cubelinux-kernel/drivers/cube/cubelinux_store.rs

// SPDX-License-Identifier: GPL-2.0

//! CUBELinux store reader — the kernel reading CUBE coordinates off a block device.
//!
//! The store is addressed by coordinate, and the pinned image's layout is:
//!
//! ```text
//! [MAGIC "CUBE" 4][version 1][curve tag]
//! records: [SpaceId 32][Key 24][value length u64 LE][value]
//! ```
//!
//! This module reads that image from a block device and reports what it holds: the record
//! count, the total value bytes, and an FNV-1a digest over every `(space, key, length,
//! value)` in order. The digest exists so the kernel and userspace can be *compared*
//! rather than assumed to agree — `cube-image digest <image>` prints the same line in the
//! same field order, and the QEMU gate fails if they differ by a byte.
//!
//! # Why a reader, and only a reader
//!
//! The store's write authority has not moved yet. `PLAN-kernel-cubelinux.md` records the
//! decision (the kernel owns the store) and the hazard that makes the order matter: a
//! kernel that writes while a userspace daemon still holds the same image in memory loses
//! one of the two writers' work, silently. Until that is settled, a reader is the correct
//! amount of authority for the kernel to hold.
//!
//! # Interface
//!
//! `/dev/cubelinux` — reading it performs the read (through the kernel's own file layer)
//! and returns one line. Nothing happens at module init, so there is no ordering to get
//! wrong against the block driver that provides the device.
//!
//! ```text
//! digest curve=0 bytes=1141 records=11 value_bytes=431 fnv1a64=161113085b1573b2 errors=0
//! ```

use core::fmt::{self, Write};

use kernel::{
    bindings, c_str,
    device::Device,
    fs::{File, Kiocb},
    iov::IovIterDest,
    miscdevice::{MiscDevice, MiscDeviceOptions, MiscDeviceRegistration},
    prelude::*,
    sync::aref::ARef,
};

module! {
    type: CubeStoreModule,
    name: "cubelinux_store",
    authors: ["CUBE OS"],
    description: "CUBELinux store reader (coordinates in the kernel)",
    license: "GPL",
}

/// The layout, restated here because the kernel cannot depend on the userspace crates.
/// `crates/cube-store-raw` is the source of truth; the digest comparison is what keeps
/// this copy honest.
const MAGIC: &[u8; 4] = b"CUBE";
/// The original format: magic, version, curve, then records until zero padding.
const VERSION_V1: u8 = 1;
/// The current format: the same, plus the image's byte extent and record count.
const VERSION: u8 = 2;
const HEADER_LEN_V1: usize = 6;
const HEADER_LEN_V2: usize = 6 + 8 + 8;
const SPACE_ID_LEN: usize = 32;
const RAW_KEY_LEN: usize = 24;
const RECORD_FIXED: usize = SPACE_ID_LEN + RAW_KEY_LEN + 8;

/// The device to read. A module parameter is the obvious next step; for the boot gate one
/// fixed name is honest and has one less way to be wrong.
const STORE_DEVICE: &core::ffi::CStr = c_str!("/dev/vda");

/// Refuse to pull an unbounded device into memory. The gate's images are tiny; this is the
/// guard against a wrong device name turning a read into an allocation storm.
const MAX_BYTES: usize = 64 * 1024 * 1024;

/// FNV-1a offset basis.
const FNV_OFFSET: u64 = 0xcbf2_9ce4_8422_2325;

/// A line of output, built in place. No allocation: the read path formats into a fixed
/// buffer, so it cannot fail for want of memory while holding a file open.
struct Line {
    buf: [u8; 256],
    len: usize,
}

impl Line {
    fn new() -> Self {
        Line {
            buf: [0; 256],
            len: 0,
        }
    }

    fn as_bytes(&self) -> &[u8] {
        &self.buf[..self.len]
    }
}

impl Write for Line {
    fn write_str(&mut self, s: &str) -> fmt::Result {
        let bytes = s.as_bytes();
        if self.len + bytes.len() > self.buf.len() {
            return Err(fmt::Error);
        }
        self.buf[self.len..self.len + bytes.len()].copy_from_slice(bytes);
        self.len += bytes.len();
        Ok(())
    }
}

/// FNV-1a 64 over a run of bytes, continuing from `h`.
fn fnv1a64(bytes: &[u8], mut h: u64) -> u64 {
    for b in bytes {
        h ^= *b as u64;
        h = h.wrapping_mul(0x0000_0100_0000_01b3);
    }
    h
}

/// Read the whole store image through the kernel's file layer.
///
/// `kernel_read` on the block device rather than a raw bio: it is the path this kernel
/// version exposes to Rust, it goes through the page cache the way any other read does, and
/// it needs no C helper. If the store ever has to be read before the VFS is up (a root
/// filesystem, say), that is the moment to reach for the block layer directly.
fn read_image(image: &mut KVVec<u8>) -> Result<()> {
    // O_RDONLY is 0 in Linux; filp_open takes the raw flags word.
    // SAFETY: STORE_DEVICE is a NUL-terminated C string literal, and filp_open either
    // returns a valid `struct file *` or an error pointer, which is checked below.
    let file = unsafe { bindings::filp_open(STORE_DEVICE.as_ptr().cast::<u8>(), 0, 0) };
    let file = kernel::error::from_err_ptr(file)?;
    if file.is_null() {
        return Err(EINVAL);
    }

    let mut pos: bindings::loff_t = 0;
    let mut chunk = KVVec::<u8>::with_capacity(4096, GFP_KERNEL)?;
    chunk.extend_from_slice(&[0u8; 4096][..], GFP_KERNEL)?;
    let mut result = Ok(());

    loop {
        // SAFETY: `file` is a live `struct file *` from filp_open; `chunk` is a 4096-byte
        // kernel buffer we own; `pos` is a valid loff_t. kernel_read reads at most
        // `chunk.len()` bytes into the buffer and does not retain either pointer.
        let n = unsafe {
            bindings::kernel_read(
                file,
                chunk.as_mut_ptr().cast::<core::ffi::c_void>(),
                chunk.len(),
                &mut pos,
            )
        };
        if n < 0 {
            result = Err(Error::from_errno(n as i32));
            break;
        }
        if n == 0 {
            break; // end of device
        }
        let n = n as usize;
        if let Err(e) = image.extend_from_slice(&chunk[..n], GFP_KERNEL) {
            result = Err(e.into());
            break;
        }
        if image.len() >= MAX_BYTES {
            break;
        }
    }

    // SAFETY: `file` came from filp_open and has not been closed; the owner argument is
    // only meaningful for locks that no one holds here.
    unsafe { bindings::filp_close(file, core::ptr::null_mut()) };

    // Less than the shortest header is not an image at all; `digest` reports the rest.
    if result.is_ok() && image.len() < HEADER_LEN_V1 {
        return Err(EINVAL);
    }
    result
}

/// Walk the records of a store image, digesting each one, exactly as
/// `cube-store-raw::iter_records` + `cube-image digest` do.
///
/// The two rules that are easy to get wrong, both from the userspace parser: a record whose
/// value runs past the buffer is a truncated record and an error, and an all-zero frame is
/// *end of records* only when every remaining byte is also zero — otherwise a real record
/// at the origin, followed by padding, would be read as an empty one.
/// What a header says, in both formats.
struct Header {
    version: u8,
    curve: u8,
    image_bytes: Option<u64>,
    record_count: Option<u64>,
}

/// Read the header, or say what is wrong with it.
fn parse_header(image: &[u8]) -> Result<Header, &'static str> {
    if image.len() < 5 || &image[0..4] != MAGIC {
        return Err("not-a-store");
    }
    let version = image[4];
    let curve = image[5];
    match version {
        VERSION_V1 => Ok(Header {
            version,
            curve,
            image_bytes: None,
            record_count: None,
        }),
        VERSION => {
            if image.len() < HEADER_LEN_V2 {
                return Err("short-v2-header");
            }
            let mut word = [0u8; 8];
            word.copy_from_slice(&image[6..14]);
            let image_bytes = u64::from_le_bytes(word);
            word.copy_from_slice(&image[14..22]);
            let record_count = u64::from_le_bytes(word);
            // A header that does not cover itself is corrupt, and guessing at the extent
            // of an image means possibly reading somebody else's bytes.
            if (image_bytes as usize) < HEADER_LEN_V2 {
                return Err("bad-extent");
            }
            Ok(Header {
                version,
                curve,
                image_bytes: Some(image_bytes),
                record_count: Some(record_count),
            })
        }
        _ => Err("unsupported-version"),
    }
}

fn digest(image: &[u8]) -> Line {
    let mut line = Line::new();

    let header = match parse_header(image) {
        Ok(h) => h,
        Err(what) => {
            let _ = write!(line, "error={what}");
            return line;
        }
    };
    let end = match header.image_bytes {
        Some(n) => core::cmp::min(n as usize, image.len()),
        None => image.len(),
    };

    let mut h = FNV_OFFSET;
    let mut count: u64 = 0;
    let mut value_bytes: u64 = 0;
    let mut errors: u64 = 0;
    let mut off = if header.version == VERSION_V1 {
        HEADER_LEN_V1
    } else {
        HEADER_LEN_V2
    };
    let mut remaining = header.record_count;

    while off + RECORD_FIXED <= end {
        if remaining == Some(0) {
            break;
        }
        let frame = &image[off..off + RECORD_FIXED];
        // Padding is not a record — but only if it is padding all the way down, and only
        // in v1, where nothing else says where the records stop. A v2 image states its
        // count, so a zero frame inside that count is a record like any other.
        if remaining.is_none()
            && frame.iter().all(|b| *b == 0)
            && image[off..].iter().all(|b| *b == 0)
        {
            break;
        }

        let space = &image[off..off + SPACE_ID_LEN];
        let key = &image[off + SPACE_ID_LEN..off + SPACE_ID_LEN + RAW_KEY_LEN];
        let mut len_bytes = [0u8; 8];
        len_bytes.copy_from_slice(&image[off + SPACE_ID_LEN + RAW_KEY_LEN..off + RECORD_FIXED]);
        let value_len = u64::from_le_bytes(len_bytes) as usize;

        let value_at = off + RECORD_FIXED;
        // A promised record that is not there is a truncated image, and saying so beats
        // returning a shorter list that looks complete.
        if value_at + value_len > end {
            errors += 1;
            break;
        }
        let value = &image[value_at..value_at + value_len];

        h = fnv1a64(space, h);
        h = fnv1a64(key, h);
        h = fnv1a64(&(value_len as u64).to_le_bytes(), h);
        h = fnv1a64(value, h);
        count += 1;
        value_bytes += value_len as u64;
        off = value_at + value_len;
        if let Some(n) = remaining.as_mut() {
            *n -= 1;
        }
    }
    // The count was a promise; not meeting it is an error the caller must see.
    if let Some(n) = remaining {
        if n > 0 {
            errors += 1;
        }
    }

    // Field order matches cube-image's `digest` line so the two diff directly.
    let _ = write!(
        line,
        "digest version={} curve={} bytes={} records={} value_bytes={} fnv1a64={:016x} errors={}",
        header.version,
        header.curve,
        image.len(),
        count,
        value_bytes,
        h,
        errors
    );
    line
}

/// The module's registration; holds the misc device for as long as the module lives.
#[pin_data]
struct CubeStoreModule {
    #[pin]
    _miscdev: MiscDeviceRegistration<CubeStore>,
}

impl kernel::InPlaceModule for CubeStoreModule {
    fn init(_module: &'static ThisModule) -> impl PinInit<Self, Error> {
        pr_info!("cubelinux: store reader registered at /dev/cubelinux\n");
        try_pin_init!(Self {
            _miscdev <- MiscDeviceRegistration::register(MiscDeviceOptions {
                name: c_str!("cubelinux"),
            }),
        })
    }
}

#[pin_data]
struct CubeStore {
    dev: ARef<Device>,
}

#[vtable]
impl MiscDevice for CubeStore {
    type Ptr = Pin<KBox<Self>>;

    fn open(_file: &File, misc: &MiscDeviceRegistration<Self>) -> Result<Pin<KBox<Self>>> {
        KBox::try_pin_init(
            try_pin_init! {
                CubeStore { dev: ARef::from(misc.device()) }
            },
            GFP_KERNEL,
        )
    }

    fn read_iter(mut kiocb: Kiocb<'_, Self::Ptr>, iov: &mut IovIterDest<'_>) -> Result<usize> {
        // The work happens here, on demand, rather than at init: by the time anything can
        // open this device, the block driver that provides the store is certainly up.
        let mut image = KVVec::<u8>::new();
        let line = match read_image(&mut image) {
            Ok(()) => digest(&image),
            Err(e) => {
                let mut line = Line::new();
                let _ = write!(line, "error={:?}", e);
                line
            }
        };
        pr_info!("cubelinux: {}\n", core::str::from_utf8(line.as_bytes()).unwrap_or("<bad utf8>"));

        let me = kiocb.file();
        dev_info!(me.dev, "cubelinux: store read complete\n");
        iov.simple_read_from_buffer(kiocb.ki_pos_mut(), line.as_bytes())
    }
}