Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1340498

Re: Interesting csd deadlock on ARC

Show all headers | View raw

>> What I actually meant was is it OK for irq_work_queue_on() to be called locally
>> (is this a sched bug/optimization(. Further if it is OK to be called, does it need
>> to do behave more like irq_work_queue() i.e. call arch_irq_work_raise() or
>> arch_send_call_function_single_ipi() is expected to handle sending IPI to self !
> 
> Right, so I'm not actually sure we started out with this requirement.
> But you're not the first to run into this, see:
> 
>   lkml.kernel.org/r/CAJZ5v0gLankSuziQq25qTCyNqeOX43yD9jnJu_XXwbdyajfmKg@mail.gmail.com

Thx for the link, very helpful. I've posted fix for ARC which uses software
interrupt and is thus UP/SMP safe.

> Initially I think irq_work_queue_on() was only used remotely, but I
> think it makes sense to allow the current cpu, esp. since people seem to
> be using it like that.
> 
> Now the distinct difference between arch_irq_work_raise() and
> arch_send_call_function_single_ipi() is that arch_irq_work_raise()
> should be NMI-safe.

Ok - so when I implement interrupt priorities (aka NMI for ARC), this needs to be
highest.

> 
> So on x86 it has to be extra careful about the lapic state, whereas the
> regular IPI code doesn't.
> 
> I seem to have forgotten the status of NMIs on ARC, but this is
> something to make a note of.

Not had a chance to go back to it since we last discussed.
I've just been swamped with bug fixing like this one :-(

Thx,
-Vineet

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

Interesting csd deadlock on ARC Vineet Gupta <Vineet.Gupta1@synopsys.com> - 2016-02-19 07:50 +0100
  Re: Interesting csd deadlock on ARC Vineet Gupta <Vineet.Gupta1@synopsys.com> - 2016-02-23 06:30 +0100
    Re: Interesting csd deadlock on ARC Peter Zijlstra <peterz@infradead.org> - 2016-02-23 11:00 +0100
      Re: Interesting csd deadlock on ARC Vineet Gupta <Vineet.Gupta1@synopsys.com> - 2016-02-23 11:30 +0100
        Re: Interesting csd deadlock on ARC Peter Zijlstra <peterz@infradead.org> - 2016-02-23 11:50 +0100
          RE: Interesting csd deadlock on ARC Noam Camus <noamca@mellanox.com> - 2016-02-23 13:40 +0100
            Re: Interesting csd deadlock on ARC Vineet Gupta <Vineet.Gupta1@synopsys.com> - 2016-02-24 05:50 +0100
      Re: Interesting csd deadlock on ARC Vineet Gupta <Vineet.Gupta1@synopsys.com> - 2016-02-24 06:00 +0100
        Re: Interesting csd deadlock on ARC Peter Zijlstra <peterz@infradead.org> - 2016-02-25 15:10 +0100
          Re: Interesting csd deadlock on ARC Vineet Gupta <Vineet.Gupta1@synopsys.com> - 2016-02-25 15:30 +0100
            Re: Interesting csd deadlock on ARC Russell King - ARM Linux <linux@arm.linux.org.uk> - 2016-02-25 15:40 +0100
              Re: Interesting csd deadlock on ARC Vineet Gupta <vgupta@synopsys.com> - 2016-02-25 17:00 +0100

csiph-web