| Date | Mon, 9 Sep 2013 18:21:56 +0200 | From | Peter Zijlstra <> | Subject | Re: [PATCH] rcu: Is it safe to enter an RCU read-side critical section? |
| |
On Mon, Sep 09, 2013 at 04:40:38PM +0200, Frederic Weisbecker wrote: > > If the state migrates with a task from one CPU to another, it's a task > > state. > > This applies to preempt_count as well.
This is in fact true. Its something I'd like to cure, but currently the PREEMPT_ACTIVE state makes this so.
Hence the need to save/restore the per-cpu preempt state in the per-cpu preempt_count patches.
|