fix(update): stop a timed-out git from leaving .git/index.lock behind (#802)

* fix(update): stop a timed-out git from leaving .git/index.lock behind

subprocess.run's timeout SIGKILLs only the direct git child, so the lock
is left behind and git's helpers are orphaned. On a slow SD card the same
pull then times out on every retry and recreates the lock, so removing it
by hand does not help.

- run_git starts git in its own session, stops the group with SIGTERM
  before SIGKILL, and clears the lock if nothing owns it. Update Code's
  pull, checkout, reset and stash go through it, with a 600s pull timeout.
- Read-only calls (describe --dirty, status, the update-check fetch) set
  GIT_OPTIONAL_LOCKS=0 so a timed-out poll cannot take the lock.
- A timed-out pull returns a clear error; a rebase left by an interrupted
  update is aborted before pulling.
- The manual-fix hint says to stop the services and kill running git.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

* fix(update): address review of the index.lock fix

- The automatic update's status check now sets GIT_OPTIONAL_LOCKS=0
  whichever runner it is given, not only the default one.
- Update Code no longer runs `git rebase --abort` on any rebase dir: a
  rebase in progress (detached HEAD) holds the user's conflict work and
  blocks the update; an abandoned one is dropped with `rebase --quit`,
  as the automatic update does, and a failure to clear it stops the update.
- run_git waits out the lock-freshness window after stopping a timed-out
  git, so a lock created just before the timeout is not left behind.
- Mark the Popen/subprocess use with the repo's nosec comments.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

* chore(update): mark run_git's CompletedProcess as a result object, not a subprocess call

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>

web_interface/auto_update.py

@@ -302,10 +302,12 @@ def local_changes(project_dir, run=None, timeout=30):
     Returns the changed paths, or None when git could not tell. Raises what
     ``run`` raises (e.g. ``subprocess.TimeoutExpired``).
     """
-    run = run or subprocess.run
+    # A status that times out must not leave index.lock: don't refresh the index.
+    run = run or git_index_lock.run_git
     result = run(['git', '-c', 'core.fileMode=false', 'status', '--porcelain',
                   '--untracked-files=no', '-z'],
-                 cwd=str(project_dir), capture_output=True, text=True, timeout=timeout)
+                 cwd=str(project_dir), capture_output=True, text=True, timeout=timeout,
+                 env=git_index_lock.read_only_env())
     if result.returncode != 0:
         return None
     changed = []

web_interface/blueprints/api_v3/__init__.py

@@ -35,6 +35,7 @@ from typing import Dict, Any, Optional, Tuple, Type
 from urllib.parse import urlparse, urlunparse
 logger = logging.getLogger(__name__)
 # Import new infrastructure
+from web_interface import git_index_lock
 from src.web_interface.api_helpers import (success_response, error_response,
                                            exception_error_response, validate_request_json)
 from src.web_interface.errors import ErrorCode
@@ -558,7 +559,8 @@ def get_git_version(project_dir=None):
             capture_output=True,
             text=True,
             timeout=5,
-            cwd=str(project_dir)
+            cwd=str(project_dir),
+            env=git_index_lock.read_only_env()
         )
 
         if result.returncode == 0:

web_interface/blueprints/api_v3/system.py

@@ -14,6 +14,7 @@ from web_interface.blueprints.api_v3 import (
 )
 import threading
 
+from web_interface import git_index_lock
 from web_interface.cache import get_cached, set_cached
 from web_interface.system_metrics import collect_system_metrics, format_uptime
 import web_interface.blueprints.api_v3 as _pkg
@@ -163,6 +164,7 @@ def check_for_update():
             ['git', 'fetch', '--quiet', '--tags', '--force', update_channel.REMOTE,
              update_channel.BETA_BRANCH],
             capture_output=True, timeout=10, cwd=cwd,
+            env=git_index_lock.read_only_env(),
         )
         if fetch_result.returncode != 0:
             stderr = fetch_result.stderr.decode(errors='replace').strip()
@@ -332,7 +334,7 @@ def channel_status(project_dir=None, fetch=True):
 
 def _perform_core_update_locked(stash_local_changes=True):
     project_dir = str(PROJECT_ROOT)
-    from web_interface import update_channel, git_index_lock
+    from web_interface import update_channel
 
     # A git killed mid-command (a timed-out pull, a power cut) leaves
     # .git/index.lock behind, and every later update then fails with
@@ -343,6 +345,28 @@ def _perform_core_update_locked(stash_local_changes=True):
                 'message': 'Another git command is running in the LEDMatrix folder; '
                            'try again in a minute.'}
 
+    # A pull killed mid-rebase leaves .git/rebase-merge behind, and every
+    # later `pull --rebase` then fails. Same rule as the automatic update's
+    # preflight: a rebase really in progress leaves HEAD detached and holds
+    # the user's conflict work, so leave it; with HEAD back on a branch it was
+    # abandoned, and `--quit` drops its state without touching the tree.
+    git_dir = Path(project_dir) / '.git'
+    rebase_dirs = [git_dir / name for name in ('rebase-merge', 'rebase-apply') if (git_dir / name).exists()]
+    if rebase_dirs:
+        def _git(*args):
+            return git_index_lock.run_git(['git', *args], capture_output=True, text=True,
+                                          timeout=60, cwd=project_dir)
+        if _git('symbolic-ref', '-q', 'HEAD').returncode != 0:
+            return {'status': 'error', 'restart_required': False, 'dependency_failures': [],
+                    'message': 'A git rebase is in progress in the LEDMatrix folder. '
+                               'Finish or abort it (git rebase --continue / --abort), then update again.'}
+        cleared = _git('rebase', '--quit')
+        if cleared.returncode != 0 or any(path.exists() for path in rebase_dirs):
+            return {'status': 'error', 'restart_required': False, 'dependency_failures': [],
+                    'message': 'An abandoned git rebase in the LEDMatrix folder could not be cleared: '
+                               f'{(cleared.stderr or "").strip() or "unknown error"}.'}
+        logger.warning("Cleared an abandoned git rebase from %s", ', '.join(str(p) for p in rebase_dirs))
+
     # Which code to move to: the newest release (stable) or main (beta).
     # See web_interface/update_channel.py; it never picks an older commit.
     channel, fetch_error = channel_status(project_dir)
@@ -434,25 +458,33 @@ def _perform_core_update_locked(stash_local_changes=True):
     # Stable checks out the release tag, carrying edits across the way the
     # pull's --autostash does.
     channel_note = ''
-    if action == update_channel.ACTION_CHECKOUT_TAG:
-        result, autostash_note = update_channel.checkout_release(project_dir, channel.newest_release)
-        channel_note = f"Now on release {channel.newest_release} (stable channel). {autostash_note}".strip()
-    elif action == update_channel.ACTION_SWITCH_TO_BETA:
-        result, autostash_note = update_channel.checkout_beta_branch(project_dir)
-        if result.returncode == 0:
-            result = subprocess.run(['git', 'pull', '--rebase', '--autostash'],
-                                    capture_output=True, text=True, timeout=60, cwd=project_dir)
-        channel_note = f"Now following {update_channel.BETA_BRANCH} (beta channel). {autostash_note}".strip()
-    else:
-        result = subprocess.run(
-            pull_args,
-            capture_output=True,
-            text=True,
-            timeout=60,
-            cwd=project_dir
-        )
-        if channel.waiting and channel.newest_release:
-            channel_note = channel.message
+    try:
+        if action == update_channel.ACTION_CHECKOUT_TAG:
+            result, autostash_note = update_channel.checkout_release(project_dir, channel.newest_release)
+            channel_note = f"Now on release {channel.newest_release} (stable channel). {autostash_note}".strip()
+        elif action == update_channel.ACTION_SWITCH_TO_BETA:
+            result, autostash_note = update_channel.checkout_beta_branch(project_dir)
+            if result.returncode == 0:
+                result = git_index_lock.run_git(['git', 'pull', '--rebase', '--autostash'],
+                                               capture_output=True, text=True,
+                                               timeout=git_index_lock.MUTATING_TIMEOUT_SECONDS, cwd=project_dir)
+            channel_note = f"Now following {update_channel.BETA_BRANCH} (beta channel). {autostash_note}".strip()
+        else:
+            result = git_index_lock.run_git(
+                pull_args,
+                capture_output=True,
+                text=True,
+                timeout=git_index_lock.MUTATING_TIMEOUT_SECONDS,
+                cwd=project_dir
+            )
+            if channel.waiting and channel.newest_release:
+                channel_note = channel.message
+    except subprocess.TimeoutExpired:
+        # run_git has stopped git and removed the lock it left.
+        logger.warning("git timed out during Update Code")
+        return {'status': 'error', 'restart_required': False, 'dependency_failures': [],
+                'message': 'Update failed: git took too long (a slow network or SD card). '
+                           'The partial update was cleaned up; try again.'}
 
     # Give the branch tracking information so the next pull is a plain
     # `git pull` — otherwise every update repeats the fallback.

web_interface/git_index_lock.py

@@ -18,6 +18,8 @@ the file alone. Standard library only.
 """
 import logging
 import os
+import signal
+import subprocess  # nosec B404 - list-form argv only, no shell  # nosemgrep
 import time
 from pathlib import Path
 
@@ -33,6 +35,15 @@ REMOVED = 'removed'    # it was stale and has been removed
 IN_USE = 'in_use'      # a git process is running here (or the lock is brand new)
 UNKNOWN = 'unknown'    # could not tell whether git is running; left alone
 
+#: How long a timed-out git gets to exit after SIGTERM (which lets it remove
+#: its own lock) before the whole process group is SIGKILLed.
+TERM_GRACE_SECONDS = 5
+
+#: Timeout for commands that rewrite the checkout (pull, checkout, reset,
+#: stash). A Pi on an SD card can take minutes; killing git is what leaves the
+#: lock behind, so this is generous.
+MUTATING_TIMEOUT_SECONDS = 600
+
 _PROC = Path('/proc')
 
 
@@ -137,7 +148,73 @@ def clear_stale_index_lock(project_dir, proc_root=_PROC, now=None):
     return REMOVED
 
 
+def _stop_group(proc):
+    """SIGTERM the process group, then SIGKILL whatever is left of it."""
+    try:
+        os.killpg(proc.pid, signal.SIGTERM)
+    except (ProcessLookupError, PermissionError):
+        pass
+    try:
+        proc.wait(timeout=TERM_GRACE_SECONDS)
+    except subprocess.TimeoutExpired:
+        pass
+    # Also reaps git's children (git-remote-https, rebase helpers) that
+    # outlive a killed parent.
+    try:
+        os.killpg(proc.pid, signal.SIGKILL)
+    except (ProcessLookupError, PermissionError):
+        pass
+
+
+def _clear_after_stop(project_dir):
+    """Remove the lock a stopped git left, waiting out the freshness window.
+
+    A lock created within ``MIN_STALE_AGE_SECONDS`` of the stop reads as IN_USE
+    on age alone; with no git process left it only needs to age, so wait for
+    that rather than leave it to block the next attempt.
+    """
+    deadline = time.monotonic() + MIN_STALE_AGE_SECONDS + 1
+    while clear_stale_index_lock(project_dir) == IN_USE and git_running_in(project_dir) is False:
+        if time.monotonic() >= deadline:
+            break
+        time.sleep(0.5)
+
+
+def run_git(cmd, *, cwd=None, timeout=None, capture_output=True, text=True, **kwargs):
+    """``subprocess.run`` for git, without leaving ``.git/index.lock`` behind.
+
+    ``subprocess.run`` SIGKILLs only the direct child when ``timeout`` expires,
+    which skips git's cleanup and orphans its helpers. This starts git in its
+    own session, stops the whole group with SIGTERM before SIGKILL, removes a
+    lock nothing owns any more, then raises ``TimeoutExpired`` as
+    ``subprocess.run`` would.
+    """
+    if capture_output:
+        kwargs['stdout'] = kwargs['stderr'] = subprocess.PIPE
+    with subprocess.Popen(cmd, cwd=cwd, text=text, start_new_session=True, **kwargs) as proc:  # nosec B603 - list-form argv  # nosemgrep
+        try:
+            stdout, stderr = proc.communicate(timeout=timeout)
+        except subprocess.TimeoutExpired as exc:
+            _stop_group(proc)
+            exc.stdout, exc.stderr = proc.communicate()
+            if cwd is not None:
+                _clear_after_stop(cwd)
+            raise
+        except BaseException:
+            _stop_group(proc)
+            raise
+    return subprocess.CompletedProcess(proc.args, proc.returncode, stdout, stderr)  # result object only, nothing is run  # nosemgrep
+
+
+def read_only_env():
+    """Environment for git calls that only read: ``GIT_OPTIONAL_LOCKS=0``
+    stops ``status`` and ``describe --dirty`` refreshing (and so locking) the
+    index, so a poll that times out cannot leave a lock."""
+    return {**os.environ, 'GIT_OPTIONAL_LOCKS': '0'}
+
+
 def manual_fix_hint(project_dir):
     """The sentence shown when a lock blocks the update and was not removed."""
-    return (f"If no other git command is running, remove the stale lock with "
-            f"rm -f {Path(project_dir) / '.git' / 'index.lock'} and try again.")
+    lock = Path(project_dir) / '.git' / 'index.lock'
+    return (f"If it keeps coming back, stop the LEDMatrix services, kill any running git "
+            f"(ps aux | grep git), then remove it with rm -f {lock} and try again.")

web_interface/update_channel.py

@@ -24,6 +24,8 @@ import re
 import subprocess  # nosec B404 - list-form argv only, no shell  # nosemgrep
 from pathlib import Path
 
+from web_interface import git_index_lock
+
 PROJECT_ROOT = Path(__file__).resolve().parent.parent
 CHANNELS = ('stable', 'beta')
 DEFAULT_CHANNEL = 'stable'
@@ -105,7 +107,7 @@ class ChannelStatus(dict):
 
 
 def _git(project_dir, run, *args, timeout=30):
-    run = run or subprocess.run
+    run = run or git_index_lock.run_git
     return run(['git', *args], cwd=str(project_dir), capture_output=True, text=True, timeout=timeout)