Merge tag 'net-7.0-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from CAN and netfilter.

  Current release - regressions:

   - eth: mana: Null service_wq on setup error to prevent double destroy

  Previous releases - regressions:

   - nexthop: fix percpu use-after-free in remove_nh_grp_entry

   - sched: teql: fix NULL pointer dereference in iptunnel_xmit on TEQL slave xmit

   - bpf: fix nd_tbl NULL dereference when IPv6 is disabled

   - neighbour: restore protocol != 0 check in pneigh update

   - tipc: fix divide-by-zero in tipc_sk_filter_connect()

   - eth:
      - mlx5:
         - fix crash when moving to switchdev mode
         - fix DMA FIFO desync on error CQE SQ recovery
      - iavf: fix PTP use-after-free during reset
      - bonding: fix type confusion in bond_setup_by_slave()
      - lan78xx: fix WARN in __netif_napi_del_locked on disconnect

  Previous releases - always broken:

   - core: add xmit recursion limit to tunnel xmit functions

   - net-shapers: don't free reply skb after genlmsg_reply()

   - netfilter:
      - fix stack out-of-bounds read in pipapo_drop()
      - fix OOB read in nfnl_cthelper_dump_table()

   - mctp:
      - fix device leak on probe failure
      - i2c: fix skb memory leak in receive path

   - can: keep the max bitrate error at 5%

   - eth:
      - bonding: fix nd_tbl NULL dereference when IPv6 is disabled
      - bnxt_en: fix RSS table size check when changing ethtool channels
      - amd-xgbe: prevent CRC errors during RX adaptation with AN disabled
      - octeontx2-af: devlink: fix NIX RAS reporter recovery condition"

* tag 'net-7.0-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (71 commits)
  net: prevent NULL deref in ip[6]tunnel_xmit()
  octeontx2-af: devlink: fix NIX RAS reporter to use RAS interrupt status
  octeontx2-af: devlink: fix NIX RAS reporter recovery condition
  net: ethernet: ti: am65-cpsw-nuss: Fix rx_filter value for PTP support
  net/mana: Null service_wq on setup error to prevent double destroy
  selftests: rtnetlink: add neighbour update test
  neighbour: restore protocol != 0 check in pneigh update
  net: dsa: realtek: Fix LED group port bit for non-zero LED group
  tipc: fix divide-by-zero in tipc_sk_filter_connect()
  net: dsa: microchip: Fix error path in PTP IRQ setup
  bpf: bpf_out_neigh_v6: Fix nd_tbl NULL dereference when IPv6 is disabled
  bpf: bpf_out_neigh_v4: Fix nd_tbl NULL dereference when IPv6 is disabled
  net: bonding: Fix nd_tbl NULL dereference when IPv6 is disabled
  ipv6: move the disable_ipv6_mod knob to core code
  net: bcmgenet: fix broken EEE by converting to phylib-managed state
  net-shapers: don't free reply skb after genlmsg_reply()
  net: dsa: mxl862xx: don't set user_mii_bus
  net: ethernet: arc: emac: quiesce interrupts before requesting IRQ
  page_pool: store detach_time as ktime_t to avoid false-negatives
  net: macb: Shuffle the tx ring before enabling tx
  ...

MAINTAINERS

@@ -16358,7 +16358,6 @@ F:	net/dsa/tag_mtk.c
 
 MEDIATEK T7XX 5G WWAN MODEM DRIVER
 M:	Chandrashekar Devegowda <chandrashekar.devegowda@intel.com>
-R:	Chiranjeevi Rapolu <chiranjeevi.rapolu@linux.intel.com>
 R:	Liu Haijun <haijun.liu@mediatek.com>
 R:	Ricardo Martinez <ricardo.martinez@linux.intel.com>
 L:	netdev@vger.kernel.org
@@ -25759,6 +25758,7 @@ F:	include/net/pkt_cls.h
 F:	include/net/pkt_sched.h
 F:	include/net/sch_priv.h
 F:	include/net/tc_act/
+F:	include/net/tc_wrapper.h
 F:	include/uapi/linux/pkt_cls.h
 F:	include/uapi/linux/pkt_sched.h
 F:	include/uapi/linux/tc_act/

drivers/net/bonding/bond_main.c

@@ -1509,6 +1509,50 @@ static netdev_features_t bond_fix_features(struct net_device *dev,
 	return features;
 }
 
+static int bond_header_create(struct sk_buff *skb, struct net_device *bond_dev,
+			      unsigned short type, const void *daddr,
+			      const void *saddr, unsigned int len)
+{
+	struct bonding *bond = netdev_priv(bond_dev);
+	const struct header_ops *slave_ops;
+	struct slave *slave;
+	int ret = 0;
+
+	rcu_read_lock();
+	slave = rcu_dereference(bond->curr_active_slave);
+	if (slave) {
+		slave_ops = READ_ONCE(slave->dev->header_ops);
+		if (slave_ops && slave_ops->create)
+			ret = slave_ops->create(skb, slave->dev,
+						type, daddr, saddr, len);
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+static int bond_header_parse(const struct sk_buff *skb, unsigned char *haddr)
+{
+	struct bonding *bond = netdev_priv(skb->dev);
+	const struct header_ops *slave_ops;
+	struct slave *slave;
+	int ret = 0;
+
+	rcu_read_lock();
+	slave = rcu_dereference(bond->curr_active_slave);
+	if (slave) {
+		slave_ops = READ_ONCE(slave->dev->header_ops);
+		if (slave_ops && slave_ops->parse)
+			ret = slave_ops->parse(skb, haddr);
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+static const struct header_ops bond_header_ops = {
+	.create	= bond_header_create,
+	.parse	= bond_header_parse,
+};
+
 static void bond_setup_by_slave(struct net_device *bond_dev,
 				struct net_device *slave_dev)
 {
@@ -1516,7 +1560,8 @@ static void bond_setup_by_slave(struct net_device *bond_dev,
 
 	dev_close(bond_dev);
 
-	bond_dev->header_ops	    = slave_dev->header_ops;
+	bond_dev->header_ops	    = slave_dev->header_ops ?
+				      &bond_header_ops : NULL;
 
 	bond_dev->type		    = slave_dev->type;
 	bond_dev->hard_header_len   = slave_dev->hard_header_len;
@@ -2801,8 +2846,14 @@ static void bond_miimon_commit(struct bonding *bond)
 
 			continue;
 
+		case BOND_LINK_FAIL:
+		case BOND_LINK_BACK:
+			slave_dbg(bond->dev, slave->dev, "link_new_state %d on slave\n",
+				  slave->link_new_state);
+			continue;
+
 		default:
-			slave_err(bond->dev, slave->dev, "invalid new link %d on slave\n",
+			slave_err(bond->dev, slave->dev, "invalid link_new_state %d on slave\n",
 				  slave->link_new_state);
 			bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 
@@ -3377,7 +3428,7 @@ int bond_rcv_validate(const struct sk_buff *skb, struct bonding *bond,
 	} else if (is_arp) {
 		return bond_arp_rcv(skb, bond, slave);
 #if IS_ENABLED(CONFIG_IPV6)
-	} else if (is_ipv6) {
+	} else if (is_ipv6 && likely(ipv6_mod_enabled())) {
 		return bond_na_rcv(skb, bond, slave);
 #endif
 	} else {
@@ -5069,13 +5120,18 @@ static void bond_set_slave_arr(struct bonding *bond,
 {
 	struct bond_up_slave *usable, *all;
 
-	usable = rtnl_dereference(bond->usable_slaves);
-	rcu_assign_pointer(bond->usable_slaves, usable_slaves);
-	kfree_rcu(usable, rcu);
-
 	all = rtnl_dereference(bond->all_slaves);
 	rcu_assign_pointer(bond->all_slaves, all_slaves);
 	kfree_rcu(all, rcu);
+
+	if (BOND_MODE(bond) == BOND_MODE_BROADCAST) {
+		kfree_rcu(usable_slaves, rcu);
+		return;
+	}
+
+	usable = rtnl_dereference(bond->usable_slaves);
+	rcu_assign_pointer(bond->usable_slaves, usable_slaves);
+	kfree_rcu(usable, rcu);
 }
 
 static void bond_reset_slave_arr(struct bonding *bond)

drivers/net/caif/caif_serial.c

@@ -297,6 +297,7 @@ static void ser_release(struct work_struct *work)
 			dev_close(ser->dev);
 			unregister_netdevice(ser->dev);
 			debugfs_deinit(ser);
+			tty_kref_put(tty->link);
 			tty_kref_put(tty);
 		}
 		rtnl_unlock();
@@ -331,6 +332,7 @@ static int ldisc_open(struct tty_struct *tty)
 
 	ser = netdev_priv(dev);
 	ser->tty = tty_kref_get(tty);
+	tty_kref_get(tty->link);
 	ser->dev = dev;
 	debugfs_init(ser, tty);
 	tty->receive_room = 4096;
@@ -339,6 +341,7 @@ static int ldisc_open(struct tty_struct *tty)
 	rtnl_lock();
 	result = register_netdevice(dev);
 	if (result) {
+		tty_kref_put(tty->link);
 		tty_kref_put(tty);
 		rtnl_unlock();
 		free_netdev(dev);

drivers/net/can/dev/calc_bittiming.c

@@ -8,7 +8,7 @@
 #include <linux/units.h>
 #include <linux/can/dev.h>
 
-#define CAN_CALC_MAX_ERROR 50 /* in one-tenth of a percent */
+#define CAN_CALC_MAX_ERROR 500 /* max error 5% */
 
 /* CiA recommended sample points for Non Return to Zero encoding. */
 static int can_calc_sample_point_nrz(const struct can_bittiming *bt)

drivers/net/can/spi/hi311x.c

@@ -755,7 +755,9 @@ static int hi3110_open(struct net_device *net)
 		return ret;
 
 	mutex_lock(&priv->hi3110_lock);
-	hi3110_power_enable(priv->transceiver, 1);
+	ret = hi3110_power_enable(priv->transceiver, 1);
+	if (ret)
+		goto out_close_candev;
 
 	priv->force_quit = 0;
 	priv->tx_skb = NULL;
@@ -790,6 +792,7 @@ static int hi3110_open(struct net_device *net)
 	hi3110_hw_sleep(spi);
  out_close:
 	hi3110_power_enable(priv->transceiver, 0);
+ out_close_candev:
 	close_candev(net);
 	mutex_unlock(&priv->hi3110_lock);
 	return ret;

drivers/net/dsa/microchip/ksz_ptp.c

@@ -1108,6 +1108,7 @@ static int ksz_ptp_msg_irq_setup(struct ksz_port *port, u8 n)
 	const struct ksz_dev_ops *ops = port->ksz_dev->dev_ops;
 	struct ksz_irq *ptpirq = &port->ptpirq;
 	struct ksz_ptp_irq *ptpmsg_irq;
+	int ret;
 
 	ptpmsg_irq = &port->ptpmsg_irq[n];
 	ptpmsg_irq->num = irq_create_mapping(ptpirq->domain, n);
@@ -1119,9 +1120,13 @@ static int ksz_ptp_msg_irq_setup(struct ksz_port *port, u8 n)
 
 	strscpy(ptpmsg_irq->name, name[n]);
 
-	return request_threaded_irq(ptpmsg_irq->num, NULL,
-				    ksz_ptp_msg_thread_fn, IRQF_ONESHOT,
-				    ptpmsg_irq->name, ptpmsg_irq);
+	ret = request_threaded_irq(ptpmsg_irq->num, NULL,
+				   ksz_ptp_msg_thread_fn, IRQF_ONESHOT,
+				   ptpmsg_irq->name, ptpmsg_irq);
+	if (ret)
+		irq_dispose_mapping(ptpmsg_irq->num);
+
+	return ret;
 }
 
 int ksz_ptp_irq_setup(struct dsa_switch *ds, u8 p)

drivers/net/dsa/mxl862xx/mxl862xx.c

@@ -149,7 +149,6 @@ static int mxl862xx_setup_mdio(struct dsa_switch *ds)
 		return -ENOMEM;
 
 	bus->priv = priv;
-	ds->user_mii_bus = bus;
 	bus->name = KBUILD_MODNAME "-mii";
 	snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(dev));
 	bus->read_c45 = mxl862xx_phy_read_c45_mii_bus;

drivers/net/dsa/realtek/rtl8365mb.c

@@ -1480,8 +1480,7 @@ static void rtl8365mb_stats_update(struct realtek_priv *priv, int port)
 
 	stats->rx_packets = cnt[RTL8365MB_MIB_ifInUcastPkts] +
 			    cnt[RTL8365MB_MIB_ifInMulticastPkts] +
-			    cnt[RTL8365MB_MIB_ifInBroadcastPkts] -
-			    cnt[RTL8365MB_MIB_ifOutDiscards];
+			    cnt[RTL8365MB_MIB_ifInBroadcastPkts];
 
 	stats->tx_packets = cnt[RTL8365MB_MIB_ifOutUcastPkts] +
 			    cnt[RTL8365MB_MIB_ifOutMulticastPkts] +

drivers/net/dsa/realtek/rtl8366rb-leds.c

@@ -12,11 +12,11 @@ static inline u32 rtl8366rb_led_group_port_mask(u8 led_group, u8 port)
 	case 0:
 		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
 	case 1:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+		return FIELD_PREP(RTL8366RB_LED_X_1_CTRL_MASK, BIT(port));
 	case 2:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+		return FIELD_PREP(RTL8366RB_LED_2_X_CTRL_MASK, BIT(port));
 	case 3:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+		return FIELD_PREP(RTL8366RB_LED_X_3_CTRL_MASK, BIT(port));
 	default:
 		return 0;
 	}

drivers/net/dsa/sja1105/sja1105_main.c

@@ -2339,14 +2339,13 @@ int sja1105_static_config_reload(struct sja1105_private *priv,
 			goto out;
 	}
 
+	rc = sja1105_reload_cbs(priv);
+
+out:
 	dsa_switch_for_each_available_port(dp, ds)
 		if (dp->pl)
 			phylink_replay_link_end(dp->pl);
 
-	rc = sja1105_reload_cbs(priv);
-	if (rc < 0)
-		goto out;
-out:
 	mutex_unlock(&priv->mgmt_lock);
 	mutex_unlock(&priv->fdb_lock);
 

drivers/net/ethernet/amd/xgbe/xgbe-drv.c

@@ -1271,20 +1271,25 @@ static int xgbe_start(struct xgbe_prv_data *pdata)
 	if (ret)
 		goto err_napi;
 
+	/* Reset the phy settings */
+	ret = xgbe_phy_reset(pdata);
+	if (ret)
+		goto err_irqs;
+
+	/* Start the phy */
 	ret = phy_if->phy_start(pdata);
 	if (ret)
 		goto err_irqs;
 
 	hw_if->enable_tx(pdata);
 	hw_if->enable_rx(pdata);
+	/* Synchronize flag with hardware state after enabling TX/RX.
+	 * This prevents stale state after device restart cycles.
+	 */
+	pdata->data_path_stopped = false;
 
 	udp_tunnel_nic_reset_ntf(netdev);
 
-	/* Reset the phy settings */
-	ret = xgbe_phy_reset(pdata);
-	if (ret)
-		goto err_txrx;
-
 	netif_tx_start_all_queues(netdev);
 
 	xgbe_start_timers(pdata);
@@ -1294,10 +1299,6 @@ static int xgbe_start(struct xgbe_prv_data *pdata)
 
 	return 0;
 
-err_txrx:
-	hw_if->disable_rx(pdata);
-	hw_if->disable_tx(pdata);
-
 err_irqs:
 	xgbe_free_irqs(pdata);
 

drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c

@@ -1942,7 +1942,7 @@ static void xgbe_set_rx_adap_mode(struct xgbe_prv_data *pdata,
 static void xgbe_rx_adaptation(struct xgbe_prv_data *pdata)
 {
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
-	unsigned int reg;
+	int reg;
 
 	/* step 2: force PCS to send RX_ADAPT Req to PHY */
 	XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_RX_EQ_CTRL4,
@@ -1964,11 +1964,20 @@ static void xgbe_rx_adaptation(struct xgbe_prv_data *pdata)
 
 	/* Step 4: Check for Block lock */
 
-	/* Link status is latched low, so read once to clear
-	 * and then read again to get current state
+	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
+	if (reg < 0)
+		goto set_mode;
+
+	/* Link status is latched low so that momentary link drops
+	 * can be detected. If link was already down read again
+	 * to get the latest state.
 	 */
-	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
-	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
+	if (!pdata->phy.link && !(reg & MDIO_STAT1_LSTATUS)) {
+		reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
+		if (reg < 0)
+			goto set_mode;
+	}
+
 	if (reg & MDIO_STAT1_LSTATUS) {
 		/* If the block lock is found, update the helpers
 		 * and declare the link up
@@ -2008,6 +2017,48 @@ rx_adapt_reinit:
 	xgbe_rx_adaptation(pdata);
 }
 
+/*
+ * xgbe_phy_stop_data_path - Stop TX/RX to prevent packet corruption
+ * @pdata: driver private data
+ *
+ * This function stops the data path (TX and RX) to prevent packet
+ * corruption during critical PHY operations like RX adaptation.
+ * Must be called before initiating RX adaptation when link goes down.
+ */
+static void xgbe_phy_stop_data_path(struct xgbe_prv_data *pdata)
+{
+	if (pdata->data_path_stopped)
+		return;
+
+	/* Stop TX/RX to prevent packet corruption during RX adaptation */
+	pdata->hw_if.disable_tx(pdata);
+	pdata->hw_if.disable_rx(pdata);
+	pdata->data_path_stopped = true;
+
+	netif_dbg(pdata, link, pdata->netdev,
+		  "stopping data path for RX adaptation\n");
+}
+
+/*
+ * xgbe_phy_start_data_path - Re-enable TX/RX after RX adaptation
+ * @pdata: driver private data
+ *
+ * This function re-enables the data path (TX and RX) after RX adaptation
+ * has completed successfully. Only called when link is confirmed up.
+ */
+static void xgbe_phy_start_data_path(struct xgbe_prv_data *pdata)
+{
+	if (!pdata->data_path_stopped)
+		return;
+
+	pdata->hw_if.enable_rx(pdata);
+	pdata->hw_if.enable_tx(pdata);
+	pdata->data_path_stopped = false;
+
+	netif_dbg(pdata, link, pdata->netdev,
+		  "restarting data path after RX adaptation\n");
+}
+
 static void xgbe_phy_rx_reset(struct xgbe_prv_data *pdata)
 {
 	int reg;
@@ -2801,13 +2852,27 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
 	if (pdata->en_rx_adap) {
 		/* if the link is available and adaptation is done,
 		 * declare link up
+		 *
+		 * Note: When link is up and adaptation is done, we can
+		 * safely re-enable the data path if it was stopped
+		 * for adaptation.
 		 */
-		if ((reg & MDIO_STAT1_LSTATUS) && pdata->rx_adapt_done)
+		if ((reg & MDIO_STAT1_LSTATUS) && pdata->rx_adapt_done) {
+			xgbe_phy_start_data_path(pdata);
 			return 1;
+		}
 		/* If either link is not available or adaptation is not done,
 		 * retrigger the adaptation logic. (if the mode is not set,
 		 * then issue mailbox command first)
 		 */
+
+		/* CRITICAL: Stop data path BEFORE triggering RX adaptation
+		 * to prevent CRC errors from packets corrupted during
+		 * the adaptation process. This is especially important
+		 * when AN is OFF in 10G KR mode.
+		 */
+		xgbe_phy_stop_data_path(pdata);
+
 		if (pdata->mode_set) {
 			xgbe_phy_rx_adaptation(pdata);
 		} else {
@@ -2815,8 +2880,11 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
 			xgbe_phy_set_mode(pdata, phy_data->cur_mode);
 		}
 
-		if (pdata->rx_adapt_done)
+		if (pdata->rx_adapt_done) {
+			/* Adaptation complete, safe to re-enable data path */
+			xgbe_phy_start_data_path(pdata);
 			return 1;
+		}
 	} else if (reg & MDIO_STAT1_LSTATUS)
 		return 1;
 

drivers/net/ethernet/amd/xgbe/xgbe.h

@@ -1243,6 +1243,10 @@ struct xgbe_prv_data {
 	bool en_rx_adap;
 	int rx_adapt_retries;
 	bool rx_adapt_done;
+	/* Flag to track if data path (TX/RX) was stopped for RX adaptation.
+	 * This prevents packet corruption during the adaptation window.
+	 */
+	bool data_path_stopped;
 	bool mode_set;
 	bool sph;
 };

drivers/net/ethernet/arc/emac_main.c

@@ -934,6 +934,17 @@ int arc_emac_probe(struct net_device *ndev, int interface)
 	/* Set poll rate so that it polls every 1 ms */
 	arc_reg_set(priv, R_POLLRATE, clock_frequency / 1000000);
 
+	/*
+	 * Put the device into a known quiescent state before requesting
+	 * the IRQ. Clear only EMAC interrupt status bits here; leave the
+	 * MDIO completion bit alone and avoid writing TXPL_MASK, which is
+	 * used to force TX polling rather than acknowledge interrupts.
+	 */
+	arc_reg_set(priv, R_ENABLE, 0);
+	arc_reg_set(priv, R_STATUS, RXINT_MASK | TXINT_MASK | ERR_MASK |
+		    TXCH_MASK | MSER_MASK | RXCR_MASK |
+		    RXFR_MASK | RXFL_MASK);
+
 	ndev->irq = irq;
 	dev_info(dev, "IRQ is %d\n", ndev->irq);
 

drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c

@@ -979,8 +979,8 @@ static int bnxt_set_channels(struct net_device *dev,
 
 	if (bnxt_get_nr_rss_ctxs(bp, req_rx_rings) !=
 	    bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) &&
-	    netif_is_rxfh_configured(dev)) {
-		netdev_warn(dev, "RSS table size change required, RSS table entries must be default to proceed\n");
+	    (netif_is_rxfh_configured(dev) || bp->num_rss_ctx)) {
+		netdev_warn(dev, "RSS table size change required, RSS table entries must be default (with no additional RSS contexts present) to proceed\n");
 		return -EINVAL;
 	}
 

drivers/net/ethernet/broadcom/genet/bcmgenet.c

@@ -1342,8 +1342,7 @@ static void bcmgenet_get_ethtool_stats(struct net_device *dev,
 	}
 }
 
-void bcmgenet_eee_enable_set(struct net_device *dev, bool enable,
-			     bool tx_lpi_enabled)
+void bcmgenet_eee_enable_set(struct net_device *dev, bool enable)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	u32 off = priv->hw_params->tbuf_offset + TBUF_ENERGY_CTRL;
@@ -1363,7 +1362,7 @@ void bcmgenet_eee_enable_set(struct net_device *dev, bool enable,
 
 	/* Enable EEE and switch to a 27Mhz clock automatically */
 	reg = bcmgenet_readl(priv->base + off);
-	if (tx_lpi_enabled)
+	if (enable)
 		reg |= TBUF_EEE_EN | TBUF_PM_EN;
 	else
 		reg &= ~(TBUF_EEE_EN | TBUF_PM_EN);
@@ -1382,14 +1381,12 @@ void bcmgenet_eee_enable_set(struct net_device *dev, bool enable,
 		priv->clk_eee_enabled = false;
 	}
 
-	priv->eee.eee_enabled = enable;
-	priv->eee.tx_lpi_enabled = tx_lpi_enabled;
 }
 
 static int bcmgenet_get_eee(struct net_device *dev, struct ethtool_keee *e)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	struct ethtool_keee *p = &priv->eee;
+	int ret;
 
 	if (GENET_IS_V1(priv))
 		return -EOPNOTSUPP;
@@ -1397,17 +1394,21 @@ static int bcmgenet_get_eee(struct net_device *dev, struct ethtool_keee *e)
 	if (!dev->phydev)
 		return -ENODEV;
 
-	e->tx_lpi_enabled = p->tx_lpi_enabled;
+	ret = phy_ethtool_get_eee(dev->phydev, e);
+	if (ret)
+		return ret;
+
+	/* tx_lpi_timer is maintained by the MAC hardware register; the
+	 * PHY-level eee_cfg timer is not set for GENET.
+	 */
 	e->tx_lpi_timer = bcmgenet_umac_readl(priv, UMAC_EEE_LPI_TIMER);
 
-	return phy_ethtool_get_eee(dev->phydev, e);
+	return 0;
 }
 
 static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_keee *e)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	struct ethtool_keee *p = &priv->eee;
-	bool active;
 
 	if (GENET_IS_V1(priv))
 		return -EOPNOTSUPP;
@@ -1415,15 +1416,7 @@ static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_keee *e)
 	if (!dev->phydev)
 		return -ENODEV;
 
-	p->eee_enabled = e->eee_enabled;
-
-	if (!p->eee_enabled) {
-		bcmgenet_eee_enable_set(dev, false, false);
-	} else {
-		active = phy_init_eee(dev->phydev, false) >= 0;
-		bcmgenet_umac_writel(priv, e->tx_lpi_timer, UMAC_EEE_LPI_TIMER);
-		bcmgenet_eee_enable_set(dev, active, e->tx_lpi_enabled);
-	}
+	bcmgenet_umac_writel(priv, e->tx_lpi_timer, UMAC_EEE_LPI_TIMER);
 
 	return phy_ethtool_set_eee(dev->phydev, e);
 }

drivers/net/ethernet/broadcom/genet/bcmgenet.h

@@ -665,8 +665,6 @@ struct bcmgenet_priv {
 	u8 sopass[SOPASS_MAX];
 
 	struct bcmgenet_mib_counters mib;
-
-	struct ethtool_keee eee;
 };
 
 static inline bool bcmgenet_has_40bits(struct bcmgenet_priv *priv)
@@ -749,7 +747,6 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 int bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
 			      enum bcmgenet_power_mode mode);
 
-void bcmgenet_eee_enable_set(struct net_device *dev, bool enable,
-			     bool tx_lpi_enabled);
+void bcmgenet_eee_enable_set(struct net_device *dev, bool enable);
 
 #endif /* __BCMGENET_H__ */

drivers/net/ethernet/broadcom/genet/bcmmii.c

@@ -29,7 +29,6 @@ static void bcmgenet_mac_config(struct net_device *dev)
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct phy_device *phydev = dev->phydev;
 	u32 reg, cmd_bits = 0;
-	bool active;
 
 	/* speed */
 	if (phydev->speed == SPEED_1000)
@@ -90,10 +89,6 @@ static void bcmgenet_mac_config(struct net_device *dev)
 	bcmgenet_umac_writel(priv, reg, UMAC_CMD);
 	spin_unlock_bh(&priv->reg_lock);
 
-	active = phy_init_eee(phydev, 0) >= 0;
-	bcmgenet_eee_enable_set(dev,
-				priv->eee.eee_enabled && active,
-				priv->eee.tx_lpi_enabled);
 }
 
 /* setup netdev link state when PHY link status change and
@@ -113,6 +108,8 @@ void bcmgenet_mii_setup(struct net_device *dev)
 		bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL);
 	}
 
+	bcmgenet_eee_enable_set(dev, phydev->enable_tx_lpi);
+
 	phy_print_status(phydev);
 }
 
@@ -412,6 +409,9 @@ int bcmgenet_mii_probe(struct net_device *dev)
 	/* Indicate that the MAC is responsible for PHY PM */
 	dev->phydev->mac_managed_pm = true;
 
+	if (!GENET_IS_V1(priv))
+		phy_support_eee(dev->phydev);
+
 	return 0;
 }
 

drivers/net/ethernet/cadence/macb_main.c

@@ -36,6 +36,7 @@
 #include <linux/tcp.h>
 #include <linux/types.h>
 #include <linux/udp.h>
+#include <linux/gcd.h>
 #include <net/pkt_sched.h>
 #include "macb.h"
 
@@ -668,6 +669,97 @@ static void macb_mac_link_down(struct phylink_config *config, unsigned int mode,
 	netif_tx_stop_all_queues(ndev);
 }
 
+/* Use juggling algorithm to left rotate tx ring and tx skb array */
+static void gem_shuffle_tx_one_ring(struct macb_queue *queue)
+{
+	unsigned int head, tail, count, ring_size, desc_size;
+	struct macb_tx_skb tx_skb, *skb_curr, *skb_next;
+	struct macb_dma_desc *desc_curr, *desc_next;
+	unsigned int i, cycles, shift, curr, next;
+	struct macb *bp = queue->bp;
+	unsigned char desc[24];
+	unsigned long flags;
+
+	desc_size = macb_dma_desc_get_size(bp);
+
+	if (WARN_ON_ONCE(desc_size > ARRAY_SIZE(desc)))
+		return;
+
+	spin_lock_irqsave(&queue->tx_ptr_lock, flags);
+	head = queue->tx_head;
+	tail = queue->tx_tail;
+	ring_size = bp->tx_ring_size;
+	count = CIRC_CNT(head, tail, ring_size);
+
+	if (!(tail % ring_size))
+		goto unlock;
+
+	if (!count) {
+		queue->tx_head = 0;
+		queue->tx_tail = 0;
+		goto unlock;
+	}
+
+	shift = tail % ring_size;
+	cycles = gcd(ring_size, shift);
+
+	for (i = 0; i < cycles; i++) {
+		memcpy(&desc, macb_tx_desc(queue, i), desc_size);
+		memcpy(&tx_skb, macb_tx_skb(queue, i),
+		       sizeof(struct macb_tx_skb));
+
+		curr = i;
+		next = (curr + shift) % ring_size;
+
+		while (next != i) {
+			desc_curr = macb_tx_desc(queue, curr);
+			desc_next = macb_tx_desc(queue, next);
+
+			memcpy(desc_curr, desc_next, desc_size);
+
+			if (next == ring_size - 1)
+				desc_curr->ctrl &= ~MACB_BIT(TX_WRAP);
+			if (curr == ring_size - 1)
+				desc_curr->ctrl |= MACB_BIT(TX_WRAP);
+
+			skb_curr = macb_tx_skb(queue, curr);
+			skb_next = macb_tx_skb(queue, next);
+			memcpy(skb_curr, skb_next, sizeof(struct macb_tx_skb));
+
+			curr = next;
+			next = (curr + shift) % ring_size;
+		}
+
+		desc_curr = macb_tx_desc(queue, curr);
+		memcpy(desc_curr, &desc, desc_size);
+		if (i == ring_size - 1)
+			desc_curr->ctrl &= ~MACB_BIT(TX_WRAP);
+		if (curr == ring_size - 1)
+			desc_curr->ctrl |= MACB_BIT(TX_WRAP);
+		memcpy(macb_tx_skb(queue, curr), &tx_skb,
+		       sizeof(struct macb_tx_skb));
+	}
+
+	queue->tx_head = count;
+	queue->tx_tail = 0;
+
+	/* Make descriptor updates visible to hardware */
+	wmb();
+
+unlock:
+	spin_unlock_irqrestore(&queue->tx_ptr_lock, flags);
+}
+
+/* Rotate the queue so that the tail is at index 0 */
+static void gem_shuffle_tx_rings(struct macb *bp)
+{
+	struct macb_queue *queue;
+	int q;
+
+	for (q = 0, queue = bp->queues; q < bp->num_queues; q++, queue++)
+		gem_shuffle_tx_one_ring(queue);
+}
+
 static void macb_mac_link_up(struct phylink_config *config,
 			     struct phy_device *phy,
 			     unsigned int mode, phy_interface_t interface,
@@ -706,8 +798,6 @@ static void macb_mac_link_up(struct phylink_config *config,
 			ctrl |= MACB_BIT(PAE);
 
 		for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
-			queue->tx_head = 0;
-			queue->tx_tail = 0;
 			queue_writel(queue, IER,
 				     bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP));
 		}
@@ -721,8 +811,10 @@ static void macb_mac_link_up(struct phylink_config *config,
 
 	spin_unlock_irqrestore(&bp->lock, flags);
 
-	if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC))
+	if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) {
 		macb_set_tx_clk(bp, speed);
+		gem_shuffle_tx_rings(bp);
+	}
 
 	/* Enable Rx and Tx; Enable PTP unicast */
 	ctrl = macb_readl(bp, NCR);

drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c

@@ -333,11 +333,13 @@ static int netc_get_phy_addr(struct device_node *np)
 
 	mdio_node = of_get_child_by_name(np, "mdio");
 	if (!mdio_node)
-		return 0;
+		return -ENODEV;
 
 	phy_node = of_get_next_child(mdio_node, NULL);
-	if (!phy_node)
+	if (!phy_node) {
+		err = -ENODEV;
 		goto of_put_mdio_node;
+	}
 
 	err = of_property_read_u32(phy_node, "reg", &addr);
 	if (err)
@@ -423,6 +425,9 @@ static int imx95_enetc_mdio_phyaddr_config(struct platform_device *pdev)
 
 			addr = netc_get_phy_addr(gchild);
 			if (addr < 0) {
+				if (addr == -ENODEV)
+					continue;
+
 				dev_err(dev, "Failed to get PHY address\n");
 				return addr;
 			}
@@ -433,12 +438,6 @@ static int imx95_enetc_mdio_phyaddr_config(struct platform_device *pdev)
 				return -EINVAL;
 			}
 
-			/* The default value of LaBCR[MDIO_PHYAD_PRTAD ] is
-			 * 0, so no need to set the register.
-			 */
-			if (!addr)
-				continue;
-
 			switch (bus_devfn) {
 			case IMX95_ENETC0_BUS_DEVFN:
 				netc_reg_write(priv->ierb, IERB_LBCR(0),
@@ -578,16 +577,13 @@ static int imx94_enetc_mdio_phyaddr_config(struct netc_blk_ctrl *priv,
 
 	addr = netc_get_phy_addr(np);
 	if (addr < 0) {
+		if (addr == -ENODEV)
+			return 0;
+
 		dev_err(dev, "Failed to get PHY address\n");
 		return addr;
 	}
 
-	/* The default value of LaBCR[MDIO_PHYAD_PRTAD] is 0,
-	 * so no need to set the register.
-	 */
-	if (!addr)
-		return 0;
-
 	if (phy_mask & BIT(addr)) {
 		dev_err(dev,
 			"Find same PHY address in EMDIO and ENETC node\n");