3 files changed, 69 insertions, 0 deletions

diff --git a/drivers/iommu/intel_intr_remapping.c b/drivers/iommu/intel_intr_remapping.c
index f495eba4b6ab..25372c1f3c8c 100644
--- a/drivers/iommu/intel_intr_remapping.c
+++ b/drivers/iommu/intel_intr_remapping.c
@@ -901,6 +901,59 @@ static int intel_setup_ioapic_entry(int irq,
 	return 0;
 }
 
+/*
+ * Migrate the IO-APIC irq in the presence of intr-remapping.
+ *
+ * For both level and edge triggered, irq migration is a simple atomic
+ * update(of vector and cpu destination) of IRTE and flush the hardware cache.
+ *
+ * For level triggered, we eliminate the io-apic RTE modification (with the
+ * updated vector information), by using a virtual vector (io-apic pin number).
+ * Real vector that is used for interrupting cpu will be coming from
+ * the interrupt-remapping table entry.
+ *
+ * As the migration is a simple atomic update of IRTE, the same mechanism
+ * is used to migrate MSI irq's in the presence of interrupt-remapping.
+ */
+static int
+intel_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
+			  bool force)
+{
+	struct irq_cfg *cfg = data->chip_data;
+	unsigned int dest, irq = data->irq;
+	struct irte irte;
+
+	if (!cpumask_intersects(mask, cpu_online_mask))
+		return -EINVAL;
+
+	if (get_irte(irq, &irte))
+		return -EBUSY;
+
+	if (assign_irq_vector(irq, cfg, mask))
+		return -EBUSY;
+
+	dest = apic->cpu_mask_to_apicid_and(cfg->domain, mask);
+
+	irte.vector = cfg->vector;
+	irte.dest_id = IRTE_DEST(dest);
+
+	/*
+	 * Atomically updates the IRTE with the new destination, vector
+	 * and flushes the interrupt entry cache.
+	 */
+	modify_irte(irq, &irte);
+
+	/*
+	 * After this point, all the interrupts will start arriving
+	 * at the new destination. So, time to cleanup the previous
+	 * vector allocation.
+	 */
+	if (cfg->move_in_progress)
+		send_cleanup_vector(cfg);
+
+	cpumask_copy(data->affinity, mask);
+	return 0;
+}
 
 struct irq_remap_ops intel_irq_remap_ops = {
 	.supported		= intel_intr_remapping_supported,
@@ -910,4 +963,5 @@ struct irq_remap_ops intel_irq_remap_ops = {
 	.hardware_reenable	= reenable_intr_remapping,
 	.enable_faulting	= enable_drhd_fault_handling,
 	.setup_ioapic_entry	= intel_setup_ioapic_entry,
+	.set_affinity		= intel_ioapic_set_affinity,
 };
diff --git a/drivers/iommu/intr_remapping.c b/drivers/iommu/intr_remapping.c
index 739148ab2538..2f4f27ffb861 100644
--- a/drivers/iommu/intr_remapping.c
+++ b/drivers/iommu/intr_remapping.c
@@ -110,3 +110,12 @@ int intr_setup_ioapic_entry(int irq,
 	return remap_ops->setup_ioapic_entry(irq, entry, destination,
 					     vector, attr);
 }
+
+int intr_set_affinity(struct irq_data *data, const struct cpumask *mask,
+		      bool force)
+{
+	if (!remap_ops || !remap_ops->set_affinity)
+		return 0;
+
+	return remap_ops->set_affinity(data, mask, force);
+}
diff --git a/drivers/iommu/intr_remapping.h b/drivers/iommu/intr_remapping.h
index e8994f2b3bbe..e0bc6e0ba1fb 100644
--- a/drivers/iommu/intr_remapping.h
+++ b/drivers/iommu/intr_remapping.h
@@ -26,6 +26,8 @@
 
 struct IO_APIC_route_entry;
 struct io_apic_irq_attr;
+struct irq_data;
+struct cpumask;
 
 extern int disable_intremap;
 extern int disable_sourceid_checking;
@@ -54,6 +56,10 @@ struct irq_remap_ops {
 	int (*setup_ioapic_entry)(int irq, struct IO_APIC_route_entry *,
 				  unsigned int, int,
 				  struct io_apic_irq_attr *);
+
+	/* Set the CPU affinity of a remapped interrupt */
+	int (*set_affinity)(struct irq_data *data, const struct cpumask *mask,
+			    bool force);
 };
 
 extern struct irq_remap_ops intel_irq_remap_ops;