204 lines
7.9 KiB
Zig
204 lines
7.9 KiB
Zig
//! Physical memory manager: a bitmap frame allocator. It hands out and reclaims
|
|
//! 4 KiB physical frames — the primitive every later memory feature (page
|
|
//! tables, the heap) is built on top of.
|
|
//!
|
|
//! This is generic kernel code: it works on the neutral `boot_handoff.MemoryRegion`
|
|
//! array the loader hands over (see docs/memory-map.md), so it carries no UEFI
|
|
//! and nothing architecture-specific beyond the 4 KiB page.
|
|
|
|
const std = @import("std");
|
|
const boot_handoff = @import("boot-handoff");
|
|
const abi = @import("abi");
|
|
|
|
const page_size = abi.page_size;
|
|
|
|
/// One bit per frame, covering physical RAM from 0 up to the highest usable
|
|
/// address: 1 = used/unavailable, 0 = free. The bitmap itself lives in a frame
|
|
/// we carve out of usable memory during init.
|
|
var bitmap: []u8 = &.{};
|
|
var total_frames: usize = 0;
|
|
var used_frames: usize = 0;
|
|
/// Where the next allocation scan begins, so we don't rescan from frame 0 every
|
|
/// time. Pulled back on free() so reclaimed low frames get reused.
|
|
var next_hint: usize = 0;
|
|
|
|
pub const Stats = struct {
|
|
total_frames: usize,
|
|
used_frames: usize,
|
|
free_frames: usize,
|
|
};
|
|
|
|
pub fn stats() Stats {
|
|
return .{
|
|
.total_frames = total_frames,
|
|
.used_frames = used_frames,
|
|
.free_frames = total_frames - used_frames,
|
|
};
|
|
}
|
|
|
|
inline fn bit(frame: usize) u3 {
|
|
return @intCast(frame & 7);
|
|
}
|
|
inline fn isUsed(frame: usize) bool {
|
|
return (bitmap[frame >> 3] >> bit(frame)) & 1 != 0;
|
|
}
|
|
inline fn setUsed(frame: usize) void {
|
|
bitmap[frame >> 3] |= @as(u8, 1) << bit(frame);
|
|
}
|
|
inline fn setFree(frame: usize) void {
|
|
bitmap[frame >> 3] &= ~(@as(u8, 1) << bit(frame));
|
|
}
|
|
|
|
fn regions(map: boot_handoff.MemoryMap) []const boot_handoff.MemoryRegion {
|
|
return @as([*]const boot_handoff.MemoryRegion, @ptrFromInt(boot_handoff.physicalToVirtual(map.regions)))[0..map.len];
|
|
}
|
|
|
|
/// Build the allocator from the loader's memory map. Reaches physical memory
|
|
/// (the region array, the bitmap's own storage) through the physmap, which the
|
|
/// loader's bootstrap tables already provide — so this works before the kernel
|
|
/// installs its own tables. Invariant: the bitmap lands in the first usable
|
|
/// region (lowest address), which must sit under the bootstrap physmap's reach
|
|
/// (4 GiB); it always does, as both this and the page-table allocator scan from
|
|
/// low addresses up.
|
|
pub fn init(map: boot_handoff.MemoryMap) void {
|
|
const regs = regions(map);
|
|
|
|
// 1. Size the bitmap to cover every frame up to the highest RAM address —
|
|
// including reserved RAM, so those frames are trackable (e.g. to free the
|
|
// boot buffers later). Only MMIO (device address space) is excluded.
|
|
// Everything starts unallocatable; usable regions are freed below.
|
|
var highest: u64 = 0;
|
|
for (regs) |r| {
|
|
if (r.kind == .mmio) continue;
|
|
const end = r.base + r.pages * page_size;
|
|
if (end > highest) highest = end;
|
|
}
|
|
total_frames = @intCast(highest / page_size);
|
|
if (total_frames == 0) @panic("pmm: no usable memory");
|
|
const bitmap_bytes = (total_frames + 7) / 8;
|
|
const bitmap_pages = (bitmap_bytes + page_size - 1) / page_size;
|
|
|
|
// 2. Park the bitmap in the first usable region large enough to hold it.
|
|
// Start at least one page in, so we never place it on frame 0 (which is
|
|
// kept reserved as the "none" address, and is an awkward pointer besides).
|
|
var storage: ?u64 = null;
|
|
for (regs) |r| {
|
|
if (r.kind != .usable) continue;
|
|
const base = if (r.base == 0) page_size else r.base;
|
|
const skipped = (base - r.base) / page_size;
|
|
if (r.pages - skipped >= bitmap_pages) {
|
|
storage = base;
|
|
break;
|
|
}
|
|
}
|
|
const bitmap_base = storage orelse @panic("pmm: no region large enough for the frame bitmap");
|
|
bitmap = @as([*]u8, @ptrFromInt(boot_handoff.physicalToVirtual(bitmap_base)))[0..bitmap_bytes];
|
|
|
|
// 3. Start with everything marked used, then free the usable regions. Doing
|
|
// it this way means every gap, reserved span and MMIO hole is unallocatable
|
|
// by default — we only ever hand back memory the firmware called usable.
|
|
@memset(bitmap, 0xff);
|
|
used_frames = total_frames;
|
|
for (regs) |r| {
|
|
if (r.kind != .usable) continue;
|
|
var f: usize = @intCast(r.base / page_size);
|
|
const end = f + @as(usize, @intCast(r.pages));
|
|
while (f < end and f < total_frames) : (f += 1) {
|
|
setFree(f);
|
|
used_frames -= 1;
|
|
}
|
|
}
|
|
|
|
// 4. Take back the frames the bitmap occupies, and frame 0 — so a 0 result
|
|
// stays reserved to mean "no frame".
|
|
reserve(bitmap_base, bitmap_pages);
|
|
reserve(0, 1);
|
|
}
|
|
|
|
/// Mark `count` frames from physical `base` as used, counting only those that
|
|
/// were actually free.
|
|
fn reserve(base: u64, count: usize) void {
|
|
var f: usize = @intCast(base / page_size);
|
|
const end = f + count;
|
|
while (f < end and f < total_frames) : (f += 1) {
|
|
if (!isUsed(f)) {
|
|
setUsed(f);
|
|
used_frames += 1;
|
|
}
|
|
}
|
|
}
|
|
|
|
/// Allocate one physical frame, or null if none are free. The address is
|
|
/// page-aligned; the frame's contents are undefined.
|
|
pub fn alloc() ?u64 {
|
|
var scanned: usize = 0;
|
|
var f = next_hint;
|
|
while (scanned < total_frames) : (scanned += 1) {
|
|
if (f >= total_frames) f = 0;
|
|
if (!isUsed(f)) {
|
|
setUsed(f);
|
|
used_frames += 1;
|
|
next_hint = f + 1;
|
|
return @as(u64, f) * page_size;
|
|
}
|
|
f += 1;
|
|
}
|
|
return null; // out of physical memory
|
|
}
|
|
|
|
/// Allocate one free frame whose physical address is below `limit`, or null if
|
|
/// none is free down there. The AP trampoline needs this: an x86 STARTUP IPI vectors
|
|
/// a waking core to physical `vector << 12`, and `vector` is a byte — so the
|
|
/// trampoline must live under 1 MiB. A short linear scan of the low frames; only run
|
|
/// a handful of times at boot, so it needn't be fast.
|
|
pub fn allocBelow(limit: u64) ?u64 {
|
|
const cap = @min(total_frames, @as(usize, @intCast(limit / page_size)));
|
|
var f: usize = 1; // frame 0 stays reserved as the "none" address
|
|
while (f < cap) : (f += 1) {
|
|
if (!isUsed(f)) {
|
|
setUsed(f);
|
|
used_frames += 1;
|
|
return @as(u64, f) * page_size;
|
|
}
|
|
}
|
|
return null;
|
|
}
|
|
|
|
/// Return a frame obtained from alloc() to the pool. Bogus or double frees are
|
|
/// ignored rather than corrupting the count.
|
|
pub fn free(address: u64) void {
|
|
const f: usize = @intCast(address / page_size);
|
|
if (f >= total_frames or !isUsed(f)) return;
|
|
setFree(f);
|
|
used_frames -= 1;
|
|
if (f < next_hint) next_hint = f;
|
|
}
|
|
|
|
/// Allocate `count` physically **contiguous** frames whose highest byte is below
|
|
/// `max_phys` (pass `~0` for no limit; use a real limit for DMA engines with 32-bit
|
|
/// addressing). Returns the physical base, or null if no free run of that size fits.
|
|
/// A DMA descriptor ring needs contiguity, a known physical address, and pinning —
|
|
/// none of which one-frame `alloc` gives. Linear scan for a run of clear bits: fine
|
|
/// for the small rings DMA needs; a buddy allocator is a later optimisation. The
|
|
/// frames are freed individually with `free`, so there is no bespoke free path.
|
|
pub fn allocContiguous(count: usize, max_phys: u64) ?u64 {
|
|
if (count == 0) return null;
|
|
const limit: usize = @intCast(@min(@as(u64, total_frames), max_phys / page_size));
|
|
var start: usize = 1; // frame 0 stays reserved as the "none" address
|
|
while (start + count <= limit) {
|
|
if (isUsed(start)) {
|
|
start += 1;
|
|
continue;
|
|
}
|
|
var run: usize = 0;
|
|
while (run < count and !isUsed(start + run)) : (run += 1) {}
|
|
if (run == count) {
|
|
for (0..count) |i| setUsed(start + i);
|
|
used_frames += count;
|
|
return @as(u64, start) * page_size;
|
|
}
|
|
start += run + 1; // the frame at start+run is used; skip past it
|
|
}
|
|
return null; // no contiguous run of `count` frames below max_phys
|
|
}
|