ARM: CPU hotplug: ensure we migrate all IRQs off a downed CPU

Our selection of interrupts to consider for IRQ migration is sub-
standard.  We were potentially including per-CPU interrupts in our
migration strategy, but omitting chained interrupts.  This caused
some interrupts to remain on a downed CPU.

We were also trying to migrate interrupts which were not migratable,
resulting in an OOPS.

Instead, iterate over all interrupts, skipping per-CPU interrupts
or interrupts whose affinity does not include the downed CPU, and
attempt to set the affinity for every one else if their chip
implements irq_set_affinity().

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

1 files changed, 28 insertions, 11 deletions

diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index ab63c05290e5..0f928a131af8 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -131,46 +131,63 @@ int __init arch_probe_nr_irqs(void)
 
 #ifdef CONFIG_HOTPLUG_CPU
 
-static bool migrate_one_irq(struct irq_data *d)
+static bool migrate_one_irq(struct irq_desc *desc)
 {
+        struct irq_data *d = irq_desc_get_irq_data(desc);
         const struct cpumask *affinity = d->affinity;
+        struct irq_chip *c;
         bool ret = false;
 
+        /*
+         * If this is a per-CPU interrupt, or the affinity does not
+         * include this CPU, then we have nothing to do.
+         */
+        if (irqd_is_per_cpu(d) || !cpumask_test_cpu(smp_processor_id(), affinity))
+                return false;
+
         if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
-                affinity cpu_online_mask;
+                affinity = cpu_online_mask;
                 ret = true;
         }
 
-        d->chip->irq_set_affinity(d, affinity, true);
+        c = irq_data_get_irq_chip(d);
+        if (c->irq_set_affinity)
+                c->irq_set_affinity(d, affinity, true);
+        else
+                pr_debug("IRQ%u: unable to set affinity\n", d->irq);
 
         return ret;
 }
 
 /*
- * The CPU has been marked offline.  Migrate IRQs off this CPU.  If
- * the affinity settings do not allow other CPUs, force them onto any
+ * The current CPU has been marked offline.  Migrate IRQs off this CPU.
+ * If the affinity settings do not allow other CPUs, force them onto any
  * available CPU.
+ *
+ * Note: we must iterate over all IRQs, whether they have an attached
+ * action structure or not, as we need to get chained interrupts too.
  */
 void migrate_irqs(void)
 {
-        unsigned int i, cpu = smp_processor_id();
+        unsigned int i;
         struct irq_desc *desc;
         unsigned long flags;
 
         local_irq_save(flags);
 
         for_each_irq_desc(i, desc) {
-                struct irq_data *d = &desc->irq_data;
                 bool affinity_broken = false;
 
+                if (!desc)
+                        continue;
+
                 raw_spin_lock(&desc->lock);
-                if (desc->action != NULL &&
-                    cpumask_test_cpu(smp_processor_id(), d->affinity))
-                        affinity_broken = migrate_one_irq(d);
+                affinity_broken = migrate_one_irq(desc);
                 raw_spin_unlock(&desc->lock);
 
                 if (affinity_broken && printk_ratelimit())
-                        pr_warning("IRQ%u no longer affine to CPU%u\n", i, cpu);
+                        pr_warning("IRQ%u no longer affine to CPU%u\n", i,
+                                smp_processor_id());
         }
 
         local_irq_restore(flags);