Hello,
We are still facing some ext2fs hangs sometimes, and I got an
interesting backtrace today:
Thread 94 (thread 348.94):
#0 0x010d753c in mach_msg_trap () from /lib/libc.so.0.3
#1 0x010d7cc9 in mach_msg () from /lib/libc.so.0.3
#2 0x010a3630 in cproc_block ()
at /build/mbanck/hurd-20071119/build-tree/hurd/libthreads/cprocs.c:643
#3 0x010a3d1a in __mutex_lock_solid (ptr=________ CCCC 0x8123c6c __________)
at /build/mbanck/hurd-20071119/build-tree/hurd/libthreads/cprocs.c:955
#4 0x0104a1e9 in diskfs_release_peropen (po=0x8242640)
at /build/mbanck/hurd-20071119/build-tree/hurd/libdiskfs/peropen-rele.c:25
#5 0x0104a402 in diskfs_protid_rele (arg=0x81d0818)
at /build/mbanck/hurd-20071119/build-tree/hurd/libdiskfs/protid-rele.c:34
#6 0x010aa912 in _ports_complete_deallocate (pi=0x81d0818)
at
/build/mbanck/hurd-20071119/build-tree/hurd/libports/complete-deallocate.c:49
#7 0x010a9421 in ports_port_deref (portstruct=0x81d0818)
at /build/mbanck/hurd-20071119/build-tree/hurd/libports/port-deref.c:48
#8 0x01038825 in diskfs_S_dir_lookup (dircred=0x80e9698,
path=0x1aedf4c "@test", flags=262154=O_NONBLOCK|O_WRONLY|O_EXLOCK, mode=0,
retry=0x1aebf44,
retryname=0x1aebf4c "", returned_port=0x1aec350,
returned_port_poly=0x1aebe48)
at /build/mbanck/hurd-20071119/build-tree/hurd/libdiskfs/dir-lookup.c:478
dir-lookup.c:478 is as follows:
469 if (! error)
470 {
471 if (flags & O_EXLOCK)
472 error = fshelp_acquire_lock (&np->userlock, &newpi->po->lock_status,
473 &np->lock, LOCK_EX);
474 else if (flags & O_SHLOCK)
475 error = fshelp_acquire_lock (&np->userlock, &newpi->po->lock_status,
476 &np->lock, LOCK_SH);
477 if (error)
478 ports_port_deref (newpi); /* Get rid of NEWPI. */
479 }
i.e. someone tried to open @test exclusively, but it failed (EINTR),
and thus we drop newpi. The problem is that since that's the last
reference, it cals _ports_complete_deallocate, which ends up calling
diskfs_release_peropen which tries to acquire the lock on np, which we
_already_ have, thus the deadlock, which quickly propagates to the /.
It looks like we have the same problem with diskfs_create_protid().
Since in case of an error we don't return a locked np, I guess the
correct fix is as attached to this mail?
Samuel
Index: libdiskfs/dir-lookup.c
===================================================================
RCS file: /cvsroot/hurd/hurd/libdiskfs/dir-lookup.c,v
retrieving revision 1.53
diff -u -p -r1.53 dir-lookup.c
--- libdiskfs/dir-lookup.c 13 May 2002 22:04:48 -0000 1.53
+++ libdiskfs/dir-lookup.c 5 Jun 2008 23:11:18 -0000
@@ -463,7 +463,10 @@ diskfs_S_dir_lookup (struct protid *dirc
{
error = diskfs_create_protid (newpo, dircred->user, &newpi);
if (error)
- diskfs_release_peropen (newpo);
+ {
+ mutex_unlock(&np->lock);
+ diskfs_release_peropen (newpo);
+ }
}
if (! error)
@@ -475,7 +478,10 @@ diskfs_S_dir_lookup (struct protid *dirc
error = fshelp_acquire_lock (&np->userlock, &newpi->po->lock_status,
&np->lock, LOCK_SH);
if (error)
- ports_port_deref (newpi); /* Get rid of NEWPI. */
+ {
+ mutex_unlock(&np->lock);
+ ports_port_deref (newpi); /* Get rid of NEWPI. */
+ }
}
if (! error)
