On Thu, 20 Jun 2019 13:24:20 -0700, Shannon Nelson wrote:
> Add both the Tx and Rx queue setup and handling.  The related
> stats display come later.  Instead of using the generic napi
> routines used by the slow-path command, the Tx and Rx paths
> are simplified and inlined in one file in order to get better
> compiler optimizations.
> 
> Signed-off-by: Shannon Nelson <snel...@pensando.io>

> diff --git a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c 
> b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c
> index 5ebfaa320edf..6dfcada9e822 100644
> --- a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c
> +++ b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c
> @@ -351,6 +351,54 @@ int ionic_debugfs_add_qcq(struct lif *lif, struct qcq 
> *qcq)
>                                   desc_blob);
>       }
>  
> +     if (qcq->flags & QCQ_F_TX_STATS) {
> +             stats_dentry = debugfs_create_dir("tx_stats", q_dentry);
> +             if (IS_ERR_OR_NULL(stats_dentry))
> +                     return PTR_ERR(stats_dentry);
> +
> +             debugfs_create_u64("dma_map_err", 0400, stats_dentry,
> +                                &qcq->stats->tx.dma_map_err);
> +             debugfs_create_u64("pkts", 0400, stats_dentry,
> +                                &qcq->stats->tx.pkts);
> +             debugfs_create_u64("bytes", 0400, stats_dentry,
> +                                &qcq->stats->tx.bytes);
> +             debugfs_create_u64("clean", 0400, stats_dentry,
> +                                &qcq->stats->tx.clean);
> +             debugfs_create_u64("linearize", 0400, stats_dentry,
> +                                &qcq->stats->tx.linearize);
> +             debugfs_create_u64("no_csum", 0400, stats_dentry,
> +                                &qcq->stats->tx.no_csum);
> +             debugfs_create_u64("csum", 0400, stats_dentry,
> +                                &qcq->stats->tx.csum);
> +             debugfs_create_u64("crc32_csum", 0400, stats_dentry,
> +                                &qcq->stats->tx.crc32_csum);
> +             debugfs_create_u64("tso", 0400, stats_dentry,
> +                                &qcq->stats->tx.tso);
> +             debugfs_create_u64("frags", 0400, stats_dentry,
> +                                &qcq->stats->tx.frags);

I wonder why debugfs over ethtool -S?

> +static int ionic_tx(struct queue *q, struct sk_buff *skb)
> +{
> +     struct tx_stats *stats = q_to_tx_stats(q);
> +     int err;
> +
> +     if (skb->ip_summed == CHECKSUM_PARTIAL)
> +             err = ionic_tx_calc_csum(q, skb);
> +     else
> +             err = ionic_tx_calc_no_csum(q, skb);
> +     if (err)
> +             return err;
> +
> +     err = ionic_tx_skb_frags(q, skb);
> +     if (err)
> +             return err;
> +
> +     skb_tx_timestamp(skb);
> +     stats->pkts++;
> +     stats->bytes += skb->len;

nit: I think counting stats on completion may be a better idea,
     otherwise when you can a full ring on stop your HW counters are
     guaranteed to be different than SW counters.  Am I wrong?

> +     ionic_txq_post(q, !netdev_xmit_more(), ionic_tx_clean, skb);
> +
> +     return 0;
> +}
> +
> +static int ionic_tx_descs_needed(struct queue *q, struct sk_buff *skb)
> +{
> +     struct tx_stats *stats = q_to_tx_stats(q);
> +     int err;
> +
> +     /* If TSO, need roundup(skb->len/mss) descs */
> +     if (skb_is_gso(skb))
> +             return (skb->len / skb_shinfo(skb)->gso_size) + 1;

This doesn't look correct, are you sure you don't want
skb_shinfo(skb)->gso_segs ?

> +
> +     /* If non-TSO, just need 1 desc and nr_frags sg elems */
> +     if (skb_shinfo(skb)->nr_frags <= IONIC_TX_MAX_SG_ELEMS)
> +             return 1;
> +
> +     /* Too many frags, so linearize */
> +     err = skb_linearize(skb);
> +     if (err)
> +             return err;
> +
> +     stats->linearize++;
> +
> +     /* Need 1 desc and zero sg elems */
> +     return 1;
> +}
> +
> +netdev_tx_t ionic_start_xmit(struct sk_buff *skb, struct net_device *netdev)
> +{
> +     u16 queue_index = skb_get_queue_mapping(skb);
> +     struct lif *lif = netdev_priv(netdev);
> +     struct queue *q;
> +     int ndescs;
> +     int err;
> +
> +     if (unlikely(!test_bit(LIF_UP, lif->state))) {
> +             dev_kfree_skb(skb);
> +             return NETDEV_TX_OK;
> +     }

Surely you stop TX before taking the queues down?

> +     if (likely(lif_to_txqcq(lif, queue_index)))
> +             q = lif_to_txq(lif, queue_index);
> +     else
> +             q = lif_to_txq(lif, 0);
> +
> +     ndescs = ionic_tx_descs_needed(q, skb);
> +     if (ndescs < 0)
> +             goto err_out_drop;
> +
> +     if (!ionic_q_has_space(q, ndescs)) {
> +             netif_stop_subqueue(netdev, queue_index);
> +             q->stop++;
> +
> +             /* Might race with ionic_tx_clean, check again */
> +             smp_rmb();
> +             if (ionic_q_has_space(q, ndescs)) {
> +                     netif_wake_subqueue(netdev, queue_index);
> +                     q->wake++;
> +             } else {
> +                     return NETDEV_TX_BUSY;
> +             }
> +     }
> +
> +     if (skb_is_gso(skb))
> +             err = ionic_tx_tso(q, skb);
> +     else
> +             err = ionic_tx(q, skb);
> +
> +     if (err)
> +             goto err_out_drop;
> +
> +     return NETDEV_TX_OK;
> +
> +err_out_drop:
> +     q->drop++;
> +     dev_kfree_skb(skb);
> +     return NETDEV_TX_OK;
> +}

Reply via email to