From: Chen Fan <address@hidden>
when boot up a VM that assigning vfio devices with aer enabled, we
must check the vfio device whether support host bus reset. because
when one error occur. OS driver always recover the device by do a
bus reset, in order to recover the vfio device, qemu must to do a
host bus reset to reset the device to default status. and for all
affected devices by the bus reset. we must check them whether all
are assigned to the VM.
Signed-off-by: Chen Fan <address@hidden>
---
hw/vfio/pci.c | 218 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++--
hw/vfio/pci.h | 1 +
2 files changed, 212 insertions(+), 7 deletions(-)
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 8ec9b25..0898e34 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -1868,6 +1868,197 @@ static int vfio_add_std_cap(VFIOPCIDevice *vdev,
uint8_t pos)
return 0;
}
+static bool vfio_pci_host_slot_match(PCIHostDeviceAddress *host1,
+ PCIHostDeviceAddress *host2)
+{
+ return (host1->domain == host2->domain && host1->bus == host2->bus &&
+ host1->slot == host2->slot);
+}
+
+static bool vfio_pci_host_match(PCIHostDeviceAddress *host1,
+ PCIHostDeviceAddress *host2)
+{
+ return (vfio_pci_host_slot_match(host1, host2) &&
+ host1->function == host2->function);
+}
+
+struct VFIODeviceFind {
+ PCIDevice *pdev;
+ bool found;
+};
+
+static void vfio_check_device_noreset(PCIBus *bus, PCIDevice *pdev,
+ void *opaque)
+{
+ DeviceState *dev = DEVICE(pdev);
+ DeviceClass *dc = DEVICE_GET_CLASS(dev);
+ VFIOPCIDevice *vdev;
+ struct VFIODeviceFind *find = opaque;
+
+ if (find->found) {
+ return;
+ }
+
+ if (!object_dynamic_cast(OBJECT(dev), "vfio-pci")) {
+ if (!dc->reset) {
+ goto found;
+ }
+ return;
+ }
+ vdev = DO_UPCAST(VFIOPCIDevice, pdev, pdev);
+ if (!(vdev->features & VFIO_FEATURE_ENABLE_AER) &&
+ !vdev->vbasedev.reset_works) {
+ goto found;
+ }
+
+ return;
+found:
+ find->pdev = pdev;
+ find->found = true;
+}
+
+static void vfio_check_host_bus_reset(VFIOPCIDevice *vdev, Error **errp)
+{
+ PCIBus *bus = vdev->pdev.bus;
+ struct vfio_pci_hot_reset_info *info = NULL;
+ struct vfio_pci_dependent_device *devices;
+ VFIOGroup *group;
+ struct VFIODeviceFind find;
+ int ret, i;
+
+ ret = vfio_get_hot_reset_info(vdev, &info);
+ if (ret) {
+ error_setg(errp, "vfio: Cannot enable AER for device %s,"
+ " device does not support hot reset.",
+ vdev->vbasedev.name);
+ return;
+ }
+
+ /* List all affected devices by bus reset */
+ devices = &info->devices[0];
+
+ /* Verify that we have all the groups required */
+ for (i = 0; i < info->count; i++) {
+ PCIHostDeviceAddress host;
+ VFIOPCIDevice *tmp;
+ VFIODevice *vbasedev_iter;
+ bool found = false;
+
+ host.domain = devices[i].segment;
+ host.bus = devices[i].bus;
+ host.slot = PCI_SLOT(devices[i].devfn);
+ host.function = PCI_FUNC(devices[i].devfn);
+
+ /* Skip the current device */
+ if (vfio_pci_host_match(&host, &vdev->host)) {
+ continue;
+ }
+
+ /* Ensure we own the group of the affected device */
+ QLIST_FOREACH(group, &vfio_group_list, next) {
+ if (group->groupid == devices[i].group_id) {
+ break;
+ }
+ }
+
+ if (!group) {
+ error_setg(errp, "vfio: Cannot enable AER for device %s, "
+ "depends on group %d which is not owned.",
+ vdev->vbasedev.name, devices[i].group_id);
+ goto out;
+ }
+
+ /* Ensure affected devices for reset on the same slot */
+ QLIST_FOREACH(vbasedev_iter, &group->device_list, next) {
+ if (vbasedev_iter->type != VFIO_DEVICE_TYPE_PCI) {
+ continue;
+ }
+ tmp = container_of(vbasedev_iter, VFIOPCIDevice, vbasedev);
+ if (vfio_pci_host_match(&host, &tmp->host)) {
+ /*
+ * AER errors may be broadcast to all functions of a multi-
+ * function endpoint. If any of those sibling functions are
+ * also assigned, they need to have AER enabled or else an
+ * error may continue to cause a vm_stop condition. IOW,
+ * AER setup of this function would be pointless.
+ */
+ if (vfio_pci_host_slot_match(&vdev->host, &tmp->host) &&
+ !(tmp->features & VFIO_FEATURE_ENABLE_AER)) {
+ error_setg(errp, "vfio: Cannot enable AER for device %s, on
same slot"
+ " the dependent device %s which does not enable
AER.",
+ vdev->vbasedev.name, tmp->vbasedev.name);
+ goto out;
+ }
+
+ if (tmp->pdev.bus != bus) {
+ error_setg(errp, "vfio: Cannot enable AER for device %s, "
+ "the dependent device %s is not on the same
bus",
+ vdev->vbasedev.name, tmp->vbasedev.name);
+ goto out;
+ }
+ found = true;
+ break;
+ }
+ }
+
+ /* Ensure all affected devices assigned to VM */
+ if (!found) {
+ error_setg(errp, "vfio: Cannot enable AER for device %s, "
+ "the dependent device %04x:%02x:%02x.%x "
+ "is not assigned to VM.",
+ vdev->vbasedev.name, host.domain, host.bus,
+ host.slot, host.function);
+ goto out;
+ }
+ }
+
+ /*
+ * Check the all pci devices on or below the target bus
+ * have a reset mechanism at least.
+ */
+ find.pdev = NULL;
+ find.found = false;
+ pci_for_each_device(bus, pci_bus_num(bus),