Re: [dpdk-dev] [PATCH 12/18] fm10k: add PF RSS support

[Neil Horman <nhorman@tuxdriver.com>]

On Fri, Jan 30, 2015 at 01:07:28PM +0800, Chen Jing D(Mark) wrote:
> From: Jeff Shaw <jeffrey.b.shaw@intel.com>
> 
> 1. Configure RSS in fm10k_dev_rx_init function.
> 2. Add fm10k_rss_hash_update and fm10k_rss_hash_conf_get to get
>    and inquery RSS configuration.
> 
> Signed-off-by: Jeff Shaw <jeffrey.b.shaw@intel.com>
> Signed-off-by: Chen Jing D(Mark) <jing.d.chen@intel.com>
> ---
>  lib/librte_pmd_fm10k/fm10k_ethdev.c |  156 +++++++++++++++++++++++++++++++++++
>  1 files changed, 156 insertions(+), 0 deletions(-)
> 
> diff --git a/lib/librte_pmd_fm10k/fm10k_ethdev.c b/lib/librte_pmd_fm10k/fm10k_ethdev.c
> index 9907906..4711047 100644
> --- a/lib/librte_pmd_fm10k/fm10k_ethdev.c
> +++ b/lib/librte_pmd_fm10k/fm10k_ethdev.c
> @@ -269,6 +269,78 @@ fm10k_dev_configure(struct rte_eth_dev *dev)
>  	return 0;
>  }
>  
> +static void
> +fm10k_dev_mq_rx_configure(struct rte_eth_dev *dev)
> +{
> +	struct fm10k_hw *hw = FM10K_DEV_PRIVATE_TO_HW(dev->data->dev_private);
> +	struct rte_eth_conf *dev_conf = &dev->data->dev_conf;
> +	uint32_t mrqc, *key, i, reta, j;
> +	uint64_t hf;
> +
> +#define RSS_KEY_SIZE 40
> +	static uint8_t rss_intel_key[RSS_KEY_SIZE] = {
> +		0x6D, 0x5A, 0x56, 0xDA, 0x25, 0x5B, 0x0E, 0xC2,
> +		0x41, 0x67, 0x25, 0x3D, 0x43, 0xA3, 0x8F, 0xB0,
> +		0xD0, 0xCA, 0x2B, 0xCB, 0xAE, 0x7B, 0x30, 0xB4,
> +		0x77, 0xCB, 0x2D, 0xA3, 0x80, 0x30, 0xF2, 0x0C,
> +		0x6A, 0x42, 0xB7, 0x3B, 0xBE, 0xAC, 0x01, 0xFA,
> +	};
> +
> +	if (dev->data->nb_rx_queues == 1 ||
> +	    dev_conf->rxmode.mq_mode != ETH_MQ_RX_RSS ||
> +	    dev_conf->rx_adv_conf.rss_conf.rss_hf == 0)
> +		return;
> +
> +	/* random key is rss_intel_key (default) or user provided (rss_key) */
> +	if (dev_conf->rx_adv_conf.rss_conf.rss_key == NULL)
> +		key = (uint32_t *)rss_intel_key;
Its not really random if its statically allocated and assigned.  The kernel has
started randomizing these default keys, it seems like a sensible thing to do
here as well, as this is the init path and not performance sensitive

Neil