1 files changed, 21 insertions, 20 deletions

diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c
index ea3ca5203919..cf7b6882ec75 100644
--- a/drivers/iommu/intel/irq_remapping.c
+++ b/drivers/iommu/intel/irq_remapping.c
@@ -530,11 +530,11 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu)
 	if (!ir_table)
 		return -ENOMEM;
 
-	ir_table_base = iommu_alloc_pages_node(iommu->node, GFP_KERNEL,
-					       INTR_REMAP_PAGE_ORDER);
+	/* 1MB - maximum possible interrupt remapping table size */
+	ir_table_base =
+		iommu_alloc_pages_node_sz(iommu->node, GFP_KERNEL, SZ_1M);
 	if (!ir_table_base) {
-		pr_err("IR%d: failed to allocate pages of order %d\n",
-		       iommu->seq_id, INTR_REMAP_PAGE_ORDER);
+		pr_err("IR%d: failed to allocate 1M of pages\n", iommu->seq_id);
 		goto out_free_table;
 	}
 
@@ -612,7 +612,7 @@ out_free_fwnode:
 out_free_bitmap:
 	bitmap_free(bitmap);
 out_free_pages:
-	iommu_free_pages(ir_table_base, INTR_REMAP_PAGE_ORDER);
+	iommu_free_pages(ir_table_base);
 out_free_table:
 	kfree(ir_table);
 
@@ -633,7 +633,7 @@ static void intel_teardown_irq_remapping(struct intel_iommu *iommu)
 			irq_domain_free_fwnode(fn);
 			iommu->ir_domain = NULL;
 		}
-		iommu_free_pages(iommu->ir_table->base, INTR_REMAP_PAGE_ORDER);
+		iommu_free_pages(iommu->ir_table->base);
 		bitmap_free(iommu->ir_table->bitmap);
 		kfree(iommu->ir_table);
 		iommu->ir_table = NULL;
@@ -1287,43 +1287,44 @@ static struct irq_chip intel_ir_chip = {
 };
 
 /*
- * With posted MSIs, all vectors are multiplexed into a single notification
- * vector. Devices MSIs are then dispatched in a demux loop where
- * EOIs can be coalesced as well.
+ * With posted MSIs, the MSI vectors are multiplexed into a single notification
+ * vector, and only the notification vector is sent to the APIC IRR.  Device
+ * MSIs are then dispatched in a demux loop that harvests the MSIs from the
+ * CPU's Posted Interrupt Request bitmap.  I.e. Posted MSIs never get sent to
+ * the APIC IRR, and thus do not need an EOI.  The notification handler instead
+ * performs a single EOI after processing the PIR.
  *
- * "INTEL-IR-POST" IRQ chip does not do EOI on ACK, thus the dummy irq_ack()
- * function. Instead EOI is performed by the posted interrupt notification
- * handler.
+ * Note!  Pending SMP/CPU affinity changes, which are per MSI, must still be
+ * honored, only the APIC EOI is omitted.
  *
  * For the example below, 3 MSIs are coalesced into one CPU notification. Only
- * one apic_eoi() is needed.
+ * one apic_eoi() is needed, but each MSI needs to process pending changes to
+ * its CPU affinity.
  *
  * __sysvec_posted_msi_notification()
  *	irq_enter();
  *		handle_edge_irq()
  *			irq_chip_ack_parent()
- *				dummy(); // No EOI
+ *				irq_move_irq(); // No EOI
  *			handle_irq_event()
  *				driver_handler()
  *		handle_edge_irq()
  *			irq_chip_ack_parent()
- *				dummy(); // No EOI
+ *				irq_move_irq(); // No EOI
  *			handle_irq_event()
  *				driver_handler()
  *		handle_edge_irq()
  *			irq_chip_ack_parent()
- *				dummy(); // No EOI
+ *				irq_move_irq(); // No EOI
  *			handle_irq_event()
  *				driver_handler()
  *	apic_eoi()
  *	irq_exit()
+ *
  */
-
-static void dummy_ack(struct irq_data *d) { }
-
 static struct irq_chip intel_ir_chip_post_msi = {
 	.name			= "INTEL-IR-POST",
-	.irq_ack		= dummy_ack,
+	.irq_ack		= irq_move_irq,
 	.irq_set_affinity	= intel_ir_set_affinity,
 	.irq_compose_msi_msg	= intel_ir_compose_msi_msg,
 	.irq_set_vcpu_affinity	= intel_ir_set_vcpu_affinity,