Merge tag 'net-6.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel…

…/git/netdev/net

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

  It looks like that most people are still traveling: both the ML volume
  and the processing capacity are low.

  Previous releases - regressions:

    - netfilter:
        - nf_reject_ipv6: fix nf_reject_ip6_tcphdr_put()
        - nf_tables: keep deleted flowtable hooks until after RCU

    - tcp: check skb is non-NULL in tcp_rto_delta_us()

    - phy: aquantia: fix -ETIMEDOUT PHY probe failure when firmware not
      present

    - eth: virtio_net: fix mismatched buf address when unmapping for
      small packets

    - eth: stmmac: fix zero-division error when disabling tc cbs

    - eth: bonding: fix unnecessary warnings and logs from
      bond_xdp_get_xmit_slave()

  Previous releases - always broken:

    - netfilter:
        - fix clash resolution for bidirectional flows
        - fix allocation with no memcg accounting

    - eth: r8169: add tally counter fields added with RTL8125

    - eth: ravb: fix rx and tx frame size limit"

* tag 'net-6.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (35 commits)
  selftests: netfilter: Avoid hanging ipvs.sh
  kselftest: add test for nfqueue induced conntrack race
  netfilter: nfnetlink_queue: remove old clash resolution logic
  netfilter: nf_tables: missing objects with no memcg accounting
  netfilter: nf_tables: use rcu chain hook list iterator from netlink dump path
  netfilter: ctnetlink: compile ctnetlink_label_size with CONFIG_NF_CONNTRACK_EVENTS
  netfilter: nf_reject: Fix build warning when CONFIG_BRIDGE_NETFILTER=n
  netfilter: nf_tables: Keep deleted flowtable hooks until after RCU
  docs: tproxy: ignore non-transparent sockets in iptables
  netfilter: ctnetlink: Guard possible unused functions
  selftests: netfilter: nft_tproxy.sh: add tcp tests
  selftests: netfilter: add reverse-clash resolution test case
  netfilter: conntrack: add clash resolution for reverse collisions
  netfilter: nf_nat: don't try nat source port reallocation for reverse dir clash
  selftests/net: packetdrill: increase timing tolerance in debug mode
  usbnet: fix cyclical race on disconnect with work queue
  net: stmmac: set PP_FLAG_DMA_SYNC_DEV only if XDP is enabled
  virtio_net: Fix mismatched buf address when unmapping for small packets
  bonding: Fix unnecessary warnings and logs from bond_xdp_get_xmit_slave()
  r8169: add missing MODULE_FIRMWARE entry for RTL8126A rev.b
  ...

Documentation/networking/tproxy.rst

@@ -17,7 +17,7 @@ The idea is that you identify packets with destination address matching a local
 socket on your box, set the packet mark to a certain value::
 
     # iptables -t mangle -N DIVERT
-    # iptables -t mangle -A PREROUTING -p tcp -m socket -j DIVERT
+    # iptables -t mangle -A PREROUTING -p tcp -m socket --transparent -j DIVERT
     # iptables -t mangle -A DIVERT -j MARK --set-mark 1
     # iptables -t mangle -A DIVERT -j ACCEPT
 

MAINTAINERS

@@ -17316,8 +17316,8 @@ M:	Parthiban Veerasooran <parthiban.veerasooran@microchip.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/networking/oa-tc6-framework.rst
-F:	drivers/include/linux/oa_tc6.h
 F:	drivers/net/ethernet/oa_tc6.c
+F:	include/linux/oa_tc6.h
 
 OPEN FIRMWARE AND FLATTENED DEVICE TREE
 M:	Rob Herring <robh@kernel.org>

drivers/net/bonding/bond_main.c

@@ -5610,9 +5610,9 @@ bond_xdp_get_xmit_slave(struct net_device *bond_dev, struct xdp_buff *xdp)
 		break;
 
 	default:
-		/* Should never happen. Mode guarded by bond_xdp_check() */
-		netdev_err(bond_dev, "Unknown bonding mode %d for xdp xmit\n", BOND_MODE(bond));
-		WARN_ON_ONCE(1);
+		if (net_ratelimit())
+			netdev_err(bond_dev, "Unknown bonding mode %d for xdp xmit\n",
+				   BOND_MODE(bond));
 		return NULL;
 	}
 

drivers/net/ethernet/realtek/r8169_main.c

@@ -579,6 +579,33 @@ struct rtl8169_counters {
 	__le32	rx_multicast;
 	__le16	tx_aborted;
 	__le16	tx_underrun;
+	/* new since RTL8125 */
+	__le64 tx_octets;
+	__le64 rx_octets;
+	__le64 rx_multicast64;
+	__le64 tx_unicast64;
+	__le64 tx_broadcast64;
+	__le64 tx_multicast64;
+	__le32 tx_pause_on;
+	__le32 tx_pause_off;
+	__le32 tx_pause_all;
+	__le32 tx_deferred;
+	__le32 tx_late_collision;
+	__le32 tx_all_collision;
+	__le32 tx_aborted32;
+	__le32 align_errors32;
+	__le32 rx_frame_too_long;
+	__le32 rx_runt;
+	__le32 rx_pause_on;
+	__le32 rx_pause_off;
+	__le32 rx_pause_all;
+	__le32 rx_unknown_opcode;
+	__le32 rx_mac_error;
+	__le32 tx_underrun32;
+	__le32 rx_mac_missed;
+	__le32 rx_tcam_dropped;
+	__le32 tdu;
+	__le32 rdu;
 };
 
 struct rtl8169_tc_offsets {
@@ -681,6 +708,7 @@ MODULE_FIRMWARE(FIRMWARE_8107E_2);
 MODULE_FIRMWARE(FIRMWARE_8125A_3);
 MODULE_FIRMWARE(FIRMWARE_8125B_2);
 MODULE_FIRMWARE(FIRMWARE_8126A_2);
+MODULE_FIRMWARE(FIRMWARE_8126A_3);
 
 static inline struct device *tp_to_dev(struct rtl8169_private *tp)
 {

drivers/net/ethernet/renesas/ravb.h

@@ -1052,6 +1052,7 @@ struct ravb_hw_info {
 	netdev_features_t net_features;
 	int stats_len;
 	u32 tccr_mask;
+	u32 tx_max_frame_size;
 	u32 rx_max_frame_size;
 	u32 rx_buffer_size;
 	u32 rx_desc_size;

drivers/net/ethernet/renesas/ravb_main.c

@@ -555,8 +555,16 @@ static void ravb_emac_init_gbeth(struct net_device *ndev)
 
 static void ravb_emac_init_rcar(struct net_device *ndev)
 {
-	/* Receive frame limit set register */
-	ravb_write(ndev, ndev->mtu + ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN, RFLR);
+	struct ravb_private *priv = netdev_priv(ndev);
+
+	/* Set receive frame length
+	 *
+	 * The length set here describes the frame from the destination address
+	 * up to and including the CRC data. However only the frame data,
+	 * excluding the CRC, are transferred to memory. To allow for the
+	 * largest frames add the CRC length to the maximum Rx descriptor size.
+	 */
+	ravb_write(ndev, priv->info->rx_max_frame_size + ETH_FCS_LEN, RFLR);
 
 	/* EMAC Mode: PAUSE prohibition; Duplex; RX Checksum; TX; RX */
 	ravb_write(ndev, ECMR_ZPF | ECMR_DM |
@@ -2674,6 +2682,7 @@ static const struct ravb_hw_info ravb_gen2_hw_info = {
 	.net_features = NETIF_F_RXCSUM,
 	.stats_len = ARRAY_SIZE(ravb_gstrings_stats),
 	.tccr_mask = TCCR_TSRQ0 | TCCR_TSRQ1 | TCCR_TSRQ2 | TCCR_TSRQ3,
+	.tx_max_frame_size = SZ_2K,
 	.rx_max_frame_size = SZ_2K,
 	.rx_buffer_size = SZ_2K +
 			  SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
@@ -2696,6 +2705,7 @@ static const struct ravb_hw_info ravb_gen3_hw_info = {
 	.net_features = NETIF_F_RXCSUM,
 	.stats_len = ARRAY_SIZE(ravb_gstrings_stats),
 	.tccr_mask = TCCR_TSRQ0 | TCCR_TSRQ1 | TCCR_TSRQ2 | TCCR_TSRQ3,
+	.tx_max_frame_size = SZ_2K,
 	.rx_max_frame_size = SZ_2K,
 	.rx_buffer_size = SZ_2K +
 			  SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
@@ -2721,6 +2731,7 @@ static const struct ravb_hw_info ravb_gen4_hw_info = {
 	.net_features = NETIF_F_RXCSUM,
 	.stats_len = ARRAY_SIZE(ravb_gstrings_stats),
 	.tccr_mask = TCCR_TSRQ0 | TCCR_TSRQ1 | TCCR_TSRQ2 | TCCR_TSRQ3,
+	.tx_max_frame_size = SZ_2K,
 	.rx_max_frame_size = SZ_2K,
 	.rx_buffer_size = SZ_2K +
 			  SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
@@ -2770,6 +2781,7 @@ static const struct ravb_hw_info gbeth_hw_info = {
 	.net_features = NETIF_F_RXCSUM | NETIF_F_HW_CSUM,
 	.stats_len = ARRAY_SIZE(ravb_gstrings_stats_gbeth),
 	.tccr_mask = TCCR_TSRQ0,
+	.tx_max_frame_size = 1522,
 	.rx_max_frame_size = SZ_8K,
 	.rx_buffer_size = SZ_2K,
 	.rx_desc_size = sizeof(struct ravb_rx_desc),
@@ -2981,7 +2993,7 @@ static int ravb_probe(struct platform_device *pdev)
 	priv->avb_link_active_low =
 		of_property_read_bool(np, "renesas,ether-link-active-low");
 
-	ndev->max_mtu = info->rx_max_frame_size -
+	ndev->max_mtu = info->tx_max_frame_size -
 		(ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN);
 	ndev->min_mtu = ETH_MIN_MTU;
 

drivers/net/ethernet/seeq/ether3.c

@@ -847,9 +847,11 @@ static void ether3_remove(struct expansion_card *ec)
 {
 	struct net_device *dev = ecard_get_drvdata(ec);
 
+	ether3_outw(priv(dev)->regs.config2 |= CFG2_CTRLO, REG_CONFIG2);
 	ecard_set_drvdata(ec, NULL);
 
 	unregister_netdev(dev);
+	del_timer_sync(&priv(dev)->timer);
 	free_netdev(dev);
 	ecard_release_resources(ec);
 }

drivers/net/ethernet/stmicro/stmmac/stmmac_main.c

@@ -2035,7 +2035,7 @@ static int __alloc_dma_rx_desc_resources(struct stmmac_priv *priv,
 	rx_q->queue_index = queue;
 	rx_q->priv_data = priv;
 
-	pp_params.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
+	pp_params.flags = PP_FLAG_DMA_MAP | (xdp_prog ? PP_FLAG_DMA_SYNC_DEV : 0);
 	pp_params.pool_size = dma_conf->dma_rx_size;
 	num_pages = DIV_ROUND_UP(dma_conf->dma_buf_sz, PAGE_SIZE);
 	pp_params.order = ilog2(num_pages);

drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c

@@ -386,6 +386,7 @@ static int tc_setup_cbs(struct stmmac_priv *priv,
 			return ret;
 
 		priv->plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB;
+		return 0;
 	}
 
 	/* Final adjustments for HW */

drivers/net/ethernet/xilinx/xilinx_axienet_main.c

@@ -736,15 +736,15 @@ static int axienet_device_reset(struct net_device *ndev)
  *
  * Would either be called after a successful transmit operation, or after
  * there was an error when setting up the chain.
- * Returns the number of descriptors handled.
+ * Returns the number of packets handled.
  */
 static int axienet_free_tx_chain(struct axienet_local *lp, u32 first_bd,
 				 int nr_bds, bool force, u32 *sizep, int budget)
 {
 	struct axidma_bd *cur_p;
 	unsigned int status;
+	int i, packets = 0;
 	dma_addr_t phys;
-	int i;
 
 	for (i = 0; i < nr_bds; i++) {
 		cur_p = &lp->tx_bd_v[(first_bd + i) % lp->tx_bd_num];
@@ -763,8 +763,10 @@ static int axienet_free_tx_chain(struct axienet_local *lp, u32 first_bd,
 				 (cur_p->cntrl & XAXIDMA_BD_CTRL_LENGTH_MASK),
 				 DMA_TO_DEVICE);
 
-		if (cur_p->skb && (status & XAXIDMA_BD_STS_COMPLETE_MASK))
+		if (cur_p->skb && (status & XAXIDMA_BD_STS_COMPLETE_MASK)) {
 			napi_consume_skb(cur_p->skb, budget);
+			packets++;
+		}
 
 		cur_p->app0 = 0;
 		cur_p->app1 = 0;
@@ -780,7 +782,13 @@ static int axienet_free_tx_chain(struct axienet_local *lp, u32 first_bd,
 			*sizep += status & XAXIDMA_BD_STS_ACTUAL_LEN_MASK;
 	}
 
-	return i;
+	if (!force) {
+		lp->tx_bd_ci += i;
+		if (lp->tx_bd_ci >= lp->tx_bd_num)
+			lp->tx_bd_ci %= lp->tx_bd_num;
+	}
+
+	return packets;
 }
 
 /**
@@ -953,13 +961,10 @@ static int axienet_tx_poll(struct napi_struct *napi, int budget)
 	u32 size = 0;
 	int packets;
 
-	packets = axienet_free_tx_chain(lp, lp->tx_bd_ci, budget, false, &size, budget);
+	packets = axienet_free_tx_chain(lp, lp->tx_bd_ci, lp->tx_bd_num, false,
+					&size, budget);
 
 	if (packets) {
-		lp->tx_bd_ci += packets;
-		if (lp->tx_bd_ci >= lp->tx_bd_num)
-			lp->tx_bd_ci %= lp->tx_bd_num;
-
 		u64_stats_update_begin(&lp->tx_stat_sync);
 		u64_stats_add(&lp->tx_packets, packets);
 		u64_stats_add(&lp->tx_bytes, size);
@@ -1282,9 +1287,10 @@ static irqreturn_t axienet_tx_irq(int irq, void *_ndev)
 		u32 cr = lp->tx_dma_cr;
 
 		cr &= ~(XAXIDMA_IRQ_IOC_MASK | XAXIDMA_IRQ_DELAY_MASK);
-		axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, cr);
-
-		napi_schedule(&lp->napi_tx);
+		if (napi_schedule_prep(&lp->napi_tx)) {
+			axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, cr);
+			__napi_schedule(&lp->napi_tx);
+		}
 	}
 
 	return IRQ_HANDLED;
@@ -1326,9 +1332,10 @@ static irqreturn_t axienet_rx_irq(int irq, void *_ndev)
 		u32 cr = lp->rx_dma_cr;
 
 		cr &= ~(XAXIDMA_IRQ_IOC_MASK | XAXIDMA_IRQ_DELAY_MASK);
-		axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, cr);
-
-		napi_schedule(&lp->napi_rx);
+		if (napi_schedule_prep(&lp->napi_rx)) {
+			axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, cr);
+			__napi_schedule(&lp->napi_rx);
+		}
 	}
 
 	return IRQ_HANDLED;

drivers/net/phy/aquantia/aquantia_firmware.c

@@ -353,26 +353,32 @@ int aqr_firmware_load(struct phy_device *phydev)
 {
 	int ret;
 
-	ret = aqr_wait_reset_complete(phydev);
-	if (ret)
-		return ret;
-
-	/* Check if the firmware is not already loaded by pooling
-	 * the current version returned by the PHY. If 0 is returned,
-	 * no firmware is loaded.
+	/* Check if the firmware is not already loaded by polling
+	 * the current version returned by the PHY.
 	 */
-	ret = phy_read_mmd(phydev, MDIO_MMD_VEND1, VEND1_GLOBAL_FW_ID);
-	if (ret > 0)
-		goto exit;
-
-	ret = aqr_firmware_load_nvmem(phydev);
-	if (!ret)
-		goto exit;
-
-	ret = aqr_firmware_load_fs(phydev);
-	if (ret)
+	ret = aqr_wait_reset_complete(phydev);
+	switch (ret) {
+	case 0:
+		/* Some firmware is loaded => do nothing */
+		return 0;
+	case -ETIMEDOUT:
+		/* VEND1_GLOBAL_FW_ID still reads 0 after 2 seconds of polling.
+		 * We don't have full confidence that no firmware is loaded (in
+		 * theory it might just not have loaded yet), but we will
+		 * assume that, and load a new image.
+		 */
+		ret = aqr_firmware_load_nvmem(phydev);
+		if (!ret)
+			return ret;
+
+		ret = aqr_firmware_load_fs(phydev);
+		if (ret)
+			return ret;
+		break;
+	default:
+		/* PHY read error, propagate it to the caller */
 		return ret;
+	}
 
-exit:
 	return 0;
 }

drivers/net/phy/aquantia/aquantia_leds.c

@@ -120,7 +120,8 @@ int aqr_phy_led_hw_control_set(struct phy_device *phydev, u8 index,
 int aqr_phy_led_active_low_set(struct phy_device *phydev, int index, bool enable)
 {
 	return phy_modify_mmd(phydev, MDIO_MMD_VEND1, AQR_LED_DRIVE(index),
-			      VEND1_GLOBAL_LED_DRIVE_VDD, enable);
+			      VEND1_GLOBAL_LED_DRIVE_VDD,
+			      enable ? VEND1_GLOBAL_LED_DRIVE_VDD : 0);
 }
 
 int aqr_phy_led_polarity_set(struct phy_device *phydev, int index, unsigned long modes)

drivers/net/phy/aquantia/aquantia_main.c

@@ -435,6 +435,9 @@ static int aqr107_set_tunable(struct phy_device *phydev,
 	}
 }
 
+#define AQR_FW_WAIT_SLEEP_US	20000
+#define AQR_FW_WAIT_TIMEOUT_US	2000000
+
 /* If we configure settings whilst firmware is still initializing the chip,
  * then these settings may be overwritten. Therefore make sure chip
  * initialization has completed. Use presence of the firmware ID as
@@ -444,11 +447,19 @@ static int aqr107_set_tunable(struct phy_device *phydev,
  */
 int aqr_wait_reset_complete(struct phy_device *phydev)
 {
-	int val;
+	int ret, val;
+
+	ret = read_poll_timeout(phy_read_mmd, val, val != 0,
+				AQR_FW_WAIT_SLEEP_US, AQR_FW_WAIT_TIMEOUT_US,
+				false, phydev, MDIO_MMD_VEND1,
+				VEND1_GLOBAL_FW_ID);
+	if (val < 0) {
+		phydev_err(phydev, "Failed to read VEND1_GLOBAL_FW_ID: %pe\n",
+			   ERR_PTR(val));
+		return val;
+	}
 
-	return phy_read_mmd_poll_timeout(phydev, MDIO_MMD_VEND1,
-					 VEND1_GLOBAL_FW_ID, val, val != 0,
-					 20000, 2000000, false);
+	return ret;
 }
 
 static void aqr107_chip_info(struct phy_device *phydev)
@@ -478,7 +489,7 @@ static int aqr107_config_init(struct phy_device *phydev)
 {
 	struct aqr107_priv *priv = phydev->priv;
 	u32 led_active_low;
-	int ret, index = 0;
+	int ret;
 
 	/* Check that the PHY interface type is compatible */
 	if (phydev->interface != PHY_INTERFACE_MODE_SGMII &&
@@ -505,10 +516,9 @@ static int aqr107_config_init(struct phy_device *phydev)
 
 	/* Restore LED polarity state after reset */
 	for_each_set_bit(led_active_low, &priv->leds_active_low, AQR_MAX_LEDS) {
-		ret = aqr_phy_led_active_low_set(phydev, index, led_active_low);
+		ret = aqr_phy_led_active_low_set(phydev, led_active_low, true);
 		if (ret)
 			return ret;
-		index++;
 	}
 
 	return 0;