On 7/26/2019 1:35 AM, simei wrote:
> From: Simei Su <simei...@intel.com>
>
> This RFC reserves several bits as input set selection from bottom
> of the 64 bits. The flow type is combined with input set to
> represent rss types.
>
> Correct the input set mask to align with the definition in rte_ethdev.h.
> for example:
> ETH_RSS_IPV4 | ETH_RSS_INSET_L3_SRC: hash on src ip address only
> ETH_RSS_IPV4_UDP | ETH_RSS_INSET_L4_DST: hash on src/dst IP and
> dst UDP port
> ETH_RSS_L2_PAYLOAD | ETH_RSS_INSET_L2_DST: hash on dst mac address
>
> Signed-off-by: Simei Su <simei...@intel.com>
> ---
> lib/librte_ethdev/rte_ethdev.h | 12 ++++++++++++
> 1 file changed, 12 insertions(+)
>
> diff --git a/lib/librte_ethdev/rte_ethdev.h b/lib/librte_ethdev/rte_ethdev.h
> index dc6596b..452d29f 100644
> --- a/lib/librte_ethdev/rte_ethdev.h
> +++ b/lib/librte_ethdev/rte_ethdev.h
> @@ -508,6 +508,18 @@ struct rte_eth_rss_conf {
> #define ETH_RSS_GENEVE (1ULL << RTE_ETH_FLOW_GENEVE)
> #define ETH_RSS_NVGRE (1ULL << RTE_ETH_FLOW_NVGRE)
>
> +/*
> + * The following six macros are used combined with ETH_RSS_* to
> + * represent rss types. The structure rte_flow_action_rss.types is
> + * 64-bit wide and we reserve couple bits here for input set selection.
> + */
> +#define ETH_RSS_INSET_L2_SRC 0x0400000000000000
> +#define ETH_RSS_INSET_L2_DST 0x0800000000000000
> +#define ETH_RSS_INSET_L3_SRC 0x1000000000000000
> +#define ETH_RSS_INSET_L3_DST 0x2000000000000000
> +#define ETH_RSS_INSET_L4_SRC 0x4000000000000000
> +#define ETH_RSS_INSET_L4_DST 0x8000000000000000
A question, will it easier to represent/comprehend if we replace these as
(1ULL << ###) instead of too many zeros ?
> +
> #define ETH_RSS_IP ( \
> ETH_RSS_IPV4 | \
> ETH_RSS_FRAG_IPV4 | \
>
