Merge pull request 'Make lxc-docker a privileged container: unprivileged can't NFS-mount at all' (#28) from worktree-fix-container-dns-search-domain into main

Reviewed-on: #28

modules/platforms/lxc.nix

@@ -1,4 +1,4 @@
-{ lib, modulesPath, flakeTarget, ... }:
+{ config, lib, modulesPath, flakeTarget, ... }:
 
 let
   # Bakes this exact flake target's pre-generated SSH host key straight
@@ -58,8 +58,28 @@ in
     # host.nix declares each host's real hostname (networking.hostName);
     # keep that instead of letting Proxmox's ambient container config win.
     manageHostName = true;
-    # Unprivileged matches how these containers are actually created.
-    privileged = false;
+    # Unprivileged by default -- matches how these containers are actually
+    # created (scripts/proxmox/create-proxmox-resource.sh reads this value
+    # back to decide `pct create`'s --unprivileged flag, so the two stay
+    # in sync).
+    #
+    # lxc-docker is the one exception: the kernel's NFS client doesn't set
+    # FS_USERNS_MOUNT, so mounting NFS from inside *any* non-init user
+    # namespace -- which is exactly what an unprivileged container's
+    # UID-mapped root runs in -- is rejected at the VFS layer with EPERM,
+    # no matter what Proxmox's own `mount=nfs;nfs4` container feature
+    # allows at the AppArmor layer (confirmed live: TCP to the NFS server
+    # succeeds, the server's export table matches the container's IP, and
+    # `mount.nfs: Operation not permitted` still fires immediately with no
+    # corresponding denial anywhere in the server's logs -- a kernel-level
+    # rejection, not a network or export-permission one). Keying off
+    # hostName rather than something docker-build-type-specific because
+    # modules/build-types/docker.nix is also composed for linode-docker/
+    # proxmox-docker, which don't import proxmox-lxc.nix at all --setting
+    # this option there would break their eval with "option does not
+    # exist" regardless of any mkIf guard, since mkIf only makes a value
+    # conditional, not whether the option needs to exist somewhere.
+    privileged = config.networking.hostName == "docker";
   };
 
   boot.loader = {

scripts/lib/nix-eval.sh

@@ -34,3 +34,21 @@ flake_target_hostname() {
   nix eval --raw "${NIX_EVAL_FLAGS[@]}" \
     "${flake_ref}#nixosConfigurations.${target}.config.networking.hostName" 2>/dev/null
 }
+
+# flake_target_lxc_privileged <flake_ref> <target>
+# Prints "true" or "false" for one lxc-* target's config.proxmoxLXC.privileged
+# (modules/platforms/lxc.nix is the single source of truth -- e.g.
+# lxc-docker sets this true so it can NFS-mount; every other lxc-* host
+# stays unprivileged). Only meaningful for lxc-* targets -- the option
+# doesn't exist for linode-*/proxmox-* (nixpkgs' proxmox-lxc.nix, which
+# declares it, is only ever imported by modules/platforms/lxc.nix). Empty
+# (not an error under set -e) if the eval fails.
+flake_target_lxc_privileged() {
+  local flake_ref="$1" target="$2"
+  # Not --raw: the option is a Nix boolean, and --raw can only coerce
+  # strings ("cannot coerce a Boolean to a string"). Plain `nix eval`
+  # prints a bare `true`/`false` for a boolean, which is exactly the
+  # string this needs.
+  nix eval "${NIX_EVAL_FLAGS[@]}" \
+    "${flake_ref}#nixosConfigurations.${target}.config.proxmoxLXC.privileged" 2>/dev/null
+}

scripts/proxmox/create-proxmox-resource.sh

@@ -766,13 +766,22 @@ if [[ "$type" == "lxc" ]]; then
   # 512M default otherwise (confirmed live: --memory 2048 left swap at
   # 512). Default to matching whatever --memory resolved to above.
   local_swap="${swap:-$memory}"
-  # --unprivileged 1: modules/platforms/lxc.nix sets proxmoxLXC.privileged
-  # = false, so the NixOS config inside the image assumes it's running as
-  # an unprivileged container (cgroup/capability/mount expectations baked
-  # in at boot). `pct create`'s own CLI default for this flag is
-  # privileged (unlike the web UI, which defaults its checkbox the other
-  # way) -- leaving it unset creates a privileged container running a
-  # NixOS config that assumes unprivileged, a real mismatch.
+  # --unprivileged: read back from modules/platforms/lxc.nix's own
+  # proxmoxLXC.privileged (via flake_target_lxc_privileged) rather than
+  # hardcoded, since that's no longer the same for every lxc-* target --
+  # lxc-docker sets it true so the container's NFS mounts work at all (the
+  # kernel's NFS client can't mount from inside any unprivileged
+  # container's user namespace, no matter what AppArmor allows -- see that
+  # option's own comment). The NixOS config inside the image bakes in
+  # cgroup/capability/mount expectations matching whichever value it was
+  # built with, so this must stay in sync with it -- `pct create`'s own
+  # CLI default for this flag is privileged (unlike the web UI, which
+  # defaults its checkbox the other way), so leaving it unset would create
+  # a privileged container running a NixOS config that assumes
+  # unprivileged for every target except lxc-docker, a real mismatch.
+  privileged_eval="$(flake_target_lxc_privileged "$repo_root" "$flake_target")"
+  unprivileged_flag=1
+  [[ "$privileged_eval" == "true" ]] && unprivileged_flag=0
   #
   # --features nesting=1,keyctl=1: required for a modern (v247+) systemd
   # guest to actually boot unprivileged -- confirmed live: without this,
@@ -790,7 +799,7 @@ if [[ "$type" == "lxc" ]]; then
   # hands the whole string to `ssh` as a single command for the *remote*
   # shell to parse -- unquoted, that `;` would be read as a remote
   # command separator and silently truncate this into two commands.
-  create_cmd="pct create ${vmid} ${iso_storage}:vztmpl/${remote_filename} --unprivileged 1 --features '${PROXMOX_DEFAULT_LXC_FEATURES}' --rootfs ${storage}:${local_disk_size} --hostname ${name} --cores ${cores} --memory ${memory} --swap ${local_swap} --net0 name=eth0,bridge=${bridge},ip=dhcp"
+  create_cmd="pct create ${vmid} ${iso_storage}:vztmpl/${remote_filename} --unprivileged ${unprivileged_flag} --features '${PROXMOX_DEFAULT_LXC_FEATURES}' --rootfs ${storage}:${local_disk_size} --hostname ${name} --cores ${cores} --memory ${memory} --swap ${local_swap} --net0 name=eth0,bridge=${bridge},ip=dhcp"
   remote "$create_cmd"
   remote "pct start ${vmid}"
 else