[PATCH 2/5] genirq: add flags for controlling the default threaded irq behavior

[Paolo Abeni]

A threadable irq can benefit from irq_set_affinity when running
in non threaded mode and prefer running unbounded to cpu when in
threaded mode. Setting the IRQF_TH_NO_AFFINITY flag on irq
registration allow the irq to achieve both behaviors.

A long running threaded irq can starve the system if scheduled under
SCHED_FIFO. Setting the IRQF_TH_SCHED_NORMAL flag on irq will cause
the irq thread to run by default under the SCHED_NORMAL scheduler.

Signed-off-by: Paolo Abeni <pab...@redhat.com>
Signed-off-by: Hannes Frederic Sowa <han...@stressinduktion.org>
---
 include/linux/interrupt.h |  6 ++++++
 kernel/irq/manage.c       | 17 +++++++++++------
 2 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 85d3738..33c3033 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -61,6 +61,10 @@
  *                interrupt handler after suspending interrupts. For system
  *                wakeup devices users need to implement wakeup detection in
  *                their interrupt handlers.
+ * IRQF_TH_SCHED_NORMAL - If the IRQ is threaded, it will use SCHED_NORMAL,
+ *                instead the default SCHED_FIFO scheduler
+ * IRQF_TH_NO_AFFINITY - If the IRQ is threaded, the affinity hint will not be
+ *                enforced in the IRQ thread
  */
 #define IRQF_SHARED            0x00000080
 #define IRQF_PROBE_SHARED      0x00000100
@@ -74,6 +78,8 @@
 #define IRQF_NO_THREAD         0x00010000
 #define IRQF_EARLY_RESUME      0x00020000
 #define IRQF_COND_SUSPEND      0x00040000
+#define IRQF_TH_SCHED_NORMAL   0x00080000
+#define IRQF_TH_NO_AFFINITY    0x00100000
 
 #define IRQF_TIMER             (__IRQF_TIMER | IRQF_NO_SUSPEND | 
IRQF_NO_THREAD)
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index cce4efd..d695e12 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1055,9 +1055,7 @@ static struct task_struct *
 create_irq_thread(struct irqaction *new, unsigned int irq, bool secondary)
 {
        struct task_struct *t;
-       struct sched_param param = {
-               .sched_priority = MAX_USER_RT_PRIO/2,
-       };
+       struct sched_param param;
 
        if (!secondary) {
                t = kthread_create(irq_thread, new, "irq/%d-%s", irq,
@@ -1071,7 +1069,12 @@ create_irq_thread(struct irqaction *new, unsigned int 
irq, bool secondary)
        if (IS_ERR(t))
                return t;
 
-       sched_setscheduler_nocheck(t, SCHED_FIFO, &param);
+       if (new->flags & IRQF_TH_SCHED_NORMAL) {
+               sched_setscheduler_nocheck(t, SCHED_NORMAL, &param);
+       } else {
+               param.sched_priority = MAX_USER_RT_PRIO/2;
+               sched_setscheduler_nocheck(t, SCHED_FIFO, &param);
+       }
 
        /*
         * We keep the reference to the task struct even if
@@ -1100,7 +1103,8 @@ setup_irq_thread(struct irqaction *new, unsigned int irq, 
bool secondary)
         * correct as we want the thread to move to the cpu(s)
         * on which the requesting code placed the interrupt.
         */
-       set_bit(IRQTF_AFFINITY, &new->thread_flags);
+       if (!(new->flags & IRQF_TH_NO_AFFINITY))
+               set_bit(IRQTF_AFFINITY, &new->thread_flags);
        return 0;
 }
 
@@ -1549,7 +1553,8 @@ void __irq_reconfigure_action(struct irq_desc *desc, 
struct irqaction *action,
 
        action->thread = t;
        set_bit(IRQTF_FORCED_THREAD, &action->thread_flags);
-       set_bit(IRQTF_AFFINITY, &action->thread_flags);
+       if (!(action->flags & IRQF_TH_NO_AFFINITY))
+               set_bit(IRQTF_AFFINITY, &action->thread_flags);
 
        if (!(desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE)) {
                /*
-- 
1.8.3.1