Files
regorus/tests/rvm/vm/suites/predefined.yaml
Anand Krishnamoorthi 49bd3c22f3 feat!: add Rego Virtual Machine (RVM) implementation (#495)
* feat!: add Rego Virtual Machine (RVM) implementation

This commit introduces a register-based virtual machine for executing Rego
policies with bytecode-style instructions. Unlike the existing tree-walking
interpreter, the RVM compiles policies into instruction sequences that operate
on virtual registers, offering better performance and optimization potential.

Core Components:

Instruction Set Architecture:
- Define instruction types for data operations, control flow, and builtins
- Implement instruction parameter encoding and display formatting
- Add instruction parser with comprehensive test coverage

Virtual Machine Engine:
- Register-based execution model with program counter management
- Loop execution supporting iterators, comprehensions, and quantifiers
- Function call handling with argument evaluation and context management
- Rule evaluation with default value resolution and virtual data support
- Arithmetic and comparison operation implementations

Program Representation:
- Program listing builder with instruction sequencing
- Rule tree construction for organizing policy rules
- Binary and JSON serialization for compiled programs
- Recompilation support for program modification

Testing Infrastructure:
- Extensive YAML test suites covering all VM features
- Rust unit tests for VM execution and instruction parsing
- Test suites for loops, comprehensions, builtins, and control flow

BREAKING CHANGE: Introduces new VM execution path alongside interpreter

Signed-off-by: Anand Krishnamoorthi <anakrish@microsoft.com>

* docs: add detailed RVM architecture references

Introduce architecture.md explaining program artifacts, serialization, and runtime subsystems.
Document the full opcode catalog in instruction-set.md, including operands, parameter tables, and outcomes.
Walk through execution flow, stacks, and operational guidance in vm-runtime.md, tying the runtime to the new architecture docs.

Signed-off-by: Anand Krishnamoorthi <anakrish@microsoft.com>

---------

Signed-off-by: Anand Krishnamoorthi <anakrish@microsoft.com>
2025-11-14 11:43:19 -06:00

166 lines
5.6 KiB
YAML

# Copyright (c) Microsoft Corporation.
# Licensed under the MIT License.
# Predefined Global Bindings Test Suite
# Tests Rego's predefined data and input global bindings
# These bindings are always available in Rego policies
cases:
- note: load_data_basic
description: Test loading global data object
data:
users: ["alice", "bob"]
config:
debug: true
timeout: 30
input: null
literals: ["users"]
instructions:
- "LoadData { dest: 0 }"
- "Load { dest: 1, literal_idx: 0 }" # Load "users" literal
- "Index { dest: 2, container: 0, key: 1 }" # data.users
- "Return { value: 2 }"
want_result: ["alice", "bob"]
- note: load_input_basic
description: Test loading global input object
data: null
input:
request:
method: "GET"
path: "/api/users"
user:
id: 123
role: "admin"
literals: ["request", "method"]
instructions:
- "LoadInput { dest: 0 }"
- "Load { dest: 1, literal_idx: 0 }" # Load "request" literal
- "Index { dest: 2, container: 0, key: 1 }" # input.request
- "Load { dest: 3, literal_idx: 1 }" # Load "method" literal
- "Index { dest: 4, container: 2, key: 3 }" # input.request.method
- "Return { value: 4 }"
want_result: "GET"
- note: data_and_input_combined
description: Test using both data and input in same expression
data:
permissions:
admin: ["read", "write", "delete"]
user: ["read"]
input:
user:
role: "admin"
literals: ["permissions", "user", "role"]
instructions:
- "LoadData { dest: 0 }" # Load data
- "LoadInput { dest: 1 }" # Load input
- "Load { dest: 2, literal_idx: 1 }" # Load "user" literal
- "Index { dest: 3, container: 1, key: 2 }" # input.user
- "Load { dest: 4, literal_idx: 2 }" # Load "role" literal
- "Index { dest: 5, container: 3, key: 4 }" # input.user.role
- "Load { dest: 6, literal_idx: 0 }" # Load "permissions" literal
- "Index { dest: 7, container: 0, key: 6 }" # data.permissions
- "Index { dest: 8, container: 7, key: 5 }" # data.permissions[input.user.role]
- "Return { value: 8 }"
want_result: ["read", "write", "delete"]
- note: data_null_handling
description: Test behavior when data is null
data: null
input:
test: "value"
literals: []
instructions:
- "LoadData { dest: 0 }"
- "Return { value: 0 }"
want_result: null
- note: input_null_handling
description: Test behavior when input is null
data:
test: "value"
input: null
literals: []
instructions:
- "LoadInput { dest: 0 }"
- "Return { value: 0 }"
want_result: null
- note: nested_data_access
description: Test deep nested data access
data:
api:
v1:
endpoints:
users: "/api/v1/users"
posts: "/api/v1/posts"
input: null
literals: ["api", "v1", "endpoints", "users"]
instructions:
- "LoadData { dest: 0 }"
- "Load { dest: 1, literal_idx: 0 }" # "api"
- "Index { dest: 2, container: 0, key: 1 }" # data.api
- "Load { dest: 3, literal_idx: 1 }" # "v1"
- "Index { dest: 4, container: 2, key: 3 }" # data.api.v1
- "Load { dest: 5, literal_idx: 2 }" # "endpoints"
- "Index { dest: 6, container: 4, key: 5 }" # data.api.v1.endpoints
- "Load { dest: 7, literal_idx: 3 }" # "users"
- "Index { dest: 8, container: 6, key: 7 }" # data.api.v1.endpoints.users
- "Return { value: 8 }"
want_result: "/api/v1/users"
- note: array_access_with_input
description: Test array indexing with input values
data:
colors: ["red", "green", "blue"]
input:
selected_index: 1
literals: ["colors", "selected_index"]
instructions:
- "LoadData { dest: 0 }"
- "LoadInput { dest: 1 }"
- "Load { dest: 2, literal_idx: 0 }" # "colors"
- "Index { dest: 3, container: 0, key: 2 }" # data.colors
- "Load { dest: 4, literal_idx: 1 }" # "selected_index"
- "Index { dest: 5, container: 1, key: 4 }" # input.selected_index
- "Index { dest: 6, container: 3, key: 5 }" # data.colors[input.selected_index]
- "Return { value: 6 }"
want_result: "green"
- note: data_only_access
description: Test accessing data when input is not needed
data:
settings:
theme: "dark"
notifications: true
input: null
literals: ["settings", "theme"]
instructions:
- "LoadData { dest: 0 }"
- "Load { dest: 1, literal_idx: 0 }" # "settings"
- "Index { dest: 2, container: 0, key: 1 }" # data.settings
- "Load { dest: 3, literal_idx: 1 }" # "theme"
- "Index { dest: 4, container: 2, key: 3 }" # data.settings.theme
- "Return { value: 4 }"
want_result: "dark"
- note: input_only_access
description: Test accessing input when data is not needed
data: null
input:
request:
headers:
authorization: "Bearer token123"
literals: ["request", "headers", "authorization"]
instructions:
- "LoadInput { dest: 0 }"
- "Load { dest: 1, literal_idx: 0 }" # "request"
- "Index { dest: 2, container: 0, key: 1 }" # input.request
- "Load { dest: 3, literal_idx: 1 }" # "headers"
- "Index { dest: 4, container: 2, key: 3 }" # input.request.headers
- "Load { dest: 5, literal_idx: 2 }" # "authorization"
- "Index { dest: 6, container: 4, key: 5 }" # input.request.headers.authorization
- "Return { value: 6 }"
want_result: "Bearer token123"