1 files changed, 126 insertions, 24 deletions

diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c
index 011f8c4c63da..aee8f7ec40af 100644
--- a/kernel/irq/cpuhotplug.c
+++ b/kernel/irq/cpuhotplug.c
@@ -14,37 +14,99 @@
 
 #include "internals.h"
 
+/* For !GENERIC_IRQ_EFFECTIVE_AFF_MASK this looks at general affinity mask */
+static inline bool irq_needs_fixup(struct irq_data *d)
+{
+        const struct cpumask *m = irq_data_get_effective_affinity_mask(d);
+
+        return cpumask_test_cpu(smp_processor_id(), m);
+}
+
 static bool migrate_one_irq(struct irq_desc *desc)
 {
         struct irq_data *d = irq_desc_get_irq_data(desc);
-        const struct cpumask *affinity = d->common->affinity;
-        struct irq_chip *c;
-        bool ret = false;
+        struct irq_chip *chip = irq_data_get_irq_chip(d);
+        bool maskchip = !irq_can_move_pcntxt(d) && !irqd_irq_masked(d);
+        const struct cpumask *affinity;
+        bool brokeaff = false;
+        int err;
 
         /*
-         * If this is a per-CPU interrupt, or the affinity does not
-         * include this CPU, then we have nothing to do.
+         * IRQ chip might be already torn down, but the irq descriptor is
+         * still in the radix tree. Also if the chip has no affinity setter,
+         * nothing can be done here.
          */
-        if (irqd_is_per_cpu(d) ||
-            !cpumask_test_cpu(smp_processor_id(), affinity))
+        if (!chip || !chip->irq_set_affinity) {
+                pr_debug("IRQ %u: Unable to migrate away\n", d->irq);
                 return false;
+        }
+
+        /*
+         * No move required, if:
+         * - Interrupt is per cpu
+         * - Interrupt is not started
+         * - Affinity mask does not include this CPU.
+         *
+         * Note: Do not check desc->action as this might be a chained
+         * interrupt.
+         */
+        if (irqd_is_per_cpu(d) || !irqd_is_started(d) || !irq_needs_fixup(d)) {
+                /*
+                 * If an irq move is pending, abort it if the dying CPU is
+                 * the sole target.
+                 */
+                irq_fixup_move_pending(desc, false);
+                return false;
+        }
+
+        /*
+         * Complete an eventually pending irq move cleanup. If this
+         * interrupt was moved in hard irq context, then the vectors need
+         * to be cleaned up. It can't wait until this interrupt actually
+         * happens and this CPU was involved.
+         */
+        irq_force_complete_move(desc);
+
+        /*
+         * If there is a setaffinity pending, then try to reuse the pending
+         * mask, so the last change of the affinity does not get lost. If
+         * there is no move pending or the pending mask does not contain
+         * any online CPU, use the current affinity mask.
+         */
+        if (irq_fixup_move_pending(desc, true))
+                affinity = irq_desc_get_pending_mask(desc);
+        else
+                affinity = irq_data_get_affinity_mask(d);
+
+        /* Mask the chip for interrupts which cannot move in process context */
+        if (maskchip && chip->irq_mask)
+                chip->irq_mask(d);
 
         if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
+                /*
+                 * If the interrupt is managed, then shut it down and leave
+                 * the affinity untouched.
+                 */
+                if (irqd_affinity_is_managed(d)) {
+                        irqd_set_managed_shutdown(d);
+                        irq_shutdown(desc);
+                        return false;
+                }
                 affinity = cpu_online_mask;
-                ret = true;
+                brokeaff = true;
         }
 
-        c = irq_data_get_irq_chip(d);
-        if (!c->irq_set_affinity) {
-                pr_debug("IRQ%u: unable to set affinity\n", d->irq);
-        } else {
-                int r = irq_do_set_affinity(d, affinity, false);
-                if (r)
-                        pr_warn_ratelimited("IRQ%u: set affinity failed(%d).\n",
-                                            d->irq, r);
+        err = irq_do_set_affinity(d, affinity, true);
+        if (err) {
+                pr_warn_ratelimited("IRQ%u: set affinity failed(%d).\n",
+                                    d->irq, err);
+                brokeaff = false;
         }
 
-        return ret;
+        if (maskchip && chip->irq_unmask)
+                chip->irq_unmask(d);
+
+        return brokeaff;
 }
 
 /**
@@ -59,11 +121,8 @@ static bool migrate_one_irq(struct irq_desc *desc)
  */
 void irq_migrate_all_off_this_cpu(void)
 {
-        unsigned int irq;
         struct irq_desc *desc;
-        unsigned long flags;
-
-        local_irq_save(flags);
+        unsigned int irq;
 
         for_each_active_irq(irq) {
                 bool affinity_broken;
@@ -73,10 +132,53 @@ void irq_migrate_all_off_this_cpu(void)
                 affinity_broken = migrate_one_irq(desc);
                 raw_spin_unlock(&desc->lock);
 
-                if (affinity_broken)
-                        pr_warn_ratelimited("IRQ%u no longer affine to CPU%u\n",
+                if (affinity_broken) {
+                        pr_warn_ratelimited("IRQ %u: no longer affine to CPU%u\n",
                                             irq, smp_processor_id());
+                }
+        }
+}
+
+static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu)
+{
+        struct irq_data *data = irq_desc_get_irq_data(desc);
+        const struct cpumask *affinity = irq_data_get_affinity_mask(data);
+
+        if (!irqd_affinity_is_managed(data) || !desc->action ||
+            !irq_data_get_irq_chip(data) || !cpumask_test_cpu(cpu, affinity))
+                return;
+
+        if (irqd_is_managed_and_shutdown(data)) {
+                irq_startup(desc, IRQ_RESEND, IRQ_START_COND);
+                return;
+        }
+
+        /*
+         * If the interrupt can only be directed to a single target
+         * CPU then it is already assigned to a CPU in the affinity
+         * mask. No point in trying to move it around.
+         */
+        if (!irqd_is_single_target(data))
+                irq_set_affinity_locked(data, affinity, false);
+}
+
+/**
+ * irq_affinity_online_cpu - Restore affinity for managed interrupts
+ * @cpu:        Upcoming CPU for which interrupts should be restored
+ */
+int irq_affinity_online_cpu(unsigned int cpu)
+{
+        struct irq_desc *desc;
+        unsigned int irq;
+
+        irq_lock_sparse();
+        for_each_active_irq(irq) {
+                desc = irq_to_desc(irq);
+                raw_spin_lock_irq(&desc->lock);
+                irq_restore_affinity_of_irq(desc, cpu);
+                raw_spin_unlock_irq(&desc->lock);
         }
+        irq_unlock_sparse();
 
-        local_irq_restore(flags);
+        return 0;
 }