Files
endorphin-aster-vm/crates/core/src/eval.rs
T
codex-bot f77b8370ea
Verify databases and deploy Aster VM / verify-and-deploy (push) Successful in 7m34s
refactor: extract core objects into a standalone package
2026-10-19 13:33:24 +08:00

571 lines
23 KiB
Rust

use crate::frame::StackEntry;
use crate::{
CompareOp, EndorCellObject, EndorCodeObject, EndorFrame, EndorFunctionObject,
EndorStringObject, ExecutionLimits, ExecutionLocation, Instruction, ObjectRef, Opcode, Value,
Vm, VmError,
};
fn invalid(offset: usize, reason: &'static str) -> VmError {
VmError::InvalidBytecode { offset, reason }
}
impl Vm {
/// Execute a code object in a globals dictionary. Like CPython's EvalCode
/// entry path, this constructs a temporary function and enters its frame.
/// Object results own one external reference: release_value() when done.
pub fn execute(&mut self, code: ObjectRef, globals: ObjectRef) -> Result<Value, VmError> {
self.execute_with_limits(code, globals, ExecutionLimits::default())
}
pub fn execute_with_limits(
&mut self,
code: ObjectRef,
globals: ObjectRef,
limits: ExecutionLimits,
) -> Result<Value, VmError> {
self.last_traceback.clear();
let name = self
.payload::<EndorCodeObject>(code, "code")?
.code()
.name()
.to_owned();
let function = self.new_function(name, code, globals, Vec::new(), Vec::new())?;
let result = self.call_with_limits(function, &[], limits);
self.release(function)?;
result
}
/// Dispatch both language and host functions. Arguments are borrowed;
/// every Object result owns one external reference, including native
/// callbacks that return one of their borrowed arguments.
pub fn call(&mut self, function: ObjectRef, arguments: &[Value]) -> Result<Value, VmError> {
self.call_with_limits(function, arguments, ExecutionLimits::default())
}
pub fn call_with_limits(
&mut self,
function: ObjectRef,
arguments: &[Value],
limits: ExecutionLimits,
) -> Result<Value, VmError> {
self.last_traceback.clear();
if !self
.object(function)?
.payload()
.as_any()
.is::<EndorFunctionObject>()
{
return self.invoke_native(function, arguments);
}
if limits.max_frames == 0 {
return Err(VmError::ExecutionLimit("frames"));
}
let frame = self.prepare_frame(function, arguments)?;
let mut frames = vec![frame];
let result = self.eval_frames(&mut frames, limits);
if result.is_err() {
self.last_traceback = frames
.iter()
.map(|frame| ExecutionLocation {
function: frame.name.clone(),
filename: frame.executable.filename().into(),
first_line: frame.executable.first_line(),
instruction_offset: frame.current_offset,
})
.collect();
}
while let Some(frame) = frames.pop() {
self.clear_frame(frame);
}
result
}
/// Outer-to-inner execution locations from the last failed call/execute.
/// These are copied metadata, not heap references or language exceptions.
pub fn last_traceback(&self) -> &[ExecutionLocation] {
&self.last_traceback
}
pub fn release_value(&mut self, value: Value) -> Result<(), VmError> {
if let Value::Object(reference) = value {
self.release(reference)?;
}
Ok(())
}
fn retain_value(&mut self, value: &Value) -> Result<(), VmError> {
self.validate_value(value)?;
if let Value::Object(reference) = value {
self.retain(*reference)?;
}
Ok(())
}
fn drop_root(&mut self, value: Value) {
self.release_value(value)
.expect("execution owns every object root it releases");
}
fn clear_frame(&mut self, frame: EndorFrame) {
for entry in frame.stack {
if let StackEntry::Value(value) = entry {
self.drop_root(value);
}
}
for value in frame.localsplus.into_iter().flatten() {
self.drop_root(value);
}
self.release(frame.function)
.expect("frame owns its function root");
}
fn prepare_frame(
&mut self,
function: ObjectRef,
arguments: &[Value],
) -> Result<EndorFrame, VmError> {
let data = self
.payload::<EndorFunctionObject>(function, "function")?
.clone();
let executable = self
.payload::<EndorCodeObject>(data.code(), "code")?
.shared_code();
let maximum = executable.parameters().len();
let required = maximum - data.defaults().len();
if arguments.len() < required || arguments.len() > maximum {
return Err(VmError::ArgumentCount {
name: data.name().into(),
required,
maximum,
provided: arguments.len(),
});
}
for value in arguments {
self.validate_value(value)?;
}
self.retain(function)?;
let mut frame = EndorFrame {
function,
previous: None,
code: data.code(),
globals: data.globals(),
builtins: data.builtins(),
name: data.name().into(),
instruction_offset: 0,
current_offset: 0,
localsplus: vec![None; executable.slot_count()],
stack: Vec::with_capacity(executable.stack_size()),
executable,
};
let initialized = (|| -> Result<(), VmError> {
let defaults = data.defaults().iter().skip(arguments.len() - required);
for (slot, value) in frame
.localsplus
.iter_mut()
.zip(arguments.iter().chain(defaults))
{
self.retain_value(value)?;
*slot = Some(value.clone());
}
// Captured local cells occupy the original local slots, as in
// CPython's localsplus layout. Free cells follow the local slots.
let local_count = frame.executable.layout().locals.len();
for (index, slot) in frame.localsplus[..local_count].iter_mut().enumerate() {
if frame.executable.is_cell_slot(index) {
let cell = self.new_cell(slot.clone())?;
if let Some(old) = slot.replace(Value::Object(cell)) {
self.drop_root(old);
}
}
}
let first_free = frame.executable.layout().locals.len();
for (index, cell) in data.closure().iter().enumerate() {
self.retain(*cell)?;
frame.localsplus[first_free + index] = Some(Value::Object(*cell));
}
Ok(())
})();
if let Err(error) = initialized {
self.clear_frame(frame);
return Err(error);
}
Ok(frame)
}
fn invoke_native(
&mut self,
function: ObjectRef,
arguments: &[Value],
) -> Result<Value, VmError> {
self.object(function)?;
for argument in arguments {
self.validate_value(argument)?;
}
let result = self.object(function)?.payload().call(arguments)?;
self.retain_value(&result)?;
Ok(result)
}
fn stack_value(frame: &EndorFrame, index: usize) -> Result<Value, VmError> {
match frame.stack.get(index) {
Some(StackEntry::Value(value)) => Ok(value.clone()),
_ => Err(invalid(
frame.current_offset,
"NULL call marker used as a value",
)),
}
}
fn top_value(frame: &EndorFrame) -> Result<Value, VmError> {
Self::stack_value(frame, frame.stack.len() - 1)
}
fn push_borrowed(&mut self, frame: &mut EndorFrame, value: Value) -> Result<(), VmError> {
self.retain_value(&value)?;
frame.stack.push(StackEntry::Value(value));
Ok(())
}
fn discard(&mut self, frame: &mut EndorFrame, count: usize) {
for _ in 0..count {
if let StackEntry::Value(value) = frame.stack.pop().expect("verified stack height") {
self.drop_root(value);
}
}
}
fn cell_slot(&self, frame: &EndorFrame, index: usize) -> Result<ObjectRef, VmError> {
match &frame.localsplus[index] {
Some(Value::Object(reference)) => {
self.payload::<EndorCellObject>(*reference, "cell")?;
Ok(*reference)
}
_ => Err(invalid(
frame.current_offset,
"cell slot is not initialized",
)),
}
}
fn value_is_true(&self, value: &Value) -> Result<bool, VmError> {
match value {
Value::Nil => Ok(false),
Value::Bool(value) => Ok(*value),
Value::Text(value) => Ok(!value.is_empty()),
Value::Number(value) => Ok(!value.is_zero()),
Value::Object(reference) => self.is_true(*reference),
}
}
fn text_value(&self, value: &Value) -> Result<Option<String>, VmError> {
Ok(match value {
Value::Text(text) => Some(text.clone()),
Value::Object(reference) => self
.object(*reference)?
.payload()
.as_any()
.downcast_ref::<EndorStringObject>()
.map(|text| text.as_str().to_owned()),
_ => None,
})
}
fn compare_values(
&self,
left: &Value,
right: &Value,
operation: CompareOp,
) -> Result<bool, VmError> {
if matches!(left, Value::Number(_)) || matches!(right, Value::Number(_)) {
return Err(VmError::UnsupportedOperation("numeric comparison"));
}
if let (Some(left), Some(right)) = (self.text_value(left)?, self.text_value(right)?) {
return Ok(match operation {
CompareOp::Eq => left == right,
CompareOp::Ne => left != right,
CompareOp::Lt => left < right,
CompareOp::Le => left <= right,
CompareOp::Gt => left > right,
CompareOp::Ge => left >= right,
});
}
if let (Value::Object(left), Value::Object(right)) = (left, right) {
return self.compare(*left, *right, operation);
}
match operation {
CompareOp::Eq => Ok(left == right),
CompareOp::Ne => Ok(left != right),
_ => Err(VmError::UnsupportedOperation("ordering")),
}
}
fn build_map(&mut self, frame: &EndorFrame, count: usize) -> Result<ObjectRef, VmError> {
let dictionary = self.new_dict()?;
let result = (|| -> Result<(), VmError> {
let start = frame.stack.len() - count * 2;
for index in 0..count {
let key = Self::stack_value(frame, start + index * 2)?;
let value = Self::stack_value(frame, start + index * 2 + 1)?;
self.dict_set(dictionary, key, value)?;
}
Ok(())
})();
if let Err(error) = result {
self.release(dictionary)?;
return Err(error);
}
Ok(dictionary)
}
fn make_function(&mut self, frame: &EndorFrame, argument: u32) -> Result<ObjectRef, VmError> {
let (default_count, closure_count) = Instruction::function_counts(argument);
let Value::Object(code) = Self::top_value(frame)? else {
return Err(VmError::ObjectKindMismatch("code"));
};
let name = self
.payload::<EndorCodeObject>(code, "code")?
.code()
.name()
.to_owned();
let start = frame.stack.len() - default_count - closure_count - 1;
let defaults = (start..start + default_count)
.map(|index| Self::stack_value(frame, index))
.collect::<Result<Vec<_>, _>>()?;
let closure = (start + default_count..frame.stack.len() - 1)
.map(|index| match Self::stack_value(frame, index)? {
Value::Object(cell) => Ok(cell),
_ => Err(VmError::ObjectKindMismatch("cell")),
})
.collect::<Result<Vec<_>, _>>()?;
// Keep every input root on the stack until allocation has validated
// and retained all function edges. Failure leaves cleanup to the frame.
self.new_function(name, code, frame.globals, defaults, closure)
}
fn eval_frames(
&mut self,
frames: &mut Vec<EndorFrame>,
limits: ExecutionLimits,
) -> Result<Value, VmError> {
let mut executed = 0;
loop {
if executed >= limits.max_instructions {
return Err(VmError::ExecutionLimit("instructions"));
}
executed += 1;
let frame = frames.last_mut().expect("an evaluation frame is active");
let decoded = frame.executable.instruction_at(frame.instruction_offset)?;
frame.current_offset = decoded.offset;
frame.instruction_offset = decoded.next_offset;
let opcode = decoded.instruction.opcode;
let argument = decoded.instruction.argument as usize;
match opcode {
Opcode::Nop => {}
Opcode::LoadConst => {
let value = frame.executable.constants()[argument].clone();
self.push_borrowed(frame, value)?;
}
Opcode::LoadFast => {
let value = frame.localsplus[argument].clone().ok_or_else(|| {
VmError::UnboundLocal(frame.executable.slot_name(argument).into())
})?;
self.push_borrowed(frame, value)?;
}
Opcode::StoreFast => {
let value = Self::top_value(frame)?;
// The stack root is moved into the local slot.
frame.stack.pop();
if let Some(old) = frame.localsplus[argument].replace(value) {
self.drop_root(old);
}
}
Opcode::DeleteFast => {
let value = frame.localsplus[argument].take().ok_or_else(|| {
VmError::UnboundLocal(frame.executable.slot_name(argument).into())
})?;
self.drop_root(value);
}
Opcode::LoadGlobal => {
let name = &frame.executable.layout().names[argument];
let key = Value::Text(name.clone());
let mut value = self.dict_get(frame.globals, &key)?;
if value.is_none()
&& let Some(builtins) = frame.builtins
{
value = self.dict_get(builtins, &key)?;
}
let value = value.ok_or_else(|| VmError::NameNotFound(name.clone()))?;
self.push_borrowed(frame, value)?;
}
Opcode::StoreGlobal => {
let value = Self::top_value(frame)?;
let key = Value::Text(frame.executable.layout().names[argument].clone());
self.dict_set(frame.globals, key, value)?;
self.discard(frame, 1);
}
Opcode::DeleteGlobal => {
let name = &frame.executable.layout().names[argument];
if !self.dict_delete(frame.globals, &Value::Text(name.clone()))? {
return Err(VmError::NameNotFound(name.clone()));
}
}
Opcode::LoadDeref | Opcode::LoadClosure => {
let cell = self.cell_slot(frame, argument)?;
let value = if opcode == Opcode::LoadClosure {
Value::Object(cell)
} else {
self.cell_get(cell).map_err(|error| {
if error == VmError::EmptyCell {
VmError::UnboundLocal(frame.executable.slot_name(argument).into())
} else {
error
}
})?
};
self.push_borrowed(frame, value)?;
}
Opcode::StoreDeref => {
let cell = self.cell_slot(frame, argument)?;
self.cell_set(cell, Self::top_value(frame)?)?;
self.discard(frame, 1);
}
Opcode::DeleteDeref => {
let cell = self.cell_slot(frame, argument)?;
if self.cell_get(cell).is_err() {
return Err(VmError::UnboundLocal(
frame.executable.slot_name(argument).into(),
));
}
self.cell_clear(cell)?;
}
Opcode::PopTop => self.discard(frame, 1),
Opcode::Copy => {
let entry = frame.stack[frame.stack.len() - argument].clone();
if let StackEntry::Value(value) = &entry {
self.retain_value(value)?;
}
frame.stack.push(entry);
}
Opcode::Swap => {
let length = frame.stack.len();
frame.stack.swap(length - 1, length - argument);
}
Opcode::PushNull => frame.stack.push(StackEntry::Null),
Opcode::Call => {
let start = frame.stack.len() - argument - 2;
let Value::Object(function) = Self::stack_value(frame, start)? else {
return Err(VmError::UnsupportedOperation("call"));
};
let mut arguments = Vec::with_capacity(argument + 1);
if let StackEntry::Value(value) = &frame.stack[start + 1] {
arguments.push(value.clone());
}
for index in start + 2..frame.stack.len() {
arguments.push(Self::stack_value(frame, index)?);
}
let language_function = self
.object(function)?
.payload()
.as_any()
.is::<EndorFunctionObject>();
if language_function {
if frames.len() >= limits.max_frames {
return Err(VmError::ExecutionLimit("frames"));
}
let mut callee = self.prepare_frame(function, &arguments)?;
callee.previous = Some(frames.len() - 1);
self.discard(frames.last_mut().unwrap(), argument + 2);
frames.push(callee);
} else {
let value = self.invoke_native(function, &arguments)?;
self.discard(frames.last_mut().unwrap(), argument + 2);
frames
.last_mut()
.unwrap()
.stack
.push(StackEntry::Value(value));
}
}
Opcode::ReturnValue => {
let result = Self::top_value(frame)?;
frame.stack.pop();
self.clear_frame(frames.pop().unwrap());
if let Some(caller) = frames.last_mut() {
caller.stack.push(StackEntry::Value(result));
} else {
return Ok(result);
}
}
Opcode::JumpForward | Opcode::JumpBackward => {
frame.instruction_offset = decoded.jump_target()?
}
Opcode::PopJumpIfFalse | Opcode::PopJumpIfTrue => {
let truth = self.value_is_true(&Self::top_value(frame)?)?;
self.discard(frame, 1);
if truth == (opcode == Opcode::PopJumpIfTrue) {
frame.instruction_offset = decoded.jump_target()?;
}
}
Opcode::ToBool | Opcode::UnaryNot => {
let truth = self.value_is_true(&Self::top_value(frame)?)?;
self.discard(frame, 1);
frame.stack.push(StackEntry::Value(Value::Bool(
if opcode == Opcode::UnaryNot {
!truth
} else {
truth
},
)));
}
Opcode::CompareOp => {
let left = Self::stack_value(frame, frame.stack.len() - 2)?;
let right = Self::top_value(frame)?;
let result = self.compare_values(
&left,
&right,
Instruction::compare_operation(decoded.instruction.argument).unwrap(),
)?;
self.discard(frame, 2);
frame.stack.push(StackEntry::Value(Value::Bool(result)));
}
Opcode::LoadAttr => {
let Value::Object(owner) = Self::top_value(frame)? else {
return Err(VmError::ObjectKindMismatch("object"));
};
let value = self.get_attr(owner, &frame.executable.layout().names[argument])?;
self.retain_value(&value)?;
self.discard(frame, 1);
frame.stack.push(StackEntry::Value(value));
}
Opcode::StoreAttr => {
let Value::Object(owner) = Self::top_value(frame)? else {
return Err(VmError::ObjectKindMismatch("object"));
};
let value = Self::stack_value(frame, frame.stack.len() - 2)?;
self.set_attr(
owner,
frame.executable.layout().names[argument].clone(),
value,
)?;
self.discard(frame, 2);
}
Opcode::BuildMap => {
let dictionary = self.build_map(frame, argument)?;
self.discard(frame, argument * 2);
frame
.stack
.push(StackEntry::Value(Value::Object(dictionary)));
}
Opcode::MakeFunction => {
let function = self.make_function(frame, decoded.instruction.argument)?;
let (defaults, closure) =
Instruction::function_counts(decoded.instruction.argument);
self.discard(frame, defaults + closure + 1);
frame.stack.push(StackEntry::Value(Value::Object(function)));
}
Opcode::ExtendedArg => unreachable!("EXTENDED_ARG was decoded before evaluation"),
}
}
}
}