Re: [PATCH 3/5] irq_work: Implement remote queueing

[Peter Zijlstra]

On Tue, Jun 03, 2014 at 04:40:18PM +0200, Frederic Weisbecker wrote:
> irq work currently only supports local callbacks. However its code
> is mostly ready to run remote callbacks and we have some potential user.
> 
> The full nohz subsystem currently open codes its own remote irq work
> on top of the scheduler ipi when it wants a CPU to reevaluate its next
> tick. However this ad hoc solution bloats the scheduler IPI.
> 
> Lets just extend the irq work subsystem to support remote queuing on top
> of the generic SMP IPI to handle this kind of user. This shouldn't add
> noticeable overhead.
> 
> Suggested-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
> Cc: Ingo Molnar <mingo@xxxxxxxxxx>
> Cc: Kevin Hilman <khilman@xxxxxxxxxx>
> Cc: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>

Acked-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>

> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
> Cc: Viresh Kumar <viresh.kumar@xxxxxxxxxx>
> Signed-off-by: Frederic Weisbecker <fweisbec@xxxxxxxxx>
> ---
>  include/linux/irq_work.h |  2 ++
>  kernel/irq_work.c        | 22 +++++++++++++++++++++-
>  kernel/smp.c             |  4 ++++
>  3 files changed, 27 insertions(+), 1 deletion(-)

> @@ -198,6 +199,9 @@ void generic_smp_call_function_single_interrupt(void)
>  		csd->func(csd->info);
>  		csd_unlock(csd);
>  	}
> +
> +	/* Handle irq works queued remotely by irq_work_queue_on() */
> +	irq_work_run();
>  }

One could possibly extend that comment by stating that we explicitly run
the irq_work bits after the function bits, because the function bits are
typically synchronous and have people waiting on them, while not so for
the irq_works.

Attachment: pgpeoeKjRTMcv.pgp
Description: PGP signature