[PATCH RFCv2 13/13] vfio/pci: Allow preset MSI IOVAs via VFIO_IRQ_SET_ACTION_PREPARE

[Nicolin Chen <nicolinc@xxxxxxxxxx>]

Add a new VFIO_IRQ_SET_ACTION_PREPARE to set VFIO_IRQ_SET_DATA_MSI_IOVA,
giving user space an interface to forward to kernel the stage-1 IOVA (of
a 2-stage translation: IOVA->IPA->PA) for an MSI doorbell address, since
the ITS hardware needs to be programmed with the top level IOVA address,
in order to work with the IOMMU on ARM64.

Signed-off-by: Nicolin Chen <nicolinc@xxxxxxxxxx>
---
 include/uapi/linux/vfio.h         |  8 ++++--
 drivers/vfio/pci/vfio_pci_intrs.c | 46 +++++++++++++++++++++++++++++++
 drivers/vfio/vfio_main.c          |  3 ++
 3 files changed, 55 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index c8dbf8219c4f..85095e59a3c6 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -590,6 +590,8 @@ struct vfio_irq_set {
 #define VFIO_IRQ_SET_ACTION_MASK	(1 << 3) /* Mask interrupt */
 #define VFIO_IRQ_SET_ACTION_UNMASK	(1 << 4) /* Unmask interrupt */
 #define VFIO_IRQ_SET_ACTION_TRIGGER	(1 << 5) /* Trigger interrupt */
+#define VFIO_IRQ_SET_DATA_MSI_IOVA	(1 << 6) /* Data is MSI IOVA (u64) */
+#define VFIO_IRQ_SET_ACTION_PREPARE	(1 << 7) /* Prepare interrupt */
 	__u32	index;
 	__u32	start;
 	__u32	count;
@@ -599,10 +601,12 @@ struct vfio_irq_set {
 
 #define VFIO_IRQ_SET_DATA_TYPE_MASK	(VFIO_IRQ_SET_DATA_NONE | \
 					 VFIO_IRQ_SET_DATA_BOOL | \
-					 VFIO_IRQ_SET_DATA_EVENTFD)
+					 VFIO_IRQ_SET_DATA_EVENTFD | \
+					 VFIO_IRQ_SET_DATA_MSI_IOVA)
 #define VFIO_IRQ_SET_ACTION_TYPE_MASK	(VFIO_IRQ_SET_ACTION_MASK | \
 					 VFIO_IRQ_SET_ACTION_UNMASK | \
-					 VFIO_IRQ_SET_ACTION_TRIGGER)
+					 VFIO_IRQ_SET_ACTION_TRIGGER | \
+					 VFIO_IRQ_SET_ACTION_PREPARE)
 /**
  * VFIO_DEVICE_RESET - _IO(VFIO_TYPE, VFIO_BASE + 11)
  *
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index 8382c5834335..80ea6bc1941f 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -685,6 +685,8 @@ static int vfio_pci_set_msi_trigger(struct vfio_pci_core_device *vdev,
 
 	if (irq_is(vdev, index) && !count && (flags & VFIO_IRQ_SET_DATA_NONE)) {
 		vfio_msi_disable(vdev, msix);
+		for (i = start; i < start + count; i++)
+			vfio_iommufd_device_unset_msi_iova(&vdev->vdev, i);
 		return 0;
 	}
 
@@ -728,6 +730,47 @@ static int vfio_pci_set_msi_trigger(struct vfio_pci_core_device *vdev,
 	return 0;
 }
 
+static int vfio_pci_set_msi_prepare(struct vfio_pci_core_device *vdev,
+				    unsigned int index, unsigned int start,
+				    unsigned int count, uint32_t flags,
+				    void *data)
+{
+	struct vfio_device *core = &vdev->vdev;
+	uint64_t *iovas = data;
+	unsigned int i;
+	int ret;
+
+	if (!vfio_iommufd_device_ictx(core))
+		return -EOPNOTSUPP;
+	if (!(irq_is(vdev, index) || is_irq_none(vdev)))
+		return -EINVAL;
+
+	if (flags & VFIO_IRQ_SET_DATA_NONE) {
+		if (!count)
+			return -EINVAL;
+		for (i = start; i < start + count; i++)
+			vfio_iommufd_device_unset_msi_iova(core, i);
+		return 0;
+	}
+
+	if (!(flags & VFIO_IRQ_SET_DATA_MSI_IOVA))
+		return -EOPNOTSUPP;
+	if (!IS_ENABLED(CONFIG_IRQ_MSI_IOMMU))
+		return -EOPNOTSUPP;
+
+	ret = vfio_iommufd_device_set_num_msi_iovas(core, start + count);
+	if (ret)
+		return ret;
+
+	for (i = start; i < start + count; i++) {
+		ret = vfio_iommufd_device_set_msi_iova(core, i, iovas[i]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static int vfio_pci_set_ctx_trigger_single(struct eventfd_ctx **ctx,
 					   unsigned int count, uint32_t flags,
 					   void *data)
@@ -837,6 +880,9 @@ int vfio_pci_set_irqs_ioctl(struct vfio_pci_core_device *vdev, uint32_t flags,
 		case VFIO_IRQ_SET_ACTION_TRIGGER:
 			func = vfio_pci_set_msi_trigger;
 			break;
+		case VFIO_IRQ_SET_ACTION_PREPARE:
+			func = vfio_pci_set_msi_prepare;
+			break;
 		}
 		break;
 	case VFIO_PCI_ERR_IRQ_INDEX:
diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c
index 1fd261efc582..ad11c8e7da7b 100644
--- a/drivers/vfio/vfio_main.c
+++ b/drivers/vfio/vfio_main.c
@@ -1554,6 +1554,9 @@ int vfio_set_irqs_validate_and_prepare(struct vfio_irq_set *hdr, int num_irqs,
 	case VFIO_IRQ_SET_DATA_EVENTFD:
 		size = sizeof(int32_t);
 		break;
+	case VFIO_IRQ_SET_DATA_MSI_IOVA:
+		size = sizeof(uint64_t);
+		break;
 	default:
 		return -EINVAL;
 	}
-- 
2.43.0