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: NOleg Nesterov <oleg@redhat.com>
Acked-by: NFrederic Weisbecker <fweisbec@gmail.com>
Acked-by: NMandeep Singh Baines <msb@google.com>
Acked-by: NPaul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

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: NMandeep Singh Baines <msb@chromium.org>
Reported-by: NSasha Levin <levinsasha928@gmail.com>
LKML-Reference: <1325344394.28904.43.camel@lappy>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: John Kacur <jkacur@redhat.com>
Cc: stable@kernel.org
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

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 <linux/module.h>
  +#include <linux/export.h>

This commit is only changing the kernel dir; next targets
will probably be mm, fs, the arch dirs, etc.
Signed-off-by: NPaul Gortmaker <paul.gortmaker@windriver.com>

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: NJeff Mahoney <jeffm@suse.com>
Acked-by: NMandeep Singh Baines <msb@google.com>
Link: http://lkml.kernel.org/r/4DB8600C.8080000@suse.comSigned-off-by: NIngo Molnar <mingo@elte.hu>

This fixes a minor grammar problem in the comments in
hung_task.c
Signed-off-by: NJohn Kacur <jkacur@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1281021054-4228-2-git-send-email-jkacur@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

There is no longer any functional difference between
__debug_show_held_locks() and debug_show_held_locks(),
so remove the former.
Signed-off-by: NJohn Kacur <jkacur@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1281021054-4228-1-git-send-email-jkacur@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

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: NAnton Blanchard <anton@samba.org>
Acked-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: msb@google.com
LKML-Reference: <20091127022820.GU32182@kryten>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

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: NAlexey Dobriyan <adobriyan@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: James Morris <jmorris@namei.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

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: NFrederic Weisbecker <fweisbec@gmail.com>
Acked-by: NMandeep Singh Baines <msb@google.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: saves sizeof(long) bytes per task_struct

By guaranteeing that sysctl_hung_task_timeout_secs have elapsed between
tasklist scans we can avoid using timestamps.
Signed-off-by: NMandeep Singh Baines <msb@google.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Since the tasklist is protected by rcu list operations, it is safe
to convert the read_lock()s to rcu_read_lock().
Suggested-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: NMandeep Singh Baines <msb@google.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: extend the scope of hung-task checks

Changed the default value of hung_task_check_count to PID_MAX_LIMIT.
hung_task_batch_count added to put an upper bound on the critical
section. Every hung_task_batch_count checks, the rcu lock is never
held for a too long time.

Keeping the critical section small minimizes time preemption is disabled
and keeps rcu grace periods small.

To prevent following a stale pointer, get_task_struct is called on g and t.
To verify that g and t have not been unhashed while outside the critical
section, the task states are checked.

The design was proposed by Frédéric Weisbecker.
Signed-off-by: NMandeep Singh Baines <msb@google.com>
Suggested-by: NFrédéric Weisbecker <fweisbec@gmail.com>
Acked-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: fix potential false panic

A potential race exists if sysctl_hung_task_timeout_secs is reset to 0
while inside check_hung_uniterruptible_tasks(). If check_task() is
entered, a comparison with 0 will result in a false hung_task being
detected.

If sysctl_hung_task_panic is set, the system will panic.
Signed-off-by: NMandeep Singh Baines <msb@google.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Decoupling allows:

* hung tasks check to happen at very low priority

* hung tasks check and softlockup to be enabled/disabled independently
  at compile and/or run-time

* individual panic settings to be enabled disabled independently
  at compile and/or run-time

* softlockup threshold to be reduced without increasing hung tasks
  poll frequency (hung task check is expensive relative to softlock watchdog)

* hung task check to be zero over-head when disabled at run-time
Signed-off-by: NMandeep Singh Baines <msb@google.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>