lock: while releasing, unlink lockfile even if the release function throws

Consider a hypothetical bug in the release function that causes it to raise an
exception. Also consider the bisect command, which saves its state in a finally
clause. Saving the state requires acquiring the wlock.

If we don't unlink the lockfile when the exception is thrown, we'll try to
acquire the wlock again. We're going to try and acquire a lock again while our
old lockfile is on disk. The PID on disk is our own, and of course we're still
running, so we won't take over the lock. Hence we'll be stuck waiting for a
lock that we left behind ourselves.

To avoid this, always unlink the lockfile. This preserves the invariant that
self.held > 0 is equivalent to the lockfile existing on disk.

mercurial/lock.py

@@ -1,154 +1,156 b''
 # lock.py - simple advisory locking scheme for mercurial
 #
 # Copyright 2005, 2006 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import util, error
 import errno, os, socket, time
 import warnings
 
 class lock(object):
     '''An advisory lock held by one process to control access to a set
     of files.  Non-cooperating processes or incorrectly written scripts
     can ignore Mercurial's locking scheme and stomp all over the
     repository, so don't do that.
 
     Typically used via localrepository.lock() to lock the repository
     store (.hg/store/) or localrepository.wlock() to lock everything
     else under .hg/.'''
 
     # lock is symlink on platforms that support it, file on others.
 
     # symlink is used because create of directory entry and contents
     # are atomic even over nfs.
 
     # old-style lock: symlink to pid
     # new-style lock: symlink to hostname:pid
 
     _host = None
 
     def __init__(self, vfs, file, timeout=-1, releasefn=None, desc=None):
         self.vfs = vfs
         self.f = file
         self.held = 0
         self.timeout = timeout
         self.releasefn = releasefn
         self.desc = desc
         self.postrelease  = []
         self.pid = os.getpid()
         self.delay = self.lock()
 
     def __del__(self):
         if self.held:
             warnings.warn("use lock.release instead of del lock",
                     category=DeprecationWarning,
                     stacklevel=2)
 
             # ensure the lock will be removed
             # even if recursive locking did occur
             self.held = 1
 
         self.release()
 
     def lock(self):
         timeout = self.timeout
         while True:
             try:
                 self.trylock()
                 return self.timeout - timeout
             except error.LockHeld, inst:
                 if timeout != 0:
                     time.sleep(1)
                     if timeout > 0:
                         timeout -= 1
                     continue
                 raise error.LockHeld(errno.ETIMEDOUT, inst.filename, self.desc,
                                      inst.locker)
 
     def trylock(self):
         if self.held:
             self.held += 1
             return
         if lock._host is None:
             lock._host = socket.gethostname()
         lockname = '%s:%s' % (lock._host, self.pid)
         while not self.held:
             try:
                 self.vfs.makelock(lockname, self.f)
                 self.held = 1
             except (OSError, IOError), why:
                 if why.errno == errno.EEXIST:
                     locker = self.testlock()
                     if locker is not None:
                         raise error.LockHeld(errno.EAGAIN,
                                              self.vfs.join(self.f), self.desc,
                                              locker)
                 else:
                     raise error.LockUnavailable(why.errno, why.strerror,
                                                 why.filename, self.desc)
 
     def testlock(self):
         """return id of locker if lock is valid, else None.
 
         If old-style lock, we cannot tell what machine locker is on.
         with new-style lock, if locker is on this machine, we can
         see if locker is alive.  If locker is on this machine but
         not alive, we can safely break lock.
 
         The lock file is only deleted when None is returned.
 
         """
         try:
             locker = self.vfs.readlock(self.f)
         except (OSError, IOError), why:
             if why.errno == errno.ENOENT:
                 return None
             raise
         try:
             host, pid = locker.split(":", 1)
         except ValueError:
             return locker
         if host != lock._host:
             return locker
         try:
             pid = int(pid)
         except ValueError:
             return locker
         if util.testpid(pid):
             return locker
         # if locker dead, break lock.  must do this with another lock
         # held, or can race and break valid lock.
         try:
             l = lock(self.vfs, self.f + '.break', timeout=0)
             self.vfs.unlink(self.f)
             l.release()
         except error.LockError:
             return locker
 
     def release(self):
         """release the lock and execute callback function if any
 
         If the lock has been acquired multiple times, the actual release is
         delayed to the last release call."""
         if self.held > 1:
             self.held -= 1
         elif self.held == 1:
             self.held = 0
             if os.getpid() != self.pid:
                 # we forked, and are not the parent
                 return
-            if self.releasefn:
-                self.releasefn()
             try:
-                self.vfs.unlink(self.f)
-            except OSError:
-                pass
+                if self.releasefn:
+                    self.releasefn()
+            finally:
+                try:
+                    self.vfs.unlink(self.f)
+                except OSError:
+                    pass
             for callback in self.postrelease:
                 callback()
 
 def release(*locks):
     for lock in locks:
         if lock is not None:
             lock.release()

tests/test-lock-badness.t

@@ -1,41 +1,77 b''
 #require unix-permissions no-root no-windows
 
 Prepare
 
   $ hg init a
   $ echo a > a/a
   $ hg -R a ci -A -m a
   adding a
 
   $ hg clone a b
   updating to branch default
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
+Test that raising an exception in the release function doesn't cause the lock to choke
+
+  $ cat > testlock.py << EOF
+  > from mercurial import cmdutil, error, util
+  > 
+  > cmdtable = {}
+  > command = cmdutil.command(cmdtable)
+  > 
+  > def acquiretestlock(repo, releaseexc):
+  >     def unlock():
+  >         if releaseexc:
+  >             raise util.Abort('expected release exception')
+  >     l = repo._lock(repo.vfs, 'testlock', False, unlock, None, 'test lock')
+  >     return l
+  > 
+  > @command('testlockexc')
+  > def testlockexc(ui, repo):
+  >     testlock = acquiretestlock(repo, True)
+  >     try:
+  >         testlock.release()
+  >     finally:
+  >         try:
+  >             testlock = acquiretestlock(repo, False)
+  >         except error.LockHeld:
+  >             raise util.Abort('lockfile on disk even after releasing!')
+  >         testlock.release()
+  > EOF
+  $ cat >> $HGRCPATH << EOF
+  > [extensions]
+  > testlock=$TESTTMP/testlock.py
+  > EOF
+
+  $ hg -R b testlockexc
+  abort: expected release exception
+  [255]
+
 One process waiting for another
 
   $ cat > hooks.py << EOF
   > import time
   > def sleepone(**x): time.sleep(1)
   > def sleephalf(**x): time.sleep(0.5)
   > EOF
   $ echo b > b/b
   $ hg -R b ci -A -m b --config hooks.precommit="python:`pwd`/hooks.py:sleepone" > stdout &
   $ hg -R b up -q --config hooks.pre-update="python:`pwd`/hooks.py:sleephalf"
   waiting for lock on working directory of b held by '*:*' (glob)
   got lock after ? seconds (glob)
   warning: ignoring unknown working parent d2ae7f538514!
   $ wait
   $ cat stdout
   adding b
 
 Pushing to a local read-only repo that can't be locked
 
   $ chmod 100 a/.hg/store
 
   $ hg -R b push a
   pushing to a
   searching for changes
   abort: could not lock repository a: Permission denied
   [255]
 
   $ chmod 700 a/.hg/store