Built heap allocation

src/heap.zig

@@ -0,0 +1,174 @@
+//! The kernel heap: dynamic allocation for the kernel.
+//!
+//! Where the frame allocator ([pmm]) hands out fixed 4 KiB physical frames, the
+//! heap hands out arbitrary byte-sized blocks from a virtual region, growing on
+//! demand by mapping fresh frames into it (arch.mapPage) — the first real user of
+//! the VMM (see docs/paging.md).
+//!
+//! The algorithm is a first-fit free list: an address-ordered singly linked list
+//! of free blocks, split on allocation and coalesced with neighbours on free. It
+//! is exposed as a std.mem.Allocator, so the kernel can use std containers.
+//!
+//! Not yet concurrency-safe: it assumes a single caller and no allocation from
+//! interrupt handlers (ours don't). A lock comes with threads/SMP.
+
+const std = @import("std");
+const danos = @import("danos");
+const arch = @import("arch");
+const pmm = @import("pmm.zig");
+
+const page_size = danos.page_size;
+
+/// Virtual base of the heap: the start of the higher half, which is unmapped and
+/// well clear of the identity-mapped low half. (Canonical on x86_64; an arch that
+/// splits the address space differently would choose its own.)
+const heap_base: usize = 0xFFFF_8000_0000_0000;
+/// Cap on heap growth for now.
+const heap_max: usize = 64 * 1024 * 1024;
+
+/// A block header, placed at the start of every block. While the block is free it
+/// also links into the free list via `next`.
+const Block = extern struct {
+    size: usize, // total block size in bytes, including this header; a multiple of 16
+    next: ?*Block, // free-list link (only meaningful while free)
+};
+
+const header_size = @sizeOf(Block); // 16
+const min_block = header_size + 16; // smallest block worth splitting off
+
+var free_list: ?*Block = null;
+var heap_end: usize = heap_base; // [heap_base, heap_end) is currently mapped
+
+fn alignUp(value: usize, alignment: usize) usize {
+    return (value + alignment - 1) & ~(alignment - 1);
+}
+
+fn payloadOf(block: *Block) [*]u8 {
+    return @ptrFromInt(@intFromPtr(block) + header_size);
+}
+
+/// Bring the heap up with an initial mapped region.
+pub fn init() void {
+    free_list = null;
+    heap_end = heap_base;
+    _ = grow(page_size);
+}
+
+/// Map more pages onto the end of the heap and add them as a free block. Returns
+/// false if out of heap virtual space or out of physical frames.
+fn grow(min_bytes: usize) bool {
+    const start = heap_end;
+    const bytes = alignUp(min_bytes, page_size);
+    if (start + bytes > heap_base + heap_max) return false;
+
+    var virt = start;
+    while (virt < start + bytes) : (virt += page_size) {
+        const frame = pmm.alloc() orelse return false;
+        arch.mapPage(virt, frame, true);
+    }
+    heap_end = start + bytes;
+
+    const block: *Block = @ptrFromInt(start);
+    block.size = bytes;
+    insertFree(block); // coalesces with the previous tail block if adjacent
+    return true;
+}
+
+/// Insert a block into the address-ordered free list, coalescing with the
+/// physically adjacent free blocks on either side.
+fn insertFree(block: *Block) void {
+    var prev: ?*Block = null;
+    var cur = free_list;
+    while (cur) |c| : (cur = c.next) {
+        if (@intFromPtr(c) > @intFromPtr(block)) break;
+        prev = c;
+    }
+
+    block.next = cur;
+    if (prev) |p| p.next = block else free_list = block;
+
+    // Merge forward into `cur` if they're contiguous.
+    if (cur) |c| {
+        if (@intFromPtr(block) + block.size == @intFromPtr(c)) {
+            block.size += c.size;
+            block.next = c.next;
+        }
+    }
+    // Merge `prev` forward into `block` if they're contiguous.
+    if (prev) |p| {
+        if (@intFromPtr(p) + p.size == @intFromPtr(block)) {
+            p.size += block.size;
+            p.next = block.next;
+        }
+    }
+}
+
+/// Allocate `len` bytes (16-byte aligned), or null if out of memory.
+fn rawAlloc(len: usize) ?[*]u8 {
+    const need = alignUp(header_size + len, 16);
+
+    var attempts: u32 = 0;
+    while (attempts < 2) : (attempts += 1) {
+        var prev: ?*Block = null;
+        var cur = free_list;
+        while (cur) |block| : ({
+            prev = block;
+            cur = block.next;
+        }) {
+            if (block.size < need) continue;
+
+            if (block.size >= need + min_block) {
+                // Split: carve `need` off the front, leave the rest free.
+                const rest: *Block = @ptrFromInt(@intFromPtr(block) + need);
+                rest.size = block.size - need;
+                rest.next = block.next;
+                if (prev) |p| p.next = rest else free_list = rest;
+                block.size = need;
+            } else {
+                // Take the whole block.
+                if (prev) |p| p.next = block.next else free_list = block.next;
+            }
+            return payloadOf(block);
+        }
+
+        // Nothing fit: grow and try once more.
+        if (!grow(need)) return null;
+    }
+    return null;
+}
+
+fn rawFree(ptr: [*]u8) void {
+    const block: *Block = @ptrFromInt(@intFromPtr(ptr) - header_size);
+    insertFree(block);
+}
+
+// --- std.mem.Allocator interface -----------------------------------------
+
+pub fn allocator() std.mem.Allocator {
+    return .{ .ptr = undefined, .vtable = &vtable };
+}
+
+const vtable = std.mem.Allocator.VTable{
+    .alloc = allocImpl,
+    .resize = resizeImpl,
+    .remap = remapImpl,
+    .free = freeImpl,
+};
+
+fn allocImpl(_: *anyopaque, len: usize, alignment: std.mem.Alignment, _: usize) ?[*]u8 {
+    // Blocks are 16-byte aligned; larger alignments aren't supported yet.
+    if (alignment.toByteUnits() > 16) return null;
+    return rawAlloc(len);
+}
+
+fn resizeImpl(_: *anyopaque, _: []u8, _: std.mem.Alignment, _: usize, _: usize) bool {
+    return false; // no in-place resize; the caller reallocates
+}
+
+fn remapImpl(_: *anyopaque, _: []u8, _: std.mem.Alignment, _: usize, _: usize) ?[*]u8 {
+    return null;
+}
+
+fn freeImpl(_: *anyopaque, memory: []u8, _: std.mem.Alignment, _: usize) void {
+    rawFree(memory.ptr);
+}

src/main.zig

@@ -3,6 +3,7 @@ const danos = @import("danos");
 const arch = @import("arch");
 const console = @import("console.zig");
 const pmm = @import("pmm.zig");
+const heap = @import("heap.zig");
 const tests = @import("tests.zig");
 const build_options = @import("build_options");
 const BootInfo = danos.BootInfo;
@@ -92,10 +93,14 @@ fn kmain(boot_info: *const BootInfo) noreturn {
     con.print("  page tables: CR3 = 0x{x:0>16}\n", .{arch.readCr3()});
     con.print("  kernel segs: {d} (mapped with W^X permissions)\n", .{boot_info.kernel_segment_count});
 
+    // Bring up the kernel heap (dynamic allocation), built on the VMM.
+    heap.init();
+    con.write("\ndanos: kernel heap online\n");
+
     // Start the timer and unmask interrupts — the kernel now has a heartbeat.
     arch.startTimer();
     arch.enableInterrupts();
-    con.write("\ndanos: timer interrupts enabled\n");
+    con.write("danos: timer interrupts enabled\n");
 
     // In a test build (`zig build -Dtest-case=<name>`), run that case and stop.
     // Normal builds fall through to the idle halt.

src/tests.zig

@@ -13,6 +13,7 @@ const std = @import("std");
 const danos = @import("danos");
 const arch = @import("arch");
 const pmm = @import("pmm.zig");
+const heap = @import("heap.zig");
 
 /// Formatted write straight to serial, independent of the framebuffer console.
 fn log(comptime fmt: []const u8, args: anytype) void {
@@ -50,6 +51,8 @@ pub fn run(case: []const u8, boot_info: *const BootInfo) void {
         timer();
     } else if (eql(case, "vmm")) {
         vmm();
+    } else if (eql(case, "heap")) {
+        heapTest();
     } else if (eql(case, "fault-ud")) {
         faultInvalidOpcode();
     } else if (eql(case, "fault-pf")) {
@@ -138,6 +141,69 @@ fn vmm() void {
     result();
 }
 
+/// Exercise the kernel heap: basic alloc/write/free, reuse, growth beyond the
+/// initial region, and a std container backed by it.
+fn heapTest() void {
+    log("DANOS-TEST-BEGIN: heap\n", .{});
+    const a = heap.allocator();
+
+    // Allocate, write a pattern, read it back, free.
+    const buf = a.alloc(u8, 4096) catch null;
+    check("alloc 4096 bytes", buf != null);
+    if (buf) |b| {
+        @memset(b, 0xAB);
+        check("heap memory is writable and reads back", b[0] == 0xAB and b[4095] == 0xAB);
+        a.free(b);
+    }
+
+    // Freeing then re-allocating the same size should reuse the block.
+    const p1 = a.alloc(u64, 8) catch null;
+    const addr1 = if (p1) |p| @intFromPtr(p.ptr) else 0;
+    if (p1) |p| a.free(p);
+    const p2 = a.alloc(u64, 8) catch null;
+    const addr2 = if (p2) |p| @intFromPtr(p.ptr) else 0;
+    check("freed block is reused", addr1 != 0 and addr1 == addr2);
+    if (p2) |p| a.free(p);
+
+    // Force growth past the initial page and check every block is usable.
+    var blocks: [64]?[]u8 = .{null} ** 64;
+    var ok = true;
+    for (&blocks, 0..) |*slot, i| {
+        const b = a.alloc(u8, 4096) catch null;
+        slot.* = b;
+        if (b) |bb| @memset(bb, @intCast(i & 0xff)) else {
+            ok = false;
+        }
+    }
+    for (blocks, 0..) |slot, i| {
+        if (slot) |bb| {
+            if (bb[0] != @as(u8, @intCast(i & 0xff)) or bb[4095] != @as(u8, @intCast(i & 0xff))) ok = false;
+        }
+    }
+    check("many allocations (heap growth) stay valid", ok);
+    for (blocks) |slot| {
+        if (slot) |bb| a.free(bb);
+    }
+
+    // A std container backed by the kernel heap.
+    var list: std.ArrayList(u32) = .empty;
+    var sum: u64 = 0;
+    var expected: u64 = 0;
+    var i: u32 = 0;
+    var list_ok = true;
+    while (i < 1000) : (i += 1) {
+        list.append(a, i) catch {
+            list_ok = false;
+        };
+        expected += i;
+    }
+    for (list.items) |v| sum += v;
+    list.deinit(a);
+    check("std.ArrayList on the kernel heap", list_ok and sum == expected);
+
+    result();
+}
+
 fn faultInvalidOpcode() void {
     log("DANOS-TEST-BEGIN: fault-ud\n", .{});
     asm volatile ("ud2");