blob: a0c1ff5992332f969633ebf7956549f1d04fd9e8 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
|
<think>
Okay, so I need to classify this bug report from QEMU into one of the given categories. Let me read through the problem carefully.
The user is trying to migrate a guest using vhost-net from RHEL 6 to RHEL 7. They're encountering an error where the target machine's QEMU rejects the PCI configuration. The error messages mention issues with loading the virtio-net device and invalid arguments during migration.
Looking at the test case, when they use vhost=on on both machines, the migration fails. But if they disable vhost on the source or set disable-modern=true on the target, it works. This suggests that the problem is related to how QEMU handles VIRTIO features during migration between different kernel versions.
The error seems to be happening when the target QEMU tries to load the device configuration after migration. The fact that the target kernel supports VIRTIO_F_VERSION_1 but the source doesn't might be causing a mismatch in expectations during migration.
Possible categories: I'm considering 'network' because vhost-net is related to network virtualization. It's not a mistranslation or assembly issue. Other options like 'hypervisor', 'kernel', or 'peripherals' could fit, but since it's about network devices and their configuration during migration, 'network' seems the most appropriate.
I think the bug is in how QEMU handles device configuration when migrating between kernels with different VIRTIO versions, leading to a PCI config error. So the category should be 'network'.
</think>
The issue involves vhost-net and virtio-net-pci devices failing during migration due to kernel version differences in handling VIRTIO_F_VERSION_1. This relates directly to network device configuration.
**network**
|