AbleOS/holey-bytes
3
3
Fork 5
Code Issues 2 Pull requests Packages Projects Releases Wiki Activity

Compare commits

base: AbleOS:trunk
Branches Tags
AbleOS:trunk
AbleOS:hbcb
AbleOS:soft-float
koniifer:trunk
koniifer:hbcb
koniifer:soft-float
..
compare: koniifer:soft-float
Branches Tags
koniifer:trunk
koniifer:hbcb
koniifer:soft-float
AbleOS:trunk
AbleOS:hbcb
AbleOS:soft-float

1 commit
trunk ... soft-float

Author SHA1 Message Date
Erin 6348516f8c soft-float 2024-05-09 11:58:04 +02:00
179 changed files with 1753 additions and 22405 deletions
Show stats Expand all files Collapse all files

2
.cargo/config.toml
View file

@ -1,4 +1,2 @@
[alias] [alias]
xtask = "r -p xtask --" xtask = "r -p xtask --"
wasm-build = "b --target wasm32-unknown-unknown --profile=small -Zbuild-std=core,alloc -Zbuild-std-features=optimize_for_size,panic_immediate_abort -p"
wasm-build-debug = "b --target wasm32-unknown-unknown --profile=small-dev -Zbuild-std=core,alloc -Zbuild-std-features=optimize_for_size -p"

12
.gitignore vendored
View file

@ -1,13 +1 @@
# garbage
/target /target
rustc-ice-*
# sqlite
db.sqlite
db.sqlite-journal
# assets
/depell/src/*.gz
/depell/src/*.wasm
#**/*-sv.rs
/bytecode/src/instrs.rs

1567
Cargo.lock generated
View file

File diff suppressed because it is too large Load diff

49
Cargo.toml
View file

@ -1,50 +1,3 @@
cargo-features = ["profile-rustflags"]
[workspace] [workspace]
resolver = "2" resolver = "2"
members = [ members = ["hbasm", "hbbytecode", "hbvm", "hbxrt", "xtask"]
"bytecode",
"vm",
"xrt",
"xtask",
"lang",
"depell",
"depell/wasm-fmt",
"depell/wasm-hbc",
"depell/wasm-rt",
]
[workspace.dependencies]
hbbytecode = { path = "bytecode", default-features = false }
hbvm = { path = "vm", default-features = false }
hbxrt = { path = "xrt" }
hblang = { path = "lang", default-features = false }
hbjit = { path = "jit" }
[profile.release]
lto = true
#debug = true
strip = true
codegen-units = 1
panic = "abort"
[profile.small]
rustflags = ["-Zfmt-debug=none", "-Zlocation-detail=none"]
inherits = "release"
opt-level = "z"
strip = "debuginfo"
lto = true
codegen-units = 1
panic = "abort"
[profile.small-dev]
inherits = "dev"
opt-level = "z"
strip = "debuginfo"
panic = "abort"
[profile.fuzz]
inherits = "dev"
debug = true
opt-level = 3
panic = "abort"

204
bytecode/build.rs
View file

@ -1,204 +0,0 @@
#![feature(iter_next_chunk)]
use std::{collections::HashSet, fmt::Write};
fn main() -> Result<(), Box<dyn std::error::Error>> {
println!("cargo:rerun-if-changed=build.rs");
println!("cargo:rerun-if-changed=instructions.in");
let mut generated = String::new();
gen_instrs(&mut generated)?;
std::fs::write("src/instrs.rs", generated)?;
Ok(())
}
fn gen_instrs(generated: &mut String) -> Result<(), Box<dyn std::error::Error>> {
writeln!(generated, "#![expect(dead_code)]")?;
writeln!(generated, "use crate::*;")?;
'_opcode_structs: {
let mut seen = HashSet::new();
for [.., args, _] in instructions() {
if !seen.insert(args) {
continue;
}
writeln!(generated, "#[derive(Clone, Copy, Debug)]")?;
writeln!(generated, "#[repr(packed)]")?;
write!(generated, "pub struct Ops{args}(")?;
let mut first = true;
for ch in args.chars().filter(|&ch| ch != 'N') {
if !std::mem::take(&mut first) {
write!(generated, ",")?;
}
write!(generated, "pub Op{ch}")?;
}
writeln!(generated, ");")?;
writeln!(generated, "unsafe impl BytecodeItem for Ops{args} {{}}")?;
}
}
'_max_size: {
let max = instructions()
.map(
|[_, _, ty, _]| {
if ty == "N" {
1
} else {
iter_args(ty).map(arg_to_width).sum::<usize>() + 1
}
},
)
.max()
.unwrap();
writeln!(generated, "pub const MAX_SIZE: usize = {max};")?;
}
'_encoders: {
for [op, name, ty, doc] in instructions() {
writeln!(generated, "/// {}", doc.trim_matches('"'))?;
let name = name.to_lowercase();
let args = comma_sep(
iter_args(ty)
.enumerate()
.map(|(i, c)| format!("{}{i}: {}", arg_to_name(c), arg_to_type(c))),
);
writeln!(generated, "pub fn {name}({args}) -> (usize, [u8; MAX_SIZE]) {{")?;
let arg_names =
comma_sep(iter_args(ty).enumerate().map(|(i, c)| format!("{}{i}", arg_to_name(c))));
writeln!(generated, " unsafe {{ crate::encode({ty}({op}, {arg_names})) }}")?;
writeln!(generated, "}}")?;
}
}
'_structs: {
let mut seen = std::collections::HashSet::new();
for [_, _, ty, _] in instructions() {
if !seen.insert(ty) {
continue;
}
let types = comma_sep(iter_args(ty).map(arg_to_type).map(|s| s.to_string()));
writeln!(generated, "#[repr(packed)] pub struct {ty}(u8, {types});")?;
}
}
'_name_list: {
writeln!(generated, "pub const COUNT: u8 = {};", instructions().count())?;
}
let instr = "Instr";
let oper = "Oper";
'_instr_enum: {
writeln!(generated, "#[derive(Debug, Clone, Copy, PartialEq, Eq)] #[repr(u8)]")?;
writeln!(generated, "pub enum {instr} {{")?;
for [id, name, ..] in instructions() {
writeln!(generated, " {name} = {id},")?;
}
writeln!(generated, "}}")?;
}
'_arg_kind: {
writeln!(generated, "#[derive(Debug, Clone, Copy, PartialEq, Eq)]")?;
writeln!(generated, "pub enum {oper} {{")?;
let mut seen = HashSet::new();
for ty in instructions().flat_map(|[.., ty, _]| iter_args(ty)) {
if !seen.insert(ty) {
continue;
}
writeln!(generated, " {ty}({}),", arg_to_type(ty))?;
}
writeln!(generated, "}}")?;
}
'_parse_opers: {
writeln!(
generated,
"/// This assumes the instruction byte is still at the beginning of the buffer"
)?;
writeln!(generated, "#[cfg(feature = \"disasm\")]")?;
writeln!(generated, "pub fn parse_args(bytes: &mut &[u8], kind: {instr}, buf: &mut alloc::vec::Vec<{oper}>) -> Option<()> {{")?;
writeln!(generated, " match kind {{")?;
let mut instrs = instructions().collect::<Vec<_>>();
instrs.sort_unstable_by_key(|&[.., ty, _]| ty);
for group in instrs.chunk_by(|[.., a, _], [.., b, _]| a == b) {
let ty = group[0][2];
for &[_, name, ..] in group {
writeln!(generated, " | {instr}::{name}")?;
}
generated.pop();
writeln!(generated, " => {{")?;
if iter_args(ty).count() != 0 {
writeln!(generated, " let data = crate::decode::<{ty}>(bytes)?;")?;
writeln!(
generated,
" buf.extend([{}]);",
comma_sep(
iter_args(ty).zip(1u32..).map(|(t, i)| format!("{oper}::{t}(data.{i})"))
)
)?;
} else {
writeln!(generated, " crate::decode::<{ty}>(bytes)?;")?;
}
writeln!(generated, " }}")?;
}
writeln!(generated, " }}")?;
writeln!(generated, " Some(())")?;
writeln!(generated, "}}")?;
}
std::fs::write("src/instrs.rs", generated)?;
Ok(())
}
fn comma_sep(items: impl Iterator<Item = String>) -> String {
items.map(|item| item.to_string()).collect::<Vec<_>>().join(", ")
}
fn instructions() -> impl Iterator<Item = [&'static str; 4]> {
include_str!("instructions.in")
.lines()
.filter_map(|line| line.strip_suffix(';'))
.map(|line| line.splitn(4, ',').map(str::trim).next_chunk().unwrap())
}
fn arg_to_type(arg: char) -> &'static str {
match arg {
'R' | 'B' => "u8",
'H' => "u16",
'W' => "u32",
'D' | 'A' => "u64",
'P' => "i16",
'O' => "i32",
_ => panic!("unknown type: {}", arg),
}
}
fn arg_to_width(arg: char) -> usize {
match arg {
'R' | 'B' => 1,
'H' => 2,
'W' => 4,
'D' | 'A' => 8,
'P' => 2,
'O' => 4,
_ => panic!("unknown type: {}", arg),
}
}
fn arg_to_name(arg: char) -> &'static str {
match arg {
'R' => "reg",
'B' | 'H' | 'W' | 'D' => "imm",
'P' | 'O' => "offset",
'A' => "addr",
_ => panic!("unknown type: {}", arg),
}
}
fn iter_args(ty: &'static str) -> impl Iterator<Item = char> {
ty.chars().filter(|c| *c != 'N')
}

284
bytecode/src/lib.rs
View file

@ -1,284 +0,0 @@
#![no_std]
#[cfg(feature = "disasm")]
extern crate alloc;
pub use crate::instrs::*;
use core::convert::TryFrom;
mod instrs;
type OpR = u8;
type OpA = u64;
type OpO = i32;
type OpP = i16;
type OpB = u8;
type OpH = u16;
type OpW = u32;
type OpD = u64;
/// # Safety
/// Has to be valid to be decoded from bytecode.
pub unsafe trait BytecodeItem {}
unsafe impl BytecodeItem for u8 {}
impl TryFrom<u8> for Instr {
type Error = u8;
#[inline]
fn try_from(value: u8) -> Result<Self, Self::Error> {
#[cold]
fn failed(value: u8) -> Result<Instr, u8> {
Err(value)
}
if value < COUNT {
unsafe { Ok(core::mem::transmute::<u8, Instr>(value)) }
} else {
failed(value)
}
}
}
#[inline]
unsafe fn encode<T>(instr: T) -> (usize, [u8; instrs::MAX_SIZE]) {
let mut buf = [0; instrs::MAX_SIZE];
core::ptr::write(buf.as_mut_ptr() as *mut T, instr);
(core::mem::size_of::<T>(), buf)
}
#[inline]
#[cfg(feature = "disasm")]
fn decode<T>(binary: &mut &[u8]) -> Option<T> {
let (front, rest) = core::mem::take(binary).split_at_checked(core::mem::size_of::<T>())?;
*binary = rest;
unsafe { Some(core::ptr::read(front.as_ptr() as *const T)) }
}
/// Rounding mode
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
#[repr(u8)]
pub enum RoundingMode {
NearestEven = 0,
Truncate = 1,
Up = 2,
Down = 3,
}
impl TryFrom<u8> for RoundingMode {
type Error = ();
fn try_from(value: u8) -> Result<Self, Self::Error> {
(value <= 3).then(|| unsafe { core::mem::transmute(value) }).ok_or(())
}
}
#[cfg(feature = "disasm")]
#[derive(Clone, Copy)]
pub enum DisasmItem {
Func,
Global,
}
#[cfg(feature = "disasm")]
#[derive(Debug)]
pub enum DisasmError<'a> {
InvalidInstruction(u8),
InstructionOutOfBounds(&'a str),
FmtFailed(core::fmt::Error),
HasOutOfBoundsJumps,
}
#[cfg(feature = "disasm")]
impl From<core::fmt::Error> for DisasmError<'_> {
fn from(value: core::fmt::Error) -> Self {
Self::FmtFailed(value)
}
}
#[cfg(feature = "disasm")]
impl core::fmt::Display for DisasmError<'_> {
fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result {
match *self {
DisasmError::InvalidInstruction(b) => write!(f, "invalid instruction opcode: {b}"),
DisasmError::InstructionOutOfBounds(name) => {
write!(f, "instruction would go out of bounds of {name} symbol")
}
DisasmError::FmtFailed(error) => write!(f, "fmt failed: {error}"),
DisasmError::HasOutOfBoundsJumps => write!(
f,
"the code contained jumps that dont got neither to a \
valid symbol or local insturction"
),
}
}
}
#[cfg(feature = "disasm")]
impl core::error::Error for DisasmError<'_> {}
#[cfg(feature = "disasm")]
pub fn disasm<'a>(
binary: &mut &[u8],
functions: &alloc::collections::BTreeMap<u32, (&'a str, u32, DisasmItem)>,
out: &mut alloc::string::String,
mut eca_handler: impl FnMut(&mut &[u8]),
) -> Result<(), DisasmError<'a>> {
use {
self::instrs::Instr,
alloc::{
collections::btree_map::{BTreeMap, Entry},
vec::Vec,
},
core::{convert::TryInto, fmt::Write},
};
fn instr_from_byte(b: u8) -> Result<Instr, DisasmError<'static>> {
b.try_into().map_err(DisasmError::InvalidInstruction)
}
let mut labels = BTreeMap::<u32, u32>::default();
let mut buf = Vec::<instrs::Oper>::new();
let mut has_oob = false;
'_offset_pass: for (&off, &(name, len, kind)) in functions.iter() {
if matches!(kind, DisasmItem::Global) {
continue;
}
let prev = *binary;
*binary = &binary[off as usize..];
let mut label_count = 0;
while let Some(&byte) = binary.first() {
let offset: i32 = (prev.len() - binary.len()).try_into().unwrap();
if offset as u32 == off + len {
break;
}
let Ok(inst) = instr_from_byte(byte) else { break };
instrs::parse_args(binary, inst, &mut buf)
.ok_or(DisasmError::InstructionOutOfBounds(name))?;
for op in buf.drain(..) {
let rel = match op {
instrs::Oper::O(rel) => rel,
instrs::Oper::P(rel) => rel.into(),
_ => continue,
};
let global_offset: u32 = (offset + rel).try_into().unwrap();
if functions.get(&global_offset).is_some() {
continue;
}
label_count += match labels.entry(global_offset) {
Entry::Occupied(_) => 0,
Entry::Vacant(entry) => {
entry.insert(label_count);
1
}
}
}
if matches!(inst, Instr::ECA) {
eca_handler(binary);
}
}
*binary = prev;
}
let mut ordered = functions.iter().collect::<Vec<_>>();
ordered.sort_unstable_by_key(|(_, (name, _, _))| name);
'_dump: for (&off, &(name, len, kind)) in ordered {
if matches!(kind, DisasmItem::Global) {
continue;
}
let prev = *binary;
writeln!(out, "{name}:")?;
*binary = &binary[off as usize..];
while let Some(&byte) = binary.first() {
let offset: i32 = (prev.len() - binary.len()).try_into().unwrap();
if offset as u32 == off + len {
break;
}
let Ok(inst) = instr_from_byte(byte) else {
writeln!(out, "invalid instr {byte}")?;
break;
};
instrs::parse_args(binary, inst, &mut buf).unwrap();
if let Some(label) = labels.get(&offset.try_into().unwrap()) {
write!(out, "{:>2}: ", label)?;
} else {
write!(out, " ")?;
}
write!(out, "{inst:<8?} ")?;
'a: for (i, op) in buf.drain(..).enumerate() {
if i != 0 {
write!(out, ", ")?;
}
let rel = 'b: {
match op {
instrs::Oper::O(rel) => break 'b rel,
instrs::Oper::P(rel) => break 'b rel.into(),
instrs::Oper::R(r) => write!(out, "r{r}")?,
instrs::Oper::B(b) => write!(out, "{b}b")?,
instrs::Oper::H(h) => write!(out, "{h}h")?,
instrs::Oper::W(w) => write!(out, "{w}w")?,
instrs::Oper::D(d) if (d as i64) < 0 => write!(out, "{}d", d as i64)?,
instrs::Oper::D(d) => write!(out, "{d}d")?,
instrs::Oper::A(a) => write!(out, "{a}a")?,
}
continue 'a;
};
let global_offset: u32 = (offset + rel).try_into().unwrap();
if let Some(&(name, ..)) = functions.get(&global_offset) {
if name.contains('\0') {
write!(out, ":{name:?}")?;
} else {
write!(out, ":{name}")?;
}
} else {
let local_has_oob = global_offset < off
|| global_offset > off + len
|| prev
.get(global_offset as usize)
.map_or(true, |&b| instr_from_byte(b).is_err())
|| prev[global_offset as usize] == 0;
has_oob |= local_has_oob;
let label = labels.get(&global_offset).unwrap();
if local_has_oob {
write!(out, "!!!!!!!!!{rel}")?;
} else {
write!(out, ":{label}")?;
}
}
}
writeln!(out)?;
if matches!(inst, Instr::ECA) {
eca_handler(binary);
}
}
*binary = prev;
}
if has_oob {
return Err(DisasmError::HasOutOfBoundsJumps);
}
Ok(())
}

23
depell/Cargo.toml
View file

@ -1,23 +0,0 @@
[package]
name = "depell"
version = "0.1.0"
edition = "2021"
[dependencies]
argon2 = "0.5.3"
axum = "0.7.7"
axum-server = { version = "0.7.1", optional = true, features = ["rustls", "tls-rustls"] }
const_format = "0.2.33"
getrandom = "0.2.15"
hblang.workspace = true
htmlm = "0.5.0"
log = "0.4.22"
rand_core = { version = "0.6.4", features = ["getrandom"] }
rusqlite = { version = "0.32.1", features = ["bundled"] }
serde = { version = "1.0.210", features = ["derive"] }
time = "0.3.36"
tokio = { version = "1.40.0", features = ["rt"] }
[features]
#default = ["tls"]
tls = ["dep:axum-server"]

14
depell/README.md
View file

@ -1,14 +0,0 @@
# Depell
Depell is a website that allows users to import/post/run hblang code and create huge dependency graphs. Its currently hosted at https://depell.mlokis.tech.
## Local Development
Prerequirements:
- rust nigthly toolchain: install rust from [here](https://www.rust-lang.org/tools/install)
```bash
rustup default nightly
cargo xtask watch-depell-debug
# browser http://localhost:8080
```

1
depell/src/icons/download.svg
View file

@ -1 +0,0 @@
<svg xmlns="http://www.w3.org/2000/svg" height="24px" viewBox="0 -960 960 960" width="24px" fill="#e8eaed"><path d="M480-320 280-520l56-58 104 104v-326h80v326l104-104 56 58-200 200ZM240-160q-33 0-56.5-23.5T160-240v-120h80v120h480v-120h80v120q0 33-23.5 56.5T720-160H240Z"/></svg>
Side by side

Before

Width:  |  Height:  |  Size: 279 B

1
depell/src/icons/run.svg
View file

@ -1 +0,0 @@
<svg xmlns="http://www.w3.org/2000/svg" height="24px" viewBox="0 -960 960 960" width="24px" fill="#e8eaed"><path d="M320-200v-560l440 280-440 280Zm80-280Zm0 134 210-134-210-134v268Z"/></svg>
Side by side

Before

Width:  |  Height:  |  Size: 190 B

207
depell/src/index.css
View file

@ -1,207 +0,0 @@
* {
font-family: var(--font);
}
body {
--primary: light-dark(white, #181A1B);
--secondary: light-dark(#EFEFEF, #212425);
--timestamp: light-dark(#555555, #AAAAAA);
--error: #ff3333;
}
body {
--small-gap: 5px;
--font: system-ui, -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Oxygen, Ubuntu, Cantarell, 'Open Sans', 'Helvetica Neue', sans-serif;
--monospace: 'Courier New', Courier, monospace;
nav {
display: flex;
justify-content: space-between;
align-items: center;
section:last-child {
display: flex;
gap: var(--small-gap);
}
}
main {
margin-top: var(--small-gap);
display: flex;
flex-direction: column;
gap: var(--small-gap);
}
}
div.preview {
margin: var(--small-gap) 0px;
display: flex;
flex-direction: column;
gap: var(--small-gap);
div.info {
display: flex;
gap: var(--small-gap);
span[apply=timestamp] {
color: var(--timestamp);
}
}
div.stat {
display: flex;
svg {
height: 18px;
}
}
div.code {
position: relative;
nav {
position: absolute;
right: 0;
padding: var(--small-gap);
button {
display: flex;
padding: 0;
}
}
}
}
svg {
fill: black;
}
form {
display: flex;
flex-direction: column;
gap: var(--small-gap);
.error {
color: var(--error);
text-align: center;
}
}
textarea {
outline: none;
border: none;
background: var(--secondary);
padding: var(--small-gap);
padding-top: calc(var(--small-gap) * 1.5);
font-family: var(--monospace);
resize: none;
tab-size: 4;
}
pre {
background: var(--secondary);
padding: var(--small-gap);
padding-top: calc(var(--small-gap) * 1.5);
margin: 0px;
font-family: var(--monospace);
tab-size: 4;
overflow-x: auto;
white-space: pre-wrap;
word-wrap: break-word;
}
input {
font-size: inherit;
outline: none;
border: none;
background: var(--secondary);
padding: var(--small-gap);
}
input:is(:hover, :focus) {
background: var(--primary);
}
button {
border: none;
outline: none;
font-size: inherit;
background: var(--secondary);
}
button:hover:not(:active) {
background: var(--primary);
}
div#code-editor {
display: flex;
position: relative;
textarea {
flex: 1;
}
span#code-size {
position: absolute;
right: 2px;
font-size: 12px;
}
}
div#dep-list {
display: flex;
flex-direction: column;
align-items: center;
gap: var(--small-gap);
section {
width: 100%;
display: flex;
flex-direction: column;
text-align: center;
gap: var(--small-gap);
div {
text-align: left;
}
}
}
.syn {
font-family: var(--monospace);
&.Comment {
color: #939f91;
}
&.Keyword {
color: #f85552;
}
&.Identifier,
&.Directive {
color: #3a94c5;
}
/* &.Number {} */
&.String {
color: #8da101;
}
&.Op,
&.Assign {
color: #f57d26;
}
&.Paren,
&.Bracket,
&.Comma,
&.Dot,
&.Ctor,
&.Colon {
color: light-dark(#5c6a72, #999999);
}
}

551
depell/src/index.js
View file

@ -1,551 +0,0 @@
/// @ts-check
/** @return {never} */
function never() { throw new Error() }
/**@type{WebAssembly.Instance}*/ let hbcInstance;
/**@type{Promise<WebAssembly.WebAssemblyInstantiatedSource>}*/ let hbcInstaceFuture;
async function getHbcInstance() {
hbcInstaceFuture ??= WebAssembly.instantiateStreaming(fetch("/hbc.wasm"), {});
return hbcInstance ??= (await hbcInstaceFuture).instance;
}
const stack_pointer_offset = 1 << 20;
/** @param {WebAssembly.Instance} instance @param {Post[]} packages @param {number} fuel
* @returns {string} */
function compileCode(instance, packages, fuel = 100) {
let {
INPUT, INPUT_LEN,
LOG_MESSAGES, LOG_MESSAGES_LEN,
memory, compile_and_run,
} = instance.exports;
if (!(true
&& memory instanceof WebAssembly.Memory
&& INPUT instanceof WebAssembly.Global
&& INPUT_LEN instanceof WebAssembly.Global
&& LOG_MESSAGES instanceof WebAssembly.Global
&& LOG_MESSAGES_LEN instanceof WebAssembly.Global
&& typeof compile_and_run === "function"
)) never();
const codeLength = packPosts(packages, new DataView(memory.buffer, INPUT.value));
new DataView(memory.buffer).setUint32(INPUT_LEN.value, codeLength, true);
runWasmFunction(instance, compile_and_run, fuel);
return bufToString(memory, LOG_MESSAGES, LOG_MESSAGES_LEN).trim();
}
/**@type{WebAssembly.Instance}*/ let fmtInstance;
/**@type{Promise<WebAssembly.WebAssemblyInstantiatedSource>}*/ let fmtInstaceFuture;
async function getFmtInstance() {
fmtInstaceFuture ??= WebAssembly.instantiateStreaming(fetch("/hbfmt.wasm"), {});
return fmtInstance ??= (await fmtInstaceFuture).instance;
}
/** @param {WebAssembly.Instance} instance @param {string} code @param {"tok" | "fmt" | "minify"} action
* @returns {string | Uint8Array | undefined} */
function modifyCode(instance, code, action) {
let {
INPUT, INPUT_LEN,
OUTPUT, OUTPUT_LEN,
memory, fmt, tok, minify
} = instance.exports;
let funs = { fmt, tok, minify };
let fun = funs[action];
if (!(true
&& memory instanceof WebAssembly.Memory
&& INPUT instanceof WebAssembly.Global
&& INPUT_LEN instanceof WebAssembly.Global
&& OUTPUT instanceof WebAssembly.Global
&& OUTPUT_LEN instanceof WebAssembly.Global
&& funs.hasOwnProperty(action)
&& typeof fun === "function"
)) never();
if (action !== "fmt") {
INPUT = OUTPUT;
INPUT_LEN = OUTPUT_LEN;
}
let dw = new DataView(memory.buffer);
dw.setUint32(INPUT_LEN.value, code.length, true);
new Uint8Array(memory.buffer, INPUT.value).set(new TextEncoder().encode(code));
if (!runWasmFunction(instance, fun)) {
return undefined;
}
if (action === "tok") {
return bufSlice(memory, OUTPUT, OUTPUT_LEN);
} else {
return bufToString(memory, OUTPUT, OUTPUT_LEN);
}
}
/** @param {WebAssembly.Instance} instance @param {CallableFunction} func @param {any[]} args
* @returns {boolean} */
function runWasmFunction(instance, func, ...args) {
const { PANIC_MESSAGE, PANIC_MESSAGE_LEN, memory, stack_pointer } = instance.exports;
if (!(true
&& memory instanceof WebAssembly.Memory
&& stack_pointer instanceof WebAssembly.Global
)) never();
const ptr = stack_pointer.value;
try {
func(...args);
return true;
} catch (error) {
if (error instanceof WebAssembly.RuntimeError
&& error.message == "unreachable"
&& PANIC_MESSAGE instanceof WebAssembly.Global
&& PANIC_MESSAGE_LEN instanceof WebAssembly.Global) {
console.error(bufToString(memory, PANIC_MESSAGE, PANIC_MESSAGE_LEN), error);
} else {
console.error(error);
}
stack_pointer.value = ptr;
return false;
}
}
/** @typedef {Object} Post
* @property {string} path
* @property {string} code */
/** @param {Post[]} posts @param {DataView} view @returns {number} */
function packPosts(posts, view) {
const enc = new TextEncoder(), buf = new Uint8Array(view.buffer, view.byteOffset);
let len = 0; for (const post of posts) {
view.setUint16(len, post.path.length, true); len += 2;
buf.set(enc.encode(post.path), len); len += post.path.length;
view.setUint16(len, post.code.length, true); len += 2;
buf.set(enc.encode(post.code), len); len += post.code.length;
}
return len;
}
/** @param {WebAssembly.Memory} mem
* @param {WebAssembly.Global} ptr
* @param {WebAssembly.Global} len
* @return {Uint8Array} */
function bufSlice(mem, ptr, len) {
return new Uint8Array(mem.buffer, ptr.value,
new DataView(mem.buffer).getUint32(len.value, true));
}
/** @param {WebAssembly.Memory} mem
* @param {WebAssembly.Global} ptr
* @param {WebAssembly.Global} len
* @return {string} */
function bufToString(mem, ptr, len) {
const res = new TextDecoder()
.decode(new Uint8Array(mem.buffer, ptr.value,
new DataView(mem.buffer).getUint32(len.value, true)));
new DataView(mem.buffer).setUint32(len.value, 0, true);
return res;
}
/** @param {HTMLElement} target */
function wireUp(target) {
execApply(target);
cacheInputs(target);
bindCodeEdit(target);
bindTextareaAutoResize(target);
}
const importRe = /@use\s*\(\s*"(([^"]|\\")+)"\s*\)/g;
/** @param {WebAssembly.Instance} fmt
* @param {string} code
* @param {string[]} roots
* @param {Post[]} buf
* @param {Set<string>} prevRoots
* @returns {void} */
function loadCachedPackages(fmt, code, roots, buf, prevRoots) {
buf[0].code = code;
roots.length = 0;
let changed = false;
for (const match of code.matchAll(importRe)) {
changed ||= !prevRoots.has(match[1]);
roots.push(match[1]);
}
if (!changed) return;
buf.length = 1;
prevRoots.clear();
for (let imp = roots.pop(); imp !== undefined; imp = roots.pop()) {
if (prevRoots.has(imp)) continue; prevRoots.add(imp);
const fmtd = modifyCode(fmt, localStorage.getItem("package-" + imp) ?? never(), "fmt");
if (typeof fmtd != "string") never();
buf.push({ path: imp, code: fmtd });
for (const match of buf[buf.length - 1].code.matchAll(importRe)) {
roots.push(match[1]);
}
}
}
/**@type{Set<string>}*/ const prevRoots = new Set();
/**@typedef {Object} PackageCtx
* @property {AbortController} [cancelation]
* @property {string[]} keyBuf
* @property {Set<string>} prevParams
* @property {HTMLTextAreaElement} [edit] */
/** @param {string} source @param {Set<string>} importDiff @param {HTMLPreElement} errors @param {PackageCtx} ctx */
async function fetchPackages(source, importDiff, errors, ctx) {
importDiff.clear();
for (const match of source.matchAll(importRe)) {
if (localStorage["package-" + match[1]]) continue;
importDiff.add(match[1]);
}
if (importDiff.size !== 0 && (ctx.prevParams.size != importDiff.size
|| [...ctx.prevParams.keys()].every(e => importDiff.has(e)))) {
if (ctx.cancelation) ctx.cancelation.abort();
ctx.prevParams.clear();
ctx.prevParams = new Set([...importDiff]);
ctx.cancelation = new AbortController();
ctx.keyBuf.length = 0;
ctx.keyBuf.push(...importDiff.keys());
errors.textContent = "fetching: " + ctx.keyBuf.join(", ");
await fetch(`/code`, {
method: "POST",
signal: ctx.cancelation.signal,
headers: { "Content-Type": "application/json" },
body: JSON.stringify(ctx.keyBuf),
}).then(async e => {
try {
const json = await e.json();
if (e.status == 200) {
for (const [key, value] of Object.entries(json)) {
localStorage["package-" + key] = value;
}
const missing = ctx.keyBuf.filter(i => json[i] === undefined);
if (missing.length !== 0) {
errors.textContent = "deps not found: " + missing.join(", ");
} else {
ctx.cancelation = undefined;
ctx.edit?.dispatchEvent(new InputEvent("input"));
}
}
} catch (er) {
errors.textContent = "completely failed to fetch ("
+ e.status + "): " + ctx.keyBuf.join(", ");
console.error(e, er);
}
});
}
}
/** @param {HTMLElement} target */
async function bindCodeEdit(target) {
const edit = target.querySelector("#code-edit");
if (!(edit instanceof HTMLTextAreaElement)) return;
const codeSize = target.querySelector("#code-size");
const errors = target.querySelector("#compiler-output");
if (!(true
&& codeSize instanceof HTMLSpanElement
&& errors instanceof HTMLPreElement
)) never();
const MAX_CODE_SIZE = parseInt(codeSize.innerHTML);
if (Number.isNaN(MAX_CODE_SIZE)) never();
const hbc = await getHbcInstance(), fmt = await getFmtInstance();
let importDiff = new Set();
/**@type{Post[]}*/
const packages = [{ path: "local.hb", code: "" }];
const debounce = 100;
let timeout = 0;
const ctx = { keyBuf: [], prevParams: new Set(), edit };
prevRoots.clear();
const onInput = () => {
fetchPackages(edit.value, importDiff, errors, ctx);
if (ctx.cancelation && importDiff.size !== 0) {
return;
}
loadCachedPackages(fmt, edit.value, ctx.keyBuf, packages, prevRoots);
errors.textContent = compileCode(hbc, packages);
const minified_size = modifyCode(fmt, edit.value, "minify")?.length;
if (minified_size) {
codeSize.textContent = (MAX_CODE_SIZE - minified_size) + "";
const perc = Math.min(100, Math.floor(100 * (minified_size / MAX_CODE_SIZE)));
codeSize.style.color = `color-mix(in srgb, light-dark(black, white), var(--error) ${perc}%)`;
}
timeout = 0;
};
edit.addEventListener("input", () => {
if (timeout) clearTimeout(timeout);
timeout = setTimeout(onInput, debounce)
});
edit.dispatchEvent(new InputEvent("input"));
}
/**
* @type {Array<string>}
* to be synched with `enum TokenGroup` in bytecode/src/fmt.rs */
const TOK_CLASSES = [
'Blank',
'Comment',
'Keyword',
'Identifier',
'Directive',
'Number',
'String',
'Op',
'Assign',
'Paren',
'Bracket',
'Colon',
'Comma',
'Dot',
'Ctor',
];
/** @type {{ [key: string]: (el: HTMLElement) => void | Promise<void> }} */
const applyFns = {
timestamp: (el) => {
const timestamp = el.innerText;
const date = new Date(parseInt(timestamp) * 1000);
el.innerText = date.toLocaleString();
},
fmt,
};
/**
* @param {HTMLElement} target */
async function fmt(target) {
const code = target.innerText;
const instance = await getFmtInstance();
const decoder = new TextDecoder('utf-8');
const fmt = modifyCode(instance, code, 'fmt');
if (typeof fmt !== "string") never()
const codeBytes = new TextEncoder().encode(fmt);
const tok = modifyCode(instance, fmt, 'tok');
if (!(tok instanceof Uint8Array)) never();
target.innerHTML = '';
let start = 0;
let kind = tok[0];
for (let ii = 1; ii <= tok.length; ii += 1) {
// split over same tokens and buffer end
if (tok[ii] === kind && ii < tok.length) {
continue;
}
const text = decoder.decode(codeBytes.subarray(start, ii));
const textNode = document.createTextNode(text);;
if (kind === 0) {
target.appendChild(textNode);
} else {
const el = document.createElement('span');
el.classList.add('syn');
el.classList.add(TOK_CLASSES[kind]);
el.appendChild(textNode);
target.appendChild(el);
}
if (ii == tok.length) {
break;
}
start = ii;
kind = tok[ii];
}
}
/** @param {HTMLElement} target */
function execApply(target) {
const proises = [];
for (const elem of target.querySelectorAll('[apply]')) {
if (!(elem instanceof HTMLElement)) continue;
const funcname = elem.getAttribute('apply') ?? never();
const vl = applyFns[funcname](elem);
if (vl instanceof Promise) proises.push(vl);
}
if (target === document.body) {
Promise.all(proises).then(() => document.body.hidden = false);
}
}
/** @param {HTMLElement} target */
function bindTextareaAutoResize(target) {
for (const textarea of target.querySelectorAll("textarea")) {
if (!(textarea instanceof HTMLTextAreaElement)) never();
const taCssMap = window.getComputedStyle(textarea);
const padding = parseInt(taCssMap.getPropertyValue('padding-top') ?? "0")
+ parseInt(taCssMap.getPropertyValue('padding-top') ?? "0");
textarea.style.height = "auto";
textarea.style.height = (textarea.scrollHeight - padding) + "px";
textarea.style.overflowY = "hidden";
textarea.addEventListener("input", function() {
let top = window.scrollY;
textarea.style.height = "auto";
textarea.style.height = (textarea.scrollHeight - padding) + "px";
window.scrollTo({ top });
});
textarea.onkeydown = (ev) => {
if (ev.key === "Tab") {
ev.preventDefault();
document.execCommand('insertText', false, "\t");
}
}
}
}
/** @param {HTMLElement} target */
function cacheInputs(target) {
/**@type {HTMLFormElement}*/ let form;
for (form of target.querySelectorAll('form')) {
const path = form.getAttribute('hx-post') || form.getAttribute('hx-delete');
if (!path) {
console.warn('form does not have a hx-post or hx-delete attribute', form);
continue;
}
for (const input of form.elements) {
if (input instanceof HTMLInputElement || input instanceof HTMLTextAreaElement) {
if ('password submit button'.includes(input.type)) continue;
const key = path + input.name;
input.value = localStorage.getItem(key) ?? '';
input.addEventListener("input", () => localStorage.setItem(key, input.value));
} else {
console.warn("unhandled form element: ", input);
}
}
}
}
/** @param {string} [path] */
function updateTab(path) {
for (const elem of document.querySelectorAll("button[hx-push-url]")) {
if (elem instanceof HTMLButtonElement)
elem.disabled = elem.getAttribute("hx-push-url") === (path ?? window.location.pathname);
}
}
if (window.location.hostname === 'localhost') {
let id; setInterval(async () => {
let new_id = await fetch('/hot-reload').then(reps => reps.text());
id ??= new_id;
if (id !== new_id) window.location.reload();
}, 300);
(async function test() {
{
const code = "main:=fn():void{return}";
const inst = await getFmtInstance()
const fmtd = modifyCode(inst, code, "fmt") ?? never();
if (typeof fmtd !== "string") never();
const prev = modifyCode(inst, fmtd, "minify") ?? never();
if (code != prev) console.error(code, prev);
}
{
const posts = [{
path: "foo.hb",
code: "main:=fn():int{return 42}",
}];
const res = compileCode(await getHbcInstance(), posts, 1) ?? never();
const expected = "exit code: 42";
if (expected != res) console.error(expected, res);
}
})()
}
document.body.addEventListener('htmx:afterSwap', (ev) => {
if (!(ev.target instanceof HTMLElement)) never();
wireUp(ev.target);
if (ev.target.tagName == "MAIN" || ev.target.tagName == "BODY")
updateTab(ev['detail'].pathInfo.finalRequestPath);
});
getFmtInstance().then(inst => {
document.body.addEventListener('htmx:configRequest', (ev) => {
const details = ev['detail'];
if (details.path === "/post" && details.verb === "post") {
details.parameters['code'] = modifyCode(inst, details.parameters['code'], "minify");
}
});
/** @param {string} query @param {string} target @returns {number} */
function fuzzyCost(query, target) {
let qi = 0, bi = 0, cost = 0, matched = false;
while (qi < query.length) {
if (query.charAt(qi) === target.charAt(bi++)) {
matched = true;
qi++;
} else {
cost++;
}
if (bi === target.length) (bi = 0, qi++);
}
return cost + (matched ? 0 : 100 * target.length);
}
let deps = undefined;
/** @param {HTMLInputElement} input @returns {void} */
function filterCodeDeps(input) {
deps ??= document.getElementById("deps");
if (!(deps instanceof HTMLElement)) never();
if (input.value === "") {
deps.textContent = "results show here...";
return;
}
deps.innerHTML = "";
for (const root of [...prevRoots.keys()]
.sort((a, b) => fuzzyCost(input.value, a) - fuzzyCost(input.value, b))) {
const pane = document.createElement("div");
const code = modifyCode(inst, localStorage["package-" + root], "fmt");
pane.innerHTML = `<div>${root}</div><pre>${code}</pre>`;
deps.appendChild(pane);
}
if (deps.innerHTML === "") {
deps.textContent = "no results";
}
}
Object.assign(window, { filterCodeDeps });
});
/** @param {HTMLElement} target */
function runPost(target) {
while (!target.matches("div[class=preview]")) target = target.parentElement ?? never();
const code = target.querySelector("pre[apply=fmt]");
if (!(code instanceof HTMLPreElement)) never();
const output = target.querySelector("pre[id=compiler-output]");
if (!(output instanceof HTMLPreElement)) never();
Promise.all([getHbcInstance(), getFmtInstance()]).then(async ([hbc, fmt]) => {
const ctx = { keyBuf: [], prevParams: new Set() };
await fetchPackages(code.innerText ?? never(), new Set(), output, ctx);
const posts = [{ path: "this", code: "" }];
loadCachedPackages(fmt, code.innerText ?? never(), ctx.keyBuf, posts, new Set());
output.textContent = compileCode(hbc, posts);
output.hidden = false;
});
let author = encodeURIComponent(target.dataset.author ?? never());
let name = encodeURIComponent(target.dataset.name ?? never());
fetch(`/post/run?author=${author}&name=${name}`, { method: "POST" })
}
Object.assign(window, { runPost });
updateTab();
wireUp(document.body);

972
depell/src/main.rs
View file

@ -1,972 +0,0 @@
#![feature(iter_collect_into)]
use {
argon2::{password_hash::SaltString, PasswordVerifier},
axum::{
body::Bytes,
extract::{DefaultBodyLimit, Path},
http::{header::COOKIE, request::Parts, StatusCode},
response::{AppendHeaders, Html},
},
const_format::formatcp,
core::fmt,
htmlm::{html, write_html},
rand_core::OsRng,
serde::{Deserialize, Serialize},
std::{
collections::{HashMap, HashSet},
fmt::{Display, Write},
net::Ipv4Addr,
},
};
const MAX_NAME_LENGTH: usize = 32;
const MAX_POSTNAME_LENGTH: usize = 64;
const MAX_CODE_LENGTH: usize = 1024 * 4;
const SESSION_DURATION_SECS: u64 = 60 * 60;
const MAX_FEED_SIZE: usize = 8 * 1024;
type Redirect<const COUNT: usize = 1> = AppendHeaders<[(&'static str, &'static str); COUNT]>;
macro_rules! static_asset {
($mime:literal, $body:literal) => {
get(|| async {
axum::http::Response::builder()
.header("content-type", $mime)
.header("content-encoding", "gzip")
.body(axum::body::Body::from(Bytes::from_static(include_bytes!(concat!(
$body, ".gz"
)))))
.unwrap()
})
};
}
async fn amain() {
use axum::routing::{delete, get, post};
let debug = cfg!(debug_assertions);
log::set_logger(&Logger).unwrap();
log::set_max_level(if debug { log::LevelFilter::Warn } else { log::LevelFilter::Error });
db::init();
let router = axum::Router::new()
.route("/", get(Index::page))
.route("/index.css", static_asset!("text/css", "index.css"))
.route("/index.js", static_asset!("text/javascript", "index.js"))
.route("/hbfmt.wasm", static_asset!("application/wasm", "hbfmt.wasm"))
.route("/hbc.wasm", static_asset!("application/wasm", "hbc.wasm"))
.route("/index-view", get(Index::get))
.route("/feed", get(Feed::page))
.route("/feed-view", get(Feed::get))
.route("/feed-more", post(Feed::more))
.route("/profile", get(Profile::page))
.route("/profile-view", get(Profile::get))
.route("/profile/:name", get(Profile::get_other_page))
.route("/profile/password", post(PasswordChange::post))
.route("/profile-view/:name", get(Profile::get_other))
.route("/post", get(Post::page))
.route("/post-view", get(Post::get))
.route("/post", post(Post::post))
.route("/post/run", post(Post::run))
.route("/code", post(fetch_code))
.route("/login", get(Login::page))
.route("/login-view", get(Login::get))
.route("/login", post(Login::post))
.route("/login", delete(Login::delete))
.route("/signup", get(Signup::page))
.route("/signup-view", get(Signup::get))
.route("/signup", post(Signup::post))
.route(
"/hot-reload",
get({
let id = std::time::SystemTime::now()
.duration_since(std::time::SystemTime::UNIX_EPOCH)
.unwrap()
.as_millis();
move || async move { id.to_string() }
}),
)
.layer(DefaultBodyLimit::max(16 * 1024));
#[cfg(feature = "tls")]
{
let addr =
(Ipv4Addr::UNSPECIFIED, std::env::var("DEPELL_PORT").unwrap().parse::<u16>().unwrap());
let config = axum_server::tls_rustls::RustlsConfig::from_pem_file(
std::env::var("DEPELL_CERT_PATH").unwrap(),
std::env::var("DEPELL_KEY_PATH").unwrap(),
)
.await
.unwrap();
axum_server::bind_rustls(addr.into(), config)
.serve(router.into_make_service())
.await
.unwrap();
}
#[cfg(not(feature = "tls"))]
{
let addr = (Ipv4Addr::UNSPECIFIED, 8080);
let socket = tokio::net::TcpListener::bind(addr).await.unwrap();
axum::serve(socket, router).await.unwrap();
}
}
async fn fetch_code(
axum::Json(paths): axum::Json<Vec<String>>,
) -> axum::Json<HashMap<String, String>> {
let mut deps = HashMap::<String, String>::new();
db::with(|db| {
for path in &paths {
let Some((author, name)) = path.split_once('/') else { continue };
db.fetch_deps
.query_map((name, author), |r| {
Ok((
r.get::<_, String>(1)? + "/" + r.get_ref(0)?.as_str()?,
r.get::<_, String>(2)?,
))
})
.log("fetch deps query")
.into_iter()
.flatten()
.filter_map(|r| r.log("deps row"))
.collect_into(&mut deps);
}
});
axum::Json(deps)
}
#[derive(Deserialize)]
#[serde(untagged)]
enum Feed {
Before { before_timestamp: u64 },
}
#[derive(Deserialize)]
struct Before {
before_timestamp: u64,
}
impl Feed {
async fn more(session: Session, axum::Form(data): axum::Form<Before>) -> Html<String> {
Self::Before { before_timestamp: data.before_timestamp }.render(&session)
}
}
impl Default for Feed {
fn default() -> Self {
Self::Before { before_timestamp: now() + 3600 }
}
}
impl Page for Feed {
fn render_to_buf(self, _: &Session, buf: &mut String) {
db::with(|db| {
let cursor = match self {
Feed::Before { before_timestamp } => db
.get_pots_before
.query_map((before_timestamp,), Post::from_row)
.log("fetch before posts query")
.into_iter()
.flatten()
.filter_map(|r| r.log("fetch before posts row")),
};
let base_len = buf.len();
let mut last_timestamp = None;
for post in cursor {
write!(buf, "{}", post).unwrap();
if buf.len() - base_len > MAX_FEED_SIZE {
last_timestamp = Some(post.timestamp);
break;
}
}
write_html!((*buf)
if let Some(last_timestamp) = last_timestamp {
<div "hx-post"="/feed-more"
"hx-trigger"="intersect once"
"hx-swap"="outerHTML"
"hx-vals"={format_args!("{{\"before_timestamp\":{last_timestamp}}}")}
>"there might be more"</div>
} else {
"no more stuff"
}
);
});
}
}
#[derive(Default)]
struct Index;
impl PublicPage for Index {
fn render_to_buf(self, buf: &mut String) {
buf.push_str(include_str!("welcome-page.html"));
}
}
#[derive(Deserialize, Default)]
struct Post {
author: String,
name: String,
#[serde(skip)]
timestamp: u64,
#[serde(skip)]
imports: usize,
#[serde(skip)]
runs: usize,
#[serde(skip)]
dependencies: usize,
code: String,
#[serde(skip)]
error: Option<&'static str>,
}
impl Page for Post {
fn render_to_buf(self, session: &Session, buf: &mut String) {
let Self { name, code, error, .. } = self;
write_html! { (buf)
<form id="postForm" "hx-post"="/post" "hx-swap"="outerHTML">
if let Some(e) = error { <div class="error">e</div> }
<input name="author" type="text" value={session.name} hidden>
<input name="name" type="text" placeholder="name" value=name
required maxlength=MAX_POSTNAME_LENGTH>
<div id="code-editor">
<textarea id="code-edit" name="code" placeholder="code" rows=1
required>code</textarea>
<span id="code-size">MAX_CODE_LENGTH</span>
</div>
<input type="submit" value="submit">
<pre id="compiler-output"></pre>
</form>
!{include_str!("post-page.html")}
}
}
}
#[derive(Deserialize)]
struct Run {
author: String,
name: String,
}
impl Post {
pub fn from_row(r: &rusqlite::Row) -> rusqlite::Result<Self> {
Ok(Post {
author: r.get(0)?,
name: r.get(1)?,
timestamp: r.get(2)?,
code: r.get(3)?,
imports: r.get(4)?,
runs: r.get(5)?,
..Default::default()
})
}
async fn run(
session: Session,
axum::extract::Query(run): axum::extract::Query<Run>,
) -> StatusCode {
match db::with(|qes| qes.creata_run.insert((run.name, run.author, session.name))) {
Ok(_) => StatusCode::OK,
Err(e) => {
log::error!("creating run record failed: {e}");
StatusCode::INTERNAL_SERVER_ERROR
}
}
}
async fn post(
session: Session,
axum::Form(mut data): axum::Form<Self>,
) -> Result<Redirect, Html<String>> {
if data.name.len() > MAX_POSTNAME_LENGTH {
data.error = Some(formatcp!("name too long, max length is {MAX_POSTNAME_LENGTH}"));
return Err(data.render(&session));
}
if data.code.len() > MAX_CODE_LENGTH {
data.error = Some(formatcp!("code too long, max length is {MAX_CODE_LENGTH}"));
return Err(data.render(&session));
}
db::with(|db| {
if let Err(e) = db.create_post.insert((&data.name, &session.name, now(), &data.code)) {
if let rusqlite::Error::SqliteFailure(e, _) = e {
if e.code == rusqlite::ErrorCode::ConstraintViolation {
data.error = Some("this name is already used");
}
}
data.error = data.error.or_else(|| {
log::error!("create post error: {e}");
Some("internal server error")
});
return;
}
for (author, name) in hblang::lexer::Lexer::uses(&data.code)
.filter_map(|v| v.split_once('/'))
.collect::<HashSet<_>>()
{
if db
.create_import
.insert((author, name, &session.name, &data.name))
.log("create import query")
.is_none()
{
data.error = Some("internal server error");
return;
};
}
});
if data.error.is_some() {
Err(data.render(&session))
} else {
Ok(redirect("/profile"))
}
}
}
impl fmt::Display for Post {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
let Self { author, name, timestamp, imports, runs, dependencies, code, .. } = self;
write_html! { f <div class="preview" "data-author"=author "data-name"=name>
<div class="info">
<span>
<a "hx-get"={format_args!("/profile-view/{author}")} href="" "hx-target"="main"
"hx-push-url"={format_args!("/profile/{author}")}
"hx-swam"="innerHTML">author</a>
"/"
name
</span>
<span apply="timestamp">timestamp</span>
for (name, count) in [include_str!("icons/download.svg"), include_str!("icons/run.svg"), "deps"]
.iter()
.zip([imports, runs, dependencies])
.filter(|(_, &c)| c != 0)
{
<div class="stat">!name count</div>
}
</div>
<div class="code">
<nav>
<button onmousedown="runPost(this)">!{include_str!("icons/run.svg")}</button>
</nav>
<pre apply="fmt">code</pre>
</div>
<pre hidden id="compiler-output"></pre>
if *timestamp == 0 {
<button "hx-get"="/post" "hx-swap"="outerHTML"
"hx-target"="[preview]">"edit"</button>
}
</div> }
Ok(())
}
}
#[derive(Deserialize, Default)]
struct PasswordChange {
old_password: String,
new_password: String,
#[serde(skip)]
error: Option<&'static str>,
}
impl PasswordChange {
async fn post(
session: Session,
axum::Form(mut change): axum::Form<PasswordChange>,
) -> Html<String> {
db::with(|que| {
match que.authenticate.query_row((&session.name,), |r| r.get::<_, String>(1)) {
Ok(hash) if verify_password(&hash, &change.old_password).is_err() => {
change.error = Some("invalid credentials");
}
Ok(_) => {
let new_hashed = hash_password(&change.new_password);
match que
.change_passowrd
.execute((new_hashed, &session.name))
.log("execute update")
{
None => change.error = Some("intenal server error"),
Some(0) => change.error = Some("password is incorrect"),
Some(_) => {}
}
}
Err(rusqlite::Error::QueryReturnedNoRows) => {
change.error = Some("invalid credentials");
}
Err(e) => {
log::error!("login queri failed: {e}");
change.error = Some("internal server error");
}
}
});
if change.error.is_some() {
change.render(&session)
} else {
PasswordChange::default().render(&session)
}
}
}
impl Page for PasswordChange {
fn render_to_buf(self, _: &Session, buf: &mut String) {
let Self { old_password, new_password, error } = self;
write_html! { (buf)
<form "hx-post"="/profile/password" "hx-swap"="outerHTML">
if let Some(e) = error { <div class="error">e</div> }
<input name="old_password" type="password" autocomplete="old-password"
placeholder="old password" value=old_password>
<input name="new_password" type="password" autocomplete="new-password" placeholder="new password"
value=new_password>
<input type="submit" value="submit">
</form>
}
}
}
#[derive(Default)]
struct Profile {
other: Option<String>,
}
impl Profile {
async fn get_other(session: Session, Path(name): Path<String>) -> Html<String> {
Profile { other: Some(name) }.render(&session)
}
async fn get_other_page(session: Session, Path(name): Path<String>) -> Html<String> {
base(|b| Profile { other: Some(name) }.render_to_buf(&session, b), Some(&session))
}
}
impl Page for Profile {
fn render_to_buf(self, session: &Session, buf: &mut String) {
db::with(|db| {
let name = self.other.as_ref().unwrap_or(&session.name);
let iter = db
.get_user_posts
.query_map((name,), Post::from_row)
.log("get user posts query")
.into_iter()
.flatten()
.filter_map(|p| p.log("user post row"));
write_html! { (*buf)
if name == &session.name {
|b|{PasswordChange::default().render_to_buf(session, b)}
}
for post in iter {
!{post}
} else {
"no posts"
}
!{include_str!("profile-page.html")}
}
})
}
}
fn hash_password(password: &str) -> String {
use argon2::PasswordHasher;
argon2::Argon2::default()
.hash_password(password.as_bytes(), &SaltString::generate(&mut OsRng))
.unwrap()
.to_string()
}
fn verify_password(hash: &str, password: &str) -> Result<(), argon2::password_hash::Error> {
argon2::Argon2::default()
.verify_password(password.as_bytes(), &argon2::PasswordHash::new(hash)?)
}
#[derive(Serialize, Deserialize, Default, Debug)]
struct Login {
name: String,
password: String,
#[serde(skip)]
error: Option<&'static str>,
}
impl PublicPage for Login {
fn render_to_buf(self, buf: &mut String) {
let Self { name, password, error } = self;
write_html! { (buf)
<form "hx-post"="/login" "hx-swap"="outerHTML">
if let Some(e) = error { <div class="error">e</div> }
<input name="name" type="text" autocomplete="name" placeholder="name" value=name
required maxlength=MAX_NAME_LENGTH>
<input name="password" type="password" autocomplete="current-password" placeholder="password"
value=password>
<input type="submit" value="submit">
</form>
}
}
}
impl Login {
async fn post(
axum::Form(mut data): axum::Form<Self>,
) -> Result<AppendHeaders<[(&'static str, String); 2]>, Html<String>> {
// TODO: hash password
let mut id = [0u8; 32];
db::with(|db| match db.authenticate.query_row((&data.name,), |r| r.get::<_, String>(1)) {
Ok(hash) => {
if verify_password(&hash, &data.password).is_err() {
data.error = Some("invalid credentials");
} else {
getrandom::getrandom(&mut id).unwrap();
if db
.login
.insert((id, &data.name, now() + SESSION_DURATION_SECS))
.log("create session query")
.is_none()
{
data.error = Some("internal server error");
}
}
}
Err(rusqlite::Error::QueryReturnedNoRows) => {
data.error = Some("invalid credentials");
}
Err(e) => {
log::error!("login queri failed: {e}");
data.error = Some("internal server error");
}
});
if data.error.is_some() {
Err(data.render())
} else {
Ok(AppendHeaders([
("hx-location", "/feed".into()),
(
"set-cookie",
format!(
"id={}; SameSite=Strict; Secure; Max-Age={SESSION_DURATION_SECS}",
to_hex(&id)
),
),
]))
}
}
async fn delete(session: Session) -> Redirect {
_ = db::with(|q| q.logout.execute((session.id,)).log("delete session query"));
redirect("/login")
}
}
#[derive(Serialize, Deserialize, Default)]
struct Signup {
name: String,
new_password: String,
confirm_password: String,
#[serde(default)]
confirm_no_password: bool,
#[serde(skip)]
error: Option<&'static str>,
}
impl PublicPage for Signup {
fn render_to_buf(self, buf: &mut String) {
let Signup { name, new_password, confirm_password, confirm_no_password, error } = self;
let vals = if confirm_no_password { "{\"confirm_no_password\":true}" } else { "{}" };
write_html! { (buf)
<form "hx-post"="/signup" "hx-swap"="outerHTML" "hx-vals"=vals>
if let Some(e) = error { <div class="error">e</div> }
<input name="name" type="text" autocomplete="name" placeholder="name" value=name
maxlength=MAX_NAME_LENGTH required>
<input name="new_password" type="password" autocomplete="new-password" placeholder="new password"
value=new_password>
<input name="confirm_password" type="password" autocomplete="confirm-password"
placeholder="confirm password" value=confirm_password>
<input type="submit" value="submit">
</form>
}
}
}
impl Signup {
async fn post(axum::Form(mut data): axum::Form<Self>) -> Result<Redirect, Html<String>> {
if data.name.len() > MAX_NAME_LENGTH {
data.error = Some(formatcp!("name too long, max length is {MAX_NAME_LENGTH}"));
return Err(data.render());
}
if !data.confirm_no_password && data.new_password.is_empty() {
data.confirm_no_password = true;
data.error = Some("Are you sure you don't want to use a password? (then submit again)");
return Err(data.render());
}
db::with(|db| {
// TODO: hash passwords
match db.register.insert((&data.name, hash_password(&data.new_password))) {
Ok(_) => {}
Err(rusqlite::Error::SqliteFailure(e, _))
if e.code == rusqlite::ErrorCode::ConstraintViolation =>
{
data.error = Some("username already taken");
}
Err(e) => {
log::error!("create user query: {e}");
data.error = Some("internal server error");
}
};
});
if data.error.is_some() {
Err(data.render())
} else {
Ok(redirect("/login"))
}
}
}
fn base(body: impl FnOnce(&mut String), session: Option<&Session>) -> Html<String> {
let username = session.map(|s| &s.name);
let nav_button = |f: &mut String, name: &str| {
write_html! {(f)
<button "hx-push-url"={format_args!("/{name}")}
"hx-get"={format_args!("/{name}-view")}
"hx-target"="main"
"hx-swap"="innerHTML">name</button>
}
};
Html(html! {
"<!DOCTYPE html>"
<html lang="en">
<head>
<meta name="charset" content="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<meta name="description" content="code dependency hell socila media hblang">
<link rel="stylesheet" href="/index.css">
<title>"depell"</title>
</head>
<body hidden>
<nav>
<button "hx-push-url"="/" "hx-get"="/index-view" "hx-target"="main" "hx-swap"="innerHTML">"depell"</button>
<section>
if let Some(username) = username {
<button "hx-push-url"={format_args!("/profile/{username}")} "hx-get"="/profile-view" "hx-target"="main"
"hx-swap"="innerHTML">username</button>
|f|{nav_button(f, "feed"); nav_button(f, "post")}
<button "hx-delete"="/login">"logout"</button>
} else {
|f|{nav_button(f, "login"); nav_button(f, "signup")}
}
</section>
</nav>
<section id="post-form"></section>
<main>|f|{body(f)}</main>
</body>
<script src="https://unpkg.com/htmx.org@2.0.3/dist/htmx.min.js" integrity="sha384-0895/pl2MU10Hqc6jd4RvrthNlDiE9U1tWmX7WRESftEDRosgxNsQG/Ze9YMRzHq" crossorigin="anonymous"></script>
<script type="module" src="/index.js"></script>
</html>
})
}
struct Session {
name: String,
id: [u8; 32],
}
#[axum::async_trait]
impl<S> axum::extract::FromRequestParts<S> for Session {
/// If the extractor fails it'll use this "rejection" type. A rejection is
/// a kind of error that can be converted into a response.
type Rejection = Redirect;
/// Perform the extraction.
async fn from_request_parts(parts: &mut Parts, _: &S) -> Result<Self, Self::Rejection> {
let err = redirect("/login");
let value = parts
.headers
.get_all(COOKIE)
.into_iter()
.find_map(|c| c.to_str().ok()?.trim().strip_prefix("id="))
.map(|c| c.split_once(';').unwrap_or((c, "")).0)
.ok_or(err)?;
let mut id = [0u8; 32];
parse_hex(value, &mut id).ok_or(err)?;
let (name, expiration) = db::with(|db| {
db.get_session
.query_row((id,), |r| Ok((r.get::<_, String>(0)?, r.get::<_, u64>(1)?)))
.log("fetching session")
.ok_or(err)
})?;
if expiration < now() {
return Err(err);
}
Ok(Self { name, id })
}
}
fn now() -> u64 {
std::time::SystemTime::now()
.duration_since(std::time::SystemTime::UNIX_EPOCH)
.unwrap()
.as_secs()
}
fn parse_hex(hex: &str, dst: &mut [u8]) -> Option<()> {
fn hex_to_nibble(b: u8) -> Option<u8> {
Some(match b {
b'a'..=b'f' => b - b'a' + 10,
b'A'..=b'F' => b - b'A' + 10,
b'0'..=b'9' => b - b'0',
_ => return None,
})
}
if hex.len() != dst.len() * 2 {
return None;
}
for (d, p) in dst.iter_mut().zip(hex.as_bytes().chunks_exact(2)) {
*d = (hex_to_nibble(p[0])? << 4) | hex_to_nibble(p[1])?;
}
Some(())
}
fn to_hex(src: &[u8]) -> String {
use std::fmt::Write;
let mut buf = String::new();
for &b in src {
write!(buf, "{b:02x}").unwrap()
}
buf
}
fn main() {
tokio::runtime::Builder::new_current_thread().enable_all().build().unwrap().block_on(amain());
}
mod db {
use std::cell::RefCell;
macro_rules! gen_queries {
($vis:vis struct $name:ident {
$($qname:ident: $code:expr,)*
}) => {
$vis struct $name<'a> {
$($vis $qname: rusqlite::Statement<'a>,)*
}
impl<'a> $name<'a> {
fn new(db: &'a rusqlite::Connection) -> Self {
Self {
$($qname: db.prepare($code).unwrap(),)*
}
}
}
};
}
gen_queries! {
pub struct Queries {
register: "INSERT INTO user (name, password_hash) VALUES(?, ?)",
change_passowrd: "UPDATE user SET password_hash = ? WHERE name = ?",
authenticate: "SELECT name, password_hash FROM user WHERE name = ?",
login: "INSERT OR REPLACE INTO session (id, username, expiration) VALUES(?, ?, ?)",
logout: "DELETE FROM session WHERE id = ?",
get_session: "SELECT username, expiration FROM session WHERE id = ?",
get_user_posts: "SELECT author, name, timestamp, code, (
WITH RECURSIVE roots(name, author, code) AS (
SELECT name, author, code FROM post WHERE name = outher.name AND author = outher.author
UNION
SELECT post.name, post.author, post.code FROM
post JOIN import ON post.name = import.from_name
AND post.author = import.from_author
JOIN roots ON import.to_name = roots.name
AND import.to_author = roots.author
) SELECT (count(*) - 1) FROM roots
) AS imports, (
WITH RECURSIVE roots(name, author, code) AS (
SELECT name, author, code FROM post WHERE name = outher.name AND author = outher.author
UNION
SELECT post.name, post.author, post.code FROM post
JOIN import ON post.name = import.from_name
AND post.author = import.from_author
JOIN roots ON import.to_name = roots.name
AND import.to_author = roots.author
) SELECT count(*) FROM roots
JOIN run ON roots.name = run.code_name
AND roots.author = run.code_author
) AS runs FROM post as outher WHERE author = ? ORDER BY timestamp DESC",
// TODO: we might want to cache the recursive queries
get_pots_before: "SELECT author, name, timestamp, code, (
WITH RECURSIVE roots(name, author, code) AS (
SELECT name, author, code FROM post WHERE name = outher.name AND author = outher.author
UNION
SELECT post.name, post.author, post.code FROM
post JOIN import ON post.name = import.from_name
AND post.author = import.from_author
JOIN roots ON import.to_name = roots.name
AND import.to_author = roots.author
) SELECT (count(*) - 1) FROM roots
) AS imports, (
WITH RECURSIVE roots(name, author, code) AS (
SELECT name, author, code FROM post WHERE name = outher.name AND author = outher.author
UNION
SELECT post.name, post.author, post.code FROM post
JOIN import ON post.name = import.from_name
AND post.author = import.from_author
JOIN roots ON import.to_name = roots.name
AND import.to_author = roots.author
) SELECT count(*) FROM roots
JOIN run ON roots.name = run.code_name
AND roots.author = run.code_author
) as runs FROM post AS outher WHERE timestamp < ?",
create_post: "INSERT INTO post (name, author, timestamp, code) VALUES(?, ?, ?, ?)",
fetch_deps: "
WITH RECURSIVE roots(name, author, code) AS (
SELECT name, author, code FROM post WHERE name = ? AND author = ?
UNION
SELECT post.name, post.author, post.code FROM
post JOIN import ON post.name = import.to_name
AND post.author = import.to_author
JOIN roots ON import.from_name = roots.name
AND import.from_author = roots.author
) SELECT * FROM roots;
",
create_import: "INSERT INTO import(to_author, to_name, from_author, from_name)
VALUES(?, ?, ?, ?)",
creata_run: "INSERT OR IGNORE INTO run(code_name, code_author, runner) VALUES(?, ?, ?)",
}
}
struct Db {
queries: Queries<'static>,
_db: Box<rusqlite::Connection>,
}
impl Db {
fn new() -> Self {
let db = Box::new(rusqlite::Connection::open("db.sqlite").unwrap());
Self {
queries: Queries::new(unsafe {
std::mem::transmute::<&rusqlite::Connection, &rusqlite::Connection>(&db)
}),
_db: db,
}
}
}
pub fn with<T>(with: impl FnOnce(&mut Queries) -> T) -> T {
thread_local! { static DB_CONN: RefCell<Db> = RefCell::new(Db::new()); }
DB_CONN.with_borrow_mut(|q| with(&mut q.queries))
}
pub fn init() {
const SCHEMA_VERSION: usize = 0;
const MIGRATIONS: &[&str] = &[include_str!("migrations/1.sql")];
let db = rusqlite::Connection::open("db.sqlite").unwrap();
db.execute_batch(include_str!("schema.sql")).unwrap();
let schema_version =
db.pragma_query_value(None, "user_version", |v| v.get::<_, usize>(0)).unwrap();
if schema_version != SCHEMA_VERSION {
for &mig in &MIGRATIONS[schema_version..] {
db.execute_batch(mig).expect(mig);
}
db.pragma_update(None, "user_version", SCHEMA_VERSION).unwrap();
}
Queries::new(&db);
}
}
fn redirect(to: &'static str) -> Redirect {
AppendHeaders([("hx-location", to)])
}
trait PublicPage: Default {
fn render_to_buf(self, buf: &mut String);
fn render(self) -> Html<String> {
let mut str = String::new();
self.render_to_buf(&mut str);
Html(str)
}
async fn get() -> Html<String> {
Self::default().render()
}
async fn page(session: Option<Session>) -> Html<String> {
base(|s| Self::default().render_to_buf(s), session.as_ref())
}
}
trait Page: Default {
fn render_to_buf(self, session: &Session, buf: &mut String);
fn render(self, session: &Session) -> Html<String> {
let mut str = String::new();
self.render_to_buf(session, &mut str);
Html(str)
}
async fn get(session: Session) -> Html<String> {
Self::default().render(&session)
}
async fn page(session: Option<Session>) -> Result<Html<String>, axum::response::Redirect> {
match session {
Some(session) => {
Ok(base(|f| Self::default().render_to_buf(&session, f), Some(&session)))
}
None => Err(axum::response::Redirect::permanent("/login")),
}
}
}
trait ResultExt<O, E> {
fn log(self, prefix: impl Display) -> Option<O>;
}
impl<O, E: Display> ResultExt<O, E> for Result<O, E> {
fn log(self, prefix: impl Display) -> Option<O> {
match self {
Ok(v) => Some(v),
Err(e) => {
log::error!("{prefix}: {e}");
None
}
}
}
}
struct Logger;
impl log::Log for Logger {
fn enabled(&self, _: &log::Metadata) -> bool {
true
}
fn log(&self, record: &log::Record) {
if self.enabled(record.metadata()) {
eprintln!("{} - {}", record.module_path().unwrap_or("=="), record.args());
}
}
fn flush(&self) {}
}

1
depell/src/migrations/1.sql
View file

@ -1 +0,0 @@

21
depell/src/post-page.html
View file

@ -1,21 +0,0 @@
<div id="dep-list">
<input placeholder="search impoted deps.." oninput="filterCodeDeps(this, event)">
<section id="deps">
results show here...
</section>
</div>
<div>
<h3>About posting code</h3>
<p>
If you are unfammiliar with <a href="https://git.ablecorp.us/AbleOS/holey-bytes">hblang</a>, refer to the
<strong>hblang/README.md</strong> or
vizit <a href="/profile/mlokis">mlokis'es posts</a>. Preferably don't edit the code here.
</p>
<h3>Extra textarea features</h3>
<ul>
<li>proper tab behaviour</li>
<li>snap to previous tab boundary on "empty" lines</li>
</ul>

0
depell/src/profile-page.html
View file

55
depell/src/schema.sql
View file

@ -1,55 +0,0 @@
PRAGMA foreign_keys = ON;
CREATE TABLE IF NOT EXISTS user(
name TEXT NOT NULL,
password_hash TEXT NOT NULL,
PRIMARY KEY (name)
) WITHOUT ROWID;
CREATE TABLE IF NOT EXISTS session(
id BLOB NOT NULL,
username TEXT NOT NULL,
expiration INTEGER NOT NULL,
FOREIGN KEY (username) REFERENCES user (name)
PRIMARY KEY (username)
) WITHOUT ROWID;
CREATE UNIQUE INDEX IF NOT EXISTS
session_id ON session (id);
CREATE TABLE IF NOT EXISTS post(
name TEXT NOT NULL,
author TEXT,
timestamp INTEGER,
code TEXT NOT NULL,
FOREIGN KEY (author) REFERENCES user(name) ON DELETE SET NULL,
PRIMARY KEY (author, name)
);
CREATE INDEX IF NOT EXISTS
post_timestamp ON post(timestamp DESC);
CREATE TABLE IF NOT EXISTS import(
from_name TEXT NOT NULL,
from_author TEXT,
to_name TEXT NOT NULL,
to_author TEXT,
FOREIGN KEY (from_name, from_author) REFERENCES post(name, author),
FOREIGN KEY (to_name, to_author) REFERENCES post(name, author)
);
CREATE INDEX IF NOT EXISTS
dependencies ON import(from_name, from_author);
CREATE INDEX IF NOT EXISTS
dependants ON import(to_name, to_author);
CREATE TABLE IF NOT EXISTS run(
code_name TEXT NOT NULL,
code_author TEXT NOT NULL,
runner TEXT NOT NULL,
FOREIGN KEY (code_name, code_author) REFERENCES post(name, author),
FOREIGN KEY (runner) REFERENCES user(name),
PRIMARY KEY (code_name, code_author, runner)
);

17
depell/src/welcome-page.html
View file

@ -1,17 +0,0 @@
<h1>Welcome to depell</h1>
<p>
Depell (dependency hell) is a simple "social" media site best compared to twitter, except that all you can post is
<a href="https://git.ablecorp.us/AbleOS/holey-bytes">hblang</a> code with no comments allowed. Instead of likes you
run the program, and instead of retweets you import the program as dependency. Run counts even when ran indirectly.
</p>
<p>
The backend only serves the code and frontend compiles and runs it locally. All posts are immutable.
</p>
<h2>Security?</h2>
<p>
All code runs in WASM (inside a holey-bytes VM until hblang compiles to wasm) and is controlled by JavaScript. WASM
cant do any form of IO without going trough JavaScript so as long as JS import does not allow wasm to execute
arbitrary JS code, WASM can act as a container inside the JS.
</p>

11
depell/wasm-fmt/Cargo.toml
View file

@ -1,11 +0,0 @@
[package]
name = "wasm-hbfmt"
version = "0.1.0"
edition = "2021"
[lib]
crate-type = ["cdylib"]
[dependencies]
hblang = { workspace = true, features = ["no_log"] }
wasm-rt = { version = "0.1.0", path = "../wasm-rt" }

42
depell/wasm-fmt/src/lib.rs
View file

@ -1,42 +0,0 @@
#![no_std]
#![feature(str_from_raw_parts)]
#![feature(alloc_error_handler)]
use hblang::{fmt, parser};
wasm_rt::decl_runtime!(128 * 1024, 1024 * 4);
const MAX_OUTPUT_SIZE: usize = 1024 * 10;
wasm_rt::decl_buffer!(MAX_OUTPUT_SIZE, MAX_OUTPUT, OUTPUT, OUTPUT_LEN);
const MAX_INPUT_SIZE: usize = 1024 * 4;
wasm_rt::decl_buffer!(MAX_INPUT_SIZE, MAX_INPUT, INPUT, INPUT_LEN);
#[no_mangle]
unsafe extern "C" fn fmt() {
ALLOCATOR.reset();
let code = core::str::from_raw_parts(core::ptr::addr_of!(INPUT).cast(), INPUT_LEN);
let arena = parser::Arena::with_capacity(code.len() * parser::SOURCE_TO_AST_FACTOR);
let mut ctx = parser::Ctx::default();
let exprs = parser::Parser::parse(&mut ctx, code, "source.hb", &mut parser::no_loader, &arena);
let mut f = wasm_rt::Write(&mut OUTPUT[..]);
fmt::fmt_file(exprs, code, &mut f).unwrap();
OUTPUT_LEN = MAX_OUTPUT_SIZE - f.0.len();
}
#[no_mangle]
unsafe extern "C" fn tok() {
let code = core::slice::from_raw_parts_mut(
core::ptr::addr_of_mut!(OUTPUT).cast(), OUTPUT_LEN);
OUTPUT_LEN = fmt::get_token_kinds(code);
}
#[no_mangle]
unsafe extern "C" fn minify() {
let code = core::str::from_raw_parts_mut(
core::ptr::addr_of_mut!(OUTPUT).cast(), OUTPUT_LEN);
OUTPUT_LEN = fmt::minify(code);
}

14
depell/wasm-hbc/Cargo.toml
View file

@ -1,14 +0,0 @@
[package]
name = "wasm-hbc"
version = "0.1.0"
edition = "2021"
[lib]
crate-type = ["cdylib"]
[dependencies]
hblang = { workspace = true, features = [] }
hbvm.workspace = true
log = { version = "0.4.22", features = ["release_max_level_error"] }
wasm-rt = { version = "0.1.0", path = "../wasm-rt", features = ["log"] }

127
depell/wasm-hbc/src/lib.rs
View file

@ -1,127 +0,0 @@
#![feature(alloc_error_handler)]
#![feature(slice_take)]
#![no_std]
use {
alloc::{string::String, vec::Vec},
core::ffi::CStr,
hblang::{
son::{hbvm::HbvmBackend, Codegen, CodegenCtx},
ty::Module,
Ent,
},
};
extern crate alloc;
const ARENA_CAP: usize = 128 * 16 * 1024;
wasm_rt::decl_runtime!(ARENA_CAP, 1024 * 4);
const MAX_INPUT_SIZE: usize = 32 * 4 * 1024;
wasm_rt::decl_buffer!(MAX_INPUT_SIZE, MAX_INPUT, INPUT, INPUT_LEN);
#[no_mangle]
unsafe fn compile_and_run(mut fuel: usize) {
ALLOCATOR.reset();
_ = log::set_logger(&wasm_rt::Logger);
log::set_max_level(log::LevelFilter::Error);
struct File<'a> {
path: &'a str,
code: &'a mut str,
}
let mut root = 0;
let files = {
let mut input_bytes =
core::slice::from_raw_parts_mut(core::ptr::addr_of_mut!(INPUT).cast::<u8>(), INPUT_LEN);
let mut files = Vec::with_capacity(32);
while let Some((&mut path_len, rest)) = input_bytes.split_first_chunk_mut() {
let (path, rest) = rest.split_at_mut(u16::from_le_bytes(path_len) as usize);
let (&mut code_len, rest) = rest.split_first_chunk_mut().unwrap();
let (code, rest) = rest.split_at_mut(u16::from_le_bytes(code_len) as usize);
files.push(File {
path: core::str::from_utf8_unchecked(path),
code: core::str::from_utf8_unchecked_mut(code),
});
input_bytes = rest;
}
let root_path = files[root].path;
hblang::quad_sort(&mut files, |a, b| a.path.cmp(b.path));
root = files.binary_search_by_key(&root_path, |p| p.path).unwrap();
files
};
let mut ctx = CodegenCtx::default();
let files = {
let paths = files.iter().map(|f| f.path).collect::<Vec<_>>();
let mut loader = |path: &str, _: &str, kind| match kind {
hblang::parser::FileKind::Module => Ok(paths.binary_search(&path).unwrap()),
hblang::parser::FileKind::Embed => Err("embeds are not supported".into()),
};
files
.into_iter()
.map(|f| {
hblang::parser::Ast::new(
f.path,
// since 'free' does nothing this is fine
String::from_raw_parts(f.code.as_mut_ptr(), f.code.len(), f.code.len()),
&mut ctx.parser,
&mut loader,
)
})
.collect::<Vec<_>>()
};
let mut ct = {
let mut backend = HbvmBackend::default();
Codegen::new(&mut backend, &files, &mut ctx).generate(Module::new(root));
if !ctx.parser.errors.borrow().is_empty() {
log::error!("{}", ctx.parser.errors.borrow());
return;
}
let mut c = Codegen::new(&mut backend, &files, &mut ctx);
c.assemble_comptime()
};
while fuel != 0 {
match ct.vm.run() {
Ok(hbvm::VmRunOk::End) => {
log::error!("exit code: {}", ct.vm.read_reg(1).0 as i64);
break;
}
Ok(hbvm::VmRunOk::Ecall) => {
let kind = ct.vm.read_reg(2).0;
match kind {
0 => {
let str = ct.vm.read_reg(3).0;
let str = unsafe { CStr::from_ptr(str as _) };
log::error!("{}", str.to_str().unwrap());
}
unknown => log::error!("unknown ecall: {unknown}"),
}
}
Ok(hbvm::VmRunOk::Timer) => {
fuel -= 1;
if fuel == 0 {
log::error!("program timed out");
}
}
Ok(hbvm::VmRunOk::Breakpoint) => todo!(),
Err(e) => {
log::error!("vm error: {e}");
break;
}
}
}
//log::error!("memory consumption: {}b / {}b", ALLOCATOR.used(), ARENA_CAP);
}

7
depell/wasm-rt/Cargo.toml
View file

@ -1,7 +0,0 @@
[package]
name = "wasm-rt"
version = "0.1.0"
edition = "2021"
[dependencies]
log = { version = "0.4.22", optional = true }

162
depell/wasm-rt/src/lib.rs
View file

@ -1,162 +0,0 @@
#![feature(alloc_error_handler)]
#![feature(pointer_is_aligned_to)]
#![feature(slice_take)]
#![no_std]
use core::{
alloc::{GlobalAlloc, Layout},
cell::UnsafeCell,
};
extern crate alloc;
#[macro_export]
macro_rules! decl_buffer {
($cap:expr, $export_cap:ident, $export_base:ident, $export_len:ident) => {
#[no_mangle]
static $export_cap: usize = $cap;
#[no_mangle]
static mut $export_base: [u8; $cap] = [0; $cap];
#[no_mangle]
static mut $export_len: usize = 0;
};
}
#[macro_export]
macro_rules! decl_runtime {
($memory_size:expr, $max_panic_size:expr) => {
#[cfg(debug_assertions)]
#[no_mangle]
static mut PANIC_MESSAGE: [u8; $max_panic_size] = [0; $max_panic_size];
#[cfg(debug_assertions)]
#[no_mangle]
static mut PANIC_MESSAGE_LEN: usize = 0;
#[cfg(target_arch = "wasm32")]
#[panic_handler]
pub fn handle_panic(_info: &core::panic::PanicInfo) -> ! {
#[cfg(debug_assertions)]
{
unsafe {
use core::fmt::Write;
let mut f = $crate::Write(&mut PANIC_MESSAGE[..]);
_ = writeln!(f, "{}", _info);
PANIC_MESSAGE_LEN = $max_panic_size - f.0.len();
}
}
core::arch::wasm32::unreachable();
}
#[global_allocator]
static ALLOCATOR: $crate::ArenaAllocator<{ $memory_size }> = $crate::ArenaAllocator::new();
#[cfg(target_arch = "wasm32")]
#[alloc_error_handler]
fn alloc_error(_: core::alloc::Layout) -> ! {
#[cfg(debug_assertions)]
{
unsafe {
use core::fmt::Write;
let mut f = $crate::Write(&mut PANIC_MESSAGE[..]);
_ = writeln!(f, "out of memory");
PANIC_MESSAGE_LEN = $max_panic_size - f.0.len();
}
}
core::arch::wasm32::unreachable()
}
};
}
#[cfg(feature = "log")]
pub struct Logger;
#[cfg(feature = "log")]
impl log::Log for Logger {
fn enabled(&self, _: &log::Metadata) -> bool {
true
}
fn log(&self, record: &log::Record) {
if self.enabled(record.metadata()) {
const MAX_LOG_MESSAGE: usize = 1024 * 8;
#[no_mangle]
static mut LOG_MESSAGES: [u8; MAX_LOG_MESSAGE] = [0; MAX_LOG_MESSAGE];
#[no_mangle]
static mut LOG_MESSAGES_LEN: usize = 0;
unsafe {
use core::fmt::Write;
let mut f = Write(&mut LOG_MESSAGES[LOG_MESSAGES_LEN..]);
_ = writeln!(f, "{}", record.args());
LOG_MESSAGES_LEN = MAX_LOG_MESSAGE - f.0.len();
}
}
}
fn flush(&self) {}
}
pub struct ArenaAllocator<const SIZE: usize> {
arena: UnsafeCell<[u8; SIZE]>,
head: UnsafeCell<*mut u8>,
}
impl<const SIZE: usize> ArenaAllocator<SIZE> {
#[expect(clippy::new_without_default)]
pub const fn new() -> Self {
ArenaAllocator {
arena: UnsafeCell::new([0; SIZE]),
head: UnsafeCell::new(core::ptr::null_mut()),
}
}
#[expect(clippy::missing_safety_doc)]
pub unsafe fn reset(&self) {
(*self.head.get()) = self.arena.get().cast::<u8>().add(SIZE);
}
pub fn used(&self) -> usize {
unsafe { self.arena.get() as usize + SIZE - (*self.head.get()) as usize }
}
}
unsafe impl<const SIZE: usize> Sync for ArenaAllocator<SIZE> {}
unsafe impl<const SIZE: usize> GlobalAlloc for ArenaAllocator<SIZE> {
unsafe fn alloc(&self, layout: Layout) -> *mut u8 {
let size = layout.size();
let align = layout.align();
let until = self.arena.get() as *mut u8;
let new_head = (*self.head.get()).sub(size);
let aligned_head = (new_head as usize & !(align - 1)) as *mut u8;
debug_assert!(aligned_head.is_aligned_to(align));
if until > aligned_head {
return core::ptr::null_mut();
}
*self.head.get() = aligned_head;
aligned_head
}
unsafe fn dealloc(&self, _ptr: *mut u8, _layout: Layout) {
/* lol */
}
}
pub struct Write<'a>(pub &'a mut [u8]);
impl core::fmt::Write for Write<'_> {
fn write_str(&mut self, s: &str) -> core::fmt::Result {
if let Some(m) = self.0.take_mut(..s.len()) {
m.copy_from_slice(s.as_bytes());
Ok(())
} else {
Err(core::fmt::Error)
}
}
}

9
hbasm/Cargo.toml Normal file
View file

@ -0,0 +1,9 @@
[package]
name = "hbasm"
version = "0.1.0"
edition = "2021"
[dependencies]
paste = "1.0"
rhai = "1.16"
with_builtin_macros = "0.0.3"

13
hbasm/examples/ableos/main.rhai Normal file
View file

@ -0,0 +1,13 @@
import "hbasm/examples/ableos/std" as std;
fn main(){
std::Error(":+)");
std::Warn("Your mom fell in a well!");
std::Info("Hello, world!");
std::Debug("ABC");
std::Trace("Trace Deez");
tx();
}
main();

24
hbasm/examples/ableos/std.rhai Normal file
View file

@ -0,0 +1,24 @@
fn ipc_send(buffer_id, mem_addr, length){
// set the ecall
li8(r1, 3);
// Set the buffer ID to be the BufferID
li64(r2, buffer_id);
lra(r3, r0, mem_addr);
// set the length
li64(r4, length);
// ecall
eca();
}
private fn log(log_level, string){
let str = data::str(string);
ipc_send(1, str, str.len);
}
fn Error(string) {log(0, string);}
fn Warn(string) {log(1, string);}
fn Info(string) {log(2, string);}
// Due to rhai limitations this cannot be debug
// because of this all of the log levels are upper case
fn Debug(string) {log(3, string);}
fn Trace(string) {log(4, string);}

9
hbasm/examples/hello-linux.rhai Normal file
View file

@ -0,0 +1,9 @@
let hello = data::str("Hello, world!");
li8 (r1, 1); // Write syscall
li8 (r2, 1); // Stdout FD
lra16 (r3, r0, hello); // String buffer
li8 (r4, hello.len); // String length
eca (); // System call
tx (); // End program

33
hbasm/examples/macros.rhai Normal file
View file

@ -0,0 +1,33 @@
li8(r1, 69);
li8(r2, 0);
if_eq(r1, r2,
|| puts("Equals!"),
|| puts("Not equals!"),
);
tx(); // END OF MAIN
/// Inline function – write text to stdout
fn puts(string) {
let d = data::str(string);
li8 (r1, 1); // Write syscall
li8 (r2, 1); // Stdout handle
lra16 (r3, r0, d);
li64 (r4, d.len);
eca ();
}
fn if_eq(a, b, thenblk, elseblk) {
let elselbl = declabel();
let endlbl = declabel();
jne(a, b, elselbl);
thenblk.call();
jmp16(endlbl);
elselbl.here();
elseblk.call();
endlbl.here();
}

101
hbasm/src/data.rs Normal file
View file

@ -0,0 +1,101 @@
//! Data section inserts
use {
crate::{object::SymbolRef, SharedObject},
rhai::{CustomType, Engine, FuncRegistration, ImmutableString, Module},
};
/// Generate insertions for data types
///
/// `gen_data_instructions!($module, $obj, [$type, …]);`
/// - `$module`: Rhai module
/// - `$obj`: Code object
/// - `$type`: Type of single array item
macro_rules! gen_data_insertions {
($module:expr, $obj:expr, [$($ty:ident),* $(,)?] $(,)?) => {{
let (module, obj) = ($module, $obj);
$({
// Clone object to each function
let obj = ::std::rc::Rc::clone(obj);
FuncRegistration::new(stringify!($ty))
.with_namespace(rhai::FnNamespace::Global)
.set_into_module::<_, 1, false, _, true, _>(module, move |arr: ::rhai::Array| {
let obj = &mut *obj.borrow_mut();
let symbol = obj.symbol($crate::object::Section::Data);
// Reserve space for object so we don't resize it
// all the time
obj.sections
.data
.reserve(arr.len() * ::std::mem::size_of::<$ty>());
// For every item…
for item in arr {
// … try do conversions from i32 to desired type
// and insert it.
obj.sections.data.extend(
match item.as_int() {
Ok(num) => $ty::try_from(num).map_err(|_| "i64".to_owned()),
Err(ty) => Err(ty.to_owned()),
}
.map_err(|err| {
::rhai::EvalAltResult::ErrorMismatchDataType(
stringify!($ty).to_owned(),
err,
::rhai::Position::NONE,
)
})?
.to_le_bytes(),
);
}
Ok(DataRef {
symbol,
len: obj.sections.data.len() - symbol.0,
})
});
})*
}};
}
/// Reference to entry in data section
#[derive(Clone, Copy, Debug)]
pub struct DataRef {
pub symbol: SymbolRef,
pub len: usize,
}
impl CustomType for DataRef {
fn build(mut builder: rhai::TypeBuilder<Self>) {
builder
.with_name("DataRef")
.with_get("symbol", |this: &mut Self| this.symbol)
.with_get("len", |this: &mut Self| this.len as u64 as i64);
}
}
pub fn module(engine: &mut Engine, obj: SharedObject) -> Module {
let mut module = Module::new();
gen_data_insertions!(&mut module, &obj, [i8, i16, i32, i64]);
// Specialisation for strings, they should be
// inserted as plain UTF-8 arrays
FuncRegistration::new("str")
.with_namespace(rhai::FnNamespace::Global)
.set_into_module::<_, 1, false, _, true, _>(&mut module, move |s: ImmutableString| {
let obj = &mut *obj.borrow_mut();
let symbol = obj.symbol(crate::object::Section::Data);
obj.sections.data.extend(s.as_bytes());
Ok(DataRef {
symbol,
len: s.len(),
})
});
engine.build_type::<DataRef>();
module
}

321
hbasm/src/ins.rs Normal file
View file

@ -0,0 +1,321 @@
//! Functions for inserting instructions
//!
//! Most of the code you see is just metaprogramming stuff.
//! This ensures that adding new instructions won't need any
//! specific changes and consistent behaviour.
//!
//! > I tried to comment stuff here, but I meanwhile forgor how it works.
//!
//! — Erin
use {
crate::object::Object,
rhai::{FuncRegistration, Module},
std::{cell::RefCell, rc::Rc},
};
/// Operand types and their insertions
pub mod optypes {
use {
crate::{
label::UnboundLabel,
object::{Object, RelocKey, RelocType, SymbolRef},
},
rhai::{Dynamic, EvalAltResult, ImmutableString, Position},
};
// These types represent operand types to be inserted
pub type R = u8;
pub type B = i8;
pub type H = i16;
pub type W = i32;
pub type D = i64;
pub type A = Dynamic;
pub type O = Dynamic;
pub type P = Dynamic;
/// Insert relocation into code
///
/// - If integer, just write it to the code
/// - Otherwise insert entry into relocation table
/// and fill zeroes
pub fn insert_reloc(
obj: &mut Object,
ty: RelocType,
val: &Dynamic,
) -> Result<(), EvalAltResult> {
match () {
// Direct references – insert directly to table
_ if val.is::<SymbolRef>() => {
obj.relocation(RelocKey::Symbol(val.clone_cast::<SymbolRef>().0), ty)
}
_ if val.is::<UnboundLabel>() => {
obj.relocation(RelocKey::Symbol(val.clone_cast::<UnboundLabel>().0), ty)
}
_ if val.is::<DataRef>() => {
obj.relocation(RelocKey::Symbol(val.clone_cast::<DataRef>().symbol.0), ty)
}
// String (indirect) reference
_ if val.is_string() => {
obj.relocation(RelocKey::Label(val.clone_cast::<ImmutableString>()), ty)
}
// Manual offset
_ if val.is_int() => {
let int = val.clone_cast::<i64>();
match ty {
RelocType::Rel32 => obj.sections.text.extend((int as i32).to_le_bytes()),
RelocType::Rel16 => obj.sections.text.extend((int as i16).to_le_bytes()),
RelocType::Abs64 => obj.sections.text.extend(int.to_le_bytes()),
}
}
_ => {
return Err(EvalAltResult::ErrorMismatchDataType(
"SymbolRef, UnboundLabel, String or Int".to_owned(),
val.type_name().to_owned(),
Position::NONE,
))
}
}
Ok(())
}
/// Generate macro for inserting item into the output object
///
/// Pre-defines inserts for absolute address and relative offsets.
/// These are inserted with function [`insert_reloc`]
/// # le_bytes
/// `gen_insert!(le_bytes: [B, …]);`
///
/// Takes sequence of operand types which should be inserted
/// by invoking `to_le_bytes` method on it.
macro_rules! gen_insert {
(le_bytes: [$($lety:ident),* $(,)?]) => {
/// `insert!($thing, $obj, $type)` where
/// - `$thing`: Value you want to insert
/// - `$obj`: Code object
/// - `$type`: Type of inserted value
///
/// Eg. `insert!(69_u8, obj, B);`
macro_rules! insert {
$(($thing:expr, $obj: expr, $lety) => {
$obj.sections.text.extend($thing.to_le_bytes());
};)*
($thing:expr, $obj:expr, A) => {
$crate::ins::optypes::insert_reloc(
$obj,
$crate::object::RelocType::Abs64,
$thing
)?
};
($thing:expr, $obj:expr, O) => {
$crate::ins::optypes::insert_reloc(
$obj,
$crate::object::RelocType::Rel32,
$thing
)?
};
($thing:expr, $obj:expr, P) => {
$crate::ins::optypes::insert_reloc(
$obj,
$crate::object::RelocType::Rel16,
$thing
)?
};
}
};
}
gen_insert!(le_bytes: [R, B, H, W, D]);
#[allow(clippy::single_component_path_imports)]
pub(super) use insert;
use crate::data::DataRef;
}
/// Rhai Types (types for function parameters as Rhai uses only 64bit signed integers)
pub mod rity {
pub use super::optypes::{A, O, P, R};
pub type B = i64;
pub type H = i64;
pub type W = i64;
pub type D = i64;
}
/// Generic instruction (instruction of certain operands type) inserts
pub mod generic {
use {crate::object::Object, rhai::EvalAltResult};
pub(super) fn convert_op<A, B>(from: A) -> Result<B, EvalAltResult>
where
B: TryFrom<A>,
<B as TryFrom<A>>::Error: std::error::Error + Sync + Send + 'static,
{
B::try_from(from).map_err(|e| {
EvalAltResult::ErrorSystem("Data conversion error".to_owned(), Box::new(e))
})
}
/// Generate opcode-generic instruction insert macro
macro_rules! gen_ins {
($($($name:ident : $ty:ty),*;)*) => {
paste::paste! {
$(
/// Instruction-generic opcode insertion function
/// - `obj`: Code object
/// - `opcode`: opcode, not checked if valid for instruction type
/// - … for operands
#[inline]
pub fn [<$($ty:lower)*>](
obj: &mut Object,
opcode: u8,
$($name: $crate::ins::optypes::$ty),*,
) -> Result<(), EvalAltResult> {
// Push opcode
obj.sections.text.push(opcode);
// Insert based on type
$($crate::ins::optypes::insert!(&$name, obj, $ty);)*
Ok(())
}
)*
/// Generate Rhai opcode-specific instruction insertion functions
///
/// `gen_ins_fn!($obj, $opcode, $optype);` where:
/// - `$obj`: Code object
/// - `$opcode`: Opcode value
macro_rules! gen_ins_fn {
$(
($obj:expr, $opcode:expr, [<$($ty)*>]) => {
// Opcode-specific insertion function
// - Parameters = operands
move |$($name: $crate::ins::rity::$ty),*| {
// Invoke generic function
$crate::ins::generic::[<$($ty:lower)*>](
&mut *$obj.borrow_mut(),
$opcode,
$(
// Convert to desired type (from Rhai-provided values)
$crate::ins::generic::convert_op::<
_,
$crate::ins::optypes::$ty
>($name)?
),*
)?;
Ok(())
}
};
// Internal-use: count args
(@arg_count [<$($ty)*>]) => {
{ ["", $(stringify!($ty)),*].len() - 1 }
};
)*
// Specialisation for no-operand instructions
($obj:expr, $opcode:expr, N) => {
move || {
$crate::ins::generic::n(&mut *$obj.borrow_mut(), $opcode);
Ok(())
}
};
// Internal-use specialisation: no-operand instructions
(@arg_count N) => {
{ 0 }
};
}
}
};
}
/// Specialisation for no-operand instructions – simply just push opcode
#[inline]
pub fn n(obj: &mut Object, opcode: u8) {
obj.sections.text.push(opcode);
}
// Generate opcode-generic instruction inserters
// (operand identifiers are arbitrary)
//
// New instruction types have to be added manually here
gen_ins! {
o0: R, o1: R;
o0: R, o1: R, o2: R;
o0: R, o1: R, o2: R, o3: R;
o0: R, o1: R, o2: B;
o0: R, o1: R, o2: H;
o0: R, o1: R, o2: W;
o0: R, o1: R, o2: D;
o0: R, o1: B;
o0: R, o1: H;
o0: R, o1: W;
o0: R, o1: D;
o0: R, o1: R, o2: A;
o0: R, o1: R, o2: A, o3: H;
o0: R, o1: R, o2: O, o3: H;
o0: R, o1: R, o2: P, o3: H;
o0: R, o1: R, o2: O;
o0: R, o1: R, o2: P;
o0: O;
o0: P;
}
#[allow(clippy::single_component_path_imports)]
pub(super) use gen_ins_fn;
}
/// Generate instructions from instruction table
///
/// ```ignore
/// instructions!(($module, $obj) {
/// // Data from instruction table
/// $opcode, $mnemonic, $opty, $doc;
/// …
/// });
/// ```
/// - `$module`: Rhai module
/// - `$obj`: Code object
macro_rules! instructions {
(
($module:expr, $obj:expr $(,)?)
{ $($opcode:expr, $mnemonic:ident, $ops:tt, $doc:literal;)* }
) => {{
paste::paste! {
let (module, obj) = ($module, $obj);
$({
// Object is shared across all functions
let obj = Rc::clone(&obj);
// Register newly generated function for each instruction
FuncRegistration::new(stringify!([<$mnemonic:lower>]))
.with_namespace(rhai::FnNamespace::Global)
.set_into_module::<_, { generic::gen_ins_fn!(@arg_count $ops) }, false, _, true, _>(
module,
generic::gen_ins_fn!(
obj,
$opcode,
$ops
)
);
})*
}
}};
}
/// Setup instruction insertors
pub fn setup(module: &mut Module, obj: Rc<RefCell<Object>>) {
// Import instructions table and use it for generation
with_builtin_macros::with_builtin! {
let $spec = include_from_root!("../hbbytecode/instructions.in") in {
instructions!((module, obj) { $spec });
}
}
}

112
hbasm/src/label.rs Normal file
View file

@ -0,0 +1,112 @@
//! Stuff related to labels
use {
crate::SharedObject,
rhai::{Engine, FuncRegistration, ImmutableString, Module},
};
/// Macro for creating functions for Rhai which
/// is bit more friendly
///
/// ```ignore
/// shdm_fns!{
/// module: $module;
/// shared: $shared => $shname;
///
/// $vis fn $name($param_name: $param_ty, …) -> $ret { … }
/// …
/// }
/// ```
/// - `$module`: Rhai module
/// - `$shared`: Data to be shared across the functions
/// - `$shname`: The binding name inside functions
/// - `$vis`: Function visibility for Rhai
/// - Lowercased [`rhai::FnNamespace`] variants
/// - `$name`: Function name
/// - `$param_name`: Parameter name
/// - `$param_ty`: Rust parameter type
/// - `$ret`: Optional return type (otherwise infer)
macro_rules! shdm_fns {
(
module: $module:expr;
shared: $shared:expr => $shname:ident;
$(
$vis:ident fn $name:ident($($param_name:ident: $param_ty:ty),*) $(-> $ret:ty)? $blk:block
)*
) => {{
let module = $module;
let shared = $shared;
paste::paste! {
$({
let $shname = SharedObject::clone(&shared);
FuncRegistration::new(stringify!($name))
.with_namespace(rhai::FnNamespace::[<$vis:camel>])
.set_into_module::<_, { ["", $(stringify!($param_name)),*].len() - 1 }, false, _, true, _>(
module,
move |$($param_name: $param_ty),*| $(-> $ret)? {
let mut $shname = $shname.borrow_mut();
$blk
}
);
})*
}
}};
}
/// Label without any place bound
#[derive(Clone, Copy, Debug)]
pub struct UnboundLabel(pub usize);
pub fn setup(engine: &mut Engine, module: &mut Module, object: SharedObject) {
shdm_fns! {
module: module;
shared: object => obj;
// Insert unnamed label
global fn label() {
let symbol = obj.symbol(crate::object::Section::Text);
Ok(symbol)
}
// Insert string-labeled label
global fn label(label: ImmutableString) {
let symbol = obj.symbol(crate::object::Section::Text);
obj.labels.insert(label, symbol.0);
Ok(symbol)
}
// Declare unbound label (to be bound later)
global fn declabel() {
let index = obj.symbols.len();
obj.symbols.push(None);
Ok(UnboundLabel(index))
}
// Declare unbound label (to be bound later)
// with string label
global fn declabel(label: ImmutableString) {
let index = obj.symbols.len();
obj.symbols.push(None);
obj.labels.insert(label, index);
Ok(UnboundLabel(index))
}
// Set location for unbound label
global fn here(label: UnboundLabel) {
obj.symbols[label.0] = Some(crate::object::SymbolEntry {
location: crate::object::Section::Text,
offset: obj.sections.text.len(),
});
Ok(())
}
}
engine.register_type_with_name::<UnboundLabel>("UnboundLabel");
}

45
hbasm/src/lib.rs Normal file
View file

@ -0,0 +1,45 @@
pub mod data;
pub mod ins;
pub mod label;
pub mod linker;
pub mod object;
use {
object::Object,
rhai::{Engine, Module},
std::{cell::RefCell, rc::Rc},
};
type SharedObject = Rc<RefCell<Object>>;
pub fn assembler(
linkout: &mut impl std::io::Write,
loader: impl FnOnce(&mut Engine) -> Result<(), Box<rhai::EvalAltResult>>,
) -> Result<(), Box<dyn std::error::Error>> {
let mut engine = Engine::new();
let mut module = Module::new();
let obj = Rc::new(RefCell::new(Object::default()));
ins::setup(&mut module, Rc::clone(&obj));
label::setup(&mut engine, &mut module, Rc::clone(&obj));
// Registers
for n in 0_u8..=255 {
module.set_var(format!("r{n}"), n);
}
module.set_native_fn("reg", |n: i64| {
Ok(u8::try_from(n).map_err(|_| {
rhai::EvalAltResult::ErrorRuntime("Invalid register value".into(), rhai::Position::NONE)
})?)
});
module.set_native_fn("as_i64", |n: u8| Ok(n as i64));
let datamod = Rc::new(data::module(&mut engine, SharedObject::clone(&obj)));
engine.register_global_module(Rc::new(module));
engine.register_static_module("data", datamod);
engine.register_type_with_name::<object::SymbolRef>("SymbolRef");
loader(&mut engine)?;
linker::link(obj, linkout)?;
Ok(())
}

47
hbasm/src/linker.rs Normal file
View file

@ -0,0 +1,47 @@
//! Simple flat-bytecode linker
use {
crate::{
object::{RelocKey, RelocType, Section},
SharedObject,
},
std::io::Write,
};
pub fn link(object: SharedObject, out: &mut impl Write) -> std::io::Result<()> {
let obj = &mut *object.borrow_mut();
// Walk relocation table entries
for (&loc, entry) in &obj.relocs {
let value = match &entry.key {
// Symbol – direct reference
RelocKey::Symbol(sym) => obj.symbols[*sym],
// Label – indirect label reference
RelocKey::Label(label) => obj.symbols[obj.labels[label]],
}
.ok_or_else(|| std::io::Error::other("Invalid symbol"))?;
let offset = match value.location {
// Text section is on the beginning
Section::Text => value.offset,
// Data section follows text section immediately
Section::Data => value.offset + obj.sections.text.len(),
};
// Insert address or calulate relative offset
match entry.ty {
RelocType::Rel32 => obj.sections.text[loc..loc + 4]
.copy_from_slice(&((offset as isize - loc as isize) as i32).to_le_bytes()),
RelocType::Rel16 => obj.sections.text[loc..loc + 2]
.copy_from_slice(&((offset as isize - loc as isize) as i16).to_le_bytes()),
RelocType::Abs64 => obj.sections.text[loc..loc + 8]
.copy_from_slice(&(offset as isize - loc as isize).to_le_bytes()),
}
}
// Write to output
out.write_all(&obj.sections.text)?;
out.write_all(&obj.sections.data)
}

8
hbasm/src/main.rs Normal file
View file

@ -0,0 +1,8 @@
use std::{io::stdout, path::PathBuf};
fn main() -> Result<(), Box<dyn std::error::Error>> {
let path = PathBuf::from(std::env::args().nth(1).ok_or("Missing path")?);
hbasm::assembler(&mut stdout(), |engine| engine.run_file(path))?;
Ok(())
}

94
hbasm/src/object.rs Normal file
View file

@ -0,0 +1,94 @@
//! Code object
use {rhai::ImmutableString, std::collections::HashMap};
/// Section tabel
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
pub enum Section {
Text,
Data,
}
/// Symbol entry (in what section, where)
#[derive(Clone, Copy, Debug)]
pub struct SymbolEntry {
pub location: Section,
pub offset: usize,
}
/// Relocation table key
#[derive(Clone, Debug)]
pub enum RelocKey {
/// Direct reference
Symbol(usize),
/// Indirect reference
Label(ImmutableString),
}
/// Relocation type
#[derive(Clone, Copy, Debug)]
pub enum RelocType {
Rel32,
Rel16,
Abs64,
}
/// Relocation table entry
#[derive(Clone, Debug)]
pub struct RelocEntry {
pub key: RelocKey,
pub ty: RelocType,
}
/// Object code
#[derive(Clone, Debug, Default)]
pub struct Sections {
pub text: Vec<u8>,
pub data: Vec<u8>,
}
/// Object
#[derive(Clone, Debug, Default)]
pub struct Object {
/// Vectors with sections
pub sections: Sections,
/// Symbol table
pub symbols: Vec<Option<SymbolEntry>>,
/// Labels to symbols table
pub labels: HashMap<ImmutableString, usize>,
/// Relocation table
pub relocs: HashMap<usize, RelocEntry>,
}
#[derive(Clone, Copy, Debug)]
#[repr(transparent)]
pub struct SymbolRef(pub usize);
impl Object {
/// Insert symbol at current location in specified section
pub fn symbol(&mut self, section: Section) -> SymbolRef {
let section_buf = match section {
Section::Text => &mut self.sections.text,
Section::Data => &mut self.sections.data,
};
self.symbols.push(Some(SymbolEntry {
location: section,
offset: section_buf.len(),
}));
SymbolRef(self.symbols.len() - 1)
}
/// Insert to relocation table and write zeroes to code
pub fn relocation(&mut self, key: RelocKey, ty: RelocType) {
self.relocs
.insert(self.sections.text.len(), RelocEntry { key, ty });
self.sections.text.extend(match ty {
RelocType::Rel32 => &[0_u8; 4] as &[u8],
RelocType::Rel16 => &[0; 2],
RelocType::Abs64 => &[0; 8],
});
}
}

8
bytecode/Cargo.toml → hbbytecode/Cargo.toml
View file

@ -3,8 +3,6 @@ name = "hbbytecode"
version = "0.1.0" version = "0.1.0"
edition = "2018" edition = "2018"
[features] [dependencies]
default = ["disasm"] paste = "1.0.14"
std = [] with_builtin_macros = "0.0.3"
disasm = ["std"]

0
bytecode/hbbytecode.h → hbbytecode/hbbytecode.h
View file

0
bytecode/instructions.in → hbbytecode/instructions.in
View file

185
hbbytecode/src/lib.rs Normal file
View file

@ -0,0 +1,185 @@
#![no_std]
use core::convert::TryFrom;
type OpR = u8;
type OpA = u64;
type OpO = i32;
type OpP = i16;
type OpB = u8;
type OpH = u16;
type OpW = u32;
type OpD = u64;
/// # Safety
/// Has to be valid to be decoded from bytecode.
pub unsafe trait BytecodeItem {}
macro_rules! define_items {
($($name:ident ($($nm:ident: $item:ident),* $(,)?)),* $(,)?) => {
$(
#[derive(Clone, Copy, Debug)]
#[repr(packed)]
pub struct $name($(pub $item),*);
unsafe impl BytecodeItem for $name {}
impl Encodable for $name {
fn encode(self, _buffer: &mut impl Buffer) {
let Self($($nm),*) = self;
$(
for byte in $nm.to_le_bytes() {
unsafe { _buffer.write(byte) };
}
)*
}
fn encode_len(self) -> usize {
core::mem::size_of::<Self>()
}
}
)*
};
}
define_items! {
OpsRR (a: OpR, b: OpR ),
OpsRRR (a: OpR, b: OpR, c: OpR ),
OpsRRRR (a: OpR, b: OpR, c: OpR, d: OpR),
OpsRRB (a: OpR, b: OpR, c: OpB ),
OpsRRH (a: OpR, b: OpR, c: OpH ),
OpsRRW (a: OpR, b: OpR, c: OpW ),
OpsRRD (a: OpR, b: OpR, c: OpD ),
OpsRB (a: OpR, b: OpB ),
OpsRH (a: OpR, b: OpH ),
OpsRW (a: OpR, b: OpW ),
OpsRD (a: OpR, b: OpD ),
OpsRRA (a: OpR, b: OpR, c: OpA ),
OpsRRAH (a: OpR, b: OpR, c: OpA, d: OpH),
OpsRROH (a: OpR, b: OpR, c: OpO, d: OpH),
OpsRRPH (a: OpR, b: OpR, c: OpP, d: OpH),
OpsRRO (a: OpR, b: OpR, c: OpO ),
OpsRRP (a: OpR, b: OpR, c: OpP ),
OpsO (a: OpO, ),
OpsP (a: OpP, ),
OpsN ( ),
}
unsafe impl BytecodeItem for u8 {}
::with_builtin_macros::with_builtin! {
let $spec = include_from_root!("instructions.in") in {
/// Invoke macro with bytecode definition
///
/// # Format
/// ```text
/// Opcode, Mnemonic, Type, Docstring;
/// ```
///
/// # Type
/// ```text
/// Types consist of letters meaning a single field
/// | Type | Size (B) | Meaning |
/// |:-----|:---------|:------------------------|
/// | N | 0 | Empty |
/// | R | 1 | Register |
/// | A | 8 | Absolute address |
/// | O | 4 | Relative address offset |
/// | P | 2 | Relative address offset |
/// | B | 1 | Immediate |
/// | H | 2 | Immediate |
/// | W | 4 | Immediate |
/// | D | 8 | Immediate |
/// ```
#[macro_export]
macro_rules! invoke_with_def {
($($macro:tt)*) => {
$($macro)*! { $spec }
};
}
}
}
pub trait Buffer {
fn reserve(&mut self, bytes: usize);
/// # Safety
/// Reserve needs to be called before this function, and only reserved amount can be written.
unsafe fn write(&mut self, byte: u8);
}
pub trait Encodable {
fn encode(self, buffer: &mut impl Buffer);
fn encode_len(self) -> usize;
}
macro_rules! gen_opcodes {
($($opcode:expr, $mnemonic:ident, $ty:ident, $doc:literal;)*) => {
pub mod opcode {
$(
#[doc = $doc]
pub const $mnemonic: u8 = $opcode;
)*
paste::paste! {
#[derive(Clone, Copy, Debug)]
#[repr(u8)]
pub enum Op { $(
[< $mnemonic:lower:camel >](super::[<Ops $ty>]),
)* }
impl Op {
pub fn size(&self) -> usize {
(match self {
$(Self::[<$mnemonic:lower:camel>] { .. } => core::mem::size_of::<super::[<Ops $ty>]>(),)*
}) + 1
}
}
impl crate::Encodable for Op {
fn encode(self, buffer: &mut impl crate::Buffer) {
match self {
$(
Self::[< $mnemonic:lower:camel >](op) => {
unsafe { buffer.write($opcode) };
op.encode(buffer);
}
)*
}
}
fn encode_len(self) -> usize {
match self {
$(
Self::[< $mnemonic:lower:camel >](op) => {
1 + crate::Encodable::encode_len(op)
}
)*
}
}
}
}
}
};
}
/// Rounding mode
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
#[repr(u8)]
pub enum RoundingMode {
NearestEven = 0,
Truncate = 1,
Up = 2,
Down = 3,
}
impl TryFrom<u8> for RoundingMode {
type Error = ();
fn try_from(value: u8) -> Result<Self, Self::Error> {
(value <= 3)
.then(|| unsafe { core::mem::transmute(value) })
.ok_or(())
}
}
invoke_with_def!(gen_opcodes);

13
hbvm/Cargo.toml Normal file
View file

@ -0,0 +1,13 @@
[package]
name = "hbvm"
version = "0.1.0"
edition = "2021"
[features]
default = ["alloc", "soft-float"]
alloc = []
nightly = []
soft-float = []
[dependencies]
hbbytecode = { path = "../hbbytecode" }

0
vm/README.md → hbvm/README.md
View file

0
vm/assets/add.hb → hbvm/assets/add.hb
View file

0
vm/assets/celsius_converter.hb → hbvm/assets/celsius_converter.hb
View file

0
vm/assets/ecall.hb → hbvm/assets/ecall.hb
View file

0
vm/assets/inf_loop.hb → hbvm/assets/inf_loop.hb
View file

0
vm/assets/memory.hb → hbvm/assets/memory.hb
View file

0
vm/fuzz/.gitignore → hbvm/fuzz/.gitignore vendored
View file

3
vm/fuzz/Cargo.toml → hbvm/fuzz/Cargo.toml
View file

@ -13,6 +13,9 @@ libfuzzer-sys = "0.4"
[dependencies.hbvm] [dependencies.hbvm]
path = ".." path = ".."
[dependencies.hbbytecode]
path = "../../hbbytecode"
# Prevent this from interfering with workspaces # Prevent this from interfering with workspaces
[workspace] [workspace]
members = ["."] members = ["."]

0
vm/fuzz/fuzz_targets/vm.rs → hbvm/fuzz/fuzz_targets/vm.rs
View file

39
vm/src/bmc.rs → hbvm/src/bmc.rs
View file

@ -29,7 +29,12 @@ impl BlockCopier {
/// Construct a new one /// Construct a new one
#[inline] #[inline]
pub fn new(src: Address, dst: Address, count: usize) -> Self { pub fn new(src: Address, dst: Address, count: usize) -> Self {
Self { src, dst, n_buffers: count / BUF_SIZE, rem: count % BUF_SIZE } Self {
src,
dst,
n_buffers: count / BUF_SIZE,
rem: count % BUF_SIZE,
}
} }
/// Copy one block /// Copy one block
@ -42,9 +47,15 @@ impl BlockCopier {
// We have at least one buffer size to copy // We have at least one buffer size to copy
if self.n_buffers != 0 { if self.n_buffers != 0 {
if let Err(e) = if let Err(e) = unsafe {
unsafe { act(memory, self.src, self.dst, buf.0.as_mut_ptr().cast(), BUF_SIZE) } act(
{ memory,
self.src,
self.dst,
buf.0.as_mut_ptr().cast(),
BUF_SIZE,
)
} {
return Poll::Ready(Err(e)); return Poll::Ready(Err(e));
} }
@ -64,9 +75,15 @@ impl BlockCopier {
} }
if self.rem != 0 { if self.rem != 0 {
if let Err(e) = if let Err(e) = unsafe {
unsafe { act(memory, self.src, self.dst, buf.0.as_mut_ptr().cast(), self.rem) } act(
{ memory,
self.src,
self.dst,
buf.0.as_mut_ptr().cast(),
self.rem,
)
} {
return Poll::Ready(Err(e)); return Poll::Ready(Err(e));
} }
} }
@ -86,13 +103,17 @@ unsafe fn act(
) -> Result<(), BlkCopyError> { ) -> Result<(), BlkCopyError> {
unsafe { unsafe {
// Load to buffer // Load to buffer
memory.load(src, buf, count).map_err(|super::mem::LoadError(addr)| BlkCopyError { memory
.load(src, buf, count)
.map_err(|super::mem::LoadError(addr)| BlkCopyError {
access_reason: MemoryAccessReason::Load, access_reason: MemoryAccessReason::Load,
addr, addr,
})?; })?;
// Store from buffer // Store from buffer
memory.store(dst, buf, count).map_err(|super::mem::StoreError(addr)| BlkCopyError { memory
.store(dst, buf, count)
.map_err(|super::mem::StoreError(addr)| BlkCopyError {
access_reason: MemoryAccessReason::Store, access_reason: MemoryAccessReason::Store,
addr, addr,
})?; })?;

5
vm/src/float/aarch64.rs → hbvm/src/float/aarch64.rs
View file

@ -9,8 +9,11 @@ macro_rules! fnsdef {
$vis fn $name(val: $from, mode: RoundingMode) -> $to { $vis fn $name(val: $from, mode: RoundingMode) -> $to {
let result: $to; let result: $to;
unsafe { unsafe {
let fpcr: u64; if mode == RoundingMode::NearestEven {
return;
}
let fpcr: u64;
unsafe { asm!("mrs {}, fpcr", out(reg) fpcr) }; unsafe { asm!("mrs {}, fpcr", out(reg) fpcr) };
let fpcr_new = fpcr & !(0b11 << 22) let fpcr_new = fpcr & !(0b11 << 22)

12
vm/src/float/mod.rs → hbvm/src/float/mod.rs
View file

@ -3,23 +3,23 @@ macro_rules! arch_specific {
$({$($cfg:tt)*} : $mod:ident;)* $({$($cfg:tt)*} : $mod:ident;)*
} => { } => {
$( $(
#[cfg($($cfg)*)] #[cfg(all(not(feature = "soft-float"), $($cfg)*))]
mod $mod; mod $mod;
#[cfg($($cfg)*)] #[cfg(all(not(feature = "soft-float"), $($cfg)*))]
pub use $mod::*; pub use $mod::*;
#[cfg($($cfg)*)] #[cfg(all(not(feature = "soft-float"), $($cfg)*))]
pub const FL_ARCH_SPECIFIC_SUPPORTED: bool = true; pub const FL_ARCH_SPECIFIC_SUPPORTED: bool = true;
)* )*
#[cfg(not(any($($($cfg)*),*)))] #[cfg(any(feature = "soft-float", not(any($($($cfg)*),*))))]
mod unsupported; mod unsupported;
#[cfg(not(any($($($cfg)*),*)))] #[cfg(any(feature = "soft-float", not(any($($($cfg)*),*))))]
pub use unsupported::*; pub use unsupported::*;
#[cfg(not(any($($($cfg)*),*)))] #[cfg(any(feature = "soft-float", not(any($($($cfg)*),*))))]
pub const FL_ARCH_SPECIFIC_SUPPORTED: bool = false; pub const FL_ARCH_SPECIFIC_SUPPORTED: bool = false;
}; };
} }

0
vm/src/float/riscv64.rs → hbvm/src/float/riscv64.rs
View file

0
vm/src/float/unsupported.rs → hbvm/src/float/unsupported.rs
View file

0
vm/src/float/x86_64.rs → hbvm/src/float/x86_64.rs
View file

49
vm/src/lib.rs → hbvm/src/lib.rs
View file

@ -26,6 +26,7 @@ mod utils;
mod vmrun; mod vmrun;
pub use float::FL_ARCH_SPECIFIC_SUPPORTED; pub use float::FL_ARCH_SPECIFIC_SUPPORTED;
use { use {
bmc::BlockCopier, bmc::BlockCopier,
mem::{Address, Memory}, mem::{Address, Memory},
@ -36,7 +37,7 @@ use {
pub struct Vm<Mem, const TIMER_QUOTIENT: usize> { pub struct Vm<Mem, const TIMER_QUOTIENT: usize> {
/// Holds 256 registers /// Holds 256 registers
/// ///
/// Writing to register 0 is considered idk behaviour /// Writing to register 0 is considered undefined behaviour
/// in terms of HoleyBytes program execution /// in terms of HoleyBytes program execution
pub registers: [Value; 256], pub registers: [Value; 256],
@ -53,18 +54,6 @@ pub struct Vm<Mem, const TIMER_QUOTIENT: usize> {
copier: Option<BlockCopier>, copier: Option<BlockCopier>,
} }
impl<Mem: Default, const TIMER_QUOTIENT: usize> Default for Vm<Mem, TIMER_QUOTIENT> {
fn default() -> Self {
Self {
registers: [Value::from(0_u64); 256],
memory: Mem::default(),
pc: Address::default(),
timer: 0,
copier: None,
}
}
}
impl<Mem, const TIMER_QUOTIENT: usize> Vm<Mem, TIMER_QUOTIENT> impl<Mem, const TIMER_QUOTIENT: usize> Vm<Mem, TIMER_QUOTIENT>
where where
Mem: Memory, Mem: Memory,
@ -74,7 +63,13 @@ where
/// # Safety /// # Safety
/// Program code has to be validated /// Program code has to be validated
pub unsafe fn new(memory: Mem, entry: Address) -> Self { pub unsafe fn new(memory: Mem, entry: Address) -> Self {
Self { registers: [Value::from(0_u64); 256], memory, pc: entry, timer: 0, copier: None } Self {
registers: [Value::from(0_u64); 256],
memory,
pc: entry,
timer: 0,
copier: None,
}
} }
/// Read register /// Read register
@ -126,33 +121,11 @@ pub enum VmRunError {
/// Invalid operand /// Invalid operand
InvalidOperand, InvalidOperand,
}
impl core::fmt::Display for VmRunError { /// Unimplemented feature
fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result { Unimplemented,
match self {
VmRunError::InvalidOpcode(op) => {
f.write_str("invalid op code: ").and_then(|_| op.fmt(f))
}
VmRunError::LoadAccessEx(address) => {
f.write_str("falied to load at ").and_then(|_| address.fmt(f))
}
VmRunError::ProgramFetchLoadEx(address) => {
f.write_str("falied to load instruction at ").and_then(|_| address.fmt(f))
}
VmRunError::StoreAccessEx(address) => {
f.write_str("falied to store at ").and_then(|_| address.fmt(f))
}
VmRunError::RegOutOfBounds => f.write_str("reg out of bounds"),
VmRunError::AddrOutOfBounds => f.write_str("addr out-of-bounds"),
VmRunError::Unreachable => f.write_str("unreachable"),
VmRunError::InvalidOperand => f.write_str("invalud operand"),
}
}
} }
impl core::error::Error for VmRunError {}
/// Virtual machine halt ok /// Virtual machine halt ok
#[derive(Copy, Clone, Debug, PartialEq, Eq)] #[derive(Copy, Clone, Debug, PartialEq, Eq)]
pub enum VmRunOk { pub enum VmRunOk {

8
vm/src/mem/addr.rs → hbvm/src/mem/addr.rs
View file

@ -6,7 +6,7 @@ use {
}; };
/// Memory address /// Memory address
#[derive(Default, Clone, Copy, PartialEq, Eq, PartialOrd, Ord)] #[derive(Clone, Copy, PartialEq, Eq, PartialOrd, Ord)]
pub struct Address(u64); pub struct Address(u64);
impl Address { impl Address {
/// A null address /// A null address
@ -47,12 +47,6 @@ impl Address {
self.0 self.0
} }
/// Get ptr to the next instruction
#[inline(always)]
pub fn next<A>(self) -> u64 {
self.0.wrapping_add(core::mem::size_of::<A>() as u64 + 1)
}
/// Construct new address /// Construct new address
#[inline(always)] #[inline(always)]
pub fn new(val: u64) -> Self { pub fn new(val: u64) -> Self {

39
vm/src/mem/mod.rs → hbvm/src/mem/mod.rs
View file

@ -4,9 +4,10 @@ pub mod softpaging;
pub(crate) mod addr; pub(crate) mod addr;
use crate::utils::impl_display;
pub use addr::Address; pub use addr::Address;
use crate::utils::impl_display;
/// Load-store memory access /// Load-store memory access
pub trait Memory { pub trait Memory {
/// Load data from memory on address /// Load data from memory on address
@ -35,7 +36,7 @@ pub trait Memory {
/// ///
/// # Safety /// # Safety
/// - Data read have to be valid /// - Data read have to be valid
unsafe fn prog_read<T: Copy + 'static>(&mut self, addr: Address) -> T; unsafe fn prog_read<T: Copy>(&mut self, addr: Address) -> T;
} }
/// Unhandled load access trap /// Unhandled load access trap
@ -77,37 +78,3 @@ impl From<StoreError> for crate::VmRunError {
Self::StoreAccessEx(value.0) Self::StoreAccessEx(value.0)
} }
} }
#[derive(Default)]
pub struct HostMemory;
impl Memory for HostMemory {
#[inline]
unsafe fn load(
&mut self,
addr: Address,
target: *mut u8,
count: usize,
) -> Result<(), LoadError> {
unsafe { core::ptr::copy(addr.get() as *const u8, target, count) }
Ok(())
}
#[inline]
unsafe fn store(
&mut self,
addr: Address,
source: *const u8,
count: usize,
) -> Result<(), StoreError> {
debug_assert!(addr.get() != 0);
debug_assert!(!source.is_null());
unsafe { core::ptr::copy(source, addr.get() as *mut u8, count) }
Ok(())
}
#[inline]
unsafe fn prog_read<T: Copy>(&mut self, addr: Address) -> T {
debug_assert!(addr.get() != 0);
unsafe { core::ptr::read(addr.get() as *const T) }
}
}

12
vm/src/mem/softpaging/icache.rs → hbvm/src/mem/softpaging/icache.rs
View file

@ -1,8 +1,9 @@
//! Program instruction cache //! Program instruction cache
use crate::mem::Address;
use { use {
super::{lookup::AddrPageLookuper, paging::PageTable, PageSize}, super::{lookup::AddrPageLookuper, paging::PageTable, PageSize},
crate::mem::Address,
core::{ core::{
mem::{size_of, MaybeUninit}, mem::{size_of, MaybeUninit},
ptr::{copy_nonoverlapping, NonNull}, ptr::{copy_nonoverlapping, NonNull},
@ -45,8 +46,9 @@ impl ICache {
) -> Option<T> { ) -> Option<T> {
let mut ret = MaybeUninit::<T>::uninit(); let mut ret = MaybeUninit::<T>::uninit();
let pbase = let pbase = self
self.data.or_else(|| unsafe { self.fetch_page(self.base + self.size, root_pt) })?; .data
.or_else(|| unsafe { self.fetch_page(self.base + self.size, root_pt) })?;
// Get address base // Get address base
let base = addr.map(|x| x & self.mask); let base = addr.map(|x| x & self.mask);
@ -60,7 +62,9 @@ impl ICache {
let requ_size = size_of::<T>(); let requ_size = size_of::<T>();
// Page overflow // Page overflow
let rem = (offset as usize).saturating_add(requ_size).saturating_sub(self.size as _); let rem = (offset as usize)
.saturating_add(requ_size)
.saturating_sub(self.size as _);
let first_copy = requ_size.saturating_sub(rem); let first_copy = requ_size.saturating_sub(rem);
// Copy non-overflowing part // Copy non-overflowing part

18
vm/src/mem/softpaging/lookup.rs → hbvm/src/mem/softpaging/lookup.rs
View file

@ -1,12 +1,11 @@
//! Address lookup //! Address lookup
use { use crate::mem::addr::Address;
super::{
use super::{
addr_extract_index, addr_extract_index,
paging::{PageTable, Permission}, paging::{PageTable, Permission},
PageSize, PageSize,
},
crate::mem::addr::Address,
}; };
/// Good result from address split /// Good result from address split
@ -49,7 +48,11 @@ impl AddrPageLookuper {
/// Create a new page lookuper /// Create a new page lookuper
#[inline] #[inline]
pub const fn new(addr: Address, size: usize, pagetable: *const PageTable) -> Self { pub const fn new(addr: Address, size: usize, pagetable: *const PageTable) -> Self {
Self { addr, size, pagetable } Self {
addr,
size,
pagetable,
}
} }
/// Bump address by size X /// Bump address by size X
@ -75,8 +78,9 @@ impl Iterator for AddrPageLookuper {
for lvl in (0..5).rev() { for lvl in (0..5).rev() {
// Get an entry // Get an entry
unsafe { unsafe {
let entry = let entry = (*current_pt)
(*current_pt).table.get_unchecked(addr_extract_index(self.addr, lvl)); .table
.get_unchecked(addr_extract_index(self.addr, lvl));
let ptr = entry.ptr(); let ptr = entry.ptr();
match entry.permission() { match entry.permission() {

27
vm/src/mem/softpaging/mapping.rs → hbvm/src/mem/softpaging/mapping.rs
View file

@ -1,16 +1,17 @@
//! Automatic memory mapping //! Automatic memory mapping
use crate::{mem::addr::Address, utils::impl_display};
use { use {
super::{ super::{
addr_extract_index, addr_extract_index,
paging::{PageTable, Permission, PtEntry, PtPointedData}, paging::{PageTable, Permission, PtEntry, PtPointedData},
PageSize, SoftPagedMem, PageSize, SoftPagedMem,
}, },
crate::{mem::addr::Address, utils::impl_display},
alloc::boxed::Box, alloc::boxed::Box,
}; };
impl<A, const OUT_PROG_EXEC: bool> SoftPagedMem<'_, A, OUT_PROG_EXEC> { impl<'p, A, const OUT_PROG_EXEC: bool> SoftPagedMem<'p, A, OUT_PROG_EXEC> {
/// Maps host's memory into VM's memory /// Maps host's memory into VM's memory
/// ///
/// # Safety /// # Safety
@ -35,8 +36,11 @@ impl<A, const OUT_PROG_EXEC: bool> SoftPagedMem<'_, A, OUT_PROG_EXEC> {
// Walk pagetable levels // Walk pagetable levels
for lvl in (lookup_depth + 1..5).rev() { for lvl in (lookup_depth + 1..5).rev() {
let entry = let entry = unsafe {
unsafe { (*current_pt).table.get_unchecked_mut(addr_extract_index(target, lvl)) }; (*current_pt)
.table
.get_unchecked_mut(addr_extract_index(target, lvl))
};
let ptr = entry.ptr(); let ptr = entry.ptr();
match entry.permission() { match entry.permission() {
@ -46,7 +50,9 @@ impl<A, const OUT_PROG_EXEC: bool> SoftPagedMem<'_, A, OUT_PROG_EXEC> {
// Increase children count // Increase children count
unsafe { *current_pt }.childen += 1; unsafe { *current_pt }.childen += 1;
let table = Box::into_raw(Box::new(PtPointedData { pt: PageTable::default() })); let table = Box::into_raw(Box::new(PtPointedData {
pt: PageTable::default(),
}));
unsafe { core::ptr::write(entry, PtEntry::new(table, Permission::Node)) }; unsafe { core::ptr::write(entry, PtEntry::new(table, Permission::Node)) };
current_pt = table as _; current_pt = table as _;
@ -60,7 +66,9 @@ impl<A, const OUT_PROG_EXEC: bool> SoftPagedMem<'_, A, OUT_PROG_EXEC> {
} }
let node = unsafe { let node = unsafe {
(*current_pt).table.get_unchecked_mut(addr_extract_index(target, lookup_depth)) (*current_pt)
.table
.get_unchecked_mut(addr_extract_index(target, lookup_depth))
}; };
// Check if node is not mapped // Check if node is not mapped
@ -87,8 +95,11 @@ impl<A, const OUT_PROG_EXEC: bool> SoftPagedMem<'_, A, OUT_PROG_EXEC> {
// Walk page table in reverse // Walk page table in reverse
for lvl in (0..5).rev() { for lvl in (0..5).rev() {
let entry = let entry = unsafe {
unsafe { (*current_pt).table.get_unchecked_mut(addr_extract_index(addr, lvl)) }; (*current_pt)
.table
.get_unchecked_mut(addr_extract_index(addr, lvl))
};
let ptr = entry.ptr(); let ptr = entry.ptr();
match entry.permission() { match entry.permission() {

24
vm/src/mem/softpaging/mod.rs → hbvm/src/mem/softpaging/mod.rs
View file

@ -32,8 +32,8 @@ pub struct SoftPagedMem<'p, PfH, const OUT_PROG_EXEC: bool = true> {
pub icache: ICache, pub icache: ICache,
} }
impl<PfH: HandlePageFault, const OUT_PROG_EXEC: bool> Memory impl<'p, PfH: HandlePageFault, const OUT_PROG_EXEC: bool> Memory
for SoftPagedMem<'_, PfH, OUT_PROG_EXEC> for SoftPagedMem<'p, PfH, OUT_PROG_EXEC>
{ {
/// Load value from an address /// Load value from an address
/// ///
@ -92,13 +92,14 @@ impl<PfH: HandlePageFault, const OUT_PROG_EXEC: bool> Memory
} }
} }
impl<PfH: HandlePageFault, const OUT_PROG_EXEC: bool> SoftPagedMem<'_, PfH, OUT_PROG_EXEC> { impl<'p, PfH: HandlePageFault, const OUT_PROG_EXEC: bool> SoftPagedMem<'p, PfH, OUT_PROG_EXEC> {
// Everyone behold, the holy function, the god of HBVM memory accesses! // Everyone behold, the holy function, the god of HBVM memory accesses!
/// Split address to pages, check their permissions and feed pointers with offset /// Split address to pages, check their permissions and feed pointers with offset
/// to a specified function. /// to a specified function.
/// ///
/// If page is not found, execute page fault trap handler. /// If page is not found, execute page fault trap handler.
#[allow(clippy::too_many_arguments)] // Silence peasant
fn memory_access( fn memory_access(
&mut self, &mut self,
reason: MemoryAccessReason, reason: MemoryAccessReason,
@ -126,7 +127,10 @@ impl<PfH: HandlePageFault, const OUT_PROG_EXEC: bool> SoftPagedMem<'_, PfH, OUT_
); );
// Return shifted from what we've already copied // Return shifted from what we've already copied
(src.saturating_add(to_copy as u64), len.saturating_sub(to_copy)) (
src.saturating_add(to_copy as u64),
len.saturating_sub(to_copy),
)
} else { } else {
(src, len) // Nothing weird! (src, len) // Nothing weird!
}; };
@ -141,7 +145,12 @@ impl<PfH: HandlePageFault, const OUT_PROG_EXEC: bool> SoftPagedMem<'_, PfH, OUT_
loop { loop {
match pspl.next() { match pspl.next() {
// Page is found // Page is found
Some(Ok(AddrPageLookupOk { vaddr, ptr, size, perm })) => { Some(Ok(AddrPageLookupOk {
vaddr,
ptr,
size,
perm,
})) => {
if !permission_check(perm) { if !permission_check(perm) {
return Err(vaddr); return Err(vaddr);
} }
@ -234,7 +243,10 @@ pub mod perm_check {
/// Page is readable /// Page is readable
#[inline(always)] #[inline(always)]
pub const fn readable(perm: Permission) -> bool { pub const fn readable(perm: Permission) -> bool {
matches!(perm, Permission::Readonly | Permission::Write | Permission::Exec) matches!(
perm,
Permission::Readonly | Permission::Write | Permission::Exec
)
} }
/// Page is writable /// Page is writable

5
vm/src/mem/softpaging/paging.rs → hbvm/src/mem/softpaging/paging.rs
View file

@ -68,7 +68,10 @@ pub struct PageTable {
impl Default for PageTable { impl Default for PageTable {
fn default() -> Self { fn default() -> Self {
// SAFETY: It's fine, zeroed page table entry is valid (= empty) // SAFETY: It's fine, zeroed page table entry is valid (= empty)
Self { childen: 0, table: unsafe { MaybeUninit::zeroed().assume_init() } } Self {
childen: 0,
table: unsafe { MaybeUninit::zeroed().assume_init() },
}
} }
} }

0
vm/src/utils.rs → hbvm/src/utils.rs
View file

2
vm/src/value.rs → hbvm/src/value.rs
View file

@ -6,7 +6,7 @@ use crate::utils::static_assert;
/// ///
/// # Safety /// # Safety
/// Its variants have to be sound to byte-reinterpretate /// Its variants have to be sound to byte-reinterpretate
/// between each other. Otherwise the behaviour is idk. /// between each other. Otherwise the behaviour is undefined.
macro_rules! value_def { macro_rules! value_def {
($($ty:ident),* $(,)?) => { ($($ty:ident),* $(,)?) => {
/// HBVM register value /// HBVM register value

342
vm/src/vmrun.rs → hbvm/src/vmrun.rs
View file

@ -17,8 +17,9 @@ use {
macro_rules! handler { macro_rules! handler {
($self:expr, |$ty:ident ($($ident:pat),* $(,)?)| $expr:expr) => {{ ($self:expr, |$ty:ident ($($ident:pat),* $(,)?)| $expr:expr) => {{
let $ty($($ident),*) = $self.decode::<$ty>(); #[allow(unused_unsafe)]
let e = $expr; let $ty($($ident),*) = unsafe { $self.decode::<$ty>() };
#[allow(clippy::no_effect)] let e = $expr;
$self.bump_pc::<$ty>(); $self.bump_pc::<$ty>();
e e
}}; }};
@ -33,7 +34,7 @@ where
/// Program can return [`VmRunError`] if a trap handling failed /// Program can return [`VmRunError`] if a trap handling failed
#[cfg_attr(feature = "nightly", repr(align(4096)))] #[cfg_attr(feature = "nightly", repr(align(4096)))]
pub fn run(&mut self) -> Result<VmRunOk, VmRunError> { pub fn run(&mut self) -> Result<VmRunOk, VmRunError> {
use hbbytecode::Instr as I; use hbbytecode::opcode::*;
loop { loop {
// Big match // Big match
// //
@ -55,112 +56,105 @@ where
// - Yes, we assume you run 64 bit CPU. Else ?conradluget a better CPU // - Yes, we assume you run 64 bit CPU. Else ?conradluget a better CPU
// sorry 8 bit fans, HBVM won't run on your Speccy :( // sorry 8 bit fans, HBVM won't run on your Speccy :(
unsafe { unsafe {
match self match self.memory.prog_read::<u8>(self.pc as _) {
.memory UN => {
.prog_read::<u8>(self.pc as _)
.try_into()
.map_err(VmRunError::InvalidOpcode)?
{
I::UN => {
self.bump_pc::<OpsN>(); self.bump_pc::<OpsN>();
return Err(VmRunError::Unreachable); return Err(VmRunError::Unreachable);
} }
I::TX => { TX => {
self.bump_pc::<OpsN>(); self.bump_pc::<OpsN>();
return Ok(VmRunOk::End); return Ok(VmRunOk::End);
} }
I::NOP => handler!(self, |OpsN()| ()), NOP => handler!(self, |OpsN()| ()),
I::ADD8 => self.binary_op(u8::wrapping_add), ADD8 => self.binary_op(u8::wrapping_add),
I::ADD16 => self.binary_op(u16::wrapping_add), ADD16 => self.binary_op(u16::wrapping_add),
I::ADD32 => self.binary_op(u32::wrapping_add), ADD32 => self.binary_op(u32::wrapping_add),
I::ADD64 => self.binary_op(u64::wrapping_add), ADD64 => self.binary_op(u64::wrapping_add),
I::SUB8 => self.binary_op(u8::wrapping_sub), SUB8 => self.binary_op(u8::wrapping_sub),
I::SUB16 => self.binary_op(u16::wrapping_sub), SUB16 => self.binary_op(u16::wrapping_sub),
I::SUB32 => self.binary_op(u32::wrapping_sub), SUB32 => self.binary_op(u32::wrapping_sub),
I::SUB64 => self.binary_op(u64::wrapping_sub), SUB64 => self.binary_op(u64::wrapping_sub),
I::MUL8 => self.binary_op(u8::wrapping_mul), MUL8 => self.binary_op(u8::wrapping_mul),
I::MUL16 => self.binary_op(u16::wrapping_mul), MUL16 => self.binary_op(u16::wrapping_mul),
I::MUL32 => self.binary_op(u32::wrapping_mul), MUL32 => self.binary_op(u32::wrapping_mul),
I::MUL64 => self.binary_op(u64::wrapping_mul), MUL64 => self.binary_op(u64::wrapping_mul),
I::AND => self.binary_op::<u64>(ops::BitAnd::bitand), AND => self.binary_op::<u64>(ops::BitAnd::bitand),
I::OR => self.binary_op::<u64>(ops::BitOr::bitor), OR => self.binary_op::<u64>(ops::BitOr::bitor),
I::XOR => self.binary_op::<u64>(ops::BitXor::bitxor), XOR => self.binary_op::<u64>(ops::BitXor::bitxor),
I::SLU8 => self.binary_op_shift::<u8>(u8::wrapping_shl), SLU8 => self.binary_op_shift::<u8>(u8::wrapping_shl),
I::SLU16 => self.binary_op_shift::<u16>(u16::wrapping_shl), SLU16 => self.binary_op_shift::<u16>(u16::wrapping_shl),
I::SLU32 => self.binary_op_shift::<u32>(u32::wrapping_shl), SLU32 => self.binary_op_shift::<u32>(u32::wrapping_shl),
I::SLU64 => self.binary_op_shift::<u64>(u64::wrapping_shl), SLU64 => self.binary_op_shift::<u64>(u64::wrapping_shl),
I::SRU8 => self.binary_op_shift::<u8>(u8::wrapping_shr), SRU8 => self.binary_op_shift::<u8>(u8::wrapping_shr),
I::SRU16 => self.binary_op_shift::<u16>(u16::wrapping_shr), SRU16 => self.binary_op_shift::<u16>(u16::wrapping_shr),
I::SRU32 => self.binary_op_shift::<u32>(u32::wrapping_shr), SRU32 => self.binary_op_shift::<u32>(u32::wrapping_shr),
I::SRU64 => self.binary_op_shift::<u64>(u64::wrapping_shr), SRU64 => self.binary_op_shift::<u64>(u64::wrapping_shr),
I::SRS8 => self.binary_op_shift::<i8>(i8::wrapping_shr), SRS8 => self.binary_op_shift::<i8>(i8::wrapping_shr),
I::SRS16 => self.binary_op_shift::<i16>(i16::wrapping_shr), SRS16 => self.binary_op_shift::<i16>(i16::wrapping_shr),
I::SRS32 => self.binary_op_shift::<i32>(i32::wrapping_shr), SRS32 => self.binary_op_shift::<i32>(i32::wrapping_shr),
I::SRS64 => self.binary_op_shift::<i64>(i64::wrapping_shr), SRS64 => self.binary_op_shift::<i64>(i64::wrapping_shr),
I::CMPU => handler!(self, |OpsRRR(tg, a0, a1)| self.cmp( CMPU => handler!(self, |OpsRRR(tg, a0, a1)| self.cmp(
tg, tg,
a0, a0,
self.read_reg(a1).cast::<u64>() self.read_reg(a1).cast::<u64>()
)), )),
I::CMPS => handler!(self, |OpsRRR(tg, a0, a1)| self.cmp( CMPS => handler!(self, |OpsRRR(tg, a0, a1)| self.cmp(
tg, tg,
a0, a0,
self.read_reg(a1).cast::<i64>() self.read_reg(a1).cast::<i64>()
)), )),
I::DIRU8 => self.dir::<u8>(), DIRU8 => self.dir::<u8>(),
I::DIRU16 => self.dir::<u16>(), DIRU16 => self.dir::<u16>(),
I::DIRU32 => self.dir::<u32>(), DIRU32 => self.dir::<u32>(),
I::DIRU64 => self.dir::<u64>(), DIRU64 => self.dir::<u64>(),
I::DIRS8 => self.dir::<i8>(), DIRS8 => self.dir::<i8>(),
I::DIRS16 => self.dir::<i16>(), DIRS16 => self.dir::<i16>(),
I::DIRS32 => self.dir::<i32>(), DIRS32 => self.dir::<i32>(),
I::DIRS64 => self.dir::<i64>(), DIRS64 => self.dir::<i64>(),
I::NEG => handler!(self, |OpsRR(tg, a0)| { NEG => handler!(self, |OpsRR(tg, a0)| {
// Bit negation // Bit negation
self.write_reg(tg, self.read_reg(a0).cast::<u64>().wrapping_neg()) self.write_reg(tg, !self.read_reg(a0).cast::<u64>())
}), }),
I::NOT => handler!(self, |OpsRR(tg, a0)| { NOT => handler!(self, |OpsRR(tg, a0)| {
// Logical negation // Logical negation
self.write_reg(tg, u64::from(self.read_reg(a0).cast::<u64>() == 0)); self.write_reg(tg, u64::from(self.read_reg(a0).cast::<u64>() == 0));
}), }),
I::SXT8 => handler!(self, |OpsRR(tg, a0)| { SXT8 => handler!(self, |OpsRR(tg, a0)| {
self.write_reg(tg, self.read_reg(a0).cast::<i8>() as i64) self.write_reg(tg, self.read_reg(a0).cast::<i8>() as i64)
}), }),
I::SXT16 => handler!(self, |OpsRR(tg, a0)| { SXT16 => handler!(self, |OpsRR(tg, a0)| {
self.write_reg(tg, self.read_reg(a0).cast::<i16>() as i64) self.write_reg(tg, self.read_reg(a0).cast::<i16>() as i64)
}), }),
I::SXT32 => handler!(self, |OpsRR(tg, a0)| { SXT32 => handler!(self, |OpsRR(tg, a0)| {
self.write_reg(tg, self.read_reg(a0).cast::<i32>() as i64) self.write_reg(tg, self.read_reg(a0).cast::<i32>() as i64)
}), }),
I::ADDI8 => self.binary_op_imm(u8::wrapping_add), ADDI8 => self.binary_op_imm(u8::wrapping_add),
I::ADDI16 => self.binary_op_imm(u16::wrapping_add), ADDI16 => self.binary_op_imm(u16::wrapping_add),
I::ADDI32 => self.binary_op_imm(u32::wrapping_add), ADDI32 => self.binary_op_imm(u32::wrapping_add),
I::ADDI64 => self.binary_op_imm(u64::wrapping_add), ADDI64 => self.binary_op_imm(u64::wrapping_add),
I::MULI8 => self.binary_op_imm(u8::wrapping_mul), MULI8 => self.binary_op_imm(u8::wrapping_mul),
I::MULI16 => self.binary_op_imm(u16::wrapping_mul), MULI16 => self.binary_op_imm(u16::wrapping_mul),
I::MULI32 => self.binary_op_imm(u32::wrapping_mul), MULI32 => self.binary_op_imm(u32::wrapping_mul),
I::MULI64 => self.binary_op_imm(u64::wrapping_mul), MULI64 => self.binary_op_imm(u64::wrapping_mul),
I::ANDI => self.binary_op_imm::<u64>(ops::BitAnd::bitand), ANDI => self.binary_op_imm::<u64>(ops::BitAnd::bitand),
I::ORI => self.binary_op_imm::<u64>(ops::BitOr::bitor), ORI => self.binary_op_imm::<u64>(ops::BitOr::bitor),
I::XORI => self.binary_op_imm::<u64>(ops::BitXor::bitxor), XORI => self.binary_op_imm::<u64>(ops::BitXor::bitxor),
I::SLUI8 => self.binary_op_ims::<u8>(u8::wrapping_shl), SLUI8 => self.binary_op_ims::<u8>(u8::wrapping_shl),
I::SLUI16 => self.binary_op_ims::<u16>(u16::wrapping_shl), SLUI16 => self.binary_op_ims::<u16>(u16::wrapping_shl),
I::SLUI32 => self.binary_op_ims::<u32>(u32::wrapping_shl), SLUI32 => self.binary_op_ims::<u32>(u32::wrapping_shl),
I::SLUI64 => self.binary_op_ims::<u64>(u64::wrapping_shl), SLUI64 => self.binary_op_ims::<u64>(u64::wrapping_shl),
I::SRUI8 => self.binary_op_ims::<u8>(u8::wrapping_shr), SRUI8 => self.binary_op_ims::<u8>(u8::wrapping_shr),
I::SRUI16 => self.binary_op_ims::<u16>(u16::wrapping_shr), SRUI16 => self.binary_op_ims::<u16>(u16::wrapping_shr),
I::SRUI32 => self.binary_op_ims::<u32>(u32::wrapping_shr), SRUI32 => self.binary_op_ims::<u32>(u32::wrapping_shr),
I::SRUI64 => self.binary_op_ims::<u64>(u64::wrapping_shr), SRUI64 => self.binary_op_ims::<u64>(u64::wrapping_shr),
I::SRSI8 => self.binary_op_ims::<i8>(i8::wrapping_shr), SRSI8 => self.binary_op_ims::<i8>(i8::wrapping_shr),
I::SRSI16 => self.binary_op_ims::<i16>(i16::wrapping_shr), SRSI16 => self.binary_op_ims::<i16>(i16::wrapping_shr),
I::SRSI32 => self.binary_op_ims::<i32>(i32::wrapping_shr), SRSI32 => self.binary_op_ims::<i32>(i32::wrapping_shr),
I::SRSI64 => self.binary_op_ims::<i64>(i64::wrapping_shr), SRSI64 => self.binary_op_ims::<i64>(i64::wrapping_shr),
I::CMPUI => handler!(self, |OpsRRD(tg, a0, imm)| { self.cmp(tg, a0, imm) }), CMPUI => handler!(self, |OpsRRD(tg, a0, imm)| { self.cmp(tg, a0, imm) }),
I::CMPSI => { CMPSI => handler!(self, |OpsRRD(tg, a0, imm)| { self.cmp(tg, a0, imm as i64) }),
handler!(self, |OpsRRD(tg, a0, imm)| { self.cmp(tg, a0, imm as i64) }) CP => handler!(self, |OpsRR(tg, a0)| self.write_reg(tg, self.read_reg(a0))),
} SWA => handler!(self, |OpsRR(r0, r1)| {
I::CP => handler!(self, |OpsRR(tg, a0)| self.write_reg(tg, self.read_reg(a0))),
I::SWA => handler!(self, |OpsRR(r0, r1)| {
// Swap registers // Swap registers
match (r0, r1) { match (r0, r1) {
(0, 0) => (), (0, 0) => (),
@ -173,33 +167,35 @@ where
} }
} }
}), }),
I::LI8 => handler!(self, |OpsRB(tg, imm)| self.write_reg(tg, imm)), LI8 => handler!(self, |OpsRB(tg, imm)| self.write_reg(tg, imm)),
I::LI16 => handler!(self, |OpsRH(tg, imm)| self.write_reg(tg, imm)), LI16 => handler!(self, |OpsRH(tg, imm)| self.write_reg(tg, imm)),
I::LI32 => handler!(self, |OpsRW(tg, imm)| self.write_reg(tg, imm)), LI32 => handler!(self, |OpsRW(tg, imm)| self.write_reg(tg, imm)),
I::LI64 => handler!(self, |OpsRD(tg, imm)| self.write_reg(tg, imm)), LI64 => handler!(self, |OpsRD(tg, imm)| self.write_reg(tg, imm)),
I::LRA => handler!(self, |OpsRRO(tg, reg, off)| self.write_reg( LRA => handler!(self, |OpsRRO(tg, reg, off)| self.write_reg(
tg, tg,
self.pcrel(off).wrapping_add(self.read_reg(reg).cast::<i64>()).get(), self.pcrel(off, 3)
.wrapping_add(self.read_reg(reg).cast::<i64>())
.get(),
)), )),
// Load. If loading more than register size, continue on adjecent registers // Load. If loading more than register size, continue on adjecent registers
I::LD => handler!(self, |OpsRRAH(dst, base, off, count)| self LD => handler!(self, |OpsRRAH(dst, base, off, count)| self
.load(dst, base, off, count)?), .load(dst, base, off, count)?),
// Store. Same rules apply as to LD // Store. Same rules apply as to LD
I::ST => handler!(self, |OpsRRAH(dst, base, off, count)| self ST => handler!(self, |OpsRRAH(dst, base, off, count)| self
.store(dst, base, off, count)?), .store(dst, base, off, count)?),
I::LDR => handler!(self, |OpsRROH(dst, base, off, count)| self.load( LDR => handler!(self, |OpsRROH(dst, base, off, count)| self.load(
dst, dst,
base, base,
self.pcrel(off).get(), self.pcrel(off, 3).get(),
count count
)?), )?),
I::STR => handler!(self, |OpsRROH(dst, base, off, count)| self.store( STR => handler!(self, |OpsRROH(dst, base, off, count)| self.store(
dst, dst,
base, base,
self.pcrel(off).get(), self.pcrel(off, 3).get(),
count count
)?), )?),
I::BMC => { BMC => {
// Block memory copy // Block memory copy
match if let Some(copier) = &mut self.copier { match if let Some(copier) = &mut self.copier {
// There is some copier, poll. // There is some copier, poll.
@ -233,7 +229,7 @@ where
core::task::Poll::Pending => (), core::task::Poll::Pending => (),
} }
} }
I::BRC => handler!(self, |OpsRRB(src, dst, count)| { BRC => handler!(self, |OpsRRB(src, dst, count)| {
// Block register copy // Block register copy
if src.checked_add(count).is_none() || dst.checked_add(count).is_none() { if src.checked_add(count).is_none() || dst.checked_add(count).is_none() {
return Err(VmRunError::RegOutOfBounds); return Err(VmRunError::RegOutOfBounds);
@ -245,42 +241,44 @@ where
usize::from(count), usize::from(count),
); );
}), }),
I::JMP => { JMP => {
let OpsO(off) = self.decode(); let OpsO(off) = self.decode();
self.pc = self.pc.wrapping_add(off); self.pc = self.pc.wrapping_add(off).wrapping_add(1);
} }
I::JAL => { JAL => {
// Jump and link. Save PC after this instruction to // Jump and link. Save PC after this instruction to
// specified register and jump to reg + relative offset. // specified register and jump to reg + relative offset.
let OpsRRO(save, reg, offset) = self.decode(); let OpsRRO(save, reg, offset) = self.decode();
self.write_reg(save, self.pc.next::<OpsRRO>()); self.write_reg(save, self.pc.get());
self.pc = self.pcrel(offset).wrapping_add(self.read_reg(reg).cast::<i64>()); self.pc = self
.pcrel(offset, 3)
.wrapping_add(self.read_reg(reg).cast::<i64>());
} }
I::JALA => { JALA => {
// Jump and link. Save PC after this instruction to // Jump and link. Save PC after this instruction to
// specified register and jump to reg // specified register and jump to reg
let OpsRRA(save, reg, offset) = self.decode(); let OpsRRA(save, reg, offset) = self.decode();
self.write_reg(save, self.pc.next::<OpsRRA>()); self.write_reg(save, self.pc.get());
self.pc = self.pc =
Address::new(self.read_reg(reg).cast::<u64>().wrapping_add(offset)); Address::new(self.read_reg(reg).cast::<u64>().wrapping_add(offset));
} }
// Conditional jumps, jump only to immediates // Conditional jumps, jump only to immediates
I::JEQ => self.cond_jmp::<u64>(Ordering::Equal), JEQ => self.cond_jmp::<u64>(Ordering::Equal),
I::JNE => { JNE => {
let OpsRRP(a0, a1, ja) = self.decode(); let OpsRRP(a0, a1, ja) = self.decode();
if self.read_reg(a0).cast::<u64>() != self.read_reg(a1).cast::<u64>() { if self.read_reg(a0).cast::<u64>() != self.read_reg(a1).cast::<u64>() {
self.pc = self.pcrel(ja); self.pc = self.pcrel(ja, 3);
} else { } else {
self.bump_pc::<OpsRRP>(); self.bump_pc::<OpsRRP>();
} }
} }
I::JLTS => self.cond_jmp::<i64>(Ordering::Less), JLTS => self.cond_jmp::<u64>(Ordering::Less),
I::JGTS => self.cond_jmp::<i64>(Ordering::Greater), JGTS => self.cond_jmp::<u64>(Ordering::Greater),
I::JLTU => self.cond_jmp::<u64>(Ordering::Less), JLTU => self.cond_jmp::<i64>(Ordering::Less),
I::JGTU => self.cond_jmp::<u64>(Ordering::Greater), JGTU => self.cond_jmp::<i64>(Ordering::Greater),
I::ECA => { ECA => {
// So we don't get timer interrupt after ECALL // So we don't get timer interrupt after ECALL
if TIMER_QUOTIENT != 0 { if TIMER_QUOTIENT != 0 {
self.timer = self.timer.wrapping_add(1); self.timer = self.timer.wrapping_add(1);
@ -289,33 +287,33 @@ where
self.bump_pc::<OpsN>(); self.bump_pc::<OpsN>();
return Ok(VmRunOk::Ecall); return Ok(VmRunOk::Ecall);
} }
I::EBP => { EBP => {
self.bump_pc::<OpsN>(); self.bump_pc::<OpsN>();
return Ok(VmRunOk::Breakpoint); return Ok(VmRunOk::Breakpoint);
} }
I::FADD32 => self.binary_op::<f32>(ops::Add::add), FADD32 => self.binary_op::<f32>(ops::Add::add),
I::FADD64 => self.binary_op::<f64>(ops::Add::add), FADD64 => self.binary_op::<f64>(ops::Add::add),
I::FSUB32 => self.binary_op::<f32>(ops::Sub::sub), FSUB32 => self.binary_op::<f32>(ops::Sub::sub),
I::FSUB64 => self.binary_op::<f64>(ops::Sub::sub), FSUB64 => self.binary_op::<f64>(ops::Sub::sub),
I::FMUL32 => self.binary_op::<f32>(ops::Mul::mul), FMUL32 => self.binary_op::<f32>(ops::Mul::mul),
I::FMUL64 => self.binary_op::<f64>(ops::Mul::mul), FMUL64 => self.binary_op::<f64>(ops::Mul::mul),
I::FDIV32 => self.binary_op::<f32>(ops::Div::div), FDIV32 => self.binary_op::<f32>(ops::Div::div),
I::FDIV64 => self.binary_op::<f64>(ops::Div::div), FDIV64 => self.binary_op::<f64>(ops::Div::div),
I::FMA32 => self.fma::<f32>(), FMA32 => self.fma::<f32>(),
I::FMA64 => self.fma::<f64>(), FMA64 => self.fma::<f64>(),
I::FINV32 => handler!(self, |OpsRR(tg, reg)| self FINV32 => handler!(self, |OpsRR(tg, reg)| self
.write_reg(tg, 1. / self.read_reg(reg).cast::<f32>())), .write_reg(tg, 1. / self.read_reg(reg).cast::<f32>())),
I::FINV64 => handler!(self, |OpsRR(tg, reg)| self FINV64 => handler!(self, |OpsRR(tg, reg)| self
.write_reg(tg, 1. / self.read_reg(reg).cast::<f64>())), .write_reg(tg, 1. / self.read_reg(reg).cast::<f64>())),
I::FCMPLT32 => self.fcmp::<f32>(false, Ordering::Less), FCMPLT32 => self.fcmp::<f32>(Ordering::Less),
I::FCMPLT64 => self.fcmp::<f64>(false, Ordering::Less), FCMPLT64 => self.fcmp::<f64>(Ordering::Less),
I::FCMPGT32 => self.fcmp::<f32>(true, Ordering::Greater), FCMPGT32 => self.fcmp::<f32>(Ordering::Greater),
I::FCMPGT64 => self.fcmp::<f64>(true, Ordering::Greater), FCMPGT64 => self.fcmp::<f64>(Ordering::Greater),
I::ITF32 => handler!(self, |OpsRR(tg, reg)| self ITF32 => handler!(self, |OpsRR(tg, reg)| self
.write_reg(tg, self.read_reg(reg).cast::<i64>() as f32)), .write_reg(tg, self.read_reg(reg).cast::<i64>() as f32)),
I::ITF64 => handler!(self, |OpsRR(tg, reg)| self ITF64 => handler!(self, |OpsRR(tg, reg)| self
.write_reg(tg, self.read_reg(reg).cast::<i64>() as f64)), .write_reg(tg, self.read_reg(reg).cast::<i64>() as f64)),
I::FTI32 => handler!(self, |OpsRRB(tg, reg, mode)| self.write_reg( FTI32 => handler!(self, |OpsRRB(tg, reg, mode)| self.write_reg(
tg, tg,
crate::float::f32toint( crate::float::f32toint(
self.read_reg(reg).cast::<f32>(), self.read_reg(reg).cast::<f32>(),
@ -323,7 +321,7 @@ where
.map_err(|()| VmRunError::InvalidOperand)?, .map_err(|()| VmRunError::InvalidOperand)?,
), ),
)), )),
I::FTI64 => handler!(self, |OpsRRB(tg, reg, mode)| self.write_reg( FTI64 => handler!(self, |OpsRRB(tg, reg, mode)| self.write_reg(
tg, tg,
crate::float::f64toint( crate::float::f64toint(
self.read_reg(reg).cast::<f64>(), self.read_reg(reg).cast::<f64>(),
@ -331,9 +329,9 @@ where
.map_err(|()| VmRunError::InvalidOperand)?, .map_err(|()| VmRunError::InvalidOperand)?,
), ),
)), )),
I::FC32T64 => handler!(self, |OpsRR(tg, reg)| self FC32T64 => handler!(self, |OpsRR(tg, reg)| self
.write_reg(tg, self.read_reg(reg).cast::<f32>() as f64)), .write_reg(tg, self.read_reg(reg).cast::<f32>() as f64)),
I::FC64T32 => handler!(self, |OpsRRB(tg, reg, mode)| self.write_reg( FC64T32 => handler!(self, |OpsRRB(tg, reg, mode)| self.write_reg(
tg, tg,
crate::float::conv64to32( crate::float::conv64to32(
self.read_reg(reg).cast(), self.read_reg(reg).cast(),
@ -341,26 +339,27 @@ where
.map_err(|()| VmRunError::InvalidOperand)?, .map_err(|()| VmRunError::InvalidOperand)?,
), ),
)), )),
I::LRA16 => handler!(self, |OpsRRP(tg, reg, imm)| self.write_reg( LRA16 => handler!(self, |OpsRRP(tg, reg, imm)| self.write_reg(
tg, tg,
(self.pc + self.read_reg(reg).cast::<u64>() + imm + 3_u16).get(), (self.pc + self.read_reg(reg).cast::<u64>() + imm + 3_u16).get(),
)), )),
I::LDR16 => handler!(self, |OpsRRPH(dst, base, off, count)| self.load( LDR16 => handler!(self, |OpsRRPH(dst, base, off, count)| self.load(
dst, dst,
base, base,
self.pcrel(off).get(), self.pcrel(off, 3).get(),
count count
)?), )?),
I::STR16 => handler!(self, |OpsRRPH(dst, base, off, count)| self.store( STR16 => handler!(self, |OpsRRPH(dst, base, off, count)| self.store(
dst, dst,
base, base,
self.pcrel(off).get(), self.pcrel(off, 3).get(),
count count
)?), )?),
I::JMP16 => { JMP16 => {
let OpsP(off) = self.decode(); let OpsP(off) = self.decode();
self.pc = self.pcrel(off); self.pc = self.pcrel(off, 1);
} }
op => return Err(VmRunError::InvalidOpcode(op)),
} }
} }
@ -376,12 +375,15 @@ where
/// Bump instruction pointer /// Bump instruction pointer
#[inline(always)] #[inline(always)]
fn bump_pc<T: Copy>(&mut self) { fn bump_pc<T: Copy>(&mut self) {
self.pc = self.pc.wrapping_add(core::mem::size_of::<T>()).wrapping_add(1); self.pc = self
.pc
.wrapping_add(core::mem::size_of::<T>())
.wrapping_add(1);
} }
/// Decode instruction operands /// Decode instruction operands
#[inline(always)] #[inline(always)]
unsafe fn decode<T: Copy + 'static>(&mut self) -> T { unsafe fn decode<T: Copy>(&mut self) -> T {
unsafe { self.memory.prog_read::<T>(self.pc + 1_u64) } unsafe { self.memory.prog_read::<T>(self.pc + 1_u64) }
} }
@ -402,7 +404,10 @@ where
unsafe { unsafe {
self.memory.load( self.memory.load(
self.ldst_addr_uber(dst, base, offset, count, n)?, self.ldst_addr_uber(dst, base, offset, count, n)?,
self.registers.as_mut_ptr().add(usize::from(dst) + usize::from(n)).cast(), self.registers
.as_mut_ptr()
.add(usize::from(dst) + usize::from(n))
.cast(),
usize::from(count).saturating_sub(n.into()), usize::from(count).saturating_sub(n.into()),
) )
}?; }?;
@ -439,13 +444,16 @@ where
#[inline(always)] #[inline(always)]
unsafe fn binary_op<T: ValueVariant>(&mut self, op: impl Fn(T, T) -> T) { unsafe fn binary_op<T: ValueVariant>(&mut self, op: impl Fn(T, T) -> T) {
let OpsRRR(tg, a0, a1) = unsafe { self.decode() }; let OpsRRR(tg, a0, a1) = unsafe { self.decode() };
self.write_reg(tg, op(self.read_reg(a0).cast::<T>(), self.read_reg(a1).cast::<T>())); self.write_reg(
tg,
op(self.read_reg(a0).cast::<T>(), self.read_reg(a1).cast::<T>()),
);
self.bump_pc::<OpsRRR>(); self.bump_pc::<OpsRRR>();
} }
/// Perform binary operation over register and immediate /// Perform binary operation over register and immediate
#[inline(always)] #[inline(always)]
unsafe fn binary_op_imm<T: ValueVariant + 'static>(&mut self, op: impl Fn(T, T) -> T) { unsafe fn binary_op_imm<T: ValueVariant>(&mut self, op: impl Fn(T, T) -> T) {
#[derive(Clone, Copy)] #[derive(Clone, Copy)]
#[repr(packed)] #[repr(packed)]
struct OpsRRImm<I>(OpsRR, I); struct OpsRRImm<I>(OpsRR, I);
@ -459,7 +467,13 @@ where
#[inline(always)] #[inline(always)]
unsafe fn binary_op_shift<T: ValueVariant>(&mut self, op: impl Fn(T, u32) -> T) { unsafe fn binary_op_shift<T: ValueVariant>(&mut self, op: impl Fn(T, u32) -> T) {
let OpsRRR(tg, a0, a1) = unsafe { self.decode() }; let OpsRRR(tg, a0, a1) = unsafe { self.decode() };
self.write_reg(tg, op(self.read_reg(a0).cast::<T>(), self.read_reg(a1).cast::<u32>())); self.write_reg(
tg,
op(
self.read_reg(a0).cast::<T>(),
self.read_reg(a1).cast::<u32>(),
),
);
self.bump_pc::<OpsRRR>(); self.bump_pc::<OpsRRR>();
} }
@ -474,7 +488,6 @@ where
/// Fused division-remainder /// Fused division-remainder
#[inline(always)] #[inline(always)]
unsafe fn dir<T: ValueVariant + CheckedDivRem>(&mut self) { unsafe fn dir<T: ValueVariant + CheckedDivRem>(&mut self) {
unsafe {
handler!(self, |OpsRRRR(td, tr, a0, a1)| { handler!(self, |OpsRRRR(td, tr, a0, a1)| {
let a0 = self.read_reg(a0).cast::<T>(); let a0 = self.read_reg(a0).cast::<T>();
let a1 = self.read_reg(a1).cast::<T>(); let a1 = self.read_reg(a1).cast::<T>();
@ -492,7 +505,6 @@ where
} }
}); });
} }
}
/// Fused multiply-add /// Fused multiply-add
#[inline(always)] #[inline(always)]
@ -500,7 +512,6 @@ where
where where
T: ValueVariant + core::ops::Mul<Output = T> + core::ops::Add<Output = T>, T: ValueVariant + core::ops::Mul<Output = T> + core::ops::Add<Output = T>,
{ {
unsafe {
handler!(self, |OpsRRRR(tg, a0, a1, a2)| { handler!(self, |OpsRRRR(tg, a0, a1, a2)| {
let a0 = self.read_reg(a0).cast::<T>(); let a0 = self.read_reg(a0).cast::<T>();
let a1 = self.read_reg(a1).cast::<T>(); let a1 = self.read_reg(a1).cast::<T>();
@ -508,35 +519,34 @@ where
self.write_reg(tg, a0 * a1 + a2) self.write_reg(tg, a0 * a1 + a2)
}); });
} }
}
/// Float comparsion /// Float comparsion
#[inline(always)] #[inline(always)]
unsafe fn fcmp<T: PartialOrd + ValueVariant>(&mut self, swapped: bool, expected: Ordering) { unsafe fn fcmp<T: PartialOrd + ValueVariant>(&mut self, nan: Ordering) {
unsafe {
handler!(self, |OpsRRR(tg, a0, a1)| { handler!(self, |OpsRRR(tg, a0, a1)| {
let mut a0 = self.read_reg(a0).cast::<T>(); let a0 = self.read_reg(a0).cast::<T>();
let mut a1 = self.read_reg(a1).cast::<T>(); let a1 = self.read_reg(a1).cast::<T>();
if swapped { self.write_reg(tg, (a0.partial_cmp(&a1).unwrap_or(nan) as i8 + 1) as u8)
core::mem::swap(&mut a0, &mut a1);
}
self.write_reg(tg, (a0.partial_cmp(&a1) == Some(expected)) as u8)
}); });
} }
}
/// Calculate pc-relative address /// Calculate pc-relative address
#[inline(always)] #[inline(always)]
fn pcrel(&self, offset: impl AddressOp) -> Address { fn pcrel(&self, offset: impl AddressOp, pos: u8) -> Address {
self.pc.wrapping_add(offset) self.pc.wrapping_add(pos).wrapping_add(offset)
} }
/// Jump at `PC + #3` if ordering on `#0 <=> #1` is equal to expected /// Jump at `PC + #3` if ordering on `#0 <=> #1` is equal to expected
#[inline(always)] #[inline(always)]
unsafe fn cond_jmp<T: ValueVariant + Ord>(&mut self, expected: Ordering) { unsafe fn cond_jmp<T: ValueVariant + Ord>(&mut self, expected: Ordering) {
let OpsRRP(a0, a1, ja) = unsafe { self.decode() }; let OpsRRP(a0, a1, ja) = unsafe { self.decode() };
if self.read_reg(a0).cast::<T>().cmp(&self.read_reg(a1).cast::<T>()) == expected { if self
self.pc = self.pcrel(ja); .read_reg(a0)
.cast::<T>()
.cmp(&self.read_reg(a1).cast::<T>())
== expected
{
self.pc = self.pcrel(ja, 3);
} else { } else {
self.bump_pc::<OpsRRP>(); self.bump_pc::<OpsRRP>();
} }

2
xrt/Cargo.toml → hbxrt/Cargo.toml
View file

@ -5,5 +5,5 @@ edition = "2021"
default-run = "hbxrt" default-run = "hbxrt"
[dependencies] [dependencies]
hbvm.workspace = true hbvm.path = "../hbvm"
memmap2 = "0.9" memmap2 = "0.9"

11
xrt/src/main.rs → hbxrt/src/main.rs
View file

@ -52,17 +52,16 @@ fn main() -> Result<(), Box<dyn std::error::Error>> {
eprintln!("[I] Image loaded at {:p}", mmap.as_ptr()); eprintln!("[I] Image loaded at {:p}", mmap.as_ptr());
let mut vm = unsafe { let mut vm = unsafe { Vm::<_, 0>::new(mem::HostMemory, Address::new(mmap.as_ptr() as u64)) };
Vm::<_, 0>::new(hbvm::mem::HostMemory, Address::new(mmap.as_ptr().add(stack.len()) as u64))
};
vm.write_reg(254, stack.as_mut_ptr() as u64); vm.write_reg(254, stack.as_mut_ptr() as u64);
// Execute program // Execute program
let stat = loop { let stat = loop {
match vm.run() { match vm.run() {
Ok(VmRunOk::Breakpoint) => { Ok(VmRunOk::Breakpoint) => eprintln!(
eprintln!("[I] Hit breakpoint\nIP: {}\n== Registers ==\n{:?}", vm.pc, vm.registers) "[I] Hit breakpoint\nIP: {}\n== Registers ==\n{:?}",
} vm.pc, vm.registers
),
Ok(VmRunOk::Timer) => (), Ok(VmRunOk::Timer) => (),
Ok(VmRunOk::Ecall) if dsls => unsafe { Ok(VmRunOk::Ecall) if dsls => unsafe {
std::arch::asm!( std::arch::asm!(

47
hbxrt/src/mem.rs Normal file
View file

@ -0,0 +1,47 @@
use std::alloc::Layout;
use hbvm::mem::{Address, LoadError, Memory, StoreError};
pub struct HostMemory;
impl Memory for HostMemory {
#[inline]
unsafe fn load(
&mut self,
addr: Address,
target: *mut u8,
count: usize,
) -> Result<(), LoadError> {
unsafe { core::ptr::copy(addr.get() as *const u8, target, count) }
Ok(())
}
#[inline]
unsafe fn store(
&mut self,
addr: Address,
source: *const u8,
count: usize,
) -> Result<(), StoreError> {
unsafe { core::ptr::copy(source, addr.get() as *mut u8, count) }
Ok(())
}
#[inline]
unsafe fn prog_read<T: Copy>(&mut self, addr: Address) -> T {
unsafe { core::ptr::read(addr.get() as *const T) }
}
}
const STACK_SIZE: usize = 2; // MiB
type Stack = [u8; 1024 * 1024 * STACK_SIZE];
/// Allocate stack of size [`STACK_SIZE`] MiB
pub unsafe fn alloc_stack() -> Box<Stack> {
let layout = Layout::new::<Stack>();
let ptr = unsafe { std::alloc::alloc(layout) };
if ptr.is_null() {
std::alloc::handle_alloc_error(layout);
}
unsafe { Box::from_raw(ptr.cast()) }
}

23
lang/Cargo.toml
View file

@ -1,23 +0,0 @@
[package]
name = "hblang"
version = "0.1.0"
edition = "2021"
[[bin]]
name = "hbc"
path = "src/main.rs"
[[bin]]
name = "fuzz"
path = "src/fuzz_main.rs"
[dependencies]
hbbytecode = { workspace = true, features = ["disasm"] }
hbvm = { workspace = true, features = ["nightly"] }
hashbrown = { version = "0.15.0", default-features = false, features = ["raw-entry"] }
log = "0.4.22"
[features]
default = ["std"]
std = []
no_log = ["log/max_level_off"]

1871
lang/README.md
View file

File diff suppressed because one or more lines are too long

4
lang/command-help.txt
View file

@ -1,4 +0,0 @@
--fmt - format all imported source files
--fmt-stdout - dont write the formatted file but print it
--dump-asm - output assembly instead of raw code, (the assembly is more for debugging the compiler)
--threads <1...> - number of extra threads compiler can use [default: 0]

635
lang/src/fmt.rs
View file

@ -1,635 +0,0 @@
use {
crate::{
lexer::{self, Lexer, TokenKind},
parser::{self, CommentOr, CtorField, EnumField, Expr, Poser, Radix, StructField},
},
core::{
fmt::{self},
mem,
},
};
pub fn display_radix(radix: Radix, mut value: u64, buf: &mut [u8; 64]) -> &str {
fn conv_radix(d: u8) -> u8 {
match d {
0..=9 => d + b'0',
_ => d - 10 + b'A',
}
}
for (i, b) in buf.iter_mut().enumerate().rev() {
let d = (value % radix as u64) as u8;
value /= radix as u64;
*b = conv_radix(d);
if value == 0 {
return unsafe { core::str::from_utf8_unchecked(&buf[i..]) };
}
}
unreachable!()
}
#[repr(u8)]
enum TokenGroup {
Blank,
Comment,
Keyword,
Identifier,
Directive,
Number,
String,
Op,
Assign,
Paren,
Bracket,
Colon,
Comma,
Dot,
Ctor,
}
fn token_group(kind: TokenKind) -> TokenGroup {
use {crate::lexer::TokenKind::*, TokenGroup as TG};
match kind {
BSlash | Pound | Eof | Ct => TG::Blank,
Comment => TG::Comment,
Directive => TG::Directive,
Colon => TG::Colon,
Semi | Comma => TG::Comma,
Dot => TG::Dot,
Ctor | Tupl | TArrow => TG::Ctor,
LParen | RParen => TG::Paren,
LBrace | RBrace | LBrack | RBrack => TG::Bracket,
Number | Float => TG::Number,
Under | CtIdent | Ident => TG::Identifier,
Tick | Tilde | Que | Not | Mod | Band | Bor | Xor | Mul | Add | Sub | Div | Shl | Shr
| Or | And | Lt | Gt | Eq | Le | Ge | Ne => TG::Op,
Decl | Assign | BorAss | XorAss | BandAss | AddAss | SubAss | MulAss | DivAss | ModAss
| ShrAss | ShlAss => TG::Assign,
DQuote | Quote => TG::String,
Slf | Defer | Return | If | Else | Loop | Break | Continue | Fn | Idk | Die | Struct
| Packed | True | False | Null | Match | Enum => TG::Keyword,
}
}
pub fn get_token_kinds(mut source: &mut [u8]) -> usize {
let len = source.len();
loop {
let src = unsafe { core::str::from_utf8_unchecked(source) };
let mut token = lexer::Lexer::new(src).eat();
match token.kind {
TokenKind::Eof => break,
// ???
TokenKind::CtIdent | TokenKind::Directive => token.start -= 1,
_ => {}
}
let start = token.start as usize;
let end = token.end as usize;
source[..start].fill(0);
source[start..end].fill(token_group(token.kind) as u8);
source = &mut source[end..];
}
len
}
pub fn minify(source: &mut str) -> usize {
fn needs_space(c: u8) -> bool {
matches!(c, b'a'..=b'z' | b'A'..=b'Z' | b'0'..=b'9' | 127..)
}
let mut writer = source.as_mut_ptr();
let mut reader = &source[..];
let mut prev_needs_whitecpace = false;
let mut prev_needs_newline = false;
loop {
let mut token = lexer::Lexer::new(reader).eat();
match token.kind {
TokenKind::Eof => break,
TokenKind::CtIdent | TokenKind::Directive => token.start -= 1,
_ => {}
}
let cpy_len = token.range().len();
let mut prefix = 0;
if prev_needs_whitecpace && needs_space(reader.as_bytes()[token.start as usize]) {
prefix = b' ';
debug_assert!(token.start != 0, "{reader}");
}
prev_needs_whitecpace = needs_space(reader.as_bytes()[token.end as usize - 1]);
let inbetween_new_lines =
reader[..token.start as usize].bytes().filter(|&b| b == b'\n').count()
+ token.kind.precedence().is_some() as usize;
let extra_prefix_new_lines = if inbetween_new_lines > 1 {
1 + token.kind.precedence().is_none() as usize
} else {
prev_needs_newline as usize
};
if token.kind == TokenKind::Comment && reader.as_bytes()[token.end as usize - 1] != b'/' {
prev_needs_newline = true;
prev_needs_whitecpace = false;
} else {
prev_needs_newline = false;
}
let sstr = reader[token.start as usize..].as_ptr();
reader = &reader[token.end as usize..];
unsafe {
if extra_prefix_new_lines != 0 {
for _ in 0..extra_prefix_new_lines {
writer.write(b'\n');
writer = writer.add(1);
}
} else if prefix != 0 {
writer.write(prefix);
writer = writer.add(1);
}
writer.copy_from(sstr, cpy_len);
writer = writer.add(cpy_len);
}
}
unsafe { writer.sub_ptr(source.as_mut_ptr()) }
}
pub struct Formatter<'a> {
source: &'a str,
depth: usize,
}
// we exclusively use `write_str` to reduce bloat
impl<'a> Formatter<'a> {
pub fn new(source: &'a str) -> Self {
Self { source, depth: 0 }
}
fn fmt_list<T: Poser, F: core::fmt::Write>(
&mut self,
f: &mut F,
trailing: bool,
end: &str,
sep: &str,
list: &[T],
fmt: impl Fn(&mut Self, &T, &mut F) -> fmt::Result,
) -> fmt::Result {
self.fmt_list_low(f, trailing, end, sep, list, |s, v, f| {
fmt(s, v, f)?;
Ok(true)
})
}
fn fmt_list_low<T: Poser, F: core::fmt::Write>(
&mut self,
f: &mut F,
trailing: bool,
end: &str,
sep: &str,
list: &[T],
fmt: impl Fn(&mut Self, &T, &mut F) -> Result<bool, fmt::Error>,
) -> fmt::Result {
if !trailing {
let mut first = true;
for expr in list {
if !core::mem::take(&mut first) {
f.write_str(sep)?;
f.write_str(" ")?;
}
first = !fmt(self, expr, f)?;
}
return f.write_str(end);
}
if !end.is_empty() {
writeln!(f)?;
}
self.depth += !end.is_empty() as usize;
let mut already_indented = end.is_empty();
let res = (|| {
for (i, stmt) in list.iter().enumerate() {
if !mem::take(&mut already_indented) {
for _ in 0..self.depth {
f.write_str("\t")?;
}
}
let add_sep = fmt(self, stmt, f)?;
if add_sep {
f.write_str(sep)?;
}
if let Some(expr) = list.get(i + 1)
&& let Some(rest) = self.source.get(expr.posi() as usize..)
{
if sep.is_empty() && insert_needed_semicolon(rest) {
f.write_str(";")?;
}
if preserve_newlines(&self.source[..expr.posi() as usize]) > 1 {
f.write_str("\n")?;
}
}
if add_sep {
f.write_str("\n")?;
}
}
Ok(())
})();
self.depth -= !end.is_empty() as usize;
if !end.is_empty() {
for _ in 0..self.depth {
f.write_str("\t")?;
}
f.write_str(end)?;
}
res
}
fn fmt_paren<F: core::fmt::Write>(
&mut self,
expr: &Expr,
f: &mut F,
cond: impl FnOnce(&Expr) -> bool,
) -> fmt::Result {
if cond(expr) {
f.write_str("(")?;
self.fmt(expr, f)?;
f.write_str(")")
} else {
self.fmt(expr, f)
}
}
pub fn fmt<F: core::fmt::Write>(&mut self, expr: &Expr, f: &mut F) -> fmt::Result {
macro_rules! impl_parenter {
($($name:ident => $pat:pat,)*) => {
$(
let $name = |e: &Expr| matches!(e, $pat);
)*
};
}
impl_parenter! {
unary => Expr::BinOp { .. },
postfix => Expr::UnOp { .. } | Expr::BinOp { .. },
consecutive => Expr::UnOp { .. },
}
match *expr {
Expr::Ct { value, .. } => {
f.write_str("$: ")?;
self.fmt(value, f)
}
Expr::Defer { value, .. } => {
f.write_str("defer ")?;
self.fmt(value, f)
}
Expr::Slf { .. } => f.write_str("Self"),
Expr::String { literal, .. } => f.write_str(literal),
Expr::Comment { literal, .. } => f.write_str(literal),
Expr::Mod { path, .. } => write!(f, "@use(\"{path}\")"),
Expr::Embed { path, .. } => write!(f, "@embed(\"{path}\")"),
Expr::Field { target, name: field, .. } => {
self.fmt_paren(target, f, postfix)?;
f.write_str(".")?;
f.write_str(field)
}
Expr::Directive { name, args, .. } => {
f.write_str("@")?;
f.write_str(name)?;
f.write_str("(")?;
self.fmt_list(f, false, ")", ",", args, Self::fmt)
}
Expr::Struct { fields, trailing_comma, packed, .. } => {
if packed {
f.write_str("packed ")?;
}
f.write_str("struct {")?;
self.fmt_list_low(f, trailing_comma, "}", ",", fields, |s, field, f| {
match field {
CommentOr::Or(Ok(StructField { name, ty, .. })) => {
f.write_str(name)?;
f.write_str(": ")?;
s.fmt(ty, f)?
}
CommentOr::Or(Err(scope)) => {
s.fmt_list(f, true, "", "", scope, Self::fmt)?;
return Ok(false);
}
CommentOr::Comment { literal, .. } => {
f.write_str(literal)?;
f.write_str("\n")?;
}
}
Ok(field.or().is_some())
})
}
Expr::Enum { variants, trailing_comma, .. } => {
f.write_str("enum {")?;
self.fmt_list_low(f, trailing_comma, "}", ",", variants, |_, var, f| {
match var {
CommentOr::Or(EnumField { name, .. }) => {
f.write_str(name)?;
}
CommentOr::Comment { literal, .. } => {
f.write_str(literal)?;
f.write_str("\n")?;
}
}
Ok(var.or().is_some())
})
}
Expr::Ctor { ty, fields, trailing_comma, .. } => {
if let Some(ty) = ty {
self.fmt_paren(ty, f, unary)?;
}
f.write_str(".{")?;
self.fmt_list(
f,
trailing_comma,
"}",
",",
fields,
|s: &mut Self, CtorField { name, value, .. }: &_, f| {
f.write_str(name)?;
if !matches!(value, &Expr::Ident { id, .. } if *name == &self.source[id.range()]) {
f.write_str(": ")?;
s.fmt(value, f)?;
}
Ok(())
},
)
}
Expr::Tupl {
pos,
ty: Some(&Expr::Slice { pos: spos, size: Some(&Expr::Number { value, .. }), item }),
fields,
trailing_comma,
} if value as usize == fields.len() => self.fmt(
&Expr::Tupl {
pos,
ty: Some(&Expr::Slice { pos: spos, size: None, item }),
fields,
trailing_comma,
},
f,
),
Expr::Tupl { ty, fields, trailing_comma, .. } => {
if let Some(ty) = ty {
self.fmt_paren(ty, f, unary)?;
}
f.write_str(".(")?;
self.fmt_list(f, trailing_comma, ")", ",", fields, Self::fmt)
}
Expr::Slice { item, size, .. } => {
f.write_str("[")?;
self.fmt(item, f)?;
if let Some(size) = size {
f.write_str("; ")?;
self.fmt(size, f)?;
}
f.write_str("]")
}
Expr::Index { base, index } => {
self.fmt(base, f)?;
f.write_str("[")?;
self.fmt(index, f)?;
f.write_str("]")
}
Expr::UnOp { op, val, .. } => {
f.write_str(op.name())?;
self.fmt_paren(val, f, unary)
}
Expr::Break { .. } => f.write_str("break"),
Expr::Continue { .. } => f.write_str("continue"),
Expr::If { cond, then, else_, .. } => {
f.write_str("if ")?;
self.fmt(cond, f)?;
f.write_str(" ")?;
self.fmt_paren(then, f, consecutive)?;
if let Some(e) = else_ {
f.write_str(" else ")?;
self.fmt(e, f)?;
}
Ok(())
}
Expr::Match { value, branches, .. } => {
f.write_str("match ")?;
self.fmt(value, f)?;
f.write_str(" {")?;
self.fmt_list(f, true, "}", ",", branches, |s, br, f| {
s.fmt(&br.pat, f)?;
f.write_str(" => ")?;
s.fmt(&br.body, f)
})
}
Expr::Loop { body, .. } => {
f.write_str("loop ")?;
self.fmt(body, f)
}
Expr::Closure { ret, body, args, .. } => {
f.write_str("fn(")?;
self.fmt_list(f, false, "", ",", args, |s, arg, f| {
if arg.is_ct {
f.write_str("$")?;
}
f.write_str(arg.name)?;
f.write_str(": ")?;
s.fmt(&arg.ty, f)
})?;
f.write_str("): ")?;
self.fmt(ret, f)?;
f.write_str(" ")?;
self.fmt_paren(body, f, consecutive)?;
Ok(())
}
Expr::Call { func, args, trailing_comma } => {
self.fmt_paren(func, f, postfix)?;
f.write_str("(")?;
self.fmt_list(f, trailing_comma, ")", ",", args, Self::fmt)
}
Expr::Return { val: Some(val), .. } => {
f.write_str("return ")?;
self.fmt(val, f)
}
Expr::Return { val: None, .. } => f.write_str("return"),
Expr::Wildcard { .. } => f.write_str("_"),
Expr::Ident { pos, is_ct, .. } => {
if is_ct {
f.write_str("$")?;
}
f.write_str(&self.source[Lexer::restore(self.source, pos).eat().range()])
}
Expr::Block { stmts, .. } => {
f.write_str("{")?;
self.fmt_list(f, true, "}", "", stmts, Self::fmt)
}
Expr::Number { value, radix, .. } => {
f.write_str(match radix {
Radix::Decimal => "",
Radix::Hex => "0x",
Radix::Octal => "0o",
Radix::Binary => "0b",
})?;
let mut buf = [0u8; 64];
f.write_str(display_radix(radix, value as u64, &mut buf))
}
Expr::Float { pos, .. } => {
f.write_str(&self.source[Lexer::restore(self.source, pos).eat().range()])
}
Expr::Bool { value, .. } => f.write_str(if value { "true" } else { "false" }),
Expr::Idk { .. } => f.write_str("idk"),
Expr::Die { .. } => f.write_str("die"),
Expr::Null { .. } => f.write_str("null"),
Expr::BinOp {
left,
op: TokenKind::Assign,
right: &Expr::BinOp { left: lleft, op, right, .. },
..
} if left.pos() == lleft.pos() => {
self.fmt(left, f)?;
f.write_str(" ")?;
f.write_str(op.name())?;
f.write_str("= ")?;
self.fmt(right, f)
}
Expr::BinOp { right, op, left, .. } => {
let prec_miss_left = |e: &Expr| {
matches!(
e, Expr::BinOp { op: lop, .. } if op.precedence() > lop.precedence()
)
};
let prec_miss_right = |e: &Expr| {
matches!(
e, Expr::BinOp { op: lop, .. }
if (op.precedence() == lop.precedence() && !op.is_comutative())
|| op.precedence() > lop.precedence()
)
};
self.fmt_paren(left, f, prec_miss_left)?;
if let Some(mut prev) = self.source.get(..right.pos() as usize) {
prev = prev.trim_end();
let estimate_bound =
prev.rfind(|c: char| c.is_ascii_whitespace()).map_or(prev.len(), |i| i + 1);
let exact_bound = lexer::Lexer::new(&prev[estimate_bound..]).last().start;
prev = &prev[..exact_bound as usize + estimate_bound];
if preserve_newlines(prev) > 0 {
f.write_str("\n")?;
for _ in 0..self.depth + 1 {
f.write_str("\t")?;
}
f.write_str(op.name())?;
f.write_str(" ")?;
} else {
f.write_str(" ")?;
f.write_str(op.name())?;
f.write_str(" ")?;
}
} else {
f.write_str(" ")?;
f.write_str(op.name())?;
f.write_str(" ")?;
}
self.fmt_paren(right, f, prec_miss_right)
}
}
}
}
pub fn preserve_newlines(source: &str) -> usize {
source[source.trim_end().len()..].bytes().filter(|&c| c == b'\n').count()
}
pub fn insert_needed_semicolon(source: &str) -> bool {
let kind = lexer::Lexer::new(source).eat().kind;
kind.precedence().is_some() || matches!(kind, TokenKind::Ctor | TokenKind::Tupl)
}
impl core::fmt::Display for parser::Ast {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
fmt_file(self.exprs(), &self.file, f)
}
}
pub fn fmt_file(exprs: &[Expr], file: &str, f: &mut impl fmt::Write) -> fmt::Result {
for (i, expr) in exprs.iter().enumerate() {
Formatter::new(file).fmt(expr, f)?;
if let Some(expr) = exprs.get(i + 1)
&& let Some(rest) = file.get(expr.pos() as usize..)
{
if insert_needed_semicolon(rest) {
write!(f, ";")?;
}
if preserve_newlines(&file[..expr.pos() as usize]) > 1 {
writeln!(f)?;
}
}
if i + 1 != exprs.len() {
writeln!(f)?;
}
}
Ok(())
}
#[cfg(test)]
pub mod test {
use {
crate::parser::{self, Ctx},
alloc::borrow::ToOwned,
std::{fmt::Write, string::String},
};
pub fn format(ident: &str, input: &str) {
let mut minned = input.to_owned();
let len = crate::fmt::minify(&mut minned);
minned.truncate(len);
let mut ctx = Ctx::default();
let ast = parser::Ast::new(ident, minned, &mut ctx, &mut parser::no_loader);
log::info!("{}", ctx.errors.borrow());
let mut output = String::new();
write!(output, "{ast}").unwrap();
let input_path = format!("formatter_{ident}.expected");
let output_path = format!("formatter_{ident}.actual");
std::fs::write(&input_path, input).unwrap();
std::fs::write(&output_path, output).unwrap();
let success = std::process::Command::new("diff")
.arg("-u")
.arg("--color")
.arg(&input_path)
.arg(&output_path)
.status()
.unwrap()
.success();
std::fs::remove_file(&input_path).unwrap();
std::fs::remove_file(&output_path).unwrap();
assert!(success, "test failed");
}
macro_rules! test {
($($name:ident => $input:expr;)*) => {$(
#[test]
fn $name() {
format(stringify!($name), $input);
}
)*};
}
test! {
comments => "// comment\n// comment\n\n// comment\n\n\
/* comment */\n/* comment */\n\n/* comment */";
some_ordinary_code => "loft := fn(): int return loft(1, 2, 3)";
some_arg_per_line_code => "loft := fn(): int return loft(\
\n\t1,\n\t2,\n\t3,\n)";
some_ordinary_struct => "loft := fn(): int return loft.{a: 1, b: 2}";
some_ordinary_fild_per_lin_struct => "loft := fn(): int return loft.{\
\n\ta: 1,\n\tb: 2,\n}";
code_block => "loft := fn(): int {\n\tloft()\n\treturn 1\n}";
}
}

384
lang/src/fs.rs
View file

@ -1,384 +0,0 @@
use {
crate::{
parser::{Ast, Ctx, FileKind},
son::{self, hbvm::HbvmBackend},
ty, FnvBuildHasher,
},
alloc::{string::String, vec::Vec},
core::{fmt::Write, num::NonZeroUsize, ops::Deref},
hashbrown::hash_map,
std::{
collections::VecDeque,
eprintln,
ffi::OsStr,
io::{self, Write as _},
path::{Path, PathBuf},
string::ToString,
sync::Mutex,
},
};
type HashMap<K, V> = hashbrown::HashMap<K, V, FnvBuildHasher>;
pub struct Logger;
impl log::Log for Logger {
fn enabled(&self, _: &log::Metadata) -> bool {
true
}
fn log(&self, record: &log::Record) {
if self.enabled(record.metadata()) {
eprintln!("{}", record.args())
}
}
fn flush(&self) {}
}
#[derive(Default)]
pub struct Options {
pub fmt: bool,
pub fmt_stdout: bool,
pub dump_asm: bool,
pub in_house_regalloc: bool,
pub extra_threads: usize,
}
impl Options {
pub fn from_args(args: &[&str], out: &mut Vec<u8>) -> std::io::Result<Self> {
if args.contains(&"--help") || args.contains(&"-h") {
writeln!(out, "Usage: hbc [OPTIONS...] <FILE>")?;
writeln!(out, include_str!("../command-help.txt"))?;
return Err(std::io::ErrorKind::Other.into());
}
Ok(Options {
fmt: args.contains(&"--fmt"),
fmt_stdout: args.contains(&"--fmt-stdout"),
dump_asm: args.contains(&"--dump-asm"),
in_house_regalloc: args.contains(&"--in-house-regalloc"),
extra_threads: args
.iter()
.position(|&a| a == "--threads")
.map(|i| {
args[i + 1].parse::<NonZeroUsize>().map_err(|e| {
writeln!(out, "--threads expects non zero integer: {e}")
.err()
.unwrap_or(std::io::ErrorKind::Other.into())
})
})
.transpose()?
.map_or(1, NonZeroUsize::get)
- 1,
})
}
}
pub fn run_compiler(
root_file: &str,
options: Options,
out: &mut Vec<u8>,
warnings: &mut String,
) -> std::io::Result<()> {
let parsed = parse_from_fs(options.extra_threads, root_file)?;
if (options.fmt || options.fmt_stdout) && !parsed.errors.is_empty() {
*out = parsed.errors.into_bytes();
return Err(std::io::Error::other("fmt fialed (errors are in out)"));
}
if options.fmt {
let mut output = String::new();
for ast in parsed.ast {
write!(output, "{ast}").unwrap();
if ast.file.deref().trim() != output.as_str().trim() {
std::fs::write(&*ast.path, &output)?;
}
output.clear();
}
} else if options.fmt_stdout {
write!(out, "{}", &parsed.ast[0])?;
} else {
let mut backend = HbvmBackend::default();
backend.use_in_house_regalloc = options.in_house_regalloc;
let mut ctx = crate::son::CodegenCtx::default();
*ctx.parser.errors.get_mut() = parsed.errors;
let mut codegen = son::Codegen::new(&mut backend, &parsed.ast, &mut ctx);
codegen.push_embeds(parsed.embeds);
codegen.generate(ty::Module::MAIN);
*warnings = core::mem::take(&mut *codegen.warnings.borrow_mut());
if !codegen.errors.borrow().is_empty() {
drop(codegen);
*out = ctx.parser.errors.into_inner().into_bytes();
return Err(std::io::Error::other("compilation faoled (errors are in out)"));
}
codegen.assemble(out);
if options.dump_asm {
let mut disasm = String::new();
codegen.disasm(&mut disasm, out).map_err(|e| io::Error::other(e.to_string()))?;
*out = disasm.into_bytes();
}
}
Ok(())
}
struct TaskQueue<T> {
inner: Mutex<TaskQueueInner<T>>,
}
impl<T> TaskQueue<T> {
fn new(max_waiters: usize) -> Self {
Self { inner: Mutex::new(TaskQueueInner::new(max_waiters)) }
}
pub fn push(&self, message: T) {
self.extend([message]);
}
pub fn extend(&self, messages: impl IntoIterator<Item = T>) {
self.inner.lock().unwrap().push(messages);
}
pub fn pop(&self) -> Option<T> {
TaskQueueInner::pop(&self.inner)
}
}
enum TaskSlot<T> {
Waiting,
Delivered(T),
Closed,
}
struct TaskQueueInner<T> {
max_waiters: usize,
messages: VecDeque<T>,
parked: VecDeque<(*mut TaskSlot<T>, std::thread::Thread)>,
}
unsafe impl<T: Send> Send for TaskQueueInner<T> {}
unsafe impl<T: Send + Sync> Sync for TaskQueueInner<T> {}
impl<T> TaskQueueInner<T> {
fn new(max_waiters: usize) -> Self {
Self { max_waiters, messages: Default::default(), parked: Default::default() }
}
fn push(&mut self, messages: impl IntoIterator<Item = T>) {
for msg in messages {
if let Some((dest, thread)) = self.parked.pop_front() {
unsafe { *dest = TaskSlot::Delivered(msg) };
thread.unpark();
} else {
self.messages.push_back(msg);
}
}
}
fn pop(s: &Mutex<Self>) -> Option<T> {
let mut res = TaskSlot::Waiting;
{
let mut s = s.lock().unwrap();
if let Some(msg) = s.messages.pop_front() {
return Some(msg);
}
if s.max_waiters == s.parked.len() + 1 {
for (dest, thread) in s.parked.drain(..) {
unsafe { *dest = TaskSlot::Closed };
thread.unpark();
}
return None;
}
s.parked.push_back((&mut res, std::thread::current()));
}
loop {
std::thread::park();
let _s = s.lock().unwrap();
match core::mem::replace(&mut res, TaskSlot::Waiting) {
TaskSlot::Delivered(msg) => return Some(msg),
TaskSlot::Closed => return None,
TaskSlot::Waiting => {}
}
}
}
}
pub struct Loaded {
ast: Vec<Ast>,
embeds: Vec<Vec<u8>>,
errors: String,
}
pub fn parse_from_fs(extra_threads: usize, root: &str) -> io::Result<Loaded> {
fn resolve(path: &str, from: &str, tmp: &mut PathBuf) -> Result<PathBuf, CantLoadFile> {
tmp.clear();
match Path::new(from).parent() {
Some(parent) => tmp.extend([parent, Path::new(path)]),
None => tmp.push(path),
};
tmp.canonicalize().map_err(|source| CantLoadFile { path: std::mem::take(tmp), source })
}
#[derive(Debug)]
struct CantLoadFile {
path: PathBuf,
source: io::Error,
}
impl core::fmt::Display for CantLoadFile {
fn fmt(&self, f: &mut core::fmt::Formatter) -> core::fmt::Result {
write!(f, "can't load file: {}", display_rel_path(&self.path),)
}
}
impl core::error::Error for CantLoadFile {
fn source(&self) -> Option<&(dyn core::error::Error + 'static)> {
Some(&self.source)
}
}
impl From<CantLoadFile> for io::Error {
fn from(e: CantLoadFile) -> Self {
io::Error::new(io::ErrorKind::InvalidData, e)
}
}
type Task = (usize, PathBuf);
let seen_modules = Mutex::new(HashMap::<PathBuf, usize>::default());
let seen_embeds = Mutex::new(HashMap::<PathBuf, usize>::default());
let tasks = TaskQueue::<Task>::new(extra_threads + 1);
let ast = Mutex::new(Vec::<io::Result<Ast>>::new());
let embeds = Mutex::new(Vec::<Vec<u8>>::new());
let loader = |path: &str, from: &str, kind: FileKind, tmp: &mut _| {
let mut physiscal_path = resolve(path, from, tmp)?;
match kind {
FileKind::Module => {
let id = {
let mut seen = seen_modules.lock().unwrap();
let len = seen.len();
match seen.entry(physiscal_path) {
hash_map::Entry::Occupied(entry) => {
return Ok(*entry.get());
}
hash_map::Entry::Vacant(entry) => {
physiscal_path = entry.insert_entry(len as _).key().clone();
len
}
}
};
if !physiscal_path.exists() {
return Err(io::Error::new(
io::ErrorKind::NotFound,
format!("can't find file: {}", display_rel_path(&physiscal_path)),
));
}
tasks.push((id, physiscal_path));
Ok(id)
}
FileKind::Embed => {
let id = {
let mut seen = seen_embeds.lock().unwrap();
let len = seen.len();
match seen.entry(physiscal_path) {
hash_map::Entry::Occupied(entry) => {
return Ok(*entry.get());
}
hash_map::Entry::Vacant(entry) => {
physiscal_path = entry.insert_entry(len as _).key().clone();
len
}
}
};
let content = std::fs::read(&physiscal_path).map_err(|e| {
io::Error::new(
e.kind(),
format!(
"can't load embed file: {}: {e}",
display_rel_path(&physiscal_path)
),
)
})?;
let mut embeds = embeds.lock().unwrap();
if id as usize >= embeds.len() {
embeds.resize(id as usize + 1, Default::default());
}
embeds[id as usize] = content;
Ok(id)
}
}
};
let execute_task = |ctx: &mut _, (_, path): Task, tmp: &mut _| {
let path = path.to_str().ok_or_else(|| {
io::Error::new(
io::ErrorKind::InvalidData,
format!("path contains invalid characters: {}", display_rel_path(&path)),
)
})?;
Ok(Ast::new(path, std::fs::read_to_string(path)?, ctx, &mut |path, from, kind| {
loader(path, from, kind, tmp).map_err(|e| e.to_string())
}))
};
let thread = || {
let mut ctx = Ctx::default();
let mut tmp = PathBuf::new();
while let Some(task @ (indx, ..)) = tasks.pop() {
let res = execute_task(&mut ctx, task, &mut tmp);
let mut ast = ast.lock().unwrap();
let len = ast.len().max(indx + 1);
ast.resize_with(len, || Err(io::ErrorKind::InvalidData.into()));
ast[indx] = res;
}
ctx.errors.into_inner()
};
let path = Path::new(root).canonicalize().map_err(|e| {
io::Error::new(e.kind(), format!("can't canonicalize root file path ({root})"))
})?;
seen_modules.lock().unwrap().insert(path.clone(), 0);
tasks.push((0, path));
let errors = if extra_threads == 0 {
thread()
} else {
std::thread::scope(|s| {
(0..extra_threads + 1)
.map(|_| s.spawn(thread))
.collect::<Vec<_>>()
.into_iter()
.map(|t| t.join().unwrap())
.collect::<String>()
})
};
Ok(Loaded {
ast: ast.into_inner().unwrap().into_iter().collect::<io::Result<Vec<_>>>()?,
embeds: embeds.into_inner().unwrap(),
errors,
})
}
pub fn display_rel_path(path: &(impl AsRef<OsStr> + ?Sized)) -> std::path::Display {
static CWD: std::sync::LazyLock<PathBuf> =
std::sync::LazyLock::new(|| std::env::current_dir().unwrap_or_default());
std::path::Path::new(path).strip_prefix(&*CWD).unwrap_or(std::path::Path::new(path)).display()
}

141
lang/src/fuzz.rs
View file

@ -1,141 +0,0 @@
use {
crate::{
lexer::TokenKind,
parser,
son::{hbvm::HbvmBackend, Codegen, CodegenCtx},
ty::Module,
},
alloc::string::String,
core::{fmt::Write, hash::BuildHasher, ops::Range},
};
#[derive(Default)]
struct Rand(pub u64);
impl Rand {
pub fn next(&mut self) -> u64 {
self.0 = crate::FnvBuildHasher::default().hash_one(self.0);
self.0
}
pub fn range(&mut self, min: u64, max: u64) -> u64 {
self.next() % (max - min) + min
}
fn bool(&mut self) -> bool {
self.next() % 2 == 0
}
}
#[derive(Default)]
struct FuncGen {
rand: Rand,
buf: String,
vars: u64,
}
impl FuncGen {
fn gen(&mut self, seed: u64) -> &str {
self.rand = Rand(seed);
self.buf.clear();
self.buf.push_str("main := fn(): void ");
self.block().unwrap();
&self.buf
}
fn block(&mut self) -> core::fmt::Result {
let prev_vars = self.vars;
self.buf.push('{');
for _ in 0..self.rand.range(1, 10) {
self.stmt()?;
}
self.buf.push('}');
self.vars = prev_vars;
Ok(())
}
fn stmt(&mut self) -> core::fmt::Result {
match self.rand.range(0, 100) {
0..4 => _ = self.block(),
4..10 => {
write!(self.buf, "var{} := ", self.vars)?;
self.expr()?;
self.vars += 1;
}
10..20 if self.vars != 0 => {
write!(self.buf, "var{} = ", self.rand.range(0, self.vars))?;
self.expr()?;
}
20..23 => {
self.buf.push_str("if ");
self.expr()?;
self.block()?;
if self.rand.bool() {
self.buf.push_str(" else ");
self.block()?;
}
}
_ => {
self.buf.push_str("return ");
self.expr()?;
}
}
self.buf.push(';');
Ok(())
}
fn expr(&mut self) -> core::fmt::Result {
match self.rand.range(0, 100) {
0..80 => {
write!(self.buf, "{}", self.rand.next())
}
80..90 if self.vars != 0 => {
write!(self.buf, "var{}", self.rand.range(0, self.vars))
}
80..100 => {
self.expr()?;
let ops = [
TokenKind::Add,
TokenKind::Sub,
TokenKind::Mul,
TokenKind::Div,
TokenKind::Shl,
TokenKind::Eq,
TokenKind::Ne,
TokenKind::Lt,
TokenKind::Gt,
TokenKind::Le,
TokenKind::Ge,
TokenKind::Band,
TokenKind::Bor,
TokenKind::Xor,
TokenKind::Mod,
TokenKind::Shr,
];
let op = ops[self.rand.range(0, ops.len() as u64) as usize];
write!(self.buf, " {op} ")?;
self.expr()
}
_ => unreachable!(),
}
}
}
pub fn fuzz(seed_range: Range<u64>) {
let mut gen = FuncGen::default();
let mut ctx = CodegenCtx::default();
for i in seed_range {
ctx.clear();
let src = gen.gen(i);
let parsed = parser::Ast::new("fuzz", src, &mut ctx.parser, &mut parser::no_loader);
assert!(ctx.parser.errors.get_mut().is_empty());
let mut backend = HbvmBackend::default();
let mut cdg = Codegen::new(&mut backend, core::slice::from_ref(&parsed), &mut ctx);
cdg.generate(Module::MAIN);
}
}

3
lang/src/fuzz_main.rs
View file

@ -1,3 +0,0 @@
fn main() {
hblang::fuzz::fuzz(0..1000000);
}

575
lang/src/lexer.rs
View file

@ -1,575 +0,0 @@
const fn ascii_mask(chars: &[u8]) -> u128 {
let mut eq = 0;
let mut i = 0;
while i < chars.len() {
let b = chars[i];
eq |= 1 << b;
i += 1;
}
eq
}
#[derive(Debug, PartialEq, Eq, Clone, Copy)]
pub struct Token {
pub kind: TokenKind,
pub start: u32,
pub end: u32,
}
impl Token {
pub fn range(&self) -> core::ops::Range<usize> {
self.start as usize..self.end as usize
}
}
macro_rules! gen_token_kind {
($(
#[$atts:meta])*
$vis:vis enum $name:ident {
#[patterns] $(
$pattern:ident,
)*
#[keywords] $(
$keyword:ident = $keyword_lit:literal,
)*
#[punkt] $(
$punkt:ident = $punkt_lit:literal,
)*
#[ops] $(
#[$prec:ident] $(
$op:ident = $op_lit:literal $(=> $assign:ident)?,
)*
)*
}
) => {
impl core::fmt::Display for $name {
fn fmt(&self, f: &mut core::fmt::Formatter) -> core::fmt::Result {
f.write_str(self.name())
}
}
impl $name {
pub const OPS: &[Self] = &[$($(Self::$op),*),*];
pub fn name(&self) -> &str {
let sf = unsafe { &*(self as *const _ as *const u8) } ;
match *self {
$( Self::$pattern => concat!('<', stringify!($pattern), '>'), )*
$( Self::$keyword => stringify!($keyword_lit), )*
$( Self::$punkt => stringify!($punkt_lit), )*
$($( Self::$op => $op_lit,
$(Self::$assign => concat!($op_lit, "="),)?)*)*
_ => unsafe { core::str::from_utf8_unchecked(core::slice::from_ref(&sf)) },
}
}
#[inline(always)]
pub fn precedence(&self) -> Option<u8> {
Some(match self {
$($(Self::$op => ${ignore($prec)} ${index(1)},
$(Self::$assign => 0,)?)*)*
_ => return None,
} + 1)
}
fn from_ident(ident: &[u8]) -> Self {
match ident {
$($keyword_lit => Self::$keyword,)*
_ => Self::Ident,
}
}
}
};
}
#[derive(PartialEq, Eq, Clone, Copy, Hash, PartialOrd, Ord)]
#[repr(u8)]
pub enum TokenKind {
Not = b'!',
DQuote = b'"',
Pound = b'#',
CtIdent = b'$',
Mod = b'%',
Band = b'&',
Quote = b'\'',
LParen = b'(',
RParen = b')',
Mul = b'*',
Add = b'+',
Comma = b',',
Sub = b'-',
Dot = b'.',
Div = b'/',
// Unused = 2-6
Shl = b'<' - 5,
// Unused = 8
Shr = b'>' - 5,
Colon = b':',
Semi = b';',
Lt = b'<',
Assign = b'=',
Gt = b'>',
Que = b'?',
Directive = b'@',
Comment,
Ident,
Number,
Float,
Eof,
Ct,
Ctor,
Tupl,
TArrow,
Or,
And,
// Unused = R-Z
LBrack = b'[',
BSlash = b'\\',
RBrack = b']',
Xor = b'^',
Under = b'_',
Tick = b'`',
Slf,
Return,
If,
Match,
Else,
Loop,
Break,
Continue,
Fn,
Struct,
Packed,
Enum,
True,
False,
Null,
Idk,
Die,
Defer,
// Unused = a-z
LBrace = b'{',
Bor = b'|',
RBrace = b'}',
Tilde = b'~',
Decl = b':' + 128,
Eq = b'=' + 128,
Ne = b'!' + 128,
Le = b'<' + 128,
Ge = b'>' + 128,
BorAss = b'|' + 128,
AddAss = b'+' + 128,
SubAss = b'-' + 128,
MulAss = b'*' + 128,
DivAss = b'/' + 128,
ModAss = b'%' + 128,
XorAss = b'^' + 128,
BandAss = b'&' + 128,
ShrAss = b'>' - 5 + 128,
ShlAss = b'<' - 5 + 128,
}
impl core::fmt::Debug for TokenKind {
fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result {
core::fmt::Display::fmt(self, f)
}
}
impl TokenKind {
pub fn ass_op(self) -> Option<Self> {
let id = (self as u8).saturating_sub(128);
if ascii_mask(b"|+-*/%^&79") & (1u128 << id) == 0 {
return None;
}
Some(unsafe { core::mem::transmute::<u8, Self>(id) })
}
pub fn is_comutative(self) -> bool {
use TokenKind as S;
matches!(self, S::Eq | S::Ne | S::Bor | S::Xor | S::Band | S::Add | S::Mul)
}
pub fn is_compatison(self) -> bool {
matches!(self, Self::Lt | Self::Gt | Self::Ge | Self::Le | Self::Ne | Self::Eq)
}
pub fn is_supported_float_op(self) -> bool {
matches!(
self,
Self::Add
| Self::Sub
| Self::Mul
| Self::Div
| Self::Eq
| Self::Ne
| Self::Le
| Self::Ge
| Self::Lt
| Self::Gt
)
}
pub fn apply_binop(self, a: i64, b: i64, float: bool) -> i64 {
if float {
debug_assert!(self.is_supported_float_op());
let [a, b] = [f64::from_bits(a as _), f64::from_bits(b as _)];
let res = match self {
Self::Add => a + b,
Self::Sub => a - b,
Self::Mul => a * b,
Self::Div => a / b,
Self::Eq => return (a == b) as i64,
Self::Ne => return (a != b) as i64,
Self::Lt => return (a < b) as i64,
Self::Gt => return (a > b) as i64,
Self::Le => return (a >= b) as i64,
Self::Ge => return (a <= b) as i64,
_ => todo!("floating point op: {self}"),
};
return res.to_bits() as _;
}
match self {
Self::Add => a.wrapping_add(b),
Self::Sub => a.wrapping_sub(b),
Self::Mul => a.wrapping_mul(b),
Self::Div if b == 0 => 0,
Self::Div => a.wrapping_div(b),
Self::Shl => a.wrapping_shl(b as _),
Self::Eq => (a == b) as i64,
Self::Ne => (a != b) as i64,
Self::Lt => (a < b) as i64,
Self::Gt => (a > b) as i64,
Self::Le => (a >= b) as i64,
Self::Ge => (a <= b) as i64,
Self::Band => a & b,
Self::Bor => a | b,
Self::Xor => a ^ b,
Self::Mod if b == 0 => 0,
Self::Mod => a.wrapping_rem(b),
Self::Shr => a.wrapping_shr(b as _),
s => todo!("{s}"),
}
}
pub fn is_homogenous(&self) -> bool {
self.precedence() != Self::Eq.precedence()
&& self.precedence() != Self::Gt.precedence()
&& self.precedence() != Self::Eof.precedence()
}
pub fn apply_unop(&self, value: i64, float: bool) -> i64 {
match self {
Self::Sub if float => (-f64::from_bits(value as _)).to_bits() as _,
Self::Sub => value.wrapping_neg(),
Self::Not => (value == 0) as _,
Self::Float if float => value,
Self::Float => (value as f64).to_bits() as _,
Self::Number if float => f64::from_bits(value as _) as _,
Self::Number => value,
s => todo!("{s}"),
}
}
pub fn closing(&self) -> Option<TokenKind> {
Some(match self {
Self::Ctor => Self::RBrace,
Self::Tupl => Self::RParen,
Self::LParen => Self::RParen,
Self::LBrack => Self::RBrack,
Self::LBrace => Self::RBrace,
_ => return None,
})
}
}
gen_token_kind! {
pub enum TokenKind {
#[patterns]
CtIdent,
Ident,
Number,
Float,
Eof,
Directive,
#[keywords]
Slf = b"Self",
Return = b"return",
If = b"if",
Match = b"match",
Else = b"else",
Loop = b"loop",
Break = b"break",
Continue = b"continue",
Fn = b"fn",
Struct = b"struct",
Packed = b"packed",
Enum = b"enum",
True = b"true",
False = b"false",
Null = b"null",
Idk = b"idk",
Die = b"die",
Defer = b"defer",
Under = b"_",
#[punkt]
Ctor = ".{",
Tupl = ".(",
TArrow = "=>",
// #define OP: each `#[prec]` delimeters a level of precedence from lowest to highest
#[ops]
#[prec]
// this also includess all `<op>=` tokens
Decl = ":=",
Assign = "=",
#[prec]
Or = "||",
#[prec]
And = "&&",
#[prec]
Bor = "|" => BorAss,
#[prec]
Xor = "^" => XorAss,
#[prec]
Band = "&" => BandAss,
#[prec]
Eq = "==",
Ne = "!=",
#[prec]
Le = "<=",
Ge = ">=",
Lt = "<",
Gt = ">",
#[prec]
Shl = "<<" => ShlAss,
Shr = ">>" => ShrAss,
#[prec]
Add = "+" => AddAss,
Sub = "-" => SubAss,
#[prec]
Mul = "*" => MulAss,
Div = "/" => DivAss,
Mod = "%" => ModAss,
}
}
pub struct Lexer<'a> {
pos: u32,
source: &'a [u8],
}
impl<'a> Lexer<'a> {
pub fn new(input: &'a str) -> Self {
Self::restore(input, 0)
}
pub fn uses(input: &'a str) -> impl Iterator<Item = &'a str> {
let mut s = Self::new(input);
core::iter::from_fn(move || loop {
let t = s.eat();
if t.kind == TokenKind::Eof {
return None;
}
if t.kind == TokenKind::Directive
&& s.slice(t.range()) == "use"
&& s.eat().kind == TokenKind::LParen
{
let t = s.eat();
if t.kind == TokenKind::DQuote {
return Some(&s.slice(t.range())[1..t.range().len() - 1]);
}
}
})
}
pub fn restore(input: &'a str, pos: u32) -> Self {
Self { pos, source: input.as_bytes() }
}
pub fn source(&self) -> &'a str {
unsafe { core::str::from_utf8_unchecked(self.source) }
}
pub fn slice(&self, tok: core::ops::Range<usize>) -> &'a str {
unsafe { core::str::from_utf8_unchecked(&self.source[tok]) }
}
pub fn taste(&self) -> Token {
Lexer { pos: self.pos, source: self.source }.eat()
}
fn peek(&self) -> Option<u8> {
if core::intrinsics::unlikely(self.pos >= self.source.len() as u32) {
None
} else {
Some(unsafe { *self.source.get_unchecked(self.pos as usize) })
}
}
fn advance(&mut self) -> Option<u8> {
let c = self.peek()?;
self.pos += 1;
Some(c)
}
pub fn last(&mut self) -> Token {
let mut token = self.eat();
loop {
let next = self.eat();
if next.kind == TokenKind::Eof {
break;
}
token = next;
}
token
}
pub fn eat(&mut self) -> Token {
use TokenKind as T;
loop {
let mut start = self.pos;
let Some(c) = self.advance() else {
return Token { kind: T::Eof, start, end: self.pos };
};
let advance_ident = |s: &mut Self| {
while let Some(b'a'..=b'z' | b'A'..=b'Z' | b'0'..=b'9' | b'_' | 127..) = s.peek() {
s.advance();
}
};
let identity = |s: u8| unsafe { core::mem::transmute::<u8, T>(s) };
let kind = match c {
..=b' ' => continue,
b'0' if self.advance_if(b'x') => {
while let Some(b'0'..=b'9' | b'A'..=b'F' | b'a'..=b'f') = self.peek() {
self.advance();
}
T::Number
}
b'0' if self.advance_if(b'b') => {
while let Some(b'0' | b'1') = self.peek() {
self.advance();
}
T::Number
}
b'0' if self.advance_if(b'o') => {
while let Some(b'0'..=b'7') = self.peek() {
self.advance();
}
T::Number
}
b'0'..=b'9' => {
while let Some(b'0'..=b'9') = self.peek() {
self.advance();
}
if self.advance_if(b'.') {
while let Some(b'0'..=b'9') = self.peek() {
self.advance();
}
T::Float
} else {
T::Number
}
}
b'a'..=b'z' | b'A'..=b'Z' | b'_' | 127.. => {
advance_ident(self);
let ident = &self.source[start as usize..self.pos as usize];
T::from_ident(ident)
}
b'"' | b'\'' => loop {
match self.advance() {
Some(b'\\') => _ = self.advance(),
Some(nc) if nc == c => break identity(c),
Some(_) => {}
None => break T::Eof,
}
},
b'/' if self.advance_if(b'/') => {
while let Some(l) = self.peek()
&& l != b'\n'
{
self.pos += 1;
}
let end = self.source[..self.pos as usize]
.iter()
.rposition(|&b| !b.is_ascii_whitespace())
.map_or(self.pos, |i| i as u32 + 1);
return Token { kind: T::Comment, start, end };
}
b'/' if self.advance_if(b'*') => {
let mut depth = 1;
while let Some(l) = self.advance() {
match l {
b'/' if self.advance_if(b'*') => depth += 1,
b'*' if self.advance_if(b'/') => match depth {
1 => break,
_ => depth -= 1,
},
_ => {}
}
}
T::Comment
}
b'.' if self.advance_if(b'{') => T::Ctor,
b'.' if self.advance_if(b'(') => T::Tupl,
b'=' if self.advance_if(b'>') => T::TArrow,
b'&' if self.advance_if(b'&') => T::And,
b'|' if self.advance_if(b'|') => T::Or,
b'$' if self.advance_if(b':') => T::Ct,
b'@' | b'$' => {
start += 1;
advance_ident(self);
identity(c)
}
b'<' | b'>' if self.advance_if(c) => {
identity(c - 5 + 128 * self.advance_if(b'=') as u8)
}
b':' | b'=' | b'!' | b'<' | b'>' | b'|' | b'+' | b'-' | b'*' | b'/' | b'%'
| b'^' | b'&'
if self.advance_if(b'=') =>
{
identity(c + 128)
}
_ => identity(c),
};
return Token { kind, start, end: self.pos };
}
}
fn advance_if(&mut self, arg: u8) -> bool {
if self.peek() == Some(arg) {
self.advance();
true
} else {
false
}
}
}
pub fn line_col(bytes: &[u8], pos: u32) -> (usize, usize) {
bytes[..pos as usize]
.split(|&b| b == b'\n')
.map(<[u8]>::len)
.enumerate()
.last()
.map(|(line, col)| (line + 1, col + 1))
.unwrap_or((1, 1))
}

1576
lang/src/lib.rs
View file

File diff suppressed because it is too large Load diff

31
lang/src/main.rs
View file

@ -1,31 +0,0 @@
#[cfg(feature = "std")]
fn main() {
use std::io::Write;
fn run(out: &mut Vec<u8>, warnings: &mut String) -> std::io::Result<()> {
let args = std::env::args().collect::<Vec<_>>();
let args = args.iter().map(String::as_str).collect::<Vec<_>>();
let opts = hblang::Options::from_args(&args, out)?;
let file = args.iter().filter(|a| !a.starts_with('-')).nth(1).copied().unwrap_or("main.hb");
hblang::run_compiler(file, opts, out, warnings)
}
log::set_logger(&hblang::fs::Logger).unwrap();
log::set_max_level(log::LevelFilter::Error);
let mut out = Vec::new();
let mut warnings = String::new();
match run(&mut out, &mut warnings) {
Ok(_) => {
std::io::stderr().write_all(warnings.as_bytes()).unwrap();
std::io::stdout().write_all(&out).unwrap()
}
Err(_) => {
std::io::stderr().write_all(warnings.as_bytes()).unwrap();
std::io::stderr().write_all(&out).unwrap();
std::process::exit(1);
}
}
}

1672
lang/src/parser.rs
View file

File diff suppressed because it is too large Load diff

5834
lang/src/son.rs
View file

File diff suppressed because it is too large Load diff

1172
lang/src/son/hbvm.rs
View file

File diff suppressed because it is too large Load diff

805
lang/src/son/hbvm/regalloc.rs
View file

@ -1,805 +0,0 @@
use {
super::{HbvmBackend, Nid, Nodes},
crate::{
parser,
reg::{self, Reg},
son::{debug_assert_matches, Kind, ARG_START, MEM, VOID},
ty::{self, Arg, Loc},
utils::BitSet,
PLoc, Sig, Types,
},
alloc::{borrow::ToOwned, vec::Vec},
core::{mem, ops::Range},
hbbytecode::{self as instrs},
};
impl HbvmBackend {
pub(super) fn emit_body_code(
&mut self,
nodes: &Nodes,
sig: Sig,
tys: &Types,
files: &[parser::Ast],
) -> (usize, bool) {
let tail = Function::build(nodes, tys, &mut self.ralloc, sig);
nodes.basic_blocks();
let strip_load = |value| match nodes[value].kind {
Kind::Load { .. } if nodes[value].ty.loc(tys) == Loc::Stack => nodes[value].inputs[1],
_ => value,
};
let mut res = mem::take(&mut self.ralloc);
Regalloc::run(nodes, &mut res);
'_open_function: {
self.emit(instrs::addi64(reg::STACK_PTR, reg::STACK_PTR, 0));
self.emit(instrs::st(reg::RET_ADDR + tail as u8, reg::STACK_PTR, 0, 0));
}
if let Some(PLoc::Ref(..)) = tys.parama(sig.ret).0 {
res.node_to_reg[MEM as usize] = res.bundles.len() as u8 + 1;
res.bundles.push(Bundle::new(0));
}
let reg_offset = if tail { reg::RET + 12 } else { reg::RET_ADDR + 1 };
let bundle_count = res.bundles.len() + (reg_offset as usize);
res.node_to_reg.iter_mut().filter(|r| **r != 0).for_each(|r| {
if *r == u8::MAX {
*r = 0
} else {
*r += reg_offset - 1;
if tail && *r >= reg::RET_ADDR {
*r += 1;
}
}
});
debug_assert!(!res
.node_to_reg
.iter()
.any(|&a| a == reg::RET_ADDR || (reg::RET..reg_offset - 1).contains(&a)));
let atr = |allc: Nid| {
let allc = strip_load(allc);
debug_assert_eq!(
nodes[allc].lock_rc.get(),
0,
"{:?} {}",
nodes[allc],
ty::Display::new(tys, files, nodes[allc].ty)
);
res.node_to_reg[allc as usize]
};
let (retl, mut parama) = tys.parama(sig.ret);
let mut typs = sig.args.args();
let mut args = nodes[VOID].outputs[ARG_START..].iter();
while let Some(aty) = typs.next(tys) {
let Arg::Value(ty) = aty else { continue };
let Some(loc) = parama.next(ty, tys) else { continue };
let &arg = args.next().unwrap();
let (rg, size) = match loc {
PLoc::WideReg(rg, size) => (rg, size),
PLoc::Reg(rg, size) if ty.loc(tys) == Loc::Stack => (rg, size),
PLoc::Reg(r, ..) | PLoc::Ref(r, ..) => {
self.emit_cp(atr(arg), r);
continue;
}
};
self.emit(instrs::st(rg, reg::STACK_PTR, self.offsets[arg as usize] as _, size));
if nodes.is_unlocked(arg) {
self.emit(instrs::addi64(rg, reg::STACK_PTR, self.offsets[arg as usize] as _));
}
self.emit_cp(atr(arg), rg);
}
let mut alloc_buf = vec![];
for (i, block) in res.blocks.iter().enumerate() {
self.offsets[block.entry as usize] = self.code.len() as _;
for &nid in &res.instrs[block.range()] {
if nid == VOID {
continue;
}
let node = &nodes[nid];
alloc_buf.clear();
let atr = |allc: Nid| {
let allc = strip_load(allc);
debug_assert_eq!(
nodes[allc].lock_rc.get(),
0,
"{:?} {}",
nodes[allc],
ty::Display::new(tys, files, nodes[allc].ty)
);
#[cfg(debug_assertions)]
debug_assert!(
res.marked.contains(&(allc, nid))
|| nid == allc
|| nodes.is_hard_zero(allc)
|| allc == MEM
|| matches!(node.kind, Kind::Loop | Kind::Region),
"{nid} {:?}\n{allc} {:?}",
nodes[nid],
nodes[allc]
);
res.node_to_reg[allc as usize]
};
let mut is_next_block = false;
match node.kind {
Kind::If => {
let &[_, cnd] = node.inputs.as_slice() else { unreachable!() };
if nodes.cond_op(cnd).is_some() {
let &[_, lh, rh] = nodes[cnd].inputs.as_slice() else { unreachable!() };
alloc_buf.extend([atr(lh), atr(rh)]);
} else {
alloc_buf.push(atr(cnd));
}
}
Kind::Loop | Kind::Region => {
let index = node
.inputs
.iter()
.position(|&n| block.entry == nodes.idom_of(n))
.unwrap()
+ 1;
let mut moves = vec![];
for &out in node.outputs.iter() {
if nodes[out].is_data_phi() {
let src = nodes[out].inputs[index];
if atr(out) != atr(src) {
moves.push([atr(out), atr(src), 0]);
}
}
}
debug_assert_eq!(moves.len(), {
moves.sort_unstable();
moves.dedup();
moves.len()
});
moves.sort_unstable_by(|[aa, ab, _], [ba, bb, _]| {
if aa == bb && ab == ba {
core::cmp::Ordering::Equal
} else if aa == bb {
core::cmp::Ordering::Greater
} else {
core::cmp::Ordering::Less
}
});
moves.dedup_by(|[aa, ab, _], [ba, bb, kind]| {
if aa == bb && ab == ba {
*kind = 1;
true
} else {
false
}
});
for [dst, src, kind] in moves {
if kind == 0 {
self.emit(instrs::cp(dst, src));
} else {
self.emit(instrs::swa(dst, src));
}
}
is_next_block = res.backrefs[nid as usize] as usize == i + 1;
}
Kind::Return { .. } => {
let &[_, ret, ..] = node.inputs.as_slice() else { unreachable!() };
match retl {
Some(PLoc::Reg(r, _)) if sig.ret.loc(tys) == Loc::Reg => {
alloc_buf.push(atr(ret));
self.emit(instrs::cp(r, atr(ret)));
}
Some(PLoc::Ref(..)) => alloc_buf.extend([atr(ret), atr(MEM)]),
Some(_) => alloc_buf.push(atr(ret)),
None => {}
}
}
Kind::Die => {}
Kind::CInt { .. } => alloc_buf.push(atr(nid)),
Kind::UnOp { .. } => alloc_buf.extend([atr(nid), atr(node.inputs[1])]),
Kind::BinOp { op } => {
let &[.., lhs, rhs] = node.inputs.as_slice() else { unreachable!() };
if let Kind::CInt { .. } = nodes[rhs].kind
&& nodes.is_locked(rhs)
&& op.imm_binop(node.ty).is_some()
{
alloc_buf.extend([atr(nid), atr(lhs)]);
} else {
alloc_buf.extend([atr(nid), atr(lhs), atr(rhs)]);
}
}
Kind::Call { args, .. } => {
let (ret, mut parama) = tys.parama(node.ty);
if ret.is_some() {
alloc_buf.push(atr(nid));
}
let mut args = args.args();
let mut allocs = node.inputs[1..].iter();
while let Some(arg) = args.next(tys) {
let Arg::Value(ty) = arg else { continue };
let Some(loc) = parama.next(ty, tys) else { continue };
let arg = *allocs.next().unwrap();
alloc_buf.push(atr(arg));
match loc {
PLoc::Reg(..) if ty.loc(tys) == Loc::Stack => {}
PLoc::WideReg(..) => alloc_buf.push(0),
PLoc::Reg(r, ..) | PLoc::Ref(r, ..) => {
self.emit(instrs::cp(r, atr(arg)))
}
};
}
if node.ty.loc(tys) == Loc::Stack {
alloc_buf.push(atr(*node.inputs.last().unwrap()));
}
if let Some(PLoc::Ref(r, ..)) = ret {
self.emit(instrs::cp(r, *alloc_buf.last().unwrap()))
}
}
Kind::Stck | Kind::Global { .. } => alloc_buf.push(atr(nid)),
Kind::Load => {
let (region, _) = nodes.strip_offset(node.inputs[1], node.ty, tys);
if node.ty.loc(tys) != Loc::Stack {
alloc_buf.push(atr(nid));
match nodes[region].kind {
Kind::Stck => {}
_ => alloc_buf.push(atr(region)),
}
}
}
Kind::Stre if node.inputs[1] == VOID => {}
Kind::Stre => {
let (region, _) = nodes.strip_offset(node.inputs[2], node.ty, tys);
match nodes[region].kind {
Kind::Stck if node.ty.loc(tys) == Loc::Reg => {
alloc_buf.push(atr(node.inputs[1]))
}
_ => alloc_buf.extend([atr(region), atr(node.inputs[1])]),
}
}
Kind::Mem => {
self.emit(instrs::cp(atr(MEM), reg::RET));
continue;
}
Kind::Arg => {
continue;
}
_ => {}
}
self.emit_instr(super::InstrCtx {
nid,
sig,
is_next_block,
is_last_block: i == res.blocks.len() - 1,
retl,
allocs: &alloc_buf,
nodes,
tys,
files,
});
if let Kind::Call { .. } = node.kind {
let (ret, ..) = tys.parama(node.ty);
match ret {
Some(PLoc::WideReg(..)) => {}
Some(PLoc::Reg(..)) if node.ty.loc(tys) == Loc::Stack => {}
Some(PLoc::Reg(r, ..)) => self.emit_cp(atr(nid), r),
None | Some(PLoc::Ref(..)) => {}
}
}
}
}
self.ralloc = res;
debug_assert!(bundle_count < reg::STACK_PTR as usize, "TODO: spill memory");
debug_assert_eq!(
self.ralloc
.node_to_reg
.iter()
.filter(|&&r| r
> (bundle_count as u8
+ (tail && bundle_count > (reg::RET_ADDR) as usize) as u8))
.copied()
.collect::<Vec<_>>(),
vec![],
"{bundle_count}"
);
(
if tail {
bundle_count.saturating_sub(reg::RET_ADDR as _)
} else {
self.ralloc.bundles.len()
},
tail,
)
}
fn emit_cp(&mut self, dst: Reg, src: Reg) {
if dst != 0 {
self.emit(instrs::cp(dst, src));
}
}
}
struct Function<'a> {
sig: Sig,
tail: bool,
nodes: &'a Nodes,
tys: &'a Types,
func: &'a mut Res,
}
impl core::fmt::Debug for Function<'_> {
fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result {
for block in &self.func.blocks {
writeln!(f, "{:?}", self.nodes[block.entry].kind)?;
for &instr in &self.func.instrs[block.range()] {
writeln!(f, "{:?}", self.nodes[instr].kind)?;
}
}
Ok(())
}
}
impl<'a> Function<'a> {
fn build(nodes: &'a Nodes, tys: &'a Types, func: &'a mut Res, sig: Sig) -> bool {
func.blocks.clear();
func.instrs.clear();
func.backrefs.resize(nodes.values.len(), u16::MAX);
func.visited.clear(nodes.values.len());
let mut s = Self { tail: true, nodes, tys, sig, func };
s.emit_node(VOID);
debug_assert!(s.func.blocks.array_chunks().all(|[a, b]| a.end == b.start));
log::info!("{s:?}");
s.tail
}
fn add_block(&mut self, entry: Nid) {
self.func.blocks.push(Block {
start: self.func.instrs.len() as _,
end: self.func.instrs.len() as _,
entry,
});
self.func.backrefs[entry as usize] = self.func.blocks.len() as u16 - 1;
}
fn close_block(&mut self, exit: Nid) {
if !matches!(self.nodes[exit].kind, Kind::Loop | Kind::Region) {
self.add_instr(exit);
} else {
self.func.instrs.push(exit);
}
let prev = self.func.blocks.last_mut().unwrap();
prev.end = self.func.instrs.len() as _;
}
fn add_instr(&mut self, nid: Nid) {
debug_assert_ne!(self.nodes[nid].kind, Kind::Loop);
self.func.backrefs[nid as usize] = self.func.instrs.len() as u16;
self.func.instrs.push(nid);
}
fn emit_node(&mut self, nid: Nid) {
if matches!(self.nodes[nid].kind, Kind::Region | Kind::Loop) {
match (self.nodes[nid].kind, self.func.visited.set(nid)) {
(Kind::Loop, false) | (Kind::Region, true) => {
self.close_block(nid);
return;
}
_ => {}
}
} else if !self.func.visited.set(nid) {
return;
}
if self.nodes.is_never_used(nid, self.tys) {
self.nodes.lock(nid);
return;
}
let mut node = self.nodes[nid].clone();
match node.kind {
Kind::Start => {
debug_assert_matches!(self.nodes[node.outputs[0]].kind, Kind::Entry);
self.add_block(VOID);
self.emit_node(node.outputs[0])
}
Kind::If => {
let &[_, cnd] = node.inputs.as_slice() else { unreachable!() };
let &[mut then, mut else_] = node.outputs.as_slice() else { unreachable!() };
if let Some((_, swapped)) = self.nodes.cond_op(cnd) {
if swapped {
mem::swap(&mut then, &mut else_);
}
} else {
mem::swap(&mut then, &mut else_);
}
self.close_block(nid);
self.emit_node(then);
self.emit_node(else_);
}
Kind::Region | Kind::Loop => {
self.close_block(nid);
self.add_block(nid);
self.nodes.reschedule_block(nid, &mut node.outputs);
for o in node.outputs.into_iter().rev() {
self.emit_node(o);
}
}
Kind::Return { .. } | Kind::Die => {
self.close_block(nid);
self.emit_node(node.outputs[0]);
}
Kind::Entry => {
let (ret, mut parama) = self.tys.parama(self.sig.ret);
if let Some(PLoc::Ref(..)) = ret {
self.add_instr(MEM);
}
let mut typs = self.sig.args.args();
#[expect(clippy::unnecessary_to_owned)]
let mut args = self.nodes[VOID].outputs[ARG_START..].to_owned().into_iter();
while let Some(ty) = typs.next_value(self.tys) {
let arg = args.next().unwrap();
debug_assert_eq!(self.nodes[arg].kind, Kind::Arg);
match parama.next(ty, self.tys) {
None => {}
Some(_) => self.add_instr(arg),
}
}
self.nodes.reschedule_block(nid, &mut node.outputs);
for o in node.outputs.into_iter().rev() {
self.emit_node(o);
}
}
Kind::Then | Kind::Else => {
self.add_block(nid);
self.nodes.reschedule_block(nid, &mut node.outputs);
for o in node.outputs.into_iter().rev() {
self.emit_node(o);
}
}
Kind::Call { func, .. } => {
self.tail &= func == ty::Func::ECA;
self.add_instr(nid);
self.nodes.reschedule_block(nid, &mut node.outputs);
for o in node.outputs.into_iter().rev() {
if self.nodes[o].inputs[0] == nid
|| (matches!(self.nodes[o].kind, Kind::Loop | Kind::Region)
&& self.nodes[o].inputs[1] == nid)
{
self.emit_node(o);
}
}
}
Kind::CInt { value: 0 } if self.nodes.is_hard_zero(nid) => {}
Kind::CInt { .. }
| Kind::BinOp { .. }
| Kind::UnOp { .. }
| Kind::Global { .. }
| Kind::Load { .. }
| Kind::Stre
| Kind::Stck => self.add_instr(nid),
Kind::End | Kind::Phi | Kind::Arg | Kind::Mem | Kind::Loops | Kind::Join => {}
Kind::Assert { .. } => unreachable!(),
}
}
}
impl Nodes {
fn vreg_count(&self) -> usize {
self.values.len()
}
fn use_block_of(&self, inst: Nid, uinst: Nid) -> Nid {
let mut block = self.use_block(inst, uinst, None);
while !self[block].kind.starts_basic_block() {
block = self.idom(block, None);
}
block
}
fn phi_inputs_of(&self, nid: Nid) -> impl Iterator<Item = [Nid; 3]> + use<'_> {
match self[nid].kind {
Kind::Region | Kind::Loop => Some({
self[nid]
.outputs
.as_slice()
.iter()
.filter(|&&n| self[n].is_data_phi())
.map(|&n| [n, self[n].inputs[1], self[n].inputs[2]])
})
.into_iter()
.flatten(),
_ => None.into_iter().flatten(),
}
}
fn idom_of(&self, mut nid: Nid) -> Nid {
while !self[nid].kind.starts_basic_block() {
nid = self.idom(nid, None);
}
nid
}
fn uses_of(&self, nid: Nid) -> impl Iterator<Item = (Nid, Nid)> + use<'_> {
if self[nid].kind.is_cfg() && !matches!(self[nid].kind, Kind::Call { .. }) {
return None.into_iter().flatten();
}
Some(
self[nid]
.outputs
.iter()
.filter(move |&&n| self.is_data_dep(nid, n))
.map(move |n| self.this_or_delegates(nid, n))
.flat_map(|(p, ls)| ls.iter().map(move |l| (p, l)))
.filter(|&(o, &n)| self.is_data_dep(o, n))
.map(|(p, &n)| (self.use_block_of(p, n), n))
.inspect(|&(_, n)| debug_assert_eq!(self[n].lock_rc.get(), 0)),
)
.into_iter()
.flatten()
}
}
struct Regalloc<'a> {
nodes: &'a Nodes,
res: &'a mut Res,
}
impl<'a> Regalloc<'a> {
fn instr_of(&self, nid: Nid) -> Option<Nid> {
if self.nodes[nid].kind == Kind::Phi || self.nodes.is_locked(nid) {
return None;
}
debug_assert_ne!(self.res.backrefs[nid as usize], Nid::MAX, "{:?}", self.nodes[nid]);
Some(self.res.backrefs[nid as usize])
}
fn block_of(&self, nid: Nid) -> Nid {
debug_assert!(self.nodes[nid].kind.starts_basic_block());
self.res.backrefs[nid as usize]
}
fn run(ctx: &'a Nodes, res: &'a mut Res) {
Self { nodes: ctx, res }.run_low();
}
fn run_low(&mut self) {
self.res.bundles.clear();
self.res.node_to_reg.clear();
#[cfg(debug_assertions)]
self.res.marked.clear();
self.res.node_to_reg.resize(self.nodes.vreg_count(), 0);
debug_assert!(self.res.dfs_buf.is_empty());
let mut bundle = Bundle::new(self.res.instrs.len());
self.res.visited.clear(self.nodes.values.len());
for i in (0..self.res.blocks.len()).rev() {
for [a, rest @ ..] in self.nodes.phi_inputs_of(self.res.blocks[i].entry) {
if self.res.visited.set(a) {
self.append_bundle(a, &mut bundle, None);
}
for r in rest {
if !self.res.visited.set(r) {
continue;
}
self.append_bundle(
r,
&mut bundle,
Some(self.res.node_to_reg[a as usize] as usize - 1),
);
}
}
}
let instrs = mem::take(&mut self.res.instrs);
for &inst in &instrs {
if self.nodes[inst].has_no_value() || self.res.visited.get(inst) || inst == 0 {
continue;
}
self.append_bundle(inst, &mut bundle, None);
}
self.res.instrs = instrs;
}
fn collect_bundle(&mut self, inst: Nid, into: &mut Bundle) {
let dom = self.nodes.idom_of(inst);
self.res.dfs_seem.clear(self.nodes.values.len());
for (cursor, uinst) in self.nodes.uses_of(inst) {
if !self.res.dfs_seem.set(uinst) {
continue;
}
#[cfg(debug_assertions)]
debug_assert!(self.res.marked.insert((inst, uinst)));
self.reverse_cfg_dfs(cursor, dom, |s, n, b| {
let mut range = b.range();
debug_assert!(range.start < range.end);
range.start = range.start.max(s.instr_of(inst).map_or(0, |n| n + 1) as usize);
debug_assert!(
range.start < range.end,
"{:?} {:?} {n} {inst}",
range,
self.nodes[inst]
);
let new = range.end.min(
s.instr_of(uinst)
.filter(|_| {
n == cursor
&& self.nodes.loop_depth(dom, None)
== self.nodes.loop_depth(cursor, None)
})
.map_or(Nid::MAX, |n| n + 1) as usize,
);
range.end = new;
debug_assert!(range.start < range.end, "{:?} {inst} {uinst}", range);
into.add(range);
});
}
}
fn append_bundle(&mut self, inst: Nid, tmp: &mut Bundle, prefered: Option<usize>) {
self.collect_bundle(inst, tmp);
if tmp.is_empty() {
self.res.node_to_reg[inst as usize] = u8::MAX;
return;
}
if let Some(prefered) = prefered
&& !self.res.bundles[prefered].overlaps(tmp)
{
self.res.bundles[prefered].merge(tmp);
tmp.clear();
self.res.node_to_reg[inst as usize] = prefered as Reg + 1;
return;
}
match self.res.bundles.iter_mut().enumerate().find(|(_, b)| !b.overlaps(tmp)) {
Some((i, other)) => {
other.merge(tmp);
tmp.clear();
self.res.node_to_reg[inst as usize] = i as Reg + 1;
}
None => {
self.res.bundles.push(tmp.take());
self.res.node_to_reg[inst as usize] = self.res.bundles.len() as Reg;
}
}
}
fn reverse_cfg_dfs(
&mut self,
from: Nid,
until: Nid,
mut each: impl FnMut(&mut Self, Nid, Block),
) {
debug_assert!(self.res.dfs_buf.is_empty());
self.res.dfs_buf.push(from);
debug_assert!(self.nodes.dominates(until, from, None));
while let Some(nid) = self.res.dfs_buf.pop() {
debug_assert!(
self.nodes.dominates(until, nid, None),
"{until} {:?}",
self.nodes[until]
);
each(self, nid, self.res.blocks[self.block_of(nid) as usize]);
if nid == until {
continue;
}
match self.nodes[nid].kind {
Kind::Then | Kind::Else | Kind::Region | Kind::Loop => {
for &n in self.nodes[nid].inputs.iter() {
if self.nodes[n].kind == Kind::Loops {
continue;
}
let d = self.nodes.idom_of(n);
if self.res.dfs_seem.set(d) {
self.res.dfs_buf.push(d);
}
}
}
Kind::Start => {}
_ => unreachable!(),
}
}
}
}
#[derive(Default)]
pub(super) struct Res {
blocks: Vec<Block>,
instrs: Vec<Nid>,
backrefs: Vec<u16>,
bundles: Vec<Bundle>,
node_to_reg: Vec<Reg>,
visited: BitSet,
dfs_buf: Vec<Nid>,
dfs_seem: BitSet,
#[cfg(debug_assertions)]
marked: hashbrown::HashSet<(Nid, Nid), crate::FnvBuildHasher>,
}
struct Bundle {
taken: Vec<bool>,
}
impl Bundle {
fn new(size: usize) -> Self {
Self { taken: vec![false; size] }
}
fn add(&mut self, range: Range<usize>) {
self.taken[range].fill(true);
}
fn overlaps(&self, other: &Self) -> bool {
self.taken.iter().zip(other.taken.iter()).any(|(a, b)| a & b)
}
fn merge(&mut self, other: &Self) {
debug_assert!(!self.overlaps(other));
self.taken.iter_mut().zip(other.taken.iter()).for_each(|(a, b)| *a |= *b);
}
fn clear(&mut self) {
self.taken.fill(false);
}
fn is_empty(&self) -> bool {
!self.taken.contains(&true)
}
fn take(&mut self) -> Self {
mem::replace(self, Self::new(self.taken.len()))
}
}
#[derive(Clone, Copy)]
struct Block {
start: u16,
end: u16,
entry: Nid,
}
impl Block {
pub fn range(&self) -> Range<usize> {
self.start as usize..self.end as usize
}
}

649
lang/src/utils.rs
View file

@ -1,649 +0,0 @@
#![expect(dead_code)]
use {
alloc::alloc,
core::{
alloc::Layout,
fmt::Debug,
hint::unreachable_unchecked,
marker::PhantomData,
mem::MaybeUninit,
ops::{Deref, DerefMut, Not},
ptr::Unique,
},
};
fn decide(b: bool, name: &'static str) -> Result<(), &'static str> {
b.then_some(()).ok_or(name)
}
pub fn is_snake_case(str: &str) -> Result<(), &'static str> {
decide(str.bytes().all(|c| matches!(c, b'a'..=b'z' | b'0'..=b'9' | b'_')), "snake_case")
}
pub fn is_pascal_case(str: &str) -> Result<(), &'static str> {
decide(
str.as_bytes()[0].is_ascii_uppercase() && str.bytes().all(|c| c.is_ascii_alphanumeric()),
"PascalCase",
)
}
pub fn is_screaming_case(str: &str) -> Result<(), &'static str> {
decide(str.bytes().all(|c| matches!(c, b'A'..=b'Z' | b'0'..=b'9' | b'_')), "SCREAMING_CASE")
}
type Nid = u16;
pub union BitSet {
inline: usize,
alloced: Unique<AllocedBitSet>,
}
impl Debug for BitSet {
fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result {
f.debug_list().entries(self.iter()).finish()
}
}
impl Clone for BitSet {
fn clone(&self) -> Self {
if self.is_inline() {
Self { inline: unsafe { self.inline } }
} else {
let (data, _) = self.data_and_len();
let (layout, _) = Self::layout(data.len());
unsafe {
let ptr = alloc::alloc(layout);
ptr.copy_from_nonoverlapping(self.alloced.as_ptr() as _, layout.size());
Self { alloced: Unique::new_unchecked(ptr as _) }
}
}
}
}
impl Drop for BitSet {
fn drop(&mut self) {
if !self.is_inline() {
unsafe {
let cap = self.alloced.as_ref().cap;
alloc::dealloc(self.alloced.as_ptr() as _, Self::layout(cap).0);
}
}
}
}
impl Default for BitSet {
fn default() -> Self {
Self { inline: Self::FLAG }
}
}
impl BitSet {
const FLAG: usize = 1 << (Self::UNIT - 1);
const INLINE_ELEMS: usize = Self::UNIT - 1;
const UNIT: usize = core::mem::size_of::<usize>() * 8;
pub fn with_capacity(len: usize) -> Self {
let mut s = Self::default();
s.reserve(len);
s
}
fn is_inline(&self) -> bool {
unsafe { self.inline & Self::FLAG != 0 }
}
fn data_and_len(&self) -> (&[usize], usize) {
unsafe {
if self.is_inline() {
(core::slice::from_ref(&self.inline), Self::INLINE_ELEMS)
} else {
let small_vec = self.alloced.as_ref();
(
core::slice::from_raw_parts(
&small_vec.data as *const _ as *const usize,
small_vec.cap,
),
small_vec.cap * core::mem::size_of::<usize>() * 8,
)
}
}
}
fn data_mut_and_len(&mut self) -> (&mut [usize], usize) {
unsafe {
if self.is_inline() {
(core::slice::from_mut(&mut self.inline), INLINE_ELEMS)
} else {
let small_vec = self.alloced.as_mut();
(
core::slice::from_raw_parts_mut(
&mut small_vec.data as *mut _ as *mut usize,
small_vec.cap,
),
small_vec.cap * Self::UNIT,
)
}
}
}
fn indexes(index: usize) -> (usize, usize) {
(index / Self::UNIT, index % Self::UNIT)
}
pub fn get(&self, index: Nid) -> bool {
let index = index as usize;
let (data, len) = self.data_and_len();
if index >= len {
return false;
}
let (elem, bit) = Self::indexes(index);
(unsafe { *data.get_unchecked(elem) }) & (1 << bit) != 0
}
pub fn set(&mut self, index: Nid) -> bool {
let index = index as usize;
let (mut data, len) = self.data_mut_and_len();
if core::intrinsics::unlikely(index >= len) {
self.grow((index + 1).next_power_of_two().max(4 * Self::UNIT));
(data, _) = self.data_mut_and_len();
}
let (elem, bit) = Self::indexes(index);
debug_assert!(elem < data.len(), "{} < {}", elem, data.len());
let elem = unsafe { data.get_unchecked_mut(elem) };
let prev = *elem;
*elem |= 1 << bit;
*elem != prev
}
fn grow(&mut self, size: usize) {
debug_assert!(size.is_power_of_two());
let slot_count = size / Self::UNIT;
let (layout, off) = Self::layout(slot_count);
let (ptr, prev_len) = unsafe {
if self.is_inline() {
let ptr = alloc::alloc(layout);
*ptr.add(off).cast::<usize>() = self.inline & !Self::FLAG;
(ptr, 1)
} else {
let prev_len = self.alloced.as_ref().cap;
let (prev_layout, _) = Self::layout(prev_len);
(alloc::realloc(self.alloced.as_ptr() as _, prev_layout, layout.size()), prev_len)
}
};
unsafe {
MaybeUninit::fill(
core::slice::from_raw_parts_mut(
ptr.add(off).cast::<MaybeUninit<usize>>().add(prev_len),
slot_count - prev_len,
),
0,
);
*ptr.cast::<usize>() = slot_count;
core::ptr::write(self, Self { alloced: Unique::new_unchecked(ptr as _) });
}
}
fn layout(slot_count: usize) -> (core::alloc::Layout, usize) {
unsafe {
core::alloc::Layout::new::<AllocedBitSet>()
.extend(Layout::array::<usize>(slot_count).unwrap_unchecked())
.unwrap_unchecked()
}
}
pub fn iter(&self) -> BitSetIter {
if self.is_inline() {
BitSetIter { index: 0, current: unsafe { self.inline & !Self::FLAG }, remining: &[] }
} else {
let &[current, ref remining @ ..] = self.data_and_len().0 else {
unsafe { unreachable_unchecked() }
};
BitSetIter { index: 0, current, remining }
}
}
pub fn clear(&mut self, len: usize) {
self.reserve(len);
if self.is_inline() {
unsafe { self.inline &= Self::FLAG };
} else {
self.data_mut_and_len().0.fill(0);
}
}
pub fn units<'a>(&'a self, slot: &'a mut usize) -> &'a [usize] {
if self.is_inline() {
*slot = unsafe { self.inline } & !Self::FLAG;
core::slice::from_ref(slot)
} else {
self.data_and_len().0
}
}
pub fn reserve(&mut self, len: usize) {
if len > self.data_and_len().1 {
self.grow(len.next_power_of_two().max(4 * Self::UNIT));
}
}
pub fn units_mut(&mut self) -> Result<&mut [usize], &mut InlineBitSetView> {
if self.is_inline() {
Err(unsafe {
core::mem::transmute::<&mut usize, &mut InlineBitSetView>(&mut self.inline)
})
} else {
Ok(self.data_mut_and_len().0)
}
}
}
pub struct InlineBitSetView(usize);
impl InlineBitSetView {
pub(crate) fn add_mask(&mut self, tmp: usize) {
debug_assert!(tmp & BitSet::FLAG == 0);
self.0 |= tmp;
}
}
pub struct BitSetIter<'a> {
index: usize,
current: usize,
remining: &'a [usize],
}
impl Iterator for BitSetIter<'_> {
type Item = usize;
fn next(&mut self) -> Option<Self::Item> {
while self.current == 0 {
self.current = *self.remining.take_first()?;
self.index += 1;
}
let sub_idx = self.current.trailing_zeros() as usize;
self.current &= self.current - 1;
Some(self.index * BitSet::UNIT + sub_idx)
}
}
struct AllocedBitSet {
cap: usize,
data: [usize; 0],
}
#[cfg(test)]
#[test]
fn test_small_bit_set() {
use std::vec::Vec;
let mut sv = BitSet::default();
sv.set(10);
debug_assert!(sv.get(10));
sv.set(100);
debug_assert!(sv.get(100));
sv.set(10000);
debug_assert!(sv.get(10000));
debug_assert_eq!(sv.iter().collect::<Vec<_>>(), &[10, 100, 10000]);
sv.clear(10000);
debug_assert_eq!(sv.iter().collect::<Vec<_>>(), &[]);
}
pub union Vc {
inline: InlineVc,
alloced: AllocedVc,
}
impl Default for Vc {
fn default() -> Self {
Vc { inline: InlineVc { elems: MaybeUninit::uninit(), cap: Default::default() } }
}
}
impl Debug for Vc {
fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result {
self.as_slice().fmt(f)
}
}
impl FromIterator<Nid> for Vc {
fn from_iter<T: IntoIterator<Item = Nid>>(iter: T) -> Self {
let mut slf = Self::default();
for i in iter {
slf.push(i);
}
slf
}
}
const INLINE_ELEMS: usize = VC_SIZE / 2 - 1;
const VC_SIZE: usize = 16;
impl Vc {
fn is_inline(&self) -> bool {
unsafe { self.inline.cap <= INLINE_ELEMS as Nid }
}
fn layout(&self) -> Option<core::alloc::Layout> {
unsafe {
self.is_inline().not().then(|| {
core::alloc::Layout::array::<Nid>(self.alloced.cap as _).unwrap_unchecked()
})
}
}
pub fn len(&self) -> usize {
unsafe {
if self.is_inline() {
self.inline.cap as _
} else {
self.alloced.len as _
}
}
}
fn len_mut(&mut self) -> &mut Nid {
unsafe {
if self.is_inline() {
&mut self.inline.cap
} else {
&mut self.alloced.len
}
}
}
fn as_ptr(&self) -> *const Nid {
unsafe {
match self.is_inline() {
true => self.inline.elems.as_ptr().cast(),
false => self.alloced.base.as_ptr(),
}
}
}
fn as_mut_ptr(&mut self) -> *mut Nid {
unsafe {
match self.is_inline() {
true => self.inline.elems.as_mut_ptr().cast(),
false => self.alloced.base.as_ptr(),
}
}
}
pub fn as_slice(&self) -> &[Nid] {
unsafe { core::slice::from_raw_parts(self.as_ptr(), self.len()) }
}
fn as_slice_mut(&mut self) -> &mut [Nid] {
unsafe { core::slice::from_raw_parts_mut(self.as_mut_ptr(), self.len()) }
}
pub fn push(&mut self, value: Nid) {
if let Some(layout) = self.layout()
&& unsafe { self.alloced.len == self.alloced.cap }
{
unsafe {
self.alloced.cap *= 2;
self.alloced.base = Unique::new_unchecked(
alloc::realloc(
self.alloced.base.as_ptr().cast(),
layout,
self.alloced.cap as usize * core::mem::size_of::<Nid>(),
)
.cast(),
);
}
} else if self.len() == INLINE_ELEMS {
unsafe {
let mut allcd =
Self::alloc((self.inline.cap + 1).next_power_of_two() as _, self.len());
core::ptr::copy_nonoverlapping(self.as_ptr(), allcd.as_mut_ptr(), self.len());
*self = allcd;
}
}
unsafe {
*self.len_mut() += 1;
self.as_mut_ptr().add(self.len() - 1).write(value);
}
}
unsafe fn alloc(cap: usize, len: usize) -> Self {
debug_assert!(cap > INLINE_ELEMS);
let layout = unsafe { core::alloc::Layout::array::<Nid>(cap).unwrap_unchecked() };
let alloc = unsafe { alloc::alloc(layout) };
unsafe {
Vc {
alloced: AllocedVc {
base: Unique::new_unchecked(alloc.cast()),
len: len as _,
cap: cap as _,
},
}
}
}
pub fn swap_remove(&mut self, index: usize) {
let len = self.len() - 1;
self.as_slice_mut().swap(index, len);
*self.len_mut() -= 1;
}
pub fn remove(&mut self, index: usize) {
self.as_slice_mut().copy_within(index + 1.., index);
*self.len_mut() -= 1;
}
}
impl Drop for Vc {
fn drop(&mut self) {
if let Some(layout) = self.layout() {
unsafe {
alloc::dealloc(self.alloced.base.as_ptr().cast(), layout);
}
}
}
}
impl Clone for Vc {
fn clone(&self) -> Self {
self.as_slice().into()
}
}
impl IntoIterator for Vc {
type IntoIter = VcIntoIter;
type Item = Nid;
fn into_iter(self) -> Self::IntoIter {
VcIntoIter { start: 0, end: self.len(), vc: self }
}
}
pub struct VcIntoIter {
start: usize,
end: usize,
vc: Vc,
}
impl Iterator for VcIntoIter {
type Item = Nid;
fn next(&mut self) -> Option<Self::Item> {
if self.start == self.end {
return None;
}
let ret = unsafe { core::ptr::read(self.vc.as_slice().get_unchecked(self.start)) };
self.start += 1;
Some(ret)
}
fn size_hint(&self) -> (usize, Option<usize>) {
let len = self.end - self.start;
(len, Some(len))
}
}
impl DoubleEndedIterator for VcIntoIter {
fn next_back(&mut self) -> Option<Self::Item> {
if self.start == self.end {
return None;
}
self.end -= 1;
Some(unsafe { core::ptr::read(self.vc.as_slice().get_unchecked(self.end)) })
}
}
impl ExactSizeIterator for VcIntoIter {}
impl<const SIZE: usize> From<[Nid; SIZE]> for Vc {
fn from(value: [Nid; SIZE]) -> Self {
value.as_slice().into()
}
}
impl<'a> From<&'a [Nid]> for Vc {
fn from(value: &'a [Nid]) -> Self {
if value.len() <= INLINE_ELEMS {
let mut dflt = Self::default();
unsafe {
core::ptr::copy_nonoverlapping(value.as_ptr(), dflt.as_mut_ptr(), value.len())
};
dflt.inline.cap = value.len() as _;
dflt
} else {
let mut allcd = unsafe { Self::alloc(value.len(), value.len()) };
unsafe {
core::ptr::copy_nonoverlapping(value.as_ptr(), allcd.as_mut_ptr(), value.len())
};
allcd
}
}
}
impl Deref for Vc {
type Target = [Nid];
fn deref(&self) -> &Self::Target {
self.as_slice()
}
}
impl DerefMut for Vc {
fn deref_mut(&mut self) -> &mut Self::Target {
self.as_slice_mut()
}
}
#[derive(Clone, Copy)]
#[repr(C)]
struct InlineVc {
cap: Nid,
elems: MaybeUninit<[Nid; INLINE_ELEMS]>,
}
#[derive(Clone, Copy)]
#[repr(C)]
struct AllocedVc {
cap: Nid,
len: Nid,
base: Unique<Nid>,
}
pub trait Ent: Copy {
fn new(index: usize) -> Self;
fn index(self) -> usize;
}
pub struct EntVec<K: Ent, T> {
data: ::alloc::vec::Vec<T>,
k: PhantomData<fn(K)>,
}
impl<K: Ent, T> Default for EntVec<K, T> {
fn default() -> Self {
Self { data: Default::default(), k: PhantomData }
}
}
impl<K: Ent, T> EntVec<K, T> {
pub fn clear(&mut self) {
self.data.clear();
}
pub fn is_empty(&self) -> bool {
self.data.is_empty()
}
pub fn len(&self) -> usize {
self.data.len()
}
pub fn push(&mut self, value: T) -> K {
let k = K::new(self.data.len());
self.data.push(value);
k
}
pub fn next(&self, index: K) -> Option<&T> {
self.data.get(index.index() + 1)
}
pub fn shadow(&mut self, len: usize)
where
T: Default,
{
if self.data.len() < len {
self.data.resize_with(len, Default::default);
}
}
pub fn iter(&self) -> core::slice::Iter<T> {
self.data.iter()
}
}
impl<K: Ent, T> core::ops::Index<K> for EntVec<K, T> {
type Output = T;
fn index(&self, index: K) -> &Self::Output {
&self.data[index.index()]
}
}
impl<K: Ent, T> core::ops::IndexMut<K> for EntVec<K, T> {
fn index_mut(&mut self, index: K) -> &mut Self::Output {
&mut self.data[index.index()]
}
}
macro_rules! decl_ent {
($(
$vis:vis struct $name:ident($index:ty);
)*) => {$(
#[derive(Clone, Copy, PartialEq, Eq, PartialOrd, Ord, Hash, Debug)]
$vis struct $name($index);
impl crate::utils::Ent for $name {
fn new(index: usize) -> Self {
Self(index as $index)
}
fn index(self) -> usize {
self.0 as _
}
}
impl core::fmt::Display for $name {
fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result {
write!(f, concat!(stringify!($name), "{}"), self.0)
}
}
)*};
}
pub(crate) use decl_ent;

48
lang/tests/son_tests_advanced_floating_point_arithmetic.txt
View file

@ -1,48 +0,0 @@
main:
ADDI64 r254, r254, -24d
ST r31, r254, 0a, 24h
LI32 r32, 1148846080w
CP r2, r32
JAL r31, r0, :sin
CP r33, r1
FMUL32 r32, r33, r32
FTI32 r32, r32, 1b
CP r1, r32
LD r31, r254, 0a, 24h
ADDI64 r254, r254, 24d
JALA r0, r31, 0a
sin:
CP r13, r2
LI32 r14, 1124073472w
LI32 r15, 1078530011w
FMUL32 r14, r13, r14
FDIV32 r14, r14, r15
FTI32 r14, r14, 1b
ANDI r15, r14, 255d
ITF64 r16, r14
MULI64 r15, r15, 4d
LRA r17, r0, :sin_table
LI32 r18, 1086918619w
FC64T32 r16, r16, 1b
ADDI64 r14, r14, 64d
ADD64 r15, r17, r15
LI32 r19, 1132462080w
FMUL32 r16, r16, r18
ANDI r14, r14, 255d
LI32 r18, 1056964608w
LD r15, r15, 0a, 4h
FDIV32 r16, r16, r19
MULI64 r14, r14, 4d
FMUL32 r18, r15, r18
FSUB32 r13, r13, r16
ADD64 r14, r17, r14
FMUL32 r16, r13, r18
LD r14, r14, 0a, 4h
FSUB32 r14, r14, r16
FMUL32 r13, r14, r13
FADD32 r13, r15, r13
CP r1, r13
JALA r0, r31, 0a
code size: 1315
ret: 826
status: Ok(())

6
lang/tests/son_tests_aliasing_overoptimization.txt
View file

@ -1,6 +0,0 @@
main:
CP r1, r0
JALA r0, r31, 0a
code size: 22
ret: 0
status: Ok(())

6
lang/tests/son_tests_arithmetic.txt
View file

@ -1,6 +0,0 @@
main:
CP r1, r0
JALA r0, r31, 0a
code size: 22
ret: 0
status: Ok(())

32
lang/tests/son_tests_arrays.txt
View file

@ -1,32 +0,0 @@
main:
ADDI64 r254, r254, -56d
ST r31, r254, 24a, 32h
LI64 r32, 1d
ADDI64 r33, r254, 0d
ST r32, r254, 0a, 8h
LI64 r34, 2d
ST r34, r254, 8a, 8h
LI64 r34, 4d
ST r34, r254, 16a, 8h
CP r2, r33
JAL r31, r0, :pass
CP r33, r1
ADD64 r32, r33, r32
CP r1, r32
LD r31, r254, 24a, 32h
ADDI64 r254, r254, 56d
JALA r0, r31, 0a
pass:
CP r13, r2
LD r14, r13, 8a, 8h
MULI64 r15, r14, 8d
LD r16, r13, 0a, 8h
ADD64 r13, r15, r13
ADD64 r14, r14, r16
LD r13, r13, 0a, 8h
ADD64 r13, r13, r14
CP r1, r13
JALA r0, r31, 0a
code size: 246
ret: 8
status: Ok(())

8
lang/tests/son_tests_big_array_crash.txt
View file

@ -1,8 +0,0 @@
main:
LRA r13, r0, :sin_table
LD r13, r13, 80a, 8h
CP r1, r13
JALA r0, r31, 0a
code size: 770
ret: 1736
status: Ok(())

14
lang/tests/son_tests_branch_assignments.txt
View file

@ -1,14 +0,0 @@
main:
CP r14, r2
LI64 r13, 1d
JNE r14, r13, :0
JMP :1
0: JNE r14, r0, :2
LI64 r13, 2d
JMP :1
2: LI64 r13, 3d
1: CP r1, r13
JALA r0, r31, 0a
code size: 75
ret: 2
status: Ok(())

32
lang/tests/son_tests_c_strings.txt
View file

@ -1,32 +0,0 @@
main:
ADDI64 r254, r254, -24d
ST r31, r254, 0a, 24h
LRA r32, r0, :"abඞ\n\r\t56789\0"
CP r2, r32
JAL r31, r0, :str_len
CP r32, r1
LRA r33, r0, :"fff\0"
CP r2, r33
JAL r31, r0, :str_len
CP r33, r1
ADD64 r32, r33, r32
CP r1, r32
LD r31, r254, 0a, 24h
ADDI64 r254, r254, 24d
JALA r0, r31, 0a
str_len:
CP r15, r2
CP r14, r0
CP r13, r14
2: LD r16, r15, 0a, 1h
ANDI r16, r16, 255d
JNE r16, r14, :0
CP r1, r13
JMP :1
0: ADDI64 r15, r15, 1d
ADDI64 r13, r13, 1d
JMP :2
1: JALA r0, r31, 0a
code size: 216
ret: 16
status: Ok(())

13
lang/tests/son_tests_comments.txt
View file

@ -1,13 +0,0 @@
foo:
JALA r0, r31, 0a
main:
ADDI64 r254, r254, -8d
ST r31, r254, 0a, 8h
JAL r31, r0, :foo
CP r1, r0
LD r31, r254, 0a, 8h
ADDI64 r254, r254, 8d
JALA r0, r31, 0a
code size: 88
ret: 0
status: Ok(())

8
lang/tests/son_tests_comptime_function_from_another_file.txt
View file

@ -1,8 +0,0 @@
main:
LRA r13, r0, :a
LD r13, r13, 0a, 8h
CP r1, r13
JALA r0, r31, 0a
code size: 50
ret: 50
status: Ok(())

8
lang/tests/son_tests_comptime_min_reg_leak.txt
View file

@ -1,8 +0,0 @@
main:
LRA r13, r0, :a
LD r13, r13, 0a, 8h
CP r1, r13
JALA r0, r31, 0a
code size: 50
ret: 50
status: Ok(())

19
lang/tests/son_tests_conditional_stores.txt
View file

@ -1,19 +0,0 @@
cond:
CP r1, r0
JALA r0, r31, 0a
main:
ADDI64 r254, r254, -24d
ST r31, r254, 0a, 24h
JAL r31, r0, :cond
CP r33, r1
CP r32, r0
JNE r33, r32, :0
JMP :1
0: LI64 r32, 2d
1: CP r1, r32
LD r31, r254, 0a, 24h
ADDI64 r254, r254, 24d
JALA r0, r31, 0a
code size: 117
ret: 0
status: Ok(())

6
lang/tests/son_tests_const_folding_with_arg.txt
View file

@ -1,6 +0,0 @@
main:
CP r1, r0
JALA r0, r31, 0a
code size: 22
ret: 0
status: Ok(())

7
lang/tests/son_tests_constants.txt
View file

@ -1,7 +0,0 @@
main:
LI32 r13, 69w
CP r1, r13
JALA r0, r31, 0a
code size: 28
ret: 69
status: Ok(())

6
lang/tests/son_tests_dead_code_in_loop.txt
View file

@ -1,6 +0,0 @@
main:
CP r1, r0
JALA r0, r31, 0a
code size: 22
ret: 0
status: Ok(())

19
lang/tests/son_tests_defer.txt
View file

@ -1,19 +0,0 @@
main:
LI64 r15, 3d
LI64 r16, 10d
CP r14, r0
CP r13, r14
3: JNE r13, r16, :0
LI64 r14, -10d
ADD64 r14, r13, r14
CP r1, r14
JMP :1
0: DIRU64 r0, r17, r13, r15
JNE r17, r14, :2
JMP :2
2: ADDI64 r13, r13, 1d
JMP :3
1: JALA r0, r31, 0a
code size: 103
ret: 0
status: Ok(())

Some files were not shown because too many files have changed in this diff Show more