* Deadlock (un-killable processes) in sys_futex
@ 2013-10-07 16:22 ` Robert Święcki
0 siblings, 0 replies; 2+ messages in thread
From: Robert Święcki @ 2013-10-07 16:22 UTC (permalink / raw
To: linux-kernel, linux-mm
After fuzzing the linux kernel (3.12-rc4) I have two processes which
are stuck in an un-killable state. This is not specific to 3.12-rc4,
as I'm able to reproduce it on most modern kernels (e.g. Ubuntu's 3.5)
after a few minutes of fuzzing with a syscall fuzzer.
The debug data can be found here: http://alt.swiecki.net/linux/20327/
- process PIDs: 20327 and 13735
It includes..
ftrace report (probably the most useful):
I'm not expert in this kernel area (futex/mm), but it seems like a
constatnt loop between fault_in_user_writeable() and do_page_fault():
http://alt.swiecki.net/linux/20327/20327.trace.report.txt
/proc/pid/maps, /proc/pid/status:
http://alt.swiecki.net/linux/20327/20327.maps.txt
http://alt.swiecki.net/linux/20327/20327.status.txt
kdb stacktraces showing that both processes (single-threaded) are
stuck in sys_futex:
http://alt.swiecki.net/linux/20327/20327.kdb.txt
http://alt.swiecki.net/linux/20327/13735.kdb.txt
kgdb stacktraces displaying rather corrupted data:
http://alt.swiecki.net/linux/20327/20327.kgdb.txt
http://alt.swiecki.net/linux/20327/13735.kgdb.txt
kernel conf:
http://alt.swiecki.net/linux/20327/config-3.12-rc4.txt
--
Robert Święcki
^ permalink raw reply [flat|nested] 2+ messages in thread
* Deadlock (un-killable processes) in sys_futex
@ 2013-10-07 16:22 ` Robert Święcki
0 siblings, 0 replies; 2+ messages in thread
From: Robert Święcki @ 2013-10-07 16:22 UTC (permalink / raw
To: linux-kernel, linux-mm
After fuzzing the linux kernel (3.12-rc4) I have two processes which
are stuck in an un-killable state. This is not specific to 3.12-rc4,
as I'm able to reproduce it on most modern kernels (e.g. Ubuntu's 3.5)
after a few minutes of fuzzing with a syscall fuzzer.
The debug data can be found here: http://alt.swiecki.net/linux/20327/
- process PIDs: 20327 and 13735
It includes..
ftrace report (probably the most useful):
I'm not expert in this kernel area (futex/mm), but it seems like a
constatnt loop between fault_in_user_writeable() and do_page_fault():
http://alt.swiecki.net/linux/20327/20327.trace.report.txt
/proc/pid/maps, /proc/pid/status:
http://alt.swiecki.net/linux/20327/20327.maps.txt
http://alt.swiecki.net/linux/20327/20327.status.txt
kdb stacktraces showing that both processes (single-threaded) are
stuck in sys_futex:
http://alt.swiecki.net/linux/20327/20327.kdb.txt
http://alt.swiecki.net/linux/20327/13735.kdb.txt
kgdb stacktraces displaying rather corrupted data:
http://alt.swiecki.net/linux/20327/20327.kgdb.txt
http://alt.swiecki.net/linux/20327/13735.kgdb.txt
kernel conf:
http://alt.swiecki.net/linux/20327/config-3.12-rc4.txt
--
Robert Święcki
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2013-10-07 16:22 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2013-10-07 16:22 Deadlock (un-killable processes) in sys_futex Robert Święcki
2013-10-07 16:22 ` Robert Święcki
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.