Adi Masputra wrote:
If you are wondering whether the stack will utilize hardware
checksum offload for non-simple IPv4/IPv6 packets, then the
answer to it is no. If there's any IPv4 option or intermediate
IPv6 header then the stack will punt and use software checksum.
Adi,
That might be true of the currently implementation of TCP/IP. But a
driver shouldn't assume that this will remain true. Drivers should do
the checksum offload operation based on how the checksum offload
interface is specified. And that specification doesn't say that the
checksum offload will never apply to packets with IPv4 options or IPv6
extension headers.
For a more descriptive set of comments, you can look at
IP_CKSUM_XMIT() macro in uts/common/inet/ip_impl.h
Please don't confuse the implementation with the interface specification.
Erik
_______________________________________________
networking-discuss mailing list
[email protected]
