net: fec: add initial XDP support

This patch adds the initial XDP support to Freescale driver. It supports
XDP_PASS, XDP_DROP and XDP_REDIRECT actions. Upcoming patches will add
support for XDP_TX and Zero Copy features.

As the patch is rather large, the part of codes to collect the
statistics is separated and will prepare a dedicated patch for that
part.

I just tested with the application of xdpsock.
  -- Native here means running command of "xdpsock -i eth0"
  -- SKB-Mode means running command of "xdpsock -S -i eth0"

The following are the testing result relating to XDP mode:

root@imx8qxpc0mek:~/bpf# ./xdpsock -i eth0
 sock0@eth0:0 rxdrop xdp-drv
                   pps            pkts           1.00
rx                 371347         2717794
tx                 0              0

root@imx8qxpc0mek:~/bpf# ./xdpsock -S -i eth0
 sock0@eth0:0 rxdrop xdp-skb
                   pps            pkts           1.00
rx                 202229         404528
tx                 0              0

root@imx8qxpc0mek:~/bpf# ./xdp2 eth0
proto 0:     496708 pkt/s
proto 0:     505469 pkt/s
proto 0:     505283 pkt/s
proto 0:     505443 pkt/s
proto 0:     505465 pkt/s

root@imx8qxpc0mek:~/bpf# ./xdp2 -S eth0
proto 0:          0 pkt/s
proto 17:     118778 pkt/s
proto 17:     118989 pkt/s
proto 0:          1 pkt/s
proto 17:     118987 pkt/s
proto 0:          0 pkt/s
proto 17:     118943 pkt/s
proto 17:     118976 pkt/s
proto 0:          1 pkt/s
proto 17:     119006 pkt/s
proto 0:          0 pkt/s
proto 17:     119071 pkt/s
proto 17:     119092 pkt/s

Signed-off-by: Shenwei Wang <shenwei.wang@nxp.com>
Reported-by: kernel test robot <lkp@intel.com>
Link: https://lore.kernel.org/r/20221031185350.2045675-1-shenwei.wang@nxp.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

drivers/net/ethernet/freescale/fec.h

@@ -348,7 +348,6 @@ struct bufdesc_ex {
  */
 
 #define FEC_ENET_XDP_HEADROOM	(XDP_PACKET_HEADROOM)
-
 #define FEC_ENET_RX_PAGES	256
 #define FEC_ENET_RX_FRSIZE	(PAGE_SIZE - FEC_ENET_XDP_HEADROOM \
 		- SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
@@ -663,6 +662,9 @@ struct fec_enet_private {
 
 	struct imx_sc_ipc *ipc_handle;
 
+	/* XDP BPF Program */
+	struct bpf_prog *xdp_prog;
+
 	u64 ethtool_stats[];
 };
 

drivers/net/ethernet/freescale/fec_main.c

@@ -89,6 +89,11 @@ static const u16 fec_enet_vlan_pri_to_queue[8] = {0, 0, 1, 1, 1, 2, 2, 2};
 #define FEC_ENET_OPD_V	0xFFF0
 #define FEC_MDIO_PM_TIMEOUT  100 /* ms */
 
+#define FEC_ENET_XDP_PASS          0
+#define FEC_ENET_XDP_CONSUMED      BIT(0)
+#define FEC_ENET_XDP_TX            BIT(1)
+#define FEC_ENET_XDP_REDIR         BIT(2)
+
 struct fec_devinfo {
 	u32 quirks;
 };
@@ -418,13 +423,14 @@ static int
 fec_enet_create_page_pool(struct fec_enet_private *fep,
 			  struct fec_enet_priv_rx_q *rxq, int size)
 {
+	struct bpf_prog *xdp_prog = READ_ONCE(fep->xdp_prog);
 	struct page_pool_params pp_params = {
 		.order = 0,
 		.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
 		.pool_size = size,
 		.nid = dev_to_node(&fep->pdev->dev),
 		.dev = &fep->pdev->dev,
-		.dma_dir = DMA_FROM_DEVICE,
+		.dma_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE,
 		.offset = FEC_ENET_XDP_HEADROOM,
 		.max_len = FEC_ENET_RX_FRSIZE,
 	};
@@ -1499,6 +1505,59 @@ static void fec_enet_update_cbd(struct fec_enet_priv_rx_q *rxq,
 	bdp->cbd_bufaddr = cpu_to_fec32(phys_addr);
 }
 
+static u32
+fec_enet_run_xdp(struct fec_enet_private *fep, struct bpf_prog *prog,
+		 struct xdp_buff *xdp, struct fec_enet_priv_rx_q *rxq, int index)
+{
+	unsigned int sync, len = xdp->data_end - xdp->data;
+	u32 ret = FEC_ENET_XDP_PASS;
+	struct page *page;
+	int err;
+	u32 act;
+
+	act = bpf_prog_run_xdp(prog, xdp);
+
+	/* Due xdp_adjust_tail: DMA sync for_device cover max len CPU touch */
+	sync = xdp->data_end - xdp->data_hard_start - FEC_ENET_XDP_HEADROOM;
+	sync = max(sync, len);
+
+	switch (act) {
+	case XDP_PASS:
+		ret = FEC_ENET_XDP_PASS;
+		break;
+
+	case XDP_REDIRECT:
+		err = xdp_do_redirect(fep->netdev, xdp, prog);
+		if (!err) {
+			ret = FEC_ENET_XDP_REDIR;
+		} else {
+			ret = FEC_ENET_XDP_CONSUMED;
+			page = virt_to_head_page(xdp->data);
+			page_pool_put_page(rxq->page_pool, page, sync, true);
+		}
+		break;
+
+	default:
+		bpf_warn_invalid_xdp_action(fep->netdev, prog, act);
+		fallthrough;
+
+	case XDP_TX:
+		bpf_warn_invalid_xdp_action(fep->netdev, prog, act);
+		fallthrough;
+
+	case XDP_ABORTED:
+		fallthrough;    /* handle aborts by dropping packet */
+
+	case XDP_DROP:
+		ret = FEC_ENET_XDP_CONSUMED;
+		page = virt_to_head_page(xdp->data);
+		page_pool_put_page(rxq->page_pool, page, sync, true);
+		break;
+	}
+
+	return ret;
+}
+
 /* During a receive, the bd_rx.cur 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,
@@ -1520,6 +1579,9 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 	u16	vlan_tag;
 	int	index = 0;
 	bool	need_swap = fep->quirks & FEC_QUIRK_SWAP_FRAME;
+	struct bpf_prog *xdp_prog = READ_ONCE(fep->xdp_prog);
+	u32 ret, xdp_result = FEC_ENET_XDP_PASS;
+	struct xdp_buff xdp;
 	struct page *page;
 
 #ifdef CONFIG_M532x
@@ -1531,6 +1593,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 	 * These get messed up if we get called due to a busy condition.
 	 */
 	bdp = rxq->bd.cur;
+	xdp_init_buff(&xdp, PAGE_SIZE, &rxq->xdp_rxq);
 
 	while (!((status = fec16_to_cpu(bdp->cbd_sc)) & BD_ENET_RX_EMPTY)) {
 
@@ -1580,6 +1643,17 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 		prefetch(page_address(page));
 		fec_enet_update_cbd(rxq, bdp, index);
 
+		if (xdp_prog) {
+			xdp_buff_clear_frags_flag(&xdp);
+			xdp_prepare_buff(&xdp, page_address(page),
+					 FEC_ENET_XDP_HEADROOM, pkt_len, false);
+
+			ret = fec_enet_run_xdp(fep, xdp_prog, &xdp, rxq, index);
+			xdp_result |= ret;
+			if (ret != FEC_ENET_XDP_PASS)
+				goto rx_processing_done;
+		}
+
 		/* The packet length includes FCS, but we don't want to
 		 * include that when passing upstream as it messes up
 		 * bridging applications.
@@ -1675,6 +1749,10 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 		writel(0, rxq->bd.reg_desc_active);
 	}
 	rxq->bd.cur = bdp;
+
+	if (xdp_result & FEC_ENET_XDP_REDIR)
+		xdp_do_flush_map();
+
 	return pkt_received;
 }
 
@@ -3518,6 +3596,148 @@ static u16 fec_enet_select_queue(struct net_device *ndev, struct sk_buff *skb,
 	return fec_enet_vlan_pri_to_queue[vlan_tag >> 13];
 }
 
+static int fec_enet_bpf(struct net_device *dev, struct netdev_bpf *bpf)
+{
+	struct fec_enet_private *fep = netdev_priv(dev);
+	bool is_run = netif_running(dev);
+	struct bpf_prog *old_prog;
+
+	switch (bpf->command) {
+	case XDP_SETUP_PROG:
+		if (is_run) {
+			napi_disable(&fep->napi);
+			netif_tx_disable(dev);
+		}
+
+		old_prog = xchg(&fep->xdp_prog, bpf->prog);
+		fec_restart(dev);
+
+		if (is_run) {
+			napi_enable(&fep->napi);
+			netif_tx_start_all_queues(dev);
+		}
+
+		if (old_prog)
+			bpf_prog_put(old_prog);
+
+		return 0;
+
+	case XDP_SETUP_XSK_POOL:
+		return -EOPNOTSUPP;
+
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int
+fec_enet_xdp_get_tx_queue(struct fec_enet_private *fep, int cpu)
+{
+	int index = cpu;
+
+	if (unlikely(index < 0))
+		index = 0;
+
+	while (index >= fep->num_tx_queues)
+		index -= fep->num_tx_queues;
+
+	return index;
+}
+
+static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep,
+				   struct fec_enet_priv_tx_q *txq,
+				   struct xdp_frame *frame)
+{
+	unsigned int index, status, estatus;
+	struct bufdesc *bdp, *last_bdp;
+	dma_addr_t dma_addr;
+	int entries_free;
+
+	entries_free = fec_enet_get_free_txdesc_num(txq);
+	if (entries_free < MAX_SKB_FRAGS + 1) {
+		netdev_err(fep->netdev, "NOT enough BD for SG!\n");
+		return NETDEV_TX_OK;
+	}
+
+	/* Fill in a Tx ring entry */
+	bdp = txq->bd.cur;
+	last_bdp = bdp;
+	status = fec16_to_cpu(bdp->cbd_sc);
+	status &= ~BD_ENET_TX_STATS;
+
+	index = fec_enet_get_bd_index(bdp, &txq->bd);
+
+	dma_addr = dma_map_single(&fep->pdev->dev, frame->data,
+				  frame->len, DMA_TO_DEVICE);
+	if (dma_mapping_error(&fep->pdev->dev, dma_addr))
+		return FEC_ENET_XDP_CONSUMED;
+
+	status |= (BD_ENET_TX_INTR | BD_ENET_TX_LAST);
+	if (fep->bufdesc_ex)
+		estatus = BD_ENET_TX_INT;
+
+	bdp->cbd_bufaddr = cpu_to_fec32(dma_addr);
+	bdp->cbd_datlen = cpu_to_fec16(frame->len);
+
+	if (fep->bufdesc_ex) {
+		struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
+
+		if (fep->quirks & FEC_QUIRK_HAS_AVB)
+			estatus |= FEC_TX_BD_FTYPE(txq->bd.qid);
+
+		ebdp->cbd_bdu = 0;
+		ebdp->cbd_esc = cpu_to_fec32(estatus);
+	}
+
+	index = fec_enet_get_bd_index(last_bdp, &txq->bd);
+	txq->tx_skbuff[index] = NULL;
+
+	/* Send it on its way.  Tell FEC it's ready, interrupt when done,
+	 * it's the last BD of the frame, and to put the CRC on the end.
+	 */
+	status |= (BD_ENET_TX_READY | BD_ENET_TX_TC);
+	bdp->cbd_sc = cpu_to_fec16(status);
+
+	/* If this was the last BD in the ring, start at the beginning again. */
+	bdp = fec_enet_get_nextdesc(last_bdp, &txq->bd);
+
+	txq->bd.cur = bdp;
+
+	return 0;
+}
+
+static int fec_enet_xdp_xmit(struct net_device *dev,
+			     int num_frames,
+			     struct xdp_frame **frames,
+			     u32 flags)
+{
+	struct fec_enet_private *fep = netdev_priv(dev);
+	struct fec_enet_priv_tx_q *txq;
+	int cpu = smp_processor_id();
+	struct netdev_queue *nq;
+	unsigned int queue;
+	int i;
+
+	queue = fec_enet_xdp_get_tx_queue(fep, cpu);
+	txq = fep->tx_queue[queue];
+	nq = netdev_get_tx_queue(fep->netdev, queue);
+
+	__netif_tx_lock(nq, cpu);
+
+	for (i = 0; i < num_frames; i++)
+		fec_enet_txq_xmit_frame(fep, txq, frames[i]);
+
+	/* Make sure the update to bdp and tx_skbuff are performed. */
+	wmb();
+
+	/* Trigger transmission start */
+	writel(0, txq->bd.reg_desc_active);
+
+	__netif_tx_unlock(nq);
+
+	return num_frames;
+}
+
 static const struct net_device_ops fec_netdev_ops = {
 	.ndo_open		= fec_enet_open,
 	.ndo_stop		= fec_enet_close,
@@ -3532,6 +3752,8 @@ static const struct net_device_ops fec_netdev_ops = {
 	.ndo_poll_controller	= fec_poll_controller,
 #endif
 	.ndo_set_features	= fec_set_features,
+	.ndo_bpf		= fec_enet_bpf,
+	.ndo_xdp_xmit		= fec_enet_xdp_xmit,
 };
 
 static const unsigned short offset_des_active_rxq[] = {