feat: enhance guest network configuration and recovery process for UVM

uvm/images.py

@@ -8,6 +8,7 @@ import stat
 import tempfile
 import time
 from dataclasses import dataclass
+from ipaddress import IPv4Address
 from pathlib import Path
 
 from .config import MAX_STORAGE_MIB, MIN_STORAGE_MIB, Settings
@@ -35,6 +36,16 @@ _HOST_KEY_TYPES = (
     ("ed25519", None),
 )
 
+# Keep the kernel's proto-boot default route until networkd takes over. On
+# Ubuntu 22.04, KeepConfiguration=static preserves addresses but drops that route.
+GUEST_NETWORK_TEMPLATE = (
+    "[Match]\nName=eth0\n\n[Network]\n"
+    "KeepConfiguration=yes\nDHCP=no\nLinkLocalAddressing=no\nIPv6AcceptRA=no\n"
+)
+_LEGACY_GUEST_NETWORK_TEMPLATE = GUEST_NETWORK_TEMPLATE.replace(
+    "KeepConfiguration=yes", "KeepConfiguration=static",
+)
+
 
 @dataclass(frozen=True, slots=True)
 class GuestAssets:
@@ -150,6 +161,91 @@ class ImageStore:
         finally:
             temporary.unlink(missing_ok=True)
 
+    def configure_guest_network(self, disk: Path, guest_ip: str) -> bool:
+        """Specialize an unedited UVM profile on a proven-offline private disk.
+
+        Lifecycle owns the operation lock and confirms process exit. Stage and
+        check a sparse copy so failed migrations retain the original disk. A
+        completed migration, custom image, or guest-edited profile is a no-op.
+        """
+        try:
+            address = IPv4Address(guest_ip)
+        except ValueError as error:
+            raise ValidationError("guest network configuration requires a valid IPv4 address") from error
+        if address not in self._settings.network or address in {
+            self._settings.network.network_address,
+            self._settings.network.broadcast_address,
+            self._settings.gateway,
+        }:
+            raise ValidationError("guest network configuration requires a usable IP inside the UVM subnet")
+
+        try:
+            metadata = disk.lstat()
+            if (not stat.S_ISREG(metadata.st_mode) or metadata.st_nlink != 1
+                    or disk.resolve() == self._settings.rootfs_image.resolve()):
+                raise UvmError(f"private VM disk is unsafe to configure: {disk}")
+            with tempfile.TemporaryDirectory(prefix="uvm-guest-network-") as name:
+                files = Path(name)
+                if self._unconfigured_guest_network(disk, files) is None:
+                    return False
+
+                descriptor, candidate = tempfile.mkstemp(prefix=".rootfs-network-", suffix=".ext4", dir=disk.parent)
+                os.close(descriptor)
+                temporary = Path(candidate)
+                try:
+                    self._copy_sparse(disk, temporary)
+                    temporary.chmod(0o600)
+                    checked = self._runner.run(("e2fsck", "-f", "-p", temporary), check=False, capture=True)
+                    if checked.returncode not in (0, 1):
+                        detail = checked.stderr.strip() or checked.stdout.strip()
+                        raise UvmError(f"filesystem check failed before guest network configuration: {detail}")
+                    # Journal replay may reveal guest edits not visible to the
+                    # initial debugfs read. Recheck ownership on the recovered copy.
+                    profile = self._unconfigured_guest_network(temporary, files)
+                    if profile is None:
+                        return False
+                    profile.path.write_text(
+                        GUEST_NETWORK_TEMPLATE
+                        + f"Address={address}/{self._settings.network.prefixlen}\n"
+                        + f"Gateway={self._settings.gateway}\n",
+                        encoding="utf-8",
+                    )
+                    self._write_guest_file(temporary, "/etc/systemd/network/10-uvm.network", profile)
+                    self._runner.run(("e2fsck", "-f", "-n", temporary), capture=True)
+                    with temporary.open("rb") as image:
+                        os.fsync(image.fileno())
+                    os.replace(temporary, disk)
+                    directory = os.open(disk.parent, os.O_RDONLY)
+                    try:
+                        os.fsync(directory)
+                    finally:
+                        os.close(directory)
+                finally:
+                    temporary.unlink(missing_ok=True)
+            return True
+        except (OSError, UnicodeError) as error:
+            raise UvmError(f"could not configure guest networking: {error}") from error
+
+    def _unconfigured_guest_network(self, disk: Path, temporary: Path) -> _GuestFile | None:
+        marker = self._read_guest_file(
+            disk, "/etc/uvm-image", temporary / "marker", required=False, regular_only=True,
+        )
+        if marker is None or marker.path.read_text(encoding="utf-8") not in {
+            "uvm-ubuntu-jammy-v1\n", "uvm-ubuntu-jammy-v2\n", "uvm-ubuntu-jammy-v3\n",
+        }:
+            return None
+        profile = self._read_guest_file(
+            disk, "/etc/systemd/network/10-uvm.network", temporary / "network", required=False, regular_only=True,
+        )
+        if (profile is None or (profile.uid, profile.gid, profile.mode, profile.links) != (0, 0, 0o644, 1)
+                or profile.has_extended_attributes):
+            return None
+        if profile.path.read_text(encoding="utf-8") not in {
+            _LEGACY_GUEST_NETWORK_TEMPLATE, GUEST_NETWORK_TEMPLATE,
+        }:
+            return None
+        return profile
+
     @staticmethod
     def _validate_storage(storage_mib: int) -> None:
         if type(storage_mib) is not int or not MIN_STORAGE_MIB <= storage_mib <= MAX_STORAGE_MIB:
@@ -397,12 +493,16 @@ class ImageStore:
         destination: Path,
         *,
         required: bool = True,
+        regular_only: bool = False,
     ) -> _GuestFile | None:
         stat_result = self._runner.run(
             ("debugfs", "-R", f"stat {guest_path}", disk),
             check=False,
             capture=True,
         )
+        file_type = re.search(r"Type:\s+(\S+)", stat_result.stdout)
+        if regular_only and file_type is not None and file_type.group(1) != "regular":
+            return None
         mode_match = _MODE_PATTERN.search(stat_result.stdout)
         owner_match = _OWNER_PATTERN.search(stat_result.stdout)
         flags_match = _FLAGS_PATTERN.search(stat_result.stdout)

uvm/install.py

@@ -14,14 +14,14 @@ from pathlib import Path
 
 from .config import Settings
 from .errors import UvmError
-from .images import GuestAssets
+from .images import GUEST_NETWORK_TEMPLATE, GuestAssets
 from .integrity import load_manifest, require_checksum, sha256_file, verify_file, write_manifest
 from .state import StateStore
 from .system import CommandRunner, check_kvm, ensure_data_directories, require_root
 
 
 _UBUNTU_RELEASE = "jammy"
-_ROOTFS_RECIPE = "uvm-ubuntu-jammy-v2\n"
+_ROOTFS_RECIPE = "uvm-ubuntu-jammy-v3\n"
 _GUEST_PACKAGES = (
     "ca-certificates", "openssh-server", "sudo", "systemd-sysv", "udev",
     "dbus", "libpam-systemd", "iproute2", "iputils-ping", "curl",
@@ -383,10 +383,7 @@ class Installer:
             "etc/resolv.conf": "nameserver 1.1.1.1\nnameserver 8.8.8.8\n",
             "etc/machine-id": "",
             "etc/uvm-image": _ROOTFS_RECIPE,
-            "etc/systemd/network/10-uvm.network": (
-                "[Match]\nName=eth0\n\n[Network]\n"
-                "KeepConfiguration=static\nDHCP=no\nLinkLocalAddressing=no\nIPv6AcceptRA=no\n"
-            ),
+            "etc/systemd/network/10-uvm.network": GUEST_NETWORK_TEMPLATE,
         }
         for relative, contents in files.items():
             path = root / relative

uvm/lifecycle.py

@@ -89,6 +89,7 @@ class LifecycleService:
                 self._save(vm)
                 disk = self._images.create_vm_disk(assets.rootfs, Path(vm.disk), storage_mib=spec.storage_mib)
                 self._images.provision_credentials(disk, vm.username, vm.password)
+                self._images.configure_guest_network(disk, vm.guest_ip)
                 vm.disk_ready = True
                 self._save(vm)
                 self._boot(vm, assets.kernel)
@@ -188,6 +189,7 @@ class LifecycleService:
         try:
             self._cleanup_runtime(vm)
             self._apply_pending_resize(vm)
+            self._images.configure_guest_network(Path(vm.disk), vm.guest_ip)
             vm.network, vm.bridge = str(self._settings.network), self._settings.bridge
             self._boot(vm, kernel)
             return vm