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 revaluate 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 <[email protected]> Cc: Andrew Morton <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Kevin Hilman <[email protected]> Cc: Paul E. McKenney <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Thomas Gleixner <[email protected]> Cc: Viresh Kumar <[email protected]> Signed-off-by: Frederic Weisbecker <[email protected]> --- include/linux/irq_work.h | 2 ++ kernel/irq_work.c | 17 +++++++++++++++++ kernel/smp.c | 3 +++ 3 files changed, 22 insertions(+) diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index 429b1ba..511e7f7 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -33,6 +33,8 @@ void init_irq_work(struct irq_work *work, void (*func)(struct irq_work *)) #define DEFINE_IRQ_WORK(name, _f) struct irq_work name = { .func = (_f), } bool irq_work_queue(struct irq_work *work); +bool irq_work_queue_on(struct irq_work *work, int cpu); + void irq_work_run(void); void irq_work_run_tick(void); void irq_work_sync(struct irq_work *work); diff --git a/kernel/irq_work.c b/kernel/irq_work.c index 292a9ac..98dab29 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -66,6 +66,23 @@ bool __weak arch_irq_work_can_raise(void) * * Can be re-enqueued while the callback is still in progress. */ +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(work->flags & IRQ_WORK_LAZY); + + 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); + bool irq_work_queue(struct irq_work *work) { unsigned long flags; diff --git a/kernel/smp.c b/kernel/smp.c index 06d574e..f5edb96 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -3,6 +3,7 @@ * * (C) Jens Axboe <[email protected]> 2008 */ +#include <linux/irq_work.h> #include <linux/rcupdate.h> #include <linux/rculist.h> #include <linux/kernel.h> @@ -198,6 +199,8 @@ void generic_smp_call_function_single_interrupt(void) csd->func(csd->info); csd_unlock(csd); } + + irq_work_run(); } /* -- 1.8.3.1 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
