furtka/webinstaller/diskprep.py

"""Release a target disk before handing it to archinstall.

The live ISO ships lvm2, mdadm, dmraid and cryptsetup (releng defaults), and
udev happily auto-activates whatever it finds on attached disks at boot. A
drive that used to live in another machine — the first hardware bench had an
old Proxmox VE install on its SSD — therefore comes up with device-mapper
volumes (or swap, or md arrays) stacked on top of its partitions. archinstall
then writes the new partition table fine but `BLKRRPART` fails with

    Partition(s) 2, 3 on /dev/sda have been written, but we have been unable
    to inform the kernel of the change, probably because it/they are in use.

and the install dies at 12 %. Nothing on a fresh VM ever triggers this,
which is why it survived every smoke run.

`release_disk()` tears that stack down leaves-first (swapoff, umount, dmsetup
remove / mdadm --stop), wipes signatures and asks the kernel to re-read the
partition table. Every step is logged so the install log shows what was
done. All commands are best-effort: the point is to leave archinstall a
disk the kernel can re-partition, not to be a full disk-management tool.
"""

import re
import subprocess

_PAIR_RE = re.compile(r'(\w+)="([^"]*)"')


def _run(cmd, run):
    try:
        result = run(cmd, capture_output=True, text=True)
    except FileNotFoundError:
        return 127, f"{cmd[0]}: command not found"
    out = ((result.stdout or "") + (result.stderr or "")).strip()
    return result.returncode, out


def _parse_pairs(output):
    """Parse `lsblk -P` key="value" lines into dicts."""
    rows = []
    for line in output.splitlines():
        row = {}
        for match in _PAIR_RE.finditer(line):
            row[match.group(1)] = match.group(2)
        if row.get("NAME"):
            rows.append(row)
    return rows


def _children(disk, run):
    """Everything stacked on `disk`, in lsblk tree order, disk itself excluded."""
    rc, out = _run(["lsblk", "-lnP", "-o", "NAME,TYPE,MOUNTPOINTS", disk], run)
    if rc != 0:
        return []
    rows = _parse_pairs(out)
    seen = set()
    children = []
    for row in rows:
        if row.get("TYPE") == "disk" or row["NAME"] in seen:
            continue
        seen.add(row["NAME"])
        children.append(row)
    return children


def release_disk(disk, run=subprocess.run):
    """Free `disk` (e.g. "/dev/sda") of anything that would block a
    partition-table reload. Returns the log lines describing what happened."""
    if not disk.startswith("/dev/"):
        disk = f"/dev/{disk}"
    lines = [f"Releasing {disk} before install…"]

    children = _children(disk, run)
    if not children:
        lines.append("  nothing stacked on the disk — good.")
    else:
        lines.append("  found: " + ", ".join(f"{c['NAME']} ({c['TYPE']})" for c in children))

    # Leaves first: mountpoints and swap sit on the outermost devices.
    for child in reversed(children):
        dev = f"/dev/{child['NAME']}"
        mounts = child.get("MOUNTPOINTS", "")
        if "[SWAP]" in mounts:
            rc, out = _run(["swapoff", dev], run)
            lines.append(f"  swapoff {dev}: {'ok' if rc == 0 else out}")
        elif mounts:
            rc, out = _run(["umount", "--all-targets", dev], run)
            lines.append(f"  umount {dev}: {'ok' if rc == 0 else out}")

    # Device-mapper (LVM, thin pools, LUKS) and md stacks. Thin pools need
    # their thin LVs gone before the pool goes, and lsblk lists shared nodes
    # more than once, so go leaves-first and retry a couple of passes until
    # nothing dm/md-shaped is left.
    for _ in range(3):
        stacked = [c for c in reversed(_children(disk, run)) if c["TYPE"] != "part"]
        if not stacked:
            break
        for child in stacked:
            name, typ = child["NAME"], child["TYPE"]
            if typ.startswith("raid") or name.startswith("md"):
                cmd = ["mdadm", "--stop", f"/dev/{name}"]
            else:
                cmd = ["dmsetup", "remove", name]
            rc, out = _run(cmd, run)
            lines.append(f"  {' '.join(cmd)}: {'ok' if rc == 0 else out}")

    leftovers = [c["NAME"] for c in _children(disk, run) if c["TYPE"] != "part"]
    if leftovers:
        lines.append(
            "  WARNING: still in use after cleanup: "
            + ", ".join(leftovers)
            + " — the install may fail to re-read the partition table."
        )

    # Old signatures (LVM PV headers, RAID superblocks) would otherwise be
    # re-activated by udev the moment the kernel re-reads the table.
    for child in reversed(_children(disk, run)):
        if child["TYPE"] == "part":
            rc, out = _run(["wipefs", "-a", f"/dev/{child['NAME']}"], run)
            lines.append(f"  wipefs /dev/{child['NAME']}: {'ok' if rc == 0 else out}")
    rc, out = _run(["wipefs", "-a", disk], run)
    lines.append(f"  wipefs {disk}: {'ok' if rc == 0 else out}")
    rc, out = _run(["blockdev", "--rereadpt", disk], run)
    lines.append(f"  re-read partition table: {'ok' if rc == 0 else out}")
    return lines