Re: [tsvwg] RDMA Support by UDP FRAG Option

[Tom Herbert <[e-mail]>]

On Sun, Jun 20, 2021, 8:04 PM Joseph Touch <[e-mail]> wrote:

>
>
> On Jun 20, 2021, at 6:24 PM, Tom Herbert <[e-mail]> wrote:
>
> …
>
>
> Mike,
>
> Please consider the simple case where the UDP checksum is set. There
> are two common methods to offload the checksum: protocol agnostic and
> protocol specific. In the protocol agnostic case the stack provides
> the starting offset of the checksum area (offset of the UDP header)
> and the offset of the checksum field to write the result (UDP
> checksum)-- these values are placed in the TX descriptor for a packet.
> The checksum field is primed with the pseudo header. The end of the
> checksum area is the end of the packet
>
>
> No, it is not and has never been. Again, see the text I quoted from RFCs
> 768, repeated below:
>
> Checksum is the 16-bit one's complement of the one's complement sum of a
> pseudo header of information from the IP header, the UDP header, and the
> data,  padded  with zero octets  at the end (if  necessary)  to  make  a
> multiple of two octets.
>
>
> Data, which is the UDP field. Not entire IP packet payload, as noted just
> before the above paragraph:
>
> Length  is the length  in octets  of this user datagram  including  this
> header  and the data.   (This  means  the minimum value of the length is
> eight.)
>
>
> Please stop repeating any claim to the contrary, except to note an error
> in an existing implementation (which should be corrected, not propagated).
>

I am describing how real implementation actually *works*. There is no error
because the correct checksum per RFC768 can be produced.

(trying to add a length of the
> area in the hardware interface is a non-starter). If there is surplus
> and that sums to zero then the algorithm works unchanged. If the
> surplus area sums to non-zero then that requires an offsetting sum by
> the host adding in the negative sum value of the surplus area into the
> checksum field. The good news is that this works with any case of
> checksum offload in a UDP packet including encapsulated checksums.
>
>
> Checksums of packets that encapsulate IP/UDP as a payload would cover the
> entire IP packet, not just the UDP portion.
>
> Checksums of IP/UDP that encapsulate other packets as a payload would
> place that packet in the UDP data area, preceding the options if not
> fragmented.
>
> If errors are corrected, we can stop trying to do cartwheels to enable
> them.
>

> Joe
>