return ret;
}
-static int vfio_msix_vector_use(PCIDevice *pdev,
- unsigned int nr, MSIMessage msg)
+static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr,
+ MSIMessage *msg, IOHandler *handler)
{
VFIODevice *vdev = DO_UPCAST(VFIODevice, pdev, pdev);
VFIOMSIVector *vector;
* Attempt to enable route through KVM irqchip,
* default to userspace handling if unavailable.
*/
- vector->virq = kvm_irqchip_add_msi_route(kvm_state, msg);
+ vector->virq = msg ? kvm_irqchip_add_msi_route(kvm_state, *msg) : -1;
if (vector->virq < 0 ||
kvm_irqchip_add_irqfd_notifier(kvm_state, &vector->interrupt,
vector->virq) < 0) {
vector->virq = -1;
}
qemu_set_fd_handler(event_notifier_get_fd(&vector->interrupt),
- vfio_msi_interrupt, NULL, vector);
+ handler, NULL, vector);
}
/*
return 0;
}
+static int vfio_msix_vector_use(PCIDevice *pdev,
+ unsigned int nr, MSIMessage msg)
+{
+ return vfio_msix_vector_do_use(pdev, nr, &msg, vfio_msi_interrupt);
+}
+
static void vfio_msix_vector_release(PCIDevice *pdev, unsigned int nr)
{
VFIODevice *vdev = DO_UPCAST(VFIODevice, pdev, pdev);
vdev->interrupt = VFIO_INT_MSIX;
+ /*
+ * Some communication channels between VF & PF or PF & fw rely on the
+ * physical state of the device and expect that enabling MSI-X from the
+ * guest enables the same on the host. When our guest is Linux, the
+ * guest driver call to pci_enable_msix() sets the enabling bit in the
+ * MSI-X capability, but leaves the vector table masked. We therefore
+ * can't rely on a vector_use callback (from request_irq() in the guest)
+ * to switch the physical device into MSI-X mode because that may come a
+ * long time after pci_enable_msix(). This code enables vector 0 with
+ * triggering to userspace, then immediately release the vector, leaving
+ * the physical device with no vectors enabled, but MSI-X enabled, just
+ * like the guest view.
+ */
+ vfio_msix_vector_do_use(&vdev->pdev, 0, NULL, NULL);
+ vfio_msix_vector_release(&vdev->pdev, 0);
+
if (msix_set_vector_notifiers(&vdev->pdev, vfio_msix_vector_use,
vfio_msix_vector_release, NULL)) {
error_report("vfio: msix_set_vector_notifiers failed\n");
ret = ioctl(group->fd, VFIO_GROUP_GET_DEVICE_FD, name);
if (ret < 0) {
- error_report("vfio: error getting device %s from group %d: %m\n",
+ error_report("vfio: error getting device %s from group %d: %m",
name, group->groupid);
- error_report("Verify all devices in group %d are bound to vfio-pci "
+ error_printf("Verify all devices in group %d are bound to vfio-pci "
"or pci-stub and not already in use\n", group->groupid);
return ret;
}
error_report("Warning, device %s does not support reset\n", name);
}
- if (dev_info.num_regions != VFIO_PCI_NUM_REGIONS) {
+ if (dev_info.num_regions < VFIO_PCI_CONFIG_REGION_INDEX + 1) {
error_report("vfio: unexpected number of io regions %u\n",
dev_info.num_regions);
goto error;
}
- if (dev_info.num_irqs != VFIO_PCI_NUM_IRQS) {
+ if (dev_info.num_irqs < VFIO_PCI_MSIX_IRQ_INDEX + 1) {
error_report("vfio: unexpected number of irqs %u\n", dev_info.num_irqs);
goto error;
}
(unsigned long)reg_info.flags);
vdev->config_size = reg_info.size;
+ if (vdev->config_size == PCI_CONFIG_SPACE_SIZE) {
+ vdev->pdev.cap_present &= ~QEMU_PCI_CAP_EXPRESS;
+ }
vdev->config_offset = reg_info.offset;
error:
pdc->exit = vfio_exitfn;
pdc->config_read = vfio_pci_read_config;
pdc->config_write = vfio_pci_write_config;
+ pdc->is_express = 1; /* We might be */
}
static const TypeInfo vfio_pci_dev_info = {