From 8dc8f4265dd172d4ba9aa24487c1c22a552d4668 Mon Sep 17 00:00:00 2001 From: Git Sagar Date: Wed, 9 Sep 2026 11:21:24 -0300 Subject: [PATCH] macOS: drive the install and all customization from a Recovery "PE", no GUI Replace the screenshot/OCR/keystroke driving of Apple's Recovery with a "PE": BaseSystem.dmg (a journaled HFS+ volume, writable from Linux) with one LaunchDaemon added (makeRecoveryPE) that runs /Volumes/VMIX/run.sh as root at boot, records the status and powers off. launchd loads it alongside its signed cache (verified on Tahoe 26.6.2); same idea as AutoNBI/Imagr NetBoot images. - makeImage: the PE runs vmix-install.sh (erase, installer app, SharedSupport pkgdmg, startosinstall). Progress is read from the serial console (boot-args serial=3 -v, VMIX-* markers) and screenshots (brightness only). Fully offline; prepare now takes ~5 min instead of ~10. - customizeImage: boots the PE with the image attached and runs the template offline against the mounted System/Data volumes; OpenCore ScanPolicy restricted to HFS+/SATA so only the PE can boot. One PE boot ~30 s. The installed macOS is never booted for customization, so nothing depends on launchd/BTM approval or a first-boot agent (removed). - templates rewritten for offline use: generalize creates the user with dscl -f (admin, home, auto-login kcpassword, Setup Assistant suppression, hostname, locale, timezone, keyboard type, container resize); remote-access, no-updates, performance edit the target's plists. - makeBootDisk: build-time OpenCore variant (serial console, ScanPolicy). - vm-driver.py rewritten: passive observation only (serial markers, kernel boots, panics, brightness), disk+serial-aware hang watchdog, reboot-death reset, halt/loginwindow detection. No OCR/tesseract. - OpenCore: four SMBIOS DIMMs for MacPro7,1 (no "Memory Modules Misconfigured" warning). - tools/soak.sh: repeatability harness. Verified on daku: base install 23 min end to end; basic + generalize in three ~30 s PE boots; the result auto-logs into the desktop with the created user. Root cause of the "first-boot hang" (from the serial log): the guest's restart path panics (IOPlatformHaltRestartAction -> AppleSMC, SMCWDT smcWriteKey kSMCBadCommand, nested panic) because the pinned OSX-KVM Lilu disables itself on macOS 26, so VirtualSMC never loads. Handled by the driver (reset within 60 s); kext update to follow. Co-Authored-By: Claude Fable 5.1 Claude-Session: https://claude.ai/code/session_01XsESshRCoBoUVWV9qKURUF --- lib/images/macos/README.md | 208 +++--- lib/images/macos/default.nix | 7 +- lib/images/macos/guest/agent.sh | 42 -- .../{ch.vmix.agent.plist => ch.vmix.pe.plist} | 10 +- lib/images/macos/guest/pe-lib.sh | 51 ++ lib/images/macos/guest/pe.sh | 40 + lib/images/macos/guest/vmix-install.sh | 163 ++--- lib/images/macos/helpers/customizeImage.nix | 77 +- lib/images/macos/helpers/makeAgentPkg.nix | 105 --- lib/images/macos/helpers/makeBootDisk.nix | 29 + lib/images/macos/helpers/makeImage.nix | 95 +-- lib/images/macos/helpers/makeOpenCore.nix | 3 +- lib/images/macos/helpers/makeRecoveryPE.nix | 30 + lib/images/macos/helpers/oc-config.py | 16 + lib/images/macos/helpers/qemu.nix | 3 + lib/images/macos/helpers/vm-driver.py | 682 +++++++----------- lib/images/macos/helpers/vmix-readback.nix | 12 +- lib/images/macos/tahoe/images.nix | 7 +- lib/images/macos/templates/default.nix | 2 +- .../macos/templates/essentials/no-updates.nix | 12 +- .../templates/essentials/performance.nix | 33 +- .../templates/essentials/remote-access.nix | 7 +- lib/images/macos/templates/generalize.nix | 117 +-- lib/images/macos/tools/soak.sh | 28 + 24 files changed, 802 insertions(+), 977 deletions(-) delete mode 100644 lib/images/macos/guest/agent.sh rename lib/images/macos/guest/{ch.vmix.agent.plist => ch.vmix.pe.plist} (64%) create mode 100644 lib/images/macos/guest/pe-lib.sh create mode 100755 lib/images/macos/guest/pe.sh delete mode 100644 lib/images/macos/helpers/makeAgentPkg.nix create mode 100644 lib/images/macos/helpers/makeBootDisk.nix create mode 100644 lib/images/macos/helpers/makeRecoveryPE.nix create mode 100755 lib/images/macos/tools/soak.sh diff --git a/lib/images/macos/README.md b/lib/images/macos/README.md index 9672842..db8f90b 100644 --- a/lib/images/macos/README.md +++ b/lib/images/macos/README.md @@ -1,138 +1,100 @@ -# vmix macOS images +# macOS images (Tahoe 26) -Unattended macOS (Tahoe / 26) VM images, built the same way as the Windows -images: `makeImage` installs the OS once, templates customize it by booting it, -`.generalize` creates the user and seals the image. +Pre-installed, Apple-ID-capable macOS VM images built the same way as the +Windows ones: `makeImage` (unattended install) → templates → `.generalize` +(user, hostname, fresh SMBIOS identity). Runs on QEMU/KVM with OpenCore. ``` -vmix build --image macos.images.tahoe.basic \ - --generalize username=sagar,password=secret,hostname=MAC,timezone=Europe/Zurich -vmix run ./result --macos --vnc :10 --mem 8192 # VNC on port 5910 +vmix build --image macos.images.tahoe.basic --generalize username=sagar,password=secret,hostname=MAC +vmix run ./result --macos --vnc :10 --mem 8192 ``` -## How it works +Nix: `macos.images.tahoe.{pe,upstream,basic,remote}` and +`.generalize { username; password; hostname; timezone; locale; seed; … }`. -| step | what happens | -|---|---| -| `fetchRecovery` | BaseSystem.dmg from Apple's recovery servers (fixed-output, pinned by sha256) | -| `installerPayload` | takes the App Store `InstallAssistant.pkg` (18 GB, pinned) apart on Linux: the app skeleton (pbzx/cpio) and the byte offset of `SharedSupport.dmg` | -| `makeOpenCore` | OSX-KVM's OpenCore ESP with a config.plist rewritten for this image: SMBIOS model, serial + MLB (`macserial`), UUID and ROM = NIC MAC (derived from a seed), NIC marked built-in | -| `makeImage` | one QEMU session: Recovery boots via OpenCore → `vm-driver.py` opens Terminal with keystrokes (Ctrl-F2 menu navigation, screen-settle detection + OCR of the menu bar) and types `sh /Volumes/VMIX/run.sh` → `vmix-install.sh` erases the disk, rebuilds `Install macOS Tahoe.app` (skeleton + `SharedSupport.dmg` copied from a raw disk mapped straight out of the pkg), runs `startosinstall --installpackage vmix-agent.pkg` → installer reboots through its phases → first boot runs the **vmix agent** which powers off. OpenCore is then copied into the image's EFI partition, so it boots standalone with OVMF | -| `customizeImage` | boots the image with a FAT volume `VMIX`; the agent (LaunchDaemon `ch.vmix.agent`) runs `vmix-run.sh` as root, writes `vmix-run.status`/`.log` back and shuts down | -| `templates.generalize` | user (admin) + auto-login (`/etc/kcpassword`), Setup Assistant suppressed, hostname, timezone, no sleep, APFS grown to the disk, then the agent removes itself; a fresh SMBIOS identity is written to the ESP | +## How it works: the vmix "PE" -The vmix agent replaces Windows' Audit Mode RunOnce; `.AppleSetupDone` replaces -the OOBE unattend. Everything on the host side runs inside `__noChroot` -derivations (KVM + `/tmp`), exactly like the Windows builders. +Apple's Recovery (`BaseSystem.dmg`, a plain journaled HFS+ volume) with **one +LaunchDaemon added** (`makeRecoveryPE`): at boot it mounts a `VMIX` volume and +runs `run.sh` from it as root, records the exit status and powers off. That is +the whole automation surface — the equivalent of Windows PE + Autounattend: -## Generalize options +* **no GUI is driven**: no OCR, no keystrokes, no screen layouts to learn per + macOS version; the hook is a launchd plist, stable across releases (same idea + as AutoNBI/Imagr NetBoot images). +* **observable**: the guest prints `VMIX-*` markers to `/dev/console`, which the + build reads from QEMU's serial log (`boot-args serial=3 -v`). Kernel panics and + reboots show up there too. Screenshots are still taken for debugging. +* **offline**: no NIC during the install, and the guest blackholes Apple's + install/verify endpoints so `startosinstall` never waits on the network. The + only inputs are the pinned `InstallAssistant.pkg` and `BaseSystem.dmg`. +* **everything else happens offline from the PE too**: templates and generalize + mount the image's Data volume (rw) and System volume (ro) and edit them + (`dscl -f` for users, `plutil` for preferences) — the installed macOS is + never booted for customization, so nothing depends on launchd/BTM approval, + first-boot agents or auto-login inside the guest. One PE boot ≈ 30 s. -`username password fullName autoLogon hostname locale timezone delayOobeRun` -as for Windows (`bgColor` is accepted but ignored), plus the SMBIOS identity: -`model serial mlb uuid mac seed`. Anything unset is generated: serial/MLB by -macserial (random per build), MAC and UUID deterministically from `seed` -(default `hostname-username`). `vmix macserial --model MacPro7,1` prints a -ready-to-paste set. +### Pipeline -`delay-oobe-run=true` creates no user and re-arms Setup Assistant for the first -real boot. - -## Apple ID / iMessage - -The image satisfies what Dortania lists for iServices: unique serial + MLB for a -Tahoe-supported model (`MacPro7,1` by default; `iMac20,1/2`, -`MacBookPro16,x` also work), SystemUUID, ROM equal to en0's MAC, and en0 marked -built-in (the NIC is pinned to `PciRoot(0x0)/Pci(0x12,0x0)`). The NixOS module -and `vmix run --macos` use the MAC recorded in the image (`EFI/vmix/vmix.json`). -Give each deployed VM its own generalized image (different `seed`, or explicit -`serial=`/`mlb=`) — two VMs with the same identity will be blocked. - -## Runtime - -* `vmix run --macos [--vnc :N] [--mac ..]` -* NixOS module: `disks.os.file = vmixLib.macos.images.tahoe.basic.generalize {...}` - is auto-detected (`_vmixOsType = "macos"`): Skylake-Client CPU spoof, AppleSMC, - USB keyboard/tablet, AHCI system disk, VMware SVGA, pinned NIC with the image's MAC. - `macos.cpu`, `macos.mac`, `macos.enable` override the defaults. -* `vmix copy` writes the image to a disk but cannot grow APFS from Linux - (`diskutil apfs resizeContainer disk0s2 0` in macOS afterwards). - -## Debugging a build - -Screenshots (`NNN-.png`), `driver.log` and the QMP socket of every VM -session are in `/tmp/vmix-macos//` on the build host. The guest logs -(`install.log`, `vmix-run.log`, `vmix-agent.log`) are printed at the end of the -build. Pass `vncDisplay = ":10"` to `makeImage`/`customizeImage` (or -`--generalize vncDisplay=:10`) to watch live; with a `DISPLAY` an SDL window -is used as for Windows. - -## Updating pins (`upstream.json`) - -* installer: URL + SRI hash of a newer `InstallAssistant.pkg` - (`nix store prefetch-file --name InstallAssistant.pkg `; Mr. Macintosh's - database lists Apple's URLs) -* recovery: Apple serves the current build for the board id, so the sha256 - changes with each point release — copy the "got:" hash from the failed build -* opencore: OSX-KVM `OpenCore.qcow2` at a commit; OpenCorePkg release zip (macserial/ocvalidate) - -## Known limits - -* The Recovery bootstrap depends on keyboard navigation of the Recovery UI - (Ctrl-F2 → Utilities → Terminal). It self-corrects with screenshots + OCR and - falls back to a blind sequence, but a Recovery UI change would need - `vm-driver.py` adjusted. -* Hosts must run KVM with an AVX2-capable CPU (Intel or AMD; the guest sees a - Skylake). `sandbox = relaxed` and the `kvm` system feature, as for Windows. -* Software updates inside the VM are disabled by the `noUpdates` template - (OTA updates in a VM need the RestrictEvents kext). - -## Current status (2026-09-09): working offline install - -`macos.images.tahoe.upstream` builds a bootable, installed macOS Tahoe 26.6.2 -qcow2 **fully offline** on the KVM host — no dependency on Apple's servers at build -time, just the pinned local `InstallAssistant.pkg` and `BaseSystem.dmg`. The -finished image boots standalone (OpenCore from its own ESP) to the macOS -loginwindow. Serial/MLB/UUID/ROM are per-image for Apple ID / iMessage. - -How the install is driven (`vm-driver.py`, all by screenshot + OCR over QMP): - -* The whole `InstallAssistant.pkg` is mapped as a raw disk (it is a "pkgdmg": - xar + koly footer) and `dd`'d byte-exact into the app as `SharedSupport.dmg` — - extracting the bare xar member fails startosinstall with "pkgdmg missing a footer". -* No NIC during install + `/etc/hosts` blackhole of Apple's install/verify - endpoints, so `startosinstall`'s network calls fail fast instead of hanging — - offline prepare, no external dependency. `SecureBootModel=Disabled` lets the - sealed volume install without online personalization. -* The recovery display is kept awake with a tiny mouse jiggle (a lone keypress - does not reset display sleep, and the sleeping display swallows the menu-nav - keystrokes); the settle detector uses a coarse fingerprint so the jiggling - cursor is not seen as a screen change. -* startosinstall prepare is intermittently slow/stalls; a guest watchdog kills and - re-erases/retries an attempt that stalls or runs > 9 min. -* First boot in QEMU intermittently hangs at the Apple logo; a disk-aware watchdog - (`--progress-file`) issues a QMP `system_reset` only when the screen is dark AND - the disk is idle, so a slow-but-working boot is never interrupted. -* The install reaching the (bright) loginwindow is detected by brightness (the - faint gray "password" text does not OCR) and the driver powers the VM down — - the image is installed. macOS `shutdown -h now` halts to black without an ACPI - power-off, so a black+disk-idle screen is also treated as a completed halt. -* OpenCore is then copied into the image's own ESP so it boots standalone with OVMF. +1. `makeRecoveryPE` — BaseSystem.dmg → raw HFS+ image + `ch.vmix.pe` daemon. +2. `makeImage` — QEMU with: OpenCore boot disk (build variant with serial + console), the PE, the empty target disk, the VMIX volume (`vmix-install.sh`, + installer app skeleton) and the whole `InstallAssistant.pkg` mapped as a raw + disk. The guest script erases the target as APFS, unpacks the app and `dd`s + the pkg into it as `SharedSupport.dmg` (it is a "pkgdmg": xar + koly footer; + the bare xar member fails with "pkgdmg is missing a footer"), then runs + `startosinstall`, which reboots itself through the install phases. The + installed system's first boot ends at the loginwindow: the driver detects the + bright screen and powers the VM down. OpenCore is then copied into the image's + own ESP so it boots with plain OVMF. +3. `customizeImage` — boots the PE with the image attached (OpenCore + `ScanPolicy` restricted to HFS+ on SATA, so only the PE can boot) and runs the + template script with `$SYS`/`$DATA` mounted. `pe-lib.sh` has the helpers. +4. `templates/generalize.nix` — user (dscl, admin, home from the user template), + auto-login (`kcpassword`), Setup Assistant suppression, hostname, locale, + timezone, keyboard type, container resize, fresh SMBIOS via a new OpenCore + ESP (`serial`/`mlb` from macserial, MAC + UUID from `seed`). ### Recovery source -`recovery.file` in `upstream.json` points at a content-addressed store path for the -verified Tahoe `BaseSystem.dmg` (Apple's CDN load-balances Sequoia/Tahoe during the -rollout, so a plain fetch is non-deterministic). Reproduce it on any host with -`nix store add-path --name macos-tahoe-BaseSystem.dmg BaseSystem.dmg` (same path -from the same bytes). Set `recovery.sha256` and remove `recovery.file` to fetch it -from Apple instead (subject to the CDN rollout). +`recovery.file` in `upstream.json` points at a content-addressed store path for +the verified Tahoe `BaseSystem.dmg` (Apple's CDN load-balances Sequoia/Tahoe +during the rollout, so a plain fetch is non-deterministic). Reproduce it on any +host with `nix store add-path --name macos-tahoe-BaseSystem.dmg BaseSystem.dmg`. +Drop `recovery.file` to fetch from Apple instead (`fetchRecovery` retries until +the pinned hash matches). -### Not yet done: generalize / user creation +## Reliability -The base image installs and boots to loginwindow. `.generalize` (user creation, -auto-login, hostname) relies on the vmix agent LaunchDaemon running on first boot, -but macOS Ventura+ Background Task Management does not auto-run a headless -third-party daemon, and neither the pkg `launchctl bootstrap` (installer domain -only) nor a cron `@reboot` reliably triggered it. The robust next step is to inject -the user record + settings offline from the agent pkg's postinstall (which runs as -root on the target during install), instead of a first-boot daemon. +Things QEMU does intermittently, and what handles each (all in `vm-driver.py` +and `vmix-install.sh`; every event is logged with a reason): + +* `startosinstall` prepare stalls or crawls — the guest kills and retries it on a + freshly erased target (free-space watchdog + time cap). +* the installer comes back to the PE instead of the install phase — the PE + counts boots and simply re-runs the install (max 3). +* the installed system hangs at the Apple logo on first boot — a `system_reset` + is issued only when the screen is dark and frozen **and** disk and serial + console are idle, so a slow-but-working boot is never interrupted. +* macOS `shutdown -h` halts to a black screen without an ACPI power-off — an + idle black screen counts as a completed halt. +* a kernel panic (seen on the serial console) resets the VM. +* a wedged run fails at the 4 h timeout instead of hanging. + +`tools/soak.sh macos.images.tahoe.upstream 3` rebuilds an image N +times and tabulates outcome, duration, boots, resets, panics and retries. + +## Debugging + +`/tmp/vmix-macos//` on the build host: `driver.log`, `serial.log` +(kernel + `VMIX-*` markers), periodic PNG screenshots, `qmp.sock`. +`vmix-run.log` / `system-install.log` from the VMIX volume are printed at the +end of the build. Add `vncDisplay = ":10"` to watch. + +## QEMU profile + +`helpers/qemu.nix`: q35, `Skylake-Client` CPU spoof (works on AMD), +AppleSMC with the OSK, XHCI keyboard/tablet, AHCI disks, VMware SVGA, +virtio-net pinned to `PciRoot(0x0)/Pci(0x12,0x0)` so OpenCore marks it built-in +(en0, required for Apple ID / iMessage). SMBIOS `MacPro7,1` with four DIMMs +described (avoids the "Memory Modules Misconfigured" warning). diff --git a/lib/images/macos/default.nix b/lib/images/macos/default.nix index 6b36d2f..46c957d 100644 --- a/lib/images/macos/default.nix +++ b/lib/images/macos/default.nix @@ -9,16 +9,17 @@ let fetchRecovery = import ./helpers/fetchRecovery.nix { inherit pkgs upstream; }; installerPayload = import ./helpers/installerPayload.nix { inherit pkgs lib; }; makeOpenCore = import ./helpers/makeOpenCore.nix { inherit pkgs lib upstream macserial qemu; }; + makeBootDisk = import ./helpers/makeBootDisk.nix { inherit pkgs lib; }; + makeRecoveryPE = import ./helpers/makeRecoveryPE.nix { inherit pkgs lib; }; makeVmixVolume = import ./helpers/makeVmixVolume.nix { inherit pkgs lib; }; - makeAgentPkg = import ./helpers/makeAgentPkg.nix { inherit pkgs lib; }; installBootloader = import ./helpers/installBootloader.nix { inherit pkgs lib; }; vmixReadback = import ./helpers/vmix-readback.nix { inherit pkgs lib; }; vmDriver = ./helpers/vm-driver.py; makeImage = import ./helpers/makeImage.nix { - inherit pkgs lib qemu ident installerPayload makeOpenCore makeVmixVolume makeAgentPkg installBootloader vmixReadback vmDriver; + inherit pkgs lib qemu ident installerPayload makeOpenCore makeBootDisk makeVmixVolume installBootloader vmixReadback vmDriver; }; customizeImage = import ./helpers/customizeImage.nix { - inherit pkgs lib qemu ident makeVmixVolume makeOpenCore installBootloader vmixReadback vmDriver; + inherit pkgs lib qemu ident makeVmixVolume makeOpenCore makeBootDisk installBootloader vmixReadback vmDriver; }; customizeImageFold = builtins.foldl' customizeImage; templates = import ./templates { inherit pkgs lib; }; diff --git a/lib/images/macos/guest/agent.sh b/lib/images/macos/guest/agent.sh deleted file mode 100644 index 3e2ba02..0000000 --- a/lib/images/macos/guest/agent.sh +++ /dev/null @@ -1,42 +0,0 @@ -#!/bin/sh -# vmix agent: LaunchDaemon that runs at every boot as root (installed by the vmix -# agent pkg via startosinstall --installpackage). If a volume named VMIX carrying -# vmix-run.sh is attached, run it, record the result on the volume and power off. -# Without the volume it is a no-op (normal boot). Counterpart of the Windows Audit -# Mode RunOnce script; the generalize step removes it once the image is sealed. -LOG=/var/log/vmix-agent.log -exec >>"$LOG" 2>&1 -echo "=== vmix agent: $(date) ===" -# The agent pkg bootstraps this daemon during the OS install (to approve it past -# Background Task Management, so launchd runs it at first boot). Don't do the job -# in that installer environment — only on the installed system's first boot. -if pgrep -x bootinstalld >/dev/null 2>&1 || pgrep -qx "Installer Progress" 2>/dev/null \ - || [ -d /System/Volumes/Update/mnt1 ]; then - echo "vmix agent: OS installer is running, skipping" - exit 0 -fi -# let DiskArbitration settle so the VMIX volume is mountable -sleep 5 -V=/Volumes/VMIX -i=0 -while [ ! -f "$V/vmix-run.sh" ] && [ $i -lt 30 ]; do - diskutil mount VMIX >/dev/null 2>&1 - sleep 2 - i=$((i + 1)) -done -if [ ! -f "$V/vmix-run.sh" ]; then - echo "vmix agent: no VMIX volume, normal boot" - exit 0 -fi -echo "vmix agent: running vmix-run.sh" -cd "$V" || exit 1 -sh "$V/vmix-run.sh" >"$V/vmix-run.log" 2>&1 -rc=$? -echo "vmix agent: vmix-run.sh exited $rc" -echo "$rc" >"$V/vmix-run.status" -cp "$LOG" "$V/vmix-agent.log" 2>/dev/null -cp /var/log/vmix-agent-install.log "$V/vmix-agent-install.log" 2>/dev/null -sync -sleep 2 -diskutil unmount force "$V" >/dev/null 2>&1 -shutdown -h now diff --git a/lib/images/macos/guest/ch.vmix.agent.plist b/lib/images/macos/guest/ch.vmix.pe.plist similarity index 64% rename from lib/images/macos/guest/ch.vmix.agent.plist rename to lib/images/macos/guest/ch.vmix.pe.plist index c518fa4..a83065a 100644 --- a/lib/images/macos/guest/ch.vmix.agent.plist +++ b/lib/images/macos/guest/ch.vmix.pe.plist @@ -3,17 +3,17 @@ Label - ch.vmix.agent + ch.vmix.pe ProgramArguments - /bin/sh - /Library/vmix/agent.sh + /bin/bash + /usr/libexec/vmix/pe.sh RunAtLoad StandardOutPath - /var/log/vmix-agent.log + /dev/console StandardErrorPath - /var/log/vmix-agent.log + /dev/console diff --git a/lib/images/macos/guest/pe-lib.sh b/lib/images/macos/guest/pe-lib.sh new file mode 100644 index 0000000..08b09c1 --- /dev/null +++ b/lib/images/macos/guest/pe-lib.sh @@ -0,0 +1,51 @@ +# vmix PE helpers, sourced by run.sh scripts running in the recovery. +# Expects V=/Volumes/VMIX (set by pe.sh) and VOLUME_NAME from vmix.conf. +V=${V:-/Volumes/VMIX} +[ -f "$V/vmix.conf" ] && . "$V/vmix.conf" +VOLUME_NAME=${VOLUME_NAME:-Macintosh HD} + +pe_log() { echo "VMIX: $*"; } +pe_fail() { echo "VMIX-FAIL: $*"; exit 1; } + +# Mount the installed system's APFS volume group (System read-only, Data rw) and +# export SYS / DATA mount points plus SYS_ID / DATA_ID device identifiers. +pe_mount_target() { + local list; list=$(diskutil list) + DATA_ID=$(echo "$list" | awk -v n="APFS Volume $VOLUME_NAME - Data" 'index($0, n) {print $NF; exit}') + SYS_ID=$(echo "$list" | awk -v n="APFS Volume $VOLUME_NAME " '!/ - Data/ && index($0, n) {print $NF; exit}') + [ -n "$DATA_ID" ] && [ -n "$SYS_ID" ] || { pe_log "target volumes not found"; echo "$list"; return 1; } + diskutil mount "$SYS_ID" >/dev/null 2>&1 || true + diskutil mount "$DATA_ID" >/dev/null 2>&1 || true + SYS=$(diskutil info "$SYS_ID" | sed -n 's/^ *Mount Point: *//p') + DATA=$(diskutil info "$DATA_ID" | sed -n 's/^ *Mount Point: *//p') + [ -d "$DATA/private/var/db" ] || { pe_log "Data volume not mounted (SYS=[$SYS] DATA=[$DATA])"; return 1; } + pe_log "target mounted: SYS=[$SYS] DATA=[$DATA]" + export SYS DATA SYS_ID DATA_ID +} + +pe_unmount_target() { + sync + diskutil unmount "$DATA_ID" >/dev/null 2>&1 || true + diskutil unmount "$SYS_ID" >/dev/null 2>&1 || true +} + +# plist helpers on files of the (offline) target: create the file if missing. +pe_plist_set() { # FILE KEYPATH TYPE VALUE (TYPE: string|bool|integer|float) + local f=$1 k=$2 t=$3 v=$4 + [ -f "$f" ] || plutil -create xml1 "$f" + plutil -replace "$k" "-$t" "$v" "$f" +} +pe_plist_dict() { # FILE KEYPATH — make sure a dictionary exists at KEYPATH + local f=$1 k=$2 + [ -f "$f" ] || plutil -create xml1 "$f" + plutil -extract "$k" xml1 -o /dev/null "$f" >/dev/null 2>&1 || plutil -insert "$k" -dictionary "$f" +} +# launchd service override on the target (disabled.plist): pe_service LABEL true|false +pe_service_disabled() { + local f="$DATA/private/var/db/com.apple.xpc.launchd/disabled.plist" + mkdir -p "$(dirname "$f")" + pe_plist_set "$f" "$1" bool "$2" +} +# version of the installed system +pe_target_version() { plutil -extract ProductVersion raw -o - "$SYS/System/Library/CoreServices/SystemVersion.plist" 2>/dev/null; } +pe_target_build() { plutil -extract ProductBuildVersion raw -o - "$SYS/System/Library/CoreServices/SystemVersion.plist" 2>/dev/null; } diff --git a/lib/images/macos/guest/pe.sh b/lib/images/macos/guest/pe.sh new file mode 100755 index 0000000..ecb8f29 --- /dev/null +++ b/lib/images/macos/guest/pe.sh @@ -0,0 +1,40 @@ +#!/bin/bash +# vmix PE hook. Runs as root from launchd when the patched Recovery boots +# (injected by makeRecoveryPE). If a VMIX volume is attached it runs +# /Volumes/VMIX/run.sh, records the exit status on the volume and powers off; +# without one it does nothing and the recovery behaves normally. +# Everything printed here goes to /dev/console, i.e. the host's serial log. +exec >/dev/console 2>&1 +echo "VMIX-PE: hook started $(date) uid=$(id -u)" +V=/Volumes/VMIX +i=0 +while [ ! -f "$V/run.sh" ] && [ $i -lt 90 ]; do + diskutil mount VMIX >/dev/null 2>&1 + sleep 2; i=$((i + 1)) +done +if [ ! -f "$V/run.sh" ]; then + echo "VMIX-PE: no VMIX volume, leaving the recovery alone" + exit 0 +fi +echo "VMIX-PE: VMIX mounted after $i retries" +caffeinate -dimsu -t 86400 >/dev/null 2>&1 & +[ -f "$V/vmix.conf" ] && . "$V/vmix.conf" +# certificate checks need a sane clock; a fresh VM RTC can be off +[ -n "${BUILD_DATE:-}" ] && date -u "$BUILD_DATE" >/dev/null 2>&1 && echo "VMIX-PE: clock set to $(date -u)" +export V +cd "$V" +echo "VMIX-PE: running run.sh" +/bin/bash "$V/run.sh" 2>&1 | tee "$V/vmix-run.log" +rc=${PIPESTATUS[0]} +echo "$rc" > "$V/vmix-run.status" +echo "VMIX-PE: run.sh exited $rc" +if [ -f "$V/vmix-reboot" ]; then + rm -f "$V/vmix-reboot"; sync + echo "VMIX-PE: rebooting as requested" + reboot + exit 0 +fi +sync; sleep 1 +diskutil unmount force "$V" >/dev/null 2>&1 +echo "VMIX-PE-DONE rc=$rc" +shutdown -h now diff --git a/lib/images/macos/guest/vmix-install.sh b/lib/images/macos/guest/vmix-install.sh index 486f28d..8374331 100644 --- a/lib/images/macos/guest/vmix-install.sh +++ b/lib/images/macos/guest/vmix-install.sh @@ -1,88 +1,65 @@ -#!/bin/sh -# vmix: automated macOS install. Runs inside macOS Recovery's Terminal, started -# by vm-driver.py which types "sh /Volumes/VMIX/run.sh" for us. -# -# 1. erase the target disk (found by size) as APFS "Macintosh HD" -# 2. rebuild "Install macOS .app": app skeleton from installer-app.tar -# (host-extracted Payload) + SharedSupport.dmg = the WHOLE InstallAssistant.pkg -# dd'd byte-exact from a raw disk (Apple's own postinstall hardlinks the pkg -# there: it is a "pkgdmg" whose koly footer points at the dmg inside; the bare -# xar member fails startosinstall with "pkgdmg is missing a footer") -# 3. startosinstall unattended, with the vmix agent pkg as --installpackage -# 4. startosinstall reboots itself into the install phase; the vmix agent pkg -# installs during that phase and runs on the installed system's first boot -# -# On first boot of the installed system the agent runs /Volumes/VMIX/vmix-run.sh -# and powers off, which ends the QEMU session on the host. - -# macOS Recovery invokes us as `sh` (bash in POSIX mode, no process substitution); -# re-exec once under bash so `>(tee ...)` and other bashisms work. -if [ -z "${VMIX_REEXEC:-}" ]; then VMIX_REEXEC=1 exec bash "$0" "$@"; fi - -V="/Volumes/VMIX" -# tee to the Terminal (visible in host screenshots) and to a log on the volume -exec > >(tee "$V/install.log") 2>&1 +#!/bin/bash +# vmix unattended macOS install, run by the PE hook (pe.sh) as root in the +# Recovery with /Volumes/VMIX mounted (V). Needs vmix.conf: TARGET_BYTES, +# PKG_BYTES, PKG_DISK_BYTES, APP_NAME, VOLUME_NAME. +# 1. find the target disk and the SharedSupport (InstallAssistant.pkg) disk by size +# 2. erase the target as APFS, unpack the installer app, dd the whole pkg into it +# as SharedSupport.dmg (a "pkgdmg", startosinstall checks its koly footer) +# 3. startosinstall prepares, then reboots itself into the install phase; the +# installed system's first boot ends at the loginwindow (the host powers off) +# Never returns on success; a return means failure (the PE records the status). set -x -. "$V/vmix.conf" -# keep the recovery display awake so the host driver can watch the screen -caffeinate -dimsu -t 86400 >/dev/null 2>&1 & -pmset -a displaysleep 0 sleep 0 >/dev/null 2>&1 || true - +. "$V/pe-lib.sh" fail() { - echo "vmix-install: FAIL: $*" - cp /var/log/install.log "$V/system-install.log" 2>/dev/null || true - echo 1 >"$V/install.status" + echo "VMIX-FAIL: $*" + cp /var/log/install.log "$V/system-install.log" 2>/dev/null sync - sleep 2 - shutdown -h now 2>/dev/null || halt 2>/dev/null || true exit 1 } +# each boot into the PE with the install still pending is one attempt +ATTEMPT=$(( $(cat "$V/install.attempt" 2>/dev/null || echo 0) + 1 )) +echo "$ATTEMPT" > "$V/install.attempt"; sync +echo "VMIX-INSTALL: attempt $ATTEMPT (boot into the PE)" +[ "$ATTEMPT" -le 3 ] || fail "the installer keeps coming back to the PE ($ATTEMPT boots)" -# whole-disk identifier (diskN) whose size in bytes is exactly $1 +# --- 1. disks by exact size disk_by_size() { - for d in $(diskutil list | grep -oE '^/dev/disk[0-9]+'); do - s=$(diskutil info "$d" | sed -n 's/.*Disk Size:.*(\([0-9][0-9]*\) Bytes).*/\1/p') - [ "$s" = "$1" ] && { echo "${d#/dev/}"; return 0; } + for d in $(diskutil list | grep -oE '^/dev/disk[0-9]+' | sort -u); do + if [ "$(diskutil info "$d" | sed -n 's/.*Disk Size:.*(\([0-9]*\) Bytes).*/\1/p')" = "$1" ]; then + echo "${d#/dev/}"; return 0 + fi done return 1 } +TARGET=$(disk_by_size "$TARGET_BYTES") || fail "target disk of $TARGET_BYTES bytes not found" +SSDISK=$(disk_by_size "$PKG_DISK_BYTES") || fail "SharedSupport disk of $PKG_DISK_BYTES bytes not found" +echo "VMIX-INSTALL: target=$TARGET sharedsupport=$SSDISK" -echo "vmix-install: $(date) app=$APP_NAME volume=$VOLUME_NAME" -TARGET=$(disk_by_size "$TARGET_BYTES") || fail "target disk ($TARGET_BYTES bytes) not found" -SSDISK=$(disk_by_size "$PKG_DISK_BYTES") || fail "installer pkg disk ($PKG_DISK_BYTES bytes) not found" -echo "vmix-install: target=$TARGET sharedsupport=$SSDISK" - -# --- 1. erase the target disk as an APFS volume -diskutil eraseDisk APFS "$VOLUME_NAME" GPT "$TARGET" || fail "eraseDisk $TARGET" +# --- 2. target volume + installer app (the pkg payload skeleton + SharedSupport.dmg) VOL="/Volumes/$VOLUME_NAME" -[ -d "$VOL" ] || fail "$VOL not mounted" - -# --- 2. rebuild the installer app on the target volume -tar -xf "$V/installer-app.tar" -C "$VOL" || fail "untar installer-app.tar" APP="$VOL/$APP_NAME" -SOI="$APP/Contents/Resources/startosinstall" -[ -x "$SOI" ] || fail "startosinstall missing in $APP" SS="$APP/Contents/SharedSupport/SharedSupport.dmg" -mkdir -p "$APP/Contents/SharedSupport" -FULL=$((PKG_BYTES / 1048576)) -REM=$((PKG_BYTES % 1048576)) -dd if="/dev/r$SSDISK" of="$SS" bs=1048576 count=$FULL || fail "dd SharedSupport.dmg" -if [ "$REM" -gt 0 ]; then - dd if="/dev/r$SSDISK" bs=1048576 skip=$FULL count=1 2>/dev/null | dd bs=1 count=$REM >>"$SS" || fail "dd SharedSupport.dmg tail" -fi -[ "$(stat -f %z "$SS")" = "$PKG_BYTES" ] || fail "SharedSupport.dmg size mismatch: $(stat -f %z "$SS") != $PKG_BYTES" -tail -c 512 "$SS" | grep -qa koly || fail "SharedSupport.dmg has no UDIF koly footer" -chflags -h norestricted "$SS" 2>/dev/null || true -echo "vmix-install: app=$APP SharedSupport.dmg=$(stat -f %z "$SS") bytes" +prepare_target() { + diskutil eraseDisk APFS "$VOLUME_NAME" GPT "$TARGET" || fail "eraseDisk" + [ -d "$VOL" ] || fail "$VOL not mounted after erase" + tar -xf "$V/installer-app.tar" -C "$VOL" || fail "untar installer app" + [ -x "$APP/Contents/Resources/startosinstall" ] || fail "startosinstall missing from $APP" + mkdir -p "$APP/Contents/SharedSupport" + FULL=$(( PKG_BYTES / 1048576 )); REM=$(( PKG_BYTES % 1048576 )) + echo "VMIX-INSTALL: copying SharedSupport.dmg ($PKG_BYTES bytes) from /dev/r$SSDISK" + dd if="/dev/r$SSDISK" of="$SS" bs=1048576 count=$FULL || fail "dd SharedSupport" + [ "$REM" -gt 0 ] && { dd if="/dev/r$SSDISK" bs=1048576 skip=$FULL count=1 | dd bs=1 count=$REM >> "$SS"; } || true + [ "$(stat -f %z "$SS")" = "$PKG_BYTES" ] || fail "SharedSupport.dmg size $(stat -f %z "$SS") != $PKG_BYTES" + tail -c 512 "$SS" | grep -qa koly || fail "SharedSupport.dmg has no koly footer" + chflags -h norestricted "$SS" 2>/dev/null || true + sync +} +prepare_target +SOI="$APP/Contents/Resources/startosinstall" +echo "VMIX-INSTALL: app ready, clock $(date -u)" -# macOS certificate validation needs a sane clock; a fresh VM RTC can be wrong. -echo "vmix-install: guest clock is $(date) (UTC $(date -u))" -if [ -n "${BUILD_DATE:-}" ]; then - date -u "$BUILD_DATE" && echo "vmix-install: set clock to $(date)" -fi - -# Blackhole Apple's install/verify endpoints so osinstallersetupd's network calls -# fail immediately instead of timing out (prepare otherwise crawls). Fully offline. +# Offline install: no NIC is attached. Blackhole Apple's install/verify endpoints +# too, so osinstallersetupd's requests fail immediately instead of timing out. for d in swscan.apple.com swcdn.apple.com swdist.apple.com swquery.apple.com \ gs.apple.com gsa.apple.com gdmf.apple.com mesu.apple.com xp.apple.com \ albert.apple.com captive.apple.com deviceservices-external.apple.com \ @@ -90,50 +67,34 @@ for d in swscan.apple.com swcdn.apple.com swdist.apple.com swquery.apple.com \ ocsp2.apple.com valid.apple.com; do echo "127.0.0.1 $d" >> /etc/hosts done -echo "vmix-install: blackholed Apple install endpoints for a fast offline prepare" -# --- 3. unattended install. startosinstall prepares then reboots the machine -# itself into the install phase. Prepare intermittently stalls (~46% — an online -# verify/personalization step through the VM's NAT), so a watchdog kills and -# retries startosinstall if the target volume makes no write progress for a while. -# The vmix agent pkg installs during the install phase and runs on first boot. -# quote args properly — $VOL contains a space ("Macintosh HD") +# --- 3. startosinstall prepares (~5 min) then reboots the machine itself into the +# install phase; it never returns on success. Prepare is intermittently slow in +# QEMU, so an attempt that stalls or runs too long is killed and retried on a +# freshly erased target. run_soi() { "$SOI" --volume "$VOL" --agreetolicense --nointeraction --rebootdelay 5 "$@"; } free_kb() { df -k "$VOL" 2>/dev/null | awk 'NR==2 {print $4}'; } - -attempt=0 -while [ "$attempt" -lt 10 ]; do - attempt=$((attempt + 1)) - echo "vmix-install: startosinstall attempt $attempt" - if [ "$attempt" -eq 1 ]; then - run_soi --installpackage "$V/vmix-agent.pkg" 2>&1 & - else - # a stalled attempt leaves the volume dirty; re-erase and rebuild for a clean retry - diskutil eraseDisk APFS "$VOLUME_NAME" GPT "$TARGET" || fail "eraseDisk on retry" - tar -xf "$V/installer-app.tar" -C "$VOL" || fail "untar on retry" - mkdir -p "$APP/Contents/SharedSupport" - dd if="/dev/r$SSDISK" of="$SS" bs=1048576 count=$FULL 2>/dev/null - [ "$REM" -gt 0 ] && dd if="/dev/r$SSDISK" bs=1048576 skip=$FULL count=1 2>/dev/null | dd bs=1 count=$REM >>"$SS" 2>/dev/null - chflags -h norestricted "$SS" 2>/dev/null || true - run_soi --installpackage "$V/vmix-agent.pkg" 2>&1 & - fi +try=0 +while [ "$try" -lt 6 ]; do + try=$((try + 1)) + [ "$try" -gt 1 ] && prepare_target + echo "VMIX-INSTALL: startosinstall try $try" + run_soi 2>&1 & SOI_PID=$! - # watchdog: kill startosinstall if free space stalls for ~4 min OR the attempt - # simply takes too long (prepare is intermittently slow; healthy = a few minutes) last=$(free_kb); stalled=0; elapsed=0 while kill -0 "$SOI_PID" 2>/dev/null; do sleep 30; elapsed=$((elapsed + 30)) now=$(free_kb) if [ "$now" = "$last" ]; then stalled=$((stalled + 30)); else stalled=0; last=$now; fi - if [ "$stalled" -ge 240 ] || [ "$elapsed" -ge 540 ]; then - echo "vmix-install: prepare too slow (stalled=${stalled}s elapsed=${elapsed}s), killing to retry" + [ $((elapsed % 120)) -eq 0 ] && echo "VMIX-INSTALL: prepare running ${elapsed}s (stalled ${stalled}s)" + if [ "$stalled" -ge 240 ] || [ "$elapsed" -ge 600 ]; then + echo "VMIX-INSTALL: prepare too slow (stalled=${stalled}s elapsed=${elapsed}s), killing to retry" kill -9 "$SOI_PID" 2>/dev/null; pkill -9 -f startosinstall 2>/dev/null break fi done wait "$SOI_PID" 2>/dev/null - # on success startosinstall reboots the machine and we never get here - echo "vmix-install: startosinstall attempt $attempt ended without rebooting" + echo "VMIX-INSTALL: startosinstall try $try ended without rebooting" sleep 3 done -fail "startosinstall did not complete after $attempt attempts" +fail "startosinstall did not complete after $try tries" diff --git a/lib/images/macos/helpers/customizeImage.nix b/lib/images/macos/helpers/customizeImage.nix index df8df32..fd267eb 100644 --- a/lib/images/macos/helpers/customizeImage.nix +++ b/lib/images/macos/helpers/customizeImage.nix @@ -1,13 +1,16 @@ -# Customize a macOS image by booting it with a VMIX volume: the vmix agent -# (LaunchDaemon installed by makeImage) runs `script` as root, records the exit -# status on the volume and powers off. Optionally re-installs OpenCore with a new -# SMBIOS identity (`smbios`). Counterpart of the Windows auditScript flow. +# Customize a macOS image offline from the vmix PE: the recovery boots with the +# image and a VMIX volume attached, its hook runs `script` as root with the +# image's System (read-only) and Data (rw) volumes mounted at $SYS / $DATA, then +# powers off. The installed macOS itself is never booted, so nothing depends on +# launchd/BTM approval inside the guest. Counterpart of the Windows +# registry/audit flow. Optionally re-installs OpenCore with a new SMBIOS +# identity (`smbios`). # # Templates provide: -# script — sh script run as root on the booted system +# script — sh script run as root in the PE (pe-lib.sh helpers available) # files — [{ source; name; }] extra files placed next to it on /Volumes/VMIX # smbios — { model? serial? mlb? uuid? mac? seed? } → fresh OpenCore config in the ESP -{ pkgs, lib, qemu, ident, makeVmixVolume, makeOpenCore, installBootloader, vmixReadback, vmDriver, ... }: +{ pkgs, lib, qemu, ident, makeVmixVolume, makeOpenCore, makeBootDisk, installBootloader, vmixReadback, vmDriver, ... }: originalImage: { name ? "", script ? "", @@ -19,7 +22,7 @@ originalImage: { smp ? 4, memSize ? 4096, cpu ? qemu.defaultCpu, - timeout ? 3600, + timeout ? 1800, }: let originalImageName = lib.strings.removeSuffix "-vmix" (lib.strings.removeSuffix ".qcow2" originalImage.name); @@ -27,6 +30,8 @@ let resultImg = "./disk.qcow2"; hasScript = script != ""; hasSmbios = smbios != null; + pe = originalImage.pe or (throw "vmix: image ${originalImage.name} carries no PE (built by an older makeImage?)"); + volumeName = originalImage.volumeName or "Macintosh HD"; model = originalImage.model or "MacPro7,1"; seed = if hasSmbios && (smbios.seed or null) != null then smbios.seed else null; @@ -45,46 +50,60 @@ let inherit mac uuid; } // builtins.removeAttrs smbios [ "seed" "mac" "uuid" "model" ]) else originalImage.opencore; + # PE boot disk: serial console, and an OpenCore ScanPolicy that only allows + # HFS+ volumes on SATA (= the PE), so the image's own macOS is never booted. + # 0x10203 = FILE_SYSTEM_LOCK | DEVICE_LOCK | ALLOW_FS_HFS | ALLOW_DEVICE_SATA + bootDisk = makeBootDisk { + name = "${name}-${originalImageName}-pe"; + esp = originalImage.opencore; + bootArgs = "keepsyms=1 serial=3 -v"; + scanPolicy = 66051; + }; - runScript = pkgs.writeText "${name}-vmix-run.sh" '' - #!/bin/sh + runScript = pkgs.writeText "${name}-run.sh" '' + #!/bin/bash + . /Volumes/VMIX/pe-lib.sh echo "=== vmix: ${name} ===" + pe_mount_target || pe_fail "could not mount the target volumes" ${script} + pe_unmount_target ''; vmixVol = makeVmixVolume { name = "${name}-${originalImageName}"; - files = [ { source = runScript; name = "vmix-run.sh"; } ] ++ files; + files = [ + { source = runScript; name = "run.sh"; } + { source = ../guest/pe-lib.sh; name = "pe-lib.sh"; } + ] ++ files; }; driverPython = pkgs.python3.withPackages (p: [ p.pillow ]); bootCommands = lib.optionalString hasScript '' cp ${vmixVol} vmix.img chmod +w vmix.img + cat > vmix.conf </dev/null | head -1) - if [ -n "$VMIX_DF" ] && [ "$(stat -c %s "$VMIX_DF")" -lt 256 ] && ! grep -q -P '[^\x20-\x7e\n]' "$VMIX_DF"; then - export DISPLAY=$(tr -d '\n' < "$VMIX_DF") - export HOME=$(mktemp -d) - export XDG_RUNTIME_DIR=$HOME - export SDL_VIDEODRIVER=x11 - VMIX_DISPLAY="-display sdl" - fi - ''} - echo "=== vmix: booting ${originalImageName} for ${name} ===" - python3 ${vmDriver} --mode boot --name "${name}-${originalImageName}" --timeout ${toString timeout} --progress-file ${resultImg} -- \ + echo "=== vmix: running ${name} in the PE against ${originalImageName} ===" + python3 ${vmDriver} --mode pe --name "${name}-${originalImageName}" --timeout ${toString timeout} \ + --serial-log serial.log --progress-file ${resultImg} -- \ qemu-system-x86_64 $VMIX_DISPLAY \ ${qemu.machineArgs { inherit cpu smp memSize; }} \ ${qemu.firmwareArgs "vars.fd"} \ - ${qemu.sataDrive { id = "system"; port = 0; file = resultImg; }} \ - ${qemu.sataDrive { id = "vmix"; port = 1; file = "vmix.img"; format = "raw"; }} \ - ${qemu.netArgs { mac = originalImage.macAddress; }} \ - || { echo "vmix: VM failed during ${name} (see /tmp/vmix-macos/${name}-${originalImageName})"; exit 1; } + ${qemu.serialArgs "serial.log"} \ + ${qemu.sataDrive { id = "opencore"; port = 0; file = "ocboot.qcow2"; }} \ + ${qemu.sataDrive { id = "pe"; port = 1; file = "pe.qcow2"; }} \ + ${qemu.sataDrive { id = "system"; port = 2; file = resultImg; }} \ + ${qemu.sataDrive { id = "vmix"; port = 3; file = "vmix.img"; format = "raw"; }} \ + || { echo "vmix: PE failed during ${name} (see /tmp/vmix-macos/${name}-${originalImageName})"; exit 1; } ${vmixReadback "vmix.img"} [ "$STATUS" = "0" ] || { echo "vmix: ${name} script failed (status '$STATUS')"; exit 1; } @@ -92,7 +111,7 @@ let ''; builtImage = pkgs.runCommand customImageName ({ - nativeBuildInputs = with pkgs; [ pkgs.qemu mtools driverPython libguestfs-with-appliance ]; + nativeBuildInputs = with pkgs; [ pkgs.qemu driverPython libguestfs-with-appliance ]; requiredSystemFeatures = [ "kvm" ]; } // lib.optionalAttrs impure { __noChroot = true; }) '' qemu-img create -q -f qcow2 -b ${originalImage} -F qcow2 ${resultImg} @@ -102,4 +121,4 @@ let mv ${resultImg} $out ''; in - builtImage // { _vmixOsType = "macos"; macAddress = mac; opencore = esp; model = esp.model or model; } + builtImage // { _vmixOsType = "macos"; macAddress = mac; opencore = esp; model = esp.model or model; inherit pe volumeName; } diff --git a/lib/images/macos/helpers/makeAgentPkg.nix b/lib/images/macos/helpers/makeAgentPkg.nix deleted file mode 100644 index 77dcf19..0000000 --- a/lib/images/macos/helpers/makeAgentPkg.nix +++ /dev/null @@ -1,105 +0,0 @@ -# Distribution-style flat package (xar + bom + cpio, built on Linux) for -# `startosinstall --installpackage`. macOS installs it during the first boot of the -# installed system (bootinstalld, "Installer Progress"): it places the vmix agent -# LaunchDaemon, marks Setup Assistant as done, starts the agent, and schedules a -# reboot as a fallback so the daemon runs even if bootstrapping failed. -# -# The files are shipped inside Scripts and copied by postinstall: installd unpacks -# our Scripts archive fine, but "shoves 0 items" from a Linux-made Payload. -{ pkgs, lib, ... }: -{ version ? "1.0" }: -let - id = "ch.vmix.agent"; - # nixpkgs' bomutils aborts under _FORTIFY_SOURCE - bomutils = pkgs.bomutils.overrideAttrs (_: { hardeningDisable = [ "fortify" ]; }); - postinstall = pkgs.writeText "postinstall" '' - #!/bin/sh - # Runs during the OS install (bootinstalld) with $3 = the target system root. - # Only place files; the ch.vmix.agent LaunchDaemon then runs on the installed - # system's first boot via RunAtLoad (confirmed loading on Tahoe). - T="''${3%/}" - HERE="$(cd "$(dirname "$0")" && pwd)" - LOG="$T/private/var/log/vmix-agent-install.log" - mkdir -p "$T/private/var/log" - exec >>"$LOG" 2>&1 - echo "=== vmix agent pkg postinstall $(date) target=[$3] ===" - mkdir -p "$T/Library/LaunchDaemons" "$T/Library/vmix" "$T/private/var/db" - cp "$HERE/agent.sh" "$T/Library/vmix/agent.sh" - cp "$HERE/${id}.plist" "$T/Library/LaunchDaemons/${id}.plist" - chmod 755 "$T/Library/vmix/agent.sh" - chmod 644 "$T/Library/LaunchDaemons/${id}.plist" - chown -R root:wheel "$T/Library/vmix" "$T/Library/LaunchDaemons/${id}.plist" - touch "$T/private/var/db/.AppleSetupDone" - chown root:wheel "$T/private/var/db/.AppleSetupDone" - ls -la "$T/Library/vmix/agent.sh" "$T/Library/LaunchDaemons/${id}.plist" - # A pkg LaunchDaemon is registered with Background Task Management but stays - # pending approval, so it will not auto-run headless. Two BTM-exempt triggers: - # - bootstrap it now (starts it in the installer env; the agent no-ops there) - # - a root cron @reboot job (Apple's cron daemon is trusted, runs it at boot) - launchctl bootstrap system "$T/Library/LaunchDaemons/${id}.plist" 2>&1 && echo "bootstrapped" || echo "bootstrap returned $?" - mkdir -p "$T/usr/lib/cron/tabs" - printf '@reboot /bin/sh /Library/vmix/agent.sh\n' > "$T/usr/lib/cron/tabs/root" - chmod 600 "$T/usr/lib/cron/tabs/root" - chown root:wheel "$T/usr/lib/cron/tabs/root" - echo "cron @reboot installed" - exit 0 - ''; -in -pkgs.runCommand "vmix-agent-${version}.pkg" { - nativeBuildInputs = [ pkgs.xar bomutils pkgs.cpio pkgs.libarchive pkgs.gzip ]; -} '' - mkdir -p root/Library/LaunchDaemons root/Library/vmix scripts flat/vmix-agent.pkg - cp ${../guest/agent.sh} root/Library/vmix/agent.sh - cp ${../guest/ch.vmix.agent.plist} root/Library/LaunchDaemons/${id}.plist - chmod 755 root/Library/vmix/agent.sh - chmod 644 root/Library/LaunchDaemons/${id}.plist - # the same files ride along in Scripts, which is what postinstall installs from - cp ${postinstall} scripts/postinstall - cp ${../guest/agent.sh} scripts/agent.sh - cp ${../guest/ch.vmix.agent.plist} scripts/${id}.plist - chmod 755 scripts/postinstall scripts/agent.sh - - NFILES=$(find root | wc -l) - KBYTES=$(du -sk root | cut -f1) - # bsdcpio keeps the "./" prefix the Bom uses (GNU cpio strips it and installd then extracts nothing) - (cd root && find . | bsdcpio -o --format odc --quiet | gzip -c > ../flat/vmix-agent.pkg/Payload) - (cd scripts && find . | cpio -o --format odc --owner 0:0 --quiet | gzip -c > ../flat/vmix-agent.pkg/Scripts) - mkbom -u 0 -g 80 root flat/vmix-agent.pkg/Bom - - cat > flat/vmix-agent.pkg/PackageInfo < - - - - - - - - - - - - - XML - cat > flat/Distribution < - - vmix agent - - - - - - - - - - - - #vmix-agent.pkg - - XML - sed -i 's/^ //' flat/vmix-agent.pkg/PackageInfo flat/Distribution - (cd flat && xar --compression none -cf $out Distribution vmix-agent.pkg) - xar -t -f $out -'' diff --git a/lib/images/macos/helpers/makeBootDisk.nix b/lib/images/macos/helpers/makeBootDisk.nix new file mode 100644 index 0000000..9eaba7e --- /dev/null +++ b/lib/images/macos/helpers/makeBootDisk.nix @@ -0,0 +1,29 @@ +# OpenCore boot disk for build-time boots, derived from an image's ESP +# (makeOpenCore output) with build-only settings: extra boot-args (serial +# console, verbose) and optionally an OpenCore ScanPolicy so that only the PE +# (an HFS+ volume on SATA) is bootable — the build never lands on the wrong OS. +{ pkgs, lib, ... }: +{ esp, bootArgs ? null, scanPolicy ? null, name ? "boot" }: +pkgs.runCommand "${name}-bootdisk" { + nativeBuildInputs = with pkgs; [ python3 mtools dosfstools gptfdisk ]; +} '' + cp -r ${esp}/EFI EFI + chmod -R u+w EFI + python3 - <<'PY' + import plistlib + p = 'EFI/OC/config.plist' + cfg = plistlib.load(open(p, 'rb')) + nv = cfg['NVRAM']['Add']['7C436110-AB2A-4BBB-A880-FE41995C9F82'] + ${lib.optionalString (bootArgs != null) ''nv['boot-args'] = ${builtins.toJSON bootArgs}''} + ${lib.optionalString (scanPolicy != null) ''cfg['Misc']['Security']['ScanPolicy'] = ${toString scanPolicy}''} + plistlib.dump(cfg, open(p, 'wb')) + print('boot-args:', nv['boot-args'], 'ScanPolicy:', cfg['Misc']['Security']['ScanPolicy']) + PY + mkdir -p $out + truncate -s 64M $out/boot.img + sgdisk -n 1:2048:0 -t 1:EF00 -c 1:EFI $out/boot.img >/dev/null + SECTORS=$(( 64*1024*1024/512 - 2048 - 34 )) + mkfs.vfat -F 32 -n OPENCORE --offset 2048 $out/boot.img $(( SECTORS / 2 )) >/dev/null + mcopy -i $out/boot.img@@1M -s EFI :: + mdir -i $out/boot.img@@1M ::EFI/OC >/dev/null +'' diff --git a/lib/images/macos/helpers/makeImage.nix b/lib/images/macos/helpers/makeImage.nix index fdafac2..0d64426 100644 --- a/lib/images/macos/helpers/makeImage.nix +++ b/lib/images/macos/helpers/makeImage.nix @@ -1,77 +1,59 @@ -# Build a pre-installed macOS qcow2 with an unattended QEMU install. -# -# One QEMU session, driven by vm-driver.py: -# Recovery (BaseSystem) boots via OpenCore → driver opens Terminal with -# keystrokes and types "sh /Volumes/VMIX/run.sh" → vmix-install.sh erases the -# disk, rebuilds the installer app from installer-app.tar + the SharedSupport.dmg -# raw disk, runs startosinstall (--installpackage vmix-agent.pkg) → the installer -# reboots through its phases → first boot of macOS runs the vmix agent, which -# executes vmix-run.sh and powers off → QEMU exits. -# Afterwards OpenCore is copied into the image's EFI partition so the result -# boots standalone with plain OVMF. Apply templates with customizeImageFold, -# then .generalize to create the user and set a fresh SMBIOS identity. -{ pkgs, lib, qemu, ident, installerPayload, makeOpenCore, makeVmixVolume, makeAgentPkg, installBootloader, vmixReadback, vmDriver, ... }: +# Build a pre-installed macOS qcow2 with an unattended install driven from the +# vmix PE (Apple's Recovery + one LaunchDaemon, see makeRecoveryPE): +# OpenCore boots the PE → its hook runs /Volumes/VMIX/run.sh (vmix-install.sh) +# → erase the disk, rebuild the installer app from installer-app.tar + the +# SharedSupport raw disk, startosinstall → the installer reboots through its +# phases → the installed system's first boot reaches the loginwindow → the +# driver powers it off. No GUI is driven; progress is read from the serial +# console and screenshots (brightness). Fully offline: no NIC is attached. +# Then OpenCore is copied into the image's own ESP so it boots with plain OVMF. +# Apply templates with customizeImageFold, then .generalize. +{ pkgs, lib, qemu, ident, installerPayload, makeOpenCore, makeBootDisk, makeVmixVolume, installBootloader, vmixReadback, vmDriver, ... }: { name ? "macos", - installer, # InstallAssistant.pkg (fetchurl) - recovery, # BaseSystem.dmg (fetchRecovery) + installer, # InstallAssistant.pkg + pe, # makeRecoveryPE output for the same macOS version diskSize ? "128G", volumeName ? "Macintosh HD", smp ? 4, memSize ? 8192, cpu ? qemu.defaultCpu, - model ? "MacPro7,1", # SMBIOS model; must be Tahoe-supported (MacPro7,1, iMac20,1/2, MacBookPro16,x) + model ? "MacPro7,1", # SMBIOS model; must be supported by the installed macOS seed ? name, # MAC address + SystemUUID are derived from this bootArgs ? "keepsyms=1", vncDisplay ? null, # e.g. ":10" to watch the install on port 5910 timeout ? 4 * 3600, # seconds for the whole install extraOpenCoreConfig ? {}, # merged into config.plist - installNetwork ? false, # attach a NIC during install (default: offline — startosinstall - # otherwise hangs on Apple personalization through a flaky NAT) + installNetwork ? false, # attach a NIC during the install (default: offline) }: let mac = ident.macFromSeed seed; uuid = ident.uuidFromSeed seed; - esp = makeOpenCore { name = "${name}-opencore"; inherit model mac uuid bootArgs; extraConfig = extraOpenCoreConfig; }; + esp = makeOpenCore { name = "${name}-opencore"; inherit model mac uuid bootArgs memSize; extraConfig = extraOpenCoreConfig; }; + # build-time boot disk: same identity, plus serial console + verbose boot + bootDisk = makeBootDisk { name = "${name}-install"; inherit esp; bootArgs = "${bootArgs} serial=3 -v"; }; payload = installerPayload { inherit name; pkg = installer; }; - recoveryImg = pkgs.runCommand "${name}-BaseSystem.img" { nativeBuildInputs = [ pkgs.dmg2img ]; } '' - dmg2img -s ${recovery} $out - ''; - agentPkg = makeAgentPkg { }; - agentDir = pkgs.runCommand "vmix-agent-files" { } '' - mkdir -p $out - cp ${../guest/agent.sh} $out/agent.sh - cp ${../guest/ch.vmix.agent.plist} $out/ch.vmix.agent.plist - ''; - firstBoot = pkgs.writeText "vmix-run.sh" '' - echo "vmix: first boot of the installed system" - sw_vers - exit 0 - ''; vmixVol = makeVmixVolume { inherit name; size = "512M"; files = [ { source = ../guest/vmix-install.sh; name = "run.sh"; } + { source = ../guest/pe-lib.sh; name = "pe-lib.sh"; } { source = "${payload}/installer-app.tar"; name = "installer-app.tar"; } - { source = agentPkg; name = "vmix-agent.pkg"; } - { source = agentDir; name = "agent"; } - { source = firstBoot; name = "vmix-run.sh"; } ]; }; - driverPython = pkgs.python3.withPackages (p: [ p.pillow p.pytesseract ]); - tesseract = pkgs.tesseract.override { enableLanguages = [ "eng" ]; }; + driverPython = pkgs.python3.withPackages (p: [ p.pillow ]); drv = pkgs.runCommand "${name}-vmix.qcow2" { __noChroot = true; requiredSystemFeatures = [ "kvm" ]; - nativeBuildInputs = with pkgs; [ pkgs.qemu mtools jq driverPython tesseract libguestfs-with-appliance ]; + nativeBuildInputs = with pkgs; [ pkgs.qemu jq driverPython libguestfs-with-appliance ]; } '' echo "=== vmix: creating ${diskSize} disk ===" qemu-img create -f qcow2 disk.qcow2 ${diskSize} # store files are read-only and AHCI needs writable nodes: qcow2 overlays - qemu-img create -q -f qcow2 -F raw -b ${recoveryImg} recovery.qcow2 - qemu-img create -q -f qcow2 -F raw -b ${esp}/boot.img ocboot.qcow2 + qemu-img create -q -f qcow2 -F raw -b ${pe} pe.qcow2 + qemu-img create -q -f qcow2 -F raw -b ${bootDisk}/boot.img ocboot.qcow2 # Apple's postinstall hardlinks the WHOLE InstallAssistant.pkg as # Contents/SharedSupport/SharedSupport.dmg: the pkg is a "pkgdmg" (xar + koly @@ -99,42 +81,33 @@ let cp ${pkgs.OVMF.fd}/FV/OVMF_VARS.fd vars.fd chmod +w vars.fd - VMIX_DISPLAY="-display none" ${lib.optionalString (vncDisplay != null) ''VMIX_DISPLAY="-display none -vnc ${vncDisplay}"''} - ${lib.optionalString (vncDisplay == null) '' - VMIX_DF=$(ls -t /tmp/.vmix-display-* 2>/dev/null | head -1) - if [ -n "$VMIX_DF" ] && [ "$(stat -c %s "$VMIX_DF")" -lt 256 ] && ! grep -q -P '[^\x20-\x7e\n]' "$VMIX_DF"; then - export DISPLAY=$(tr -d '\n' < "$VMIX_DF") - export HOME=$(mktemp -d) - export XDG_RUNTIME_DIR=$HOME - export SDL_VIDEODRIVER=x11 - VMIX_DISPLAY="-display sdl" - fi - ''} - echo "=== vmix: installing ${name} (unattended, 1-2 h; screenshots in /tmp/vmix-macos/${name}) ===" - python3 ${vmDriver} --mode install --name ${name} --timeout ${toString timeout} --progress-file disk.qcow2 -- \ + echo "=== vmix: installing ${name} (unattended, ~1 h; logs and screenshots in /tmp/vmix-macos/${name}) ===" + python3 ${vmDriver} --mode install --name ${name} --timeout ${toString timeout} \ + --serial-log serial.log --progress-file disk.qcow2 -- \ qemu-system-x86_64 $VMIX_DISPLAY \ ${qemu.machineArgs { inherit cpu smp memSize; }} \ ${qemu.firmwareArgs "vars.fd"} \ + ${qemu.serialArgs "serial.log"} \ ${qemu.sataDrive { id = "opencore"; port = 0; file = "ocboot.qcow2"; }} \ - ${qemu.sataDrive { id = "recovery"; port = 1; file = "recovery.qcow2"; }} \ + ${qemu.sataDrive { id = "pe"; port = 1; file = "pe.qcow2"; }} \ ${qemu.sataDrive { id = "system"; port = 2; file = "disk.qcow2"; }} \ ${qemu.sataDrive { id = "vmix"; port = 3; file = "vmix.img"; format = "raw"; }} \ ${qemu.sataDrive { id = "sharedsupport"; port = 4; file = "sharedsupport.qcow2"; }} \ ${lib.optionalString installNetwork (qemu.netArgs { inherit mac; })} \ || { echo "vmix: install VM failed (see /tmp/vmix-macos/${name})"; exit 1; } - # The driver exits non-zero (handled above) if the install did not reach a - # completed/powered-off state, so reaching here means the OS is installed. - # vmix-run.status is written only when the agent ran (cron/daemon); log it. + # The PE records a status only if run.sh returned, i.e. the install failed + # before the installer took over and rebooted. ${vmixReadback "vmix.img"} - [ "$STATUS" = "0" ] && echo "vmix: first-boot agent completed (status 0)" \ - || echo "vmix: install reached loginwindow (agent status '$STATUS'); image is installed" + if [ -n "$STATUS" ] && [ "$STATUS" != "0" ]; then + echo "vmix: install script failed (status $STATUS), see /tmp/vmix-macos/${name}"; exit 1 + fi ${installBootloader { inherit esp; image = "disk.qcow2"; }} echo "=== vmix: ${name} install complete (serial $(jq -r .serial ${esp}/vmix.json), mac ${mac}) ===" mv disk.qcow2 $out ''; -in drv // { _vmixOsType = "macos"; macAddress = mac; opencore = esp; inherit model; } +in drv // { _vmixOsType = "macos"; macAddress = mac; opencore = esp; inherit model pe volumeName; } diff --git a/lib/images/macos/helpers/makeOpenCore.nix b/lib/images/macos/helpers/makeOpenCore.nix index f0a120b..5ae1475 100644 --- a/lib/images/macos/helpers/makeOpenCore.nix +++ b/lib/images/macos/helpers/makeOpenCore.nix @@ -18,6 +18,7 @@ showPicker ? true, pickerTimeout ? 2, extraConfig ? {}, + memSize ? 8192, # RAM described in SMBIOS (MacPro7,1 wants 4 DIMMs) }: let ocImage = pkgs.fetchurl { inherit (upstream.opencore.image) url sha256; name = "OSX-KVM-OpenCore.qcow2"; }; @@ -50,7 +51,7 @@ pkgs.runCommand "${name}-esp" { --model "${model}" --serial "$SERIAL" --mlb "$MLB" --uuid "${uuid}" --mac "${mac}" \ --nic-path "${qemu.nicDevicePath}" --boot-args "${bootArgs}" --resolution "${resolution}" \ --show-picker "${lib.boolToString showPicker}" --timeout ${toString pickerTimeout} \ - --extra-json ${lib.escapeShellArg (builtins.toJSON extraConfig)} + --extra-json ${lib.escapeShellArg (builtins.toJSON extraConfig)} --memory-mb ${toString memSize} ocvalidate $out/EFI/OC/config.plist || echo "vmix: ocvalidate reported issues (OpenCore version may differ from validator), continuing" jq -n --arg model "${model}" --arg serial "$SERIAL" --arg mlb "$MLB" --arg uuid "${uuid}" --arg mac "${mac}" \ diff --git a/lib/images/macos/helpers/makeRecoveryPE.nix b/lib/images/macos/helpers/makeRecoveryPE.nix new file mode 100644 index 0000000..6e6694a --- /dev/null +++ b/lib/images/macos/helpers/makeRecoveryPE.nix @@ -0,0 +1,30 @@ +# The vmix "PE": Apple's Recovery (BaseSystem.dmg) with one LaunchDaemon added +# that runs /Volumes/VMIX/run.sh as root at boot and powers off afterwards. +# BaseSystem is a plain (journaled) HFS+ volume that Linux can write with the +# hfsplus driver's force option — the pristine image's journal is empty, so this +# is safe. The kernel and boot.efi are untouched; launchd loads the extra plist +# from /System/Library/LaunchDaemons alongside its signed cache (verified on +# Tahoe 26.6.2). Same idea as AutoNBI/Imagr NetBoot images. +# Output: raw disk image (HFS+ volume with a partition table) that OpenCore boots. +{ pkgs, lib, ... }: +{ name ? "macos", recovery }: +pkgs.runCommand "${name}-pe.img" { + nativeBuildInputs = with pkgs; [ dmg2img libguestfs-with-appliance ]; +} '' + echo "=== vmix: building the recovery PE from BaseSystem.dmg ===" + dmg2img -s ${recovery} $out + chmod +w $out + guestfish -a $out <= 4); with QEMU's single SMBIOS + # module macOS shows "Memory Modules Misconfigured" at every login. Describe + # the VM's RAM as four DDR4 modules instead. + if a.model.startswith('MacPro7'): + size = max(1024, a.memory_mb // 4) + cfg['PlatformInfo']['CustomMemory'] = True + cfg['PlatformInfo']['Memory'] = { + 'DataWidth': 64, 'ErrorCorrection': 3, 'FormFactor': 9, 'MaxCapacity': 1536 * 1024 * 1024 * 1024, + 'TotalWidth': 64, 'Type': 26, 'TypeDetail': 128, + 'Devices': [{ + 'AssetTag': '', 'BankLocator': f'BANK {i}', 'DeviceLocator': f'DIMM{i + 1}', + 'Manufacturer': 'Apple', 'PartNumber': f'VMIX{size}', 'SerialNumber': f'VMIX{i:04d}', + 'Size': size, 'Speed': 2666, + } for i in range(4)], + } cfg['Misc']['Security']['SecureBootModel'] = 'Disabled' cfg['Misc']['Security']['AllowSetDefault'] = True cfg['Misc']['Debug']['Target'] = 0 diff --git a/lib/images/macos/helpers/qemu.nix b/lib/images/macos/helpers/qemu.nix index c8e8474..86a48d3 100644 --- a/lib/images/macos/helpers/qemu.nix +++ b/lib/images/macos/helpers/qemu.nix @@ -30,6 +30,9 @@ rec { sataDrive = { id, port, file, format ? "qcow2", extra ? "" }: "-drive id=${id},if=none,format=${format},file=${file}${extra} -device ide-hd,bus=sata.${toString port},drive=${id}"; + # XNU logs to COM1 with boot-args serial=3; the build drivers read this file + serialArgs = file: "-serial file:${file}"; + firmwareArgs = varsFile: "-drive if=pflash,format=raw,readonly=on,file=${pkgs.OVMF.fd}/FV/OVMF_CODE.fd -drive if=pflash,format=raw,file=${varsFile}"; } diff --git a/lib/images/macos/helpers/vm-driver.py b/lib/images/macos/helpers/vm-driver.py index e4d038c..f27ba33 100644 --- a/lib/images/macos/helpers/vm-driver.py +++ b/lib/images/macos/helpers/vm-driver.py @@ -1,21 +1,27 @@ #!/usr/bin/env python3 -"""vmix macOS VM driver. +"""vmix macOS VM driver: runs QEMU and decides when a build boot is finished. -Launches QEMU with a QMP socket and either +Modes + pe the recovery PE runs /Volumes/VMIX/run.sh and powers off. Success is + QEMU exiting on its own; the caller checks vmix-run.status. + install the PE starts the macOS installer, which reboots through its phases + into the installed system. Finished when that system reaches the + (bright) loginwindow / Setup Assistant — the driver powers it down — + or halts on its own. + boot boot an installed image and wait for it to halt or reach the loginwindow. - --mode install drives macOS Recovery to a Terminal with keystrokes (screen - settle detection + OCR of the menu bar), types the bootstrap - command and waits for the VM to power itself off - --mode boot waits for the VM to power itself off (customize steps) - -Everything after `--` is the QEMU command line. Screenshots and a log are -written to --debug-dir (default /tmp/vmix-macos/) for troubleshooting. +Observation is passive: the serial console (boot-args serial=3: the PE's +"VMIX-*" markers, kernel boots, panics) and screenshots over QMP (mean +brightness + a coarse change fingerprint). No OCR, no keystrokes. A boot hang +(dark, frozen screen, disk and serial idle) is retried with a system_reset. +Screenshots, the driver log and the serial log are kept in --debug-dir. """ import argparse import hashlib import io import json import os +import shutil import socket import subprocess import sys @@ -23,60 +29,66 @@ import time try: from PIL import Image -except ImportError: # pragma: no cover +except ImportError: # screenshots then only serve as debug files Image = None -try: - import pytesseract -except ImportError: # pragma: no cover - pytesseract = None - -# QEMU qcodes for characters that are not plain alphanumerics -PLAIN = {' ': 'spc', '/': 'slash', '-': 'minus', '.': 'dot', ';': 'semicolon', ',': 'comma', - '=': 'equal', "'": 'apostrophe', '`': 'grave_accent', '[': 'bracket_left', - ']': 'bracket_right', '\\': 'backslash', '\n': 'ret', '\t': 'tab'} -SHIFTED = {'!': '1', '@': '2', '#': '3', '$': '4', '%': '5', '^': '6', '&': '7', '*': '8', - '(': '9', ')': '0', '_': 'minus', '+': 'equal', '{': 'bracket_left', - '}': 'bracket_right', '|': 'backslash', ':': 'semicolon', '"': 'apostrophe', - '<': 'comma', '>': 'dot', '?': 'slash', '~': 'grave_accent'} +PANIC_MARKS = ('panic(cpu', 'Kernel Extensions in backtrace', 'Debugger called: ', 'Nested panic detected', 'panic string:') +REBOOT_MARK = 'MACH Reboot' class Log: def __init__(self, path): - self.f = open(path, 'a') + self.f = open(path, 'a') if path else None self.t0 = time.time() def __call__(self, msg): line = f'[{time.time() - self.t0:7.1f}s] {msg}' print(f'vmix driver: {line}', flush=True) - self.f.write(line + '\n') - self.f.flush() + if self.f: + self.f.write(line + '\n') + self.f.flush() class QMP: def __init__(self, path): - self.sock = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM) - self.sock.connect(path) - self.f = self.sock.makefile('rwb', buffering=0) - self._read() - self.cmd('qmp_capabilities') + self.path = path + self.s = None + self.buf = b'' + + def connect(self, timeout=90): + t0 = time.time() + while True: + try: + s = socket.socket(socket.AF_UNIX) + s.settimeout(60) + s.connect(self.path) + self.s = s + self.buf = b'' + self._read() # greeting + self.cmd('qmp_capabilities') + return + except (OSError, ValueError): + if time.time() - t0 > timeout: + raise + time.sleep(1) def _read(self): - while True: - line = self.f.readline() - if not line: - raise EOFError('QMP connection closed') - msg = json.loads(line) - if 'event' in msg: - continue - return msg + while b'\n' not in self.buf: + d = self.s.recv(65536) + if not d: + raise OSError('QMP socket closed') + self.buf += d + line, self.buf = self.buf.split(b'\n', 1) + return json.loads(line) def cmd(self, name, **args): - self.f.write((json.dumps({'execute': name, 'arguments': args}) + '\n').encode()) - r = self._read() - if 'error' in r: - raise RuntimeError(f'QMP {name}: {r["error"]}') - return r.get('return') + self.s.sendall(json.dumps({'execute': name, 'arguments': args}).encode() + b'\n') + while True: + r = self._read() + if 'return' in r: + return r['return'] + if 'error' in r: + raise RuntimeError(r['error']) def screendump(self, path): self.cmd('screendump', filename=path) @@ -87,182 +99,117 @@ class QMP: def system_powerdown(self): self.cmd('system_powerdown') - _jig = 0 - - def jiggle(self): - # tiny absolute (usb-tablet) pointer move to keep the display awake: a real - # HID event, but < 2 screen px so it does not change the settle fingerprint - self._jig = 16060 if self._jig < 16030 else 16000 - try: - self.cmd('input-send-event', events=[ - {'type': 'abs', 'data': {'axis': 'x', 'value': self._jig}}, - {'type': 'abs', 'data': {'axis': 'y', 'value': 16000}}]) - except Exception: # noqa: BLE001 - self.send_key('shift') - - def send_key(self, *keys, hold=80): - self.cmd('send-key', keys=[{'type': 'qcode', 'data': k} for k in keys], **{'hold-time': hold}) - time.sleep(0.15) - - def type_text(self, text): - for ch in text: - if ch.isascii() and ch.isalnum(): - if ch.isupper(): - self.send_key('shift', ch.lower()) - else: - self.send_key(ch) - elif ch in PLAIN: - self.send_key(PLAIN[ch]) - elif ch in SHIFTED: - self.send_key('shift', SHIFTED[ch]) - else: - raise ValueError(f'cannot type {ch!r}') - class Screen: - """Screenshot helper: settle detection via hashing, OCR of regions.""" + """Screenshots over QMP with a coarse change fingerprint (cursor-insensitive).""" def __init__(self, qmp, debug_dir, log): self.qmp = qmp - self.debug_dir = debug_dir + self.dir = debug_dir self.log = log - import tempfile - fd, self.tmp = tempfile.mkstemp(prefix='.shot-', suffix='.ppm', dir=debug_dir) - os.close(fd) - os.chmod(self.tmp, 0o666) - self.n = 0 - self.last_hash = None - self.stable_since = time.time() + self.tmp = os.path.join(debug_dir, f'.grab-{os.getpid()}.ppm') self.img = None + self.last_fp = None + self.stable_since = time.time() + self.n = 0 def grab(self): self.qmp.screendump(self.tmp) with open(self.tmp, 'rb') as f: data = f.read() - self.img = Image.open(io.BytesIO(data)) if Image else None - # fingerprint from a coarse, quantized grayscale thumbnail so the moving - # mouse cursor (keepalive jiggle) does not count as a screen change - if self.img is not None: - px = self.img.convert('L').resize((48, 36)) - fp = bytes(b & 0xF0 for b in px.getdata()) - h = hashlib.sha256(fp).hexdigest() + if Image is None: + fp = hashlib.sha256(data).hexdigest() else: - h = hashlib.sha256(data).hexdigest() - if h != self.last_hash: - self.last_hash = h + self.img = Image.open(io.BytesIO(data)) + small = self.img.convert('L').resize((48, 36)) + fp = hashlib.sha256(bytes(b & 0xF0 for b in small.tobytes())).hexdigest() + if fp != self.last_fp: + self.last_fp = fp self.stable_since = time.time() return self.img def stable_for(self): return time.time() - self.stable_since + def mean(self): + if self.img is None: + return 0 + g = self.img.convert('L').resize((64, 48)) + px = g.tobytes() + return sum(px) / len(px) + + def is_blank(self): + return self.img is not None and self.mean() < 3 + def save(self, tag): self.n += 1 - path = os.path.join(self.debug_dir, f'{self.n:03d}-{tag}.png') + path = os.path.join(self.dir, f'{self.n:03d}-{tag}.png') try: if self.img is not None: self.img.save(path) else: - os.link(self.tmp, path.replace('.png', '.ppm')) + shutil.copy(self.tmp, path.replace('.png', '.ppm')) except Exception as e: # noqa: BLE001 self.log(f'could not save screenshot: {e}') return path - def ocr(self, region=None, scale=3, psm=6): - if self.img is None or pytesseract is None: - return '' - img = self.img - if region: - img = img.crop(region) - img = img.convert('L').resize((img.width * scale, img.height * scale), Image.LANCZOS) - try: - return pytesseract.image_to_string(img, config=f'--psm {psm}').lower() - except Exception as e: # noqa: BLE001 - self.log(f'ocr failed: {e}') - return '' - def mean(self): - if self.img is None: - return 128 - px = self.img.convert('L').resize((32, 24)) - d = list(px.getdata()) - return sum(d) / len(d) +class Serial: + """Tail the serial console file QEMU writes (-serial file:...).""" - def is_blank(self): - # black/uniform screen (firmware, boot): nothing to act on - if self.img is None: - return False - lo, hi = self.img.convert('L').resize((64, 48)).getextrema() - return hi - lo < 24 + def __init__(self, path): + self.path = path + self.pos = 0 + self.last_activity = time.time() + self.boots = 0 + self.reboot_at = None - def menubar_text(self): - w = self.img.width if self.img else 1024 - return self.ocr((0, 0, w, 40), scale=4, psm=7) + def poll(self): + if not self.path or not os.path.exists(self.path): + return [] + with open(self.path, 'rb') as f: + f.seek(self.pos) + data = f.read() + self.pos = f.tell() + if not data: + return [] + self.last_activity = time.time() + lines = data.decode('utf-8', 'replace').replace('\r', '').split('\n') + for l in lines: + if l.startswith('Darwin Kernel Version'): + self.boots += 1 + self.reboot_at = None + elif REBOOT_MARK in l: + self.reboot_at = time.time() + return lines + + def idle_for(self): + return time.time() - self.last_activity def prepare_debug_dir(path): - # nix builds run as different nixbld users: keep the shared dirs world-writable + os.makedirs(path, exist_ok=True) try: - for d in (os.path.dirname(path), path): - os.makedirs(d, exist_ok=True) - try: - os.chmod(d, 0o1777 if d != path else 0o777) - except OSError: - pass - probe = os.path.join(path, '.probe') - open(probe, 'w').close() - os.unlink(probe) - # a rebuild reuses this dir but runs as a different nixbld user; drop stale - # files so screendumps/PNGs are not blocked by another owner's 0644 files - import glob - for f in glob.glob(os.path.join(path, '*')) + glob.glob(os.path.join(path, '.current*')): - try: - os.unlink(f) - except OSError: - pass - return path + os.chmod(path, 0o777) except OSError: - import tempfile - alt = tempfile.mkdtemp(prefix='vmix-macos-') - print(f'vmix driver: {path} not writable, using {alt}', flush=True) - return alt + pass + for f in os.listdir(path): + if f.endswith(('.png', '.ppm', '.log')) or f.startswith('.grab-') or f == 'qmp.sock': + try: + os.remove(os.path.join(path, f)) + except OSError: + pass def launch(qemu_args, qmp_sock, log): if os.path.exists(qmp_sock): - os.unlink(qmp_sock) - args = list(qemu_args) + ['-qmp', f'unix:{qmp_sock},server,nowait'] - log('launching: ' + ' '.join(args)) - proc = subprocess.Popen(args) - deadline = time.time() + 60 - while not os.path.exists(qmp_sock): - if proc.poll() is not None: - return proc, None - if time.time() > deadline: - proc.kill() - raise RuntimeError('QEMU did not create the QMP socket') - time.sleep(0.2) - time.sleep(0.5) - return proc, QMP(qmp_sock) - - -def open_terminal(qmp, log): - # Ctrl-F2 focuses the menu bar; typing jumps to the menu whose title starts - # with that letter (Utilities), Down opens it, "t" jumps to Terminal. - log('opening Terminal via menu bar (ctrl-f2, u, down, t, ret)') - qmp.send_key('ctrl', 'f2') - time.sleep(1.0) - qmp.send_key('u') - time.sleep(0.7) - qmp.send_key('down') - time.sleep(0.7) - qmp.send_key('t') - time.sleep(0.7) - qmp.send_key('ret') + os.remove(qmp_sock) + cmd = list(qemu_args) + ['-qmp', f'unix:{qmp_sock},server,nowait'] + log('launching: ' + ' '.join(cmd)) + return subprocess.Popen(cmd) def disk_idle(args): - """True if the system disk has had no writes recently (guest not doing I/O).""" if not args.progress_file: return True try: @@ -271,289 +218,150 @@ def disk_idle(args): return True -def run_install(args, proc, qmp, log): - """Drive the install VM to completion. - - OpenCore shows a boot picker on every (re)boot and does not always auto-boot, - so on any settled picker we press Return to boot the highlighted macOS entry - (aux entries are hidden; during the install phases startosinstall blesses the - right default). That runs on EVERY iteration, because the install reboots - several times after we hand off to startosinstall. Before we have typed the - bootstrap command we also drive Recovery: language/welcome -> Return, the - Recovery window -> open Terminal, Terminal -> type the command. - """ - RECOVERY_BODY = ('reinstall', 'disk utility', 'restore from', 'recovery assistant', - 'macos utilities') - PICKER_BODY = ('base system', 'macos installer', 'rel-1', 'rel-0') # OpenCore picker - LANG_BODY = ('language', 'select your', 'main language', 'country or region', - 'welcome', 'get started', 'choose your') - screen = Screen(qmp, args.debug_dir, log) +def drive(args, proc, qmp, screen, serial, log): start = time.time() - typed_at = None - terminal_attempts = 0 last_periodic = 0 - last_progress = start - blind_done = False resets = 0 + panics = 0 + started = args.mode == 'boot' # pe/install: wait for the PE marker first blank_since = None login_since = None - recovery_start = None - last_term_action = 0 while True: rc = proc.poll() if rc is not None: + log(f'QEMU exited with {rc}') return rc now = time.time() if now - start > args.timeout: try: - screen.grab(); screen.save('timeout') + screen.grab() + screen.save('timeout') except Exception: # noqa: BLE001 pass log('timeout reached, killing QEMU') proc.kill() return 124 time.sleep(args.interval) - try: - screen.grab() - except Exception as e: # noqa: BLE001 - log(f'screendump failed ({e}), assuming QEMU is exiting') - time.sleep(2) - continue - if now - last_periodic > args.periodic: - last_periodic = now - screen.save('periodic') - # keep the recovery display awake until the command is typed (mouse jiggle) - if typed_at is None and now - last_term_action > 8: - qmp.jiggle() - if now - start < args.min_boot or screen.stable_for() < args.settle: - continue - if screen.is_blank(): - last_progress = now - if blank_since is None: - blank_since = now - if typed_at is None: - # recovery display asleep — jiggle the mouse to wake it, wait for UI - qmp.jiggle() - continue - # macOS `shutdown -h now` halts the guest to a black screen without an - # ACPI power-off, so QEMU never exits. Once we have handed off (command - # typed), a long pure-black screen means the agent finished and halted. - elif typed_at is not None and now - blank_since > args.halt_timeout and disk_idle(args): - screen.save('halt') - log(f'guest halted (black {now - blank_since:.0f}s, disk idle); killing QEMU, readback will validate') + + panic = False + for line in serial.poll(): + if 'VMIX' in line: + log('serial: ' + line.strip()[:220]) + if 'VMIX-PE: running run.sh' in line and not started: + started = True + log('PE started run.sh') + if 'VMIX-PE: no VMIX volume' in line and args.mode != 'boot': + log('PE did not find the VMIX volume') + proc.kill() + return 3 + if line.startswith('Darwin Kernel Version'): + log(f'guest kernel boot #{serial.boots}') + if any(m in line for m in PANIC_MARKS): + panic = True + log('serial: ' + line.strip()[:220]) + if panic: + panics += 1 + try: + screen.grab() + screen.save('panic') + except Exception: # noqa: BLE001 + pass + if args.mode == 'pe' or panics > args.max_resets: + log(f'kernel panic #{panics}, giving up') proc.kill() - try: - proc.wait(timeout=10) - except Exception: # noqa: BLE001 - pass - return 0 + return 3 + log(f'kernel panic #{panics}, system_reset') + qmp.system_reset() + screen.stable_since = time.time() continue - blank_since = None - top = screen.menubar_text() - body = screen.ocr() - log(f'settled: menubar={top.strip()!r} body~={" ".join(body.split())[:80]!r}') - - # Boot-hang watchdog: a dark screen (Apple logo / black) frozen for a long - # time with no menu bar is a stuck (re)boot — kick it with a system reset. - # Never fires on the bright, static Terminal of the prepare phase. - if 'terminal' not in top and 'utilities' not in top and screen.mean() < 40 \ - and screen.stable_for() > args.stall_reset and disk_idle(args) and resets < args.max_resets: + # The guest asked for a reboot but no kernel came back: macOS' restart + # path panics in QEMU (AppleSMC watchdog keys, see README); reset now + # instead of waiting for the frozen-screen watchdog. + if serial.reboot_at and now - serial.reboot_at > args.reboot_timeout and args.mode != 'pe': resets += 1 - screen.save('stall-reset') - log(f'boot hung ({screen.stable_for():.0f}s frozen, dark, disk idle), system_reset #{resets}') try: - qmp.system_reset() - except Exception as e: # noqa: BLE001 - log(f'system_reset failed: {e}') - screen.stable_since = time.time() - last_progress = now - continue - - # OpenCore boot picker — always handle it (the install reboots many times) - if 'terminal' not in top and 'utilities' not in top and any(k in body for k in PICKER_BODY): - screen.save('picker') - log('OpenCore boot picker, pressing Return to boot the default macOS entry') - qmp.send_key('ret') - last_progress = now - screen.stable_since = time.time() - continue - - # After the install, the loginwindow/desktop is a BRIGHT gray screen, unlike - # the dark install/boot screens (Apple logo). The vmix agent powers the VM - # off if it runs (cron/daemon); if BTM blocks it, we power down here so the - # build still completes with a bootable, installed image. Brightness is a - # far more reliable signal than OCR of the faint "password" text. - bright = screen.mean() > 80 - loginish = (typed_at is not None and bright and 'terminal' not in top - and 'utilities' not in top and not any(k in body for k in PICKER_BODY)) - if loginish: - if login_since is None: - login_since = now - log('bright post-install screen (loginwindow/desktop) — OS installed; grace before powerdown') - elif now - login_since > args.login_grace: - screen.save('loginwindow') - log(f'loginwindow persisted {now - login_since:.0f}s, powering down (install complete)') - try: - qmp.system_powerdown() - except Exception as e: # noqa: BLE001 - log(f'powerdown failed: {e}') - for _ in range(90): - if proc.poll() is not None: - return 0 - time.sleep(1) - proc.kill() - return 0 - continue - else: - login_since = None - - # once the bootstrap command is typed, only the picker (above) and an - # unexpected return to Recovery matter (post-prepare reboot landed on the - # recovery instead of the installer — restart the install then). - if typed_at is not None: - if ('utilities' in top or 'recovery' in top): - if recovery_start is None: - recovery_start = now - if now - typed_at > 120 and now - recovery_start > 45: - log('unexpectedly back at Recovery after install started — restarting install') - typed_at = None - terminal_attempts = 0 - recovery_start = None - # fall through to the recovery/terminal handling below - else: - continue - else: - recovery_start = None - continue - - if 'terminal' in top: - screen.save('terminal') - log(f'typing bootstrap command: {args.command!r}') - qmp.type_text(args.command + '\n') - typed_at = time.time() - continue - - acted = False - if 'utilities' in top or 'recovery' in top or any(k in body for k in RECOVERY_BODY): - screen.save('recovery') - terminal_attempts += 1 - log(f'recovery window (attempt {terminal_attempts}), opening Terminal') - last_term_action = now - open_terminal(qmp, log) - if terminal_attempts >= 3: - time.sleep(8) - log('typing bootstrap command (Terminal assumed open)') - qmp.type_text(args.command + '\n') - typed_at = time.time() - continue - acted = True - elif any(k in body for k in LANG_BODY): - screen.save('language') - log('language/welcome screen, pressing Return') - qmp.send_key('ret') - acted = True - - if acted: - last_progress = now - screen.stable_since = time.time() - elif now - last_progress > args.settle * args.max_actions and not blind_done: - blind_done = True - screen.save('blind') - log('nothing recognised for a long time, blind sequence') - qmp.send_key('ret') - time.sleep(20) - open_terminal(qmp, log) - time.sleep(10) - qmp.type_text(args.command + '\n') - typed_at = time.time() - - -def run_boot(args, proc, qmp, log): - """Wait for the VM to power itself off (customize/generalize/first-boot), - handling the OpenCore picker and kicking a hung boot with a system reset.""" - PICKER_BODY = ('base system', 'macos installer', 'macintosh hd', 'rel-1', 'rel-0') - screen = Screen(qmp, args.debug_dir, log) - start = time.time() - last_periodic = 0 - resets = 0 - blank_since = None - login_since = None - while True: - rc = proc.poll() - if rc is not None: - return rc - if time.time() - start > args.timeout: - try: - screen.grab(); screen.save('timeout') + screen.grab() + screen.save('reboot-dead') except Exception: # noqa: BLE001 pass - log('timeout reached, killing QEMU') + log(f'guest requested a reboot {now - serial.reboot_at:.0f}s ago and died, system_reset #{resets}') + serial.reboot_at = None + if resets > args.max_resets: + proc.kill() + return 3 + qmp.system_reset() + screen.stable_since = time.time() + continue + + if not started and now - start > args.start_timeout: + try: + screen.grab() + screen.save('no-start') + except Exception: # noqa: BLE001 + pass + log(f'PE did not start run.sh within {args.start_timeout:.0f}s') proc.kill() - return 124 - time.sleep(args.interval) + return 3 + try: screen.grab() except Exception as e: # noqa: BLE001 log(f'screendump failed ({e})') time.sleep(2) continue - now = time.time() if now - last_periodic > args.periodic: last_periodic = now screen.save('periodic') - if now - start < args.min_boot or screen.stable_for() < args.settle: + + if args.mode == 'pe': + continue # the PE powers off by itself; nothing to decide + # install: the PE phase (kernel boot #1) is protected by the guest's own + # retries; the checks below apply once the installer has rebooted. + in_os = args.mode == 'boot' or serial.boots >= 2 + if not in_os or screen.stable_for() < args.settle: continue + idle = disk_idle(args) and serial.idle_for() > args.disk_idle + if screen.is_blank(): - if blank_since is None: - blank_since = now - elif now - blank_since > args.halt_timeout and disk_idle(args): + blank_since = blank_since or now + # macOS `shutdown -h` halts to a black screen without an ACPI power-off + if now - blank_since > args.halt_timeout and idle: screen.save('halt') - log(f'guest halted (black {now - blank_since:.0f}s, disk idle); killing QEMU') + log(f'guest halted (black {now - blank_since:.0f}s, idle); killing QEMU') proc.kill() - try: - proc.wait(timeout=10) - except Exception: # noqa: BLE001 - pass return 0 continue blank_since = None - top = screen.menubar_text() - body = screen.ocr() - if 'terminal' not in top and 'utilities' not in top and any(k in body for k in PICKER_BODY): - screen.save('picker') - log('OpenCore boot picker, pressing Return') - qmp.send_key('ret') - screen.stable_since = time.time() - login_since = None - continue - # bright post-boot screen (loginwindow/desktop) => booted; power down if the - # agent did not (so customize/generalize completes even if BTM blocks it) - if screen.mean() > 80 and 'terminal' not in top and 'utilities' not in top: + + if screen.mean() > args.bright: + # loginwindow / Setup Assistant: the OS is installed and booted if login_since is None: login_since = now - log('bright screen (loginwindow/desktop) after boot; grace before powerdown') + log(f'bright screen (mean {screen.mean():.0f}): loginwindow/desktop, grace {args.login_grace:.0f}s') elif now - login_since > args.login_grace: screen.save('loginwindow') - log(f'loginwindow persisted {now - login_since:.0f}s, powering down') + log('powering down (boot complete)') try: qmp.system_powerdown() except Exception as e: # noqa: BLE001 log(f'powerdown failed: {e}') - for _ in range(90): + for _ in range(120): if proc.poll() is not None: + log('QEMU exited after powerdown') return 0 time.sleep(1) + log('guest ignored powerdown, killing QEMU') proc.kill() return 0 continue - else: - login_since = None - if 'terminal' not in top and 'utilities' not in top and screen.mean() < 40 \ - and screen.stable_for() > args.stall_reset and disk_idle(args) and resets < args.max_resets: + login_since = None + + # dark, frozen, nothing happening: a boot hang (seen at the Apple logo) + if screen.stable_for() > args.stall_reset and idle and resets < args.max_resets: resets += 1 screen.save('stall-reset') - log(f'boot hung ({screen.stable_for():.0f}s frozen, dark, disk idle), system_reset #{resets}') + log(f'boot hung ({screen.stable_for():.0f}s frozen, dark, idle), system_reset #{resets}') try: qmp.system_reset() except Exception as e: # noqa: BLE001 @@ -562,54 +370,60 @@ def run_boot(args, proc, qmp, log): def main(): - p = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter) - p.add_argument('--mode', choices=['install', 'boot'], required=True) + p = argparse.ArgumentParser() + p.add_argument('--mode', choices=['pe', 'install', 'boot'], required=True) p.add_argument('--name', default='macos') p.add_argument('--debug-dir', default=None) + p.add_argument('--serial-log', default=None, help='file QEMU writes the serial console to') p.add_argument('--timeout', type=int, default=4 * 3600, help='seconds before QEMU is killed') + p.add_argument('--start-timeout', type=float, default=600.0, help='seconds for the PE to start run.sh') p.add_argument('--interval', type=float, default=5.0, help='seconds between screenshots') p.add_argument('--periodic', type=float, default=120.0, help='seconds between saved debug screenshots') p.add_argument('--settle', type=float, default=12.0, help='seconds a screen must be unchanged to act on it') - p.add_argument('--min-boot', type=float, default=45.0, help='seconds before the first action') - p.add_argument('--max-actions', type=int, default=8) - p.add_argument('--stall-reset', type=float, default=360.0, help='reset the VM if a non-Terminal screen is frozen this long (boot hang)') + p.add_argument('--stall-reset', type=float, default=360.0, help='reset the VM if a dark screen is frozen this long while disk and serial are idle') p.add_argument('--max-resets', type=int, default=6) - p.add_argument('--halt-timeout', type=float, default=150.0, help='after the bootstrap, a pure-black screen this long means the guest halted (macOS shutdown does not ACPI-power-off QEMU)') - p.add_argument('--progress-file', default=None, help='a file (the system disk) whose mtime shows guest activity; resets/halt only fire when it is also idle, so a slow-but-working boot is never interrupted') - p.add_argument('--disk-idle', type=float, default=90.0, help='seconds of no writes to --progress-file that count as idle') - p.add_argument('--login-grace', type=float, default=240.0, help='seconds to wait at the loginwindow for the agent to power off before the driver powers down itself') - p.add_argument('--command', default='diskutil mount VMIX;sh /Volumes/VMIX/run.sh') + p.add_argument('--reboot-timeout', type=float, default=60.0, help='seconds after a guest reboot request without a new kernel boot before the VM is reset') + p.add_argument('--halt-timeout', type=float, default=150.0, help='a pure-black, idle screen this long means the guest halted') + p.add_argument('--progress-file', default=None, help='the system disk; its mtime shows guest disk activity') + p.add_argument('--disk-idle', type=float, default=90.0, help='seconds without disk/serial activity that count as idle') + p.add_argument('--bright', type=float, default=80.0, help='mean brightness above which a screen is the loginwindow/desktop') + p.add_argument('--login-grace', type=float, default=180.0, help='seconds a bright screen must persist before powering down') p.add_argument('qemu', nargs=argparse.REMAINDER) args = p.parse_args() - qemu_args = args.qemu[1:] if args.qemu and args.qemu[0] == '--' else args.qemu + qemu_args = [a for a in args.qemu if a != '--'] if not qemu_args: p.error('QEMU command line required after --') - args.debug_dir = prepare_debug_dir(args.debug_dir or f'/tmp/vmix-macos/{args.name}') - log = Log(os.path.join(args.debug_dir, 'driver.log')) - log(f'mode={args.mode} debug-dir={args.debug_dir} ocr={"yes" if pytesseract else "no"}') - qmp_sock = os.path.join(args.debug_dir, 'qmp.sock') - - proc, qmp = launch(qemu_args, qmp_sock, log) - if qmp is None and '-display' in qemu_args and 'sdl' in qemu_args: - # SDL could not open a window: retry headless - log(f'QEMU exited early ({proc.returncode}) with SDL, retrying headless') - i = qemu_args.index('-display') - qemu_args = qemu_args[:i] + ['-display', 'none'] + qemu_args[i + 2:] - proc, qmp = launch(qemu_args, qmp_sock, log) - if qmp is None: - log(f'QEMU exited immediately with {proc.returncode}') - return proc.returncode or 1 + debug_dir = args.debug_dir or f'/tmp/vmix-macos/{args.name}' + prepare_debug_dir(debug_dir) + log = Log(os.path.join(debug_dir, 'driver.log')) + log(f'mode={args.mode} debug-dir={debug_dir} serial={args.serial_log}') + qmp_sock = os.path.join(debug_dir, 'qmp.sock') + proc = launch(qemu_args, qmp_sock, log) + qmp = QMP(qmp_sock) try: - if args.mode == 'install': - rc = run_install(args, proc, qmp, log) - else: - rc = run_boot(args, proc, qmp, log) + qmp.connect() + except Exception as e: # noqa: BLE001 + log(f'QMP connect failed: {e}') + proc.kill() + return 2 + screen = Screen(qmp, debug_dir, log) + serial = Serial(args.serial_log) + try: + rc = drive(args, proc, qmp, screen, serial, log) finally: - if proc.poll() is None: - proc.kill() - log(f'QEMU exited with {rc}') + if args.serial_log and os.path.exists(args.serial_log): + try: + shutil.copy(args.serial_log, os.path.join(debug_dir, 'serial.log')) + except OSError: + pass + try: + if proc.poll() is None: + proc.kill() + except Exception: # noqa: BLE001 + pass + log(f'done rc={rc}') return rc diff --git a/lib/images/macos/helpers/vmix-readback.nix b/lib/images/macos/helpers/vmix-readback.nix index 1121c6c..23c6a91 100644 --- a/lib/images/macos/helpers/vmix-readback.nix +++ b/lib/images/macos/helpers/vmix-readback.nix @@ -1,14 +1,14 @@ -# Shell snippet: read the vmix agent's result off the VMIX HFS+ volume of a raw -# disk image (${image}). Prints the guest logs and sets STATUS to the contents -# of vmix-run.status ("0" on success). Uses libguestfs (mtools is FAT-only). The -# agent unmounts VMIX cleanly before shutdown, so a read-only mount is safe. +# Shell snippet: read the PE's result off the VMIX HFS+ volume of a raw disk +# image (${image}). Prints the guest logs and sets STATUS to the contents of +# vmix-run.status ("0" on success, empty if run.sh never returned, e.g. the +# installer rebooted). The PE unmounts VMIX before powering off. { ... }: image: '' echo "=== vmix: reading result from ${image} ===" - for f in install.log system-install.log vmix-run.log vmix-agent.log; do + for f in vmix-run.log system-install.log; do C=$(guestfish --ro -a ${image} -m /dev/sda1 cat /$f 2>/dev/null || true) - [ -n "$C" ] && { echo "--- $f ---"; printf '%s\n' "$C"; } + [ -n "$C" ] && { echo "--- $f ---"; printf '%s\n' "$C" | tail -400; } done STATUS=$(guestfish --ro -a ${image} -m /dev/sda1 cat /vmix-run.status 2>/dev/null | tr -d '[:space:]' || true) '' diff --git a/lib/images/macos/tahoe/images.nix b/lib/images/macos/tahoe/images.nix index a3e6868..e848fcd 100644 --- a/lib/images/macos/tahoe/images.nix +++ b/lib/images/macos/tahoe/images.nix @@ -1,11 +1,14 @@ # Pre-built macOS Tahoe (26) images -# Pipeline: makeImage (unattended install, vmix agent) → templates → generalize +# Pipeline: makeRecoveryPE (Recovery + vmix hook) → makeImage (unattended, offline +# install) → templates (applied offline from the PE) → generalize { pkgs, lib, system, macos, installer, recovery, ... }: with macos; rec { + pe = makeRecoveryPE { name = "macos-tahoe"; inherit recovery; }; + upstream = makeImage { name = "macos-tahoe"; - inherit installer recovery; + inherit installer pe; }; basic = customizeImageFold upstream templates.bundles.basic; diff --git a/lib/images/macos/templates/default.nix b/lib/images/macos/templates/default.nix index 1edb923..b800c8f 100644 --- a/lib/images/macos/templates/default.nix +++ b/lib/images/macos/templates/default.nix @@ -5,7 +5,7 @@ rec { essentials = { remoteAccess = import ./essentials/remote-access.nix { }; noUpdates = import ./essentials/no-updates.nix { }; - performance = import ./essentials/performance.nix { }; + performance = import ./essentials/performance.nix { inherit pkgs; }; }; bundles = { diff --git a/lib/images/macos/templates/essentials/no-updates.nix b/lib/images/macos/templates/essentials/no-updates.nix index 736f824..1e4008f 100644 --- a/lib/images/macos/templates/essentials/no-updates.nix +++ b/lib/images/macos/templates/essentials/no-updates.nix @@ -4,12 +4,10 @@ { name = "no-updates"; script = '' - softwareupdate --schedule off || true - defaults write /Library/Preferences/com.apple.SoftwareUpdate AutomaticCheckEnabled -bool false - defaults write /Library/Preferences/com.apple.SoftwareUpdate AutomaticDownload -bool false - defaults write /Library/Preferences/com.apple.SoftwareUpdate AutomaticallyInstallMacOSUpdates -bool false - defaults write /Library/Preferences/com.apple.SoftwareUpdate ConfigDataInstall -bool false - defaults write /Library/Preferences/com.apple.SoftwareUpdate CriticalUpdateInstall -bool false - defaults write /Library/Preferences/com.apple.commerce AutoUpdate -bool false + SU="$DATA/Library/Preferences/com.apple.SoftwareUpdate.plist" + for k in AutomaticCheckEnabled AutomaticDownload AutomaticallyInstallMacOSUpdates ConfigDataInstall CriticalUpdateInstall; do + pe_plist_set "$SU" "$k" bool false + done + pe_plist_set "$DATA/Library/Preferences/com.apple.commerce.plist" AutoUpdate bool false ''; } diff --git a/lib/images/macos/templates/essentials/performance.nix b/lib/images/macos/templates/essentials/performance.nix index f6d3a99..805f01a 100644 --- a/lib/images/macos/templates/essentials/performance.nix +++ b/lib/images/macos/templates/essentials/performance.nix @@ -1,11 +1,32 @@ -# Less background work in a VM: no Spotlight indexing, no Time Machine, no sleep -{ ... }: +# Less background work in a VM: no Spotlight indexing, no Time Machine, no +# sleep, no immediate screen lock. +{ pkgs, ... }: +let + power = pkgs.writeText "com.apple.PowerManagement.plist" '' + + + + + ActivePowerProfilesAC Power-1 + Custom ProfileAC Power + Display Sleep Timer0 + System Sleep Timer0 + Disk Sleep Timer0 + Wake On LAN0 + hibernatemode0 + + + + ''; +in { name = "performance"; + files = [ { source = power; name = "com.apple.PowerManagement.plist"; } ]; script = '' - mdutil -a -i off || true - tmutil disable || true - pmset -a sleep 0 displaysleep 0 disksleep 0 hibernatemode 0 womp 0 || true - defaults write /Library/Preferences/com.apple.loginwindow DisableScreenLockImmediate -bool true + touch "$DATA/.metadata_never_index" + pe_plist_set "$DATA/Library/Preferences/com.apple.TimeMachine.plist" AutoBackup bool false + pe_plist_set "$DATA/Library/Preferences/com.apple.loginwindow.plist" DisableScreenLockImmediate bool true + cp "$V/com.apple.PowerManagement.plist" "$DATA/Library/Preferences/com.apple.PowerManagement.plist" + chown 0:0 "$DATA/Library/Preferences/com.apple.PowerManagement.plist" ''; } diff --git a/lib/images/macos/templates/essentials/remote-access.nix b/lib/images/macos/templates/essentials/remote-access.nix index 51bb432..eb80941 100644 --- a/lib/images/macos/templates/essentials/remote-access.nix +++ b/lib/images/macos/templates/essentials/remote-access.nix @@ -1,11 +1,10 @@ # Enable SSH (Remote Login) and Screen Sharing (VNC on 5900 inside the guest) +# by clearing their launchd overrides on the image's Data volume. { ... }: { name = "remote-access"; script = '' - systemsetup -setremotelogin on >/dev/null 2>&1 || launchctl load -w /System/Library/LaunchDaemons/ssh.plist - launchctl load -w /System/Library/LaunchDaemons/com.apple.screensharing.plist - # allow all local users to screen share - defaults write /var/db/launchd.db/com.apple.launchd/overrides.plist com.apple.screensharing -dict Disabled -bool false 2>/dev/null || true + pe_service_disabled com.apple.openssh.sshd false + pe_service_disabled com.apple.screensharing false ''; } diff --git a/lib/images/macos/templates/generalize.nix b/lib/images/macos/templates/generalize.nix index ac59348..620aa6a 100644 --- a/lib/images/macos/templates/generalize.nix +++ b/lib/images/macos/templates/generalize.nix @@ -1,7 +1,8 @@ -# Generalize a macOS image: create the user, auto-login, hostname, timezone, -# suppress Setup Assistant prompts, then remove the vmix agent. Also gives the -# image a fresh SMBIOS identity (serial/MLB from macserial, MAC + UUID from -# `seed`) so every generalized VM looks like a distinct Mac to Apple ID/iMessage. +# Generalize a macOS image, offline from the PE: create the (admin) user on the +# image's Data volume with dscl, auto-login, suppress the first-login Setup +# Assistant, hostname, locale, timezone, use the whole disk, and give the image +# a fresh SMBIOS identity (serial/MLB from macserial, MAC + UUID from `seed`) so +# every generalized VM looks like a distinct Mac to Apple ID/iMessage. # Usage: (templates.generalize { username = "User"; password = ""; hostname = "MAC"; }) # delayOobeRun = true: no user, Setup Assistant runs on first real boot (like Windows OOBE) { pkgs, lib, ... }: @@ -34,7 +35,8 @@ let "DidSeeCloudSetup" "DidSeeSiriSetup" "DidSeePrivacy" "DidSeeTouchIDSetup" "DidSeeAppearanceSetup" "DidSeeScreenTime" "DidSeeAccessibility" "DidSeeTrueTonePrivacy" "DidSeeActivationLock" "DidSeeiCloudLoginForStorageServices" "DidSeeSyncSetup" "DidSeeSyncSetup2" "DidSeeAppleIDSyncSetup" - "DidSeeApplePaySetup" "DidSeeIntelligence" "DidSeeLockdownMode" "DidSeeAppStore" "SkipFirstLoginOptimization" + "DidSeeApplePaySetup" "DidSeeIntelligence" "DidSeeLockdownMode" "DidSeeAppStore" "DidSeeUpdateMacAutomatically" + "DidSeeSoftwareUpdate" "SkipFirstLoginOptimization" ]; in { @@ -44,60 +46,81 @@ in script = '' set -x ${lib.optionalString (bgColor != null) ''echo "vmix: bgColor is not supported on macOS, ignoring"''} + VER=$(pe_target_version); BUILD=$(pe_target_build) + echo "vmix: target macOS $VER ($BUILD)" + N="$DATA/private/var/db/dslocal/nodes/Default" + D() { dscl -f "$N" localhost "$@"; } ${lib.optionalString (!delayOobeRun) '' - # --- user account (admin) - if ! id "${username}" >/dev/null 2>&1; then - sysadminctl -addUser "${username}" -fullName ${lib.escapeShellArg fullName} \ - -password ${lib.escapeShellArg (if password == "" then tempPassword else password)} \ - -admin -home "/Users/${username}" || exit 1 - ${lib.optionalString (password == "") '' - dscl . -passwd "/Users/${username}" "${tempPassword}" "" || echo "vmix: WARNING: could not set an empty password, password is '${tempPassword}'" - ''} + # --- user account (admin), created directly in the local directory node + U="${username}"; HOME_DIR="$DATA/Users/$U" + if ! D -read "/Local/Default/Users/$U" >/dev/null 2>&1; then + UID_NEW=$(D -list /Local/Default/Users UniqueID | awk '$2 >= 501 && $2 < 1000 && $2 > m {m = $2} END {print (m ? m + 1 : 501)}') + D -create "/Local/Default/Users/$U" || pe_fail "dscl create user" + D -create "/Local/Default/Users/$U" UserShell /bin/zsh + D -create "/Local/Default/Users/$U" RealName ${lib.escapeShellArg fullName} + D -create "/Local/Default/Users/$U" UniqueID "$UID_NEW" + D -create "/Local/Default/Users/$U" PrimaryGroupID 20 + D -create "/Local/Default/Users/$U" NFSHomeDirectory "/Users/$U" + if ! D -passwd "/Local/Default/Users/$U" ${lib.escapeShellArg password}; then + echo "vmix: WARNING: could not set the requested password, using '${tempPassword}'" + D -passwd "/Local/Default/Users/$U" "${tempPassword}" || pe_fail "dscl passwd" + fi + for g in admin _appserverusr _appserveradm _lpadmin; do + D -append "/Local/Default/Groups/$g" GroupMembership "$U" 2>/dev/null || true + done + mkdir -p "$HOME_DIR" + T="$SYS/System/Library/User Template/Non_localized"; [ -d "$T" ] || T="/System/Library/User Template/Non_localized" + ditto "$T" "$HOME_DIR" 2>/dev/null || true + L="$SYS/System/Library/User Template/English.lproj"; [ -d "$L" ] && ditto "$L" "$HOME_DIR" 2>/dev/null || true + else + UID_NEW=$(D -read "/Local/Default/Users/$U" UniqueID | awk '{print $2}') fi ${lib.optionalString autoLogon '' - defaults write /Library/Preferences/com.apple.loginwindow autoLoginUser "${username}" - cp /Volumes/VMIX/kcpassword /etc/kcpassword - chmod 600 /etc/kcpassword - chown root:wheel /etc/kcpassword + pe_plist_set "$DATA/Library/Preferences/com.apple.loginwindow.plist" autoLoginUser string "$U" + cp "$V/kcpassword" "$DATA/private/etc/kcpassword" + chmod 600 "$DATA/private/etc/kcpassword"; chown 0:0 "$DATA/private/etc/kcpassword" ''} # --- no Setup Assistant / "What's new" prompts at first login - P="/Users/${username}/Library/Preferences/com.apple.SetupAssistant" - VER=$(sw_vers -productVersion) - BUILD=$(sw_vers -buildVersion) - for k in ${lib.concatStringsSep " " setupKeys}; do - defaults write "$P" "$k" -bool true - done - defaults write "$P" GestureMovieSeen none - defaults write "$P" LastSeenCloudProductVersion "$VER" - defaults write "$P" LastSeenBuddyBuildVersion "$BUILD" - defaults write "$P" LastSeenSiriProductVersion "$VER" - defaults write "$P" LastPreLoginTasksPerformedVersion "$VER" - defaults write "/Users/${username}/Library/Preferences/.GlobalPreferences" AppleLocale "${macLocale}" - chown -R "${username}" "/Users/${username}/Library/Preferences" + mkdir -p "$HOME_DIR/Library/Preferences" + P="$HOME_DIR/Library/Preferences/com.apple.SetupAssistant.plist" + for k in ${lib.concatStringsSep " " setupKeys}; do pe_plist_set "$P" "$k" bool true; done + pe_plist_set "$P" GestureMovieSeen string none + pe_plist_set "$P" LastSeenCloudProductVersion string "$VER" + pe_plist_set "$P" LastSeenBuddyBuildVersion string "$BUILD" + pe_plist_set "$P" LastSeenSiriProductVersion string "$VER" + pe_plist_set "$P" LastPreLoginTasksPerformedVersion string "$VER" + pe_plist_set "$P" LastPreLoginTasksPerformedBuild string "$BUILD" + pe_plist_set "$HOME_DIR/Library/Preferences/.GlobalPreferences.plist" AppleLocale string "${macLocale}" + chown -R "$UID_NEW:20" "$HOME_DIR" + touch "$DATA/private/var/db/.AppleSetupDone" + ''} + ${lib.optionalString delayOobeRun '' + rm -f "$DATA/private/var/db/.AppleSetupDone" ''} # --- machine identity - scutil --set ComputerName "${hostname}" - scutil --set HostName "${hostname}" - scutil --set LocalHostName "${hostname}" - defaults write /Library/Preferences/.GlobalPreferences AppleLocale "${macLocale}" - systemsetup -settimezone "${timezone}" >/dev/null 2>&1 || ln -sfn "/usr/share/zoneinfo/${timezone}" /etc/localtime + PF="$DATA/Library/Preferences/SystemConfiguration/preferences.plist" + mkdir -p "$(dirname "$PF")" + pe_plist_dict "$PF" System + pe_plist_dict "$PF" System.System + pe_plist_dict "$PF" System.Network + pe_plist_dict "$PF" System.Network.HostNames + pe_plist_set "$PF" System.System.ComputerName string "${hostname}" + pe_plist_set "$PF" System.System.HostName string "${hostname}" + pe_plist_set "$PF" System.Network.HostNames.LocalHostName string "${hostname}" + pe_plist_set "$DATA/Library/Preferences/.GlobalPreferences.plist" AppleLocale string "${macLocale}" + ln -sfn "/var/db/timezone/zoneinfo/${timezone}" "$DATA/private/etc/localtime" + pe_plist_set "$DATA/Library/Preferences/com.apple.timezone.auto.plist" Active bool false - # --- never sleep (VM) - pmset -a sleep 0 displaysleep 0 disksleep 0 hibernatemode 0 || true + # --- QEMU's USB keyboard (vendor 0x0627, product 0x0001) is unknown to macOS, + # which would open the Keyboard Setup Assistant at every login: declare it ANSI + KT="$DATA/Library/Preferences/com.apple.keyboardtype.plist" + pe_plist_dict "$KT" keyboardtype + pe_plist_set "$KT" keyboardtype.1-1575-0 integer 40 # --- use the whole (possibly grown) disk - STORE=$(diskutil info / | awk '/APFS Physical Store/ {print $NF}') + STORE=$(diskutil info "$SYS_ID" | sed -n 's/.*APFS Physical Store: *//p' | awk '{print $1}') [ -n "$STORE" ] && diskutil apfs resizeContainer "$STORE" 0 || true - - ${lib.optionalString delayOobeRun '' - # Setup Assistant will run on the next boot - rm -f /var/db/.AppleSetupDone - ''} - - # --- the agent's job is done: remove it (this is the last vmix step) - rm -f /Library/LaunchDaemons/ch.vmix.agent.plist - rm -rf /Library/vmix ''; } diff --git a/lib/images/macos/tools/soak.sh b/lib/images/macos/tools/soak.sh new file mode 100755 index 0000000..bdb1435 --- /dev/null +++ b/lib/images/macos/tools/soak.sh @@ -0,0 +1,28 @@ +#!/usr/bin/env bash +# Repeatability check for a macOS image build: build the same attribute N times +# (forcing a rebuild each time), keep every run's driver + serial logs, and print +# a table of outcome / duration / which recovery mechanisms fired. +# tools/soak.sh [runs] [outdir] +# e.g. tools/soak.sh /root/vmix.nix macos.images.tahoe.upstream 3 +set -u +FLAKE=${1:?flake dir}; ATTR=${2:?attribute}; RUNS=${3:-3}; OUT=${4:-/tmp/vmix-macos-soak} +NAME=$(nix eval --impure --raw --expr "(builtins.getFlake \"path:$FLAKE\").lib.x86_64-linux.$ATTR.name" | sed 's/-vmix\.qcow2$//') +DRV=$(nix eval --impure --raw --expr "(builtins.getFlake \"path:$FLAKE\").lib.x86_64-linux.$ATTR.drvPath") +mkdir -p "$OUT" +printf '%-4s %-8s %-9s %-6s %-7s %-7s %-6s %s\n' run result minutes boots resets panics tries note | tee "$OUT/summary.txt" +for i in $(seq 1 "$RUNS"); do + D="$OUT/run-$i"; rm -rf "$D"; mkdir -p "$D" + rm -rf "/tmp/vmix-macos/$NAME" + t0=$(date +%s) + if [ "$i" -eq 1 ]; then nix build --no-link -L "$DRV^*" > "$D/build.log" 2>&1; rc=$? + else nix build --no-link -L --rebuild "$DRV^*" > "$D/build.log" 2>&1; rc=$?; fi + t1=$(date +%s) + cp "/tmp/vmix-macos/$NAME"/driver.log "/tmp/vmix-macos/$NAME"/serial.log "$D/" 2>/dev/null + cp "/tmp/vmix-macos/$NAME"/*.png "$D/" 2>/dev/null + L="$D/driver.log" + boots=$(grep -c 'guest kernel boot' "$L" 2>/dev/null); resets=$(grep -c 'system_reset' "$L" 2>/dev/null) + panics=$(grep -c 'kernel panic' "$L" 2>/dev/null); tries=$(grep -c 'startosinstall try' "$L" 2>/dev/null) + note=$(grep -oE 'prepare too slow[^,]*|PE did not[^,]*|guest halted|powering down|timeout reached' "$L" 2>/dev/null | sort | uniq -c | tr '\n' ';' | tr -s ' ') + printf '%-4s %-8s %-9s %-6s %-7s %-7s %-6s %s\n' "$i" "$([ $rc -eq 0 ] && echo OK || echo FAIL)" "$(( (t1 - t0) / 60 ))" "$boots" "$resets" "$panics" "$tries" "$note" | tee -a "$OUT/summary.txt" +done +echo "logs: $OUT"