From 9999e48639b3cecb08ffb37358bcba3b48161b29 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Fri, 10 May 2024 08:50:17 +0000
Subject: [PATCH] add ax88772_rst

---
 kernel/drivers/net/ethernet/nvidia/forcedeth.c |  222 ++++++++++++++++++++++++++++++++++++++-----------------
 1 files changed, 152 insertions(+), 70 deletions(-)

diff --git a/kernel/drivers/net/ethernet/nvidia/forcedeth.c b/kernel/drivers/net/ethernet/nvidia/forcedeth.c
index 1d9b0d4..e14dd10 100644
--- a/kernel/drivers/net/ethernet/nvidia/forcedeth.c
+++ b/kernel/drivers/net/ethernet/nvidia/forcedeth.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * forcedeth: Ethernet driver for NVIDIA nForce media access controllers.
  *
@@ -14,19 +15,6 @@
  * Copyright (C) 2004 Carl-Daniel Hailfinger (invalid MAC handling, insane
  *		IRQ rate fixes, bigendian fixes, cleanups, verification)
  * Copyright (c) 2004,2005,2006,2007,2008,2009 NVIDIA Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  *
  * Known bugs:
  * We suspect that on some hardware no TX done interrupts are generated.
@@ -725,6 +713,21 @@
 	struct nv_skb_map *next_tx_ctx;
 };
 
+struct nv_txrx_stats {
+	u64 stat_rx_packets;
+	u64 stat_rx_bytes; /* not always available in HW */
+	u64 stat_rx_missed_errors;
+	u64 stat_rx_dropped;
+	u64 stat_tx_packets; /* not always available in HW */
+	u64 stat_tx_bytes;
+	u64 stat_tx_dropped;
+};
+
+#define nv_txrx_stats_inc(member) \
+		__this_cpu_inc(np->txrx_stats->member)
+#define nv_txrx_stats_add(member, count) \
+		__this_cpu_add(np->txrx_stats->member, (count))
+
 /*
  * SMP locking:
  * All hardware access under netdev_priv(dev)->lock, except the performance
@@ -809,10 +812,7 @@
 
 	/* RX software stats */
 	struct u64_stats_sync swstats_rx_syncp;
-	u64 stat_rx_packets;
-	u64 stat_rx_bytes; /* not always available in HW */
-	u64 stat_rx_missed_errors;
-	u64 stat_rx_dropped;
+	struct nv_txrx_stats __percpu *txrx_stats;
 
 	/* media detection workaround.
 	 * Locking: Within irq hander or disable_irq+spin_lock(&np->lock);
@@ -838,9 +838,6 @@
 
 	/* TX software stats */
 	struct u64_stats_sync swstats_tx_syncp;
-	u64 stat_tx_packets; /* not always available in HW */
-	u64 stat_tx_bytes;
-	u64 stat_tx_dropped;
 
 	/* msi/msi-x fields */
 	u32 msi_flags;
@@ -1733,6 +1730,39 @@
 	}
 }
 
+static void nv_get_stats(int cpu, struct fe_priv *np,
+			 struct rtnl_link_stats64 *storage)
+{
+	struct nv_txrx_stats *src = per_cpu_ptr(np->txrx_stats, cpu);
+	unsigned int syncp_start;
+	u64 rx_packets, rx_bytes, rx_dropped, rx_missed_errors;
+	u64 tx_packets, tx_bytes, tx_dropped;
+
+	do {
+		syncp_start = u64_stats_fetch_begin_irq(&np->swstats_rx_syncp);
+		rx_packets       = src->stat_rx_packets;
+		rx_bytes         = src->stat_rx_bytes;
+		rx_dropped       = src->stat_rx_dropped;
+		rx_missed_errors = src->stat_rx_missed_errors;
+	} while (u64_stats_fetch_retry_irq(&np->swstats_rx_syncp, syncp_start));
+
+	storage->rx_packets       += rx_packets;
+	storage->rx_bytes         += rx_bytes;
+	storage->rx_dropped       += rx_dropped;
+	storage->rx_missed_errors += rx_missed_errors;
+
+	do {
+		syncp_start = u64_stats_fetch_begin_irq(&np->swstats_tx_syncp);
+		tx_packets  = src->stat_tx_packets;
+		tx_bytes    = src->stat_tx_bytes;
+		tx_dropped  = src->stat_tx_dropped;
+	} while (u64_stats_fetch_retry_irq(&np->swstats_tx_syncp, syncp_start));
+
+	storage->tx_packets += tx_packets;
+	storage->tx_bytes   += tx_bytes;
+	storage->tx_dropped += tx_dropped;
+}
+
 /*
  * nv_get_stats64: dev->ndo_get_stats64 function
  * Get latest stats value from the nic.
@@ -1745,7 +1775,7 @@
 	__releases(&netdev_priv(dev)->hwstats_lock)
 {
 	struct fe_priv *np = netdev_priv(dev);
-	unsigned int syncp_start;
+	int cpu;
 
 	/*
 	 * Note: because HW stats are not always available and for
@@ -1758,20 +1788,8 @@
 	 */
 
 	/* software stats */
-	do {
-		syncp_start = u64_stats_fetch_begin_irq(&np->swstats_rx_syncp);
-		storage->rx_packets       = np->stat_rx_packets;
-		storage->rx_bytes         = np->stat_rx_bytes;
-		storage->rx_dropped       = np->stat_rx_dropped;
-		storage->rx_missed_errors = np->stat_rx_missed_errors;
-	} while (u64_stats_fetch_retry_irq(&np->swstats_rx_syncp, syncp_start));
-
-	do {
-		syncp_start = u64_stats_fetch_begin_irq(&np->swstats_tx_syncp);
-		storage->tx_packets = np->stat_tx_packets;
-		storage->tx_bytes   = np->stat_tx_bytes;
-		storage->tx_dropped = np->stat_tx_dropped;
-	} while (u64_stats_fetch_retry_irq(&np->swstats_tx_syncp, syncp_start));
+	for_each_online_cpu(cpu)
+		nv_get_stats(cpu, np, storage);
 
 	/* If the nic supports hw counters then retrieve latest values */
 	if (np->driver_data & DEV_HAS_STATISTICS_V123) {
@@ -1839,7 +1857,7 @@
 		} else {
 packet_dropped:
 			u64_stats_update_begin(&np->swstats_rx_syncp);
-			np->stat_rx_dropped++;
+			nv_txrx_stats_inc(stat_rx_dropped);
 			u64_stats_update_end(&np->swstats_rx_syncp);
 			return 1;
 		}
@@ -1881,7 +1899,7 @@
 		} else {
 packet_dropped:
 			u64_stats_update_begin(&np->swstats_rx_syncp);
-			np->stat_rx_dropped++;
+			nv_txrx_stats_inc(stat_rx_dropped);
 			u64_stats_update_end(&np->swstats_rx_syncp);
 			return 1;
 		}
@@ -2025,7 +2043,7 @@
 		}
 		if (nv_release_txskb(np, &np->tx_skb[i])) {
 			u64_stats_update_begin(&np->swstats_tx_syncp);
-			np->stat_tx_dropped++;
+			nv_txrx_stats_inc(stat_tx_dropped);
 			u64_stats_update_end(&np->swstats_tx_syncp);
 		}
 		np->tx_skb[i].dma = 0;
@@ -2207,6 +2225,7 @@
 	struct nv_skb_map *prev_tx_ctx;
 	struct nv_skb_map *tmp_tx_ctx = NULL, *start_tx_ctx = NULL;
 	unsigned long flags;
+	netdev_tx_t ret = NETDEV_TX_OK;
 
 	/* add fragments to entries count */
 	for (i = 0; i < fragments; i++) {
@@ -2222,7 +2241,12 @@
 		netif_stop_queue(dev);
 		np->tx_stop = 1;
 		spin_unlock_irqrestore(&np->lock, flags);
-		return NETDEV_TX_BUSY;
+
+		/* When normal packets and/or xmit_more packets fill up
+		 * tx_desc, it is necessary to trigger NIC tx reg.
+		 */
+		ret = NETDEV_TX_BUSY;
+		goto txkick;
 	}
 	spin_unlock_irqrestore(&np->lock, flags);
 
@@ -2239,9 +2263,12 @@
 			/* on DMA mapping error - drop the packet */
 			dev_kfree_skb_any(skb);
 			u64_stats_update_begin(&np->swstats_tx_syncp);
-			np->stat_tx_dropped++;
+			nv_txrx_stats_inc(stat_tx_dropped);
 			u64_stats_update_end(&np->swstats_tx_syncp);
-			return NETDEV_TX_OK;
+
+			ret = NETDEV_TX_OK;
+
+			goto dma_error;
 		}
 		np->put_tx_ctx->dma_len = bcnt;
 		np->put_tx_ctx->dma_single = 1;
@@ -2285,9 +2312,12 @@
 				dev_kfree_skb_any(skb);
 				np->put_tx_ctx = start_tx_ctx;
 				u64_stats_update_begin(&np->swstats_tx_syncp);
-				np->stat_tx_dropped++;
+				nv_txrx_stats_inc(stat_tx_dropped);
 				u64_stats_update_end(&np->swstats_tx_syncp);
-				return NETDEV_TX_OK;
+
+				ret = NETDEV_TX_OK;
+
+				goto dma_error;
 			}
 
 			np->put_tx_ctx->dma_len = bcnt;
@@ -2339,8 +2369,15 @@
 
 	spin_unlock_irqrestore(&np->lock, flags);
 
-	writel(NVREG_TXRXCTL_KICK|np->txrxctl_bits, get_hwbase(dev) + NvRegTxRxControl);
-	return NETDEV_TX_OK;
+txkick:
+	if (netif_queue_stopped(dev) || !netdev_xmit_more()) {
+		u32 txrxctl_kick;
+dma_error:
+		txrxctl_kick = NVREG_TXRXCTL_KICK | np->txrxctl_bits;
+		writel(txrxctl_kick, get_hwbase(dev) + NvRegTxRxControl);
+	}
+
+	return ret;
 }
 
 static netdev_tx_t nv_start_xmit_optimized(struct sk_buff *skb,
@@ -2363,6 +2400,7 @@
 	struct nv_skb_map *start_tx_ctx = NULL;
 	struct nv_skb_map *tmp_tx_ctx = NULL;
 	unsigned long flags;
+	netdev_tx_t ret = NETDEV_TX_OK;
 
 	/* add fragments to entries count */
 	for (i = 0; i < fragments; i++) {
@@ -2378,7 +2416,13 @@
 		netif_stop_queue(dev);
 		np->tx_stop = 1;
 		spin_unlock_irqrestore(&np->lock, flags);
-		return NETDEV_TX_BUSY;
+
+		/* When normal packets and/or xmit_more packets fill up
+		 * tx_desc, it is necessary to trigger NIC tx reg.
+		 */
+		ret = NETDEV_TX_BUSY;
+
+		goto txkick;
 	}
 	spin_unlock_irqrestore(&np->lock, flags);
 
@@ -2396,9 +2440,12 @@
 			/* on DMA mapping error - drop the packet */
 			dev_kfree_skb_any(skb);
 			u64_stats_update_begin(&np->swstats_tx_syncp);
-			np->stat_tx_dropped++;
+			nv_txrx_stats_inc(stat_tx_dropped);
 			u64_stats_update_end(&np->swstats_tx_syncp);
-			return NETDEV_TX_OK;
+
+			ret = NETDEV_TX_OK;
+
+			goto dma_error;
 		}
 		np->put_tx_ctx->dma_len = bcnt;
 		np->put_tx_ctx->dma_single = 1;
@@ -2443,9 +2490,12 @@
 				dev_kfree_skb_any(skb);
 				np->put_tx_ctx = start_tx_ctx;
 				u64_stats_update_begin(&np->swstats_tx_syncp);
-				np->stat_tx_dropped++;
+				nv_txrx_stats_inc(stat_tx_dropped);
 				u64_stats_update_end(&np->swstats_tx_syncp);
-				return NETDEV_TX_OK;
+
+				ret = NETDEV_TX_OK;
+
+				goto dma_error;
 			}
 			np->put_tx_ctx->dma_len = bcnt;
 			np->put_tx_ctx->dma_single = 0;
@@ -2524,8 +2574,15 @@
 
 	spin_unlock_irqrestore(&np->lock, flags);
 
-	writel(NVREG_TXRXCTL_KICK|np->txrxctl_bits, get_hwbase(dev) + NvRegTxRxControl);
-	return NETDEV_TX_OK;
+txkick:
+	if (netif_queue_stopped(dev) || !netdev_xmit_more()) {
+		u32 txrxctl_kick;
+dma_error:
+		txrxctl_kick = NVREG_TXRXCTL_KICK | np->txrxctl_bits;
+		writel(txrxctl_kick, get_hwbase(dev) + NvRegTxRxControl);
+	}
+
+	return ret;
 }
 
 static inline void nv_tx_flip_ownership(struct net_device *dev)
@@ -2572,9 +2629,12 @@
 					    && !(flags & NV_TX_RETRYCOUNT_MASK))
 						nv_legacybackoff_reseed(dev);
 				} else {
+					unsigned int len;
+
 					u64_stats_update_begin(&np->swstats_tx_syncp);
-					np->stat_tx_packets++;
-					np->stat_tx_bytes += np->get_tx_ctx->skb->len;
+					nv_txrx_stats_inc(stat_tx_packets);
+					len = np->get_tx_ctx->skb->len;
+					nv_txrx_stats_add(stat_tx_bytes, len);
 					u64_stats_update_end(&np->swstats_tx_syncp);
 				}
 				bytes_compl += np->get_tx_ctx->skb->len;
@@ -2589,9 +2649,12 @@
 					    && !(flags & NV_TX2_RETRYCOUNT_MASK))
 						nv_legacybackoff_reseed(dev);
 				} else {
+					unsigned int len;
+
 					u64_stats_update_begin(&np->swstats_tx_syncp);
-					np->stat_tx_packets++;
-					np->stat_tx_bytes += np->get_tx_ctx->skb->len;
+					nv_txrx_stats_inc(stat_tx_packets);
+					len = np->get_tx_ctx->skb->len;
+					nv_txrx_stats_add(stat_tx_bytes, len);
 					u64_stats_update_end(&np->swstats_tx_syncp);
 				}
 				bytes_compl += np->get_tx_ctx->skb->len;
@@ -2639,9 +2702,12 @@
 						nv_legacybackoff_reseed(dev);
 				}
 			} else {
+				unsigned int len;
+
 				u64_stats_update_begin(&np->swstats_tx_syncp);
-				np->stat_tx_packets++;
-				np->stat_tx_bytes += np->get_tx_ctx->skb->len;
+				nv_txrx_stats_inc(stat_tx_packets);
+				len = np->get_tx_ctx->skb->len;
+				nv_txrx_stats_add(stat_tx_bytes, len);
 				u64_stats_update_end(&np->swstats_tx_syncp);
 			}
 
@@ -2673,7 +2739,7 @@
  * nv_tx_timeout: dev->tx_timeout function
  * Called with netif_tx_lock held.
  */
-static void nv_tx_timeout(struct net_device *dev)
+static void nv_tx_timeout(struct net_device *dev, unsigned int txqueue)
 {
 	struct fe_priv *np = netdev_priv(dev);
 	u8 __iomem *base = get_hwbase(dev);
@@ -2818,6 +2884,15 @@
 	}
 }
 
+static void rx_missing_handler(u32 flags, struct fe_priv *np)
+{
+	if (flags & NV_RX_MISSEDFRAME) {
+		u64_stats_update_begin(&np->swstats_rx_syncp);
+		nv_txrx_stats_inc(stat_rx_missed_errors);
+		u64_stats_update_end(&np->swstats_rx_syncp);
+	}
+}
+
 static int nv_rx_process(struct net_device *dev, int limit)
 {
 	struct fe_priv *np = netdev_priv(dev);
@@ -2860,11 +2935,7 @@
 					}
 					/* the rest are hard errors */
 					else {
-						if (flags & NV_RX_MISSEDFRAME) {
-							u64_stats_update_begin(&np->swstats_rx_syncp);
-							np->stat_rx_missed_errors++;
-							u64_stats_update_end(&np->swstats_rx_syncp);
-						}
+						rx_missing_handler(flags, np);
 						dev_kfree_skb(skb);
 						goto next_pkt;
 					}
@@ -2908,8 +2979,8 @@
 		skb->protocol = eth_type_trans(skb, dev);
 		napi_gro_receive(&np->napi, skb);
 		u64_stats_update_begin(&np->swstats_rx_syncp);
-		np->stat_rx_packets++;
-		np->stat_rx_bytes += len;
+		nv_txrx_stats_inc(stat_rx_packets);
+		nv_txrx_stats_add(stat_rx_bytes, len);
 		u64_stats_update_end(&np->swstats_rx_syncp);
 next_pkt:
 		if (unlikely(np->get_rx.orig++ == np->last_rx.orig))
@@ -2994,8 +3065,8 @@
 			}
 			napi_gro_receive(&np->napi, skb);
 			u64_stats_update_begin(&np->swstats_rx_syncp);
-			np->stat_rx_packets++;
-			np->stat_rx_bytes += len;
+			nv_txrx_stats_inc(stat_rx_packets);
+			nv_txrx_stats_add(stat_rx_bytes, len);
 			u64_stats_update_end(&np->swstats_rx_syncp);
 		} else {
 			dev_kfree_skb(skb);
@@ -5663,6 +5734,12 @@
 	SET_NETDEV_DEV(dev, &pci_dev->dev);
 	u64_stats_init(&np->swstats_rx_syncp);
 	u64_stats_init(&np->swstats_tx_syncp);
+	np->txrx_stats = alloc_percpu(struct nv_txrx_stats);
+	if (!np->txrx_stats) {
+		pr_err("np->txrx_stats, alloc memory error.\n");
+		err = -ENOMEM;
+		goto out_alloc_percpu;
+	}
 
 	timer_setup(&np->oom_kick, nv_do_rx_refill, 0);
 	timer_setup(&np->nic_poll, nv_do_nic_poll, 0);
@@ -6061,6 +6138,7 @@
 	return 0;
 
 out_error:
+	nv_mgmt_release_sema(dev);
 	if (phystate_orig)
 		writel(phystate|NVREG_ADAPTCTL_RUNNING, base + NvRegAdapterControl);
 out_freering:
@@ -6072,6 +6150,8 @@
 out_disable:
 	pci_disable_device(pci_dev);
 out_free:
+	free_percpu(np->txrx_stats);
+out_alloc_percpu:
 	free_netdev(dev);
 out:
 	return err;
@@ -6117,6 +6197,9 @@
 static void nv_remove(struct pci_dev *pci_dev)
 {
 	struct net_device *dev = pci_get_drvdata(pci_dev);
+	struct fe_priv *np = netdev_priv(dev);
+
+	free_percpu(np->txrx_stats);
 
 	unregister_netdev(dev);
 
@@ -6138,8 +6221,7 @@
 #ifdef CONFIG_PM_SLEEP
 static int nv_suspend(struct device *device)
 {
-	struct pci_dev *pdev = to_pci_dev(device);
-	struct net_device *dev = pci_get_drvdata(pdev);
+	struct net_device *dev = dev_get_drvdata(device);
 	struct fe_priv *np = netdev_priv(dev);
 	u8 __iomem *base = get_hwbase(dev);
 	int i;

--
Gitblit v1.6.2