From 031fbb7110a183053b431fb667867a5244910e75 Mon Sep 17 00:00:00 2001
From: Steve Sistare <steven.sistare@oracle.com>
Date: Tue, 10 Jun 2025 08:39:24 -0700
Subject: [PATCH] vfio-pci: skip reset during cpr
MIME-Version: 1.0
Content-Type: text/plain; charset=utf8
Content-Transfer-Encoding: 8bit

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.sistare@oracle.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/1749569991-25171-12-git-send-email-steven.sistare@oracle.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
 hw/vfio/cpr.c              | 31 +++++++++++++++++++++++++++++++
 hw/vfio/pci.c              |  7 +++++++
 include/hw/vfio/vfio-cpr.h |  2 ++
 3 files changed, 40 insertions(+)

diff --git a/hw/vfio/cpr.c b/hw/vfio/cpr.c
index 0e59612228..fdbb58e203 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_incoming_needed,
+    .fields = (VMStateField[]) {
+        VMSTATE_END_OF_LIST()
+    }
+};
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index b97261c61b..2da5989581 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -30,6 +30,7 @@
 #include "hw/qdev-properties.h"
 #include "hw/qdev-properties-system.h"
 #include "migration/vmstate.h"
+#include "migration/cpr.h"
 #include "qobject/qdict.h"
 #include "qemu/error-report.h"
 #include "qemu/main-loop.h"
@@ -3354,6 +3355,11 @@ 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 (cpr_is_incoming()) {
+        return;
+    }
+
     trace_vfio_pci_reset(vdev->vbasedev.name);
 
     vfio_pci_pre_reset(vdev);
@@ -3530,6 +3536,7 @@ 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_pci_realize;
 
diff --git a/include/hw/vfio/vfio-cpr.h b/include/hw/vfio/vfio-cpr.h
index 56ede049ad..8bf85b9f4e 100644
--- a/include/hw/vfio/vfio-cpr.h
+++ b/include/hw/vfio/vfio-cpr.h
@@ -52,4 +52,6 @@ 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 */
-- 
2.39.5