Re: [PATCH 4/4] kvm,rcu: use RCU extended quiescent state when running KVM guest

["Paul E. McKenney" <paulmck@linux.vnet.ibm.com>]

On Thu, Feb 05, 2015 at 02:02:35PM -0500, Rik van Riel wrote:
> On 02/05/2015 01:56 PM, Paul E. McKenney wrote:
> 
> > The real danger is doing neither.
> > 
> > On tick_nohz_full_cpu() CPUs, the exit-to-userspace code should invoke
> > rcu_user_enter(), which sets some per-CPU state telling RCU to ignore
> > that CPU, since it cannot possibly do host RCU read-side critical sections
> > while running a guest.
> > 
> > In contrast, a non-tick_nohz_full_cpu() CPU doesn't let RCU
> > know that it is executing in a guest or in userspace.  So the
> > rcu_virt_note_context_switch() does the notification in that case.
> 
> Looking at context_tracking.h, I see the
> function context_tracking_cpu_is_enabled().
> 
> That looks like it should do the right thing
> in this case.

Right you are -- that same check is used to guard the
context_tracking_user_enter() function's call to rcu_user_enter().

Not sure why it open-codes the check rather than invoking
context_tracking_cpu_is_enabled().  Hmmm....  One reason is that
the context_tracking_cpu_is_enabled() function isn't available in
that context, according to my compiler.  ;-)

							Thanx, Paul