Files
ladybird/Libraries/LibJS/Bytecode/Validator.cpp
Andreas Kling 0b8fbc03ef LibJS: Add per-field bytecode validation generated from Bytecode.def
Pass 2 of the validator now runs a per-instruction check that walks
each opcode's fields and verifies every reference points somewhere
sensible. Operand indices, label addresses, identifier/string/
property-key/regex table indices, cache indices, and trailing
operand arrays are all bound-checked against the values the C++
side carries on the Executable. Fields whose bound depends on an
enum variant count or other type information not present in
Bytecode.def are left for a follow-up.

The codegen lives in build.rs and reuses the existing layout
machinery from the bytecode_def crate, so each opcode gets a match
arm whose body reads each field at its known byte offset and calls
the right hand-written validate_* helper. Variable-length
instructions cross-check the count field against m_length before
iterating the trailing array, which guards against an attacker
sneaking a count that walks off the end of the instruction.

Note that the encoded operand format is a flat u32 index into the
runtime [registers | locals | constants | arguments] array, since
Operand::offset_index_by zeroes the 3-bit type tag during assembly.
The validator therefore range-checks the flat index rather than
reading the type tag and dispatching per kind.

The argument-count upper bound isn't tracked on Executable yet, so
arguments remain effectively unbounded; tightening that bound is
left for a later commit.

Cache pointer fields are validated only when before_cache_fixup is
true, since after the fixup pass they hold real pointers and must
be left alone. NewFunction and NewClass have plain u32 fields for
shared-function-data and class-blueprint indices; those are
recognized by name in the codegen so the indices still get
range-checked.

The error category enum is renumbered to drop the per-operand-kind
codes, since at the bytecode level we no longer differentiate.
2026-05-03 08:43:19 +02:00

107 lines
4.8 KiB
C++

/*
* Copyright (c) 2026-present, the Ladybird developers.
*
* SPDX-License-Identifier: BSD-2-Clause
*/
#include <AK/Debug.h>
#include <AK/Format.h>
#include <AK/NumericLimits.h>
#include <AK/StringView.h>
#include <LibJS/Bytecode/Executable.h>
#include <LibJS/Bytecode/Validator.h>
#include <LibJS/RustFFI.h>
namespace JS::Bytecode {
static StringView validation_error_kind_to_string(JS::FFI::ValidationErrorKind kind)
{
switch (kind) {
case JS::FFI::ValidationErrorKind::Ok:
return "Ok"sv;
case JS::FFI::ValidationErrorKind::BufferNotAligned:
return "BufferNotAligned"sv;
case JS::FFI::ValidationErrorKind::InstructionMisaligned:
return "InstructionMisaligned"sv;
case JS::FFI::ValidationErrorKind::UnknownOpcode:
return "UnknownOpcode"sv;
case JS::FFI::ValidationErrorKind::TruncatedInstruction:
return "TruncatedInstruction"sv;
case JS::FFI::ValidationErrorKind::InvalidLength:
return "InvalidLength"sv;
case JS::FFI::ValidationErrorKind::OperandOutOfRange:
return "OperandOutOfRange"sv;
case JS::FFI::ValidationErrorKind::OperandInvalid:
return "OperandInvalid"sv;
case JS::FFI::ValidationErrorKind::LabelNotAtInstructionBoundary:
return "LabelNotAtInstructionBoundary"sv;
case JS::FFI::ValidationErrorKind::IdentifierIndexOutOfRange:
return "IdentifierIndexOutOfRange"sv;
case JS::FFI::ValidationErrorKind::StringIndexOutOfRange:
return "StringIndexOutOfRange"sv;
case JS::FFI::ValidationErrorKind::PropertyKeyIndexOutOfRange:
return "PropertyKeyIndexOutOfRange"sv;
case JS::FFI::ValidationErrorKind::RegexIndexOutOfRange:
return "RegexIndexOutOfRange"sv;
case JS::FFI::ValidationErrorKind::PropertyLookupCacheIndexOutOfRange:
return "PropertyLookupCacheIndexOutOfRange"sv;
case JS::FFI::ValidationErrorKind::GlobalVariableCacheIndexOutOfRange:
return "GlobalVariableCacheIndexOutOfRange"sv;
case JS::FFI::ValidationErrorKind::TemplateObjectCacheIndexOutOfRange:
return "TemplateObjectCacheIndexOutOfRange"sv;
case JS::FFI::ValidationErrorKind::ObjectShapeCacheIndexOutOfRange:
return "ObjectShapeCacheIndexOutOfRange"sv;
case JS::FFI::ValidationErrorKind::ObjectPropertyIteratorCacheIndexOutOfRange:
return "ObjectPropertyIteratorCacheIndexOutOfRange"sv;
case JS::FFI::ValidationErrorKind::SharedFunctionDataIndexOutOfRange:
return "SharedFunctionDataIndexOutOfRange"sv;
case JS::FFI::ValidationErrorKind::ClassBlueprintIndexOutOfRange:
return "ClassBlueprintIndexOutOfRange"sv;
case JS::FFI::ValidationErrorKind::EnumOutOfRange:
return "EnumOutOfRange"sv;
}
VERIFY_NOT_REACHED();
}
ErrorOr<void> validate_bytecode(Executable const& executable, CacheState cache_state)
{
JS::FFI::FFIValidatorBounds bounds {
.number_of_registers = executable.number_of_registers,
.number_of_locals = static_cast<u32>(executable.local_variable_names.size()),
.number_of_constants = static_cast<u32>(executable.constants.size()),
// Argument count isn't tracked on Executable yet; per-instruction
// argument-index checks land in a follow-up commit.
.number_of_arguments = NumericLimits<u32>::max(),
.identifier_table_size = static_cast<u32>(executable.identifier_table->identifiers().size()),
.string_table_size = static_cast<u32>(executable.string_table->size()),
.property_key_table_size = static_cast<u32>(executable.property_key_table->property_keys().size()),
// The regex table is not consulted at runtime; m_regex_index fields
// are skipped during validation.
.regex_table_size = 0,
.property_lookup_cache_count = static_cast<u32>(executable.property_lookup_caches.size()),
.global_variable_cache_count = static_cast<u32>(executable.global_variable_caches.size()),
.template_object_cache_count = static_cast<u32>(executable.template_object_caches.size()),
.object_shape_cache_count = static_cast<u32>(executable.object_shape_caches.size()),
.object_property_iterator_cache_count = static_cast<u32>(executable.object_property_iterator_caches.size()),
.class_blueprint_count = static_cast<u32>(executable.class_blueprints.size()),
.shared_function_data_count = static_cast<u32>(executable.shared_function_data.size()),
.before_cache_fixup = cache_state == CacheState::BeforeFixup,
};
JS::FFI::FFIValidationError error {};
auto ok = rust_validate_bytecode(
executable.bytecode.data(),
executable.bytecode.size(),
&bounds,
&error);
if (ok)
return {};
auto kind = validation_error_kind_to_string(error.kind);
dbgln("Bytecode validation failed at offset {} (opcode {}): {}",
error.offset, error.opcode, kind);
return AK::Error::from_string_view(kind);
}
}