Files
Drew Newberry c1f2e7189f feat(isolation): implement the RFC 0012 sandbox architecture (#2942)
* feat(isolation): add RFC 0012 backend contract

Signed-off-by: Drew Newberry <385+drew@users.noreply.github.com>

* refactor(isolation): name the interface crate explicitly

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* feat(isolation): expose trusted host gateway

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* docs(agents): inventory the MXC driver

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* feat(isolation): add mediated DNS transport

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(isolation): tighten interface error and digest contracts

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* docs(isolation): remove unrelated driver inventory

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* feat(isolation): define capability-free launch contract

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(isolation): seal confirmed boundary state

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(isolation): validate confirmation for external backend implementations

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(isolation): clarify mediated DNS identity

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* refactor(isolation): generalize loopback connector

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* refactor(isolation): unify typed network mediation

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* feat(isolation): bind launches to sandbox sessions

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(mxc): initialize extended sandbox status

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* feat(isolation): add boundary protocol and Linux primitives

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(isolation): harden signals and separate process status from transport

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(isolation): validate remote confirmation through public contract

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(isolation): validate wire state and propagate snapshot failures

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* test(isolation): import owned agent specification explicitly

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* docs(isolation): describe mediated DNS channel

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(isolation): bound mediation attach without nested retries

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* refactor(isolation): generalize loopback protocol

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* feat(isolation): add transport-neutral session authentication

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* refactor(isolation): separate sandbox backend protocol

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(isolation): harden runtime boundary controls

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* feat(isolation): add terminal boundary operation

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* feat(isolation): split supervisor and sandbox runtimes

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(sandbox): harden boundary isolation and lifecycle ownership

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(sandbox): reject private root redirects and adopt typed errors

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(sandbox): preserve accept thread ownership on musl

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* test(sandbox): isolate credential probes from filtered threads

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(sandbox): return retained exec exit status to independent waiters

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(sandbox): bound network mediation and preserve socket authorization

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(sandbox): bound control admission and retire stale mediation

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* ci(e2e): select migrated drivers per stack layer

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* refactor(sandbox): implement loopback connector

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* feat(isolation): authenticate the Sandbox Protocol

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* feat(supervisor): rotate launch-scoped authentication

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* refactor(sandbox): consume dedicated backend crate

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* test(sandbox): align topology session fixture

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(sandbox): align projected bootstrap bundle

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(auth): validate refreshed credentials before rotation

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(sandbox): fail closed across supervisor disconnects

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(isolation): repair rebased sandbox CI

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* build(runtime): publish separate sandbox and supervisor images

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* feat(config): configure the sandbox runtime image

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(ci): validate sandbox binary linkage

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* refactor(isolation): use backend and runtime terminology

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* refactor(sandbox): use a scratch runtime image

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(ci): refresh schema and dependency policy

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(sandbox): bind reconnects to supervisor process

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* docs: align runtime split operational guidance

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* chore(security): document Kubernetes runtime RBAC

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(isolation): enforce runtime lifecycle invariants

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* feat(compute): identify sandbox start generations

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(server): restore sandbox launch sessions

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(isolation): support authenticated runtime replacement

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(auth): bind sandbox session successors

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(auth): retry pending sandbox successors

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* feat(vm): run the supervisor outside the guest workload

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* refactor(vm): use sandbox backend protocol

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(vm): repair rebase integration

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(vm): use unified build toolchain

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* refactor(vm): use sandbox runtime terminology

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* refactor(vm): own guest network bootstrap

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(vm): expose guest init version

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(vm): select native supervisor artifacts

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(vm): guard guest init Linux symbols

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(vm): scope Linux test imports

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(vm): avoid guest interface casts

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(vm): reconcile admitted sandbox identity

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(vm): share resolved sandbox identity

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(vm): surface host supervisor failures

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(vm): include guest logs on supervisor exit

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(vm): rotate and clean runtime generations

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(vm): make sandbox starts generation-aware

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(vm): rotate restored sandbox sessions

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* refactor(vm): keep shared paths in the base layer

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(vm): bind sandbox session lineage

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* feat(docker): isolate workloads behind the host supervisor

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* feat(docker): rotate launch-scoped authentication

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* refactor(docker): use sandbox backend protocol

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* refactor(docker): use host networking for supervisor

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(docker): preserve host gateway alias resolution

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* feat(docker): use separate sandbox and supervisor images

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(docker): restore startup validation after rebase

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* refactor(docker): name the sandbox runtime directly

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(docker): narrow supervisor CA runtime storage

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(docker): close companion isolation gaps

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* test(docker): align mediated network expectations

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* test(docker): exercise mediated network paths

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(docker): attach supervisor to managed network

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(docker): defer supervisor recovery until gateway is ready

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(docker): make sandbox starts generation-aware

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(docker): rotate restored sandbox sessions

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(docker): preserve workloads during session rotation

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* refactor(docker): remove unrelated configuration RFC changes

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(docker): bind sandbox session lineage

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* feat(kubernetes): add proxy-pod isolation topology

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* refactor(kubernetes): use sandbox backend protocol

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(kubernetes): use stable sandbox service authority

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* feat(kubernetes): split sandbox and supervisor images

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(kubernetes): adapt proxy pods to current runtime APIs

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* refactor(kubernetes): describe the single runtime placement

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* refactor(kubernetes): simplify sandbox orchestration

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(kubernetes): validate deployment prerequisites

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(kubernetes): update Trivy Helm profile inventory

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* test(kubernetes): update Trivy scan inventory count

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(kubernetes): reuse preloaded runtime images in e2e

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(kubernetes): type and clean runtime resources

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(kubernetes): make sandbox restarts recoverable

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(kubernetes): rotate restored sandbox sessions

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(kubernetes): preserve supervisor egress

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(kubernetes): bind sandbox session lineage

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* feat(podman): adopt isolated sandbox and supervisor containers

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(podman): stage bootstrap archives at named volume destinations

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* feat(podman): rotate launch-scoped authentication

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* refactor(podman): use sandbox backend protocol

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* refactor(podman): use host networking for supervisor

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* feat(podman): split sandbox and supervisor images

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(podman): repair rebase integration

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* refactor(podman): name the sandbox runtime directly

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(podman): provision supervisor CA runtime storage

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(podman): address isolation review findings

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(podman): inspect Debian supervisor provenance

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(podman): use libpod-compatible tmpfs options

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(podman): bind verified sandbox runtime binary

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(podman): provide external driver data directory

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(podman): start sandbox before joining user namespace

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(podman): separate supervisor user namespace

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(podman): make sandbox starts generation-aware

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(podman): rotate restored sandbox sessions

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(podman): bind sandbox session lineage

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* perf(isolation): add TCP and DNS benchmark harnesses

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(perf): align benchmark timing and supported protocols

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(perf): report TCP benchmark metrics accurately

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(perf): cancel failed worker startup

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(docker): build matching local supervisor image

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(podman): make local sandbox smoke test runnable

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(kubernetes): wire local sandbox runtime image

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(kubernetes): narrow sandbox service RBAC

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(ci): validate split runtime artifacts

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(isolation): harden runtime session handling

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* feat(supervisor): add standalone network proxy role

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* docs(rfc): remove implementation companion notes

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* refactor(vm): standardize runtime release name

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(vm): pin renamed runtime artifacts

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(auth): persist sandbox runtime identity

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(runtime): restore branch validation

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(isolation): reconcile main after rebase

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(network): close unframed HTTP 1.0 responses

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* chore(isolation): preserve upstream OCSF updates

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(security): close credential and TLS replay paths

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(auth): make sandbox refresh retries idempotent

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

---------

Signed-off-by: Drew Newberry <385+drew@users.noreply.github.com>
Signed-off-by: Drew Newberry <anewberry@nvidia.com>
2026-09-16 00:49:14 +00:00

72 lines
2.0 KiB
TOML

# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
# Docker image build tasks
["build:docker"]
description = "Build all Docker images"
depends = [
"build:docker:gateway",
"build:docker:sandbox",
"build:docker:supervisor",
]
hide = true
["build:docker:ci"]
description = "Build the CI Docker image"
run = "tasks/scripts/docker-build-ci.sh"
hide = true
["build:docker:prebuilt"]
description = "Build and stage Rust binaries consumed by Docker image builds"
run = "tasks/scripts/stage-prebuilt-binaries.sh all"
hide = true
["build:docker:gateway"]
description = "Build the gateway Docker image"
run = "tasks/scripts/docker-build-image.sh gateway"
hide = true
["build:docker:sandbox"]
description = "Build the sandbox runtime image"
run = "tasks/scripts/docker-build-image.sh sandbox"
hide = true
["build:docker:supervisor"]
description = "Build the supervisor image"
run = "tasks/scripts/docker-build-image.sh supervisor"
hide = true
["docker:build:gateway"]
description = "Alias for build:docker:gateway"
depends = ["build:docker:gateway"]
hide = true
["docker:build:sandbox"]
description = "Alias for build:docker:sandbox"
depends = ["build:docker:sandbox"]
hide = true
["docker:build:supervisor"]
description = "Alias for build:docker:supervisor"
depends = ["build:docker:supervisor"]
hide = true
["build:docker:multiarch"]
description = "Build multi-arch gateway, sandbox, and supervisor images and push to a registry"
run = "tasks/scripts/docker-publish-multiarch.sh"
hide = true
["docker:build:multiarch"]
description = "Alias for build:docker:multiarch"
depends = ["build:docker:multiarch"]
hide = true
["docker:cleanup"]
description = "Remove stale images, volumes, and build cache not used by current deployments"
run = "scripts/docker-cleanup.sh --force"
["docker:cleanup:dry-run"]
description = "Preview what docker:cleanup would remove without deleting anything"
run = "scripts/docker-cleanup.sh --dry-run"