[arch-projects] [devtools] [PATCH v2] makechrootpkg: Be recursive when deleting btrfs subvolumes.

[Luke Shumaker]

From: Luke Shumaker <lukeshu at parabola.nu>

Motivation:

  tmpfiles.d(5) has directives to create btrfs subvolumes.  This means
  that systemd-tmpfiles (which may be called by an ALPM hook) might
  create subvolumes.  For instance, systemd's systemd-nspawn.conf
  creates a subvolume at `/var/lib/machines/`.

  This causes a problem when we go to delete the chroot.  The command
  `btrfs subvolume delete` won't recursively delete subvolumes; if a
  child subvolume was created, it will fail with the fairly unhelpful
  error message "directory not empty".

Solution:

  Because the subvolume that gets mounted isn't necessarily the
  toplevel subvolume, and `btrfs subvolume list` gives us paths
  relative to the toplevel; we need to figure out how our path relates
  to the toplevel.  Figure out the mountpoint (which turns out to be
  slightly tricky; see below), and call `btrfs subvolume list -a` on
  it to get the list of subvolumes that are visible to us (and quite
  possibly some that aren't; the logic for determining which ones it
  shows is... absurd).  This gives us a list of subvolumes with
  numeric IDs, and paths relative to the toplevel (actually it gives
  us more than that, and we use a hopefully-correct `sed` expression
  to trim it down) So then we look at that list of pairs and find the
  one that matches the ID of the subvolume we're trying to delete
  (which is easy to get with `btrfs subvolume show`); once we've found
  the path of our subvolume, we can use that to filter and trim the
  complete list of paths.  From there the remainder of the solution is
  obvious.

  Now, back to "figure out the mountpoint"; the normal `stat -c %m`
  doesn't work.  It gives the mounted path of the subvolume closest to
  the path we give it, not the actual mountpoint.  Now, it turns out
  that `df` can figure out the correct mountpoint (though I haven't
  investigated how it knows when stat doesn't; but I suspect it parses
  `/proc/mounts`).  So we are reduced to parsing `df`'s output.

  Now, back to "hopefully-correct `sed` expression"; the output of
  `btrfs subvolume list -a` is a space-separated sequence of
  "key value key value...".  Unfortunately both keys and values can
  contain space, and there's no escaping or indication of when this
  happens.  With how we choose to parse it, a path containing a space
  is truncated at the first space.  This means that at least the
  prefix is correct; if a path gets mangled, it just means that the
  deletion fails.  As "path" is (currently) the last key, it seems
  tempting to allow it to simply run until the end of the line.
  However, this creates the possibility of a path containing " path ",
  which would cause the *prefix* to be trimmed, which means our
  failure case is now unpredictable, and potentially harmful.  While
  we pretty much trust the user, that's still scary.
---
 makechrootpkg.in | 84 ++++++++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 82 insertions(+), 2 deletions(-)

diff --git a/makechrootpkg.in b/makechrootpkg.in
index 5c4b530..ef90a68 100644
--- a/makechrootpkg.in
+++ b/makechrootpkg.in
@@ -80,6 +80,86 @@ load_vars() {
 	return 0
 }
 
+# Usage: btrfs_subvolume_id $SUBVOLUME
+btrfs_subvolume_id() (
+	set -o pipefail
+	LC_ALL=C btrfs subvolume show "$1" | sed -n 's/^\tSubvolume ID:\s*//p'
+)
+
+# Usage: btrfs_subvolume_list_all $FILEPATH
+#
+# Given $FILEPATH somewhere on a mounted btrfs filesystem, print the
+# ID and full path of every subvolume on the filesystem, one per line
+# in the format "$ID $PATH", where $PATH is relative to the top-level
+# subvolume (which might not be what is mounted).
+#
+# BUG: Due to limitations in the `btrfs` tool, this will not correctly
+# list subvolumes whose path contains a space.
+btrfs_subvolume_list_all() (
+	set -o pipefail
+
+	local mountpoint all
+	mountpoint="$(df --output=target "$1" | sed 1d)" || return
+	# The output of `btrfs subvolume list -a` is a space-separated
+	# sequence of "key value key value...".  Unfortunately, both
+	# keys and values can contain space, and there's no escaping
+	# or indication of when this happens.  So we assume
+	#  1. ID is the first column
+	#  2. That no key or value will contain " path"
+	#  3. That the "path" value does not contain a space.
+	all="$(LC_ALL=C btrfs subvolume list -a "$mountpoint" | sed -r 's|^ID ([0-9]+) .* path (<FS_TREE>/)?(\S*).*|\1 \3|')" || return
+
+	# Sanity check the output
+	local id path
+	while read -r id path; do
+		# ID should be numeric
+		[[ "$id" =~ ^-?[0-9]+$ ]] || return
+		# While a path could countain a space, the above code
+		# doesn't support it; if there is space, then it means
+		# we got a line not matching the expected format.
+		[[ "$path" != *' '* ]] || return
+	done <<<"$all"
+
+	printf '%s\n' "$all"
+)
+
+# Usage: btrfs_subvolume_list $SUBVOLUME
+#
+# Assuming that $SUBVOLUME is a btrfs subvolume, list all child
+# subvolumes; from most deeply nested to most shallowly nested.
+#
+# This is intended to be a sane version of `btrfs subvolume list`.
+btrfs_subvolume_list() {
+	local subvolume=$1
+
+	local id all path subpath
+	id="$(btrfs_subvolume_id "$subvolume")" || return
+	all="$(btrfs_subvolume_list_all "$subvolume")" || return
+	path=$(awk -v id="$1" '$1 == id { sub($1 FS, ""); print }' <<<"$all")
+	while read -r id subpath; do
+		if [[ "$subpath" = "$path"/* ]]; then
+			printf '%s\n' "${subpath#"${path}/"}"
+		fi
+	done <<<"$all" | LC_ALL=C sort --reverse
+}
+
+# Usage: btrfs_subvolume_delete $SUBVOLUME
+#
+# Assuming that $SUBVOLUME is a btrfs subvolume, delete it and all
+# subvolumes below it.
+#
+# This is intended to be a recursive version of
+# `btrfs subvolume delete`.
+btrfs_subvolume_delete() {
+	local dir="$1"
+	local subvolumes subvolume
+	subvolumes="$(btrfs_subvolume_list "$dir")" || return
+	for read -r subvolume; do
+		btrfs subvolume delete "$dir/$subvolume" || return
+	done <<<"$subvolumes"
+	btrfs subvolume delete "$dir"
+}
+
 create_chroot() {
 	# Lock the chroot we want to use. We'll keep this lock until we exit.
 	lock 9 "$copydir.lock" "Locking chroot copy [%s]" "$copy"
@@ -92,7 +172,7 @@ create_chroot() {
 		stat_busy "Creating clean working copy [%s]" "$copy"
 		if [[ "$chroottype" == btrfs ]] && ! mountpoint -q "$copydir"; then
 			if [[ -d $copydir ]]; then
-				btrfs subvolume delete "$copydir" >/dev/null ||
+				btrfs_subvolume_delete "$copydir" >/dev/null ||
 					die "Unable to delete subvolume %s" "$copydir"
 			fi
 			btrfs subvolume snapshot "$chrootdir/root" "$copydir" >/dev/null ||
@@ -114,7 +194,7 @@ create_chroot() {
 clean_temporary() {
 	stat_busy "Removing temporary copy [%s]" "$copy"
 	if [[ "$chroottype" == btrfs ]] && ! mountpoint -q "$copydir"; then
-		btrfs subvolume delete "$copydir" >/dev/null ||
+		btrfs_subvolume_delete "$copydir" >/dev/null ||
 			die "Unable to delete subvolume %s" "$copydir"
 	else
 		# avoid change of filesystem in case of an umount failure
-- 
2.11.1