Merge branch 'remotes/lorenzo/pci/vmd'

- Program IRTE with Requester ID of VMD endpoint, not child device (Jon
  Derrick)

- Disable VMD MSI-X remapping when possible so children can use more MSI-X
  vectors (Jon Derrick)

* remotes/lorenzo/pci/vmd:
  PCI: vmd: Disable MSI-X remapping when possible
  iommu/vt-d: Use Real PCI DMA device for IRTE

2 files changed, 53 insertions, 13 deletions

diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c
index 611ef5243cb6..75429a5373ec 100644
--- a/drivers/iommu/intel/irq_remapping.c
+++ b/drivers/iommu/intel/irq_remapping.c
@@ -1280,7 +1280,8 @@ static void intel_irq_remapping_prepare_irte(struct intel_ir_data *data,
 		break;
 	case X86_IRQ_ALLOC_TYPE_PCI_MSI:
 	case X86_IRQ_ALLOC_TYPE_PCI_MSIX:
-		set_msi_sid(irte, msi_desc_to_pci_dev(info->desc));
+		set_msi_sid(irte,
+			    pci_real_dma_dev(msi_desc_to_pci_dev(info->desc)));
 		break;
 	default:
 		BUG_ON(1);
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 5e80f28f0119..e3fcdfec58b3 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -28,6 +28,7 @@
 #define BUS_RESTRICT_CAP(vmcap)	(vmcap & 0x1)
 #define PCI_REG_VMCONFIG	0x44
 #define BUS_RESTRICT_CFG(vmcfg)	((vmcfg >> 8) & 0x3)
+#define VMCONFIG_MSI_REMAP	0x2
 #define PCI_REG_VMLOCK		0x70
 #define MB2_SHADOW_EN(vmlock)	(vmlock & 0x2)
 
@@ -59,6 +60,13 @@ enum vmd_features {
 	 * be used for MSI remapping
 	 */
 	VMD_FEAT_OFFSET_FIRST_VECTOR		= (1 << 3),
+
+	/*
+	 * Device can bypass remapping MSI-X transactions into its MSI-X table,
+	 * avoiding the requirement of a VMD MSI domain for child device
+	 * interrupt handling.
+	 */
+	VMD_FEAT_CAN_BYPASS_MSI_REMAP		= (1 << 4),
 };
 
 /*
@@ -306,6 +314,16 @@ static struct msi_domain_info vmd_msi_domain_info = {
 	.chip		= &vmd_msi_controller,
 };
 
+static void vmd_set_msi_remapping(struct vmd_dev *vmd, bool enable)
+{
+	u16 reg;
+
+	pci_read_config_word(vmd->dev, PCI_REG_VMCONFIG, &reg);
+	reg = enable ? (reg & ~VMCONFIG_MSI_REMAP) :
+		       (reg | VMCONFIG_MSI_REMAP);
+	pci_write_config_word(vmd->dev, PCI_REG_VMCONFIG, reg);
+}
+
 static int vmd_create_irq_domain(struct vmd_dev *vmd)
 {
 	struct fwnode_handle *fn;
@@ -325,6 +343,13 @@ static int vmd_create_irq_domain(struct vmd_dev *vmd)
 
 static void vmd_remove_irq_domain(struct vmd_dev *vmd)
 {
+	/*
+	 * Some production BIOS won't enable remapping between soft reboots.
+	 * Ensure remapping is restored before unloading the driver.
+	 */
+	if (!vmd->msix_count)
+		vmd_set_msi_remapping(vmd, true);
+
 	if (vmd->irq_domain) {
 		struct fwnode_handle *fn = vmd->irq_domain->fwnode;
 
@@ -679,15 +704,32 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features)
 
 	sd->node = pcibus_to_node(vmd->dev->bus);
 
-	ret = vmd_create_irq_domain(vmd);
-	if (ret)
-		return ret;
-
 	/*
-	 * Override the irq domain bus token so the domain can be distinguished
-	 * from a regular PCI/MSI domain.
+	 * Currently MSI remapping must be enabled in guest passthrough mode
+	 * due to some missing interrupt remapping plumbing. This is probably
+	 * acceptable because the guest is usually CPU-limited and MSI
+	 * remapping doesn't become a performance bottleneck.
 	 */
-	irq_domain_update_bus_token(vmd->irq_domain, DOMAIN_BUS_VMD_MSI);
+	if (!(features & VMD_FEAT_CAN_BYPASS_MSI_REMAP) ||
+	    offset[0] || offset[1]) {
+		ret = vmd_alloc_irqs(vmd);
+		if (ret)
+			return ret;
+
+		vmd_set_msi_remapping(vmd, true);
+
+		ret = vmd_create_irq_domain(vmd);
+		if (ret)
+			return ret;
+
+		/*
+		 * Override the IRQ domain bus token so the domain can be
+		 * distinguished from a regular PCI/MSI domain.
+		 */
+		irq_domain_update_bus_token(vmd->irq_domain, DOMAIN_BUS_VMD_MSI);
+	} else {
+		vmd_set_msi_remapping(vmd, false);
+	}
 
 	pci_add_resource(&resources, &vmd->resources[0]);
 	pci_add_resource_offset(&resources, &vmd->resources[1], offset[0]);
@@ -753,10 +795,6 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	if (features & VMD_FEAT_OFFSET_FIRST_VECTOR)
 		vmd->first_vec = 1;
 
-	err = vmd_alloc_irqs(vmd);
-	if (err)
-		return err;
-
 	spin_lock_init(&vmd->cfg_lock);
 	pci_set_drvdata(dev, vmd);
 	err = vmd_enable_domain(vmd, features);
@@ -825,7 +863,8 @@ static const struct pci_device_id vmd_ids[] = {
 		.driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP,},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_28C0),
 		.driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW |
-				VMD_FEAT_HAS_BUS_RESTRICTIONS,},
+				VMD_FEAT_HAS_BUS_RESTRICTIONS |
+				VMD_FEAT_CAN_BYPASS_MSI_REMAP,},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x467f),
 		.driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP |
 				VMD_FEAT_HAS_BUS_RESTRICTIONS |