svn commit: r205104 - in head/sys: dev/xen/netback netinet
tuexen at fh-muenster.de
Tue Mar 16 09:25:48 UTC 2010
shouldn't be the right fix "for now" that we do not
offload SCTP checksum computation for IPv6?
The point is the semantic of the CSUM_SCTP flag. I think
it means "will csum SCTP for IPv4" as all the other
flags (CSUM_TCP, CSUM_UDP).
With "for now" I mean "until there is a IPv6 checksum
offload infrastructure" (I know, it is on my TODO list).
On Mar 13, 2010, at 8:54 PM, Randall Stewart wrote:
> Hmm... M_PROTO* good idea ;-)
> On Mar 13, 2010, at 10:56 PM, Bruce Simpson wrote:
>> On 03/13/10 13:53, Robert N. M. Watson wrote:
>>> On Mar 13, 2010, at 1:50 PM, Randall Stewart wrote:
>>>> I could refactor that this way if you want... it would mean a few more de-ref's and
>>>> looking to see if its a v4 or v6 packet and then doing the proper offset...
>> This is the sort of thing which M_PROTO* flags are good for.
>> Derefs in the hot path should be amortized whenever that makes sense.
> Randall Stewart
> 803-317-4952 (cell)
More information about the svn-src-all