@@ -114,6 +114,12 @@ typedef struct VFIOMSIXInfo {
unsigned long *pending;
} VFIOMSIXInfo;
+typedef struct VFIOPCIExtIRQ {
+ struct VFIOPCIDevice *vdev;
+ EventNotifier notifier;
+ uint32_t index;
+} VFIOPCIExtIRQ;
+
#define TYPE_VFIO_PCI "vfio-pci"
OBJECT_DECLARE_SIMPLE_TYPE(VFIOPCIDevice, VFIO_PCI)
@@ -138,6 +144,7 @@ struct VFIOPCIDevice {
PCIHostDeviceAddress host;
EventNotifier err_notifier;
EventNotifier req_notifier;
+ VFIOPCIExtIRQ *ext_irqs;
int (*resetfn)(struct VFIOPCIDevice *);
uint32_t vendor_id;
uint32_t device_id;
@@ -2864,6 +2864,76 @@ static PCIPASIDOps vfio_pci_pasid_ops = {
.set_pasid_table = vfio_iommu_set_pasid_table,
};
+static void vfio_dma_fault_notifier_handler(void *opaque)
+{
+ VFIOPCIExtIRQ *ext_irq = opaque;
+
+ if (!event_notifier_test_and_clear(&ext_irq->notifier)) {
+ return;
+ }
+}
+
+static int vfio_register_ext_irq_handler(VFIOPCIDevice *vdev,
+ uint32_t type, uint32_t subtype,
+ IOHandler *handler)
+{
+ int32_t fd, ext_irq_index, index;
+ struct vfio_irq_info *irq_info;
+ Error *err = NULL;
+ EventNotifier *n;
+ int ret;
+
+ ret = vfio_get_dev_irq_info(&vdev->vbasedev, type, subtype, &irq_info);
+ if (ret) {
+ return ret;
+ }
+ index = irq_info->index;
+ ext_irq_index = irq_info->index - VFIO_PCI_NUM_IRQS;
+ g_free(irq_info);
+
+ vdev->ext_irqs[ext_irq_index].vdev = vdev;
+ vdev->ext_irqs[ext_irq_index].index = index;
+ n = &vdev->ext_irqs[ext_irq_index].notifier;
+
+ ret = event_notifier_init(n, 0);
+ if (ret) {
+ error_report("vfio: Unable to init event notifier for ext irq %d(%d)",
+ ext_irq_index, ret);
+ return ret;
+ }
+
+ fd = event_notifier_get_fd(n);
+ qemu_set_fd_handler(fd, vfio_dma_fault_notifier_handler, NULL,
+ &vdev->ext_irqs[ext_irq_index]);
+
+ ret = vfio_set_irq_signaling(&vdev->vbasedev, index, 0,
+ VFIO_IRQ_SET_ACTION_TRIGGER, fd, &err);
+ if (ret) {
+ error_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name);
+ qemu_set_fd_handler(fd, NULL, NULL, vdev);
+ event_notifier_cleanup(n);
+ }
+ return ret;
+}
+
+static void vfio_unregister_ext_irq_notifiers(VFIOPCIDevice *vdev)
+{
+ VFIODevice *vbasedev = &vdev->vbasedev;
+ Error *err = NULL;
+ int i;
+
+ for (i = 0; i < vbasedev->num_irqs - VFIO_PCI_NUM_IRQS; i++) {
+ if (vfio_set_irq_signaling(vbasedev, i + VFIO_PCI_NUM_IRQS , 0,
+ VFIO_IRQ_SET_ACTION_TRIGGER, -1, &err)) {
+ error_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name);
+ }
+ qemu_set_fd_handler(event_notifier_get_fd(&vdev->ext_irqs[i].notifier),
+ NULL, NULL, vdev);
+ event_notifier_cleanup(&vdev->ext_irqs[i].notifier);
+ }
+ g_free(vdev->ext_irqs);
+}
+
static void vfio_realize(PCIDevice *pdev, Error **errp)
{
VFIOPCIDevice *vdev = VFIO_PCI(pdev);
@@ -2874,7 +2944,7 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
ssize_t len;
struct stat st;
int groupid;
- int i, ret;
+ int i, ret, nb_ext_irqs;
bool is_mdev;
if (!vdev->vbasedev.sysfsdev) {
@@ -2962,6 +3032,11 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
goto error;
}
+ nb_ext_irqs = vdev->vbasedev.num_irqs - VFIO_PCI_NUM_IRQS;
+ if (nb_ext_irqs > 0) {
+ vdev->ext_irqs = g_new0(VFIOPCIExtIRQ, nb_ext_irqs);
+ }
+
vfio_populate_device(vdev, &err);
if (err) {
error_propagate(errp, err);
@@ -3173,6 +3248,9 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
vfio_register_err_notifier(vdev);
vfio_register_req_notifier(vdev);
+ vfio_register_ext_irq_handler(vdev, VFIO_IRQ_TYPE_NESTED,
+ VFIO_IRQ_SUBTYPE_DMA_FAULT,
+ vfio_dma_fault_notifier_handler);
vfio_setup_resetfn_quirk(vdev);
pci_setup_pasid_ops(pdev, &vfio_pci_pasid_ops);
@@ -3215,6 +3293,7 @@ static void vfio_exitfn(PCIDevice *pdev)
vfio_unregister_req_notifier(vdev);
vfio_unregister_err_notifier(vdev);
+ vfio_unregister_ext_irq_notifiers(vdev);
pci_device_set_intx_routing_notifier(&vdev->pdev, NULL);
if (vdev->irqchip_change_notifier.notify) {
kvm_irqchip_remove_change_notifier(&vdev->irqchip_change_notifier);
We use the new extended IRQ VFIO_IRQ_TYPE_NESTED type and VFIO_IRQ_SUBTYPE_DMA_FAULT subtype to set/unset a notifier for physical DMA faults. The associated eventfd is triggered, in nested mode, whenever a fault is detected at IOMMU physical level. The actual handler will be implemented in subsequent patches. Signed-off-by: Eric Auger <eric.auger@redhat.com> --- v4 -> v5: - index_to_str now returns the index name, ie. DMA_FAULT - use the extended IRQ v3 -> v4: - check VFIO_PCI_DMA_FAULT_IRQ_INDEX is supported at kernel level before attempting to set signaling for it. --- hw/vfio/pci.h | 7 +++++ hw/vfio/pci.c | 81 ++++++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 87 insertions(+), 1 deletion(-)