user/sven/linux.git/kernel/hung_task.c, branch v3.10

hung task debugging: Inject NMI when hung and going to panic

2012-04-25T10:39:25Z

Send an NMI to all CPUs when a hung task is detected and the hung task code is configured to panic. This gives us a fairly uptodate snapshot of all CPUs in the system. This lets us get stack trace of all CPUs which makes life easier trying to debug a deadlock, and the NMI doesn't change anything since the next step is a kernel panic. Signed-off-by: Sasha Levin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/1331848040-1676-1-git-send-email-levinsasha928@gmail.com [ extended the changelog a bit ] Signed-off-by: Ingo Molnar

hung_task: fix the broken rcu_lock_break() logic

2012-03-05T23:49:42Z

check_hung_uninterruptible_tasks()->rcu_lock_break() introduced by "softlockup: check all tasks in hung_task" commit ce9dbe24 looks absolutely wrong. - rcu_lock_break() does put_task_struct(). If the task has exited it is not safe to even read its ->state, nothing protects this task_struct. - The TASK_DEAD checks are wrong too. Contrary to the comment, we can't use it to check if the task was unhashed. It can be unhashed without TASK_DEAD, or it can be valid with TASK_DEAD. For example, an autoreaping task can do release_task(current) long before it sets TASK_DEAD in do_exit(). Or, a zombie task can have ->state == TASK_DEAD but release_task() was not called, and in this case we must not break the loop. Change this code to check pid_alive() instead, and do this before we drop the reference to the task_struct. Note: while_each_thread() under rcu_read_lock() is not really safe, it can livelock. This will be fixed later, but fortunately in this case the "max_count" logic saves us anyway. Signed-off-by: Oleg Nesterov Acked-by: Frederic Weisbecker Acked-by: Mandeep Singh Baines Acked-by: Paul E. McKenney Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

hung_task: fix false positive during vfork

2012-01-04T00:14:32Z

vfork parent uninterruptibly and unkillably waits for its child to exec/exit. This wait is of unbounded length. Ignore such waits in the hung_task detector. Signed-off-by: Mandeep Singh Baines Reported-by: Sasha Levin LKML-Reference: <1325344394.28904.43.camel@lappy> Cc: Linus Torvalds Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Andrew Morton Cc: John Kacur Cc: stable@kernel.org Signed-off-by: Linus Torvalds

kernel: Map most files to use export.h instead of module.h

2011-10-31T13:20:12Z

The changed files were only including linux/module.h for the EXPORT_SYMBOL infrastructure, and nothing else. Revector them onto the isolated export header for faster compile times. Nothing to see here but a whole lot of instances of: -#include +#include This commit is only changing the kernel dir; next targets will probably be mm, fs, the arch dirs, etc. Signed-off-by: Paul Gortmaker

watchdog, hung_task_timeout: Add Kconfig configurable default

2011-04-28T07:13:17Z

This patch allows the default value for sysctl_hung_task_timeout_secs to be set at build time. The feature carries virtually no overhead, so it makes sense to keep it enabled. On heavily loaded systems, though, it can end up triggering stack traces when there is no bug other than the system being underprovisioned. We use this patch to keep the hung task facility available but disabled at boot-time. The default of 120 seconds is preserved. As a note, commit e162b39a may have accidentally reverted commit fb822db4, which raised the default from 120 seconds to 480 seconds. Signed-off-by: Jeff Mahoney Acked-by: Mandeep Singh Baines Link: http://lkml.kernel.org/r/4DB8600C.8080000@suse.com Signed-off-by: Ingo Molnar

lockup detector: Fix grammar by adding a missing "to" in the comments

2010-08-17T07:11:52Z

This fixes a minor grammar problem in the comments in hung_task.c Signed-off-by: John Kacur Cc: Peter Zijlstra LKML-Reference: <1281021054-4228-2-git-send-email-jkacur@redhat.com> Signed-off-by: Ingo Molnar

lockdep: Remove __debug_show_held_locks

2010-08-17T07:11:10Z

There is no longer any functional difference between __debug_show_held_locks() and debug_show_held_locks(), so remove the former. Signed-off-by: John Kacur Cc: Peter Zijlstra LKML-Reference: <1281021054-4228-1-git-send-email-jkacur@redhat.com> Signed-off-by: Ingo Molnar

softlockup: Fix hung_task_check_count sysctl

2009-11-27T05:21:57Z

I'm seeing spikes of up to 0.5ms in khungtaskd on a large machine. To reduce this source of jitter I tried setting hung_task_check_count to 0: # echo 0 > /proc/sys/kernel/hung_task_check_count which didn't have the intended response. Change to a post increment of max_count, so a value of 0 means check 0 tasks. Signed-off-by: Anton Blanchard Acked-by: Frederic Weisbecker Cc: msb@google.com LKML-Reference: <20091127022820.GU32182@kryten> Signed-off-by: Ingo Molnar

sysctl: remove "struct file *" argument of ->proc_handler

2009-09-24T14:21:04Z

It's unused. It isn't needed -- read or write flag is already passed and sysctl shouldn't care about the rest. It _was_ used in two places at arch/frv for some reason. Signed-off-by: Alexey Dobriyan Cc: David Howells Cc: "Eric W. Biederman" Cc: Al Viro Cc: Ralf Baechle Cc: Martin Schwidefsky Cc: Ingo Molnar Cc: "David S. Miller" Cc: James Morris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

softlockup: ensure the task has been switched out once

2009-02-11T10:04:16Z

When we check if a task has been switched out since the last scan, we might have a race condition on the following scenario: - the task is freshly created and scheduled - it puts its state to TASK_UNINTERRUPTIBLE and is not yet switched out - check_hung_task() scans this task and will report a false positive because t->nvcsw + t->nivcsw == t->last_switch_count == 0 Add a check for such cases. Signed-off-by: Frederic Weisbecker Acked-by: Mandeep Singh Baines Signed-off-by: Ingo Molnar