Messages in this thread | | | Date | Mon, 26 May 2014 18:50:41 +0200 | From | Frederic Weisbecker <> | Subject | Re: [PATCH 3/5] irq_work: Implement remote queueing |
| |
On Mon, May 26, 2014 at 06:02:24PM +0200, Peter Zijlstra wrote: > On Sun, May 25, 2014 at 04:29:49PM +0200, Frederic Weisbecker wrote: > > +bool irq_work_queue_on(struct irq_work *work, int cpu) > > +{ > > + /* Only queue if not already pending */ > > + if (!irq_work_claim(work)) > > + return false; > > + > > + /* All work should have been flushed before going offline */ > > + WARN_ON_ONCE(cpu_is_offline(cpu)); > WARN_ON_ONCE(in_nmi());
But it's actually NMI safe, isn't it?
> > > Also, I would do both these checks before the claim thing.
Right, I'll move the check.
> > > + > > + if (llist_add(&work->llnode, &per_cpu(raised_list, cpu))) > > + native_send_call_func_single_ipi(cpu); > > + > > + return true; > > +} > > +EXPORT_SYMBOL_GPL(irq_work_queue_on); > >
| |