# HG changeset patch
# User Valentin Gatien-Baron <valentin.gatienbaron@gmail.com>
# Date 1574136638 28800
# Node ID 039fbd14d4e2889be830cc114957c31972c6ea04
# Parent  cd822413b9aa72da9ab040ff17b4131a7a23e250
lock: fix race in lock-breaking code

With low frequency, I see hg pulls fail with output like:
abort: no such file or directory: .hg/store/lock

I think what happens is, in lock.py, in:

    def _testlock(self, locker):
        if not self._lockshouldbebroken(locker):
            return locker

        # if locker dead, break lock.  must do this with another lock
        # held, or can race and break valid lock.
        try:
            with lock(self.vfs, self.f + b'.break', timeout=0):
                self.vfs.unlink(self.f)
        except error.LockError:
            return locker

if a lock is breakable on disk, and two hg processes concurrently get
to the "if locker dead" comment, a possible interleaving is: process1
finishes executing the function and then process2 finishes executing
the function. If that happens, process2 will either get ENOENT in
self.vfs.unlink (resulting in the spurious failure above), or break a
valid lock and potentially cause repository corruption.

The fix is simple enough: make sure the lock is breakable _inside_ the
critical section, because only then can we know that no other process
can invalidate our knowledge on the lock on disk.

I don't think there are tests for this. I've tested this manually
with:

diff --git a/mercurial/lock.py b/mercurial/lock.py
--- a/mercurial/lock.py
+++ b/mercurial/lock.py
@@ -351,6 +351,8 @@ class lock(object):
         if not self._lockshouldbebroken(locker):
             return locker

+        import random
+        time.sleep(1. + random.random())
         # if locker dead, break lock.  must do this with another lock
         # held, or can race and break valid lock.
         try:
@@ -358,6 +360,7 @@ class lock(object):
                 self.vfs.unlink(self.f)
         except error.LockError:
             return locker
+        time.sleep(1)

     def testlock(self):
         """return id of locker if lock is valid, else None.

and I see this change of behavior before/after this commit:

 $ $hg init repo
 $ cd repo
 $ ln -s $HOSTNAME/effffffc:987654321 .hg/wlock
 $ touch a
 $ $hg commit -Am_ & $hg commit -Am _; wait
-abort: No such file or directory: '/tmp/repo/.hg/wlock'
 adding a
+warning: ignoring unknown working parent 679a8959a8ca!
+nothing changed

Differential Revision: https://phab.mercurial-scm.org/D7199

diff -r cd822413b9aa -r 039fbd14d4e2 mercurial/lock.py
--- a/mercurial/lock.py	Fri Nov 01 19:59:07 2019 -0400
+++ b/mercurial/lock.py	Mon Nov 18 20:10:38 2019 -0800
@@ -355,6 +355,9 @@
         # held, or can race and break valid lock.
         try:
             with lock(self.vfs, self.f + b'.break', timeout=0):
+                locker = self._readlock()
+                if not self._lockshouldbebroken(locker):
+                    return locker
                 self.vfs.unlink(self.f)
         except error.LockError:
             return locker