Messages in this thread | | | Date | Thu, 12 Sep 2013 14:20:18 +0000 | From | Christoph Lameter <> | Subject | Re: [PATCH] rcu: Is it safe to enter an RCU read-side critical section? |
| |
On Thu, 12 Sep 2013, Ingo Molnar wrote:
> > * Christoph Lameter <cl@linux.com> wrote: > > > On Mon, 9 Sep 2013, Ingo Molnar wrote: > > > > > I saw those, he posted 'needs testing' patches. He still behaved > > > passive-aggressively, pretending that it was some difficult task to > > > perform, as if we were pulling his teeth. > > > > I need your review of those. I will rediff as soon as rc1 is out to send > > something that can be put into -next. Please tell me until then if the > > approach is ok. I dont think we can do anything in the merge window. > > The patch looked OK. Have you tested it, such as using a this_cpu op on a > PREEMPT=y kernel in a preemptible section? That should trigger the preempt > warning.
The reason that certain __this_cpu ops were converted to raw_cpu ops is because they triggered the preemption check. The test was done in a kvm environment (as evident from the description).
| |