel.zig)
- check the invariant-TSC bit (CPUID 0x80000007 EDX[8]) on Intel and AMD
- cross-core "warp" check at SMP bring-up, pairwise BSP<->AP as each core comes up
- fall back to the HPET clocksource when the TSC is not invariant (a bare VM) or
  not synchronized (a warp), switched continuously so time never jumps
- boot log reports the outcome; new tsc-sync test exercises the TSC + warp path

Verified: zig build; zig build test; 60/60 QEMU cases (incl. new containment and
tsc-sync).
2026-07-13 11:56:43 +01:00

226 lines
10 KiB
Zig

//! Device service: the kernel side of user-space driver access. At boot it
//! flattens the discovered device tree (src/device) into a stable, id-indexed
//! snapshot and a per-device claim table. User drivers enumerate the snapshot,
//! claim the device they own, and map its MMIO — the claim is the capability that
//! gates `mmio_map`/`irq_bind`, so a process can only ever touch hardware the
//! firmware-neutral device tree says it owns.
//!
//! The table is a **tree**: each entry carries its parent's id. Firmware discovery
//! seeds it, and a **bus driver** grows it — a process that has claimed a bus can
//! `register` children below it as it enumerates them (USB devices behind a hub, PCI
//! functions behind a bridge, comparators inside a timer block).
//!
//! Registration is where the capability model earns its keep. A `DeviceDescriptor` is, in
//! effect, a licence to map physical memory: whoever claims it may `mmio_map` its
//! `.memory` resources and `irq_bind` its `.irq` resources. If a bus driver could
//! invent arbitrary resources, it would invent one covering the kernel's RAM, claim
//! it, and map it. So `register` enforces **containment**: every resource of a child
//! must lie inside a resource of the same kind on its parent. A bus driver can only
//! ever subdivide what it was already given.
const std = @import("std");
const platform = @import("platform");
const device_abi = @import("device-abi");
const maximum_devices = 64;
/// Cap on children a single parent may have. A zero-resource child (legal — a USB
/// device is addressed through its controller, not by MMIO) sidesteps the containment
/// check, so without a bound a process that claimed one device could loop
/// `device_register` and exhaust the whole table, permanently denying it to every other
/// driver. This bounds the blast radius of one claim; a real quota (and a
/// `device_release` to reclaim on exit) is future work — see docs/driver-model.md.
const maximum_children_per_parent = 16;
var devices: [maximum_devices]device_abi.DeviceDescriptor = undefined;
var claimed: [maximum_devices]?u32 = .{null} ** maximum_devices; // owner task id, or null
var count: usize = 0;
/// Devices discovery found but the table had no room for. Non-zero means the machine
/// is bigger than `maximum_devices` and some hardware is simply invisible to drivers —
/// which would otherwise be an entirely silent failure. Logged at boot.
pub var dropped: usize = 0;
/// Snapshot the device tree into the flat table. Run once, right after discovery.
pub fn init(device_tree: *const platform.DeviceTree) void {
count = 0;
dropped = 0;
for (&claimed) |*c| c.* = null;
walk(device_tree.root, device_abi.no_parent);
}
/// Record `node` (unless it's the synthetic root) and recurse, threading the id we
/// assigned it down to its children as their parent.
fn walk(node: *platform.Device, parent_id: u64) void {
const id = if (node.class == .root) device_abi.no_parent else record(node, parent_id);
var child = node.first_child;
while (child) |c| : (child = c.next_sibling) walk(c, id);
}
fn record(node: *platform.Device, parent_id: u64) u64 {
if (count >= maximum_devices) {
dropped += 1;
return device_abi.no_parent; // children of a dropped node become roots, not orphans
}
var d = std.mem.zeroes(device_abi.DeviceDescriptor);
d.id = count;
d.parent = parent_id;
d.class = @intFromEnum(node.class);
d.pci_class = if (node.ids.pci_class) |code| code else device_abi.no_pci_class;
const h = node.hid();
d.hid_len = @min(h.len, d.hid.len);
@memcpy(d.hid[0..d.hid_len], h[0..d.hid_len]);
const rc = @min(node.resource_count, device_abi.maximum_device_resources);
d.resource_count = rc;
for (0..rc) |i| {
const r = node.resources[i];
d.resources[i] = .{ .kind = @intFromEnum(r.kind), .start = r.start, .len = r.len };
}
devices[count] = d;
count += 1;
return d.id;
}
/// Copy up to `out.len` device descriptors into `out`; returns the total count
/// available (which may exceed `out.len`).
pub fn enumerate(out: []device_abi.DeviceDescriptor) usize {
const n = @min(count, out.len);
@memcpy(out[0..n], devices[0..n]);
return count;
}
/// Take exclusive ownership of device `id` for task `owner`. Fails if the id is
/// out of range or already claimed.
pub fn claim(id: u64, owner: u32) bool {
if (id >= count) return false;
if (claimed[@intCast(id)] != null) return false;
claimed[@intCast(id)] = owner;
return true;
}
/// The task that owns device `id`, or null.
pub fn ownerOf(id: u64) ?u32 {
if (id >= count) return null;
return claimed[@intCast(id)];
}
/// Release every claim held by `owner` — called by the process layer on every
/// path out of a process (exit, fault, kill), so a restarted driver can claim its
/// hardware again (docs/process-lifecycle.md iron rule 1: cleanup is the kernel's
/// job). The devices stay in the table — they describe hardware, which did not go
/// away — only their ownership clears.
pub fn releaseAllOwnedBy(owner: u32) void {
for (claimed[0..count]) |*slot| {
if (slot.*) |o| {
if (o == owner) slot.* = null;
}
}
}
/// Resource `index` of device `id`, or null if out of range.
pub fn resourceOf(id: u64, index: u64) ?device_abi.ResourceDescriptor {
if (id >= count) return null;
const d = &devices[@intCast(id)];
if (index >= d.resource_count) return null;
return d.resources[@intCast(index)];
}
/// Is `child` wholly inside `parent`? For a range (memory, io_port, bus_range) that's
/// interval containment; for an irq it's equality, since an interrupt line is not
/// divisible. Zero-length child ranges are refused — an empty window is meaningless
/// and would otherwise vacuously "fit" anywhere.
fn contains(parent: device_abi.ResourceDescriptor, child: device_abi.ResourceDescriptor) bool {
if (parent.kind != child.kind) return false;
if (child.kind == @intFromEnum(device_abi.ResourceKind.irq)) {
// Range containment: an interrupt line is still indivisible (a child owns
// exactly one GSI), but a parent may own a *range* of lines so a broad
// owner — the acpi-tables node, whose firmware names any legacy IRQ —
// can contain its children's specific lines. A length-1 parent range is
// exactly the old equality rule, so existing single-IRQ parents are
// unaffected.
const span = if (parent.len == 0) 1 else parent.len;
return child.start >= parent.start and child.start < parent.start + span;
}
if (child.len == 0 or parent.len == 0) return false;
// No overflow: a resource that wraps the address space is not containable.
const child_end = std.math.add(u64, child.start, child.len) catch return false;
const parent_end = std.math.add(u64, parent.start, parent.len) catch return false;
return child.start >= parent.start and child_end <= parent_end;
}
pub const RegisterError = error{
NoSpace, // the device table is full
BadParent, // no such device, or not claimed by this task
TooManyResources,
TooManyChildren, // this parent is at maximum_children_per_parent
NotContained, // a child resource escapes its parent's window
};
/// Number of devices currently recorded with `parent_id` as their parent.
fn childCount(parent_id: u64) usize {
var n: usize = 0;
for (devices[0..count]) |d| {
if (d.parent == parent_id) n += 1;
}
return n;
}
/// Publish `descriptor` as a child of `parent_id`, on behalf of `owner`. Returns the new
/// device id. The child is left **unclaimed**, so another process (a class driver)
/// can claim it — that is how a bus hands a device to its driver.
///
/// `owner` must have claimed `parent_id`, and every resource in `descriptor` must be
/// contained in a parent resource of the same kind. A device with no resources is
/// fine and common: a USB device is addressed through its controller, not by MMIO.
pub fn register(parent_id: u64, owner: u32, descriptor: *const device_abi.DeviceDescriptor) RegisterError!u64 {
const parent_owner = ownerOf(parent_id) orelse return error.BadParent;
if (parent_owner != owner) return error.BadParent;
if (descriptor.resource_count > device_abi.maximum_device_resources) return error.TooManyResources;
if (childCount(parent_id) >= maximum_children_per_parent) return error.TooManyChildren;
if (count >= maximum_devices) return error.NoSpace;
const parent = &devices[@intCast(parent_id)];
for (0..@intCast(descriptor.resource_count)) |i| {
const r = descriptor.resources[i];
var ok = false;
for (0..@intCast(parent.resource_count)) |j| {
if (contains(parent.resources[j], r)) ok = true;
}
if (!ok) return error.NotContained;
}
// Idempotent on exact match (docs/device-manager.md): a restarted
// registering bus re-registers what it rediscovers, and the table has no
// unregister — an identical (class, identity, resources) child under the
// same parent returns the existing id instead of appending a duplicate.
for (devices[0..count]) |*existing| {
if (existing.parent != parent_id) continue;
if (existing.class != descriptor.class) continue;
if (existing.pci_class != descriptor.pci_class) continue;
if (existing.hid_len != descriptor.hid_len) continue;
if (!std.mem.eql(u8, existing.hid[0..@intCast(existing.hid_len)], descriptor.hid[0..@intCast(descriptor.hid_len)])) continue;
if (existing.resource_count != descriptor.resource_count) continue;
var same = true;
for (0..@intCast(descriptor.resource_count)) |i| {
const a = existing.resources[i];
const b = descriptor.resources[i];
if (a.kind != b.kind or a.start != b.start or a.len != b.len) same = false;
}
if (same) return existing.id;
}
var d = std.mem.zeroes(device_abi.DeviceDescriptor);
d.id = count;
d.parent = parent_id;
d.class = descriptor.class;
d.pci_class = descriptor.pci_class;
d.hid_len = @min(descriptor.hid_len, d.hid.len);
@memcpy(d.hid[0..@intCast(d.hid_len)], descriptor.hid[0..@intCast(d.hid_len)]);
d.resource_count = descriptor.resource_count;
for (0..@intCast(descriptor.resource_count)) |i| d.resources[i] = descriptor.resources[i];
devices[count] = d;
count += 1;
return d.id;
}