Erik Stromdahl <erik.stromdahl@xxxxxxxxx> writes:
> From: Alagu Sankar <alagusankar@xxxxxxxxxxxxxxx>
>
> The existing implementation of initiating multiple sdio transfers for
> receive bundling is slowing down the receive speed.
>
> Instead of having one sdio transfer for each packet in the bundle, we
> read all packets in one sdio transfer.
>
> This results in significant performance improvement on some targets.
Do you have any numbers? Before and after would be nice to know.
> +static int ath10k_sdio_mbox_rx_fetch(struct ath10k *ar)
> {
> struct ath10k_sdio *ar_sdio = ath10k_sdio_priv(ar);
> + struct ath10k_sdio_rx_data *pkt = &ar_sdio->rx_pkts[0];
> struct sk_buff *skb = pkt->skb;
> int ret;
>
> - ret = ath10k_sdio_readsb(ar, ar_sdio->mbox_info.htc_addr,
> - skb->data, pkt->alloc_len);
> - pkt->status = ret;
> - if (!ret)
> + ret = ath10k_sdio_read(ar, ar_sdio->mbox_info.htc_addr,
> + skb->data, pkt->alloc_len);
> + if (ret) {
> + ar_sdio->n_rx_pkts = 0;
> + ath10k_sdio_mbox_free_rx_pkt(pkt);
> + } else {
> + pkt->status = ret;
> skb_put(skb, pkt->act_len);
> + }
With this you can avoid the else branch:
if (ret) {
ar_sdio->n_rx_pkts = 0;
ath10k_sdio_mbox_free_rx_pkt(pkt);
return ret;
}
> -static int ath10k_sdio_mbox_rx_fetch(struct ath10k *ar)
> +static int ath10k_sdio_mbox_rx_fetch_bundle(struct ath10k *ar)
> {
> struct ath10k_sdio *ar_sdio = ath10k_sdio_priv(ar);
> + struct ath10k_sdio_rx_data *pkt;
> int ret, i;
> + u32 pkt_offset = 0, pkt_bundle_len = 0;
> +
> + for (i = 0; i < ar_sdio->n_rx_pkts; i++)
> + pkt_bundle_len += ar_sdio->rx_pkts[i].alloc_len;
> +
> + if (pkt_bundle_len > ATH10K_SDIO_READ_BUF_SIZE) {
> + ret = -ENOMEM;
> + ath10k_err(ar, "bundle size (%d) exceeding limit %d\n",
> + pkt_bundle_len, ATH10K_SDIO_READ_BUF_SIZE);
As this is a recoverable case please use ath10k_warn(). And would
-ENOSPC be more descriptive error?
> + goto err;
> + }
> +
> + ret = ath10k_sdio_readsb(ar, ar_sdio->mbox_info.htc_addr,
> + ar_sdio->sdio_read_buf, pkt_bundle_len);
> + if (ret)
> + goto err;
>
> for (i = 0; i < ar_sdio->n_rx_pkts; i++) {
> - ret = ath10k_sdio_mbox_rx_packet(ar,
> - &ar_sdio->rx_pkts[i]);
> - if (ret)
> - goto err;
> + struct sk_buff *skb = ar_sdio->rx_pkts[i].skb;
> +
> + pkt = &ar_sdio->rx_pkts[i];
> + memcpy(skb->data, ar_sdio->sdio_read_buf + pkt_offset,
> + pkt->alloc_len);
> + pkt->status = 0;
> + skb_put(skb, pkt->act_len);
Shouldn't you call first skb_put() and then memcpy()?
--
Kalle Valo
