danos/system/boot-handoff.zig

//! The **loader ↔ kernel** contract: everything a bootloader (boot/, e.g. efi.zig
//! built as BOOTX64.efi) and the kernel (system/kernel/kernel.zig) must agree on to
//! hand control over — the handoff structures the loader fills in, plus the kernel's
//! virtual-memory layout and the physical↔virtual addressing both sides use.
//!
//! Both binaries import this as the `boot-handoff` module, so the layout is defined
//! in exactly one place. **User space never sees this** — the kernel↔user contract is
//! [[abi]] (system/abi.zig); device types are [[device-abi]] (library/device/model/device-abi.zig).

const std = @import("std");

/// Calling convention for the bootloader→kernel jump. Pinned to SystemV so it does
/// not depend on each binary's target default: the UEFI bootloader's C
/// convention is Microsoft x64 (first arg in RCX), the freestanding kernel's is
/// SystemV (first arg in RDI). Both reference this to agree on where `*BootInformation`
/// is passed.
pub const kernel_abi: std.builtin.CallingConvention = .{ .x86_64_sysv = .{} };

/// Pixel byte order of the linear framebuffer the firmware handed us.
pub const PixelFormat = enum(u32) {
    /// Byte 0 = Red, 1 = Green, 2 = Blue, 3 = reserved.
    rgbx,
    /// Byte 0 = Blue, 1 = Green, 2 = Red, 3 = reserved.
    bgrx,
};

/// A linear framebuffer: `width`x`height` pixels, each a 32-bit value, with
/// `pitch` bytes between the start of one row and the next (which may be larger
/// than `width * 4` due to hardware padding).
///
/// A `base` of 0 means **no framebuffer** — the firmware exposed no Graphics
/// Output Protocol (a headless server, say). The kernel must treat on-screen
/// output as optional and never assume a framebuffer exists.
pub const Framebuffer = extern struct {
    base: usize, // the memory address where pixel data starts (0 = none)
    width: u32, // visible pixels per row (e.g. 1920)
    height: u32, // visible rows (e.g. 1080)
    pitch: u32, // bytes from the start of one row to the start of the next
    format: PixelFormat,
    /// The panel's refresh rate in Hz, computed from its EDID preferred timing (pixel
    /// clock / total pixels per frame) while GOP was still alive — the one moment it is
    /// readable (docs/gop.md). 0 = unknown (no EDID). The display service paces its
    /// frame clock by it; without vblank this fixes the *rate*, never the *phase*.
    refresh_hz: u32 = 0,

    /// Whether a usable framebuffer was handed over.
    pub fn present(self: Framebuffer) bool {
        return self.base != 0 and self.width != 0 and self.height != 0;
    }
};

/// The kernel's virtual-memory layout (higher-half). The kernel is linked at
/// `kernel_virt_base` but loaded at a low physical address; all of RAM (and the
/// device MMIO windows) is also mapped at `physmap_base + physical`, so the kernel
/// can reach any physical address by adding a constant. The low half is left
/// entirely to user space.
///
///   user image + stack : 0x0000_7000_0000_0000  (PML4[224], low half)
///   kernel heap        : 0xFFFF_8000_0000_0000  (PML4[256])
///   physmap            : 0xFFFF_8800_0000_0000  (PML4[272]) + physical
///   kernel image       : 0xFFFF_FFFF_8000_0000  (PML4[511])
pub const physmap_base: u64 = 0xFFFF_8800_0000_0000;
pub const kernel_virt_base: u64 = 0xFFFF_FFFF_8000_0000;

/// Physical address -> its virtual address in the physmap. The single way the
/// kernel dereferences a physical address once paging is up.
///
/// **Hazard:** valid only once the (bootstrap or final) page tables are live.
/// The bootloader may use the *constant* `physmap_base` to build those tables,
/// but must not call this to dereference memory before its own CR3 is loaded —
/// it runs under the firmware's identity map, where these addresses are unmapped.
pub inline fn physicalToVirtual(physical: u64) u64 {
    return physical + physmap_base;
}

/// Physmap virtual address -> physical. Inverse of `physicalToVirtual`; for producing
/// the physical address of something the kernel holds a physmap pointer to
/// (e.g. a page-table frame for CR3, a post-mortem breadcrumb's RAM location).
pub inline fn virtualToPhysical(virtual: u64) u64 {
    return virtual - physmap_base;
}

/// danos's own classification of a span of physical memory — deliberately not
/// UEFI's vocabulary. Each boot path (UEFI now, device tree later) translates its
/// native memory description into these kinds, so the kernel never learns what
/// booted it. [[architecture]] keeps the same discipline for CPU code.
pub const MemoryKind = enum(u32) {
    /// Free RAM the kernel may allocate. Each boot path folds its own transient
    /// memory into this once it's genuinely free (e.g. the UEFI loader classifies
    /// boot-services memory as usable after ExitBootServices), so the kernel never
    /// has to know about boot-protocol-specific "reclaimable" states.
    usable,
    /// Firmware, MMIO, the kernel image, our own boot buffers, the boot stack —
    /// never hand out.
    reserved,
    /// ACPI tables: parse, then reclaim.
    acpi_tables,
    /// ACPI non-volatile storage: preserve across sleep, do not allocate.
    acpi_nvs,
    /// Not backed by RAM: memory-mapped device registers or a reserved
    /// address-space window (e.g. PCIe configuration space). Kept distinct from
    /// `reserved` so RAM accounting doesn't count device address space.
    mmio,
};

/// One contiguous span of physical memory. Because danos defines this layout
/// itself (unlike the UEFI descriptor it's built from), `@sizeOf` is
/// authoritative — the kernel walks a plain `[]MemoryRegion`, with none of the
/// firmware's variable descriptor-stride to worry about.
pub const MemoryRegion = extern struct {
    base: u64, // physical start address
    pages: u64, // length in 4 KiB pages (the [[abi]] `page_size` unit)
    kind: MemoryKind,
    _pad: u32 = 0,
};

/// The physical memory layout handed to the kernel: a pointer to an array of
/// `len` `MemoryRegion`s, in a buffer that outlives the loader.
pub const MemoryMap = extern struct {
    regions: usize, // address of a `[len]MemoryRegion`
    len: usize,
};

/// One PT_LOAD segment of the kernel image, so the kernel can re-map itself with
/// correct permissions (code R+X, rodata R, data R+W+NX). `flags` are raw ELF
/// segment flags: PF_X=1, PF_W=2, PF_R=4. `virtual` is the higher-half link address;
/// `physical` is where the loader actually placed the segment (they differ once the
/// kernel links high — the loader records the real load address here).
pub const KernelSegment = extern struct {
    virtual: u64,
    physical: u64,
    pages: u64,
    flags: u32,
    _pad: u32 = 0,
};

/// Handoff structure the bootloader fills in and passes to the kernel's
/// `_start` in RDI (the first argument under the SystemV AMD64 C ABI).
pub const BootInformation = extern struct {
    framebuffer: Framebuffer,
    memory_map: MemoryMap,
    /// The kernel's own PT_LOAD segments (it has three: text, rodata, data).
    kernel_segments: [8]KernelSegment,
    kernel_segment_count: u32,
    /// Physical address of the ACPI RSDP the firmware exposed, or 0 if none. The
    /// kernel's device layer parses the ACPI tables from here to discover hardware.
    /// A device-tree boot path leaves this 0 and (later) fills a `device_tree_blob`
    /// field instead, so the kernel discovers devices without knowing what booted it.
    acpi_rsdp: u64 = 0,
    /// The initial_ramdisk image: every user binary from the boot volume's /system
    /// tree (init included), packed by the loader into memory that survives the
    /// handoff (classified reserved, so the kernel identity-maps it and never
    /// allocates over it). Entries are named by full FHS path. 0/0 = no binaries
    /// found — the kernel boots without user space. See system/initial-ramdisk.zig.
    initial_ramdisk_base: u64 = 0,
    initial_ramdisk_len: u64 = 0,
};