1 files changed, 158 insertions, 95 deletions

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 42ec6ca3bf03..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);
 		}
@@ -1011,24 +1026,6 @@ static void fec_enet_enable_ring(struct net_device *ndev)
 	}
 }
 
-static void fec_enet_reset_skb(struct net_device *ndev)
-{
-	struct fec_enet_private *fep = netdev_priv(ndev);
-	struct fec_enet_priv_tx_q *txq;
-	int i, j;
-
-	for (i = 0; i < fep->num_tx_queues; i++) {
-		txq = fep->tx_queue[i];
-
-		for (j = 0; j < txq->bd.ring_size; j++) {
-			if (txq->tx_skbuff[j]) {
-				dev_kfree_skb_any(txq->tx_skbuff[j]);
-				txq->tx_skbuff[j] = NULL;
-			}
-		}
-	}
-}
-
 /*
  * This function is called to start or restart the FEC during a link
  * change, transmit timeout, or to reconfigure the FEC.  The network
@@ -1071,9 +1068,6 @@ fec_restart(struct net_device *ndev)
 
 	fec_enet_enable_ring(ndev);
 
-	/* Reset tx SKB buffers. */
-	fec_enet_reset_skb(ndev);
-
 	/* Enable MII mode */
 	if (fep->full_duplex == DUPLEX_FULL) {
 		/* FD enable */
@@ -1378,9 +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;
@@ -1408,16 +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 |
@@ -1436,21 +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,
@@ -1459,10 +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();
@@ -1486,14 +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,
@@ -1836,7 +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) {
@@ -2810,6 +2840,7 @@ static void fec_enet_get_xdp_stats(struct fec_enet_private *fep, u64 *data)
 
 static void fec_enet_page_pool_stats(struct fec_enet_private *fep, u64 *data)
 {
+#ifdef CONFIG_PAGE_POOL_STATS
 	struct page_pool_stats stats = {};
 	struct fec_enet_priv_rx_q *rxq;
 	int i;
@@ -2824,6 +2855,7 @@ static void fec_enet_page_pool_stats(struct fec_enet_private *fep, u64 *data)
 	}
 
 	page_pool_ethtool_stats_get(data, &stats);
+#endif
 }
 
 static void fec_enet_get_ethtool_stats(struct net_device *dev,
@@ -3268,9 +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;
+			}
 		}
 	}
 }
@@ -3315,8 +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,
@@ -3751,12 +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) {
@@ -3764,8 +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;
 
@@ -3791,20 +3838,18 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep,
 				   struct xdp_frame *frame)
 {
 	unsigned int index, status, estatus;
-	struct bufdesc *bdp, *last_bdp;
+	struct bufdesc *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");
-		xdp_return_frame(frame);
-		return NETDEV_TX_BUSY;
+		netdev_err_once(fep->netdev, "NOT enough BD for SG!\n");
+		return -EBUSY;
 	}
 
 	/* 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;
 
@@ -3813,7 +3858,7 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep,
 	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;
+		return -ENOMEM;
 
 	status |= (BD_ENET_TX_INTR | BD_ENET_TX_LAST);
 	if (fep->bufdesc_ex)
@@ -3832,8 +3877,13 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep,
 		ebdp->cbd_esc = cpu_to_fec32(estatus);
 	}
 
-	index = fec_enet_get_bd_index(last_bdp, &txq->bd);
-	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.
+	 */
+	dma_wmb();
 
 	/* 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.
@@ -3842,10 +3892,16 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep,
 	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);
+	bdp = fec_enet_get_nextdesc(bdp, &txq->bd);
+
+	/* Make sure the update to bdp are performed before txq->bd.cur. */
+	dma_wmb();
 
 	txq->bd.cur = bdp;
 
+	/* Trigger transmission start */
+	writel(0, txq->bd.reg_desc_active);
+
 	return 0;
 }
 
@@ -3868,18 +3924,14 @@ 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)
+		if (fec_enet_txq_xmit_frame(fep, txq, frames[i]) < 0)
 			break;
 		sent_frames++;
 	}
 
-	/* 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 sent_frames;
@@ -4031,6 +4083,10 @@ static int fec_enet_init(struct net_device *ndev)
 
 	ndev->hw_features = ndev->features;
 
+	if (!(fep->quirks & FEC_QUIRK_SWAP_FRAME))
+		ndev->xdp_features = NETDEV_XDP_ACT_BASIC |
+				     NETDEV_XDP_ACT_REDIRECT;
+
 	fec_restart(ndev);
 
 	if (fep->quirks & FEC_QUIRK_MIB_CLEAR)
@@ -4478,9 +4534,11 @@ fec_drv_remove(struct platform_device *pdev)
 	struct device_node *np = pdev->dev.of_node;
 	int ret;
 
-	ret = pm_runtime_resume_and_get(&pdev->dev);
+	ret = pm_runtime_get_sync(&pdev->dev);
 	if (ret < 0)
-		return ret;
+		dev_err(&pdev->dev,
+			"Failed to resume device in remove callback (%pe)\n",
+			ERR_PTR(ret));
 
 	cancel_work_sync(&fep->tx_timeout_work);
 	fec_ptp_stop(pdev);
@@ -4493,8 +4551,13 @@ fec_drv_remove(struct platform_device *pdev)
 		of_phy_deregister_fixed_link(np);
 	of_node_put(fep->phy_node);
 
-	clk_disable_unprepare(fep->clk_ahb);
-	clk_disable_unprepare(fep->clk_ipg);
+	/* After pm_runtime_get_sync() failed, the clks are still off, so skip
+	 * disabling them again.
+	 */
+	if (ret >= 0) {
+		clk_disable_unprepare(fep->clk_ahb);
+		clk_disable_unprepare(fep->clk_ipg);
+	}
 	pm_runtime_put_noidle(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);