On Tue, Feb 26, 2013 at 07:55:06PM +0100, Thomas Gleixner wrote:
> On Tue, 26 Feb 2013, Paul E. McKenney wrote:
> > On Tue, Feb 26, 2013 at 04:14:43PM +0100, Thomas Gleixner wrote:
> > >
> > > On Tue, 26 Feb 2013, Frederic Weisbecker wrote:
> > > > And what do you think about Linus's idea to move
On Tue, 26 Feb 2013, Paul E. McKenney wrote:
> On Tue, Feb 26, 2013 at 04:14:43PM +0100, Thomas Gleixner wrote:
> >
> > On Tue, 26 Feb 2013, Frederic Weisbecker wrote:
> > > And what do you think about Linus's idea to move tick_nohz_irq_exit()
> > > to do_softirq()?
> > > This sounds feasible and
On Tue, Feb 26, 2013 at 04:14:43PM +0100, Thomas Gleixner wrote:
>
> On Tue, 26 Feb 2013, Frederic Weisbecker wrote:
>
> > 2013/2/26 Thomas Gleixner :
> > > On Fri, 22 Feb 2013, Linus Torvalds wrote:
> > >> On Fri, Feb 22, 2013 at 7:06 AM, Thomas Gleixner
> > >> wrote:
> > >> >>
> > >> >> I pre
2013/2/26 Thomas Gleixner :
>
> On Tue, 26 Feb 2013, Frederic Weisbecker wrote:
>
>> 2013/2/26 Thomas Gleixner :
>> > On Fri, 22 Feb 2013, Linus Torvalds wrote:
>> >> On Fri, Feb 22, 2013 at 7:06 AM, Thomas Gleixner
>> >> wrote:
>> >> >>
>> >> >> I prefer to let you guys have the final word on th
On Tue, 26 Feb 2013, Frederic Weisbecker wrote:
> 2013/2/26 Thomas Gleixner :
> > On Fri, 22 Feb 2013, Linus Torvalds wrote:
> >> On Fri, Feb 22, 2013 at 7:06 AM, Thomas Gleixner
> >> wrote:
> >> >>
> >> >> I prefer to let you guys have the final word on this patch. Whether you
> >> >> apply it
2013/2/26 Thomas Gleixner :
> On Fri, 22 Feb 2013, Linus Torvalds wrote:
>> On Fri, Feb 22, 2013 at 7:06 AM, Thomas Gleixner wrote:
>> >>
>> >> I prefer to let you guys have the final word on this patch. Whether you
>> >> apply it or not, I fear I'll never be entirely happy either way :)
>> >> Tha
On Fri, 22 Feb 2013, Linus Torvalds wrote:
> On Fri, Feb 22, 2013 at 7:06 AM, Thomas Gleixner wrote:
> >>
> >> I prefer to let you guys have the final word on this patch. Whether you
> >> apply it or not, I fear I'll never be entirely happy either way :)
> >> That's the sad fate of dealing with ci
On Sat, Feb 23, 2013 at 10:21 AM, Frederic Weisbecker
wrote:
>
> But tick_nohz_irq_exit() may trigger the timer softirq itself.
Suggestion: merge it with the whole softirq handler.
The softirq code *already* knows about the whole "oops, one softirq
may trigger another" issue, and has a loop - wi
On Fri, Feb 22, 2013 at 01:08:17PM -0800, Linus Torvalds wrote:
> On Fri, Feb 22, 2013 at 7:06 AM, Thomas Gleixner wrote:
> >>
> >> I prefer to let you guys have the final word on this patch. Whether you
> >> apply it or not, I fear I'll never be entirely happy either way :)
> >> That's the sad fa
On Fri, Feb 22, 2013 at 7:06 AM, Thomas Gleixner wrote:
>>
>> I prefer to let you guys have the final word on this patch. Whether you
>> apply it or not, I fear I'll never be entirely happy either way :)
>> That's the sad fate of dealing with circular dependencies...
>
> plus the butt ugly softirq
On Fri, 22 Feb 2013, Frederic Weisbecker wrote:
> On Fri, Feb 22, 2013 at 03:33:51PM +0100, Thomas Gleixner wrote:
> > The minimal extra check at the end of irq_exit() is way better than
> > any other special cased workaround and the softirq stuff is really the
> > only thing which needs to be take
On Fri, Feb 22, 2013 at 03:33:51PM +0100, Thomas Gleixner wrote:
> On Fri, 22 Feb 2013, Frederic Weisbecker wrote:
> > The irq code is run under HARDIRQ_OFFSET preempt offset until
> > we reach the softirq code. Then it's substracted, leaving the
> > preempt count to 0, whether we have pending soft
On Fri, 22 Feb 2013, Frederic Weisbecker wrote:
> The irq code is run under HARDIRQ_OFFSET preempt offset until
> we reach the softirq code. Then it's substracted, leaving the
> preempt count to 0, whether we have pending softirqs or not.
>
> Afterward, if we have softirqs to run, we'll run them u
The irq code is run under HARDIRQ_OFFSET preempt offset until
we reach the softirq code. Then it's substracted, leaving the
preempt count to 0, whether we have pending softirqs or not.
Afterward, if we have softirqs to run, we'll run them under
the SOFTIRQ_OFFSET then set the preempt offset back t
14 matches
Mail list logo
