move the running task into per-CPU state

PerCpu.current via the GS base; ready queues stay global.

src/kernel/arch/x86_64/cpu.zig

@@ -81,6 +81,24 @@ pub fn readCr3() u64 {
     );
 }
 
+/// IA32_GS_BASE: the hidden base of the GS segment. We repurpose it as the per-CPU
+/// data pointer (there's no user mode yet, so no `swapgs` dance — GS base is always
+/// the running core's per-CPU block). Set once per core during bring-up, after the
+/// GDT is loaded (loading a GS *selector* would otherwise clobber this base).
+const ia32_gs_base = 0xC000_0101;
+
+/// Publish this core's per-CPU data pointer so `cpuLocal` can retrieve it. Each
+/// core calls this once, after its GDT is in place.
+pub fn setCpuLocal(ptr: usize) void {
+    io.wrmsr(ia32_gs_base, ptr);
+}
+
+/// This core's per-CPU data pointer (the value `setCpuLocal` stored). Reads the GS
+/// base MSR — a per-core register, so each core sees its own without any locking.
+pub fn cpuLocal() usize {
+    return io.rdmsr(ia32_gs_base);
+}
+
 /// Kernel tick rate: 1000 Hz (1 ms), the scheduler's time quantum.
 pub const timer_hz = 1000;
 

src/kernel/scheduler.zig

@@ -42,22 +42,57 @@ const Task = struct {
 };
 
 var tasks = [_]Task{.{}} ** max_tasks;
-var current: *Task = undefined;
 var next_id: u32 = 1;
 
-// Per-priority FIFO ready queues, and a bitmap of which levels are non-empty.
+/// Per-CPU scheduler state: the task each core is running, plus its own idle task.
+/// One entry per core; the arch layer stashes a pointer to the *running* core's
+/// entry in the GS base, so `thisCpu()` fetches it with a single read and no lock.
+/// This is the only state that's genuinely per-core — the ready queues below stay
+/// **global** under the big kernel lock, so any idle core pulls the highest-priority
+/// ready task (work-conserving). Per-core ready queues are a later optimisation if
+/// the global queue's lock contention ever bites (docs/smp.md).
+pub const PerCpu = struct {
+    current: *Task = undefined, // the task running on this core
+    idle: *Task = undefined, // this core's idle task (always ready, lowest priority)
+    apic_id: u32 = 0, // the core's Local APIC id
+    index: u32 = 0, // dense 0-based core index
+    online: bool = false, // has this core finished bring-up?
+};
+
+const max_cpus = 64; // matches the discovery pool (src/device/acpi.zig)
+var cpus = [_]PerCpu{.{}} ** max_cpus;
+
+/// This core's per-CPU state, via the arch layer's GS-base pointer. Valid only once
+/// this core has run its scheduler bring-up (BSP in `init`, AP in `secondaryInit`).
+inline fn thisCpu() *PerCpu {
+    return @ptrFromInt(arch.cpuLocal());
+}
+
+/// The task running on this core — the per-CPU replacement for the old global
+/// `current`. A convenience reader; writes go through `thisCpu().current`.
+inline fn cur() *Task {
+    return thisCpu().current;
+}
+
+// Per-priority FIFO ready queues, and a bitmap of which levels are non-empty. These
+// are shared across all cores and mutated only under the big kernel lock.
 var ready_head: [num_priorities]?*Task = .{null} ** num_priorities;
 var ready_tail: [num_priorities]?*Task = .{null} ** num_priorities;
 var ready_bitmap: u8 = 0;
 
 var preemption_enabled = true;
 
-/// Register the currently-running kernel context as the first task, spawn the
+/// Bring up scheduling on the bootstrap processor: register the currently-running
-/// idle task, and hook the timer for preemption.
+/// kernel context as task 0, publish this core's per-CPU state (via the GS base),
+/// give the core an idle task, and hook the timer for preemption. Runs once, at
+/// boot, before interrupts are enabled — so no lock is needed here.
 pub fn init(boot_priority: Priority) void {
+    const pc = &cpus[0];
+    pc.* = .{ .index = 0, .online = true };
+    arch.setCpuLocal(@intFromPtr(pc));
     tasks[0] = .{ .id = 0, .state = .running, .priority = boot_priority };
-    current = &tasks[0];
+    pc.current = &tasks[0];
-    spawn(idle, 0); // lowest priority, always runnable — runs when nothing else is
+    pc.idle = create(idle, 0); // this core's idle task: always ready, lowest priority
     arch.setTickHook(tick);
 }
 
@@ -93,7 +128,18 @@ fn levelBit(p: Priority) u8 {
 }
 
 /// Create a task that runs `entry` at `priority`. It becomes ready immediately.
+/// Takes the kernel lock: it mutates the shared task table and ready queues and
+/// allocates from the (non-thread-safe) heap, so on SMP it must be serialised.
 pub fn spawn(entry: *const fn () void, priority: Priority) void {
+    const flags = sync.enter();
+    _ = create(entry, priority);
+    sync.leave(flags);
+}
+
+/// The unlocked task-creation primitive. Caller must hold the kernel lock (or be
+/// the single-threaded boot path). Returns the new task so a core can keep a handle
+/// to its idle task.
+fn create(entry: *const fn () void, priority: Priority) *Task {
     const t = freeSlot() orelse @panic("sched: task table full");
     const stack = heap.allocator().alloc(u8, stack_size) catch @panic("sched: no memory for task stack");
     t.* = .{ .id = next_id, .state = .ready, .priority = priority, .stack = stack };
@@ -101,6 +147,7 @@ pub fn spawn(entry: *const fn () void, priority: Priority) void {
     const top = @intFromPtr(stack.ptr) + stack.len;
     t.rsp = arch.initTaskStack(top, @intFromPtr(entry));
     enqueue(t);
+    return t;
 }
 
 fn freeSlot() ?*Task {
@@ -110,10 +157,14 @@ fn freeSlot() ?*Task {
     return null;
 }
 
-/// Pick the highest-priority ready task and switch to it. Interrupts must be
+/// Pick the highest-priority ready task and switch this core to it. The big kernel
-/// disabled by the caller.
+/// lock must be held by the caller (which also keeps local interrupts disabled);
+/// it serialises every core's scheduling, so no other core can touch the shared
+/// queues while we requeue `prev` and dequeue `next`. A dequeued task is `.ready`,
+/// never running elsewhere, so two cores never run the same task.
 fn schedule() void {
-    const prev = current;
+    const pc = thisCpu();
+    const prev = pc.current;
     if (prev.state == .running) {
         prev.state = .ready;
         enqueue(prev); // back of its level's queue (round-robin)
@@ -123,7 +174,7 @@ fn schedule() void {
         return;
     };
     next.state = .running;
-    current = next;
+    pc.current = next;
     if (next != prev) arch.switchContext(&prev.rsp, next.rsp);
 }
 
@@ -138,8 +189,9 @@ pub fn yield() void {
 /// again. The idle task (or other work) runs in the meantime.
 pub fn sleep(ms: u64) void {
     const flags = sync.enter();
-    current.wake_at = arch.millis() + ms;
+    const t = cur();
-    current.state = .blocked;
+    t.wake_at = arch.millis() + ms;
+    t.state = .blocked;
     schedule(); // current is blocked, so schedule() won't re-enqueue it
     sync.leave(flags);
 }
@@ -160,9 +212,10 @@ pub const WaitQueue = struct {
 /// it also keeps local interrupts disabled). On return — when woken — the lock is
 /// still held.
 pub fn waitLocked(wq: *WaitQueue) void {
-    current.state = .blocked;
+    const t = cur();
-    current.next = wq.head;
+    t.state = .blocked;
-    wq.head = current;
+    t.next = wq.head;
+    wq.head = t;
     schedule();
 }
 
@@ -173,10 +226,10 @@ pub fn wakeLocked(wq: *WaitQueue) void {
     var best_prev: ?*Task = null;
     var best: ?*Task = null;
     var prev: ?*Task = null;
-    var cur = wq.head;
+    var node = wq.head;
-    while (cur) |t| : ({
+    while (node) |t| : ({
         prev = t;
-        cur = t.next;
+        node = t.next;
     }) {
         if (best == null or t.priority > best.?.priority) {
             best = t;
@@ -202,7 +255,7 @@ pub fn wake(wq: *WaitQueue) void {
     wakeLocked(wq);
     // If a higher-priority task is now ready, run it immediately.
     if (highestReadyPriority()) |p| {
-        if (p > current.priority) schedule();
+        if (p > cur().priority) schedule();
     }
     sync.leave(flags);
 }
@@ -247,20 +300,21 @@ pub fn setPreemption(enabled: bool) void {
 /// the task we switch into (which releases it) — this frame never returns to leave.
 pub fn exit() noreturn {
     _ = sync.enter();
-    current.state = .free;
+    const pc = thisCpu();
+    pc.current.state = .free;
     const next = dequeueHighest() orelse @panic("sched: no task left to run");
     next.state = .running;
-    current = next;
+    pc.current = next;
     var discard: usize = 0;
     arch.switchContext(&discard, next.rsp);
     unreachable;
 }
 
 pub fn currentId() u32 {
-    return current.id;
+    return cur().id;
 }
 
 /// Change the running task's priority (takes effect next time it's enqueued).
 pub fn setPriority(p: Priority) void {
-    current.priority = p;
+    cur().priority = p;
 }