Files
danos/library/device/block/block.zig
T
Daniel Samson f1bdce25e0 block: per-sender range confinement — V2a mechanism
The block protocol gains define_range (appended, numbers hold): confine the
process named by `badge` to blocks [base, base+count). usb-storage keeps a
per-badge range table and, in read/write, translates volume-relative LBAs
(base added) and refuses any transfer past the volume end. geometry returns
the confined size, so a filesystem mounts against what it may actually touch.

The security seam (decision 4, settled): the clamp lives at the PROVIDER, so
a channel carries exactly the authority it grants — handing a filesystem the
whole disk plus a base offset would let it reach the neighbouring partition.
The gate: a confined caller may NOT call define_range, so a filesystem cannot
widen its own range or confine anyone; only an unconfined party (the volume
manager, whole-device) may. The volume manager defines a filesystem's range
before handing it the channel, so the ordering holds by construction.

Default (no range for a badge) is the whole device — behaviour-neutral for a
single-volume boot and what the volume manager itself uses to probe
partitions. The range table is declared through bounds.md as a runaway
detector (ours, refuse at limit), not a real-partition cap. Neutral:
fat-mount, usb-storage, iommu-usb-storage green. The discrimination fixture
(a confined process reads past its range and is refused) follows next.
2026-08-09 17:13:26 +01:00

97 lines
4.9 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 envelope = @import("envelope");
const ipc = @import("ipc");
const block_protocol = @import("block-protocol");
const Protocol = block_protocol.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 reply: [block_protocol.message_maximum]u8 = undefined;
const answered = self.call(.geometry, {}, null, &reply) orelse return null;
const result = Protocol.decodeReply(.geometry, answered) orelse 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 reply: [block_protocol.message_maximum]u8 = undefined;
return self.call(.attach, {}, handle, &reply) != null;
}
/// The reverse of `attach`: the buffer leaves the device's reach. The same
/// region capability rides again (the kernel matches the region). Do not name
/// the buffer's physical address in `read`/`write` after this.
pub fn detach(self: Device, handle: ipc.Handle) bool {
var reply: [block_protocol.message_maximum]u8 = undefined;
return self.call(.detach, {}, handle, &reply) != null;
}
/// Read `count` blocks starting at `lba` into the DMA buffer at `physical`.
pub fn read(self: Device, lba: u64, count: u32, physical: u64) bool {
var reply: [block_protocol.message_maximum]u8 = undefined;
return self.call(.read, .{ .lba = lba, .count = count, .physical = physical }, null, &reply) != null;
}
/// Write `count` blocks starting at `lba` from the DMA buffer at `physical`.
pub fn write(self: Device, lba: u64, count: u32, physical: u64) bool {
var reply: [block_protocol.message_maximum]u8 = undefined;
return self.call(.write, .{ .lba = lba, .count = count, .physical = physical }, null, &reply) != null;
}
/// 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 {
var reply: [block_protocol.message_maximum]u8 = undefined;
return self.call(.flush, {}, null, &reply) != null;
}
/// Confine the process `badge` to blocks `[base_lba, base_lba + block_count)`
/// on this device — the volume manager's per-volume grant to a filesystem.
/// The caller must itself be unconfined (whole-device); a confined caller is
/// refused, so a filesystem cannot widen its own range. See `DefineRange`.
pub fn defineRange(self: Device, badge: u32, base_lba: u64, block_count: u64) bool {
var reply: [block_protocol.message_maximum]u8 = undefined;
return self.call(.define_range, .{ .badge = badge, .base_lba = base_lba, .block_count = block_count }, null, &reply) != null;
}
/// One request at the driver. `target` is always 0: one endpoint per device, so
/// there is no object within the peer to address.
fn call(
self: Device,
comptime operation: Protocol.Operation,
request: Protocol.RequestOf(operation),
capability: ?ipc.Handle,
reply: []u8,
) ?[]u8 {
var packet: [block_protocol.message_maximum]u8 = undefined;
const framed = Protocol.encodeRequest(operation, 0, request, &.{}, &packet) orelse return null;
const answer = ipc.callCap(self.endpoint, framed, reply, capability) catch return null;
const status = envelope.statusOf(reply[0..answer.len]) orelse return null;
if (status.status != 0) return null;
return reply[0..answer.len];
}
};
// There is deliberately no open-by-name here: `block` is not a registry name.
// One storage process serves each volume, and a consumer receives its volume's
// channel from the device manager (establishment by lineage, communication.md
// "Establishment: two planes"), then wraps it: `block.Device{ .endpoint = c }`.