Date: Tue, 16 Mar 2010 10:25:44 +0100 From: Michael Tuexen <tuexen@fh-muenster.de> To: Randall Stewart <rstewart@huawei.com> Cc: svn-src-head@FreeBSD.org, svn-src-all@FreeBSD.org, Bruce Simpson <bms@incunabulum.net>, "Robert N. M. Watson" <rwatson@FreeBSD.org>, src-committers@FreeBSD.org Subject: Re: svn commit: r205104 - in head/sys: dev/xen/netback netinet netinet6 Message-ID: <FC4E1314-341A-4B62-94A8-99263640BCF6@fh-muenster.de> In-Reply-To: <17A93DA8-4022-4AA6-B1B2-28CD3E7719C2@lakerest.net> References: <201003122258.o2CMwqDM039077@svn.freebsd.org> <alpine.BSF.2.00.1003131257060.51476@fledge.watson.org> <2F4A2F84-4955-49C2-B25E-BB987BC27815@lakerest.net> <92C0A9B0-9297-4F56-A6A1-603006423230@FreeBSD.org> <4B9B99A9.7040904@incunabulum.net> <17A93DA8-4022-4AA6-B1B2-28CD3E7719C2@lakerest.net>
next in thread | previous in thread | raw e-mail | index | archive | help
Hi Randy, 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). Best regards Michael On Mar 13, 2010, at 8:54 PM, Randall Stewart wrote: > Hmm... M_PROTO* good idea ;-) >=20 >=20 > On Mar 13, 2010, at 10:56 PM, Bruce Simpson wrote: >=20 >> On 03/13/10 13:53, Robert N. M. Watson wrote: >>> On Mar 13, 2010, at 1:50 PM, Randall Stewart wrote: >>>=20 >>>> 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... >>>>=20 >>=20 >> This is the sort of thing which M_PROTO* flags are good for. >>=20 >> Derefs in the hot path should be amortized whenever that makes sense. >>=20 >=20 > ------------------------------ > Randall Stewart > 803-317-4952 (cell) > 803-345-0391(direct) >=20 >=20
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?FC4E1314-341A-4B62-94A8-99263640BCF6>