Messages in this thread | | | Date | Fri, 12 Sep 2014 20:05:49 +0200 | From | Frederic Weisbecker <> | Subject | Re: [PATCH 0/8] nohz: Fix nohz kick irq work on tick v2 |
| |
On Thu, Sep 11, 2014 at 10:28:12AM +0200, Peter Zijlstra wrote: > On Wed, Sep 10, 2014 at 11:33:20PM +0200, Frederic Weisbecker wrote: > > > Frederic Weisbecker (7): > > nohz: Move nohz full init call to tick init > > irq_work: Force raised irq work to run on irq work interrupt > > x86: Tell irq work about self IPI support > > arm: Tell irq work about self IPI support > > arm64: Tell irq work about self IPI support > > nohz: Consolidate nohz full init code > > nohz: nohz full depends on irq work self IPI support > > > > Peter Zijlstra (1): > > irq_work: Introduce arch_irq_work_has_interrupt() > > Looks ok to me. > > Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Intel? :-) Wow.
Thanks a lot!
Note, I fear I'll have to turn the static_cpu_has into cpu_has. The alternatives code which initialize all static_cpu_has() things is called from check_bugs() in start_kernel() which is way after IRQs are enabled for the 1st time. irq_work_tick() has many opportunities to run in between.
| |