On Wed, Aug 07, 2013 at 05:38:27AM -0700, Paul E. McKenney wrote:
> On Wed, Aug 07, 2013 at 06:24:56PM +0800, Lai Jiangshan wrote:
> > Although all articles declare that rcu read site is deadlock-immunity.
> > It is not true for rcu-preempt, it will be deadlock if rcu read site
> > overlaps with scheduler lock.
> 
> The real rule is that if the scheduler does its outermost rcu_read_unlock()
> with one of those locks held, it has to have avoided enabling preemption
> through the entire RCU read-side critical section.
> 
> That said, avoiding the need for this rule would be a good thing.
> 
> How did you test this?  The rcutorture tests will not exercise this.
> (Intentionally so, given that it can deadlock!)
> 
> > ec433f0c, 10f39bb1 and 016a8d5b just partially solve it. But rcu read site
> > is still not deadlock-immunity. And the problem described in 016a8d5b
> > is still existed(rcu_read_unlock_special() calls wake_up).
> > 
> > The problem is fixed in patch5.
> 
> This is going to require some serious review and testing.  One requirement
> is that RCU priority boosting not persist significantly beyond the
> re-enabling of interrupts associated with the irq-disabled lock.  To do
> otherwise breaks RCU priority boosting.  At first glance, the added
> set_need_resched() might handle this, but that is part of the review
> and testing required.
> 
> Steven, would you and Carsten be willing to try this and see if it
> helps with the issues you are seeing in -rt?  (My guess is "no", since
> a deadlock would block forever rather than waking up after a couple
> thousand seconds, but worth a try.)

No joy from either Steven or Carsten on the -rt hangs.

I pushed this to -rcu and ran tests.  I hit this in one of the
configurations:

[  393.641012] =================================
[  393.641012] [ INFO: inconsistent lock state ]
[  393.641012] 3.11.0-rc1+ #1 Not tainted
[  393.641012] ---------------------------------
[  393.641012] inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage.
[  393.641012] rcu_torture_rea/697 [HC1[1]:SC0[0]:HE0:SE1] takes:
[  393.641012]  (&lock->wait_lock){?.+...}, at: [<ffffffff818860f3>] rt_mutex_unlock+0x53/0x100
[  393.641012] {HARDIRQ-ON-W} state was registered at:
[  393.641012]   [<ffffffff810aecb1>] __lock_acquire+0x651/0x1d40
[  393.641012]   [<ffffffff810b0a65>] lock_acquire+0x95/0x210
[  393.641012]   [<ffffffff81886d26>] _raw_spin_lock+0x36/0x50
[  393.641012]   [<ffffffff81886329>] rt_mutex_slowlock+0x39/0x170
[  393.641012]   [<ffffffff818864ca>] rt_mutex_lock+0x2a/0x30
[  393.641012]   [<ffffffff810ebc03>] rcu_boost_kthread+0x173/0x800
[  393.641012]   [<ffffffff810759d6>] kthread+0xd6/0xe0
[  393.641012]   [<ffffffff8188f52c>] ret_from_fork+0x7c/0xb0
[  393.641012] irq event stamp: 96581116
[  393.641012] hardirqs last  enabled at (96581115): [<ffffffff81887ba0>] restore_args+0x0/0x30
[  393.641012] hardirqs last disabled at (96581116): [<ffffffff8189022a>] apic_timer_interrupt+0x6a/0x80
[  393.641012] softirqs last  enabled at (96576304): [<ffffffff81051844>] __do_softirq+0x174/0x470
[  393.641012] softirqs last disabled at (96576275): [<ffffffff81051ca6>] irq_exit+0x96/0xc0
[  393.641012] 
[  393.641012] other info that might help us debug this:
[  393.641012]  Possible unsafe locking scenario:
[  393.641012] 
[  393.641012]        CPU0
[  393.641012]        ----
[  393.641012]   lock(&lock->wait_lock);
[  393.641012]   <Interrupt>
[  393.641012]     lock(&lock->wait_lock);
[  393.641012] 
[  393.641012]  *** DEADLOCK ***
[  393.641012] 
[  393.641012] no locks held by rcu_torture_rea/697.
[  393.641012] 
[  393.641012] stack backtrace:
[  393.641012] CPU: 3 PID: 697 Comm: rcu_torture_rea Not tainted 3.11.0-rc1+ #1
[  393.641012] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2007
[  393.641012]  ffffffff8586fea0 ffff88001fcc3a78 ffffffff8187b4cb ffffffff8104a261
[  393.641012]  ffff88001e1a20c0 ffff88001fcc3ad8 ffffffff818773e4 0000000000000000
[  393.641012]  ffff880000000000 ffff880000000001 ffffffff81010a0a 0000000000000001
[  393.641012] Call Trace:
[  393.641012]  <IRQ>  [<ffffffff8187b4cb>] dump_stack+0x4f/0x84
[  393.641012]  [<ffffffff8104a261>] ? console_unlock+0x291/0x410
[  393.641012]  [<ffffffff818773e4>] print_usage_bug+0x1f5/0x206
[  393.641012]  [<ffffffff81010a0a>] ? save_stack_trace+0x2a/0x50
[  393.641012]  [<ffffffff810ae603>] mark_lock+0x283/0x2e0
[  393.641012]  [<ffffffff810ada10>] ? print_irq_inversion_bug.part.40+0x1f0/0x1f0
[  393.641012]  [<ffffffff810aef66>] __lock_acquire+0x906/0x1d40
[  393.641012]  [<ffffffff810ae94b>] ? __lock_acquire+0x2eb/0x1d40
[  393.641012]  [<ffffffff810ae94b>] ? __lock_acquire+0x2eb/0x1d40
[  393.641012]  [<ffffffff810b0a65>] lock_acquire+0x95/0x210
[  393.641012]  [<ffffffff818860f3>] ? rt_mutex_unlock+0x53/0x100
[  393.641012]  [<ffffffff81886d26>] _raw_spin_lock+0x36/0x50
[  393.641012]  [<ffffffff818860f3>] ? rt_mutex_unlock+0x53/0x100
[  393.641012]  [<ffffffff818860f3>] rt_mutex_unlock+0x53/0x100
[  393.641012]  [<ffffffff810ee3ca>] rcu_read_unlock_special+0x17a/0x2a0
[  393.641012]  [<ffffffff810ee803>] rcu_check_callbacks+0x313/0x950
[  393.641012]  [<ffffffff8107a6bd>] ? hrtimer_run_queues+0x1d/0x180
[  393.641012]  [<ffffffff810abb9d>] ? trace_hardirqs_off+0xd/0x10
[  393.641012]  [<ffffffff8105bae3>] update_process_times+0x43/0x80
[  393.641012]  [<ffffffff810a9801>] tick_sched_handle.isra.10+0x31/0x40
[  393.641012]  [<ffffffff810a98f7>] tick_sched_timer+0x47/0x70
[  393.641012]  [<ffffffff8107941c>] __run_hrtimer+0x7c/0x490
[  393.641012]  [<ffffffff810a260d>] ? ktime_get_update_offsets+0x4d/0xe0
[  393.641012]  [<ffffffff810a98b0>] ? tick_nohz_handler+0xa0/0xa0
[  393.641012]  [<ffffffff8107a017>] hrtimer_interrupt+0x107/0x260
[  393.641012]  [<ffffffff81030173>] local_apic_timer_interrupt+0x33/0x60
[  393.641012]  [<ffffffff8103059e>] smp_apic_timer_interrupt+0x3e/0x60
[  393.641012]  [<ffffffff8189022f>] apic_timer_interrupt+0x6f/0x80
[  393.641012]  <EOI>  [<ffffffff810ee250>] ? rcu_scheduler_starting+0x60/0x60
[  393.641012]  [<ffffffff81072101>] ? __rcu_read_unlock+0x91/0xa0
[  393.641012]  [<ffffffff810e80e3>] rcu_torture_read_unlock+0x33/0x70
[  393.641012]  [<ffffffff810e8f54>] rcu_torture_reader+0xe4/0x450
[  393.641012]  [<ffffffff810e92c0>] ? rcu_torture_reader+0x450/0x450
[  393.641012]  [<ffffffff810e8e70>] ? rcutorture_trace_dump+0x30/0x30
[  393.641012]  [<ffffffff810759d6>] kthread+0xd6/0xe0
[  393.641012]  [<ffffffff818874bb>] ? _raw_spin_unlock_irq+0x2b/0x60
[  393.641012]  [<ffffffff81075900>] ? flush_kthread_worker+0x130/0x130
[  393.641012]  [<ffffffff8188f52c>] ret_from_fork+0x7c/0xb0
[  393.641012]  [<ffffffff81075900>] ? flush_kthread_worker+0x130/0x130

I don't see this without your patches.

.config attached.  The other configurations completed without errors.
Short tests, 30 minutes per configuration.

Thoughts?

							Thanx, Paul