Files
Daniel Samson 4e7cbc9792 iommu: DMA-region capabilities — per-grant reachability, protocol flag-day
Replaces L2's interim DMA pool (every buffer reachable by every claimed
device) with true per-grant confinement: a device reaches only buffers
whose capability was delegated to its driver.

Kernel:
- DmaRegionObject (handle kind 2): a delegation token naming a dma_alloc'd
  region, passable across processes on the IPC cap slot like an endpoint
  or shared-memory object. Frames stay owned by the allocating address
  space (freed on dma_free/teardown as before); the token carries a `dead`
  flag so a stale downstream handle can no longer bind a freed region.
- dma_alloc gains the dma_shareable flag: it returns a capability handle
  in r8 and every region is tracked in a registry. A task's own regions
  auto-bind into the devices it claims (its rings just work); foreign
  buffers are bound explicitly.
- dma_bind / dma_unbind / handle_close syscalls (51-53). dma_bind maps a
  held region (or shared-memory) capability into a claimed device's domain;
  it is idempotent. handle_close reclaims a table slot (raised 16 -> 32).
- dma_free and task death unmap a region from every domain and invalidate
  BEFORE its frames return to the allocator — the stale-IOTLB use-after-
  free window, closed structurally.

Protocols (flag-day): block gains attach, usb-transfer gains dma_attach —
each carries a region capability on the cap slot. fat allocates its bounce
buffer shareable and attaches it; usb-storage allocates its transport
buffers shareable, attaches them to the controller, and forwards fat's
capability downstream; usb-xhci-bus binds and closes; virtio-gpu binds its
shared scanout surface. The physical addresses on the wire are unchanged
(identity IOVA), so no register-programming code moved.

Cross-process DMA (fat -> usb-storage -> xHC) now flows only through
delegated capabilities. iommu-usb-storage / iommu-usb-hid / iommu-fault
all green under per-grant enforcement; 104/104 overall (fail-open paths
unchanged).
2026-07-26 18:31:27 +01:00

92 lines
4.7 KiB
Zig

//! Block-device client: the helper a filesystem uses to read and write a block
//! device (a USB stick, via usb-storage) without hand-rolling the block-protocol
//! IPC. Layered over `ipc` and the shared `block-protocol` wire format, like
//! `runtime.usb` over the transfer protocol.
//!
//! Transfers name a caller-owned DMA buffer by physical address (from
//! `runtime.dma.alloc`), so whole sectors move without crossing the IPC size
//! limit — the same handoff usb-storage uses toward the controller.
const std = @import("std");
const ipc = @import("ipc");
const time = @import("time");
const block_protocol = @import("block-protocol");
pub const Geometry = struct { block_size: u32, block_count: u64 };
pub const Device = struct {
endpoint: ipc.Handle,
/// The device's block size and total block count.
pub fn geometry(self: Device) ?Geometry {
var request = block_protocol.Request{ .operation = @intFromEnum(block_protocol.Operation.geometry), .lba = 0, .count = 0, .physical = 0 };
var reply: [block_protocol.reply_size]u8 = undefined;
const n = ipc.call(self.endpoint, std.mem.asBytes(&request), &reply) catch return null;
if (n < block_protocol.reply_size) return null;
const result = std.mem.bytesToValue(block_protocol.Reply, reply[0..block_protocol.reply_size]);
if (result.status != 0) return null;
return .{ .block_size = result.block_size, .block_count = result.block_count };
}
/// Hand the block server a DMA-region capability (`handle` — from a `shareable`
/// dma_alloc) so it forwards it to the controller and the buffer's physical
/// addresses become reachable by the device. Call once per buffer before naming it
/// in `read`/`write`. Harmless success when no IOMMU is enforcing.
pub fn attach(self: Device, handle: ipc.Handle) bool {
var request = block_protocol.Request{ .operation = @intFromEnum(block_protocol.Operation.attach), .lba = 0, .count = 0, .physical = 0 };
var reply: [block_protocol.reply_size]u8 = undefined;
const result = ipc.callCap(self.endpoint, std.mem.asBytes(&request), &reply, handle) catch return false;
if (result.len < block_protocol.reply_size) return false;
return std.mem.bytesToValue(block_protocol.Reply, reply[0..block_protocol.reply_size]).status == 0;
}
/// Read `count` blocks starting at `lba` into the DMA buffer at `physical`.
pub fn read(self: Device, lba: u64, count: u32, physical: u64) bool {
return self.transfer(.read, lba, count, physical);
}
/// Write `count` blocks starting at `lba` from the DMA buffer at `physical`.
pub fn write(self: Device, lba: u64, count: u32, physical: u64) bool {
return self.transfer(.write, lba, count, physical);
}
/// Commit any device write cache to stable media (SCSI SYNCHRONIZE CACHE), so
/// prior writes survive a power-off. A filesystem calls this before the machine
/// goes down; no data transfer, so the buffer arguments are unused.
pub fn flush(self: Device) bool {
return self.transfer(.flush, 0, 0, 0);
}
fn transfer(self: Device, operation: block_protocol.Operation, lba: u64, count: u32, physical: u64) bool {
var request = block_protocol.Request{ .operation = @intFromEnum(operation), .lba = lba, .count = count, .physical = physical };
var reply: [block_protocol.reply_size]u8 = undefined;
const n = ipc.call(self.endpoint, std.mem.asBytes(&request), &reply) catch return false;
if (n < block_protocol.reply_size) return false;
return std.mem.bytesToValue(block_protocol.Reply, reply[0..block_protocol.reply_size]).status == 0;
}
};
/// One lookup attempt, no waiting — for a server that retries on its own
/// timer (the fat service) instead of blocking its harness in here.
pub fn tryOpen() ?Device {
if (ipc.lookup(.block)) |handle| return .{ .endpoint = handle };
return null;
}
/// Look up the block device, retrying generously while the USB storage chain
/// (controller reset, enumeration, mass-storage bring-up) comes up.
pub fn open() ?Device {
// Patient: the whole USB storage chain (firmware discovery, xHCI reset and
// enumeration, mass-storage bring-up) must complete first, which can take
// tens of seconds under emulation.
var attempts: usize = 0;
// 30 s covers the slowest observed healthy chain (a flaky QEMU enumeration
// completed at ~24 s); a machine whose stick genuinely failed setup should
// not sit a further minute pretending otherwise.
while (attempts < 600) : (attempts += 1) {
if (ipc.lookup(.block)) |handle| return .{ .endpoint = handle };
time.sleepMillis(50);
}
return null;
}