Files
danos/system/drivers/pci-bus/pci-bus.zig
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

271 lines
13 KiB
Zig

//! /system/drivers/pci-bus — the PCI bus driver: enumeration moved out of ring 0
//! (docs/discovery.md). The device manager matches the `pci_host_bridge`
//! node and spawns one instance per bridge, the bridge's device id as argv[1] —
//! the same per-device contract as usb-xhci-bus.
//!
//! M19.1 (this increment): claim the bridge, map its ECAM window (resource 0;
//! the bus range and the MMIO apertures follow it), walk every
//! bus/device/function config header, and log what the walk finds — ending
//! with "/system/drivers/pci-bus: N functions found", which the `pci-scan` scenario compares
//! against the kernel's own enumeration. Registration and reports (M19.2), and
//! the kernel walk's retirement (M19.3), build on this proven-equivalent scan.
const std = @import("std");
const runtime = @import("runtime");
const protocol = runtime.device_manager_protocol;
const device = runtime.device;
const pci_class = @import("pci-class");
fn writeLine(comptime fmt: []const u8, arguments: anytype) void {
var line: [128]u8 = undefined;
_ = runtime.system.write(std.fmt.bufPrint(&line, fmt, arguments) catch return);
}
/// Log a discovered function with its (class / subclass / prog-IF) triple decoded
/// to human names — the boot-log breadcrumb that says *what* the hardware is, so
/// "class 0x01 (Mass Storage Controller) subclass 0x06 (Serial ATA Controller)
/// progif 0x01 (AHCI 1.0)" reads straight off the log when writing a new driver.
/// A dedicated wider buffer than `writeLine`'s, since the decoded names are long.
fn logFunction(bus: u64, dev: u64, function: u64, class_triple: u32) void {
const cc = pci_class.ClassCode.unpack(@truncate(class_triple));
const pif = pci_class.progIfName(cc.base, cc.subclass, cc.prog_if);
var line: [200]u8 = undefined;
const text = if (pif.len != 0)
std.fmt.bufPrint(&line, "/system/drivers/pci-bus: {d}:{d}.{d} class 0x{x:0>2} ({s}) subclass 0x{x:0>2} ({s}) progif 0x{x:0>2} ({s})\n", .{ bus, dev, function, cc.base, pci_class.className(cc.base), cc.subclass, pci_class.subclassName(cc.base, cc.subclass), cc.prog_if, pif }) catch return
else
std.fmt.bufPrint(&line, "/system/drivers/pci-bus: {d}:{d}.{d} class 0x{x:0>2} ({s}) subclass 0x{x:0>2} ({s}) progif 0x{x:0>2}\n", .{ bus, dev, function, cc.base, pci_class.className(cc.base), cc.subclass, pci_class.subclassName(cc.base, cc.subclass), cc.prog_if }) catch return;
_ = runtime.system.write(text);
}
var bridge_id: u64 = protocol.no_device;
var ecam_base: usize = 0;
var ecam_physical: u64 = 0;
var start_bus: u64 = 0;
var bus_count: u64 = 0;
var manager_handle: runtime.ipc.Handle = 0;
/// One aligned 32-bit read from a function's configuration space.
fn configRead(bus: u64, dev: u64, function: u64, offset: u64) u32 {
const address = ecam_base + (((bus - start_bus) << 20) | (dev << 15) | (function << 12) | offset);
const register: *volatile u32 = @ptrFromInt(address);
return register.*;
}
fn configWrite(bus: u64, dev: u64, function: u64, offset: u64, value: u32) void {
const address = ecam_base + (((bus - start_bus) << 20) | (dev << 15) | (function << 12) | offset);
const register: *volatile u32 = @ptrFromInt(address);
register.* = value;
}
fn configRead16(bus: u64, dev: u64, function: u64, offset: u64) u16 {
const word = configRead(bus, dev, function, offset & ~@as(u64, 3));
return @truncate(word >> @intCast((offset & 3) * 8));
}
fn configWrite16(bus: u64, dev: u64, function: u64, offset: u64, value: u16) void {
const aligned = offset & ~@as(u64, 3);
const shift: u5 = @intCast((offset & 3) * 8);
const word = configRead(bus, dev, function, aligned);
const mask = @as(u32, 0xFFFF) << shift;
configWrite(bus, dev, function, aligned, (word & ~mask) | (@as(u32, value) << shift));
}
/// Claim the bridge, map the ECAM, hello the manager, then scan.
fn initialise(endpoint: runtime.ipc.Handle) bool {
_ = endpoint;
if (!device.claim(bridge_id)) {
writeLine("/system/drivers/pci-bus: unable to claim bridge device {d}\n", .{bridge_id});
return false;
}
const buffer = runtime.allocator().alloc(device.DeviceDescriptor, 64) catch {
_ = runtime.system.write("/system/drivers/pci-bus: out of memory\n");
return false;
};
const total = device.enumerate(buffer);
const descriptor = for (buffer[0..@min(total, buffer.len)]) |d| {
if (d.id == bridge_id) break d;
} else {
writeLine("/system/drivers/pci-bus: device {d} not in the device tree\n", .{bridge_id});
return false;
};
// Resource 0 is the ECAM window (1 MiB of config space per bus); the bus
// range rides beside it. The MMIO apertures (M19.0) come after both.
if (descriptor.resource_count < 2 or descriptor.resources[0].kind != @intFromEnum(device.ResourceKind.memory)) {
_ = runtime.system.write("/system/drivers/pci-bus: bridge has no ECAM window\n");
return false;
}
const bus_range = for (descriptor.resources[0..@intCast(descriptor.resource_count)]) |resource| {
if (resource.kind == @intFromEnum(device.ResourceKind.bus_range)) break resource;
} else {
_ = runtime.system.write("/system/drivers/pci-bus: bridge has no bus range\n");
return false;
};
start_bus = bus_range.start;
bus_count = bus_range.len;
ecam_physical = descriptor.resources[0].start;
ecam_base = device.mmioMap(bridge_id, 0) orelse {
_ = runtime.system.write("/system/drivers/pci-bus: ECAM mmio_map failed\n");
return false;
};
// The handshake, then the scan (reports join in M19.2).
var manager: ?runtime.ipc.Handle = null;
var tries: u32 = 0;
while (manager == null and tries < 100) : (tries += 1) {
manager = runtime.ipc.lookup(.device_manager);
if (manager == null) runtime.system.sleep(20);
}
const h = manager orelse {
_ = runtime.system.write("/system/drivers/pci-bus: no device manager to hello\n");
return false;
};
const hello = protocol.Hello{ .role = @intFromEnum(protocol.Role.bus), .device_id = bridge_id };
var reply: [protocol.message_maximum]u8 = undefined;
const n = runtime.ipc.call(h, std.mem.asBytes(&hello), &reply) catch {
_ = runtime.system.write("/system/drivers/pci-bus: hello call failed\n");
return false;
};
if (n < protocol.reply_size or std.mem.bytesToValue(protocol.HelloReply, reply[0..protocol.reply_size]).status != 0) {
_ = runtime.system.write("/system/drivers/pci-bus: hello refused\n");
return false;
}
manager_handle = h;
scan();
return true;
}
/// The brute-force walk the kernel does today, from ring 3: every bus in the
/// range, 32 devices, 8 functions; vendor id FFFFh means nothing decodes there,
/// and only multifunction devices get their functions 1..7 probed.
fn scan() void {
var found: u32 = 0;
var bus: u64 = start_bus;
while (bus < start_bus + bus_count) : (bus += 1) {
var dev: u64 = 0;
while (dev < 32) : (dev += 1) {
const first = configRead(bus, dev, 0, 0);
if (first & 0xFFFF == 0xFFFF) continue;
const multifunction = (configRead(bus, dev, 0, 0x0C) >> 16) & 0x80 != 0;
var function: u64 = 0;
while (function < 8) : (function += 1) {
if (function != 0 and !multifunction) break;
const vendor_device = configRead(bus, dev, function, 0);
if (vendor_device & 0xFFFF == 0xFFFF) continue;
const class_revision = configRead(bus, dev, function, 0x08);
found += 1;
logFunction(bus, dev, function, class_revision >> 8);
registerAndReport(bus, dev, function, class_revision >> 8);
}
}
}
writeLine("/system/drivers/pci-bus: {d} functions found\n", .{found});
}
/// Register one function under the bridge and report it to the manager. The
/// descriptor mirrors the kernel's own recording byte for byte — config slice
/// as resource 0, then the sized BARs — so during coexistence the idempotent
/// device_register (M19.0) returns the kernel's existing node id rather than
/// growing a duplicate, and the report carries the id drivers already use.
fn registerAndReport(bus: u64, dev: u64, function: u64, class_triple: u32) void {
var descriptor = std.mem.zeroes(device.DeviceDescriptor);
descriptor.class = @intFromEnum(device.DeviceClass.pci_device);
descriptor.pci_class = class_triple;
descriptor.resources[0] = .{
.kind = @intFromEnum(device.ResourceKind.memory),
.start = ecam_physical + (((bus - start_bus) << 20) | (dev << 15) | (function << 12)),
.len = 4096,
};
descriptor.resource_count = 1;
// The standard BAR-sizing probe, exactly as the kernel does it: decode off,
// write all-ones, read the writable mask back, restore. Header type 0 only.
const header_type = (configRead(bus, dev, function, 0x0C) >> 16) & 0x7F;
if (header_type == 0) {
const command = configRead16(bus, dev, function, 0x04);
configWrite16(bus, dev, function, 0x04, command & ~@as(u16, 0b11));
var i: u64 = 0;
while (i < 6) : (i += 1) {
if (descriptor.resource_count >= 8) break;
const off = 0x10 + i * 4;
const original = configRead(bus, dev, function, off);
if (original == 0) continue;
const slot: usize = @intCast(descriptor.resource_count);
if (original & 1 != 0) {
configWrite(bus, dev, function, off, 0xFFFF_FFFF);
const readback = configRead(bus, dev, function, off);
configWrite(bus, dev, function, off, original);
const mask = readback & 0xFFFF_FFFC;
const size: u32 = if (mask == 0) 0 else (~mask +% 1) & 0xFFFF;
if (size == 0) continue; // unimplemented BAR — nothing to register
descriptor.resources[slot] = .{ .kind = @intFromEnum(device.ResourceKind.io_port), .start = original & 0xFFFF_FFFC, .len = size };
descriptor.resource_count += 1;
} else if ((original >> 1) & 0x3 == 2) {
const original_high = configRead(bus, dev, function, off + 4);
configWrite(bus, dev, function, off, 0xFFFF_FFFF);
configWrite(bus, dev, function, off + 4, 0xFFFF_FFFF);
const lo = configRead(bus, dev, function, off);
const hi = configRead(bus, dev, function, off + 4);
configWrite(bus, dev, function, off, original);
configWrite(bus, dev, function, off + 4, original_high);
const readback = (@as(u64, hi) << 32) | (lo & 0xFFFF_FFF0);
const size: u64 = if (readback == 0) 0 else ~readback +% 1;
i += 1; // consumed the high half regardless
if (size == 0) continue;
descriptor.resources[slot] = .{ .kind = @intFromEnum(device.ResourceKind.memory), .start = (@as(u64, original_high) << 32) | (original & 0xFFFF_FFF0), .len = size };
descriptor.resource_count += 1;
} else {
configWrite(bus, dev, function, off, 0xFFFF_FFFF);
const readback = configRead(bus, dev, function, off);
configWrite(bus, dev, function, off, original);
const mask = readback & 0xFFFF_FFF0;
const size: u32 = if (mask == 0) 0 else ~mask +% 1;
if (size == 0) continue;
descriptor.resources[slot] = .{ .kind = @intFromEnum(device.ResourceKind.memory), .start = original & 0xFFFF_FFF0, .len = size };
descriptor.resource_count += 1;
}
}
configWrite16(bus, dev, function, 0x04, command);
}
const registered = device.register(bridge_id, &descriptor) orelse {
writeLine("/system/drivers/pci-bus: register refused for {d}:{d}.{d}\n", .{ bus, dev, function });
return;
};
const report = protocol.ChildAdded{
.parent = bridge_id,
.bus_address = (bus << 8) | (dev << 3) | function,
.identity = class_triple,
.device_id = registered,
};
var reply: [protocol.message_maximum]u8 = undefined;
_ = runtime.ipc.call(manager_handle, std.mem.asBytes(&report), &reply) catch {
writeLine("/system/drivers/pci-bus: child report for {d}:{d}.{d} failed\n", .{ bus, dev, function });
};
}
fn onMessage(message: []const u8, reply: []u8, sender: u32, capability: ?runtime.ipc.Handle) usize {
_ = message;
_ = reply;
_ = sender;
_ = capability;
return 0;
}
pub fn main(init: runtime.process.Init) void {
const argument = init.arguments.get(1) orelse return; // bare (ramdisk sweep): stay silent
bridge_id = std.fmt.parseInt(u64, argument, 10) catch {
writeLine("/system/drivers/pci-bus: malformed bridge device id '{s}'\n", .{argument});
return;
};
runtime.service.run(protocol.message_maximum, .{
.init = initialise,
.on_message = onMessage,
});
}
pub const panic = runtime.panic;
comptime {
_ = &runtime.start._start; // pull the runtime entry shim into the image
}