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

Groups > linux.kernel > #1618968

Re: [PATCH 6/5]rcu/tracing: Add rcu_disabled to denote when rcu_irq_enter() will not work

Show all headers | View raw

On Fri, Apr 07, 2017 at 12:44:40PM -0400, Steven Rostedt wrote:
> On Fri, 7 Apr 2017 09:42:20 -0700
> "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> wrote:
> 
> > On Fri, Apr 07, 2017 at 12:35:16PM -0400, Steven Rostedt wrote:
> > > From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
> > > 
> > > Tracing uses rcu_irq_enter() as a way to make sure that RCU is watching when
> > > it needs to use rcu_read_lock() and friends. This is because tracing can
> > > happen as RCU is about to enter user space, or about to go idle, and RCU
> > > does not watch for RCU read side critical sections as it makes the
> > > transition.
> > > 
> > > There is a small location within the RCU infrastructure that rcu_irq_enter()
> > > itself will not work. If tracing were to occur in that section it will break
> > > if it tries to use rcu_irq_enter().
> > > 
> > > Originally, this happens with the stack_tracer, because it will call
> > > save_stack_trace when it encounters stack usage that is greater than any
> > > stack usage it had encountered previously. There was a case where that
> > > happened in the RCU section where rcu_irq_enter() did not work, and lockdep
> > > complained loudly about it. To fix it, stack tracing added a call to be
> > > disabled and RCU would disable stack tracing during the critical section
> > > that rcu_irq_enter() was inoperable. This solution worked, but there are
> > > other cases that use rcu_irq_enter() and it would be a good idea to let RCU
> > > give a way to let others know that rcu_irq_enter() will not work. For
> > > example, in trace events.
> > > 
> > > Another helpful aspect of this change is that it also moves the per cpu
> > > variable called in the RCU critical section into a cache locale along with
> > > other RCU per cpu variables used in that same location.
> > > 
> > > I'm keeping the stack_trace_disable() code, as that still could be used in
> > > the future by places that really need to disable it. And since it's only a
> > > static inline, it wont take up any kernel text if it is not used.
> > > 
> > > Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>  
> > 
> > Looks better, especially __this_cpu_inc() and __this_cpu_dec().
> > 
> > How about rcu_irq_enter_disabled instead of rcu_disabled?  We aren't
> > really disabling all of RCU.  ;-)
> 
> OK, I'll make the update and send a 6.1 (and also a new 7/5)!

So the ex-Borg member was really 9 of 7 rather than 7 of 9, then?  ;-)

							Thanx, Paul

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

Thread

[PATCH 0/5 v2] tracing: Add usecase of synchronize_rcu_tasks() and stack_tracer_disable() Steven Rostedt <rostedt@goodmis.org> - 2017-04-07 16:10 +0200
  [PATCH 1/5 v2] ftrace: Add use of synchronize_rcu_tasks() with dynamic trampolines Steven Rostedt <rostedt@goodmis.org> - 2017-04-07 16:10 +0200
  [PATCH 3/5 v2] tracing: Add stack_tracer_disable/enable() functions Steven Rostedt <rostedt@goodmis.org> - 2017-04-07 16:10 +0200
    [PATCH 3/5 v2.1] tracing: Add stack_tracer_disable/enable()  functions Steven Rostedt <rostedt@goodmis.org> - 2017-04-07 16:30 +0200
    Re: [PATCH 3/5 v2] tracing: Add stack_tracer_disable/enable()  functions Steven Rostedt <rostedt@goodmis.org> - 2017-04-07 16:30 +0200
  Re: [PATCH 0/5 v2] tracing: Add usecase of synchronize_rcu_tasks()  and stack_tracer_disable() "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-04-07 16:50 +0200
    Re: [PATCH 0/5 v2] tracing: Add usecase of synchronize_rcu_tasks()  and stack_tracer_disable() Steven Rostedt <rostedt@goodmis.org> - 2017-04-07 17:10 +0200
      Re: [PATCH 0/5 v2] tracing: Add usecase of synchronize_rcu_tasks()  and stack_tracer_disable() "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-04-07 17:20 +0200
        Re: [PATCH 0/5 v2] tracing: Add usecase of synchronize_rcu_tasks()  and stack_tracer_disable() Steven Rostedt <rostedt@goodmis.org> - 2017-04-07 17:30 +0200
  [PATCH 6/5]rcu/tracing: Add rcu_disabled to denote when  rcu_irq_enter() will not work Steven Rostedt <rostedt@goodmis.org> - 2017-04-07 18:40 +0200
    Re: [PATCH 6/5]rcu/tracing: Add rcu_disabled to denote when  rcu_irq_enter() will not work "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-04-07 18:50 +0200
      Re: [PATCH 6/5]rcu/tracing: Add rcu_disabled to denote when  rcu_irq_enter() will not work Steven Rostedt <rostedt@goodmis.org> - 2017-04-07 18:50 +0200
        Re: [PATCH 6/5]rcu/tracing: Add rcu_disabled to denote when  rcu_irq_enter() will not work "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-04-07 19:00 +0200
      [PATCH 6/5 v2] rcu/tracing: Add rcu_disabled to denote when  rcu_irq_enter() will not work Steven Rostedt <rostedt@goodmis.org> - 2017-04-07 19:10 +0200
        Re: [PATCH 6/5 v2] rcu/tracing: Add rcu_disabled to denote when  rcu_irq_enter() will not work "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-04-07 19:20 +0200
  [PATCH 7/5] tracing: Make sure rcu_irq_enter() can work for  trace_*_rcuidle() trace events Steven Rostedt <rostedt@goodmis.org> - 2017-04-07 19:10 +0200
    Re: [PATCH 7/5] tracing: Make sure rcu_irq_enter() can work for  trace_*_rcuidle() trace events "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-04-07 19:20 +0200
    Re: [PATCH 7/5] tracing: Make sure rcu_irq_enter() can work for  trace_*_rcuidle() trace events Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2017-04-07 19:20 +0200
      Re: [PATCH 7/5] tracing: Make sure rcu_irq_enter() can work for  trace_*_rcuidle() trace events Steven Rostedt <rostedt@goodmis.org> - 2017-04-07 19:30 +0200
        Re: [PATCH 7/5] tracing: Make sure rcu_irq_enter() can work for  trace_*_rcuidle() trace events Steven Rostedt <rostedt@goodmis.org> - 2017-04-07 19:40 +0200
        Re: [PATCH 7/5] tracing: Make sure rcu_irq_enter() can work for  trace_*_rcuidle() trace events Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2017-04-07 19:50 +0200
          Re: [PATCH 7/5] tracing: Make sure rcu_irq_enter() can work for  trace_*_rcuidle() trace events Steven Rostedt <rostedt@goodmis.org> - 2017-04-07 20:00 +0200
          [PATCH 7/5 v3] tracing: Make sure rcu_irq_enter() can work for  trace_*_rcuidle() trace events Steven Rostedt <rostedt@goodmis.org> - 2017-04-07 20:20 +0200
            Re: [PATCH 7/5 v3] tracing: Make sure rcu_irq_enter() can work for  trace_*_rcuidle() trace events Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2017-04-07 20:20 +0200
              Re: [PATCH 7/5 v4] tracing: Make sure rcu_irq_enter() can work for  trace_*_rcuidle() trace events Steven Rostedt <rostedt@goodmis.org> - 2017-04-07 21:50 +0200
              [PATCH 7/5 v4] tracing: Make sure rcu_irq_enter() can work for  trace_*_rcuidle() trace events Steven Rostedt <rostedt@goodmis.org> - 2017-04-07 21:50 +0200
      Re: [PATCH 7/5] tracing: Make sure rcu_irq_enter() can work for  trace_*_rcuidle() trace events Steven Rostedt <rostedt@goodmis.org> - 2017-04-07 19:30 +0200
      [PATCH 7/5 v2] tracing: Make sure rcu_irq_enter() can work for  trace_*_rcuidle() trace events Steven Rostedt <rostedt@goodmis.org> - 2017-04-07 19:50 +0200

csiph-web