[dpdk-dev] [PATCH] net/i40e: fix Tx fn selection when using new ethdev offloads

[Ananyev, Konstantin]

Hi Bruce,

> 
> The Tx function selection code in the driver only used the older txq
> flags values to check whether the scalar or vector functions should be
> used. This caused performance regressions with testpmd io-fwd as the
> scalar path rather than the vector one was being used in the default
> case. Fix this by changing the code to take account of new offloads and
> deleting the defines used for the old ones.
> 
> Fixes: 7497d3e2f777 ("net/i40e: convert to new Tx offloads API")
> 
> Signed-off-by: Bruce Richardson <bruce.richardson at intel.com>
> ---
>  drivers/net/i40e/i40e_rxtx.c | 45 +++++++++++++++++++++++---------------------
>  1 file changed, 24 insertions(+), 21 deletions(-)
> 
> diff --git a/drivers/net/i40e/i40e_rxtx.c b/drivers/net/i40e/i40e_rxtx.c
> index ec1ce54ca..c523af575 100644
> --- a/drivers/net/i40e/i40e_rxtx.c
> +++ b/drivers/net/i40e/i40e_rxtx.c
> @@ -40,9 +40,6 @@
>  /* Base address of the HW descriptor ring should be 128B aligned. */
>  #define I40E_RING_BASE_ALIGN	128
> 
> -#define I40E_SIMPLE_FLAGS ((uint32_t)ETH_TXQ_FLAGS_NOMULTSEGS | \
> -					ETH_TXQ_FLAGS_NOOFFLOADS)
> -
>  #define I40E_TXD_CMD (I40E_TX_DESC_CMD_EOP | I40E_TX_DESC_CMD_RS)
> 
>  #ifdef RTE_LIBRTE_IEEE1588
> @@ -70,6 +67,12 @@
>  #define I40E_TX_OFFLOAD_NOTSUP_MASK \
>  		(PKT_TX_OFFLOAD_MASK ^ I40E_TX_OFFLOAD_MASK)
> 
> +static const uint64_t i40e_simple_ol_mask = (DEV_TX_OFFLOAD_MULTI_SEGS |
> +		DEV_TX_OFFLOAD_VLAN_INSERT |
> +		DEV_TX_OFFLOAD_SCTP_CKSUM |
> +		DEV_TX_OFFLOAD_UDP_CKSUM |
> +		DEV_TX_OFFLOAD_TCP_CKSUM);
> +

Seems incomplete.
>From i40e_ethdev.c full-featured tx supports:
dev_info->tx_offload_capa =
                DEV_TX_OFFLOAD_VLAN_INSERT |
                DEV_TX_OFFLOAD_QINQ_INSERT |
                DEV_TX_OFFLOAD_IPV4_CKSUM |
                DEV_TX_OFFLOAD_UDP_CKSUM |
                DEV_TX_OFFLOAD_TCP_CKSUM |
                DEV_TX_OFFLOAD_SCTP_CKSUM |
                DEV_TX_OFFLOAD_OUTER_IPV4_CKSUM |
                DEV_TX_OFFLOAD_TCP_TSO |
                DEV_TX_OFFLOAD_VXLAN_TNL_TSO |
                DEV_TX_OFFLOAD_GRE_TNL_TSO |
                DEV_TX_OFFLOAD_IPIP_TNL_TSO |
                DEV_TX_OFFLOAD_GENEVE_TNL_TSO;

So we probably need the same here plus multiseg.
BTW, it is really strange that we don't have multiseg in tx_offload_capa.
Should be present I think.
Might be worse to create a new define for it, or just use dev_info->tx_offload_capa directly.
Konstantin



>  static inline void
>  i40e_rxd_to_vlan_tci(struct rte_mbuf *mb, volatile union i40e_rx_desc *rxdp)
>  {
> @@ -2108,11 +2111,9 @@ i40e_dev_tx_queue_setup_runtime(struct rte_eth_dev *dev,
>  				 dev->data->nb_tx_queues)) {
>  		/**
>  		 * If it is the first queue to setup,
> -		 * set all flags to default and call
> +		 * set all flags and call
>  		 * i40e_set_tx_function.
>  		 */
> -		ad->tx_simple_allowed = true;
> -		ad->tx_vec_allowed = true;
>  		i40e_set_tx_function_flag(dev, txq);
>  		i40e_set_tx_function(dev);
>  		return 0;
> @@ -2128,9 +2129,8 @@ i40e_dev_tx_queue_setup_runtime(struct rte_eth_dev *dev,
>  	}
>  	/* check simple tx conflict */
>  	if (ad->tx_simple_allowed) {
> -		if (((txq->txq_flags & I40E_SIMPLE_FLAGS) !=
> -		     I40E_SIMPLE_FLAGS) ||
> -		    txq->tx_rs_thresh < RTE_PMD_I40E_TX_MAX_BURST) {
> +		if ((txq->offloads & i40e_simple_ol_mask) != 0 ||
> +				txq->tx_rs_thresh < RTE_PMD_I40E_TX_MAX_BURST) {
>  			PMD_DRV_LOG(ERR, "No-simple tx is required.");
>  			return -EINVAL;
>  		}
> @@ -3080,18 +3080,21 @@ i40e_set_tx_function_flag(struct rte_eth_dev *dev, struct i40e_tx_queue *txq)
>  		I40E_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
> 
>  	/* Use a simple Tx queue (no offloads, no multi segs) if possible */
> -	if (((txq->txq_flags & I40E_SIMPLE_FLAGS) == I40E_SIMPLE_FLAGS)
> -			&& (txq->tx_rs_thresh >= RTE_PMD_I40E_TX_MAX_BURST)) {
> -		if (txq->tx_rs_thresh <= RTE_I40E_TX_MAX_FREE_BUF_SZ) {
> -			PMD_INIT_LOG(DEBUG, "Vector tx"
> -				     " can be enabled on this txq.");
> -
> -		} else {
> -			ad->tx_vec_allowed = false;
> -		}
> -	} else {
> -		ad->tx_simple_allowed = false;
> -	}
> +	ad->tx_simple_allowed = ((txq->offloads & i40e_simple_ol_mask) == 0 &&
> +			txq->tx_rs_thresh >= RTE_PMD_I40E_TX_MAX_BURST);
> +	ad->tx_vec_allowed = (ad->tx_simple_allowed &&
> +			txq->tx_rs_thresh <= RTE_I40E_TX_MAX_FREE_BUF_SZ);
> +
> +	if (ad->tx_vec_allowed)
> +		PMD_INIT_LOG(DEBUG, "Vector Tx can be enabled on Tx queue %u.",
> +				txq->queue_id);
> +	else if (ad->tx_simple_allowed)
> +		PMD_INIT_LOG(DEBUG, "Simple Tx can be enabled on Tx queue %u.",
> +				txq->queue_id);
> +	else
> +		PMD_INIT_LOG(DEBUG,
> +				"Neither simple nor vector Tx enabled on Tx queue %u\n",
> +				txq->queue_id);
>  }
> 
>  void __attribute__((cold))
> --
> 2.14.3