On Tue, May 23, 2017 at 03:39:39PM -0400, Steven Rostedt wrote:
> On Mon, 22 May 2017 17:00:36 -0700
> "Paul E. McKenney" <paul...@linux.vnet.ibm.com> wrote:
>
> > >
> > > Hmmm... The goal is to make sure that any task that was preempted
> > > or running at a given point in time passes through a voluntary
> > > context switch (or userspace execution, or, ...).
> > >
> > > What is the simplest way to get this job done? To Ingo's point, I
> > > bet that there is a simpler way than the current TASKS_RCU
> > > implementation.
> > >
> > > Ingo, if I make it fit into 100 lines of code, would you be OK with
> > > it? I probably need a one-line hook at task-creation time and
> > > another at task-exit time, if that makes a difference.
> >
> > And please see below for such a patch, which does add (just barely)
> > fewer than 100 lines net.
> >
> > Unfortunately, it does not work, as I should have known ahead of time
> > from the dyntick-idle experience. Not all context switches go through
> > context_switch(). :-/
>
> Wait. What context switch doesn't go through a context switch? Or do
> you mean a user/kernel context switch?
I mean that putting printk() before and after the call to context_switch()
can show tasks switching out twice without switching in and vice versa.
No sign of lost printk()s, and I also confirmed this behavior using a
flag in task_struct.
One way that this can happen on some architectures is via the "helper"
mechanism, where the task sleeps normally, but where a later interrupt
or exception takes on its context "behind the scenes" in the arch code.
This is what messed up my attempt to use a simple interrupt-nesting
counter for RCU dynticks some years back. What I counted on there was
that the idle loop would never do that sort of thing, so I could zero
the count when entering idle from process context.
But I have not yet found a similar trick for counting voluntary
context switches.
I also tried making context_switch() look like a momentary quiescent
state, but of course that means that tasks that block forever also
block the grace period forever. At which point, I need to scan the task
list to find them. And that pretty much brings me back to the current
RCU-tasks implementation. :-/
Thanx, Paul
> -- Steve
>
> >
> > I believe this is fixable, more or less like dyntick-idle's
> > half-interrupts were fixable, but it will likely be a few days. Not
> > clear whether the result will be simpler than current TASKS_RCU, but
> > there is only one way to find out. ;-)
> >
>
