Fix partition issue

This commit is contained in:
Ryan Hughes committed 2026-08-13 23:57:22 -04:00
1 parent 7c50d72f40
commit 7d3b01eae9
5 files changed
+424 -64

No files matched your search

+101 -52
View File
@@ -24,6 +24,17 @@ if [[ ! -r $SETUP_FORM ]]; then
fi
source "$SETUP_FORM"
# Partition creation helpers, shared with test/partition-numbering-test.sh so
# the numbering logic can be exercised without a real disk.
DISK_PARTITIONING="${DISK_PARTITIONING:-/usr/share/omarchy-iso/disk-partitioning.sh}"
[[ -r $DISK_PARTITIONING ]] ||
DISK_PARTITIONING="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/../usr/share/omarchy-iso/disk-partitioning.sh"
if [[ ! -r $DISK_PARTITIONING ]]; then
echo "ERROR: disk partitioning helpers not found at $DISK_PARTITIONING" >&2
exit 1
fi
source "$DISK_PARTITIONING"
LOGO_WIDTH=$(awk '{ if (length > max) max = length } END { print max+0 }' "$LOGO_PATH")
export GUM_CONFIRM_PROMPT_FOREGROUND="6"
@@ -361,15 +372,7 @@ get_root_disk() {
fi
}
# Compute partition device path, handling NVMe/mmcblk's pN naming.
partition_path() {
local _disk="$1" _num="$2"
if [[ "$_disk" == *nvme* || "$_disk" == *mmcblk* ]]; then
echo "${_disk}p${_num}"
else
echo "${_disk}${_num}"
fi
}
# partition_path lives in disk-partitioning.sh alongside the creation helpers.
# BitLocker writes the "-FVE-FS-" signature at offset 3 of the partition.
detect_bitlocker() {
@@ -416,13 +419,20 @@ detect_kernel() {
fi
}
# Give udev a moment to create a device node after partitioning.
wait_for_device() {
local i
for i in 1 2 3 4 5; do
[[ -b "$1" ]] && return 0
sleep 1
done
# wait_for_device lives in disk-partitioning.sh: it now reports failure, and
# every caller here aborts on it.
# disk_step and create_partition fail through this rather than abort() so a
# half-built layout is undone before the user is handed back their disk.
disk_abort_hook() {
# Release the target before reclaiming its partitions: a mounted filesystem
# or an open LUKS mapping would keep parted from removing them.
umount -R /mnt 2>/dev/null || true
umount /mnt/btrfs-root 2>/dev/null || true
rmdir /mnt/btrfs-root 2>/dev/null || true
cryptsetup close omarchy_root 2>/dev/null || true
rollback_created_parts "$disk"
abort "$1"
}
# Save the configurator answers the installer consumes: git identity and
@@ -654,17 +664,17 @@ run_partition_decide() {
kernel_choice=$(detect_kernel)
local last_part
last_part=$(lsblk -n -o PARTN "$disk" 2>/dev/null | grep -E '^[0-9]+$' | sort -n | tail -1)
efi_part_num=$(( ${last_part:-0} + 1 ))
root_part_num=$(( efi_part_num + 1 ))
efi_dev=$(partition_path "$disk" "$efi_part_num")
root_partition_device=$(partition_path "$disk" "$root_part_num")
# Partition numbers are not knowable until parted assigns them (it fills the
# lowest free GPT slot, and freeing space by deleting a partition leaves one
# below the highest). run_partition_execute reads them back after creation;
# a dry run has nothing to read.
efi_part_num=""
root_part_num=""
efi_dev="<assigned at creation>"
root_partition_device="<assigned at creation>"
root_mapper="<assigned at creation>"
if [[ "$encrypt_installation" == "true" ]]; then
root_mapper="/dev/mapper/omarchy_root"
else
root_mapper="$root_partition_device"
fi
}
@@ -672,64 +682,103 @@ run_partition_decide() {
# the pre-mounted (protected) install configuration. Runs after the user step
# so LUKS can be formatted with the user's password.
run_partition_execute() {
local dry=false
local dry=false subvol
[[ "${1:-}" == "dry" ]] && dry=true
if $dry; then
$needs_mklabel && say "[dry] would initialize GPT on $disk"
say "[dry] would create root partition at $root_partition_device"
say "[dry] would create EFI partition at $efi_dev"
say "[dry] would create an EFI partition and a root partition in the free region"
say "[dry] partition numbers are assigned by parted at creation, then read back"
say "[dry] encrypted=$encrypt_installation kernel=$kernel_choice"
else
step "Creating partitions on $disk"
if $needs_mklabel; then
parted --script "$disk" mklabel gpt
disk_step "initializing GPT on $disk" parted --script "$disk" mklabel gpt
partprobe "$disk" 2>/dev/null || true
sleep 1
fi
parted --script "$disk" mkpart primary fat32 "${EFI_START_B}B" "${EFI_END_B}B"
parted --script "$disk" set "$efi_part_num" esp on
parted --script "$disk" name "$efi_part_num" "OMARCHY_EFI"
parted --script "$disk" mkpart primary btrfs "${ROOT_START_B}B" "${ROOT_END_B}B"
parted --script "$disk" name "$root_part_num" "OMARCHY_ROOT"
# create_partition reports the number parted actually used; nothing here
# may assume it. It sets created_partition_number rather than printing so
# the rollback bookkeeping survives (a $(...) would subshell it away).
create_partition "$disk" "$EFI_START_B" "$EFI_END_B" fat32 OMARCHY_EFI ||
disk_abort_hook "Could not create the EFI partition on $disk"
efi_part_num="$created_partition_number"
create_partition "$disk" "$ROOT_START_B" "$ROOT_END_B" btrfs OMARCHY_ROOT ||
disk_abort_hook "Could not create the root partition on $disk"
root_part_num="$created_partition_number"
disk_step "flagging partition $efi_part_num as ESP" \
parted --script "$disk" set "$efi_part_num" esp on
efi_dev=$(partition_path "$disk" "$efi_part_num")
root_partition_device=$(partition_path "$disk" "$root_part_num")
partprobe "$disk"
sync
sleep 2
wait_for_device "$efi_dev"
wait_for_device "$root_partition_device"
wait_for_device "$efi_dev" || disk_abort_hook "EFI partition $efi_dev never appeared"
wait_for_device "$root_partition_device" ||
disk_abort_hook "Root partition $root_partition_device never appeared"
# Both partitions are ours and brand new, but the space they occupy may
# carry signatures from whatever was deleted to free it.
disk_step "clearing stale signatures on $efi_dev" wipefs -af "$efi_dev"
disk_step "clearing stale signatures on $root_partition_device" wipefs -af "$root_partition_device"
if [[ "$encrypt_installation" == "true" ]]; then
step "Setting up LUKS2 on $root_partition_device"
printf "%s" "$password" | cryptsetup luksFormat --type luks2 --batch-mode "$root_partition_device" -
printf "%s" "$password" | cryptsetup open "$root_partition_device" omarchy_root -
# Kept as pipes rather than routed through disk_step: the passphrase must
# not become an argv the process table can show. Folding stderr into
# stdout still lands any error in the install log.
if ! printf "%s" "$password" |
cryptsetup luksFormat --type luks2 --batch-mode "$root_partition_device" - 2>&1; then
disk_abort_hook "Formatting LUKS2 on $root_partition_device failed"
fi
if ! printf "%s" "$password" |
cryptsetup open "$root_partition_device" omarchy_root - 2>&1; then
disk_abort_hook "Opening the encrypted root on $root_partition_device failed"
fi
root_mapper="/dev/mapper/omarchy_root"
else
wipefs -af "$root_partition_device"
root_mapper="$root_partition_device"
fi
step "Creating Btrfs filesystem and subvolumes"
mkfs.btrfs -f -L OMARCHY "$root_mapper"
wait_for_device "$root_mapper"
disk_step "creating the Btrfs filesystem on $root_mapper" \
mkfs.btrfs -f -L OMARCHY "$root_mapper"
wait_for_device "$root_mapper" || disk_abort_hook "Root device $root_mapper never appeared"
mkdir -p /mnt/btrfs-root
mount "$root_mapper" /mnt/btrfs-root
btrfs subvolume create /mnt/btrfs-root/@
btrfs subvolume create /mnt/btrfs-root/@home
btrfs subvolume create /mnt/btrfs-root/@log
btrfs subvolume create /mnt/btrfs-root/@pkg
disk_step "mounting $root_mapper" mount "$root_mapper" /mnt/btrfs-root
for subvol in @ @home @log @pkg; do
disk_step "creating subvolume $subvol" btrfs subvolume create "/mnt/btrfs-root/$subvol"
done
umount /mnt/btrfs-root
rmdir /mnt/btrfs-root
mount -o noatime,compress=zstd,subvol=@ "$root_mapper" /mnt
disk_step "mounting the target root" \
mount -o noatime,compress=zstd,subvol=@ "$root_mapper" /mnt
mkdir -p /mnt/home /mnt/var/log /mnt/var/cache/pacman/pkg /mnt"$esp_mount_in_target"
mount -o noatime,compress=zstd,subvol=@home "$root_mapper" /mnt/home
mount -o noatime,compress=zstd,subvol=@log "$root_mapper" /mnt/var/log
mount -o noatime,compress=zstd,subvol=@pkg "$root_mapper" /mnt/var/cache/pacman/pkg
disk_step "mounting /home" \
mount -o noatime,compress=zstd,subvol=@home "$root_mapper" /mnt/home
disk_step "mounting /var/log" \
mount -o noatime,compress=zstd,subvol=@log "$root_mapper" /mnt/var/log
disk_step "mounting the package cache" \
mount -o noatime,compress=zstd,subvol=@pkg "$root_mapper" /mnt/var/cache/pacman/pkg
mkfs.fat -F32 -n OMARCHY_EFI "$efi_dev"
mount "$efi_dev" /mnt"$esp_mount_in_target"
disk_step "creating the ESP filesystem on $efi_dev" mkfs.fat -F32 -n OMARCHY_EFI "$efi_dev"
disk_step "mounting the ESP" mount "$efi_dev" /mnt"$esp_mount_in_target"
# The orchestrator's first act is to verify this handoff. Check it here so
# a failure names the step that broke rather than surfacing later as
# "protected mode: /mnt is not a mountpoint".
mountpoint -q /mnt ||
disk_abort_hook "Target /mnt is not mounted; not starting the installer"
mountpoint -q "/mnt$esp_mount_in_target" ||
disk_abort_hook "ESP is not mounted at /mnt$esp_mount_in_target"
fi
local luks_uuid_json="null" luks_uuid
@@ -0,0 +1,131 @@
# Disk partitioning helpers, shared by the ISO configurator and its tests.
#
# The rule here is: never predict a partition number. parted fills the lowest
# free GPT slot, not "highest existing + 1", so any disk whose numbering has a
# hole — exactly what deleting a partition to free space leaves behind, which
# is what our own partition tool tells the user to do — hands back a number we
# did not choose. Everything below reads back what was actually created.
#
# Sourced, not executed. The configurator defines abort() and
# disk_abort_hook(); tests get the plain fallbacks.
# Partitions this run created, in creation order. rollback_created_parts()
# undoes exactly these and nothing else.
created_parts=()
# Set by create_partition() instead of being printed: a command substitution
# would run it in a subshell and lose the created_parts bookkeeping.
created_partition_number=""
# Compute partition device path, handling NVMe/mmcblk's pN naming.
partition_path() {
local _disk="$1" _num="$2"
if [[ "$_disk" == *nvme* || "$_disk" == *mmcblk* ]]; then
echo "${_disk}p${_num}"
else
echo "${_disk}${_num}"
fi
}
# Partition numbers as the on-disk GPT reports them. parted rather than lsblk
# on purpose: this is the table parted itself is about to modify, so discovery
# never depends on the kernel having re-read the partition table yet — and the
# same code works against an image file in tests, where lsblk sees nothing.
partition_numbers() {
parted -ms "$1" unit B print 2>/dev/null | tail -n +3 | cut -d: -f1
}
partition_size_bytes() {
parted -ms "$1" unit B print 2>/dev/null |
awk -F: -v n="$2" '$1 == n { gsub(/B/, "", $4); print $4; exit }'
}
# Fail loudly. The former version looped over sleep and returned its status,
# so a device that never appeared was indistinguishable from one that did.
wait_for_device() {
local i
for i in $(seq 1 10); do
[[ -b "$1" ]] && return 0
udevadm settle 2>/dev/null || true
sleep 1
done
return 1
}
_disk_abort() {
if declare -F disk_abort_hook >/dev/null; then
disk_abort_hook "$1"
elif declare -F abort >/dev/null; then
abort "$1"
fi
echo "Error: $1" >&2
exit 1
}
# Run a disk-writing command, fold its stderr into stdout, and abort on a
# non-zero exit. The fold matters: .automated_script.sh tees stdout into
# /var/log/omarchy-install.log but sends stderr straight to the tty (gum draws
# its TUI there), so an unwrapped failure leaves no trace in the log the user
# uploads — and the configurator's next screen clears it off the display too.
disk_step() {
local desc="$1"
shift
local output status=0
output=$("$@" 2>&1) || status=$?
[[ -n $output ]] && printf '%s\n' "$output"
(( status == 0 )) && return 0
_disk_abort "$desc failed (exit $status)"
}
# Create one partition and report the number parted actually assigned.
# Returns non-zero without touching created_parts if anything looks wrong;
# the caller decides how loudly to fail.
create_partition() {
local disk="$1" start="$2" end="$3" fstype="$4" name="$5"
local before after num actual want tolerance
created_partition_number=""
# Lexicographic sort on both sides: comm needs its inputs ordered the same
# way it compares them, and `sort -n` (1, 2, 10) is not that order.
before=$(partition_numbers "$disk" | sort)
parted --script "$disk" mkpart primary "$fstype" "${start}B" "${end}B" || return 1
partprobe "$disk" 2>/dev/null || true
udevadm settle 2>/dev/null || true
after=$(partition_numbers "$disk" | sort)
num=$(comm -13 <(printf '%s\n' "$before") <(printf '%s\n' "$after") | head -1)
[[ -n $num ]] || return 1
# The number must be genuinely new. This is the safety property that keeps a
# numbering mistake from ever formatting a partition somebody else is using;
# it is cheaper and more reliable than sniffing the target for signatures,
# which would false-positive on remnants left in freed space.
grep -qx "$num" <<<"$before" && return 1
actual=$(partition_size_bytes "$disk" "$num")
[[ -n $actual ]] || return 1
want=$((end - start))
tolerance=$((1024 * 1024))
(( actual >= want - tolerance && actual <= want + tolerance )) || return 1
parted --script "$disk" name "$num" "$name" || true
created_parts+=("$num")
created_partition_number="$num"
}
# Undo the partitions this run created, highest number first. Scoped strictly
# to created_parts: without this, a failed install leaves the user's freed
# space occupied by orphans, and the retry reports "not enough free space"
# with no way to connect that to what just happened.
rollback_created_parts() {
local disk="$1" n
(( ${#created_parts[@]} > 0 )) || return 0
for n in $(printf '%s\n' "${created_parts[@]}" | sort -rn); do
parted --script "$disk" rm "$n" >/dev/null 2>&1 || true
done
partprobe "$disk" 2>/dev/null || true
created_parts=()
}
@@ -765,20 +765,26 @@ def _storage_intent(ctx: InstallContext) -> dict:
def verify_protected_mounts(ctx: InstallContext) -> None:
target = ctx.target
if not _is_mountpoint(target):
raise RuntimeError(f"protected mode: {target} is not a mountpoint")
boot = _boot_intent(ctx)
storage = _storage_intent(ctx)
# Devices before the mountpoint: when the configurator hands over paths for
# partitions that do not exist, "root_device /dev/nvme0n1p12 does not
# exist" is diagnosable from the log alone, where "/mnt is not a
# mountpoint" sends everyone looking at the mount instead of the paths.
for key in ("esp_device", "root_device"):
if not storage.get(key):
device = storage.get(key)
if not device:
raise RuntimeError(f"protected mode: omarchy_install.storage.{key} missing")
if not Path(device).exists():
raise RuntimeError(f"protected mode: {key} {device} does not exist")
if not _is_mountpoint(target):
raise RuntimeError(f"protected mode: {target} is not a mountpoint")
esp_mp = target / boot["esp_mount"].lstrip("/")
if not _is_mountpoint(esp_mp):
esp_dev = storage["esp_device"]
if not Path(esp_dev).exists():
raise RuntimeError(f"protected mode: ESP device {esp_dev} does not exist")
info(f"› remounting protected ESP {esp_dev} at {esp_mp}")
esp_mp.mkdir(parents=True, exist_ok=True)
subprocess.run(["mount", esp_dev, str(esp_mp)], check=True)