Re: [PATCH net-next 1/5] net: ethtool: only allow set_rxnfc with rss + ring_cookie if driver opts in

[Gal Pressman <gal@nvidia.com>]

Hi Edward,

On 13/11/2024 14:13, edward.cree@amd.com wrote:
> From: Edward Cree <ecree.xilinx@gmail.com>
> 
> Ethtool ntuple filters with FLOW_RSS were originally defined as adding
>  the base queue ID (ring_cookie) to the value from the indirection table,
>  so that the same table could distribute over more than one set of queues
>  when used by different filters.

TBH, I'm not sure I understand the difference? Perhaps you can share an
example?

> However, some drivers / hardware ignore the ring_cookie, and simply use
>  the indirection table entries as queue IDs directly.  Thus, for drivers
>  which have not opted in by setting ethtool_ops.cap_rss_rxnfc_adds to
>  declare that they support the original (addition) semantics, reject in
>  ethtool_set_rxnfc any filter which combines FLOW_RSS and a nonzero ring.
> (For a ring_cookie of zero, both behaviours are equivalent.)
> Set the cap bit in sfc, as it is known to support this feature.
> 
> Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
> ---
> diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
> index 7da94e26ced6..d86399bcf223 100644
> --- a/net/ethtool/ioctl.c
> +++ b/net/ethtool/ioctl.c
> @@ -992,6 +992,11 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev,
>  	if (rc)
>  		return rc;
>  
> +	/* Nonzero ring with RSS only makes sense if NIC adds them together */
> +	if (info.flow_type & FLOW_RSS && !ops->cap_rss_rxnfc_adds &&
> +	    ethtool_get_flow_spec_ring(info.fs.ring_cookie))
> +		return -EINVAL;

I believe this check shouldn't happen when we do ETHTOOL_SRXCLSRLDEL as
flow_type is garbage, WDYT?

> +
>  	if (ops->get_rxfh) {
>  		struct ethtool_rxfh_param rxfh = {};
>  
>