On 07/12/2021 22.04, Matthew Rosato wrote:
Use the associated vfio feature ioctl to enable interpretation for devices
when requested. As part of this process, we must use the host function
handle rather than a QEMU-generated one -- this is provided as part of the
ioctl payload.
Signed-off-by: Matthew Rosato <mjrosato@xxxxxxxxxxxxx>
---
hw/s390x/s390-pci-bus.c | 69 +++++++++++++++++++++++++++++++-
hw/s390x/s390-pci-inst.c | 63 ++++++++++++++++++++++++++++-
hw/s390x/s390-pci-vfio.c | 55 +++++++++++++++++++++++++
include/hw/s390x/s390-pci-bus.h | 1 +
include/hw/s390x/s390-pci-vfio.h | 15 +++++++
5 files changed, 201 insertions(+), 2 deletions(-)
diff --git a/hw/s390x/s390-pci-bus.c b/hw/s390x/s390-pci-bus.c
index 01b58ebc70..451bd32d92 100644
--- a/hw/s390x/s390-pci-bus.c
+++ b/hw/s390x/s390-pci-bus.c
@@ -971,12 +971,57 @@ static void s390_pci_update_subordinate(PCIDevice *dev, uint32_t nr)
}
}
+static int s390_pci_interp_plug(S390pciState *s, S390PCIBusDevice *pbdev)
+{
+ uint32_t idx;
+ int rc;
+
+ rc = s390_pci_probe_interp(pbdev);
+ if (rc) {
+ return rc;
+ }
+
+ rc = s390_pci_update_passthrough_fh(pbdev);
+ if (rc) {
+ return rc;
+ }
+
+ /*
+ * The host device is in an enabled state, but the device must
+ * begin as disabled for the guest so mask off the enable bit
+ * from the passthrough handle.
+ */
+ pbdev->fh &= ~FH_MASK_ENABLE;
+
+ /* Next, see if the idx is already in-use */
+ idx = pbdev->fh & FH_MASK_INDEX;
+ if (pbdev->idx != idx) {
+ if (s390_pci_find_dev_by_idx(s, idx)) {
+ return -EINVAL;
+ }
+ /*
+ * Update the idx entry with the passed through idx
+ * If the relinquised idx is lower than next_idx, use it
s/relinquised/relinquished/
+ * to replace next_idx
+ */
+ g_hash_table_remove(s->zpci_table, &pbdev->idx);
+ if (idx < s->next_idx) {
+ s->next_idx = idx;
+ }
+ pbdev->idx = idx;
+ g_hash_table_insert(s->zpci_table, &pbdev->idx, pbdev);
+ }
+
+ return 0;
+}
[...]
diff --git a/hw/s390x/s390-pci-vfio.c b/hw/s390x/s390-pci-vfio.c
index 6f80a47e29..78093aaac7 100644
--- a/hw/s390x/s390-pci-vfio.c
+++ b/hw/s390x/s390-pci-vfio.c
@@ -97,6 +97,61 @@ void s390_pci_end_dma_count(S390pciState *s, S390PCIDMACount *cnt)
}
}
+int s390_pci_probe_interp(S390PCIBusDevice *pbdev)
+{
+ VFIOPCIDevice *vdev = container_of(pbdev->pdev, VFIOPCIDevice, pdev);
+ struct vfio_device_feature feat = {
+ .argsz = sizeof(struct vfio_device_feature),
+ .flags = VFIO_DEVICE_FEATURE_PROBE + VFIO_DEVICE_FEATURE_ZPCI_INTERP
+ };
+
+ return ioctl(vdev->vbasedev.fd, VFIO_DEVICE_FEATURE, &feat);
+}
+
+int s390_pci_set_interp(S390PCIBusDevice *pbdev, bool enable)
+{
+ VFIOPCIDevice *vdev = container_of(pbdev->pdev, VFIOPCIDevice, pdev);
+ g_autofree struct vfio_device_feature *feat;
IIRC there have been compiler versions that complain if a g_autofree
variable is initialized at the point of declaration, so you might need to
add the "= g_malloc0(size)" here already.
+ struct vfio_device_zpci_interp *data;
+ int size;
+
+ size = sizeof(*feat) + sizeof(*data);
+ feat = g_malloc0(size);
+ feat->argsz = size;
+ feat->flags = VFIO_DEVICE_FEATURE_SET + VFIO_DEVICE_FEATURE_ZPCI_INTERP;
+
+ data = (struct vfio_device_zpci_interp *)&feat->data;
+ if (enable) {
+ data->flags = VFIO_DEVICE_ZPCI_FLAG_INTERP;
+ } else {
+ data->flags = 0;
+ }
+
+ return ioctl(vdev->vbasedev.fd, VFIO_DEVICE_FEATURE, feat);
+}
+
+int s390_pci_update_passthrough_fh(S390PCIBusDevice *pbdev)
+{
+ VFIOPCIDevice *vdev = container_of(pbdev->pdev, VFIOPCIDevice, pdev);
+ g_autofree struct vfio_device_feature *feat;
dito
+ struct vfio_device_zpci_interp *data;
+ int size, rc;
+
+ size = sizeof(*feat) + sizeof(*data);
+ feat = g_malloc0(size);
+ feat->argsz = size;
+ feat->flags = VFIO_DEVICE_FEATURE_GET + VFIO_DEVICE_FEATURE_ZPCI_INTERP;
+
+ rc = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_FEATURE, feat);
+ if (rc) {
+ return rc;
+ }
+
+ data = (struct vfio_device_zpci_interp *)&feat->data;
+ pbdev->fh = data->fh;
+ return 0;
+}
Thomas
