Re: [3.15-rc3] rtmutex-debug assertion.

2014-05-08 Thread Dave Jones
On Thu, May 08, 2014 at 05:28:54PM +0200, Thomas Gleixner wrote: > > > All I see in dmesg are occasional ooms which kill random trinity > > > childs. > > > > hm, that sounds odd. if it's only fuzzing futex, it shouldn't be > > doing much memory allocation. > > It has a fast memory leak

Re: [3.15-rc3] rtmutex-debug assertion.

2014-05-08 Thread Thomas Gleixner
On Mon, 5 May 2014, Dave Jones wrote: > On Mon, May 05, 2014 at 08:08:02PM +0200, Thomas Gleixner wrote: > > > I twisted my brain around that for a fricking long time, but I really > > can't see the failure in the code. > > > > Neither did I succeed to trigger the issue in a VM (with and wi

Re: [3.15-rc3] rtmutex-debug assertion.

2014-05-05 Thread Thomas Gleixner
B1;3202;0cOn Fri, 2 May 2014, Dave Jones wrote: > On Wed, Apr 30, 2014 at 11:13:57AM +0200, Thomas Gleixner wrote: > > On Tue, 29 Apr 2014, Dave Jones wrote: > > > This is trickier to reproduce than it first seemed, as logging slows > > > things down so much. But after a few hours, it logged th

Re: [3.15-rc3] rtmutex-debug assertion.

2014-05-01 Thread Dave Jones
On Wed, Apr 30, 2014 at 11:13:57AM +0200, Thomas Gleixner wrote: > On Tue, 29 Apr 2014, Dave Jones wrote: > > This is trickier to reproduce than it first seemed, as logging slows > > things down so much. But after a few hours, it logged that the > > call that triggered this was.. > > > > fu

Re: [3.15-rc3] rtmutex-debug assertion.

2014-04-30 Thread Thomas Gleixner
On Tue, 29 Apr 2014, Dave Jones wrote: > This is trickier to reproduce than it first seemed, as logging slows > things down so much. But after a few hours, it logged that the > call that triggered this was.. > > futex(uaddr=0x7f55ff8c4000, op=0x6, val=0x20006223800b, > utime=0x7f55ff8c4000,

Re: [3.15-rc3] rtmutex-debug assertion.

2014-04-30 Thread Thomas Gleixner
On Tue, 29 Apr 2014, Davidlohr Bueso wrote: > On Tue, 2014-04-29 at 20:14 -0400, Dave Jones wrote: > > > > futex(uaddr=0x7f55ff8c4000, op=0x6, val=0x20006223800b, > > utime=0x7f55ff8c4000, uaddr2=0x7f55ff8c4000, val3=-123) > > Perhaps because of chance. Even for pi futexes, if the lock is >

Re: [3.15-rc3] rtmutex-debug assertion.

2014-04-29 Thread Dave Jones
On Tue, Apr 29, 2014 at 07:24:30PM -0700, Davidlohr Bueso wrote: > > futex(uaddr=0x7f55ff8c4000, op=0x6, val=0x20006223800b, > > utime=0x7f55ff8c4000, uaddr2=0x7f55ff8c4000, val3=-123) > > Perhaps because of chance. Even for pi futexes, if the lock is > uncontended, the kernel will neve

Re: [3.15-rc3] rtmutex-debug assertion.

2014-04-29 Thread Davidlohr Bueso
On Tue, 2014-04-29 at 20:14 -0400, Dave Jones wrote: > On Tue, Apr 29, 2014 at 11:16:55AM -0400, Dave Jones wrote: > > Just hit this while fuzzing the futex() syscall. > > > > > > WARNING: CPU: 2 PID: 6202 at kernel/locking/rtmutex-debug.c:151 > debug_rt_mutex_proxy_unlock+0x4e/0x60() > > D

Re: [3.15-rc3] rtmutex-debug assertion.

2014-04-29 Thread Dave Jones
On Tue, Apr 29, 2014 at 11:16:55AM -0400, Dave Jones wrote: > Just hit this while fuzzing the futex() syscall. > > > WARNING: CPU: 2 PID: 6202 at kernel/locking/rtmutex-debug.c:151 > debug_rt_mutex_proxy_unlock+0x4e/0x60() > DEBUG_LOCKS_WARN_ON(!rt_mutex_owner(lock)) > Modules linked in:

[3.15-rc3] rtmutex-debug assertion.

2014-04-29 Thread Dave Jones
Just hit this while fuzzing the futex() syscall. WARNING: CPU: 2 PID: 6202 at kernel/locking/rtmutex-debug.c:151 debug_rt_mutex_proxy_unlock+0x4e/0x60() DEBUG_LOCKS_WARN_ON(!rt_mutex_owner(lock)) Modules linked in: tun fuse ipt_ULOG nfnetlink bnep can_bcm scsi_transport_iscsi nfc caif_socket c