|
|
|
|
|
|
|
|
|
|
xen-devel
Re: [Xen-devel] [0/5] [NET]: Add TSO support
On 27 Jun 2006, at 13:02, Herbert Xu wrote:
The following patches add TCP Segmentation Offload (TSO) support in the
domU => dom0 direction. If everyone's happy with this approach then
it's
trivial to do the same thing for the opposite direction.
I've checked in all but the netfront patch. The glitches so far are:
1. The GSO patch broke netback, because netback/interface.c accesses
dev->xmit_lock. None of your patches fixed this and you can't build the
driver unless it's fixed -- did you somehow miss that file from one of
the patches you sent?
2. The new 'wire format' with netif_tx_extra: I placed the GSO fields
inside a struct inside a union, so we can extend the union with other
extra-info types in future. I hope that's okay and in line with what
you intended.
3. Wire format again: we need some extra documentation and info in
netif.h for the new GSO fields. Currently they conveniently directly
correspond to fields in a Linux skbuff: you read them out in netfront
and write them straight back in netback. That's fine for Linux for now,
but not so good for other OSes, nor potentially if the Linux GSO
internals change later.
In particular the gso_type field is concerning. We should provide
defines for the legitimate values of that field in netif.h, with a
comment explaining what each one means. Extra comments are also
required for the other two fields, to convince us that they aren't
Linux-specific in some way. Some brief info about how GSO works in
general, including usage of those fields, would help.
This is why I haven't added the netfront patch yet -- I don't want
domU's using the new interface until we're satisfied we're not going to
have to change the interface and break compatibility.
Thanks,
Keir
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel
|
|
|
|
|