On Mon, Feb 9, 2026 at 3:38 AM Cédric Le Goater <[email protected]> wrote:
>
> On 2/8/26 15:39, Ani Sinha wrote:
> > On Tue, Jan 27, 2026 at 10:47 AM Ani Sinha <[email protected]> wrote:
> >>
> >> Normally the vfio pseudo device file descriptor lives for the life of the 
> >> VM.
> >> However, when the kvm VM file descriptor changes, a new file descriptor
> >> for the pseudo device needs to be generated against the new kvm VM 
> >> descriptor.
> >> Other existing vfio descriptors needs to be reattached to the new pseudo 
> >> device
> >> descriptor. This change performs the above steps.
> >
> > I have not been able to test this change. Can someone suggest a way to
> > add a functional test and/or test this manually?
>
> Automated VFIO testing [*] is tough because it depends on a "real"
> physical PCI device.
>
> I have tested you series using a sev-snp guest with an assigned device
> (SATA controller) and verified that the guest could reboot. The SATA
> controller has no disks connected, so further testing is required.
>
> However, a 'system_reset' command issued from the QEMU monitor leaves
> the guest hanging. May be this is expected ?

I do not think so. On non-coco, I just tried it and it reboots fine
with x-change-vmfd-on-reset turned on.
I tried a RHEL 10 guest image as well as a simple UKI kernel.
Maybe there is some bug in this patch, not sure. In QEMU the code path
should be the same for both.

>
>
> > Otherwise I am going to add a comment in the next spin up that this
> > change is not tested.
>
> I will provide some more comments on the code. Please give me a day
> or two before resending.

Sure, please take all the time you need.

>
> Thanks,
>
> C.
>
> [*] One way to address this constraint for VFIO testing would be
>      to run the test in a nested environment using emulated devices,
>      like IGB, attached to an L1 which would be assigned to an L2.
>      But that's unrelated to this series.
> >
> >>
> >> Signed-off-by: Ani Sinha <[email protected]>
> >> ---
> >>   hw/vfio/helpers.c | 86 +++++++++++++++++++++++++++++++++++++++++++++--
> >>   1 file changed, 83 insertions(+), 3 deletions(-)
> >>
> >> diff --git a/hw/vfio/helpers.c b/hw/vfio/helpers.c
> >> index f68f8165d0..d467875b4b 100644
> >> --- a/hw/vfio/helpers.c
> >> +++ b/hw/vfio/helpers.c
> >> @@ -110,12 +110,71 @@ bool vfio_get_info_dma_avail(struct 
> >> vfio_iommu_type1_info *info,
> >>   #ifdef CONFIG_KVM
> >>   /*
> >>    * We have a single VFIO pseudo device per KVM VM.  Once created it lives
> >> - * for the life of the VM.  Closing the file descriptor only drops our
> >> - * reference to it and the device's reference to kvm.  Therefore once
> >> - * initialized, this file descriptor is only released on QEMU exit and
> >> + * for the life of the VM except when the vm file descriptor changes for
> >> + * confidential virtual machines. In that case, the old file descriptor is
> >> + * closed and a new file descriptor is recreated.  Closing the file 
> >> descriptor
> >> + * only drops our reference to it and the device's reference to kvm.
> >> + * Therefore once initialized, this file descriptor is normally only 
> >> released
> >> + * on QEMU exit (except for confidential VMs as stated above) and
> >>    * we'll re-use it should another vfio device be attached before then.
> >>    */
> >>   int vfio_kvm_device_fd = -1;
> >> +
> >> +typedef struct KVMVfioFileFd {
> >> +    int fd;
> >> +    QLIST_ENTRY(KVMVfioFileFd) node;
> >> +} KVMVfioFileFd;
> >> +
> >> +static QLIST_HEAD(, KVMVfioFileFd) kvm_vfio_file_fds =
> >> +    QLIST_HEAD_INITIALIZER(kvm_vfio_file_fds);
> >> +
> >> +static int kvm_vfio_filefd_rebind(NotifierWithReturn *notifier, void 
> >> *data,
> >> +                                  Error **errp);
> >> +static struct NotifierWithReturn kvm_vfio_vmfd_change_notifier = {
> >> +    .notify = kvm_vfio_filefd_rebind,
> >> +};
> >> +
> >> +static int kvm_vfio_filefd_rebind(NotifierWithReturn *notifier, void 
> >> *data,
> >> +                                  Error **errp)
> >> +{
> >> +    KVMVfioFileFd *file_fd;
> >> +    int ret = 0;
> >> +    struct kvm_device_attr attr = {
> >> +        .group = KVM_DEV_VFIO_FILE,
> >> +        .attr = KVM_DEV_VFIO_FILE_ADD,
> >> +    };
> >> +    struct kvm_create_device cd = {
> >> +        .type = KVM_DEV_TYPE_VFIO,
> >> +    };
> >> +
> >> +    /* we are not interested in pre vmfd change notification */
> >> +    if (((VmfdChangeNotifier *)data)->pre) {
> >> +        return 0;
> >> +    }
> >> +
> >> +    if (kvm_vm_ioctl(kvm_state, KVM_CREATE_DEVICE, &cd)) {
> >> +        error_setg_errno(errp, errno, "Failed to create KVM VFIO device");
> >> +        return -errno;
> >> +    }
> >> +
> >> +    if (vfio_kvm_device_fd) {
> >> +        close(vfio_kvm_device_fd);
> >> +    }
> >> +
> >> +    vfio_kvm_device_fd = cd.fd;
> >> +
> >> +    QLIST_FOREACH(file_fd, &kvm_vfio_file_fds, node) {
> >> +        attr.addr = (uint64_t)(unsigned long)&file_fd->fd;
> >> +        if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) {
> >> +            error_setg_errno(errp, errno,
> >> +                             "Failed to add fd %d to KVM VFIO device",
> >> +                             file_fd->fd);
> >> +            ret = -errno;
> >> +        }
> >> +    }
> >> +    return ret;
> >> +}
> >> +
> >>   #endif
> >>
> >>   void vfio_kvm_device_close(void)
> >> @@ -137,6 +196,7 @@ int vfio_kvm_device_add_fd(int fd, Error **errp)
> >>           .attr = KVM_DEV_VFIO_FILE_ADD,
> >>           .addr = (uint64_t)(unsigned long)&fd,
> >>       };
> >> +    KVMVfioFileFd *file_fd;
> >>
> >>       if (!kvm_enabled()) {
> >>           return 0;
> >> @@ -153,6 +213,11 @@ int vfio_kvm_device_add_fd(int fd, Error **errp)
> >>           }
> >>
> >>           vfio_kvm_device_fd = cd.fd;
> >> +        /*
> >> +         * If the vm file descriptor changes, add a notifier so that we 
> >> can
> >> +         * re-create the vfio_kvm_device_fd.
> >> +         */
> >> +        kvm_vmfd_add_change_notifier(&kvm_vfio_vmfd_change_notifier);
> >>       }
> >>
> >>       if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) {
> >> @@ -160,6 +225,11 @@ int vfio_kvm_device_add_fd(int fd, Error **errp)
> >>                            fd);
> >>           return -errno;
> >>       }
> >> +
> >> +    file_fd = g_malloc0(sizeof(*file_fd));
> >> +    file_fd->fd = fd;
> >> +    QLIST_INSERT_HEAD(&kvm_vfio_file_fds, file_fd, node);
> >> +
> >>   #endif
> >>       return 0;
> >>   }
> >> @@ -172,6 +242,7 @@ int vfio_kvm_device_del_fd(int fd, Error **errp)
> >>           .attr = KVM_DEV_VFIO_FILE_DEL,
> >>           .addr = (uint64_t)(unsigned long)&fd,
> >>       };
> >> +    KVMVfioFileFd *file_fd;
> >>
> >>       if (vfio_kvm_device_fd < 0) {
> >>           error_setg(errp, "KVM VFIO device isn't created yet");
> >> @@ -183,6 +254,15 @@ int vfio_kvm_device_del_fd(int fd, Error **errp)
> >>                            "Failed to remove fd %d from KVM VFIO device", 
> >> fd);
> >>           return -errno;
> >>       }
> >> +
> >> +    QLIST_FOREACH(file_fd, &kvm_vfio_file_fds, node) {
> >> +        if (file_fd->fd == fd) {
> >> +            QLIST_REMOVE(file_fd, node);
> >> +            g_free(file_fd);
> >> +            break;
> >> +        }
> >> +    }
> >> +
> >>   #endif
> >>       return 0;
> >>   }
> >> --
> >> 2.42.0
> >>
> >
>


Reply via email to