On Tue, Jan 10, 2023 at 12:57:38AM -0500, Michael S. Tsirkin wrote: > On Tue, Jan 10, 2023 at 12:25:02AM -0500, Michael S. Tsirkin wrote: > > > This will give extra pressure on the management stack, e.g it requires > > > the device to have an out of spec way for introspection. > > > > > > Thanks > > > > As I tried to explain this is already the case. Feature bits do not > > describe device capabilities fully, some of them are in config space. > > To be precise, this does not necessarily require introspection, but > it does require management control over config space > such as supported hash types just like it has control over feature bits. > E.g. QEMU currently seems to hard-code these to > #define VIRTIO_NET_RSS_SUPPORTED_HASHES (VIRTIO_NET_RSS_HASH_TYPE_IPv4 | \ > VIRTIO_NET_RSS_HASH_TYPE_TCPv4 | \ > VIRTIO_NET_RSS_HASH_TYPE_UDPv4 | \ > VIRTIO_NET_RSS_HASH_TYPE_IPv6 | \ > VIRTIO_NET_RSS_HASH_TYPE_TCPv6 | \ > VIRTIO_NET_RSS_HASH_TYPE_UDPv6 | \ > VIRTIO_NET_RSS_HASH_TYPE_IP_EX | \ > VIRTIO_NET_RSS_HASH_TYPE_TCP_EX | \ > VIRTIO_NET_RSS_HASH_TYPE_UDP_EX) > > but there's no reason not to give management control over these.
Yes, QEMU has requirements for live migration: the PCI config space will be checked in get_pci_config_device(), and if src and dst are inconsistent, it will prompt that the live migration failed. In fact, this is also done within our group. Live migration requires that the two VMs have the same rss configuration, otherwise the migration will fail. Therefore, it seems that we can regularize the description of VIRTIO_NET_F_HASH_TUNNEL into "[VIRTIO_NET_F_HASH_TUNNEL(52)] Device supports inner header hash for tunnel-encapsulated packets.", and use different hash_types to help the migration determine whether it can succeed. Thanks. > > -- > MST --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
