danos/system/kernel/ipc-synchronous.zig

//! Synchronous IPC: the microkernel message backbone. An `Endpoint` is a
//! rendezvous point; a client `call`s it (send a message, block for a reply) and
//! a server `replyWait`s on it (reply to the last client, then block for the next
//! request). This is the substrate the user-space VFS server and device drivers
//! are reached through — `open`/`read`/`write` become user-space wrappers that
//! marshal a request into a `call`.
//!
//! Design (see docs/syscall.md, the plan):
//! - **Copy method, no bounce buffer.** Payloads are copied frame-to-frame
//!   through the physmap (`copyAcross`), which is mapped in every address space's
//!   shared kernel half — so the kernel reads/writes either process's user memory
//!   without a CR3 switch, and an unmapped page fails the copy instead of #PF-ing.
//! - **Reply routing on the server.** IPC is synchronous, so a server owes a reply
//!   to exactly one client at a time; that caller is held in `Task.ipc_client`.
//! - **Sender FIFO on the endpoint.** A blocked caller must be *received without
//!   becoming runnable*, which a WaitQueue can't express, so callers queue on the
//!   endpoint's own FIFO (threaded through the otherwise-idle `Task.next`); servers
//!   waiting for work use a normal WaitQueue.
//!
//! Trust model (bring-up): copies honour only page presence and a user-half bound,
//! not the leaf U/S or R/W bits and not SMAP — a #PF-tolerant, permission-checked
//! copy is a later security-track item, matching the existing debug_write gap.

const std = @import("std");
const boot_handoff = @import("boot-handoff");
const abi = @import("abi");
const architecture = @import("architecture");
const scheduler = @import("scheduler.zig");
const sync = @import("sync.zig");
const heap = @import("heap.zig");

const page_size = abi.page_size;
const Task = scheduler.Task;

/// Largest message a single call/reply may carry. Bumping it is trivial; kept
/// small because the copy runs under the big kernel lock.
pub const MESSAGE_MAXIMUM: usize = 256;

pub const maximum_handles = scheduler.ipc_maximum_handles;
pub const maximum_services = 8;

/// Errno-style failures, returned as `-value` in the system_call result register.
pub const EBADF: i64 = 1; // bad handle
pub const E2BIG: i64 = 2; // message exceeds MESSAGE_MAXIMUM
pub const EFAULT: i64 = 3; // buffer unmapped / out of the user half
pub const ENOENT: i64 = 4; // no such registered service
pub const ENOSPC: i64 = 5; // handle table or registry full
pub const ENOMEM: i64 = 6; // out of memory

/// A badge with this bit set is an asynchronous notification (e.g. an IRQ), not a
/// message from a client — there is no reply owed. The low bits carry the source
/// (a GSI for IRQs). Posted by `notifyFromIsr`, from the ISR in system/kernel/irq.zig;
/// the message path uses a plain task-id badge with this bit clear. Defined in the
/// shared kernel↔user ABI (system/abi.zig), because ring 3 has to test the same bit.
pub const notify_badge_bit: u64 = abi.notify_badge_bit;

/// End of the user (low) canonical half — user buffers must lie below it.
const user_half_end: u64 = 0x0000_8000_0000_0000;

/// A rendezvous endpoint. Allocated from the kernel heap; referenced by handle
/// (per process) and/or by a registry slot, counted by `refcount`.
pub const Endpoint = struct {
    refcount: u32 = 1,
    // Callers blocked in `call`, awaiting receive, in FIFO order (threaded via
    // Task.next; each such task is .blocked and in no scheduler queue).
    sender_head: ?*Task = null,
    sender_tail: ?*Task = null,
    // Servers blocked in `replyWait` awaiting a request.
    receive_wait_queue: scheduler.WaitQueue = .{},
    // Pending asynchronous notifications (badges), a small coalescing ring.
    notify_buffer: [8]u64 = undefined,
    notify_head: u8 = 0,
    notify_tail: u8 = 0,
};

pub fn createEndpoint() ?*Endpoint {
    const endpoint = heap.allocator().create(Endpoint) catch return null;
    endpoint.* = .{};
    return endpoint;
}

/// Drop a reference; free the endpoint when the last one goes. (Frames are leaked
/// today like other kernel objects — but the refcount bookkeeping lands now.)
pub fn dropRef(endpoint: *Endpoint) void {
    if (endpoint.refcount > 1) {
        endpoint.refcount -= 1;
    } else {
        heap.allocator().destroy(endpoint);
    }
}

// --- sender FIFO (endpoint-local, via Task.next) ----------------------------

fn enqueueSender(endpoint: *Endpoint, t: *Task) void {
    t.next = null;
    if (endpoint.sender_tail) |tail| tail.next = t else endpoint.sender_head = t;
    endpoint.sender_tail = t;
}

fn dequeueSender(endpoint: *Endpoint) ?*Task {
    const t = endpoint.sender_head orelse return null;
    endpoint.sender_head = t.next;
    if (endpoint.sender_head == null) endpoint.sender_tail = null;
    t.next = null;
    return t;
}

// --- cross-address-space copy ----------------------------------------------

/// Copy `len` bytes from `source_va` in address space `source_as` to `destination_va` in
/// `destination_as`, walking each side's page tables through the physmap (no CR3 switch).
/// `*_as == 0` means the kernel address space (for kernel-task endpoints). User
/// buffers must lie in the low half. Returns false — never #PFs — if any page is
/// unmapped or out of range. Handles page-straddling buffers.
fn copyAcross(source_as: u64, source_va: u64, destination_as: u64, destination_va: u64, len: usize) bool {
    const source_root = if (source_as != 0) source_as else architecture.kernelPageTable();
    const destination_root = if (destination_as != 0) destination_as else architecture.kernelPageTable();
    if (source_as != 0 and (source_va >= user_half_end or source_va + len > user_half_end)) return false;
    if (destination_as != 0 and (destination_va >= user_half_end or destination_va + len > user_half_end)) return false;

    var off: usize = 0;
    while (off < len) {
        const s = architecture.translate(source_root, source_va + off) orelse return false;
        const d = architecture.translate(destination_root, destination_va + off) orelse return false;
        const s_left = page_size - ((source_va + off) & (page_size - 1));
        const d_left = page_size - ((destination_va + off) & (page_size - 1));
        const n = @min(@min(s_left, d_left), len - off);
        const source: [*]const u8 = @ptrFromInt(boot_handoff.physicalToVirtual(s));
        const destination: [*]u8 = @ptrFromInt(boot_handoff.physicalToVirtual(d));
        @memcpy(destination[0..n], source[0..n]);
        off += n;
    }
    return true;
}

/// Copy `destination.len` bytes from `user_va` in address space `user_as` into the kernel
/// buffer `destination`, walking the user page tables through the physmap. Returns false if
/// the range escapes the user half or any source page is unmapped — so a bad user
/// pointer *fails the system_call* rather than faulting the kernel (danos has no
/// fault-recovering copy-in, so a raw dereference of an unmapped user page would halt
/// the machine). The correct way to pull a fixed-size struct in from user space, and
/// a single fetch: no TOCTOU against a hostile pointer.
pub fn copyFromUser(user_as: u64, user_va: u64, destination: []u8) bool {
    if (user_as == 0) return false; // not a user address space
    if (user_va >= user_half_end or user_va + destination.len > user_half_end) return false;
    var off: usize = 0;
    while (off < destination.len) {
        const s = architecture.translate(user_as, user_va + off) orelse return false;
        const s_left = page_size - ((user_va + off) & (page_size - 1));
        const n = @min(s_left, destination.len - off);
        const source: [*]const u8 = @ptrFromInt(boot_handoff.physicalToVirtual(s));
        @memcpy(destination[off..][0..n], source[0..n]);
        off += n;
    }
    return true;
}

// --- the two IPC operations -------------------------------------------------

/// Share the capability named by handle `cap` in `from`'s table into `to`'s table,
/// bumping the endpoint's refcount (the sender keeps its handle — this is a copy, not
/// a move). Returns the handle it landed at in `to` (>= 0), or `-EBADF` if `cap` names
/// no live handle, or `-ENOSPC` if `to`'s table is full. Callers only invoke this when
/// `cap != no_cap`. Used by both IPC directions to carry an endpoint with a message.
fn shareCapability(from: *Task, to: *Task, cap: u64) i64 {
    const endpoint = resolveHandle(from, cap) orelse return -EBADF;
    endpoint.refcount += 1;
    const handle = installHandle(to, endpoint);
    if (handle < 0) {
        dropRef(endpoint); // undo the bump; the receiver had no room
        return -ENOSPC;
    }
    return handle;
}

/// Client side of IPC_Call: send `[message_ptr, message_len)` to `endpoint` and block until a
/// server replies into `[reply_ptr, reply_cap)`. Returns the reply length, or a
/// negative errno. `send_cap` (a handle, or `no_cap`) is an endpoint transferred to the
/// server with the request; `out_received_cap` receives the handle of an endpoint the
/// server sent back in its reply, or `no_cap`. Runs as the current task.
pub fn call(endpoint: *Endpoint, message_ptr: u64, message_len: u64, reply_ptr: u64, reply_cap: u64, send_cap: u64, out_received_cap: *u64) i64 {
    if (message_len > MESSAGE_MAXIMUM or reply_cap > MESSAGE_MAXIMUM) return -E2BIG;
    const flags = sync.enter();
    defer sync.leave(flags);

    const me = scheduler.current();
    me.ipc_send_ptr = message_ptr;
    me.ipc_send_len = message_len;
    me.ipc_reply_ptr = reply_ptr;
    me.ipc_reply_cap = reply_cap;
    me.ipc_send_cap = send_cap;
    me.ipc_received_cap = abi.no_cap;
    me.ipc_status = 0;

    enqueueSender(endpoint, me); // join the FIFO, then...
    scheduler.wakeLocked(&endpoint.receive_wait_queue); // ...wake a waiting server (no-op if none)
    scheduler.blockCurrentLocked(); // block until the reply readies us again

    out_received_cap.* = me.ipc_received_cap; // a capability the replier sent back, or no_cap
    return me.ipc_status; // reply length or -errno, written by the replier
}

/// Server side of IPC_ReplyWait: deliver `[reply_ptr, reply_len)` to the client
/// we currently owe (if any), then receive the next request into
/// `[receive_ptr, receive_cap)`, blocking until one arrives. Writes the sender's badge
/// to `out_badge` and returns the request length, or a negative errno. A pending
/// notification is delivered ahead of client requests (length 0, badge with
/// `notify_badge_bit` set, no reply owed).
pub fn replyWait(endpoint: *Endpoint, reply_ptr: u64, reply_len: u64, receive_ptr: u64, receive_cap: u64, send_cap: u64, out_badge: *u64, out_received_cap: *u64) i64 {
    if (reply_len > MESSAGE_MAXIMUM or receive_cap > MESSAGE_MAXIMUM) return -E2BIG;
    const flags = sync.enter();
    defer sync.leave(flags);

    const me = scheduler.current();
    out_received_cap.* = abi.no_cap; // no capability received unless a request delivers one

    // (1) Reply to the client we're still holding, if any — carrying `send_cap` to it.
    if (me.ipc_client) |client| {
        me.ipc_client = null;
        const n = @min(reply_len, client.ipc_reply_cap);
        client.ipc_received_cap = abi.no_cap;
        if (!copyAcross(me.aspace, reply_ptr, client.aspace, client.ipc_reply_ptr, n)) {
            client.ipc_status = -EFAULT;
        } else if (send_cap != abi.no_cap) {
            // Transfer the reply's capability into the client. A failure fails the
            // client's `call` rather than delivering a reply without its promised cap.
            const shared = shareCapability(me, client, send_cap);
            if (shared < 0) {
                client.ipc_status = shared; // -EBADF (bad handle) or -ENOSPC (client table full)
            } else {
                client.ipc_received_cap = @intCast(shared);
                client.ipc_status = @intCast(n);
            }
        } else {
            client.ipc_status = @intCast(n);
        }
        scheduler.readyLocked(client); // its `call` now returns
    }

    // (2) Receive the next request (or notification), blocking until one is ready.
    while (true) {
        if (popNotify(endpoint)) |badge| {
            out_badge.* = badge | notify_badge_bit;
            return 0; // notification: no payload, no reply owed, no cap
        }
        if (dequeueSender(endpoint)) |caller| {
            const n = @min(caller.ipc_send_len, receive_cap);
            if (!copyAcross(caller.aspace, caller.ipc_send_ptr, me.aspace, receive_ptr, n)) {
                caller.ipc_status = -EFAULT; // bad sender buffer: fail it, keep serving
                scheduler.readyLocked(caller);
                continue;
            }
            // Install the capability the caller sent, if any, into my table. A failure
            // fails the caller's `call` and does not deliver — no half-delivered cap.
            if (caller.ipc_send_cap != abi.no_cap) {
                const shared = shareCapability(caller, me, caller.ipc_send_cap);
                if (shared < 0) {
                    caller.ipc_status = shared; // -EBADF or -ENOSPC
                    scheduler.readyLocked(caller);
                    continue;
                }
                out_received_cap.* = @intCast(shared);
            }
            me.ipc_client = caller; // remember who to reply to
            out_badge.* = caller.id;
            return @intCast(n);
        }
        scheduler.waitLocked(&endpoint.receive_wait_queue); // nothing yet — sleep until woken, then retry
    }
}

// --- asynchronous notification (for IRQ-as-message, M10) --------------------

fn popNotify(endpoint: *Endpoint) ?u64 {
    if (endpoint.notify_head == endpoint.notify_tail) return null;
    const badge = endpoint.notify_buffer[endpoint.notify_head % endpoint.notify_buffer.len];
    endpoint.notify_head +%= 1;
    return badge;
}

/// Post an asynchronous notification carrying `badge` to `endpoint` and wake a waiting
/// receiver. Precondition: the big kernel lock is held.
///
/// The lock must already cover whatever produced `endpoint` — an ISR that looked the
/// endpoint up in a table and *then* took the lock could be racing a process exit
/// that unbinds and frees it in between. See irq.dispatch, which holds one lock
/// region across the table read and this call.
///
/// A full ring drops the notification. That is the correct semantics, not a
/// concession: a notification is a *level* ("this device wants attention"), and the
/// driver re-reads device state on wake. It is never a count of events.
pub fn notifyLocked(endpoint: *Endpoint, badge: u64) void {
    if (endpoint.notify_tail -% endpoint.notify_head < endpoint.notify_buffer.len) {
        endpoint.notify_buffer[endpoint.notify_tail % endpoint.notify_buffer.len] = badge;
        endpoint.notify_tail +%= 1;
    }
    scheduler.wakeLocked(&endpoint.receive_wait_queue);
}

/// `notifyLocked` as a self-contained ISR critical section, for a caller that holds
/// `endpoint` by some means other than a table the lock protects. Releases the lock without
/// touching the interrupt flag (the ISR's iretq restores it), like the timer tick.
pub fn notifyFromIsr(endpoint: *Endpoint, badge: u64) void {
    _ = sync.enter();
    notifyLocked(endpoint, badge);
    sync.leaveIsr();
}

// --- per-process handle table + name registry -------------------------------

/// Install `endpoint` in task `t`'s handle table; returns the small-int handle or
/// -ENOSPC. The caller has already taken/holds the reference the slot represents.
pub fn installHandle(t: *Task, endpoint: *Endpoint) i64 {
    for (&t.handles, 0..) |*slot, i| {
        if (slot.* == null) {
            slot.* = @ptrCast(endpoint);
            return @intCast(i);
        }
    }
    return -ENOSPC;
}

/// Resolve a handle to its endpoint, or null if out of range / unused.
pub fn resolveHandle(t: *Task, h: u64) ?*Endpoint {
    if (h >= t.handles.len) return null;
    const slot = t.handles[@intCast(h)] orelse return null;
    return @ptrCast(@alignCast(slot));
}

/// Drop every endpoint reference an exiting task holds. Called from the scheduler
/// exit path so a dead server's endpoints don't linger referenced.
pub fn closeHandles(t: *Task) void {
    for (&t.handles) |*slot| {
        if (slot.*) |p| {
            dropRef(@ptrCast(@alignCast(p)));
            slot.* = null;
        }
    }
}

var registry: [maximum_services]?*Endpoint = .{null} ** maximum_services;

/// Publish `endpoint` under well-known `id` (takes a reference). Returns 0 or -errno.
pub fn register(id: u32, endpoint: *Endpoint) i64 {
    if (id >= maximum_services) return -ENOENT;
    if (registry[id]) |old| dropRef(old);
    endpoint.refcount += 1;
    registry[id] = endpoint;
    return 0;
}

/// Find the endpoint published under `id`, taking a reference for the caller to
/// install in its handle table. Null if nothing is registered there.
pub fn lookup(id: u32) ?*Endpoint {
    if (id >= maximum_services) return null;
    const endpoint = registry[id] orelse return null;
    endpoint.refcount += 1;
    return endpoint;
}