Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1696635

Re: [PATCH tip/core/rcu 02/15] rcu: Use timer as backstop for NOCB deferred wakeups

Show all headers | View raw

On Tue, 25 Jul 2017 12:18:14 -0700
"Paul E. McKenney" <paulmck@linux.vnet.ibm.com> wrote:

> On Tue, Jul 25, 2017 at 02:12:20PM -0400, Steven Rostedt wrote:
> > On Mon, 24 Jul 2017 14:44:31 -0700
> > "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> wrote:
> >   
> > > The handling of RCU's no-CBs CPUs has a maintenance headache, namely
> > > that if call_rcu() is invoked with interrupts disabled, the rcuo kthread
> > > wakeup must be defered to a point where we can be sure that scheduler
> > > locks are not held.  Of course, there are a lot of code paths leading
> > > from an interrupts-disabled invocation of call_rcu(), and missing any
> > > one of these can result in excessive callback-invocation latency, and
> > > potentially even system hangs.  
> > 
> > What about using irq_work? That's what perf and ftrace use for such a
> > case.  
> 
> I hadn't looked at irq_work before, thank you for the pointer!
> 
> I nevertheless believe that timers work better in this particular case
> because they can be cancelled (which appears to be the common case), they

Is the common case here that it doesn't trigger? That is, the
del_timer() will be called?

> normally are not at all time-critical, and because running in softirq
> is just fine -- no need to run out of the scheduling-clock interrupt.

irq_work doesn't always use the scheduling clock. IIRC, it will simply
trigger a interrupt (if the arch supports it), and the work will be
done when interrupts are enabled (the interrupt that will do the work
will trigger)

> 
> Seem reasonable?

Don't know. With irq_work, you just call it and forget about it. No
need to mod or del timers.

-- Steve

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[PATCH tip/core/rcu 0/15] General fixes "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-07-24 23:50 +0200
  [PATCH tip/core/rcu 04/15] rcu: Create reasonable API for do_exit() TASKS_RCU processing "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-07-24 23:50 +0200
  [PATCH tip/core/rcu 09/15] rcu: use idle versions of swait to make idle-hack clear "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-07-24 23:50 +0200
  [PATCH tip/core/rcu 02/15] rcu: Use timer as backstop for NOCB deferred wakeups "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-07-24 23:50 +0200
    Re: [PATCH tip/core/rcu 02/15] rcu: Use timer as backstop for NOCB  deferred wakeups Steven Rostedt <rostedt@goodmis.org> - 2017-07-25 20:20 +0200
      Re: [PATCH tip/core/rcu 02/15] rcu: Use timer as backstop for NOCB  deferred wakeups "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-07-25 21:20 +0200
        Re: [PATCH tip/core/rcu 02/15] rcu: Use timer as backstop for NOCB  deferred wakeups Steven Rostedt <rostedt@goodmis.org> - 2017-07-26 00:20 +0200
          Re: [PATCH tip/core/rcu 02/15] rcu: Use timer as backstop for NOCB  deferred wakeups "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-07-26 02:10 +0200
            Re: [PATCH tip/core/rcu 02/15] rcu: Use timer as backstop for NOCB  deferred wakeups Steven Rostedt <rostedt@goodmis.org> - 2017-07-26 23:20 +0200
              Re: [PATCH tip/core/rcu 02/15] rcu: Use timer as backstop for NOCB  deferred wakeups "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-07-26 23:50 +0200
                Re: [PATCH tip/core/rcu 02/15] rcu: Use timer as backstop for NOCB  deferred wakeups Steven Rostedt <rostedt@goodmis.org> - 2017-07-27 01:10 +0200
                Re: [PATCH tip/core/rcu 02/15] rcu: Use timer as backstop for NOCB  deferred wakeups "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-07-27 19:40 +0200
  [PATCH tip/core/rcu 10/15] rcu: Add TPS() protection for _rcu_barrier_trace strings "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-07-24 23:50 +0200
    Re: [PATCH tip/core/rcu 10/15] rcu: Add TPS() protection for  _rcu_barrier_trace strings Steven Rostedt <rostedt@goodmis.org> - 2017-07-28 03:50 +0200
  [PATCH tip/core/rcu 14/15] rcu: Add warning to rcu_idle_enter() for irqs enabled "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-07-24 23:50 +0200
  [PATCH tip/core/rcu 01/15] sched,rcu: Make cond_resched() provide RCU quiescent state "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-07-24 23:50 +0200
  [PATCH tip/core/rcu 08/15] swait: add idle variants which don't contribute to load average "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-07-24 23:50 +0200
  [PATCH tip/core/rcu 15/15] rcu: Remove exports from rcu_idle_exit() and rcu_idle_enter() "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-07-24 23:50 +0200
  [PATCH tip/core/rcu 03/15] rcu: Drive TASKS_RCU directly off of PREEMPT "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-07-24 23:50 +0200
    Re: [PATCH tip/core/rcu 03/15] rcu: Drive TASKS_RCU directly off of  PREEMPT Steven Rostedt <rostedt@goodmis.org> - 2017-07-25 20:20 +0200
      Re: [PATCH tip/core/rcu 03/15] rcu: Drive TASKS_RCU directly off of  PREEMPT "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-07-25 21:20 +0200
  [PATCH tip/core/rcu 12/15] rcu: Add assertions verifying blocked-tasks list "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-07-24 23:50 +0200
  [PATCH tip/core/rcu 05/15] rcu: Add TPS() to event-traced strings "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-07-24 23:50 +0200
    Re: [PATCH tip/core/rcu 05/15] rcu: Add TPS() to event-traced  strings Steven Rostedt <rostedt@goodmis.org> - 2017-07-28 03:40 +0200
  [PATCH tip/core/rcu 06/15] rcu: Move rcu.h to new trivial-function style "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-07-24 23:50 +0200

csiph-web