docs: document the riscv64 RVA23 profile CPU requirement

Ubuntu builds its riscv64 port against the RVA23 profile (since
25.10), and QEMU's default rv64 CPU does not implement all profile
extensions: Ubuntu binaries die with SIGILL during init and the
kernel panics with 'Attempted to kill init'. Select the rva23s64
profile CPU (QEMU 10.1+) for riscv64 under TCG; profiles are
supersets, so baseline rv64gc rootfses run unchanged on it.

KVM mode keeps -cpu host.

AGENTS.md

@@ -0,0 +1,89 @@
+# AGENTS.md
+
+Conventions for working in this tree. They apply to every commit; the
+whole history follows them.
+
+## Before every commit
+
+Run, in order, and make sure they are clean before committing:
+
+```sh
+cargo fmt --all
+cargo clippy --all-targets   # no new warnings
+cargo test                   # keep green when touching behavior
+```
+
+These mirror CI (`.github/workflows/ci.yml` runs check, `fmt --check`,
+clippy, and `cargo test --all-features`). `cargo fmt` may amend files
+you did not touch — include those changes in the commit (or in a
+separate `chore:` commit) rather than leaving the tree dirty.
+
+## Commit messages
+
+Follow Conventional Commits with a component scope:
+
+```
+<type>(<scope>): <short summary>
+```
+
+Rules:
+
+- Types: `feat`, `fix`, `refactor`, `perf`, `test`, `docs`, `build`,
+  `ci`, `chore`.
+- Scopes match the component touched — the module name under
+  `crates/ecr/src/` (library) or `crates/ecr-cli/src/` (CLI):
+  - `cli` — entry point and flags (`crates/ecr-cli/src/main.rs`,
+    `crates/ecr-cli/src/cli.rs`)
+  - `rootfs` — cache-aware preparation and persistence
+    (`crates/ecr/src/rootfs.rs`)
+  - `exec` — namespace-mode execution API (`crates/ecr/src/exec.rs`)
+  - `config` — config file (`crates/ecr/src/config.rs`)
+  - `distro` — distro definitions and mirrors (`crates/ecr/src/distro.rs`)
+  - `download` — image download (`crates/ecr/src/download.rs`)
+  - `extract` — rootfs extraction (`crates/ecr/src/extract.rs`)
+  - `chroot` — chroot setup (`crates/ecr/src/chroot.rs`)
+  - `namespace` — Linux namespaces (`crates/ecr/src/namespace.rs`)
+  - `mount` — bind mounts and mount table (`crates/ecr/src/mount.rs`)
+  - `kernel` — kernel/initramfs handling for `--kernel`
+    (`crates/ecr/src/kernel.rs`)
+  - `qemu` — QEMU VM mode (`crates/ecr/src/qemu.rs`,
+    `crates/ecr/src/qemu_vm.rs`)
+  - `utils`, `verbose` — shared helpers (`crates/ecr/src/utils.rs`,
+    `crates/ecr/src/verbose.rs`)
+  - `deps` — dependency additions/bumps (manifests, lockfile)
+- Omit the scope entirely for repo-wide changes that do not belong to a
+  single component (README.md, SPEC.md, root config).
+- Summary: imperative mood ("add", never "added" or "adds"), lowercase
+  first letter, no trailing period, max ~72 characters.
+- Body (optional): separated by a blank line, wrapped at 72 columns;
+  explain why rather than what. Reference issues as `#123`.
+- A commit touching several components should be split into one commit
+  per component when practical; otherwise use the dominant scope.
+- **No merge commits.** Integrate work by rebasing onto the target
+  branch (`git rebase`, `git pull --rebase`, `git cherry-pick`); the
+  history stays linear. When several work streams run in parallel, land
+  them one rebase at a time.
+
+### Examples
+
+```
+feat(namespace): set unique hostname per run
+fix(extract): handle hard links in rootfs archives
+fix(kernel): parse =PATH syntax for --kernel
+test(chroot): cover path resolution helpers
+feat(qemu): enable KVM when available
+deps: bump nix to 0.31
+docs: document QEMU system mode and =PATH syntax
+chore: apply cargo fmt
+```
+
+## Code
+
+- Tests live inline as `#[cfg(test)]` modules at the bottom of each
+  `src/` module; there is no `tests/` directory. Scope test commits to
+  the module under test.
+- Comments state constraints the code cannot show; no narration.
+- Anything user-facing (CLI flags, config keys, error text users act
+  on) is reflected in `README.md` before commit.
+- Design decisions that outlive the session go to `SPEC.md`, not to
+  new docs or repos.

Cargo.lock

@@ -302,7 +302,6 @@ version = "0.1.0"
 dependencies = [
  "anyhow",
  "base64",
- "clap",
  "cpio",
  "dirs",
  "flate2",
@@ -323,6 +322,15 @@ dependencies = [
  "zstd",
 ]
 
+[[package]]
+name = "ecr-cli"
+version = "0.1.0"
+dependencies = [
+ "anyhow",
+ "clap",
+ "ecr",
+]
+
 [[package]]
 name = "either"
 version = "1.16.0"

Cargo.toml

@@ -1,50 +1,14 @@
-[package]
+[workspace]
-name = "ecr"
+resolver = "2"
+members = ["crates/ecr", "crates/ecr-cli"]
+
+[workspace.package]
 version = "0.1.0"
 edition = "2021"
 rust-version = "1.77"
-description = "Enter chroot environments with Linux namespaces"
 license = "MIT"
 authors = ["Valentin Haudiquet"]
 
-[dependencies]
-# CLI parsing
-clap = { version = "4", features = ["derive", "env"] }
-
-# Config parsing
-serde = { version = "1", features = ["derive"] }
-serde_yaml = "0.9"
-
-# HTTP downloads
-reqwest = { version = "0.13", features = ["blocking", "stream"] }
-
-# Tarball extraction
-tar = "0.4"
-flate2 = "1"
-xz2 = "0.1"
-zstd = "0.13"
-
-# Unix syscall bindings
-nix = { version = "0.31", features = ["fs", "mount", "sched", "signal", "user", "process", "hostname"] }
-
-# Temp directories
-tempfile = "3"
-
-# Error handling
-anyhow = "1"
-
-# Utilities
-dirs = "6"
-which = "7"
-cpio = "0.4"
-base64 = "0.22"
-tokio = { version = "1", features = ["rt-multi-thread", "macros", "io-util"] }
-futures-util = "0.3"
-indicatif = "0.18"
-serde_json = "1"
-libc = "0.2"
-users = "0.11"
-
 [profile.release]
 strip = true
 opt-level = "z"

README.md

@@ -16,6 +16,56 @@ ecr fedora          # any Docker Hub image
 
 `ecr` pulls a root filesystem (Alpine/Ubuntu direct from their CDNs; everything else from Docker Hub), extracts it into a temporary directory, and execs a shell inside a user + mount + PID + UTS namespace. The process tree is isolated, the rootfs is discarded on exit, and your host is never touched.
 
+## Library
+
+`ecr` is a cargo workspace: `crates/ecr` is the library crate (package `ecr`), `crates/ecr-cli` the thin command-line front-end. Rust consumers can use the library directly — resolve an image, download it through the content cache, and run commands with a fully caller-controlled environment, bind targets and architecture:
+
+```toml
+[dependencies]
+ecr = { git = "https://github.com/…" } # or a path / registry source
+```
+
+```rust
+use ecr::{chroot, BindTarget, ExecOptions, PrepareRequest, RootfsCache};
+
+// Download alpine through the cache (~/.cache/ecr) and extract to a scratch dir
+let cache = RootfsCache::new(RootfsCache::default_dir()?);
+let rootfs = cache.prepare(&PrepareRequest::new("alpine:3.23"))?;
+
+// Caller-composed envp, explicit bind targets, target architecture
+let code = rootfs.exec(&ExecOptions {
+    arch: "amd64".into(),                                    // empty = host arch
+    binds: vec![BindTarget {                                 // host dir -> in-rootfs mount
+        source: "./data".into(),
+        target: "/mnt/data".into(),
+        read_only: false,                                    // true = overlay (ro)
+    }],
+    env: chroot::default_env(rootfs.dir()),                  // or your own envp
+    command: vec!["cat".into(), "/etc/os-release".into()],
+    ..ExecOptions::default()
+})?;
+
+rootfs.persist()?; // write the rootfs back into the cache (see below)
+```
+
+### Provisioned-rootfs caching (hot cells)
+
+Prepare once, provision once, amortize every later run — including runs from other processes sharing the same cache directory:
+
+```rust
+let rootfs = cache.prepare_provisioned(&PrepareRequest::new("alpine:3.23"), |rootfs| {
+    // runs at most once per cache entry
+    rootfs.exec(&ExecOptions {
+        command: vec!["apk".into(), "add".into(), "curl".into()],
+        env: chroot::default_env(rootfs.dir()),
+        ..ExecOptions::default()
+    })?;
+    Ok(())
+})?;
+```
+
+On the first call the pristine image is downloaded, the closure provisions it, and the result is persisted into the cache with a `.provisioned` marker. On every subsequent call the entry is hit directly: no download, no provisioning. Note a provisioned entry no longer tracks the upstream image; delete the entry (or pass `no_cache: true`) to re-provision.
+
 ## Usage
 
 ```
@@ -38,7 +88,7 @@ ecr [OPTIONS] <DISTRO[:VERSION]> [-- COMMAND...]
 | `--no-cache` | Force a fresh download, bypassing the cache |
 | `-v, --verbose` | Print diagnostic output (URLs, layer info, extraction steps) |
 | `-a, --arch <ARCH>` | Target architecture (`amd64`, `arm64`, `armhf`, `riscv64`, …) |
-| `--kernel[=PATH]` | Boot with QEMU system emulation. Downloads Alpine's `linux-virt` kernel if no `=PATH` given |
+| `--kernel[=PATH]` | Boot with QEMU system emulation. Downloads Alpine's default kernel if no `=PATH` given (`linux-virt`, or `linux-lts` on riscv64 where the virt flavor is not built) |
 | `-m, --memory <SIZE>` | Memory for QEMU VM (default: 2G, only with `--kernel`) |
 
 ## Examples
@@ -74,7 +124,7 @@ ecr --kernel --memory 4G alpine
 When `--kernel` is specified, ecr boots the rootfs in a full QEMU virtual machine instead of using namespaces:
 
 ```sh
-# Auto-download Alpine's linux-virt kernel (recommended)
+# Auto-download Alpine's default kernel (recommended)
 ecr --kernel alpine
 
 # Use your own kernel
@@ -83,7 +133,7 @@ ecr --kernel=/boot/vmlinuz ubuntu
 
 This mode:
 - Creates an uncompressed CPIO initramfs from the rootfs (streamed to disk)
-- Boots QEMU with your kernel (or auto-downloads Alpine's `linux-virt` kernel)
+- Boots QEMU with your kernel (or auto-downloads Alpine's default kernel: `linux-virt`, falling back to `linux-lts` on riscv64 where the virt flavor is not built; the downloaded image is stored decompressed so QEMU can load it)
 - Provides full VM isolation
 - Works for any architecture (no binfmt_misc needed)
 - Caches the default kernel in `~/.cache/ecr/`
@@ -93,6 +143,7 @@ Host bind mounts (`--bind`, `--bind-rw`) are not applied in this mode.
 Requirements:
 - `qemu-system-<arch>` installed
 - For custom kernels: kernel must have serial console support
+- riscv64 VMs need QEMU ≥ 10.1 (`rva23s64` CPU, required by Ubuntu 25.10+ RVA23 userland)
 
 ## Supported distributions
 
@@ -105,7 +156,7 @@ Requirements:
 
 ## Cache
 
-Downloaded images are cached in `~/.cache/ecr/`. For `latest` OCI tags the registry manifest digest is checked on each run — the image is only re-downloaded when it has actually changed. Use `--no-cache` to force a fresh pull regardless.
+Downloaded images are cached in `~/.cache/ecr/`. For `latest` OCI tags the registry manifest digest is checked on each run — the image is only re-downloaded when it has actually changed. Use `--no-cache` to force a fresh pull regardless. The library's `PreparedRootfs::persist` can replace a cache entry with a provisioned rootfs (see *Provisioned-rootfs caching* above).
 
 ## Requirements
 

SPEC.md

@@ -1,5 +1,63 @@
 # ecr - implementation specification
 
+## Workspace Layout
+
+Cargo workspace with two crates:
+
+- `crates/ecr` — the library (package `ecr`). All functionality lives here:
+  image resolution, download, extraction, namespaces, mounts, chroot exec,
+  QEMU VM mode.
+- `crates/ecr-cli` — the CLI front-end (package `ecr-cli`, binary `ecr`).
+  Parses flags, maps them onto the library API, propagates exit codes.
+
+The library must not depend on CLI types (`clap` is a CLI-only dependency).
+
+## Library API
+
+### Rootfs lifecycle (`ecr::rootfs`)
+
+- `RootfsCache::new(dir)` / `RootfsCache::default_dir()` — the image tarball
+  cache (default `~/.cache/ecr`).
+- `cache.prepare(&PrepareRequest)` — parse the image reference, resolve
+  floating version aliases ("latest", "lts", "edge") to a concrete version
+  before computing the cache key, run the OCI `:latest` digest freshness
+  check, download through the cache when needed, and extract into a scratch
+  directory. Returns a `PreparedRootfs` (TempDir-backed; dropped on drop).
+- `cache.prepare_provisioned(&req, provision)` — hot-cell amortization: on a
+  cache hit with a `.provisioned` sidecar the entry is extracted as-is (no
+  freshness check, no provisioning); otherwise the rootfs is prepared,
+  `provision(&PreparedRootfs)` runs once, and `persist` writes the result
+  back. `no_cache` forces re-download + re-provision.
+- `PreparedRootfs::persist()` — packs the current rootfs into its cache
+  entry (compression chosen from the entry's filename extension: gz, xz,
+  zstd, plain tar; symlinks stored as links; permissions preserved) and
+  writes the `.provisioned` sidecar. The entry's contents are replaced:
+  plain `prepare` also returns the provisioned contents from then on.
+
+### Execution (`ecr::exec`)
+
+- `exec(rootfs, &ExecOptions)` — run a command inside a prepared rootfs in
+  fresh user/PID/mount/UTS namespaces; returns the exit code (128+signal on
+  kill). Empty option fields select defaults:
+  - `arch`: host architecture; a foreign arch requires binfmt_misc.
+  - `env`: caller-composed envp as `(key, value)` pairs; empty selects
+    `chroot::default_env`. The host environment is never inherited.
+  - `binds`: explicit `BindTarget { source, target, read_only }` — host
+    directory mounted at an absolute in-rootfs mount point; read-only via
+    overlay, read-write via bind. `..` targets are rejected.
+  - `dns`: nameservers written to /etc/resolv.conf; empty copies the host
+    resolver.
+  - `command`: argv; empty runs the rootfs default shell.
+  - `working_dir`: explicit in-rootfs cwd; empty picks the first read-write
+    bind target that exists, then `/root`, then `/`.
+
+### Mount plumbing (`ecr::mount`)
+
+`setup_mounts(rootfs, &[BindTarget])` mounts proc/dev/devpts/sys and applies
+the bind targets; `in_rootfs(rootfs, target)` maps in-chroot paths and
+rejects escaping targets. Overlay upper/work directories are temp dirs the
+caller must keep alive (returned by `setup_mounts`).
+
 ## Synopsis
 
 ```
@@ -22,7 +80,7 @@ ecr [OPTIONS] <DISTRO[:VERSION]> -- [COMMAND]...
 | `--bind-rw <path>` | none | Read-write bind mount at `/mnt/<basename>` (can be specified multiple times, overrides `--bind` for same path) |
 | `--no-cache` | false | Download fresh tarball, ignore cache |
 | `--no-bind` | false | Skip mounting any directory |
-| `--kernel[=PATH]` | none | Boot with QEMU system emulation; downloads the default Alpine `linux-virt` kernel when no `=PATH` is given |
+| `--kernel[=PATH]` | none | Boot with QEMU system emulation; downloads the default Alpine kernel when no `=PATH` is given (`linux-virt`, falling back to `linux-lts` on architectures without a virt flavor, e.g. riscv64) |
 | `-m, --memory <size>` | 2G | Memory size for QEMU VM (only used with `--kernel`) |
 | `-v, --verbose` | false | Print diagnostic messages |
 | `-h, --help` | - | Show help |
@@ -36,11 +94,21 @@ ecr [OPTIONS] <DISTRO[:VERSION]> -- [COMMAND]...
 ~/.cache/ecr/
 ├── ubuntu-noble-amd64.tar.gz
 ├── alpine-latest-x86_64.tar.gz
-├── debian-bookworm-amd64.tar.gz
+├── oci-docker_io-library_archlinux-latest-amd64.tar.gz
+├── oci-docker_io-library_archlinux-latest-amd64.tar.gz.digest
 └── ...
 ```
 
-No metadata files. Tarballs are downloaded once and never redownloaded. Users can delete files manually or use `--no-cache` to fetch fresh.
+Sidecar files, never counted as image entries:
+
+- `<entry>.digest` — manifest digest of the last OCI download, used by the
+  `:latest` freshness check.
+- `<entry>.provisioned` — marker written by `PreparedRootfs::persist`;
+  `prepare_provisioned` treats an entry with this marker as provisioned.
+
+Tarballs are downloaded once and never redownloaded (unless the digest
+moves, `--no-cache` is passed, or a provisioned entry is deleted). Users
+can delete files manually.
 
 ### Config File
 
@@ -111,20 +179,20 @@ Error: No manifest found for architecture 'riscv64'. Available: amd64, arm64, pp
 
 ## Execution Flow
 
-1. Parse CLI arguments
+The CLI delegates to the library; the namespace-mode flow is:
-2. Resolve distro/version/arch to image source
+
+1. Parse CLI arguments, map flags onto library requests
+2. `cache.prepare`: resolve distro/version/arch to image source
 3. Check cache for existing tarball
 4. If not cached, download tarball (direct or OCI)
-5. Create temp directory for extraction
+5. Extract tarball to a temporary directory
-6. Extract tarball to temp directory
+6. `ecr::exec`: create namespaces: user, pid, mount, uts
-7. Create namespaces: user, pid, mount, uts
+7. Set up mounts: /proc, /sys (ro), /dev, /dev/pts
-8. Set up mounts: /proc, /sys (ro), /dev, /dev/pts
+8. Apply bind targets: overlays (ro) and bind mounts (rw)
 9. Write /etc/resolv.conf with DNS servers
-10. Set up overlay mounts for bind paths
+10. Set the working directory
-11. Set up read-write bind mounts
+11. Exec shell or command in chroot with the composed envp
-12. Set environment variables
+12. On exit, clean up the temporary directory; propagate the exit code
-13. Exec shell or command in chroot
-14. On exit, clean up temp directory
 
 ## Namespace Setup
 
@@ -206,6 +274,7 @@ ecr --kernel=/boot/vmlinuz debian -- /bin/sh -c "echo hello"
 2. Extract tarball to temporary directory
 3. Create uncompressed CPIO initramfs from rootfs (streamed to disk), including essential device nodes (/dev/ttyS0, /dev/null, /dev/tty) and an `/init` script that mounts proc/sys/dev, sets the hostname, execs the requested command argv verbatim (each argv element base64-encoded in the cmdline as `ECR_ARGV`), and powers off on exit
 4. Launch QEMU with:
+   - `-machine virt` on riscv64 only - qemu-system-riscv64's default machine is `spike`, which has neither a PCI bus (virtio-net-pci fails) nor a 16550 UART (console output is lost); `virt` has both plus bundled OpenSBI firmware
    - `-kernel <path>` - provided (or downloaded) kernel
    - `-initrd initramfs.cpio` - rootfs as initramfs
    - `-append "console=ttyS0 [quiet] ECR_SHELL=... [ECR_ARGV=...] ECR_HOSTNAME=..."` - kernel command line (`quiet` unless `-v`)
@@ -213,9 +282,14 @@ ecr --kernel=/boot/vmlinuz debian -- /bin/sh -c "echo hello"
    - `-display none -serial mon:stdio` - console on stdio
    - `-netdev user,id=net0 -device virtio-net-pci,netdev=net0` - network NIC
    - `-enable-kvm -cpu host` - when the host supports KVM and the target matches the host architecture
+   - `-cpu rva23s64` - riscv64 under TCG otherwise. Ubuntu builds its riscv64 port against the RVA23 profile (since 25.10); QEMU's default `rv64` CPU does not implement all profile extensions, so Ubuntu binaries die with SIGILL during init. Profiles are supersets, so baseline rv64gc rootfses (Alpine, older Ubuntu) run unchanged. Needs QEMU ≥ 10.1 (named profile CPUs).
 5. Wait for QEMU to exit (init powers the VM off when the command/shell exits; `-no-reboot` makes QEMU terminate)
 6. Cleanup temporary files
 
+### Default Kernel Download
+
+The default kernel (`--kernel` without `=PATH`) comes from Alpine's `main` repository. `linux-virt` is preferred; where it is not built (riscv64), the index lookup falls back to `linux-lts`. Some architectures package their kernel image gzipped (riscv64, aarch64 ship `Image.gz`), and QEMU's riscv `-kernel` loader understands only ELF, uImage and raw images, so the cached kernel is stored decompressed (gzip magic `1f 8b` detected and gunzipped at download time).
+
 ### Initramfs Creation
 
 The rootfs directory is converted to an uncompressed CPIO archive (newc format) using the `cpio` crate, streamed entry by entry so large rootfs images never need to fit in memory. Hard links are preserved: the first occurrence of a (device, inode) pair carries the data with a synthetic inode, subsequent occurrences are zero-size entries sharing that inode, which the kernel's initramfs loader turns into real hard links.
@@ -300,7 +374,8 @@ dns:
 
 ## Environment Variables
 
-Default environment inside chroot:
+Default environment inside chroot (`chroot::default_env`, used by the CLI;
+library callers compose their own envp):
 
 - HOME=/root
 - USER=root

crates/ecr-cli/Cargo.toml

@@ -0,0 +1,23 @@
+[package]
+name = "ecr-cli"
+description = "Enter chroot environments with Linux namespaces"
+version.workspace = true
+edition.workspace = true
+rust-version.workspace = true
+license.workspace = true
+authors.workspace = true
+
+# The installed binary keeps the `ecr` name even though the CLI package is
+# `ecr-cli`; the library package owns the `ecr` name for consumers.
+[[bin]]
+name = "ecr"
+path = "src/main.rs"
+
+[dependencies]
+ecr = { path = "../ecr" }
+
+# CLI parsing
+clap = { version = "4", features = ["derive", "env"] }
+
+# Error handling
+anyhow = "1"

crates/ecr-cli/src/cli.rs

@@ -36,7 +36,8 @@ pub struct Args {
     /// Boot with QEMU system emulation (optionally specify kernel path with =PATH, or omit to download default)
     ///
     /// Examples:
-    ///   --kernel             Download and use the default Alpine linux-virt kernel
+    ///   --kernel             Download and use the default Alpine kernel
+    ///                        (linux-virt, or linux-lts on riscv64)
     ///   --kernel=./vmlinuz   Use a specific kernel file
     ///
     /// The kernel path must use `=` syntax: with `--kernel ./vmlinuz` the

crates/ecr-cli/src/main.rs

@@ -0,0 +1,178 @@
+mod cli;
+
+use std::path::{Path, PathBuf};
+
+use anyhow::{Context, Result};
+use clap::Parser;
+
+use cli::Args;
+use ecr::chroot;
+use ecr::config::Config;
+use ecr::exec::ExecOptions;
+use ecr::mount::BindTarget;
+use ecr::{kernel, qemu, qemu_vm, utils, veprintln, verbose, PrepareRequest, RootfsCache};
+
+fn main() -> Result<()> {
+    let args = Args::parse();
+
+    // Initialise verbosity before anything else so all downstream code can use veprintln!.
+    verbose::set(args.verbose);
+
+    // Load config file
+    let config = Config::load()?;
+
+    // Get architecture
+    let host_arch = utils::get_host_arch().debian_name().to_string();
+    let arch = args.arch.clone().unwrap_or_else(|| host_arch.clone());
+
+    // Check QEMU binfmt early for foreign architectures (namespace mode only;
+    // VM mode uses system emulation).  Failing here avoids the download.
+    if args.kernel.is_none() && arch != host_arch {
+        qemu::check_binfmt(&arch)?;
+    }
+
+    // Resolve, download (through the cache) and extract the image
+    let cache = RootfsCache::new(RootfsCache::default_dir()?);
+    let request = PrepareRequest {
+        image: args.distro.clone(),
+        arch: args.arch.clone().unwrap_or_default(),
+        no_cache: args.no_cache,
+    };
+    let rootfs = cache.prepare(&request)?;
+
+    // Branch based on --kernel flag
+    // Option<Option<PathBuf>> (require_equals: the value must use =PATH syntax
+    // so it can never swallow the DISTRO positional):
+    //   None              -> --kernel not specified, use namespace mode
+    //   Some(None)        -> --kernel without path, download default kernel
+    //   Some(Some(path))  -> --kernel=/path/to/vmlinuz, use provided kernel
+    if let Some(kernel_opt) = &args.kernel {
+        // VM mode boots an initramfs: host bind mounts are never applied
+        if !args.bind.is_empty() || !args.bind_rw.is_empty() {
+            eprintln!(
+                "Warning: --bind/--bind-rw are ignored with --kernel \
+                 (the VM boots from an initramfs, no host directories are mounted)"
+            );
+        }
+
+        // QEMU system mode
+        let kernel_path = match kernel_opt {
+            Some(path) => {
+                veprintln!("QEMU mode: using provided kernel {}", path.display());
+                path.clone()
+            }
+            None => {
+                veprintln!("QEMU mode: downloading default kernel...");
+                kernel::get_default_kernel(cache.dir(), &arch)?
+            }
+        };
+
+        let command = if args.command.is_empty() {
+            None
+        } else {
+            Some(args.command.clone())
+        };
+
+        let result = qemu_vm::launch_qemu(qemu_vm::QemuConfig {
+            kernel_path,
+            rootfs_path: rootfs.dir().to_path_buf(),
+            memory: args.memory.clone(),
+            arch: arch.clone(),
+            command,
+        });
+
+        // Cleanup happens automatically via tempfile
+        if result.is_ok() {
+            veprintln!("Cleanup complete.");
+        }
+
+        result
+    } else {
+        // Namespace/chroot mode
+        let exit_code = namespace_mode(&args, rootfs.dir(), &config, &arch)?;
+        // Propagate the command's exit code, cleaning up the extracted rootfs
+        // first: process::exit does not run destructors.
+        drop(rootfs);
+        if exit_code != 0 {
+            std::process::exit(exit_code);
+        }
+        Ok(())
+    }
+}
+
+/// Run in namespace/chroot mode, returning the command's exit code
+fn namespace_mode(args: &Args, rootfs: &Path, config: &Config, arch: &str) -> Result<i32> {
+    let opts = ExecOptions {
+        arch: arch.to_string(),
+        binds: cli_bind_targets(args)?,
+        env: chroot::default_env(rootfs),
+        dns: config.dns.clone(),
+        command: args.command.clone(),
+        working_dir: None,
+    };
+
+    let exit_code = ecr::exec(rootfs, &opts);
+
+    // Cleanup happens automatically via tempfile
+    if exit_code.is_ok() {
+        veprintln!("Cleanup complete.");
+    }
+
+    exit_code
+}
+
+/// Translate --bind/--bind-rw/--no-bind into explicit bind targets:
+/// --bind overlays read-only at /root/<basename>, --bind-rw bind-mounts
+/// read-write at /mnt/<basename> (taking precedence over --bind for the
+/// same source path).  With no --bind given, the current directory is
+/// overlaid by default.
+fn cli_bind_targets(args: &Args) -> Result<Vec<BindTarget>> {
+    // --no-bind means "skip mounting any directory".  Combining it with an
+    // explicit --bind-rw is contradictory; error rather than silently ignoring
+    // the flag the user asked for.
+    if args.no_bind {
+        if !args.bind_rw.is_empty() {
+            return Err(anyhow::anyhow!(
+                "--no-bind and --bind-rw cannot be used together: \
+                 --no-bind skips all mounts, including read-write ones"
+            ));
+        }
+        return Ok(Vec::new());
+    }
+
+    let mut binds = Vec::new();
+
+    let ro_sources: Vec<PathBuf> = if args.bind.is_empty() {
+        vec![std::env::current_dir().context("Could not get current directory")?]
+    } else {
+        args.bind.clone()
+    };
+
+    for source in ro_sources {
+        if args.bind_rw.contains(&source) {
+            continue;
+        }
+        binds.push(BindTarget {
+            target: cli_mount_target(&source, "root")?,
+            source,
+            read_only: true,
+        });
+    }
+
+    for source in &args.bind_rw {
+        binds.push(BindTarget {
+            target: cli_mount_target(source, "mnt")?,
+            source: source.clone(),
+            read_only: false,
+        });
+    }
+
+    Ok(binds)
+}
+
+fn cli_mount_target(source: &Path, parent: &str) -> Result<PathBuf> {
+    let basename = source
+        .file_name()
+        .ok_or_else(|| anyhow::anyhow!("Invalid bind path: {}", source.display()))?;
+    Ok(Path::new("/").join(parent).join(basename))
+}

crates/ecr/Cargo.toml

@@ -0,0 +1,43 @@
+[package]
+name = "ecr"
+description = "Ephemeral chroot environments with Linux namespaces"
+version.workspace = true
+edition.workspace = true
+rust-version.workspace = true
+license.workspace = true
+authors.workspace = true
+
+[dependencies]
+# Config parsing
+serde = { version = "1", features = ["derive"] }
+serde_yaml = "0.9"
+
+# HTTP downloads
+reqwest = { version = "0.13", features = ["blocking", "stream"] }
+
+# Tarball extraction
+tar = "0.4"
+flate2 = "1"
+xz2 = "0.1"
+zstd = "0.13"
+
+# Unix syscall bindings
+nix = { version = "0.31", features = ["fs", "mount", "sched", "signal", "user", "process", "hostname"] }
+
+# Temp directories
+tempfile = "3"
+
+# Error handling
+anyhow = "1"
+
+# Utilities
+dirs = "6"
+which = "7"
+cpio = "0.4"
+base64 = "0.22"
+tokio = { version = "1", features = ["rt-multi-thread", "macros", "io-util"] }
+futures-util = "0.3"
+indicatif = "0.18"
+serde_json = "1"
+libc = "0.2"
+users = "0.11"

crates/ecr/src/chroot.rs

@@ -0,0 +1,246 @@
+use crate::veprintln;
+use anyhow::{anyhow, Context, Result};
+use nix::unistd::{chroot, execve};
+use std::os::unix::ffi::OsStrExt;
+use std::path::{Path, PathBuf};
+
+/// Compose the default environment for a rootfs: HOME, USER, SHELL (detected
+/// inside `rootfs`), TERM (inherited from the host process) and PATH.
+/// Callers use this as a starting point for their own envp, overriding or
+/// extending entries before passing them to [`run_chroot`] / [`crate::exec`].
+pub fn default_env(rootfs: &Path) -> Vec<(String, String)> {
+    let host_term = std::env::var("TERM").unwrap_or_else(|_| "xterm-256color".to_string());
+    let shell = crate::utils::detect_shell(rootfs);
+
+    vec![
+        ("HOME".to_string(), "/root".to_string()),
+        ("USER".to_string(), "root".to_string()),
+        ("SHELL".to_string(), shell.to_string()),
+        ("TERM".to_string(), host_term),
+        (
+            "PATH".to_string(),
+            "/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin".to_string(),
+        ),
+    ]
+}
+
+/// Run a command in the chroot environment.
+///
+/// `env` is the full environment (envp) of the exec'd process — the host
+/// environment is never inherited.  `working_dir` must already be resolved
+/// (absolute, inside the rootfs); exec fails if it does not exist there.
+/// `command` defaults to the rootfs shell when empty or None.  On success
+/// this function never returns (execve replaces the process).
+pub fn run_chroot(
+    rootfs: &Path,
+    command: Option<&[String]>,
+    env: &[(String, String)],
+    working_dir: &Path,
+) -> Result<()> {
+    // Set hostname in UTS namespace
+    if let Err(e) = crate::namespace::set_hostname("chroot") {
+        eprintln!("Warning: Failed to set hostname: {}", e);
+    }
+
+    // Detect shell before chroot (we're still outside)
+    let shell = crate::utils::detect_shell(rootfs);
+
+    // Change to root directory in chroot
+    chroot(rootfs).context("Failed to chroot")?;
+
+    // Now we're inside the chroot
+
+    // Determine the command to run
+    let (program, args) = match command {
+        Some(cmd) if !cmd.is_empty() => {
+            let program = cmd[0].clone();
+            let args = cmd
+                .iter()
+                .map(|s| {
+                    std::ffi::CString::new(s.as_str())
+                        .with_context(|| format!("Argument contains a null byte: {:?}", s))
+                })
+                .collect::<Result<Vec<_>>>()?;
+            (program, args)
+        }
+        _ => {
+            // Run shell (already determined above based on chroot filesystem)
+            let program = shell.to_string();
+            let args =
+                vec![std::ffi::CString::new(shell).context("Shell path contains a null byte")?];
+            (program, args)
+        }
+    };
+
+    // Build the envp from the caller-composed pairs.  execve takes this array
+    // directly; the host process environment is not touched at all.
+    let env_cstrings = env
+        .iter()
+        .map(|(k, v)| {
+            std::ffi::CString::new(format!("{}={}", k, v))
+                .with_context(|| format!("Environment variable contains a null byte: {}={}", k, v))
+        })
+        .collect::<Result<Vec<_>>>()?;
+
+    std::env::set_current_dir(working_dir).with_context(|| {
+        format!(
+            "Failed to change to working directory {}",
+            working_dir.display()
+        )
+    })?;
+
+    // Print welcome message
+    veprintln!("Entering chroot at {}", rootfs.display());
+    veprintln!("Working directory: {}", working_dir.display());
+
+    // execve(2) does not search PATH: resolve the program through the
+    // caller-composed environment like execvp(3) would.
+    let program_path = resolve_program(&program, env)?;
+
+    // Exec the program directly with the caller-composed, isolated environment.
+    // execve never returns on success.
+    let program_cstr = std::ffi::CString::new(program_path.as_os_str().as_bytes())
+        .with_context(|| format!("Invalid program path: {}", program_path.display()))?;
+
+    let result = execve(&program_cstr, &args, &env_cstrings);
+
+    match result {
+        Ok(_) => Ok(()), // Never reached
+        Err(e) => Err(anyhow!("Failed to exec {}: {}", program_path.display(), e)),
+    }
+}
+
+/// Resolve the program to exec.  Commands containing a '/' are used as-is
+/// (existing check gives a clearer error than a raw ENOENT); a bare command
+/// name is looked up in the caller-composed PATH, like execvp(3) would.
+fn resolve_program(program: &str, env: &[(String, String)]) -> Result<PathBuf> {
+    if program.contains('/') {
+        let path = PathBuf::from(program);
+        if !path.exists() {
+            return Err(anyhow!("Program not found: {}", program));
+        }
+        return Ok(path);
+    }
+
+    let path_var = env
+        .iter()
+        .find(|(k, _)| k == "PATH")
+        .map(|(_, v)| v.as_str())
+        .unwrap_or("/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin");
+
+    // Empty PATH components are skipped rather than treated as the current
+    // directory (execvp semantics) — cwd-relative lookup is a footgun here.
+    path_var
+        .split(':')
+        .filter(|dir| !dir.is_empty())
+        .map(|dir| PathBuf::from(dir).join(program))
+        .find(|candidate| candidate.exists())
+        .ok_or_else(|| anyhow!("Program not found: {} (PATH={})", program, path_var))
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn env_get<'a>(env: &'a [(String, String)], key: &str) -> Option<&'a str> {
+        env.iter().find(|(k, _)| k == key).map(|(_, v)| v.as_str())
+    }
+
+    #[test]
+    fn resolve_program_bare_name_via_path() {
+        let dir = tempfile::tempdir().unwrap();
+        std::fs::write(dir.path().join("true"), b"binary").unwrap();
+        let env = vec![(
+            "PATH".to_string(),
+            format!("/nonexistent:{}", dir.path().display()),
+        )];
+        assert_eq!(
+            resolve_program("true", &env).unwrap(),
+            dir.path().join("true")
+        );
+    }
+
+    #[test]
+    fn resolve_program_bare_name_defaults_to_standard_path() {
+        // No PATH in the composed env: the standard fallback must still
+        // resolve a program present on any Linux host.
+        let resolved = resolve_program("sh", &[]).unwrap();
+        assert!(resolved.exists());
+    }
+
+    #[test]
+    fn resolve_program_bare_name_missing() {
+        let env = vec![("PATH".to_string(), "/nonexistent".to_string())];
+        assert!(resolve_program("definitely-missing", &env).is_err());
+    }
+
+    #[test]
+    fn resolve_program_absolute_path_passthrough() {
+        let dir = tempfile::tempdir().unwrap();
+        std::fs::write(dir.path().join("tool"), b"binary").unwrap();
+        let path = dir.path().join("tool");
+        assert_eq!(resolve_program(path.to_str().unwrap(), &[]).unwrap(), path);
+    }
+
+    #[test]
+    fn resolve_program_absolute_path_missing() {
+        assert!(resolve_program("/nonexistent/tool", &[]).is_err());
+    }
+
+    #[test]
+    fn resolve_program_skips_empty_path_components() {
+        // An empty PATH component must not mean "current directory";
+        // Cargo.toml exists in the test process cwd and must not resolve.
+        let env = vec![("PATH".to_string(), ":".to_string())];
+        assert!(resolve_program("Cargo.toml", &env).is_err());
+    }
+
+    #[test]
+    fn test_default_env_entries() {
+        let dir = tempfile::tempdir().unwrap();
+        let env = default_env(dir.path());
+
+        assert_eq!(env.len(), 5);
+        assert_eq!(env_get(&env, "HOME"), Some("/root"));
+        assert_eq!(env_get(&env, "USER"), Some("root"));
+        assert_eq!(env_get(&env, "SHELL"), Some("/bin/sh"));
+    }
+
+    #[test]
+    fn test_default_env_shell_detection() {
+        // A rootfs with bash present must select /bin/bash
+        let dir = tempfile::tempdir().unwrap();
+        std::fs::create_dir_all(dir.path().join("bin")).unwrap();
+        std::fs::write(dir.path().join("bin/bash"), b"#!").unwrap();
+
+        let env = default_env(dir.path());
+        assert_eq!(env_get(&env, "SHELL"), Some("/bin/bash"));
+    }
+
+    #[test]
+    fn test_default_env_path_contains_standard_directories() {
+        let dir = tempfile::tempdir().unwrap();
+        let env = default_env(dir.path());
+        let path = env_get(&env, "PATH").expect("PATH should be set");
+
+        // Verify essential directories are in PATH
+        assert!(path.contains("/bin"));
+        assert!(path.contains("/usr/bin"));
+        assert!(path.contains("/sbin"));
+        assert!(path.contains("/usr/sbin"));
+    }
+
+    #[test]
+    fn test_default_env_has_no_host_specific_variables() {
+        // Verify the default env is a clean environment without inheriting
+        // anything from the host beyond TERM
+        let dir = tempfile::tempdir().unwrap();
+        let env = default_env(dir.path());
+
+        let keys: Vec<&str> = env.iter().map(|(k, _)| k.as_str()).collect();
+        assert!(!keys.contains(&"LANG"));
+        assert!(!keys.contains(&"DISPLAY"));
+        assert!(!keys.contains(&"PWD"));
+        assert!(keys.contains(&"TERM"));
+    }
+}

crates/ecr/src/exec.rs

@@ -0,0 +1,305 @@
+//! Namespace-mode execution: mount a prepared rootfs and run a command
+//! inside fresh user/PID/mount/UTS namespaces.
+//!
+//! The caller composes everything: the environment ([`ExecOptions::env`]),
+//! the bind targets ([`ExecOptions::binds`]) and the target architecture
+//! ([`ExecOptions::arch`]).  Fields left empty fall back to the CLI
+//! defaults (see each field's docs).
+
+use std::collections::HashSet;
+use std::io::Write;
+use std::path::{Path, PathBuf};
+
+use anyhow::{Context, Result};
+
+use crate::chroot;
+use crate::mount::{self, BindTarget};
+use crate::namespace;
+use crate::qemu;
+use crate::utils::{self, Arch};
+use crate::veprintln;
+
+/// Options for [`exec`].
+#[derive(Debug, Clone)]
+pub struct ExecOptions {
+    /// Target architecture of the rootfs (e.g. "amd64", "arm64").  When it
+    /// differs from the host, exec verifies binfmt_misc registration for
+    /// QEMU user emulation before starting.  Empty selects the host arch.
+    pub arch: String,
+
+    /// Bind targets mounted into the rootfs before the command runs.
+    pub binds: Vec<BindTarget>,
+
+    /// Environment of the exec'd process, as (key, value) pairs.  The host
+    /// environment is never inherited.  Compose from
+    /// [`chroot::default_env`] to start from the CLI defaults.  Empty
+    /// selects [`chroot::default_env`] as-is.
+    pub env: Vec<(String, String)>,
+
+    /// DNS servers written to /etc/resolv.conf.  Empty copies the host
+    /// resolver (falling back to public resolvers when unreadable).
+    pub dns: Vec<String>,
+
+    /// argv to exec inside the rootfs.  Empty runs the rootfs default shell
+    /// (bash if present, else sh).
+    pub command: Vec<String>,
+
+    /// Working directory inside the rootfs.  Empty picks the first
+    /// read-write bind target that exists, then /root, then /.
+    pub working_dir: Option<PathBuf>,
+}
+
+impl ExecOptions {
+    pub fn new() -> Self {
+        ExecOptions {
+            arch: String::new(),
+            binds: Vec::new(),
+            env: Vec::new(),
+            dns: Vec::new(),
+            command: Vec::new(),
+            working_dir: None,
+        }
+    }
+}
+
+impl Default for ExecOptions {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
+/// Run a command inside `rootfs` in fresh user/PID/mount/UTS namespaces and
+/// return its exit code (128+signal when the command is killed by a signal).
+/// Setup failures are returned as Err.
+pub fn exec(rootfs: &Path, opts: &ExecOptions) -> Result<i32> {
+    let arch = if opts.arch.is_empty() {
+        utils::get_host_arch().debian_name().to_string()
+    } else {
+        opts.arch.clone()
+    };
+
+    // Foreign-architecture rootfs needs QEMU user emulation to run its
+    // binaries; fail before doing any mount work.
+    if Arch::from_str(&arch) != utils::get_host_arch() {
+        qemu::check_binfmt(&arch)?;
+    }
+
+    namespace::check_user_namespace()?;
+
+    let mut opts = opts.clone();
+    if opts.env.is_empty() {
+        opts.env = chroot::default_env(rootfs);
+    }
+
+    let rootfs_buf = rootfs.to_path_buf();
+
+    namespace::setup_namespaces(move || {
+        // Setup mounts - overlay_temps must be kept alive for overlays to work
+        let overlay_temps = mount::setup_mounts(&rootfs_buf, &opts.binds)?;
+
+        for bind in &opts.binds {
+            if !bind.read_only {
+                veprintln!("Read-write mount: {}", bind.target.display());
+            }
+        }
+
+        write_resolv_conf(&rootfs_buf, &opts.dns)?;
+
+        let working_dir = resolve_working_dir(&rootfs_buf, &opts)?;
+
+        let command = if opts.command.is_empty() {
+            None
+        } else {
+            Some(opts.command.clone())
+        };
+
+        let result = chroot::run_chroot(&rootfs_buf, command.as_deref(), &opts.env, &working_dir);
+
+        // Keep overlay_temps alive until chroot exits
+        drop(overlay_temps);
+
+        result
+    })
+}
+
+/// Resolve the working directory for the exec'd command.
+///
+/// Existence checks happen against `rootfs`-prefixed paths, which is
+/// equivalent to checking the absolute paths after chroot(2) — same tree,
+/// same mounts (this runs after setup_mounts).
+fn resolve_working_dir(rootfs: &Path, opts: &ExecOptions) -> Result<PathBuf> {
+    if let Some(dir) = &opts.working_dir {
+        return Ok(dir.clone());
+    }
+
+    let mut candidates: Vec<PathBuf> = Vec::new();
+    if let Some(bind) = opts.binds.iter().find(|b| !b.read_only) {
+        candidates.push(bind.target.clone());
+    }
+    candidates.push("/root".into());
+    candidates.push("/".into());
+
+    // Deduplicate while keeping first-seen order
+    let mut seen = HashSet::new();
+    candidates.retain(|c| seen.insert(c.clone()));
+
+    for candidate in candidates {
+        let exists = mount::in_rootfs(rootfs, &candidate)
+            .map(|p| p.exists())
+            .unwrap_or(false);
+        if exists {
+            return Ok(candidate);
+        }
+    }
+
+    Ok(PathBuf::from("/"))
+}
+
+/// Write /etc/resolv.conf with the caller's DNS servers (host resolver when
+/// empty), atomically and never through a symlink.
+pub fn write_resolv_conf(rootfs: &Path, dns: &[String]) -> Result<()> {
+    let resolv_conf = rootfs.join("etc/resolv.conf");
+
+    // Create /etc if it doesn't exist
+    if let Some(parent) = resolv_conf.parent() {
+        std::fs::create_dir_all(parent)
+            .with_context(|| format!("Failed to create directory: {}", parent.display()))?;
+    }
+
+    // Copy host's resolv.conf if dns is empty, otherwise use provided DNS
+    let content = if dns.is_empty() {
+        // Try to copy from host
+        match std::fs::read_to_string("/etc/resolv.conf") {
+            Ok(host_resolv) => host_resolv,
+            Err(_) => "nameserver 1.1.1.1\nnameserver 8.8.8.8\n".to_string(),
+        }
+    } else {
+        let mut c = dns
+            .iter()
+            .map(|s| format!("nameserver {}", s))
+            .collect::<Vec<_>>()
+            .join("\n");
+        c.push('\n');
+        c
+    };
+
+    // Remove any existing file or symlink before writing so that we always
+    // create a plain file.  Without this, an absolute symlink such as
+    // /etc/resolv.conf -> /run/systemd/resolve/stub-resolv.conf would cause the
+    // write to follow the symlink through the *host* root (chroot() has not been
+    // called yet) and corrupt the host's DNS configuration.
+    //
+    // Use atomic file creation with O_CREAT | O_EXCL to prevent TOCTOU race:
+    // if an attacker creates a symlink between our remove_file and write, the
+    // exclusive create will fail rather than writing to the symlink target.
+    let _ = std::fs::remove_file(&resolv_conf); // ignore ENOENT
+
+    // Use OpenOptions with create_new(true) for atomic exclusive creation
+    let mut file = std::fs::OpenOptions::new()
+        .write(true)
+        .create_new(true)
+        .open(&resolv_conf)
+        .with_context(|| {
+            format!(
+                "Failed to create resolv.conf at {} (symlink attack prevented)",
+                resolv_conf.display()
+            )
+        })?;
+
+    file.write_all(content.as_bytes())
+        .with_context(|| format!("Failed to write to {}", resolv_conf.display()))?;
+
+    Ok(())
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn opts(binds: Vec<BindTarget>, working_dir: Option<PathBuf>) -> ExecOptions {
+        ExecOptions {
+            binds,
+            working_dir,
+            ..ExecOptions::default()
+        }
+    }
+
+    #[test]
+    fn explicit_working_dir_wins() {
+        let dir = tempfile::tempdir().unwrap();
+        let resolved =
+            resolve_working_dir(dir.path(), &opts(Vec::new(), Some("/custom".into()))).unwrap();
+        assert_eq!(resolved, PathBuf::from("/custom"));
+    }
+
+    #[test]
+    fn first_read_write_bind_target_preferred() {
+        let dir = tempfile::tempdir().unwrap();
+        std::fs::create_dir_all(dir.path().join("mnt/data")).unwrap();
+        let binds = vec![
+            BindTarget {
+                source: "/host/ro".into(),
+                target: "/root/ro".into(),
+                read_only: true,
+            },
+            BindTarget {
+                source: "/host/data".into(),
+                target: "/mnt/data".into(),
+                read_only: false,
+            },
+        ];
+        let resolved = resolve_working_dir(dir.path(), &opts(binds, None)).unwrap();
+        assert_eq!(resolved, PathBuf::from("/mnt/data"));
+    }
+
+    #[test]
+    fn falls_back_to_root_dir_when_no_binds() {
+        let dir = tempfile::tempdir().unwrap();
+        std::fs::create_dir_all(dir.path().join("root")).unwrap();
+        let resolved = resolve_working_dir(dir.path(), &opts(Vec::new(), None)).unwrap();
+        assert_eq!(resolved, PathBuf::from("/root"));
+    }
+
+    #[test]
+    fn missing_read_write_target_falls_through_to_root_dir() {
+        // The bind target does not exist under rootfs (e.g. bind skipped):
+        // the candidate list must move on to /root rather than failing.
+        let dir = tempfile::tempdir().unwrap();
+        std::fs::create_dir_all(dir.path().join("root")).unwrap();
+        let binds = vec![BindTarget {
+            source: "/host/data".into(),
+            target: "/mnt/data".into(),
+            read_only: false,
+        }];
+        let resolved = resolve_working_dir(dir.path(), &opts(binds, None)).unwrap();
+        assert_eq!(resolved, PathBuf::from("/root"));
+    }
+
+    #[test]
+    fn last_resort_is_slash() {
+        let dir = tempfile::tempdir().unwrap();
+        let resolved = resolve_working_dir(dir.path(), &opts(Vec::new(), None)).unwrap();
+        assert_eq!(resolved, PathBuf::from("/"));
+    }
+
+    #[test]
+    fn write_resolv_conf_uses_caller_dns() {
+        let dir = tempfile::tempdir().unwrap();
+        write_resolv_conf(dir.path(), &["8.8.8.8".to_string(), "1.0.0.1".to_string()]).unwrap();
+
+        let content = std::fs::read_to_string(dir.path().join("etc/resolv.conf")).unwrap();
+        assert_eq!(content, "nameserver 8.8.8.8\nnameserver 1.0.0.1\n");
+    }
+
+    #[test]
+    fn write_resolv_conf_replaces_existing_file() {
+        // Re-running exec on the same rootfs must overwrite, not fail on
+        // the exclusive create.
+        let dir = tempfile::tempdir().unwrap();
+        write_resolv_conf(dir.path(), &["8.8.8.8".to_string()]).unwrap();
+        write_resolv_conf(dir.path(), &["9.9.9.9".to_string()]).unwrap();
+
+        let content = std::fs::read_to_string(dir.path().join("etc/resolv.conf")).unwrap();
+        assert_eq!(content, "nameserver 9.9.9.9\n");
+    }
+}

crates/ecr/src/extract.rs

@@ -18,6 +18,14 @@ pub fn extract_tarball(tarball: &Path, dest: &Path) -> Result<()> {
         return extract_multi_layer_oci(tarball, dest);
     }
 
+    extract_single_archive(tarball, dest)
+}
+
+/// Extract a plain rootfs tarball, detecting the compression format from
+/// the filename with a magic-byte fallback.
+fn extract_single_archive(tarball: &Path, dest: &Path) -> Result<()> {
+    let filename = tarball.file_name().and_then(|n| n.to_str()).unwrap_or("");
+
     let file = File::open(tarball)
         .with_context(|| format!("Failed to open tarball: {}", tarball.display()))?;
 
@@ -100,9 +108,18 @@ fn extract_multi_layer_oci(tarball: &Path, dest: &Path) -> Result<()> {
             .context("Failed to unpack OCI bundle")?;
     }
 
+    let manifest_path = temp_dir.path().join("layers.manifest");
+    if !manifest_path.exists() {
+        // Not our layer-bundle layout: a provisioned rootfs persisted over
+        // an OCI cache entry (the dispatch above keys on the "oci-" filename
+        // prefix).  The outer archive is a plain rootfs tarball.
+        veprintln!("No layers.manifest in bundle; extracting as plain rootfs tarball");
+        return extract_single_archive(tarball, dest);
+    }
+
     // Read the layers manifest
-    let manifest = std::fs::read_to_string(temp_dir.path().join("layers.manifest"))
+    let manifest =
-        .context("Failed to read layers.manifest")?;
+        std::fs::read_to_string(&manifest_path).context("Failed to read layers.manifest")?;
 
     // Apply each layer in order with full whiteout handling.
     for layer_name in manifest.lines() {

crates/ecr/src/kernel.rs

@@ -1,22 +1,32 @@
 //! Default kernel download for QEMU VM mode.
 //!
 //! When `--kernel` is specified without a path, we download a default kernel
-//! suitable for VM booting. We use Alpine's `linux-virt` package because:
+//! suitable for VM booting from Alpine's kernel packages:
 //!
 //! - Small size (~10-15MB compressed)
-//! - VM-optimized configuration
+//! - VM-optimized configuration (`linux-virt`)
 //! - Multi-architecture support
 //! - Simple direct download URLs
 //!
-//! The kernel is cached in the same cache directory as rootfs images.
+//! `linux-virt` is preferred, but it is not built for every architecture
+//! (riscv64 has no virt flavor in `main`), so we fall back to `linux-lts`
+//! when the virt flavor is absent from the repository index.
+//!
+//! The kernel is cached in the same cache directory as rootfs images,
+//! decompressed: some architectures (aarch64, riscv64) package their
+//! kernel image gzipped, and QEMU's riscv `-kernel` loader understands
+//! only ELF, uImage and raw images.
 
 use crate::veprintln;
 use anyhow::{anyhow, Context, Result};
 use indicatif::{ProgressBar, ProgressStyle};
-use std::io::Read;
+use std::io::{Read, Seek};
 use std::path::{Path, PathBuf};
 use std::time::Duration;
 
+/// Alpine kernel packages to consider, most preferred first
+const KERNEL_PACKAGES: [&str; 2] = ["linux-virt", "linux-lts"];
+
 /// Alpine architecture mapping for kernel packages
 fn alpine_kernel_arch(arch: &str) -> &'static str {
     match arch {
@@ -91,8 +101,11 @@ fn fetch_alpine_branch_from_yaml() -> Result<String> {
     Err(anyhow!("Could not determine Alpine version from releases"))
 }
 
-/// Fetch the latest linux-virt package version from Alpine's package index
+/// Find the newest kernel package among `KERNEL_PACKAGES` in Alpine's
-fn get_linux_virt_version(branch: &str, arch: &str) -> Result<String> {
+/// package index. Returns the package name and version. The index is
+/// scanned once; whichever candidate flavor appears with the highest
+/// preference (lowest index) wins.
+fn find_kernel_package(branch: &str, arch: &str) -> Result<(&'static str, String)> {
     // Alpine package index URL
     let url = format!(
         "https://dl-cdn.alpinelinux.org/alpine/{}/main/{}/APKINDEX.tar.gz",
@@ -173,25 +186,45 @@ fn get_linux_virt_version(branch: &str, arch: &str) -> Result<String> {
 
             veprintln!("  APKINDEX size: {} bytes", contents.len());
 
-            // Parse the APKINDEX to find linux-virt
+            // Parse the APKINDEX to find the best kernel package
             // Format:
             // P:linux-virt
             // V:6.12.8-r0
             // ...
+            // The first V: line of the highest-preference package wins; the
+            // earliest version entry in the index is the latest build.
             let mut pkg_name: Option<String> = None;
+            // (preference index, package, version)
+            let mut best: Option<(usize, &'static str, String)> = None;
 
             for line in contents.lines() {
                 if let Some(name) = line.strip_prefix("P:") {
                     pkg_name = Some(name.trim().to_string());
                 } else if let Some(version) = line.strip_prefix("V:") {
-                    if pkg_name.as_deref() == Some("linux-virt") {
+                    if let Some(name) = &pkg_name {
-                        return Ok(version.trim().to_string());
+                        if let Some(idx) = KERNEL_PACKAGES.iter().position(|p| *p == name) {
+                            let preferred = best
+                                .as_ref()
+                                .map_or(true, |(best_idx, _, _)| idx < *best_idx);
+                            if preferred {
+                                best =
+                                    Some((idx, KERNEL_PACKAGES[idx], version.trim().to_string()));
+                            }
+                        }
                     }
                 }
             }
 
-            // If we got here, we found APKINDEX but not linux-virt
+            match best {
-            return Err(anyhow!("linux-virt package not found in APKINDEX. Available packages may vary by architecture."));
+                Some((_, pkg, version)) => return Ok((pkg, version)),
+                None => {
+                    return Err(anyhow!(
+                        "no kernel package found in APKINDEX (looked for: {}). \
+                         Available packages may vary by architecture.",
+                        KERNEL_PACKAGES.join(", ")
+                    ))
+                }
+            }
         }
     }
 
@@ -203,16 +236,16 @@ fn get_linux_virt_version(branch: &str, arch: &str) -> Result<String> {
     ))
 }
 
-/// Download and extract the linux-virt kernel from Alpine's package repository
+/// Download and extract the kernel from an Alpine package repository
 fn download_alpine_kernel(branch: &str, arch: &str, dest: &Path) -> Result<()> {
-    let version = get_linux_virt_version(branch, arch)?;
+    let (package, version) = find_kernel_package(branch, arch)?;
-    veprintln!("Found linux-virt version: {}", version);
+    veprintln!("Found {} version: {}", package, version);
 
-    // Construct the download URL for the linux-virt .apk
+    // Construct the download URL for the kernel .apk
     // Format: https://dl-cdn.alpinelinux.org/alpine/v3.23/main/x86_64/linux-virt-6.12.8-r0.apk
     let url = format!(
-        "https://dl-cdn.alpinelinux.org/alpine/{}/main/{}/linux-virt-{}.apk",
+        "https://dl-cdn.alpinelinux.org/alpine/{}/main/{}/{}-{}.apk",
-        branch, arch, version
+        branch, arch, package, version
     );
 
     veprintln!("Downloading kernel: {}", url);
@@ -221,12 +254,12 @@ fn download_alpine_kernel(branch: &str, arch: &str, dest: &Path) -> Result<()> {
     let rt = tokio::runtime::Runtime::new().context("Failed to create Tokio runtime")?;
     rt.block_on(download_kernel_async(&url, dest))?;
 
-    // Extract vmlinuz-virt from the APK
+    // Extract the kernel image from the APK, then store it decompressed.
-    // APK files are gzip-compressed tar archives
+    // Remove the ~45MB APK whatever the outcome — don't leave it behind
+    // in the cache directory on failure.
     let temp_apk = dest.with_extension("apk");
-    // Remove the ~45MB APK whatever the extraction outcome — don't leave
+    let result = extract_kernel_from_apk(&temp_apk, dest, package)
-    // it behind in the cache directory on failure.
+        .and_then(|()| decompress_kernel_if_gzipped(dest));
-    let result = extract_kernel_from_apk(&temp_apk, dest);
     std::fs::remove_file(&temp_apk).ok();
     result
 }
@@ -294,8 +327,15 @@ async fn download_kernel_async(url: &str, dest: &Path) -> Result<()> {
     Ok(())
 }
 
-/// Extract vmlinuz-virt from an Alpine APK file
+/// Extract the kernel image from an Alpine APK file
-fn extract_kernel_from_apk(apk_path: &Path, dest: &Path) -> Result<()> {
+fn extract_kernel_from_apk(apk_path: &Path, dest: &Path, package: &str) -> Result<()> {
+    // The kernel binary is named after the flavor: boot/vmlinuz-virt for
+    // linux-virt, boot/vmlinuz-lts for linux-lts
+    let flavor = package
+        .strip_prefix("linux-")
+        .ok_or_else(|| anyhow!("unexpected kernel package name: {}", package))?;
+    let kernel_name = format!("boot/vmlinuz-{}", flavor);
+
     veprintln!("Extracting kernel from APK...");
 
     let file = std::fs::File::open(apk_path).context("Failed to open APK file")?;
@@ -310,8 +350,7 @@ fn extract_kernel_from_apk(apk_path: &Path, dest: &Path) -> Result<()> {
 
         veprintln!("  APK entry: {}", path_str);
 
-        // Look for the kernel file: boot/vmlinuz-virt
+        if path_str == kernel_name || path_str == format!("./{}", kernel_name) {
-        if path_str == "boot/vmlinuz-virt" || path_str == "./boot/vmlinuz-virt" {
             // Extract to destination
             entry.unpack(dest).context("Failed to extract kernel")?;
             veprintln!("  Extracted kernel to: {}", dest.display());
@@ -319,7 +358,37 @@ fn extract_kernel_from_apk(apk_path: &Path, dest: &Path) -> Result<()> {
         }
     }
 
-    Err(anyhow!("vmlinuz-virt not found in APK package"))
+    Err(anyhow!("{} not found in APK package", kernel_name))
+}
+
+/// Decompress the cached kernel if it is gzip-compressed, in place.
+/// Alpine packages the kernel image gzipped on some architectures (the
+/// riscv64 and aarch64 vmlinuz are Image.gz), but QEMU's riscv `-kernel`
+/// loader understands only ELF, uImage and raw images — a gzipped Image
+/// is loaded verbatim and never boots. Uncompressed formats (x86 bzImage,
+/// ppc64le ELF, raw Image) are left untouched.
+fn decompress_kernel_if_gzipped(path: &Path) -> Result<()> {
+    let mut file =
+        std::fs::File::open(path).with_context(|| format!("Failed to open {}", path.display()))?;
+
+    let mut magic = [0u8; 2];
+    let len = file
+        .read(&mut magic)
+        .context("Failed to read kernel magic bytes")?;
+    if len < magic.len() || magic != [0x1f, 0x8b] {
+        return Ok(());
+    }
+
+    veprintln!("Kernel is gzip-compressed, decompressing...");
+    file.rewind().context("Failed to rewind kernel file")?;
+    let mut decompressed = Vec::new();
+    flate2::read::MultiGzDecoder::new(file)
+        .read_to_end(&mut decompressed)
+        .context("Failed to decompress kernel")?;
+
+    std::fs::write(path, &decompressed)
+        .with_context(|| format!("Failed to write decompressed kernel to {}", path.display()))?;
+    Ok(())
 }
 
 /// Get the path to the cached default kernel for the given architecture.
@@ -365,4 +434,34 @@ mod tests {
         assert_eq!(alpine_kernel_arch("ppc64le"), "ppc64le");
         assert_eq!(alpine_kernel_arch("s390x"), "s390x");
     }
+
+    #[test]
+    fn test_decompress_kernel_if_gzipped() {
+        use flate2::write::GzEncoder;
+        use std::io::Write;
+
+        // A gzip-compressed kernel is decompressed in place
+        let dir = tempfile::tempdir().unwrap();
+        let path = dir.path().join("kernel");
+        let mut encoder = GzEncoder::new(
+            std::fs::File::create(&path).unwrap(),
+            flate2::Compression::default(),
+        );
+        encoder.write_all(b"fake kernel image").unwrap();
+        encoder.finish().unwrap();
+
+        decompress_kernel_if_gzipped(&path).unwrap();
+        assert_eq!(std::fs::read(&path).unwrap(), b"fake kernel image");
+    }
+
+    #[test]
+    fn test_decompress_leaves_plain_kernel_untouched() {
+        let dir = tempfile::tempdir().unwrap();
+        let path = dir.path().join("kernel");
+        // An ELF-ish header that is not the gzip magic
+        std::fs::write(&path, b"\x7fELFfake kernel image").unwrap();
+
+        decompress_kernel_if_gzipped(&path).unwrap();
+        assert_eq!(std::fs::read(&path).unwrap(), b"\x7fELFfake kernel image");
+    }
 }

crates/ecr/src/lib.rs

@@ -0,0 +1,41 @@
+//! ecr — ephemeral chroot environments with Linux namespaces.
+//!
+//! This crate is the library behind the `ecr` CLI. It resolves distro and
+//! OCI image references, downloads them through a content cache, extracts
+//! the rootfs into a scratch directory, and runs commands inside
+//! unprivileged user/PID/mount/UTS namespaces — or boots it in a QEMU VM
+//! (see the `qemu_vm` module).
+//!
+//! The main entry points are [`rootfs`] (cache-aware rootfs preparation and
+//! persistence) and [`exec`] (running a command inside a prepared rootfs
+//! with a caller-composed environment, explicit bind targets and a target
+//! architecture).
+
+pub mod chroot;
+pub mod config;
+pub mod distro;
+pub mod download;
+pub mod exec;
+pub mod extract;
+pub mod kernel;
+pub mod mount;
+pub mod namespace;
+pub mod qemu;
+pub mod qemu_vm;
+pub mod rootfs;
+pub mod utils;
+pub mod verbose;
+
+/// Print to stderr only when verbose mode is active (see [`verbose::set`]).
+#[macro_export]
+macro_rules! veprintln {
+    ($($arg:tt)*) => {
+        if $crate::verbose::is_verbose() {
+            eprintln!($($arg)*);
+        }
+    };
+}
+
+pub use exec::{exec, ExecOptions};
+pub use mount::BindTarget;
+pub use rootfs::{PrepareRequest, PreparedRootfs, RootfsCache};

crates/ecr/src/mount.rs

@@ -21,16 +21,41 @@ fn escape_overlay_path(path: &Path) -> Result<String> {
     Ok(s.replace('\\', "\\\\").replace(',', "\\,"))
 }
 
-use crate::cli::Args;
+/// A host directory to expose inside the rootfs.
+///
+/// Read-only targets are overlaid (host content stays pristine, chroot
+/// writes go to a scratch upperdir that dies with the session); read-write
+/// targets are plain bind mounts (chroot writes land on the host).
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct BindTarget {
+    /// Directory on the host.
+    pub source: std::path::PathBuf,
+    /// Absolute mount point inside the rootfs (e.g. `/root/myapp`).
+    pub target: std::path::PathBuf,
+    /// Mount read-write (bind) instead of read-only (overlay).
+    pub read_only: bool,
+}
+
+/// Map an absolute in-chroot path to its location under `rootfs`.
+/// Rejects targets containing `..` components, which would escape the rootfs
+/// and let a mount clobber host paths outside it.
+pub fn in_rootfs(rootfs: &Path, target: &Path) -> Result<std::path::PathBuf> {
+    let relative = target.strip_prefix("/").unwrap_or(target);
+    let escapes = relative
+        .components()
+        .any(|c| matches!(c, std::path::Component::ParentDir));
+    if escapes {
+        return Err(anyhow!(
+            "Path '{}' escapes the rootfs: '..' components are not allowed",
+            target.display()
+        ));
+    }
+    Ok(rootfs.join(relative))
+}
 
 /// Setup all required mounts inside the chroot
 /// Returns a TempDir that must be kept alive for the duration of the chroot
-pub fn setup_mounts(
+pub fn setup_mounts(rootfs: &Path, binds: &[BindTarget]) -> Result<Vec<TempDir>> {
-    rootfs: &Path,
-    bind_paths: &[std::path::PathBuf],
-    bind_rw_paths: &[std::path::PathBuf],
-    args: &Args,
-) -> Result<Vec<TempDir>> {
     // Keep all overlay temp dirs alive
     let mut overlay_temps: Vec<TempDir> = Vec::new();
 
@@ -59,22 +84,15 @@ pub fn setup_mounts(
         eprintln!("Warning: Could not mount /sys: {}", e);
     }
 
-    // Setup overlay mounts for bind paths (read-only via overlay)
+    for bind in binds {
-    if !args.no_bind {
+        let mount_point = in_rootfs(rootfs, &bind.target)?;
-        for bind_path in bind_paths {
+        if bind.read_only {
-            // Skip if this path is also in bind_rw (bind_rw takes precedence)
+            overlay_temps.push(setup_overlay(&bind.source, &mount_point)?);
-            if !bind_rw_paths.contains(bind_path) {
+        } else {
-                let temp = setup_overlay(rootfs, bind_path)?;
+            setup_bind_rw(&bind.source, &mount_point)?;
-                overlay_temps.push(temp);
-            }
         }
     }
 
-    // Setup read-write bind mounts (these override regular bind for same paths)
-    for bind_rw_path in bind_rw_paths {
-        setup_bind_rw(rootfs, bind_rw_path)?;
-    }
-
     Ok(overlay_temps)
 }
 
@@ -164,16 +182,10 @@ fn mount_devpts(rootfs: &Path) -> Result<()> {
     Ok(())
 }
 
-/// Setup overlay mount for workspace directory
+/// Setup overlay mount for a workspace directory
 /// Returns a TempDir that must be kept alive for the overlay to work
-fn setup_overlay(rootfs: &Path, source: &Path) -> Result<TempDir> {
+fn setup_overlay(source: &Path, mount_point: &Path) -> Result<TempDir> {
-    let basename = source
+    std::fs::create_dir_all(mount_point)?;
-        .file_name()
-        .ok_or_else(|| anyhow!("Invalid bind path"))?
-        .to_string_lossy();
-
-    let mount_point = rootfs.join("root").join(basename.as_ref());
-    std::fs::create_dir_all(&mount_point)?;
 
     // Create temp directories for overlay
     let temp_dir = tempfile::tempdir()?;
@@ -196,7 +208,7 @@ fn setup_overlay(rootfs: &Path, source: &Path) -> Result<TempDir> {
 
     mount(
         Some("overlay"),
-        &mount_point,
+        mount_point,
         Some("overlay"),
         MsFlags::empty(),
         Some(options.as_str()),
@@ -208,20 +220,14 @@ fn setup_overlay(rootfs: &Path, source: &Path) -> Result<TempDir> {
 }
 
 /// Setup read-write bind mount
-fn setup_bind_rw(rootfs: &Path, source: &Path) -> Result<()> {
+fn setup_bind_rw(source: &Path, mount_point: &Path) -> Result<()> {
-    let basename = source
+    std::fs::create_dir_all(mount_point)?;
-        .file_name()
-        .ok_or_else(|| anyhow!("Invalid bind-rw path"))?
-        .to_string_lossy();
-
-    let mount_point = rootfs.join("mnt").join(basename.as_ref());
-    std::fs::create_dir_all(&mount_point)?;
 
     let source = source.canonicalize()?;
 
     mount(
         Some(&source),
-        &mount_point,
+        mount_point,
         None::<&str>,
         MsFlags::MS_BIND | MsFlags::MS_REC,
         None::<&str>,
@@ -239,8 +245,42 @@ fn setup_bind_rw(rootfs: &Path, source: &Path) -> Result<()> {
 
 #[cfg(test)]
 mod tests {
-    use super::escape_overlay_path;
+    use super::{escape_overlay_path, in_rootfs, BindTarget};
-    use std::path::Path;
+    use std::path::{Path, PathBuf};
+
+    fn bind(source: &str, target: &str, read_only: bool) -> BindTarget {
+        BindTarget {
+            source: PathBuf::from(source),
+            target: PathBuf::from(target),
+            read_only,
+        }
+    }
+
+    #[test]
+    fn absolute_target_joins_under_rootfs() {
+        let p = in_rootfs(Path::new("/rootfs"), Path::new("/mnt/data")).unwrap();
+        assert_eq!(p, Path::new("/rootfs/mnt/data"));
+    }
+
+    #[test]
+    fn root_target_maps_to_rootfs() {
+        let p = in_rootfs(Path::new("/rootfs"), Path::new("/")).unwrap();
+        assert_eq!(p, Path::new("/rootfs"));
+    }
+
+    #[test]
+    fn parent_components_rejected() {
+        assert!(in_rootfs(Path::new("/rootfs"), Path::new("/../etc")).is_err());
+        assert!(in_rootfs(Path::new("/rootfs"), Path::new("/mnt/../../host")).is_err());
+    }
+
+    #[test]
+    fn bind_target_fields_roundtrip() {
+        let b = bind("/host/dir", "/mnt/dir", false);
+        assert_eq!(b.source, PathBuf::from("/host/dir"));
+        assert_eq!(b.target, PathBuf::from("/mnt/dir"));
+        assert!(!b.read_only);
+    }
 
     #[test]
     fn plain_path_unchanged() {

crates/ecr/src/qemu_vm.rs

@@ -125,10 +125,16 @@ pub fn launch_qemu(config: QemuConfig) -> Result<()> {
     veprintln!("  Kernel append: {}", kernel_append);
 
     // Build QEMU arguments
+    // -machine virt is selected explicitly on riscv64 (see machine_for_arch)
     // -display none suppresses VGA/BIOS output
     // -serial mon:stdio connects serial console to terminal with QEMU monitor muxed
     // -no-reboot makes QEMU exit when the guest requests poweroff/reboot
-    let mut args = vec![
+    let mut args: Vec<String> = Vec::new();
+    if let Some(machine) = machine_for_arch(&config.arch) {
+        args.push("-machine".to_string());
+        args.push(machine.to_string());
+    }
+    args.extend(vec![
         "-kernel".to_string(),
         config.kernel_path.to_string_lossy().to_string(),
         "-initrd".to_string(),
@@ -146,13 +152,16 @@ pub fn launch_qemu(config: QemuConfig) -> Result<()> {
         "user,id=net0".to_string(),
         "-device".to_string(),
         "virtio-net-pci,netdev=net0".to_string(),
-    ];
+    ]);
 
     // Add KVM acceleration if available
     if use_kvm {
         args.push("-enable-kvm".to_string());
         args.push("-cpu".to_string());
         args.push("host".to_string());
+    } else if let Some(cpu) = cpu_for_arch(&config.arch) {
+        args.push("-cpu".to_string());
+        args.push(cpu.to_string());
     }
 
     // Execute QEMU
@@ -182,6 +191,35 @@ fn qemu_binary_for_arch(arch: &str) -> String {
     format!("qemu-system-{}", arch_enum.qemu_system_name())
 }
 
+/// Get the QEMU machine to select for the target architecture, if any.
+///
+/// qemu-system-riscv64's default machine is `spike`, which has neither a
+/// PCI bus (virtio-net-pci fails with "No 'PCI' bus found") nor a 16550
+/// UART (console=ttyS0 output goes nowhere); the `virt` board has both,
+/// plus bundled OpenSBI firmware for -kernel boot.
+fn machine_for_arch(arch: &str) -> Option<&'static str> {
+    match crate::utils::Arch::from_str(arch) {
+        crate::utils::Arch::Riscv64 => Some("virt"),
+        _ => None,
+    }
+}
+
+/// Get the QEMU TCG CPU model to select for the target architecture, when
+/// the emulator default is not sufficient.
+///
+/// Ubuntu builds its riscv64 port against the RVA23 profile (since 25.10),
+/// so its binaries execute instructions QEMU's default `rv64` CPU does not
+/// implement and die with SIGILL early in boot. `rva23s64` implements the
+/// full supervisor profile; baseline rv64gc rootfses (Alpine, older
+/// Ubuntu) run unchanged on it because profiles are supersets. The named
+/// profile CPU needs QEMU 10.1+.
+fn cpu_for_arch(arch: &str) -> Option<&'static str> {
+    match crate::utils::Arch::from_str(arch) {
+        crate::utils::Arch::Riscv64 => Some("rva23s64"),
+        _ => None,
+    }
+}
+
 /// Get architecture suffix for package names
 fn get_arch_package_suffix(arch: &str) -> &'static str {
     crate::utils::Arch::from_str(arch).qemu_package_suffix()
@@ -601,6 +639,33 @@ mod tests {
     use super::*;
     use std::io::Read as _;
 
+    #[test]
+    fn test_machine_for_arch() {
+        // riscv64 must select the virt machine explicitly: the
+        // qemu-system-riscv64 default is `spike`, which has no PCI bus and
+        // no 16550 UART
+        assert_eq!(machine_for_arch("riscv64"), Some("virt"));
+        // Other architectures keep their emulator's default machine
+        assert_eq!(machine_for_arch("amd64"), None);
+        assert_eq!(machine_for_arch("x86_64"), None);
+        assert_eq!(machine_for_arch("arm64"), None);
+        assert_eq!(machine_for_arch("aarch64"), None);
+        assert_eq!(machine_for_arch("ppc64le"), None);
+        assert_eq!(machine_for_arch("s390x"), None);
+    }
+
+    #[test]
+    fn test_cpu_for_arch() {
+        // Ubuntu's riscv64 userland needs the RVA23 profile CPU; QEMU's
+        // default `rv64` CPU SIGILLs on it early in boot
+        assert_eq!(cpu_for_arch("riscv64"), Some("rva23s64"));
+        // Other architectures keep their emulator's default CPU
+        assert_eq!(cpu_for_arch("amd64"), None);
+        assert_eq!(cpu_for_arch("x86_64"), None);
+        assert_eq!(cpu_for_arch("arm64"), None);
+        assert_eq!(cpu_for_arch("aarch64"), None);
+    }
+
     /// Parse a newc cpio archive into (name, ino, mode, nlink, file_size, data) tuples
     fn parse_cpio(archive: Vec<u8>) -> Vec<(String, u32, u32, u32, u32, Vec<u8>)> {
         let mut cursor = std::io::Cursor::new(archive);

crates/ecr/src/rootfs.rs

@@ -0,0 +1,612 @@
+//! Cache-aware rootfs lifecycle: resolve an image reference, download
+//! through the tarball cache, extract into a scratch directory, and
+//! optionally persist a provisioned rootfs back into the cache.
+//!
+//! The hot-cell flow is [`RootfsCache::prepare_provisioned`]: provision
+//! once (package installs, user setup, …), and every subsequent call —
+//! in this or another process sharing the cache — hits the persisted
+//! entry and skips both the download and the provisioning step:
+//!
+//! ```no_run
+//! use ecr::{chroot, ExecOptions, PrepareRequest, RootfsCache};
+//!
+//! # fn main() -> anyhow::Result<()> {
+//! let cache = RootfsCache::new(RootfsCache::default_dir()?);
+//! let req = PrepareRequest::new("alpine:3.23");
+//!
+//! let rootfs = cache.prepare_provisioned(&req, |rootfs| {
+//!     let code = rootfs.exec(&ExecOptions {
+//!         command: vec!["apk".into(), "add".into(), "curl".into()],
+//!         env: chroot::default_env(rootfs.dir()),
+//!         ..ExecOptions::default()
+//!     })?;
+//!     if code != 0 {
+//!         anyhow::bail!("provisioning command failed with exit code {}", code);
+//!     }
+//!     Ok(())
+//! })?;
+//!
+//! // Amortized run: the provisioned entry is hit directly
+//! let code = rootfs.exec(&ExecOptions {
+//!     command: vec!["curl".into(), "--version".into()],
+//!     env: chroot::default_env(rootfs.dir()),
+//!     ..ExecOptions::default()
+//! })?;
+//! # let _ = code; Ok(())
+//! # }
+//! ```
+
+use std::path::{Path, PathBuf};
+
+use anyhow::{anyhow, Context, Result};
+use tempfile::TempDir;
+
+use crate::distro::{
+    map_arch, parse_image_ref, resolve_distro_url, resolve_distro_version, Distro, ImageSource,
+};
+use crate::download::{digest_sidecar, download_image, fetch_oci_digest};
+use crate::exec::ExecOptions;
+use crate::extract::extract_tarball;
+use crate::veprintln;
+
+/// Sidecar suffix marking a cache entry that holds a provisioned rootfs.
+const PROVISIONED_SUFFIX: &str = "provisioned";
+
+/// Sidecar path for a cache entry: `foo.tar.gz` → `foo.tar.gz.<suffix>`.
+fn sidecar(path: &Path, suffix: &str) -> PathBuf {
+    let mut s = path.as_os_str().to_owned();
+    s.push(".");
+    s.push(suffix);
+    PathBuf::from(s)
+}
+
+/// The image tarball cache (default location: `~/.cache/ecr`).
+#[derive(Debug, Clone)]
+pub struct RootfsCache {
+    dir: PathBuf,
+}
+
+impl RootfsCache {
+    pub fn new(dir: impl Into<PathBuf>) -> Self {
+        RootfsCache { dir: dir.into() }
+    }
+
+    /// Default cache directory: `~/.cache/ecr` (or the platform equivalent).
+    pub fn default_dir() -> Result<PathBuf> {
+        dirs::cache_dir()
+            .map(|p| p.join("ecr"))
+            .ok_or_else(|| anyhow!("Could not determine cache directory"))
+    }
+
+    pub fn dir(&self) -> &Path {
+        &self.dir
+    }
+
+    /// Cache entry (tarball path) for an image source and architecture.
+    pub fn tarball_path(&self, source: &ImageSource, arch: &str) -> PathBuf {
+        self.dir.join(generate_cache_filename(source, arch))
+    }
+
+    /// Resolve `req`, download through the cache when needed, and extract
+    /// into a fresh scratch directory (removed when the returned
+    /// [`PreparedRootfs`] is dropped).
+    pub fn prepare(&self, req: &PrepareRequest) -> Result<PreparedRootfs> {
+        let arch = req.resolved_arch();
+        let source = resolve_source(&req.image, &arch)?;
+        let cache_path = self.tarball_path(&source, &arch);
+
+        // OCI images with a floating tag (":latest") need a freshness check:
+        // fetch the current manifest digest from the registry and compare it
+        // against the digest stored from the last download.  Only re-pull when
+        // the digest has actually changed.  On a network error we fall back to
+        // the cached image with a warning rather than hard-failing.
+        let oci_digest_changed = if cache_path.exists() {
+            if let ImageSource::OciImage {
+                registry,
+                repository,
+                tag,
+                ..
+            } = &source
+            {
+                if tag == "latest" {
+                    match fetch_oci_digest(registry, repository, tag) {
+                        Ok(current) => {
+                            let stored = std::fs::read_to_string(digest_sidecar(&cache_path)).ok();
+                            stored.as_deref() != Some(current.trim())
+                        }
+                        Err(e) => {
+                            eprintln!(
+                                "Warning: could not check image freshness ({}); using cache",
+                                e
+                            );
+                            false
+                        }
+                    }
+                } else {
+                    false // pinned tags are assumed immutable
+                }
+            } else {
+                false
+            }
+        } else {
+            false // cache absent — download triggered by !cache_path.exists() below
+        };
+
+        // Download when not cached, explicitly requested, or the remote digest
+        // has moved
+        if req.no_cache || !cache_path.exists() || oci_digest_changed {
+            std::fs::create_dir_all(&self.dir).with_context(|| {
+                format!("Failed to create cache directory {}", self.dir.display())
+            })?;
+            download_image(&source, &cache_path, &arch)?;
+        } else {
+            veprintln!("Using cached tarball: {}", cache_path.display());
+        }
+
+        extract_prepared(cache_path, arch)
+    }
+
+    /// Prepare a provisioned rootfs with cache amortization: when the cache
+    /// entry is already marked provisioned it is extracted as-is; otherwise
+    /// the rootfs is prepared from the pristine image, `provision` runs
+    /// once, and the result is persisted into the cache so subsequent calls
+    /// (including from other processes sharing this cache) skip both the
+    /// download and the provisioning step.
+    ///
+    /// A provisioned entry no longer tracks the upstream image: for
+    /// `:latest` OCI images the freshness check is skipped on a marker hit.
+    /// Re-provision by removing the entry and its `.provisioned` sidecar, or
+    /// by passing `no_cache: true` (which re-downloads, re-provisions and
+    /// re-persists).
+    pub fn prepare_provisioned<F>(
+        &self,
+        req: &PrepareRequest,
+        provision: F,
+    ) -> Result<PreparedRootfs>
+    where
+        F: FnOnce(&PreparedRootfs) -> Result<()>,
+    {
+        let arch = req.resolved_arch();
+        let source = resolve_source(&req.image, &arch)?;
+        let cache_path = self.tarball_path(&source, &arch);
+        let marker = sidecar(&cache_path, PROVISIONED_SUFFIX);
+
+        if !req.no_cache && cache_path.exists() && marker.exists() {
+            veprintln!("Using provisioned cache entry: {}", cache_path.display());
+            return extract_prepared(cache_path, arch);
+        }
+
+        let rootfs = self.prepare(req)?;
+        provision(&rootfs)?;
+        rootfs.persist().with_context(|| {
+            format!(
+                "Failed to persist provisioned rootfs to {}",
+                cache_path.display()
+            )
+        })?;
+        Ok(rootfs)
+    }
+}
+
+/// Request for [`RootfsCache::prepare`] / [`RootfsCache::prepare_provisioned`].
+#[derive(Debug, Clone)]
+pub struct PrepareRequest {
+    /// Image reference: a distro name ("ubuntu", "ubuntu:noble",
+    /// "alpine:3.23") or an OCI reference ("debian",
+    /// "ghcr.io/org/image:tag", "docker://…").
+    pub image: String,
+
+    /// Target architecture (e.g. "amd64", "arm64").  Empty selects the host
+    /// architecture.
+    pub arch: String,
+
+    /// Ignore the cache and download a fresh image.
+    pub no_cache: bool,
+}
+
+impl PrepareRequest {
+    pub fn new(image: impl Into<String>) -> Self {
+        PrepareRequest {
+            image: image.into(),
+            arch: String::new(),
+            no_cache: false,
+        }
+    }
+
+    /// The effective architecture: the request value, or the host arch.
+    pub fn resolved_arch(&self) -> String {
+        if self.arch.is_empty() {
+            crate::utils::get_host_arch().debian_name().to_string()
+        } else {
+            self.arch.clone()
+        }
+    }
+}
+
+/// A rootfs extracted into a scratch directory, ready for [`ExecOptions`] /
+/// [`crate::exec`] or QEMU.  The directory is removed when this value is
+/// dropped, unless [`PreparedRootfs::persist`] ran first.
+#[derive(Debug)]
+pub struct PreparedRootfs {
+    rootfs: TempDir,
+    cache_path: PathBuf,
+    arch: String,
+}
+
+impl PreparedRootfs {
+    /// The extracted rootfs directory.
+    pub fn dir(&self) -> &Path {
+        self.rootfs.path()
+    }
+
+    /// Architecture this rootfs was prepared for.
+    pub fn arch(&self) -> &str {
+        &self.arch
+    }
+
+    /// The cache entry this rootfs was prepared from.
+    pub fn cache_entry(&self) -> &Path {
+        &self.cache_path
+    }
+
+    /// Run a command inside the rootfs (see [`crate::exec`]).  When
+    /// `opts.arch` is empty, this rootfs's architecture is used.
+    pub fn exec(&self, opts: &ExecOptions) -> Result<i32> {
+        if opts.arch.is_empty() {
+            let mut opts = opts.clone();
+            opts.arch = self.arch.clone();
+            return crate::exec::exec(self.dir(), &opts);
+        }
+        crate::exec::exec(self.dir(), opts)
+    }
+
+    /// Persist the current contents of the rootfs into the cache entry it
+    /// was prepared from, replacing the pristine image tarball, and mark
+    /// the entry provisioned.  Later preparations for the same image and
+    /// architecture hit this entry directly; note that plain
+    /// [`RootfsCache::prepare`] also returns the provisioned contents
+    /// (indistinguishable from a pristine hit) — only
+    /// [`RootfsCache::prepare_provisioned`] interprets the marker.
+    pub fn persist(&self) -> Result<()> {
+        pack_rootfs(self.dir(), &self.cache_path)?;
+        std::fs::write(sidecar(&self.cache_path, PROVISIONED_SUFFIX), b"").with_context(|| {
+            format!(
+                "Failed to write provisioned marker for {}",
+                self.cache_path.display()
+            )
+        })?;
+        veprintln!("Persisted rootfs to cache: {}", self.cache_path.display());
+        Ok(())
+    }
+}
+
+/// Parse an image reference and resolve floating version aliases ("latest",
+/// "lts", "edge", …) to a concrete version, so the cache key is stable
+/// (e.g. "ubuntu-noble-amd64", not "ubuntu-latest-amd64") and a future
+/// release automatically gets its own cache entry.
+fn resolve_source(image: &str, arch: &str) -> Result<ImageSource> {
+    let source = parse_image_ref(image, arch)?;
+    match source {
+        ImageSource::DirectTarball { distro, version } => {
+            let resolved = resolve_distro_version(&distro, version.as_deref(), arch)?;
+            Ok(ImageSource::DirectTarball {
+                distro,
+                version: Some(resolved),
+            })
+        }
+        other => Ok(other),
+    }
+}
+
+fn extract_prepared(cache_path: PathBuf, arch: String) -> Result<PreparedRootfs> {
+    let temp = tempfile::tempdir().context("Failed to create temporary directory")?;
+    let rootfs = temp.path().to_path_buf();
+
+    veprintln!("Extracting to: {}", rootfs.display());
+    extract_tarball(&cache_path, &rootfs)?;
+
+    Ok(PreparedRootfs {
+        rootfs: temp,
+        cache_path,
+        arch,
+    })
+}
+
+/// Write a tarball of `rootfs` at `dest`, compressed according to dest's
+/// extension (.tar.gz, .tar.xz, .tar.zst, plain .tar), atomically via a
+/// `.partial` file.
+fn pack_rootfs(rootfs: &Path, dest: &Path) -> Result<()> {
+    // Packing the tree into a tarball placed inside it would recurse
+    // forever: the walker keeps seeing the archive grow.
+    let rootfs_canonical = rootfs
+        .canonicalize()
+        .with_context(|| format!("Failed to resolve rootfs directory {}", rootfs.display()))?;
+    if let Some(parent) = dest.parent() {
+        if let Ok(parent_canonical) = parent.canonicalize() {
+            if parent_canonical.starts_with(&rootfs_canonical) {
+                return Err(anyhow!(
+                    "Cache entry {} must live outside the rootfs",
+                    dest.display()
+                ));
+            }
+        }
+    }
+
+    let filename = dest.file_name().and_then(|n| n.to_str()).unwrap_or("");
+    let partial = dest.with_extension("partial");
+
+    let file = std::fs::File::create(&partial)
+        .with_context(|| format!("Failed to create {}", partial.display()))?;
+
+    let result: Result<()> = (|| {
+        if filename.ends_with(".tar.gz") || filename.ends_with(".tgz") {
+            let encoder = flate2::write::GzEncoder::new(file, flate2::Compression::default());
+            let encoder = write_rootfs_tar(rootfs, encoder)?;
+            encoder.finish().context("Failed to finalise gzip stream")?;
+        } else if filename.ends_with(".tar.xz") || filename.ends_with(".txz") {
+            let encoder = xz2::write::XzEncoder::new(file, 6);
+            let encoder = write_rootfs_tar(rootfs, encoder)?;
+            encoder.finish().context("Failed to finalise xz stream")?;
+        } else if filename.ends_with(".tar.zst") || filename.ends_with(".tar.zstd") {
+            let encoder = zstd::stream::write::Encoder::new(file, 0)
+                .context("Failed to create zstd encoder")?;
+            let encoder = write_rootfs_tar(rootfs, encoder)?;
+            encoder.finish().context("Failed to finalise zstd stream")?;
+        } else {
+            write_rootfs_tar(rootfs, file)?;
+        }
+        Ok(())
+    })();
+
+    if result.is_err() {
+        // Best-effort cleanup; ignore errors (file may not exist if creation failed).
+        let _ = std::fs::remove_file(&partial);
+        return result;
+    }
+
+    std::fs::rename(&partial, dest)
+        .with_context(|| format!("Failed to move packed rootfs to {}", dest.display()))
+}
+
+/// Write the rootfs tree into a tar archive streamed to `writer`, returning
+/// the writer so the caller can finalise the compression stream.
+fn write_rootfs_tar<W: std::io::Write>(rootfs: &Path, writer: W) -> Result<W> {
+    let mut builder = tar::Builder::new(writer);
+    // Store symlinks as symlinks; following them would duplicate the target's
+    // contents into the archive (and recurse into symlinked directories).
+    builder.follow_symlinks(false);
+
+    let entries = std::fs::read_dir(rootfs)
+        .with_context(|| format!("Failed to read {}", rootfs.display()))?;
+
+    for entry in entries {
+        let entry =
+            entry.with_context(|| format!("Failed to read entry in {}", rootfs.display()))?;
+        let path = entry.path();
+        let name = entry.file_name();
+
+        // symlink_metadata: never follow symlinks — a top-level symlink to a
+        // directory must be stored as a link, not recursed into.
+        let meta = std::fs::symlink_metadata(&path)
+            .with_context(|| format!("Failed to stat {}", path.display()))?;
+
+        if meta.is_dir() {
+            builder
+                .append_dir_all(&name, &path)
+                .with_context(|| format!("Failed to archive {}", path.display()))?;
+        } else {
+            builder
+                .append_path_with_name(&path, &name)
+                .with_context(|| format!("Failed to archive {}", path.display()))?;
+        }
+    }
+
+    builder
+        .into_inner()
+        .context("Failed to finalise tar archive")
+}
+
+/// Generate a cache filename based on the image source
+fn generate_cache_filename(source: &ImageSource, arch: &str) -> String {
+    match source {
+        ImageSource::DirectTarball { distro, version } => {
+            let distro_name = match distro {
+                Distro::Ubuntu => "ubuntu",
+                Distro::Alpine => "alpine",
+            };
+            let distro_arch = map_arch(*distro, arch);
+            // Get extension from URL
+            let url = resolve_distro_url(distro, version.as_deref(), arch).unwrap_or_default();
+            let ext = get_tarball_extension(&url);
+            format!(
+                "{}-{}-{}.{}",
+                distro_name,
+                version.as_deref().unwrap_or("latest"),
+                distro_arch,
+                ext
+            )
+        }
+        ImageSource::OciImage {
+            registry,
+            repository,
+            tag,
+            architecture,
+        } => {
+            // Sanitize for filename
+            let safe_registry = registry.replace(['.', ':'], "_");
+            let safe_repo = repository.replace(['/', ':'], "_");
+            format!(
+                "oci-{}-{}-{}-{}.tar.gz",
+                safe_registry, safe_repo, tag, architecture
+            )
+        }
+    }
+}
+
+fn get_tarball_extension(url: &str) -> &str {
+    // Extract extension from URL (e.g., .tar.gz, .tar.xz, .tar.zst)
+    if url.ends_with(".tar.zst") {
+        "tar.zst"
+    } else if url.ends_with(".tar.xz") {
+        "tar.xz"
+    } else if url.ends_with(".tar.gz") {
+        "tar.gz"
+    } else if url.ends_with(".tar.bz2") {
+        "tar.bz2"
+    } else {
+        "tar.gz" // default
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use std::os::unix::fs::PermissionsExt;
+
+    fn direct_tarball(distro: Distro, version: &str) -> ImageSource {
+        ImageSource::DirectTarball {
+            distro,
+            version: Some(version.to_string()),
+        }
+    }
+
+    #[test]
+    fn cache_filename_direct_tarball() {
+        // Explicit codename/version: no network lookups
+        let cache = RootfsCache::new("/cache");
+        assert_eq!(
+            cache.tarball_path(&direct_tarball(Distro::Ubuntu, "noble"), "amd64"),
+            PathBuf::from("/cache/ubuntu-noble-amd64.tar.gz")
+        );
+        assert_eq!(
+            cache.tarball_path(&direct_tarball(Distro::Alpine, "3.23.1"), "amd64"),
+            PathBuf::from("/cache/alpine-3.23.1-x86_64.tar.gz")
+        );
+    }
+
+    #[test]
+    fn cache_filename_oci_sanitized() {
+        let cache = RootfsCache::new("/cache");
+        let source = ImageSource::OciImage {
+            registry: "docker.io".to_string(),
+            repository: "library/ubuntu".to_string(),
+            tag: "latest".to_string(),
+            architecture: "amd64".to_string(),
+        };
+        assert_eq!(
+            cache.tarball_path(&source, "amd64"),
+            PathBuf::from("/cache/oci-docker_io-library_ubuntu-latest-amd64.tar.gz")
+        );
+    }
+
+    #[test]
+    fn resolved_arch_defaults_to_host() {
+        let req = PrepareRequest::new("alpine");
+        assert_eq!(
+            req.resolved_arch(),
+            crate::utils::get_host_arch().debian_name()
+        );
+
+        let mut req = PrepareRequest::new("alpine");
+        req.arch = "arm64".to_string();
+        assert_eq!(req.resolved_arch(), "arm64");
+    }
+
+    #[test]
+    fn sidecar_appends_suffix() {
+        assert_eq!(
+            sidecar(Path::new("/cache/foo.tar.gz"), PROVISIONED_SUFFIX),
+            PathBuf::from("/cache/foo.tar.gz.provisioned")
+        );
+    }
+
+    /// Build a minimal rootfs tree with a nested executable and a symlink,
+    /// pack it, and extract it back through the public extract_tarball path.
+    fn roundtrip(dest_name: &str) {
+        let src = tempfile::tempdir().unwrap();
+        std::fs::write(src.path().join("hello.txt"), b"hello").unwrap();
+        std::fs::create_dir_all(src.path().join("usr/bin")).unwrap();
+        std::fs::write(src.path().join("usr/bin/tool"), b"#!/bin/sh\n").unwrap();
+        std::fs::set_permissions(
+            src.path().join("usr/bin/tool"),
+            std::fs::Permissions::from_mode(0o755),
+        )
+        .unwrap();
+        std::os::unix::fs::symlink("hello.txt", src.path().join("link.txt")).unwrap();
+
+        let cache = tempfile::tempdir().unwrap();
+        let dest = cache.path().join(dest_name);
+        pack_rootfs(src.path(), &dest).unwrap();
+
+        let out = tempfile::tempdir().unwrap();
+        crate::extract::extract_tarball(&dest, out.path()).unwrap();
+
+        assert_eq!(
+            std::fs::read(out.path().join("hello.txt")).unwrap(),
+            b"hello"
+        );
+        let mode = std::fs::metadata(out.path().join("usr/bin/tool"))
+            .unwrap()
+            .permissions()
+            .mode();
+        assert_eq!(mode & 0o777, 0o755, "executable bit must survive");
+        assert_eq!(
+            std::fs::read_link(out.path().join("link.txt")).unwrap(),
+            Path::new("hello.txt")
+        );
+    }
+
+    #[test]
+    fn persist_roundtrip_gzip() {
+        roundtrip("rootfs.tar.gz");
+    }
+
+    #[test]
+    fn persist_roundtrip_xz() {
+        roundtrip("rootfs.tar.xz");
+    }
+
+    #[test]
+    fn persist_roundtrip_zstd() {
+        roundtrip("rootfs.tar.zst");
+    }
+
+    #[test]
+    fn persist_roundtrip_plain_tar() {
+        roundtrip("rootfs.tar");
+    }
+
+    #[test]
+    fn persist_writes_entry_and_provisioned_marker() {
+        let rootfs_dir = tempfile::tempdir().unwrap();
+        std::fs::write(rootfs_dir.path().join("file.txt"), b"data").unwrap();
+
+        let cache_dir = tempfile::tempdir().unwrap();
+        let cache_path = cache_dir.path().join("ubuntu-noble-amd64.tar.gz");
+
+        let prepared = PreparedRootfs {
+            rootfs: rootfs_dir,
+            cache_path: cache_path.clone(),
+            arch: "amd64".to_string(),
+        };
+        prepared.persist().unwrap();
+
+        assert!(cache_path.exists());
+        assert!(sidecar(&cache_path, PROVISIONED_SUFFIX).exists());
+
+        // The persisted entry extracts back to the original contents
+        let out = tempfile::tempdir().unwrap();
+        crate::extract::extract_tarball(&cache_path, out.path()).unwrap();
+        assert_eq!(std::fs::read(out.path().join("file.txt")).unwrap(), b"data");
+    }
+
+    #[test]
+    fn pack_failure_leaves_no_partial_file() {
+        // A nonexistent rootfs must fail cleanly and clean up the .partial
+        let cache = tempfile::tempdir().unwrap();
+        let dest = cache.path().join("x.tar.gz");
+        assert!(pack_rootfs(Path::new("/nonexistent-rootfs"), &dest).is_err());
+        assert!(!dest.exists());
+        assert!(!dest.with_extension("partial").exists());
+    }
+}

crates/ecr/src/utils.rs

@@ -42,6 +42,9 @@ pub enum Arch {
 
 impl Arch {
     /// Get the architecture from a string (any common naming convention)
+    /// Not a FromStr impl: unrecognized names map to Arch::Unknown rather
+    /// than an error, by design.
+    #[allow(clippy::should_implement_trait)]
     pub fn from_str(s: &str) -> Self {
         match s {
             "amd64" | "x86_64" | "x64" => Arch::Amd64,

src/chroot.rs

@@ -1,189 +0,0 @@
-use crate::veprintln;
-use anyhow::{anyhow, Context, Result};
-use nix::unistd::{chroot, execve};
-use std::collections::HashMap;
-use std::path::Path;
-
-/// Run a command in the chroot environment
-pub fn run_chroot(
-    rootfs: &Path,
-    command: Option<Vec<String>>,
-    bind_rw_paths: &[std::path::PathBuf],
-) -> Result<()> {
-    // Get TERM from host before chroot
-    let host_term = std::env::var("TERM").unwrap_or_else(|_| "xterm-256color".to_string());
-
-    // Set hostname in UTS namespace
-    if let Err(e) = crate::namespace::set_hostname("chroot") {
-        eprintln!("Warning: Failed to set hostname: {}", e);
-    }
-
-    // Detect shell before chroot (we're still outside)
-    let shell = crate::utils::detect_shell(rootfs);
-
-    // Change to root directory in chroot
-    chroot(rootfs).context("Failed to chroot")?;
-
-    // Now we're inside the chroot - set up environment based on chroot filesystem
-
-    // Set up environment variables (after chroot, so paths are correct)
-    let env = setup_environment(shell, &host_term);
-
-    // Determine the command to run
-    let (program, args) = match command {
-        Some(cmd) if !cmd.is_empty() => {
-            let program = cmd[0].clone();
-            let args = cmd
-                .iter()
-                .map(|s| {
-                    std::ffi::CString::new(s.as_str())
-                        .with_context(|| format!("Argument contains a null byte: {:?}", s))
-                })
-                .collect::<Result<Vec<_>>>()?;
-            (program, args)
-        }
-        _ => {
-            // Run shell (already determined above based on chroot filesystem)
-            let program = shell.to_string();
-            let args =
-                vec![std::ffi::CString::new(shell).context("Shell path contains a null byte")?];
-            (program, args)
-        }
-    };
-
-    // Build an explicit envp from setup_environment so the host environment
-    // is never inherited.  execve takes this array directly; the host process
-    // environment is not touched at all.
-    let env_cstrings = env
-        .iter()
-        .map(|(k, v)| {
-            std::ffi::CString::new(format!("{}={}", k, v))
-                .with_context(|| format!("Environment variable contains a null byte: {}={}", k, v))
-        })
-        .collect::<Result<Vec<_>>>()?;
-
-    // Change to first bind_rw directory if available, otherwise /root, otherwise /
-    // bind_rw paths are mounted at /mnt/<basename> (see mount.rs setup_bind_rw)
-    let working_dir = if let Some(first_bind_rw) = bind_rw_paths.first() {
-        let dest_dir = Path::new("/mnt").join(first_bind_rw.file_name().unwrap_or_default());
-        if dest_dir.exists() {
-            dest_dir
-        } else if Path::new("/root").exists() {
-            Path::new("/root").to_path_buf()
-        } else {
-            Path::new("/").to_path_buf()
-        }
-    } else if Path::new("/root").exists() {
-        Path::new("/root").to_path_buf()
-    } else {
-        Path::new("/").to_path_buf()
-    };
-    std::env::set_current_dir(&working_dir).context("Failed to change to working directory")?;
-
-    // Print welcome message
-    veprintln!("Entering chroot at {}", rootfs.display());
-    for path in bind_rw_paths {
-        let basename = path
-            .file_name()
-            .map(|n| n.to_string_lossy())
-            .unwrap_or_default();
-        veprintln!("Read-write mount: /mnt/{}", basename);
-    }
-    veprintln!("Working directory: {}", working_dir.display());
-
-    // Check if the program exists
-    if !Path::new(&program).exists() {
-        // Try to find it in PATH
-        let found = env.get("PATH").and_then(|path| {
-            path.split(':')
-                .map(|p| std::path::PathBuf::from(p).join(&program))
-                .find(|p| p.exists())
-        });
-
-        if found.is_none() {
-            return Err(anyhow!("Program not found: {}", program));
-        }
-    }
-
-    // Exec the program directly with an explicit, isolated environment.
-    // execve never returns on success.
-    let program_cstr = std::ffi::CString::new(program.as_str()).context("Invalid program name")?;
-
-    let result = execve(&program_cstr, &args, &env_cstrings);
-
-    match result {
-        Ok(_) => Ok(()), // Never reached
-        Err(e) => Err(anyhow!("Failed to exec {}: {}", program, e)),
-    }
-}
-
-/// Setup default environment variables for chroot
-/// Must be called AFTER chroot so paths are resolved inside the chroot
-fn setup_environment(shell: &str, term: &str) -> HashMap<&'static str, String> {
-    let mut env = HashMap::new();
-
-    env.insert("HOME", "/root".to_string());
-    env.insert("USER", "root".to_string());
-    env.insert("SHELL", shell.to_string());
-    env.insert("TERM", term.to_string());
-    env.insert(
-        "PATH",
-        "/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin".to_string(),
-    );
-
-    env
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[test]
-    fn test_setup_environment_defaults() {
-        let env = setup_environment("/bin/bash", "xterm-256color");
-
-        assert_eq!(env.get("HOME"), Some(&"/root".to_string()));
-        assert_eq!(env.get("USER"), Some(&"root".to_string()));
-        assert_eq!(env.get("SHELL"), Some(&"/bin/bash".to_string()));
-        assert_eq!(env.get("TERM"), Some(&"xterm-256color".to_string()));
-        assert_eq!(
-            env.get("PATH"),
-            Some(&"/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin".to_string())
-        );
-    }
-
-    #[test]
-    fn test_setup_environment_custom_shell() {
-        let env = setup_environment("/usr/bin/zsh", "screen");
-
-        assert_eq!(env.get("SHELL"), Some(&"/usr/bin/zsh".to_string()));
-        assert_eq!(env.get("TERM"), Some(&"screen".to_string()));
-    }
-
-    #[test]
-    fn test_environment_isolation() {
-        // Verify that setup_environment creates a clean environment
-        // without inheriting from the host
-        let env = setup_environment("/bin/sh", "dumb");
-
-        // Should have exactly 5 environment variables
-        assert_eq!(env.len(), 5);
-
-        // Should NOT have any host-specific variables
-        assert!(!env.contains_key("LANG"));
-        assert!(!env.contains_key("DISPLAY"));
-        assert!(!env.contains_key("PWD"));
-    }
-
-    #[test]
-    fn test_path_contains_standard_directories() {
-        let env = setup_environment("/bin/bash", "xterm");
-        let path = env.get("PATH").expect("PATH should be set");
-
-        // Verify essential directories are in PATH
-        assert!(path.contains("/bin"));
-        assert!(path.contains("/usr/bin"));
-        assert!(path.contains("/sbin"));
-        assert!(path.contains("/usr/sbin"));
-    }
-}

src/main.rs

@@ -1,371 +0,0 @@
-mod chroot;
-mod cli;
-mod config;
-mod distro;
-mod download;
-mod extract;
-mod kernel;
-mod mount;
-mod namespace;
-mod qemu;
-mod qemu_vm;
-mod utils;
-mod verbose;
-
-/// Print to stderr only when --verbose / -v is active.
-#[macro_export]
-macro_rules! veprintln {
-    ($($arg:tt)*) => {
-        if $crate::verbose::is_verbose() {
-            eprintln!($($arg)*);
-        }
-    };
-}
-
-use anyhow::{Context, Result};
-use clap::Parser;
-
-use cli::Args;
-use config::Config;
-use distro::{
-    map_arch, parse_image_ref, resolve_distro_url, resolve_distro_version, Distro, ImageSource,
-};
-use download::{digest_sidecar, download_image, fetch_oci_digest};
-use extract::extract_tarball;
-
-fn main() -> Result<()> {
-    let args = Args::parse();
-
-    // Initialise verbosity before anything else so all downstream code can use veprintln!.
-    verbose::set(args.verbose);
-
-    // Load config file
-    let config = Config::load()?;
-
-    // Get architecture
-    let host_arch = get_host_arch();
-    let arch = args.arch.clone().unwrap_or_else(|| host_arch.clone());
-
-    // Parse image reference
-    let image_source = parse_image_ref(&args.distro, &arch)?;
-
-    // For DirectTarball, resolve floating aliases ("latest", "lts") to a concrete
-    // version string *before* computing the cache key.  This ensures we cache as
-    // e.g. "ubuntu-noble-amd64" rather than "ubuntu-latest-amd64", so a future
-    // release automatically gets its own cache entry.
-    let image_source = match image_source {
-        ImageSource::DirectTarball { distro, version } => {
-            let resolved = resolve_distro_version(&distro, version.as_deref(), &arch)?;
-            ImageSource::DirectTarball {
-                distro,
-                version: Some(resolved),
-            }
-        }
-        other => other,
-    };
-
-    // Determine cache directory and filename
-    let cache_dir = dirs::cache_dir()
-        .expect("Could not determine cache directory")
-        .join("ecr");
-    let cache_filename = generate_cache_filename(&image_source, &arch);
-    let cache_path = cache_dir.join(&cache_filename);
-
-    // OCI images with a floating tag (":latest") need a freshness check:
-    // fetch the current manifest digest from the registry and compare it
-    // against the digest stored from the last download.  Only re-pull when
-    // the digest has actually changed.  On a network error we fall back to
-    // the cached image with a warning rather than hard-failing.
-    let oci_digest_changed = if cache_path.exists() {
-        if let ImageSource::OciImage {
-            registry,
-            repository,
-            tag,
-            ..
-        } = &image_source
-        {
-            if tag == "latest" {
-                match fetch_oci_digest(registry, repository, tag) {
-                    Ok(current) => {
-                        let stored = std::fs::read_to_string(digest_sidecar(&cache_path)).ok();
-                        stored.as_deref() != Some(current.trim())
-                    }
-                    Err(e) => {
-                        eprintln!(
-                            "Warning: could not check image freshness ({}); using cache",
-                            e
-                        );
-                        false
-                    }
-                }
-            } else {
-                false // pinned tags are assumed immutable
-            }
-        } else {
-            false
-        }
-    } else {
-        false // cache absent — download triggered by !cache_path.exists() below
-    };
-
-    // Download if not cached, --no-cache, or the remote digest has moved
-    if args.no_cache || !cache_path.exists() || oci_digest_changed {
-        std::fs::create_dir_all(&cache_dir)?;
-        download_image(&image_source, &cache_path, &arch)?;
-    } else {
-        veprintln!("Using cached tarball: {}", cache_path.display());
-    }
-
-    // Check QEMU if foreign architecture (for namespace mode)
-    // For VM mode, we don't need binfmt_misc since we're using system emulation
-    if args.kernel.is_none() && arch != host_arch {
-        qemu::check_binfmt(&arch)?;
-    }
-
-    // Create temp directory for extraction
-    let temp_dir = tempfile::tempdir()?;
-    let rootfs = temp_dir.path().to_path_buf();
-
-    veprintln!("Extracting to: {}", rootfs.display());
-    extract_tarball(&cache_path, &rootfs)?;
-
-    // Branch based on --kernel flag
-    // Option<Option<PathBuf>> (require_equals: the value must use =PATH syntax
-    // so it can never swallow the DISTRO positional):
-    //   None              -> --kernel not specified, use namespace mode
-    //   Some(None)        -> --kernel without path, download default kernel
-    //   Some(Some(path))  -> --kernel=/path/to/vmlinuz, use provided kernel
-    if let Some(kernel_opt) = &args.kernel {
-        // VM mode boots an initramfs: host bind mounts are never applied
-        if !args.bind.is_empty() || !args.bind_rw.is_empty() {
-            eprintln!(
-                "Warning: --bind/--bind-rw are ignored with --kernel \
-                 (the VM boots from an initramfs, no host directories are mounted)"
-            );
-        }
-
-        // QEMU system mode
-        let kernel_path = match kernel_opt {
-            Some(path) => {
-                veprintln!("QEMU mode: using provided kernel {}", path.display());
-                path.clone()
-            }
-            None => {
-                veprintln!("QEMU mode: downloading default kernel...");
-                kernel::get_default_kernel(&cache_dir, &arch)?
-            }
-        };
-
-        let command = if args.command.is_empty() {
-            None
-        } else {
-            Some(args.command.clone())
-        };
-
-        let result = qemu_vm::launch_qemu(qemu_vm::QemuConfig {
-            kernel_path,
-            rootfs_path: rootfs,
-            memory: args.memory.clone(),
-            arch: arch.clone(),
-            command,
-        });
-
-        // Cleanup happens automatically via tempfile
-        if result.is_ok() {
-            veprintln!("Cleanup complete.");
-        }
-
-        result
-    } else {
-        // Namespace/chroot mode
-        let exit_code = namespace_mode(args, rootfs, config)?;
-        // Propagate the command's exit code, cleaning up the extracted rootfs
-        // first: process::exit does not run destructors.
-        drop(temp_dir);
-        if exit_code != 0 {
-            std::process::exit(exit_code);
-        }
-        Ok(())
-    }
-}
-
-/// Run in namespace/chroot mode, returning the command's exit code
-fn namespace_mode(args: Args, rootfs: std::path::PathBuf, config: Config) -> Result<i32> {
-    // Check user namespace availability
-    namespace::check_user_namespace()?;
-
-    // Process bind paths - use current directory if none specified
-    let cwd = std::env::current_dir().expect("Could not get current directory");
-    let bind_paths: Vec<std::path::PathBuf> = if args.bind.is_empty() && !args.no_bind {
-        vec![cwd.clone()]
-    } else {
-        args.bind.clone()
-    };
-
-    // --no-bind means "skip mounting any directory".  Combining it with an
-    // explicit --bind-rw is contradictory; error rather than silently ignoring
-    // the flag the user asked for.
-    if args.no_bind && !args.bind_rw.is_empty() {
-        return Err(anyhow::anyhow!(
-            "--no-bind and --bind-rw cannot be used together: \
-             --no-bind skips all mounts, including read-write ones"
-        ));
-    }
-    let bind_rw_paths: Vec<std::path::PathBuf> = args.bind_rw.clone();
-
-    // Prepare data for the closure
-    let bind_paths_clone = bind_paths.clone();
-    let bind_rw_paths_clone = bind_rw_paths.clone();
-    let args_clone = args.clone();
-    let rootfs_clone = rootfs.clone();
-    let dns_clone = config.dns.clone();
-
-    // Run in namespace
-    let result = namespace::setup_namespaces(move || -> Result<()> {
-        // Setup mounts - overlay_temps must be kept alive for overlay to work
-        let overlay_temps = mount::setup_mounts(
-            &rootfs_clone,
-            &bind_paths_clone,
-            &bind_rw_paths_clone,
-            &args_clone,
-        )?;
-
-        // Write resolv.conf with DNS from config
-        write_resolv_conf(&rootfs_clone, &dns_clone)?;
-
-        // Run chroot
-        let command = if args_clone.command.is_empty() {
-            None
-        } else {
-            Some(args_clone.command.clone())
-        };
-
-        let result = chroot::run_chroot(&rootfs_clone, command, &bind_rw_paths_clone);
-
-        // Keep overlay_temps alive until chroot exits
-        drop(overlay_temps);
-
-        result
-    });
-
-    // Cleanup happens automatically via tempfile
-    if result.is_ok() {
-        veprintln!("Cleanup complete.");
-    }
-
-    result
-}
-
-/// Generate a cache filename based on the image source
-fn generate_cache_filename(source: &ImageSource, arch: &str) -> String {
-    match source {
-        ImageSource::DirectTarball { distro, version } => {
-            let distro_name = match distro {
-                Distro::Ubuntu => "ubuntu",
-                Distro::Alpine => "alpine",
-            };
-            let distro_arch = map_arch(*distro, arch);
-            // Get extension from URL
-            let url = resolve_distro_url(distro, version.as_deref(), arch).unwrap_or_default();
-            let ext = get_tarball_extension(&url);
-            format!(
-                "{}-{}-{}.{}",
-                distro_name,
-                version.as_deref().unwrap_or("latest"),
-                distro_arch,
-                ext
-            )
-        }
-        ImageSource::OciImage {
-            registry,
-            repository,
-            tag,
-            architecture,
-        } => {
-            // Sanitize for filename
-            let safe_registry = registry.replace(['.', ':'], "_");
-            let safe_repo = repository.replace(['/', ':'], "_");
-            format!(
-                "oci-{}-{}-{}-{}.tar.gz",
-                safe_registry, safe_repo, tag, architecture
-            )
-        }
-    }
-}
-
-fn get_tarball_extension(url: &str) -> &str {
-    // Extract extension from URL (e.g., .tar.gz, .tar.xz, .tar.zst)
-    if url.ends_with(".tar.zst") {
-        "tar.zst"
-    } else if url.ends_with(".tar.xz") {
-        "tar.xz"
-    } else if url.ends_with(".tar.gz") {
-        "tar.gz"
-    } else if url.ends_with(".tar.bz2") {
-        "tar.bz2"
-    } else {
-        "tar.gz" // default
-    }
-}
-
-fn get_host_arch() -> String {
-    // Use the consolidated architecture detection from utils
-    utils::get_host_arch().debian_name().to_string()
-}
-
-fn write_resolv_conf(rootfs: &std::path::Path, dns: &[String]) -> Result<()> {
-    use std::io::Write;
-
-    let resolv_conf = rootfs.join("etc/resolv.conf");
-
-    // Create /etc if it doesn't exist
-    if let Some(parent) = resolv_conf.parent() {
-        std::fs::create_dir_all(parent)
-            .with_context(|| format!("Failed to create directory: {}", parent.display()))?;
-    }
-
-    // Copy host's resolv.conf if dns is empty, otherwise use provided DNS
-    let content = if dns.is_empty() {
-        // Try to copy from host
-        match std::fs::read_to_string("/etc/resolv.conf") {
-            Ok(host_resolv) => host_resolv,
-            Err(_) => "nameserver 1.1.1.1\nnameserver 8.8.8.8\n".to_string(),
-        }
-    } else {
-        let mut c = dns
-            .iter()
-            .map(|s| format!("nameserver {}", s))
-            .collect::<Vec<_>>()
-            .join("\n");
-        c.push('\n');
-        c
-    };
-
-    // Remove any existing file or symlink before writing so that we always
-    // create a plain file.  Without this, an absolute symlink such as
-    // /etc/resolv.conf -> /run/systemd/resolve/stub-resolv.conf would cause the
-    // write to follow the symlink through the *host* root (chroot() has not been
-    // called yet) and corrupt the host's DNS configuration.
-    //
-    // Use atomic file creation with O_CREAT | O_EXCL to prevent TOCTOU race:
-    // if an attacker creates a symlink between our remove_file and write, the
-    // exclusive create will fail rather than writing to the symlink target.
-    let _ = std::fs::remove_file(&resolv_conf); // ignore ENOENT
-
-    // Use OpenOptions with create_new(true) for atomic exclusive creation
-    let mut file = std::fs::OpenOptions::new()
-        .write(true)
-        .create_new(true)
-        .open(&resolv_conf)
-        .with_context(|| {
-            format!(
-                "Failed to create resolv.conf at {} (symlink attack prevented)",
-                resolv_conf.display()
-            )
-        })?;
-
-    file.write_all(content.as_bytes())
-        .with_context(|| format!("Failed to write to {}", resolv_conf.display()))?;
-
-    Ok(())
-}