Re: [net-next v14 07/12] net: mtip: Add mtip_switch_{rx|tx} functions to the L2 switch driver

[Paolo Abeni <pabeni@redhat.com>]

On 7/1/25 1:49 PM, Lukasz Majewski wrote:
> diff --git a/drivers/net/ethernet/freescale/mtipsw/mtipl2sw.c b/drivers/net/ethernet/freescale/mtipsw/mtipl2sw.c
> index 63afdf2beea6..b5a82748b39b 100644
> --- a/drivers/net/ethernet/freescale/mtipsw/mtipl2sw.c
> +++ b/drivers/net/ethernet/freescale/mtipsw/mtipl2sw.c
> @@ -228,6 +228,39 @@ struct mtip_port_info *mtip_portinfofifo_read(struct switch_enet_private *fep)
>  	return info;
>  }
>  
> +static void mtip_atable_get_entry_port_number(struct switch_enet_private *fep,
> +					      unsigned char *mac_addr, u8 *port)
> +{
> +	int block_index, block_index_end, entry;
> +	u32 mac_addr_lo, mac_addr_hi;
> +	u32 read_lo, read_hi;
> +
> +	mac_addr_lo = (u32)((mac_addr[3] << 24) | (mac_addr[2] << 16) |
> +			    (mac_addr[1] << 8) | mac_addr[0]);
> +	mac_addr_hi = (u32)((mac_addr[5] << 8) | (mac_addr[4]));
> +
> +	block_index = GET_BLOCK_PTR(crc8_calc(mac_addr));
> +	block_index_end = block_index + ATABLE_ENTRY_PER_SLOT;
> +
> +	/* now search all the entries in the selected block */
> +	for (entry = block_index; entry < block_index_end; entry++) {
> +		mtip_read_atable(fep, entry, &read_lo, &read_hi);
> +		*port = MTIP_PORT_FORWARDING_INIT;
> +
> +		if (read_lo == mac_addr_lo &&
> +		    ((read_hi & 0x0000FFFF) ==
> +		     (mac_addr_hi & 0x0000FFFF))) {
> +			/* found the correct address */
> +			if ((read_hi & (1 << 16)) && (!(read_hi & (1 << 17))))
> +				*port = FIELD_GET(AT_PORT_MASK, read_hi);
> +			break;
> +		}
> +	}
> +
> +	dev_dbg(&fep->pdev->dev, "%s: MAC: %pM PORT: 0x%x\n", __func__,
> +		mac_addr, *port);
> +}
> +
>  /* Clear complete MAC Look Up Table */
>  void mtip_clear_atable(struct switch_enet_private *fep)
>  {
> @@ -825,11 +858,217 @@ static irqreturn_t mtip_interrupt(int irq, void *ptr_fep)
>  
>  static void mtip_switch_tx(struct net_device *dev)
>  {
> +	struct mtip_ndev_priv *priv = netdev_priv(dev);
> +	struct switch_enet_private *fep = priv->fep;
> +	unsigned short status;
> +	struct sk_buff *skb;
> +	struct cbd_t *bdp;
> +
> +	spin_lock(&fep->hw_lock);
> +	bdp = fep->dirty_tx;
> +
> +	while (((status = bdp->cbd_sc) & BD_ENET_TX_READY) == 0) {
> +		if (bdp == fep->cur_tx && fep->tx_full == 0)
> +			break;
> +
> +		dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr,
> +				 MTIP_SWITCH_TX_FRSIZE, DMA_TO_DEVICE);
> +		bdp->cbd_bufaddr = 0;
> +		skb = fep->tx_skbuff[fep->skb_dirty];
> +		/* Check for errors */
> +		if (status & (BD_ENET_TX_HB | BD_ENET_TX_LC |
> +				   BD_ENET_TX_RL | BD_ENET_TX_UN |
> +				   BD_ENET_TX_CSL)) {
> +			dev->stats.tx_errors++;
> +			if (status & BD_ENET_TX_HB)  /* No heartbeat */
> +				dev->stats.tx_heartbeat_errors++;
> +			if (status & BD_ENET_TX_LC)  /* Late collision */
> +				dev->stats.tx_window_errors++;
> +			if (status & BD_ENET_TX_RL)  /* Retrans limit */
> +				dev->stats.tx_aborted_errors++;
> +			if (status & BD_ENET_TX_UN)  /* Underrun */
> +				dev->stats.tx_fifo_errors++;
> +			if (status & BD_ENET_TX_CSL) /* Carrier lost */
> +				dev->stats.tx_carrier_errors++;
> +		} else {
> +			dev->stats.tx_packets++;
> +		}
> +
> +		if (status & BD_ENET_TX_READY)
> +			dev_err(&fep->pdev->dev,
> +				"Enet xmit interrupt and TX_READY.\n");
> +
> +		/* Deferred means some collisions occurred during transmit,
> +		 * but we eventually sent the packet OK.
> +		 */
> +		if (status & BD_ENET_TX_DEF)
> +			dev->stats.collisions++;
> +
> +		/* Free the sk buffer associated with this last transmit */
> +		dev_consume_skb_irq(skb);
> +		fep->tx_skbuff[fep->skb_dirty] = NULL;
> +		fep->skb_dirty = (fep->skb_dirty + 1) & TX_RING_MOD_MASK;
> +
> +		/* Update pointer to next buffer descriptor to be transmitted */
> +		if (status & BD_ENET_TX_WRAP)
> +			bdp = fep->tx_bd_base;
> +		else
> +			bdp++;
> +
> +		/* Since we have freed up a buffer, the ring is no longer
> +		 * full.
> +		 */
> +		if (fep->tx_full) {
> +			fep->tx_full = 0;
> +			if (netif_queue_stopped(dev))
> +				netif_wake_queue(dev);
> +		}
> +	}
> +	fep->dirty_tx = bdp;
> +	spin_unlock(&fep->hw_lock);
>  }
>  
> +/* During a receive, the cur_rx points to the current incoming buffer.
> + * When we update through the ring, if the next incoming buffer has
> + * not been given to the system, we just set the empty indicator,
> + * effectively tossing the packet.
> + */
>  static int mtip_switch_rx(struct net_device *dev, int budget, int *port)
>  {
> -	return -ENOMEM;
> +	struct mtip_ndev_priv *priv = netdev_priv(dev);
> +	u8 *data, rx_port = MTIP_PORT_FORWARDING_INIT;
> +	struct switch_enet_private *fep = priv->fep;
> +	unsigned short status, pkt_len;
> +	struct net_device *pndev;
> +	struct ethhdr *eth_hdr;
> +	int pkt_received = 0;
> +	struct sk_buff *skb;
> +	struct cbd_t *bdp;
> +	struct page *page;
> +
> +	/* First, grab all of the stats for the incoming packet.
> +	 * These get messed up if we get called due to a busy condition.
> +	 */
> +	bdp = fep->cur_rx;
> +
> +	while (!((status = bdp->cbd_sc) & BD_ENET_RX_EMPTY)) {
> +		if (pkt_received >= budget)
> +			break;
> +
> +		pkt_received++;
> +
> +		if (!fep->usage_count)
> +			goto rx_processing_done;
> +
> +		status ^= BD_ENET_RX_LAST;
> +		/* Check for errors. */
> +		if (status & (BD_ENET_RX_LG | BD_ENET_RX_SH | BD_ENET_RX_NO |
> +			      BD_ENET_RX_CR | BD_ENET_RX_OV | BD_ENET_RX_LAST |
> +			      BD_ENET_RX_CL)) {
> +			dev->stats.rx_errors++;
> +			if (status & BD_ENET_RX_OV) {
> +				/* FIFO overrun */
> +				dev->stats.rx_fifo_errors++;
> +				goto rx_processing_done;
> +			}
> +			if (status & (BD_ENET_RX_LG | BD_ENET_RX_SH
> +				      | BD_ENET_RX_LAST)) {
> +				/* Frame too long or too short. */
> +				dev->stats.rx_length_errors++;
> +				if (status & BD_ENET_RX_LAST)
> +					netdev_err(dev, "rcv is not +last\n");
> +			}
> +			if (status & BD_ENET_RX_CR)	/* CRC Error */
> +				dev->stats.rx_crc_errors++;
> +
> +			/* Report late collisions as a frame error. */
> +			if (status & (BD_ENET_RX_NO | BD_ENET_RX_CL))
> +				dev->stats.rx_frame_errors++;
> +			goto rx_processing_done;
> +		}
> +
> +		/* Get correct RX page */
> +		page = fep->page[bdp - fep->rx_bd_base];
> +		/* Process the incoming frame */
> +		pkt_len = bdp->cbd_datlen;
> +		data = (__u8 *)__va(bdp->cbd_bufaddr);
> +
> +		dma_sync_single_for_cpu(&fep->pdev->dev, bdp->cbd_bufaddr,
> +					pkt_len, DMA_FROM_DEVICE);
> +		net_prefetch(page_address(page));

Both `__va(bdp->cbd_bufaddr)` and `page_address(page)` should point to
the same same memory. Please use constantly one _or_ the other  - likely
page_address(page) is the best option.

> +
> +		if (fep->quirks & FEC_QUIRK_SWAP_FRAME)
> +			swap_buffer(data, pkt_len);
> +
> +		if (data) {

The above check is not needed. If data is null swap_buffer will still
unconditionally dereference it.

Also it looks like it can't be NULL.

/P