On 14/01/2022 21.38, 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 | 70 +++++++++++++++++++++++++++++++-
hw/s390x/s390-pci-inst.c | 63 +++++++++++++++++++++++++++-
hw/s390x/s390-pci-vfio.c | 52 ++++++++++++++++++++++++
include/hw/s390x/s390-pci-bus.h | 1 +
include/hw/s390x/s390-pci-vfio.h | 15 +++++++
5 files changed, 199 insertions(+), 2 deletions(-)
diff --git a/hw/s390x/s390-pci-bus.c b/hw/s390x/s390-pci-bus.c
index 01b58ebc70..a39ccfee05 100644
--- a/hw/s390x/s390-pci-bus.c
+++ b/hw/s390x/s390-pci-bus.c
@@ -971,12 +971,58 @@ 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 already in an enabled state, but we always present
+ * the initial device state to the guest as disabled (ZPCI_FS_DISABLED).
+ * Therefore, mask off the enable bit from the passthrough handle until
+ * the guest issues a CLP SET PCI FN later to enable the device.
+ */
+ 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 relinquished idx is lower than next_idx, use it
+ * 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;
+}
+
static void s390_pcihost_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
Error **errp)
{
S390pciState *s = S390_PCI_HOST_BRIDGE(hotplug_dev);
PCIDevice *pdev = NULL;
S390PCIBusDevice *pbdev = NULL;
+ int rc;
if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_BRIDGE)) {
PCIBridge *pb = PCI_BRIDGE(dev);
@@ -1022,12 +1068,33 @@ static void s390_pcihost_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
set_pbdev_info(pbdev);
if (object_dynamic_cast(OBJECT(dev), "vfio-pci")) {
- pbdev->fh |= FH_SHM_VFIO;
+ /*
+ * By default, interpretation is always requested; if the available
+ * facilities indicate it is not available, fallback to the
+ * intercept model.
+ */
+ if (pbdev->interp && !s390_has_feat(S390_FEAT_ZPCI_INTERP)) {
+ DPRINTF("zPCI interpretation facilities missing.\n");
+ pbdev->interp = false;
+ }
Wrong indentation in the above three lines.
+ if (pbdev->interp) {
+ rc = s390_pci_interp_plug(s, pbdev);
+ if (rc) {
+ error_setg(errp, "zpci interp plug failed: %d", rc);
The error message is a little bit scarce for something that might be
presented to the user - maybe write at least "interpretation" instead of
"interp" ?
+ return;
+ }
+ }
pbdev->iommu->dma_limit = s390_pci_start_dma_count(s, pbdev);
/* Fill in CLP information passed via the vfio region */
s390_pci_get_clp_info(pbdev);
+ if (!pbdev->interp) {
+ /* Do vfio passthrough but intercept for I/O */
+ pbdev->fh |= FH_SHM_VFIO;
+ }
} else {
pbdev->fh |= FH_SHM_EMUL;
+ /* Always intercept emulated devices */
+ pbdev->interp = false;
}
Thomas
