On 5/20/2025 2:48 AM, Cédric Le Goater wrote:
On 5/12/25 17:32, Steve Sistare wrote:
Do not reset a vfio-pci device during CPR, and do not complain if the
kernel's PCI config space changes for non-emulated bits between the
vmstate save and load, which can happen due to ongoing interrupt activity.
Signed-off-by: Steve Sistare <steven.sist...@oracle.com>
---
hw/vfio/cpr.c | 31 +++++++++++++++++++++++++++++++
hw/vfio/pci.c | 6 ++++++
include/hw/vfio/vfio-cpr.h | 2 ++
3 files changed, 39 insertions(+)
diff --git a/hw/vfio/cpr.c b/hw/vfio/cpr.c
index 0e59612..6ea8e9f 100644
--- a/hw/vfio/cpr.c
+++ b/hw/vfio/cpr.c
@@ -8,6 +8,8 @@
#include "qemu/osdep.h"
#include "hw/vfio/vfio-device.h"
#include "hw/vfio/vfio-cpr.h"
+#include "hw/vfio/pci.h"
+#include "migration/cpr.h"
#include "qapi/error.h"
#include "system/runstate.h"
@@ -37,3 +39,32 @@ void vfio_cpr_unregister_container(VFIOContainerBase
*bcontainer)
{
migration_remove_notifier(&bcontainer->cpr_reboot_notifier);
}
+
+/*
+ * The kernel may change non-emulated config bits. Exclude them from the
+ * changed-bits check in get_pci_config_device.
+ */
+static int vfio_cpr_pci_pre_load(void *opaque)
+{
+ VFIOPCIDevice *vdev = opaque;
+ PCIDevice *pdev = &vdev->pdev;
+ int size = MIN(pci_config_size(pdev), vdev->config_size);
+ int i;
+
+ for (i = 0; i < size; i++) {
+ pdev->cmask[i] &= vdev->emulated_config_bits[i];
+ }
+
+ return 0;
+}
+
+const VMStateDescription vfio_cpr_pci_vmstate = {
+ .name = "vfio-cpr-pci",
+ .version_id = 0,
+ .minimum_version_id = 0,
+ .pre_load = vfio_cpr_pci_pre_load,
+ .needed = cpr_needed_for_reuse,
+ .fields = (VMStateField[]) {
+ VMSTATE_END_OF_LIST()
+ }
+};
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index a1bfdfe..4aa83b1 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -3344,6 +3344,11 @@ static void vfio_pci_reset(DeviceState *dev)
{
VFIOPCIDevice *vdev = VFIO_PCI_BASE(dev);
+ /* Do not reset the device during qemu_system_reset prior to cpr load */
+ if (vdev->vbasedev.cpr.reused) {
+ return;
+ }
+
hw/pci/pci.c does :
if (cpr_is_incoming()) {
return;
}
So, to be consistent, I think VFIO should do the same.
will do - steve
trace_vfio_pci_reset(vdev->vbasedev.name);
vfio_pci_pre_reset(vdev);
@@ -3513,6 +3518,7 @@ static void vfio_pci_dev_class_init(ObjectClass *klass,
const void *data)
#ifdef CONFIG_IOMMUFD
object_class_property_add_str(klass, "fd", NULL, vfio_pci_set_fd);
#endif
+ dc->vmsd = &vfio_cpr_pci_vmstate;
dc->desc = "VFIO-based PCI device assignment";
pdc->realize = vfio_realize;
diff --git a/include/hw/vfio/vfio-cpr.h b/include/hw/vfio/vfio-cpr.h
index d6d22f2..e93600f 100644
--- a/include/hw/vfio/vfio-cpr.h
+++ b/include/hw/vfio/vfio-cpr.h
@@ -49,4 +49,6 @@ void vfio_cpr_giommu_remap(struct VFIOContainerBase
*bcontainer,
bool vfio_cpr_ram_discard_register_listener(
struct VFIOContainerBase *bcontainer, MemoryRegionSection *section);
+extern const VMStateDescription vfio_cpr_pci_vmstate;
+
#endif /* HW_VFIO_VFIO_CPR_H */
