3 files changed, 212 insertions, 100 deletions

diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index 1416262d4296..e0a4cb7e3f50 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -1186,14 +1186,9 @@ static int enetc_init_port_rss_memory(struct enetc_si *si)
 
 static int enetc_pf_register_with_ierb(struct pci_dev *pdev)
 {
-	struct device_node *node = pdev->dev.of_node;
 	struct platform_device *ierb_pdev;
 	struct device_node *ierb_node;
 
-	/* Don't register with the IERB if the PF itself is disabled */
-	if (!node || !of_device_is_available(node))
-		return 0;
-
 	ierb_node = of_find_compatible_node(NULL, NULL,
 					    "fsl,ls1028a-enetc-ierb");
 	if (!ierb_node || !of_device_is_available(ierb_node))
@@ -1208,56 +1203,81 @@ static int enetc_pf_register_with_ierb(struct pci_dev *pdev)
 	return enetc_ierb_register_pf(ierb_pdev, pdev);
 }
 
-static int enetc_pf_probe(struct pci_dev *pdev,
-			  const struct pci_device_id *ent)
+static struct enetc_si *enetc_psi_create(struct pci_dev *pdev)
 {
-	struct device_node *node = pdev->dev.of_node;
-	struct enetc_ndev_priv *priv;
-	struct net_device *ndev;
 	struct enetc_si *si;
-	struct enetc_pf *pf;
 	int err;
 
-	err = enetc_pf_register_with_ierb(pdev);
-	if (err == -EPROBE_DEFER)
-		return err;
-	if (err)
-		dev_warn(&pdev->dev,
-			 "Could not register with IERB driver: %pe, please update the device tree\n",
-			 ERR_PTR(err));
-
-	err = enetc_pci_probe(pdev, KBUILD_MODNAME, sizeof(*pf));
-	if (err)
-		return dev_err_probe(&pdev->dev, err, "PCI probing failed\n");
+	err = enetc_pci_probe(pdev, KBUILD_MODNAME, sizeof(struct enetc_pf));
+	if (err) {
+		dev_err_probe(&pdev->dev, err, "PCI probing failed\n");
+		goto out;
+	}
 
 	si = pci_get_drvdata(pdev);
 	if (!si->hw.port || !si->hw.global) {
 		err = -ENODEV;
 		dev_err(&pdev->dev, "could not map PF space, probing a VF?\n");
-		goto err_map_pf_space;
+		goto out_pci_remove;
 	}
 
 	err = enetc_setup_cbdr(&pdev->dev, &si->hw, ENETC_CBDR_DEFAULT_SIZE,
 			       &si->cbd_ring);
 	if (err)
-		goto err_setup_cbdr;
+		goto out_pci_remove;
 
 	err = enetc_init_port_rfs_memory(si);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to initialize RFS memory\n");
-		goto err_init_port_rfs;
+		goto out_teardown_cbdr;
 	}
 
 	err = enetc_init_port_rss_memory(si);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to initialize RSS memory\n");
-		goto err_init_port_rss;
+		goto out_teardown_cbdr;
 	}
 
-	if (node && !of_device_is_available(node)) {
-		dev_info(&pdev->dev, "device is disabled, skipping\n");
-		err = -ENODEV;
-		goto err_device_disabled;
+	return si;
+
+out_teardown_cbdr:
+	enetc_teardown_cbdr(&si->cbd_ring);
+out_pci_remove:
+	enetc_pci_remove(pdev);
+out:
+	return ERR_PTR(err);
+}
+
+static void enetc_psi_destroy(struct pci_dev *pdev)
+{
+	struct enetc_si *si = pci_get_drvdata(pdev);
+
+	enetc_teardown_cbdr(&si->cbd_ring);
+	enetc_pci_remove(pdev);
+}
+
+static int enetc_pf_probe(struct pci_dev *pdev,
+			  const struct pci_device_id *ent)
+{
+	struct device_node *node = pdev->dev.of_node;
+	struct enetc_ndev_priv *priv;
+	struct net_device *ndev;
+	struct enetc_si *si;
+	struct enetc_pf *pf;
+	int err;
+
+	err = enetc_pf_register_with_ierb(pdev);
+	if (err == -EPROBE_DEFER)
+		return err;
+	if (err)
+		dev_warn(&pdev->dev,
+			 "Could not register with IERB driver: %pe, please update the device tree\n",
+			 ERR_PTR(err));
+
+	si = enetc_psi_create(pdev);
+	if (IS_ERR(si)) {
+		err = PTR_ERR(si);
+		goto err_psi_create;
 	}
 
 	pf = enetc_si_priv(si);
@@ -1339,15 +1359,9 @@ err_alloc_si_res:
 	si->ndev = NULL;
 	free_netdev(ndev);
 err_alloc_netdev:
-err_init_port_rss:
-err_init_port_rfs:
-err_device_disabled:
 err_setup_mac_addresses:
-	enetc_teardown_cbdr(&si->cbd_ring);
-err_setup_cbdr:
-err_map_pf_space:
-	enetc_pci_remove(pdev);
-
+	enetc_psi_destroy(pdev);
+err_psi_create:
 	return err;
 }
 
@@ -1370,12 +1384,29 @@ static void enetc_pf_remove(struct pci_dev *pdev)
 	enetc_free_msix(priv);
 
 	enetc_free_si_resources(priv);
-	enetc_teardown_cbdr(&si->cbd_ring);
 
 	free_netdev(si->ndev);
 
-	enetc_pci_remove(pdev);
+	enetc_psi_destroy(pdev);
+}
+
+static void enetc_fixup_clear_rss_rfs(struct pci_dev *pdev)
+{
+	struct device_node *node = pdev->dev.of_node;
+	struct enetc_si *si;
+
+	/* Only apply quirk for disabled functions. For the ones
+	 * that are enabled, enetc_pf_probe() will apply it.
+	 */
+	if (node && of_device_is_available(node))
+		return;
+
+	si = enetc_psi_create(pdev);
+	if (si)
+		enetc_psi_destroy(pdev);
 }
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_FREESCALE, ENETC_DEV_ID_PF,
+			enetc_fixup_clear_rss_rfs);
 
 static const struct pci_device_id enetc_pf_id_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_FREESCALE, ENETC_DEV_ID_PF) },
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 9939ccafb556..63a053dea819 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -355,7 +355,7 @@ struct bufdesc_ex {
 #define RX_RING_SIZE		(FEC_ENET_RX_FRPPG * FEC_ENET_RX_PAGES)
 #define FEC_ENET_TX_FRSIZE	2048
 #define FEC_ENET_TX_FRPPG	(PAGE_SIZE / FEC_ENET_TX_FRSIZE)
-#define TX_RING_SIZE		512	/* Must be power of two */
+#define TX_RING_SIZE		1024	/* Must be power of two */
 #define TX_RING_MOD_MASK	511	/*   for this to work */
 
 #define BD_ENET_RX_INT		0x00800000
@@ -544,10 +544,23 @@ enum {
 	XDP_STATS_TOTAL,
 };
 
+enum fec_txbuf_type {
+	FEC_TXBUF_T_SKB,
+	FEC_TXBUF_T_XDP_NDO,
+};
+
+struct fec_tx_buffer {
+	union {
+		struct sk_buff *skb;
+		struct xdp_frame *xdp;
+	};
+	enum fec_txbuf_type type;
+};
+
 struct fec_enet_priv_tx_q {
 	struct bufdesc_prop bd;
 	unsigned char *tx_bounce[TX_RING_SIZE];
-	struct  sk_buff *tx_skbuff[TX_RING_SIZE];
+	struct fec_tx_buffer tx_buf[TX_RING_SIZE];
 
 	unsigned short tx_stop_threshold;
 	unsigned short tx_wake_threshold;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 8fbe47703d47..66b5cbdb43b9 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -397,7 +397,7 @@ static void fec_dump(struct net_device *ndev)
 			fec16_to_cpu(bdp->cbd_sc),
 			fec32_to_cpu(bdp->cbd_bufaddr),
 			fec16_to_cpu(bdp->cbd_datlen),
-			txq->tx_skbuff[index]);
+			txq->tx_buf[index].skb);
 		bdp = fec_enet_get_nextdesc(bdp, &txq->bd);
 		index++;
 	} while (bdp != txq->bd.base);
@@ -654,7 +654,7 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq,
 
 	index = fec_enet_get_bd_index(last_bdp, &txq->bd);
 	/* Save skb pointer */
-	txq->tx_skbuff[index] = skb;
+	txq->tx_buf[index].skb = skb;
 
 	/* Make sure the updates to rest of the descriptor are performed before
 	 * transferring ownership.
@@ -672,9 +672,7 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq,
 
 	skb_tx_timestamp(skb);
 
-	/* Make sure the update to bdp and tx_skbuff are performed before
-	 * txq->bd.cur.
-	 */
+	/* Make sure the update to bdp is performed before txq->bd.cur. */
 	wmb();
 	txq->bd.cur = bdp;
 
@@ -862,7 +860,7 @@ static int fec_enet_txq_submit_tso(struct fec_enet_priv_tx_q *txq,
 	}
 
 	/* Save skb pointer */
-	txq->tx_skbuff[index] = skb;
+	txq->tx_buf[index].skb = skb;
 
 	skb_tx_timestamp(skb);
 	txq->bd.cur = bdp;
@@ -952,16 +950,33 @@ static void fec_enet_bd_init(struct net_device *dev)
 		for (i = 0; i < txq->bd.ring_size; i++) {
 			/* Initialize the BD for every fragment in the page. */
 			bdp->cbd_sc = cpu_to_fec16(0);
-			if (bdp->cbd_bufaddr &&
-			    !IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr)))
-				dma_unmap_single(&fep->pdev->dev,
-						 fec32_to_cpu(bdp->cbd_bufaddr),
-						 fec16_to_cpu(bdp->cbd_datlen),
-						 DMA_TO_DEVICE);
-			if (txq->tx_skbuff[i]) {
-				dev_kfree_skb_any(txq->tx_skbuff[i]);
-				txq->tx_skbuff[i] = NULL;
+			if (txq->tx_buf[i].type == FEC_TXBUF_T_SKB) {
+				if (bdp->cbd_bufaddr &&
+				    !IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr)))
+					dma_unmap_single(&fep->pdev->dev,
+							 fec32_to_cpu(bdp->cbd_bufaddr),
+							 fec16_to_cpu(bdp->cbd_datlen),
+							 DMA_TO_DEVICE);
+				if (txq->tx_buf[i].skb) {
+					dev_kfree_skb_any(txq->tx_buf[i].skb);
+					txq->tx_buf[i].skb = NULL;
+				}
+			} else {
+				if (bdp->cbd_bufaddr)
+					dma_unmap_single(&fep->pdev->dev,
+							 fec32_to_cpu(bdp->cbd_bufaddr),
+							 fec16_to_cpu(bdp->cbd_datlen),
+							 DMA_TO_DEVICE);
+
+				if (txq->tx_buf[i].xdp) {
+					xdp_return_frame(txq->tx_buf[i].xdp);
+					txq->tx_buf[i].xdp = NULL;
+				}
+
+				/* restore default tx buffer type: FEC_TXBUF_T_SKB */
+				txq->tx_buf[i].type = FEC_TXBUF_T_SKB;
 			}
+
 			bdp->cbd_bufaddr = cpu_to_fec32(0);
 			bdp = fec_enet_get_nextdesc(bdp, &txq->bd);
 		}
@@ -1357,9 +1372,10 @@ fec_enet_hwtstamp(struct fec_enet_private *fep, unsigned ts,
 }
 
 static void
-fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
+fec_enet_tx_queue(struct net_device *ndev, u16 queue_id, int budget)
 {
 	struct	fec_enet_private *fep;
+	struct xdp_frame *xdpf;
 	struct bufdesc *bdp;
 	unsigned short status;
 	struct	sk_buff	*skb;
@@ -1387,16 +1403,39 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
 
 		index = fec_enet_get_bd_index(bdp, &txq->bd);
 
-		skb = txq->tx_skbuff[index];
-		txq->tx_skbuff[index] = NULL;
-		if (!IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr)))
-			dma_unmap_single(&fep->pdev->dev,
-					 fec32_to_cpu(bdp->cbd_bufaddr),
-					 fec16_to_cpu(bdp->cbd_datlen),
-					 DMA_TO_DEVICE);
-		bdp->cbd_bufaddr = cpu_to_fec32(0);
-		if (!skb)
-			goto skb_done;
+		if (txq->tx_buf[index].type == FEC_TXBUF_T_SKB) {
+			skb = txq->tx_buf[index].skb;
+			txq->tx_buf[index].skb = NULL;
+			if (bdp->cbd_bufaddr &&
+			    !IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr)))
+				dma_unmap_single(&fep->pdev->dev,
+						 fec32_to_cpu(bdp->cbd_bufaddr),
+						 fec16_to_cpu(bdp->cbd_datlen),
+						 DMA_TO_DEVICE);
+			bdp->cbd_bufaddr = cpu_to_fec32(0);
+			if (!skb)
+				goto tx_buf_done;
+		} else {
+			/* Tx processing cannot call any XDP (or page pool) APIs if
+			 * the "budget" is 0. Because NAPI is called with budget of
+			 * 0 (such as netpoll) indicates we may be in an IRQ context,
+			 * however, we can't use the page pool from IRQ context.
+			 */
+			if (unlikely(!budget))
+				break;
+
+			xdpf = txq->tx_buf[index].xdp;
+			if (bdp->cbd_bufaddr)
+				dma_unmap_single(&fep->pdev->dev,
+						 fec32_to_cpu(bdp->cbd_bufaddr),
+						 fec16_to_cpu(bdp->cbd_datlen),
+						 DMA_TO_DEVICE);
+			bdp->cbd_bufaddr = cpu_to_fec32(0);
+			if (!xdpf) {
+				txq->tx_buf[index].type = FEC_TXBUF_T_SKB;
+				goto tx_buf_done;
+			}
+		}
 
 		/* Check for errors. */
 		if (status & (BD_ENET_TX_HB | BD_ENET_TX_LC |
@@ -1415,21 +1454,11 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
 				ndev->stats.tx_carrier_errors++;
 		} else {
 			ndev->stats.tx_packets++;
-			ndev->stats.tx_bytes += skb->len;
-		}
 
-		/* NOTE: SKBTX_IN_PROGRESS being set does not imply it's we who
-		 * are to time stamp the packet, so we still need to check time
-		 * stamping enabled flag.
-		 */
-		if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS &&
-			     fep->hwts_tx_en) &&
-		    fep->bufdesc_ex) {
-			struct skb_shared_hwtstamps shhwtstamps;
-			struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
-
-			fec_enet_hwtstamp(fep, fec32_to_cpu(ebdp->ts), &shhwtstamps);
-			skb_tstamp_tx(skb, &shhwtstamps);
+			if (txq->tx_buf[index].type == FEC_TXBUF_T_SKB)
+				ndev->stats.tx_bytes += skb->len;
+			else
+				ndev->stats.tx_bytes += xdpf->len;
 		}
 
 		/* Deferred means some collisions occurred during transmit,
@@ -1438,10 +1467,32 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
 		if (status & BD_ENET_TX_DEF)
 			ndev->stats.collisions++;
 
-		/* Free the sk buffer associated with this last transmit */
-		dev_kfree_skb_any(skb);
-skb_done:
-		/* Make sure the update to bdp and tx_skbuff are performed
+		if (txq->tx_buf[index].type == FEC_TXBUF_T_SKB) {
+			/* NOTE: SKBTX_IN_PROGRESS being set does not imply it's we who
+			 * are to time stamp the packet, so we still need to check time
+			 * stamping enabled flag.
+			 */
+			if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS &&
+				     fep->hwts_tx_en) && fep->bufdesc_ex) {
+				struct skb_shared_hwtstamps shhwtstamps;
+				struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
+
+				fec_enet_hwtstamp(fep, fec32_to_cpu(ebdp->ts), &shhwtstamps);
+				skb_tstamp_tx(skb, &shhwtstamps);
+			}
+
+			/* Free the sk buffer associated with this last transmit */
+			dev_kfree_skb_any(skb);
+		} else {
+			xdp_return_frame(xdpf);
+
+			txq->tx_buf[index].xdp = NULL;
+			/* restore default tx buffer type: FEC_TXBUF_T_SKB */
+			txq->tx_buf[index].type = FEC_TXBUF_T_SKB;
+		}
+
+tx_buf_done:
+		/* Make sure the update to bdp and tx_buf are performed
 		 * before dirty_tx
 		 */
 		wmb();
@@ -1465,14 +1516,14 @@ skb_done:
 		writel(0, txq->bd.reg_desc_active);
 }
 
-static void fec_enet_tx(struct net_device *ndev)
+static void fec_enet_tx(struct net_device *ndev, int budget)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	int i;
 
 	/* Make sure that AVB queues are processed first. */
 	for (i = fep->num_tx_queues - 1; i >= 0; i--)
-		fec_enet_tx_queue(ndev, i);
+		fec_enet_tx_queue(ndev, i, budget);
 }
 
 static void fec_enet_update_cbd(struct fec_enet_priv_rx_q *rxq,
@@ -1815,7 +1866,7 @@ static int fec_enet_rx_napi(struct napi_struct *napi, int budget)
 
 	do {
 		done += fec_enet_rx(ndev, budget - done);
-		fec_enet_tx(ndev);
+		fec_enet_tx(ndev, budget);
 	} while ((done < budget) && fec_enet_collect_events(fep));
 
 	if (done < budget) {
@@ -3249,9 +3300,19 @@ static void fec_enet_free_buffers(struct net_device *ndev)
 		for (i = 0; i < txq->bd.ring_size; i++) {
 			kfree(txq->tx_bounce[i]);
 			txq->tx_bounce[i] = NULL;
-			skb = txq->tx_skbuff[i];
-			txq->tx_skbuff[i] = NULL;
-			dev_kfree_skb(skb);
+
+			if (txq->tx_buf[i].type == FEC_TXBUF_T_SKB) {
+				skb = txq->tx_buf[i].skb;
+				txq->tx_buf[i].skb = NULL;
+				dev_kfree_skb(skb);
+			} else {
+				if (txq->tx_buf[i].xdp) {
+					xdp_return_frame(txq->tx_buf[i].xdp);
+					txq->tx_buf[i].xdp = NULL;
+				}
+
+				txq->tx_buf[i].type = FEC_TXBUF_T_SKB;
+			}
 		}
 	}
 }
@@ -3296,8 +3357,7 @@ static int fec_enet_alloc_queue(struct net_device *ndev)
 		fep->total_tx_ring_size += fep->tx_queue[i]->bd.ring_size;
 
 		txq->tx_stop_threshold = FEC_MAX_SKB_DESCS;
-		txq->tx_wake_threshold =
-			(txq->bd.ring_size - txq->tx_stop_threshold) / 2;
+		txq->tx_wake_threshold = FEC_MAX_SKB_DESCS + 2 * MAX_SKB_FRAGS;
 
 		txq->tso_hdrs = dma_alloc_coherent(&fep->pdev->dev,
 					txq->bd.ring_size * TSO_HEADER_SIZE,
@@ -3732,12 +3792,18 @@ static int fec_enet_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 		if (fep->quirks & FEC_QUIRK_SWAP_FRAME)
 			return -EOPNOTSUPP;
 
+		if (!bpf->prog)
+			xdp_features_clear_redirect_target(dev);
+
 		if (is_run) {
 			napi_disable(&fep->napi);
 			netif_tx_disable(dev);
 		}
 
 		old_prog = xchg(&fep->xdp_prog, bpf->prog);
+		if (old_prog)
+			bpf_prog_put(old_prog);
+
 		fec_restart(dev);
 
 		if (is_run) {
@@ -3745,8 +3811,8 @@ static int fec_enet_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 			netif_tx_start_all_queues(dev);
 		}
 
-		if (old_prog)
-			bpf_prog_put(old_prog);
+		if (bpf->prog)
+			xdp_features_set_redirect_target(dev, false);
 
 		return 0;
 
@@ -3778,7 +3844,7 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep,
 
 	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");
+		netdev_err_once(fep->netdev, "NOT enough BD for SG!\n");
 		return -EBUSY;
 	}
 
@@ -3811,7 +3877,8 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep,
 		ebdp->cbd_esc = cpu_to_fec32(estatus);
 	}
 
-	txq->tx_skbuff[index] = NULL;
+	txq->tx_buf[index].type = FEC_TXBUF_T_XDP_NDO;
+	txq->tx_buf[index].xdp = frame;
 
 	/* Make sure the updates to rest of the descriptor are performed before
 	 * transferring ownership.
@@ -3857,6 +3924,8 @@ static int fec_enet_xdp_xmit(struct net_device *dev,
 
 	__netif_tx_lock(nq, cpu);
 
+	/* Avoid tx timeout as XDP shares the queue with kernel stack */
+	txq_trans_cond_update(nq);
 	for (i = 0; i < num_frames; i++) {
 		if (fec_enet_txq_xmit_frame(fep, txq, frames[i]) < 0)
 			break;
@@ -4016,8 +4085,7 @@ static int fec_enet_init(struct net_device *ndev)
 
 	if (!(fep->quirks & FEC_QUIRK_SWAP_FRAME))
 		ndev->xdp_features = NETDEV_XDP_ACT_BASIC |
-				     NETDEV_XDP_ACT_REDIRECT |
-				     NETDEV_XDP_ACT_NDO_XMIT;
+				     NETDEV_XDP_ACT_REDIRECT;
 
 	fec_restart(ndev);