migration: close kvm after cpr

cpr-transfer breaks vfio network connectivity to and from the guest, and
the host system log shows:
  irq bypass consumer (token 00000000a03c32e5) registration fails: -16
which is EBUSY.  This occurs because KVM descriptors are still open in
the old QEMU process.  Close them.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Fabiano Rosas <farosas@suse.de>
Link: https://lore.kernel.org/qemu-devel/1751493538-202042-4-git-send-email-steven.sistare@oracle.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>

7 files changed, 71 insertions, 0 deletions

diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index d095d1b98f..8141854617 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -515,16 +515,23 @@ static int do_kvm_destroy_vcpu(CPUState *cpu)
         goto err;
     }
 
+    /* If I am the CPU that created coalesced_mmio_ring, then discard it */
+    if (s->coalesced_mmio_ring == (void *)cpu->kvm_run + PAGE_SIZE) {
+        s->coalesced_mmio_ring = NULL;
+    }
+
     ret = munmap(cpu->kvm_run, mmap_size);
     if (ret < 0) {
         goto err;
     }
+    cpu->kvm_run = NULL;
 
     if (cpu->kvm_dirty_gfns) {
         ret = munmap(cpu->kvm_dirty_gfns, s->kvm_dirty_ring_bytes);
         if (ret < 0) {
             goto err;
         }
+        cpu->kvm_dirty_gfns = NULL;
     }
 
     kvm_park_vcpu(cpu);
@@ -608,6 +615,31 @@ err:
     return ret;
 }
 
+void kvm_close(void)
+{
+    CPUState *cpu;
+
+    if (!kvm_state || kvm_state->fd == -1) {
+        return;
+    }
+
+    CPU_FOREACH(cpu) {
+        cpu_remove_sync(cpu);
+        close(cpu->kvm_fd);
+        cpu->kvm_fd = -1;
+        close(cpu->kvm_vcpu_stats_fd);
+        cpu->kvm_vcpu_stats_fd = -1;
+    }
+
+    if (kvm_state && kvm_state->fd != -1) {
+        close(kvm_state->vmfd);
+        kvm_state->vmfd = -1;
+        close(kvm_state->fd);
+        kvm_state->fd = -1;
+    }
+    kvm_state = NULL;
+}
+
 /*
  * dirty pages logging control
  */
diff --git a/hw/vfio/cpr-legacy.c b/hw/vfio/cpr-legacy.c
index 1216717546..553b203e9b 100644
--- a/hw/vfio/cpr-legacy.c
+++ b/hw/vfio/cpr-legacy.c
@@ -179,6 +179,8 @@ bool vfio_legacy_cpr_register_container(VFIOContainer *container, Error **errp)
                                          MIG_MODE_CPR_TRANSFER, -1) == 0;
     }
 
+    vfio_cpr_add_kvm_notifier();
+
     vmstate_register(NULL, -1, &vfio_container_vmstate, container);
 
     migration_add_notifier_mode(&container->cpr.transfer_notifier,
diff --git a/hw/vfio/cpr.c b/hw/vfio/cpr.c
index f5555cabe7..0e903cdd2f 100644
--- a/hw/vfio/cpr.c
+++ b/hw/vfio/cpr.c
@@ -190,3 +190,24 @@ const VMStateDescription vfio_cpr_pci_vmstate = {
         VMSTATE_END_OF_LIST()
     }
 };
+
+static NotifierWithReturn kvm_close_notifier;
+
+static int vfio_cpr_kvm_close_notifier(NotifierWithReturn *notifier,
+                                       MigrationEvent *e,
+                                       Error **errp)
+{
+    if (e->type == MIG_EVENT_PRECOPY_DONE) {
+        vfio_kvm_device_close();
+    }
+    return 0;
+}
+
+void vfio_cpr_add_kvm_notifier(void)
+{
+    if (!kvm_close_notifier.notify) {
+        migration_add_notifier_mode(&kvm_close_notifier,
+                                    vfio_cpr_kvm_close_notifier,
+                                    MIG_MODE_CPR_TRANSFER);
+    }
+}
diff --git a/hw/vfio/helpers.c b/hw/vfio/helpers.c
index d0dbab1d17..9a5f621545 100644
--- a/hw/vfio/helpers.c
+++ b/hw/vfio/helpers.c
@@ -117,6 +117,17 @@ bool vfio_get_info_dma_avail(struct vfio_iommu_type1_info *info,
 int vfio_kvm_device_fd = -1;
 #endif
 
+void vfio_kvm_device_close(void)
+{
+#ifdef CONFIG_KVM
+    kvm_close();
+    if (vfio_kvm_device_fd != -1) {
+        close(vfio_kvm_device_fd);
+        vfio_kvm_device_fd = -1;
+    }
+#endif
+}
+
 int vfio_kvm_device_add_fd(int fd, Error **errp)
 {
 #ifdef CONFIG_KVM
diff --git a/include/hw/vfio/vfio-cpr.h b/include/hw/vfio/vfio-cpr.h
index f21578da3c..d37acc4a0a 100644
--- a/include/hw/vfio/vfio-cpr.h
+++ b/include/hw/vfio/vfio-cpr.h
@@ -63,4 +63,6 @@ void vfio_cpr_delete_vector_fd(struct VFIOPCIDevice *vdev, const char *name,
 
 extern const VMStateDescription vfio_cpr_pci_vmstate;
 
+void vfio_cpr_add_kvm_notifier(void);
+
 #endif /* HW_VFIO_VFIO_CPR_H */
diff --git a/include/hw/vfio/vfio-device.h b/include/hw/vfio/vfio-device.h
index c616652ee7..f503837ccc 100644
--- a/include/hw/vfio/vfio-device.h
+++ b/include/hw/vfio/vfio-device.h
@@ -283,4 +283,6 @@ void vfio_device_set_fd(VFIODevice *vbasedev, const char *str, Error **errp);
 void vfio_device_init(VFIODevice *vbasedev, int type, VFIODeviceOps *ops,
                       DeviceState *dev, bool ram_discard);
 int vfio_device_get_aw_bits(VFIODevice *vdev);
+
+void vfio_kvm_device_close(void);
 #endif /* HW_VFIO_VFIO_COMMON_H */
diff --git a/include/system/kvm.h b/include/system/kvm.h
index 7cc60d26f2..4896a3c9c5 100644
--- a/include/system/kvm.h
+++ b/include/system/kvm.h
@@ -195,6 +195,7 @@ bool kvm_has_sync_mmu(void);
 int kvm_has_vcpu_events(void);
 int kvm_max_nested_state_length(void);
 int kvm_has_gsi_routing(void);
+void kvm_close(void);
 
 /**
  * kvm_arm_supports_user_irq