Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from David Miller:

1) Limit xt_hashlimit hash table size to avoid OOM or hung tasks, from
Cong Wang.

2) Fix deadlock in xsk by publishing global consumer pointers when NAPI
is finished, from Magnus Karlsson.

3) Set table field properly to RT_TABLE_COMPAT when necessary, from
Jethro Beekman.

4) NLA_STRING attributes are not necessary NULL terminated, deal wiht
that in IFLA_ALT_IFNAME. From Eric Dumazet.

5) Fix checksum handling in atlantic driver, from Dmitry Bezrukov.

6) Handle mtu==0 devices properly in wireguard, from Jason A.
Donenfeld.

7) Fix several lockdep warnings in bonding, from Taehee Yoo.

8) Fix cls_flower port blocking, from Jason Baron.

9) Sanitize internal map names in libbpf, from Toke Høiland-Jørgensen.

10) Fix RDMA race in qede driver, from Michal Kalderon.

11) Fix several false lockdep warnings by adding conditions to
list_for_each_entry_rcu(), from Madhuparna Bhowmik.

12) Fix sleep in atomic in mlx5 driver, from Huy Nguyen.

13) Fix potential deadlock in bpf_map_do_batch(), from Yonghong Song.

14) Hey, variables declared in switch statement before any case
statements are not initialized. I learn something every day. Get
rids of this stuff in several parts of the networking, from Kees
Cook.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (99 commits)
bnxt_en: Issue PCIe FLR in kdump kernel to cleanup pending DMAs.
bnxt_en: Improve device shutdown method.
net: netlink: cap max groups which will be considered in netlink_bind()
net: thunderx: workaround BGX TX Underflow issue
ionic: fix fw_status read
net: disable BRIDGE_NETFILTER by default
net: macb: Properly handle phylink on at91rm9200
s390/qeth: fix off-by-one in RX copybreak check
s390/qeth: don't warn for napi with 0 budget
s390/qeth: vnicc Fix EOPNOTSUPP precedence
openvswitch: Distribute switch variables for initialization
net: ip6_gre: Distribute switch variables for initialization
net: core: Distribute switch variables for initialization
udp: rehash on disconnect
net/tls: Fix to avoid gettig invalid tls record
bpf: Fix a potential deadlock with bpf_map_do_batch
bpf: Do not grab the bucket spinlock by default on htab batch ops
ice: Wait for VF to be reset/ready before configuration
ice: Don't tell the OS that link is going down
ice: Don't reject odd values of usecs set by user
...

drivers/net/bonding/bond_main.c

···
 	}
 }
 
+#ifdef CONFIG_LOCKDEP
+static int bond_get_lowest_level_rcu(struct net_device *dev)
+{
+	struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+	struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+	int cur = 0, max = 0;
+
+	now = dev;
+	iter = &dev->adj_list.lower;
+
+	while (1) {
+		next = NULL;
+		while (1) {
+			ldev = netdev_next_lower_dev_rcu(now, &iter);
+			if (!ldev)
+				break;
+
+			next = ldev;
+			niter = &ldev->adj_list.lower;
+			dev_stack[cur] = now;
+			iter_stack[cur++] = iter;
+			if (max <= cur)
+				max = cur;
+			break;
+		}
+
+		if (!next) {
+			if (!cur)
+				return max;
+			next = dev_stack[--cur];
+			niter = iter_stack[cur];
+		}
+
+		now = next;
+		iter = niter;
+	}
+
+	return max;
+}
+#endif
+
 static void bond_get_stats(struct net_device *bond_dev,
 			   struct rtnl_link_stats64 *stats)
 {
···
 	struct rtnl_link_stats64 temp;
 	struct list_head *iter;
 	struct slave *slave;
+	int nest_level = 0;
 
-	spin_lock(&bond->stats_lock);
-	memcpy(stats, &bond->bond_stats, sizeof(*stats));
 
 	rcu_read_lock();
+#ifdef CONFIG_LOCKDEP
+	nest_level = bond_get_lowest_level_rcu(bond_dev);
+#endif
+
+	spin_lock_nested(&bond->stats_lock, nest_level);
+	memcpy(stats, &bond->bond_stats, sizeof(*stats));
+
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		const struct rtnl_link_stats64 *new =
 			dev_get_stats(slave->dev, &temp);
···
 		/* save off the slave stats for the next run */
 		memcpy(&slave->slave_stats, new, sizeof(*new));
 	}
-	rcu_read_unlock();
 
 	memcpy(&bond->bond_stats, stats, sizeof(*stats));
 	spin_unlock(&bond->stats_lock);
+	rcu_read_unlock();
 }
 
 static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd)
···
 	case BOND_RELEASE_OLD:
 	case SIOCBONDRELEASE:
 		res = bond_release(bond_dev, slave_dev);
+		if (!res)
+			netdev_update_lockdep_key(slave_dev);
 		break;
 	case BOND_SETHWADDR_OLD:
 	case SIOCBONDSETHWADDR:

drivers/net/bonding/bond_options.c

···
 	case '-':
 		slave_dbg(bond->dev, dev, "Releasing interface\n");
 		ret = bond_release(bond->dev, dev);
+		if (!ret)
+			netdev_update_lockdep_key(dev);
 		break;
 
 	default:

drivers/net/dsa/b53/b53_common.c

···
 
 		b53_get_vlan_entry(dev, vid, vl);
 
+		if (vid == 0 && vid == b53_default_pvid(dev))
+			untagged = true;
+
 		vl->members |= BIT(port);
 		if (untagged && !dsa_is_cpu_port(ds, port))
 			vl->untag |= BIT(port);

drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c

···
 	if (flags & ~AQ_PRIV_FLAGS_MASK)
 		return -EOPNOTSUPP;
 
+	if (hweight32((flags | priv_flags) & AQ_HW_LOOPBACK_MASK) > 1) {
+		netdev_info(ndev, "Can't enable more than one loopback simultaneously\n");
+		return -EINVAL;
+	}
+
 	cfg->priv_flags = flags;
 
 	if ((priv_flags ^ flags) & BIT(AQ_HW_LOOPBACK_DMA_NET)) {

drivers/net/ethernet/aquantia/atlantic/aq_filters.c

···
 	}
 
 	if ((aq_nic->ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) &&
-	    (!test_bit(be16_to_cpu(fsp->h_ext.vlan_tci),
+	    (!test_bit(be16_to_cpu(fsp->h_ext.vlan_tci) & VLAN_VID_MASK,
 		       aq_nic->active_vlans))) {
 		netdev_err(aq_nic->ndev,
 			   "ethtool: unknown vlan-id specified");

drivers/net/ethernet/aquantia/atlantic/aq_hw.h

···
 
 	void (*enable_ptp)(struct aq_hw_s *self, int enable);
 
+	void (*adjust_ptp)(struct aq_hw_s *self, uint64_t adj);
+
 	int (*set_eee_rate)(struct aq_hw_s *self, u32 speed);
 
 	int (*get_eee_rate)(struct aq_hw_s *self, u32 *rate,

drivers/net/ethernet/aquantia/atlantic/aq_nic.c

···
 				     dx_buff->len,
 				     DMA_TO_DEVICE);
 
-	if (unlikely(dma_mapping_error(aq_nic_get_dev(self), dx_buff->pa)))
+	if (unlikely(dma_mapping_error(aq_nic_get_dev(self), dx_buff->pa))) {
+		ret = 0;
 		goto exit;
+	}
 
 	first = dx_buff;
 	dx_buff->len_pkt = skb->len;
···
 	if (likely(frags)) {
 		err = self->aq_hw_ops->hw_ring_tx_xmit(self->aq_hw,
 						       ring, frags);
-		if (err >= 0) {
-			++ring->stats.tx.packets;
-			ring->stats.tx.bytes += skb->len;
-		}
 	} else {
 		err = NETDEV_TX_BUSY;
 	}

drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c

···
 	netif_device_detach(nic->ndev);
 	netif_tx_stop_all_queues(nic->ndev);
 
-	aq_nic_stop(nic);
+	if (netif_running(nic->ndev))
+		aq_nic_stop(nic);
 
 	if (deep) {
 		aq_nic_deinit(nic, !nic->aq_hw->aq_nic_cfg->wol);
···
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct aq_nic_s *nic;
-	int ret;
+	int ret = 0;
 
 	nic = pci_get_drvdata(pdev);
 
···
 			goto err_exit;
 	}
 
-	ret = aq_nic_start(nic);
-	if (ret)
-		goto err_exit;
+	if (netif_running(nic->ndev)) {
+		ret = aq_nic_start(nic);
+		if (ret)
+			goto err_exit;
+	}
 
 	netif_device_attach(nic->ndev);
 	netif_tx_start_all_queues(nic->ndev);

drivers/net/ethernet/aquantia/atlantic/aq_ring.c

···
 			}
 		}
 
-		if (unlikely(buff->is_eop))
-			dev_kfree_skb_any(buff->skb);
+		if (unlikely(buff->is_eop)) {
+			++self->stats.rx.packets;
+			self->stats.tx.bytes += buff->skb->len;
 
+			dev_kfree_skb_any(buff->skb);
+		}
 		buff->pa = 0U;
 		buff->eop_index = 0xffffU;
 		self->sw_head = aq_ring_next_dx(self, self->sw_head);
···
 				err = 0;
 				goto err_exit;
 			}
-			if (buff->is_error || buff->is_cso_err) {
+			if (buff->is_error ||
+			    (buff->is_lro && buff->is_cso_err)) {
 				buff_ = buff;
 				do {
 					next_ = buff_->next,

drivers/net/ethernet/aquantia/atlantic/aq_ring.h

···
 			u32 is_cleaned:1;
 			u32 is_error:1;
 			u32 is_vlan:1;
-			u32 rsvd3:4;
+			u32 is_lro:1;
+			u32 rsvd3:3;
 			u16 eop_index;
 			u16 rsvd4;
 		};

drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c

···
 			}
 		}
 
+		buff->is_lro = !!(HW_ATL_B0_RXD_WB_STAT2_RSCCNT &
+				  rxd_wb->status);
 		if (HW_ATL_B0_RXD_WB_STAT2_EOP & rxd_wb->status) {
 			buff->len = rxd_wb->pkt_len %
 				AQ_CFG_RX_FRAME_MAX;
···
 				rxd_wb->pkt_len > AQ_CFG_RX_FRAME_MAX ?
 				AQ_CFG_RX_FRAME_MAX : rxd_wb->pkt_len;
 
-			if (HW_ATL_B0_RXD_WB_STAT2_RSCCNT &
-				rxd_wb->status) {
+			if (buff->is_lro) {
 				/* LRO */
 				buff->next = rxd_wb->next_desc_ptr;
 				++ring->stats.rx.lro_packets;
···
 {
 	struct aq_nic_cfg_s *cfg = self->aq_nic_cfg;
 	unsigned int i = 0U;
+	u32 vlan_promisc;
+	u32 l2_promisc;
 
-	hw_atl_rpfl2promiscuous_mode_en_set(self,
-					    IS_FILTER_ENABLED(IFF_PROMISC));
+	l2_promisc = IS_FILTER_ENABLED(IFF_PROMISC) ||
+		     !!(cfg->priv_flags & BIT(AQ_HW_LOOPBACK_DMA_NET));
+	vlan_promisc = l2_promisc || cfg->is_vlan_force_promisc;
 
-	hw_atl_rpf_vlan_prom_mode_en_set(self,
-				     IS_FILTER_ENABLED(IFF_PROMISC) ||
-				     cfg->is_vlan_force_promisc);
+	hw_atl_rpfl2promiscuous_mode_en_set(self, l2_promisc);
+
+	hw_atl_rpf_vlan_prom_mode_en_set(self, vlan_promisc);
 
 	hw_atl_rpfl2multicast_flr_en_set(self,
 					 IS_FILTER_ENABLED(IFF_ALLMULTI) &&
···
 {
 	self->ptp_clk_offset += delta;
 
+	self->aq_fw_ops->adjust_ptp(self, self->ptp_clk_offset);
+
 	return 0;
 }
 
···
 	fwreq.ptp_gpio_ctrl.index = index;
 	fwreq.ptp_gpio_ctrl.period = period;
 	/* Apply time offset */
-	fwreq.ptp_gpio_ctrl.start = start - self->ptp_clk_offset;
+	fwreq.ptp_gpio_ctrl.start = start;
 
 	size = sizeof(fwreq.msg_id) + sizeof(fwreq.ptp_gpio_ctrl);
 	return self->aq_fw_ops->send_fw_request(self, &fwreq, size);

drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c

···
 #define HW_ATL_MIF_ADDR         0x0208U
 #define HW_ATL_MIF_VAL          0x020CU
 
+#define HW_ATL_MPI_RPC_ADDR     0x0334U
 #define HW_ATL_RPC_CONTROL_ADR  0x0338U
 #define HW_ATL_RPC_STATE_ADR    0x033CU
 
···
 };
 
 static int hw_atl_utils_ver_match(u32 ver_expected, u32 ver_actual);
-
 static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self,
 				      enum hal_atl_utils_fw_state_e state);
-
 static u32 hw_atl_utils_get_mpi_mbox_tid(struct aq_hw_s *self);
 static u32 hw_atl_utils_mpi_get_state(struct aq_hw_s *self);
 static u32 hw_atl_utils_mif_cmd_get(struct aq_hw_s *self);
 static u32 hw_atl_utils_mif_addr_get(struct aq_hw_s *self);
 static u32 hw_atl_utils_rpc_state_get(struct aq_hw_s *self);
+static u32 aq_fw1x_rpc_get(struct aq_hw_s *self);
 
 int hw_atl_utils_initfw(struct aq_hw_s *self, const struct aq_fw_ops **fw_ops)
 {
···
 					self, self->mbox_addr,
 					self->mbox_addr != 0U,
 					1000U, 10000U);
+	err = readx_poll_timeout_atomic(aq_fw1x_rpc_get, self,
+					self->rpc_addr,
+					self->rpc_addr != 0U,
+					1000U, 100000U);
 
 	return err;
 }
···
 						self, fw.val,
 						sw.tid == fw.tid,
 						1000U, 100000U);
+		if (err < 0)
+			goto err_exit;
+
+		err = aq_hw_err_from_flags(self);
+		if (err < 0)
+			goto err_exit;
 
 		if (fw.len == 0xFFFFU) {
 			err = hw_atl_utils_fw_rpc_call(self, sw.len);
···
 static u32 hw_atl_utils_rpc_state_get(struct aq_hw_s *self)
 {
 	return aq_hw_read_reg(self, HW_ATL_RPC_STATE_ADR);
+}
+
+static u32 aq_fw1x_rpc_get(struct aq_hw_s *self)
+{
+	return aq_hw_read_reg(self, HW_ATL_MPI_RPC_ADDR);
 }
 
 const struct aq_fw_ops aq_fw_1x_ops = {

drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c

···
 #define HW_ATL_FW3X_EXT_CONTROL_ADDR     0x378
 #define HW_ATL_FW3X_EXT_STATE_ADDR       0x37c
 
+#define HW_ATL_FW3X_PTP_ADJ_LSW_ADDR	 0x50a0
+#define HW_ATL_FW3X_PTP_ADJ_MSW_ADDR	 0x50a4
+
 #define HW_ATL_FW2X_CAP_PAUSE            BIT(CAPS_HI_PAUSE)
 #define HW_ATL_FW2X_CAP_ASYM_PAUSE       BIT(CAPS_HI_ASYMMETRIC_PAUSE)
 #define HW_ATL_FW2X_CAP_SLEEP_PROXY      BIT(CAPS_HI_SLEEP_PROXY)
···
 	aq_hw_write_reg(self, HW_ATL_FW3X_EXT_CONTROL_ADDR, ptp_opts);
 }
 
+static void aq_fw3x_adjust_ptp(struct aq_hw_s *self, uint64_t adj)
+{
+	aq_hw_write_reg(self, HW_ATL_FW3X_PTP_ADJ_LSW_ADDR,
+			(adj >>  0) & 0xffffffff);
+	aq_hw_write_reg(self, HW_ATL_FW3X_PTP_ADJ_MSW_ADDR,
+			(adj >> 32) & 0xffffffff);
+}
+
 static int aq_fw2x_led_control(struct aq_hw_s *self, u32 mode)
 {
 	if (self->fw_ver_actual < HW_ATL_FW_VER_LED)
···
 	.enable_ptp         = aq_fw3x_enable_ptp,
 	.led_control        = aq_fw2x_led_control,
 	.set_phyloopback    = aq_fw2x_set_phyloopback,
+	.adjust_ptp         = aq_fw3x_adjust_ptp,
 };

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

···
 	if (version_printed++ == 0)
 		pr_info("%s", version);
 
+	/* Clear any pending DMA transactions from crash kernel
+	 * while loading driver in capture kernel.
+	 */
+	if (is_kdump_kernel()) {
+		pci_clear_master(pdev);
+		pcie_flr(pdev);
+	}
+
 	max_irqs = bnxt_get_max_irq(pdev);
 	dev = alloc_etherdev_mq(sizeof(*bp), max_irqs);
 	if (!dev)
···
 		dev_close(dev);
 
 	bnxt_ulp_shutdown(bp);
+	bnxt_clear_int_mode(bp);
+	pci_disable_device(pdev);
 
 	if (system_state == SYSTEM_POWER_OFF) {
-		bnxt_clear_int_mode(bp);
-		pci_disable_device(pdev);
 		pci_wake_from_d3(pdev, bp->wol);
 		pci_set_power_state(pdev, PCI_D3hot);
 	}

drivers/net/ethernet/broadcom/cnic_defs.h

···
 #define L4_KWQ_UPDATE_PG_RESERVERD2_SHIFT 2
 #endif
 #if defined(__BIG_ENDIAN)
-	u16 reserverd3;
+	u16 reserved3;
 	u8 da0;
 	u8 da1;
 #elif defined(__LITTLE_ENDIAN)
 	u8 da1;
 	u8 da0;
-	u16 reserverd3;
+	u16 reserved3;
 #endif
 #if defined(__BIG_ENDIAN)
 	u8 da2;

drivers/net/ethernet/cadence/macb.h

···
 #define MACB_CAPS_GEM_HAS_PTP			0x00000040
 #define MACB_CAPS_BD_RD_PREFETCH		0x00000080
 #define MACB_CAPS_NEEDS_RSTONUBR		0x00000100
+#define MACB_CAPS_MACB_IS_EMAC			0x08000000
 #define MACB_CAPS_FIFO_MODE			0x10000000
 #define MACB_CAPS_GIGABIT_MODE_AVAILABLE	0x20000000
 #define MACB_CAPS_SG_DISABLED			0x40000000

drivers/net/ethernet/cadence/macb_main.c

···
 	old_ctrl = ctrl = macb_or_gem_readl(bp, NCFGR);
 
 	/* Clear all the bits we might set later */
-	ctrl &= ~(GEM_BIT(GBE) | MACB_BIT(SPD) | MACB_BIT(FD) | MACB_BIT(PAE) |
-		  GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL));
+	ctrl &= ~(MACB_BIT(SPD) | MACB_BIT(FD) | MACB_BIT(PAE));
+
+	if (bp->caps & MACB_CAPS_MACB_IS_EMAC) {
+		if (state->interface == PHY_INTERFACE_MODE_RMII)
+			ctrl |= MACB_BIT(RM9200_RMII);
+	} else {
+		ctrl &= ~(GEM_BIT(GBE) | GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL));
+
+		/* We do not support MLO_PAUSE_RX yet */
+		if (state->pause & MLO_PAUSE_TX)
+			ctrl |= MACB_BIT(PAE);
+
+		if (state->interface == PHY_INTERFACE_MODE_SGMII)
+			ctrl |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL);
+	}
 
 	if (state->speed == SPEED_1000)
 		ctrl |= GEM_BIT(GBE);
···
 
 	if (state->duplex)
 		ctrl |= MACB_BIT(FD);
-
-	/* We do not support MLO_PAUSE_RX yet */
-	if (state->pause & MLO_PAUSE_TX)
-		ctrl |= MACB_BIT(PAE);
-
-	if (state->interface == PHY_INTERFACE_MODE_SGMII)
-		ctrl |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL);
 
 	/* Apply the new configuration, if any */
 	if (old_ctrl ^ ctrl)
···
 	unsigned int q;
 	u32 ctrl;
 
-	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
-		queue_writel(queue, IDR,
-			     bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP));
+	if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC))
+		for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
+			queue_writel(queue, IDR,
+				     bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP));
 
 	/* Disable Rx and Tx */
 	ctrl = macb_readl(bp, NCR) & ~(MACB_BIT(RE) | MACB_BIT(TE));
···
 	struct macb_queue *queue;
 	unsigned int q;
 
-	macb_set_tx_clk(bp->tx_clk, bp->speed, ndev);
+	if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) {
+		macb_set_tx_clk(bp->tx_clk, bp->speed, ndev);
 
-	/* Initialize rings & buffers as clearing MACB_BIT(TE) in link down
-	 * cleared the pipeline and control registers.
-	 */
-	bp->macbgem_ops.mog_init_rings(bp);
-	macb_init_buffers(bp);
+		/* Initialize rings & buffers as clearing MACB_BIT(TE) in link down
+		 * cleared the pipeline and control registers.
+		 */
+		bp->macbgem_ops.mog_init_rings(bp);
+		macb_init_buffers(bp);
 
-	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
-		queue_writel(queue, IER,
-			     bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP));
+		for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
+			queue_writel(queue, IER,
+				     bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP));
+	}
 
 	/* Enable Rx and Tx */
 	macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(RE) | MACB_BIT(TE));
···
 	u32 ctl;
 	int ret;
 
+	ret = pm_runtime_get_sync(&lp->pdev->dev);
+	if (ret < 0)
+		return ret;
+
 	/* Clear internal statistics */
 	ctl = macb_readl(lp, NCR);
 	macb_writel(lp, NCR, ctl | MACB_BIT(CLRSTAT));
···
 			  q->rx_buffers, q->rx_buffers_dma);
 	q->rx_buffers = NULL;
 
-	return 0;
+	return pm_runtime_put(&lp->pdev->dev);
 }
 
 /* Transmit packet */
···
 	struct net_device *dev = platform_get_drvdata(pdev);
 	struct macb *bp = netdev_priv(dev);
 	int err;
-	u32 reg;
 
 	bp->queues[0].bp = bp;
 
···
 
 	macb_writel(bp, NCR, 0);
 
-	reg = MACB_BF(CLK, MACB_CLK_DIV32) | MACB_BIT(BIG);
-	if (bp->phy_interface == PHY_INTERFACE_MODE_RMII)
-		reg |= MACB_BIT(RM9200_RMII);
-
-	macb_writel(bp, NCFGR, reg);
+	macb_writel(bp, NCFGR, MACB_BF(CLK, MACB_CLK_DIV32) | MACB_BIT(BIG));
 
 	return 0;
 }
···
 };
 
 static const struct macb_config emac_config = {
-	.caps = MACB_CAPS_NEEDS_RSTONUBR,
+	.caps = MACB_CAPS_NEEDS_RSTONUBR | MACB_CAPS_MACB_IS_EMAC,
 	.clk_init = at91ether_clk_init,
 	.init = at91ether_init,
 };

drivers/net/ethernet/cavium/thunder/thunder_bgx.c

···
 	lmac = &bgx->lmac[lmacid];
 
 	cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
-	if (enable)
+	if (enable) {
 		cfg |= CMR_PKT_RX_EN | CMR_PKT_TX_EN;
-	else
+
+		/* enable TX FIFO Underflow interrupt */
+		bgx_reg_modify(bgx, lmacid, BGX_GMP_GMI_TXX_INT_ENA_W1S,
+			       GMI_TXX_INT_UNDFLW);
+	} else {
 		cfg &= ~(CMR_PKT_RX_EN | CMR_PKT_TX_EN);
+
+		/* Disable TX FIFO Underflow interrupt */
+		bgx_reg_modify(bgx, lmacid, BGX_GMP_GMI_TXX_INT_ENA_W1C,
+			       GMI_TXX_INT_UNDFLW);
+	}
 	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
 
 	if (bgx->is_rgx)
···
 	return bgx_init_of_phy(bgx);
 }
 
+static irqreturn_t bgx_intr_handler(int irq, void *data)
+{
+	struct bgx *bgx = (struct bgx *)data;
+	u64 status, val;
+	int lmac;
+
+	for (lmac = 0; lmac < bgx->lmac_count; lmac++) {
+		status = bgx_reg_read(bgx, lmac, BGX_GMP_GMI_TXX_INT);
+		if (status & GMI_TXX_INT_UNDFLW) {
+			pci_err(bgx->pdev, "BGX%d lmac%d UNDFLW\n",
+				bgx->bgx_id, lmac);
+			val = bgx_reg_read(bgx, lmac, BGX_CMRX_CFG);
+			val &= ~CMR_EN;
+			bgx_reg_write(bgx, lmac, BGX_CMRX_CFG, val);
+			val |= CMR_EN;
+			bgx_reg_write(bgx, lmac, BGX_CMRX_CFG, val);
+		}
+		/* clear interrupts */
+		bgx_reg_write(bgx, lmac, BGX_GMP_GMI_TXX_INT, status);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void bgx_register_intr(struct pci_dev *pdev)
+{
+	struct bgx *bgx = pci_get_drvdata(pdev);
+	int ret;
+
+	ret = pci_alloc_irq_vectors(pdev, BGX_LMAC_VEC_OFFSET,
+				    BGX_LMAC_VEC_OFFSET, PCI_IRQ_ALL_TYPES);
+	if (ret < 0) {
+		pci_err(pdev, "Req for #%d msix vectors failed\n",
+			BGX_LMAC_VEC_OFFSET);
+		return;
+	}
+	ret = pci_request_irq(pdev, GMPX_GMI_TX_INT, bgx_intr_handler, NULL,
+			      bgx, "BGX%d", bgx->bgx_id);
+	if (ret)
+		pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx);
+}
+
 static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	int err;
···
 
 	pci_set_drvdata(pdev, bgx);
 
-	err = pci_enable_device(pdev);
+	err = pcim_enable_device(pdev);
 	if (err) {
 		dev_err(dev, "Failed to enable PCI device\n");
 		pci_set_drvdata(pdev, NULL);
···
 
 	bgx_init_hw(bgx);
 
+	bgx_register_intr(pdev);
+
 	/* Enable all LMACs */
 	for (lmac = 0; lmac < bgx->lmac_count; lmac++) {
 		err = bgx_lmac_enable(bgx, lmac);
···
 
 err_enable:
 	bgx_vnic[bgx->bgx_id] = NULL;
+	pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx);
 err_release_regions:
 	pci_release_regions(pdev);
 err_disable_device:
···
 	/* Disable all LMACs */
 	for (lmac = 0; lmac < bgx->lmac_count; lmac++)
 		bgx_lmac_disable(bgx, lmac);
+
+	pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx);
 
 	bgx_vnic[bgx->bgx_id] = NULL;
 	pci_release_regions(pdev);

drivers/net/ethernet/cavium/thunder/thunder_bgx.h

···
 #define BGX_GMP_GMI_TXX_BURST		0x38228
 #define BGX_GMP_GMI_TXX_MIN_PKT		0x38240
 #define BGX_GMP_GMI_TXX_SGMII_CTL	0x38300
+#define BGX_GMP_GMI_TXX_INT		0x38500
+#define BGX_GMP_GMI_TXX_INT_W1S		0x38508
+#define BGX_GMP_GMI_TXX_INT_ENA_W1C	0x38510
+#define BGX_GMP_GMI_TXX_INT_ENA_W1S	0x38518
+#define  GMI_TXX_INT_PTP_LOST			BIT_ULL(4)
+#define  GMI_TXX_INT_LATE_COL			BIT_ULL(3)
+#define  GMI_TXX_INT_XSDEF			BIT_ULL(2)
+#define  GMI_TXX_INT_XSCOL			BIT_ULL(1)
+#define  GMI_TXX_INT_UNDFLW			BIT_ULL(0)
 
 #define BGX_MSIX_VEC_0_29_ADDR		0x400000 /* +(0..29) << 4 */
 #define BGX_MSIX_VEC_0_29_CTL		0x400008

drivers/net/ethernet/davicom/dm9000.c

···
 	mac_addr = of_get_mac_address(np);
 	if (!IS_ERR(mac_addr))
 		ether_addr_copy(pdata->dev_addr, mac_addr);
+	else if (PTR_ERR(mac_addr) == -EPROBE_DEFER)
+		return ERR_CAST(mac_addr);
 
 	return pdata;
 }

drivers/net/ethernet/intel/ice/ice_ethtool.c

···
 	else
 		return -EINVAL;
 
-	/* Tell the OS link is going down, the link will go back up when fw
-	 * says it is ready asynchronously
-	 */
-	ice_print_link_msg(vsi, false);
-	netif_carrier_off(netdev);
-	netif_tx_stop_all_queues(netdev);
-
 	/* Set the FC mode and only restart AN if link is up */
 	status = ice_set_fc(pi, &aq_failures, link_up);
 
···
 		return -EINVAL;
 	}
 
-	/* hardware only supports an ITR granularity of 2us */
-	if (coalesce_usecs % 2 != 0) {
-		netdev_info(vsi->netdev, "Invalid value, %s-usecs must be even\n",
-			    c_type_str);
-		return -EINVAL;
-	}
-
 	if (use_adaptive_coalesce) {
 		rc->itr_setting |= ICE_ITR_DYNAMIC;
 	} else {
-		/* store user facing value how it was set */
+		/* save the user set usecs */
 		rc->itr_setting = coalesce_usecs;
-		/* set to static and convert to value HW understands */
-		rc->target_itr =
-			ITR_TO_REG(ITR_REG_ALIGN(rc->itr_setting));
+		/* device ITR granularity is in 2 usec increments */
+		rc->target_itr = ITR_REG_ALIGN(rc->itr_setting);
 	}
 
 	return 0;
···
 }
 
 /**
+ * ice_print_if_odd_usecs - print message if user tries to set odd [tx|rx]-usecs
+ * @netdev: netdev used for print
+ * @itr_setting: previous user setting
+ * @use_adaptive_coalesce: if adaptive coalesce is enabled or being enabled
+ * @coalesce_usecs: requested value of [tx|rx]-usecs
+ * @c_type_str: either "rx" or "tx" to match user set field of [tx|rx]-usecs
+ */
+static void
+ice_print_if_odd_usecs(struct net_device *netdev, u16 itr_setting,
+		       u32 use_adaptive_coalesce, u32 coalesce_usecs,
+		       const char *c_type_str)
+{
+	if (use_adaptive_coalesce)
+		return;
+
+	itr_setting = ITR_TO_REG(itr_setting);
+
+	if (itr_setting != coalesce_usecs && (coalesce_usecs % 2))
+		netdev_info(netdev, "User set %s-usecs to %d, device only supports even values. Rounding down and attempting to set %s-usecs to %d\n",
+			    c_type_str, coalesce_usecs, c_type_str,
+			    ITR_REG_ALIGN(coalesce_usecs));
+}
+
+/**
  * __ice_set_coalesce - set ITR/INTRL values for the device
  * @netdev: pointer to the netdev associated with this query
  * @ec: ethtool structure to fill with driver's coalesce settings
···
 		return -EINVAL;
 
 	if (q_num < 0) {
+		struct ice_q_vector *q_vector = vsi->q_vectors[0];
 		int v_idx;
+
+		if (q_vector) {
+			ice_print_if_odd_usecs(netdev, q_vector->rx.itr_setting,
+					       ec->use_adaptive_rx_coalesce,
+					       ec->rx_coalesce_usecs, "rx");
+
+			ice_print_if_odd_usecs(netdev, q_vector->tx.itr_setting,
+					       ec->use_adaptive_tx_coalesce,
+					       ec->tx_coalesce_usecs, "tx");
+		}
 
 		ice_for_each_q_vector(vsi, v_idx) {
 			/* In some cases if DCB is configured the num_[rx|tx]q

drivers/net/ethernet/intel/ice/ice_txrx.h

···
 #define ICE_ITR_GRAN_S		1	/* ITR granularity is always 2us */
 #define ICE_ITR_GRAN_US		BIT(ICE_ITR_GRAN_S)
 #define ICE_ITR_MASK		0x1FFE	/* ITR register value alignment mask */
-#define ITR_REG_ALIGN(setting)	__ALIGN_MASK(setting, ~ICE_ITR_MASK)
+#define ITR_REG_ALIGN(setting)	((setting) & ICE_ITR_MASK)
 
 #define ICE_ITR_ADAPTIVE_MIN_INC	0x0002
 #define ICE_ITR_ADAPTIVE_MIN_USECS	0x0002

drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c

···
 }
 
 /**
+ * ice_wait_on_vf_reset - poll to make sure a given VF is ready after reset
+ * @vf: The VF being resseting
+ *
+ * The max poll time is about ~800ms, which is about the maximum time it takes
+ * for a VF to be reset and/or a VF driver to be removed.
+ */
+static void ice_wait_on_vf_reset(struct ice_vf *vf)
+{
+	int i;
+
+	for (i = 0; i < ICE_MAX_VF_RESET_TRIES; i++) {
+		if (test_bit(ICE_VF_STATE_INIT, vf->vf_states))
+			break;
+		msleep(ICE_MAX_VF_RESET_SLEEP_MS);
+	}
+}
+
+/**
+ * ice_check_vf_ready_for_cfg - check if VF is ready to be configured/queried
+ * @vf: VF to check if it's ready to be configured/queried
+ *
+ * The purpose of this function is to make sure the VF is not in reset, not
+ * disabled, and initialized so it can be configured and/or queried by a host
+ * administrator.
+ */
+static int ice_check_vf_ready_for_cfg(struct ice_vf *vf)
+{
+	struct ice_pf *pf;
+
+	ice_wait_on_vf_reset(vf);
+
+	if (ice_is_vf_disabled(vf))
+		return -EINVAL;
+
+	pf = vf->pf;
+	if (ice_check_vf_init(pf, vf))
+		return -EBUSY;
+
+	return 0;
+}
+
+/**
  * ice_set_vf_spoofchk
  * @netdev: network interface device structure
  * @vf_id: VF identifier
···
 	enum ice_status status;
 	struct device *dev;
 	struct ice_vf *vf;
-	int ret = 0;
+	int ret;
 
 	dev = ice_pf_to_dev(pf);
 	if (ice_validate_vf_id(pf, vf_id))
 		return -EINVAL;
 
 	vf = &pf->vf[vf_id];
-
-	if (ice_check_vf_init(pf, vf))
-		return -EBUSY;
+	ret = ice_check_vf_ready_for_cfg(vf);
+	if (ret)
+		return ret;
 
 	vf_vsi = pf->vsi[vf->lan_vsi_idx];
 	if (!vf_vsi) {
···
 	struct ice_vsi *vsi;
 	struct device *dev;
 	struct ice_vf *vf;
-	int ret = 0;
+	int ret;
 
 	dev = ice_pf_to_dev(pf);
 	if (ice_validate_vf_id(pf, vf_id))
···
 
 	vf = &pf->vf[vf_id];
 	vsi = pf->vsi[vf->lan_vsi_idx];
-	if (ice_check_vf_init(pf, vf))
-		return -EBUSY;
+
+	ret = ice_check_vf_ready_for_cfg(vf);
+	if (ret)
+		return ret;
 
 	if (le16_to_cpu(vsi->info.pvid) == vlanprio) {
 		/* duplicate request, so just return success */
 		dev_dbg(dev, "Duplicate pvid %d request\n", vlanprio);
-		return ret;
+		return 0;
 	}
 
 	/* If PVID, then remove all filters on the old VLAN */
···
 	if (vlan_id || qos) {
 		ret = ice_vsi_manage_pvid(vsi, vlanprio, true);
 		if (ret)
-			goto error_set_pvid;
+			return ret;
 	} else {
 		ice_vsi_manage_pvid(vsi, 0, false);
 		vsi->info.pvid = 0;
···
 		/* add new VLAN filter for each MAC */
 		ret = ice_vsi_add_vlan(vsi, vlan_id);
 		if (ret)
-			goto error_set_pvid;
+			return ret;
 	}
 
 	/* The Port VLAN needs to be saved across resets the same as the
···
 	 */
 	vf->port_vlan_id = le16_to_cpu(vsi->info.pvid);
 
-error_set_pvid:
-	return ret;
+	return 0;
 }
 
 /**
···
 }
 
 /**
- * ice_wait_on_vf_reset
- * @vf: The VF being resseting
- *
- * Poll to make sure a given VF is ready after reset
- */
-static void ice_wait_on_vf_reset(struct ice_vf *vf)
-{
-	int i;
-
-	for (i = 0; i < ICE_MAX_VF_RESET_WAIT; i++) {
-		if (test_bit(ICE_VF_STATE_INIT, vf->vf_states))
-			break;
-		msleep(20);
-	}
-}
-
-/**
  * ice_set_vf_mac
  * @netdev: network interface device structure
  * @vf_id: VF identifier
···
 {
 	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 	struct ice_vf *vf;
-	int ret = 0;
+	int ret;
 
 	if (ice_validate_vf_id(pf, vf_id))
 		return -EINVAL;
-
-	vf = &pf->vf[vf_id];
-	/* Don't set MAC on disabled VF */
-	if (ice_is_vf_disabled(vf))
-		return -EINVAL;
-
-	/* In case VF is in reset mode, wait until it is completed. Depending
-	 * on factors like queue disabling routine, this could take ~250ms
-	 */
-	ice_wait_on_vf_reset(vf);
-
-	if (ice_check_vf_init(pf, vf))
-		return -EBUSY;
 
 	if (is_zero_ether_addr(mac) || is_multicast_ether_addr(mac)) {
 		netdev_err(netdev, "%pM not a valid unicast address\n", mac);
 		return -EINVAL;
 	}
+
+	vf = &pf->vf[vf_id];
+	ret = ice_check_vf_ready_for_cfg(vf);
+	if (ret)
+		return ret;
 
 	/* copy MAC into dflt_lan_addr and trigger a VF reset. The reset
 	 * flow will use the updated dflt_lan_addr and add a MAC filter
···
 		    vf_id, mac);
 
 	ice_vc_reset_vf(vf);
-	return ret;
+	return 0;
 }
 
 /**
···
 {
 	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 	struct ice_vf *vf;
+	int ret;
 
 	if (ice_validate_vf_id(pf, vf_id))
 		return -EINVAL;
 
 	vf = &pf->vf[vf_id];
-	/* Don't set Trusted Mode on disabled VF */
-	if (ice_is_vf_disabled(vf))
-		return -EINVAL;
-
-	/* In case VF is in reset mode, wait until it is completed. Depending
-	 * on factors like queue disabling routine, this could take ~250ms
-	 */
-	ice_wait_on_vf_reset(vf);
-
-	if (ice_check_vf_init(pf, vf))
-		return -EBUSY;
+	ret = ice_check_vf_ready_for_cfg(vf);
+	if (ret)
+		return ret;
 
 	/* Check if already trusted */
 	if (trusted == vf->trusted)
···
 {
 	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 	struct ice_vf *vf;
+	int ret;
 
 	if (ice_validate_vf_id(pf, vf_id))
 		return -EINVAL;
 
 	vf = &pf->vf[vf_id];
-	if (ice_check_vf_init(pf, vf))
-		return -EBUSY;
+	ret = ice_check_vf_ready_for_cfg(vf);
+	if (ret)
+		return ret;
 
 	switch (link_state) {
 	case IFLA_VF_LINK_STATE_AUTO:
···
 	struct ice_eth_stats *stats;
 	struct ice_vsi *vsi;
 	struct ice_vf *vf;
+	int ret;
 
 	if (ice_validate_vf_id(pf, vf_id))
 		return -EINVAL;
 
 	vf = &pf->vf[vf_id];
-
-	if (ice_check_vf_init(pf, vf))
-		return -EBUSY;
+	ret = ice_check_vf_ready_for_cfg(vf);
+	if (ret)
+		return ret;
 
 	vsi = pf->vsi[vf->lan_vsi_idx];
 	if (!vsi)

drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h

···
 #define ICE_MAX_POLICY_INTR_PER_VF	33
 #define ICE_MIN_INTR_PER_VF		(ICE_MIN_QS_PER_VF + 1)
 #define ICE_DFLT_INTR_PER_VF		(ICE_DFLT_QS_PER_VF + 1)
-#define ICE_MAX_VF_RESET_WAIT		15
+#define ICE_MAX_VF_RESET_TRIES		40
+#define ICE_MAX_VF_RESET_SLEEP_MS	20
 
 #define ice_for_each_vf(pf, i) \
 	for ((i) = 0; (i) < (pf)->num_alloc_vfs; (i)++)

drivers/net/ethernet/mellanox/mlx5/core/en/health.c

···
 	netdev_err(priv->netdev, err_str);
 
 	if (!reporter)
-		return err_ctx->recover(&err_ctx->ctx);
+		return err_ctx->recover(err_ctx->ctx);
 
 	return devlink_health_report(reporter, err_str, err_ctx);
 }

drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h

···
 	}
 }
 
+static inline void mlx5e_rqwq_reset(struct mlx5e_rq *rq)
+{
+	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
+		mlx5_wq_ll_reset(&rq->mpwqe.wq);
+	else
+		mlx5_wq_cyc_reset(&rq->wqe.wq);
+}
+
 /* SW parser related functions */
 
 struct mlx5e_swp_spec {

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

···
 	if (!in)
 		return -ENOMEM;
 
+	if (curr_state == MLX5_RQC_STATE_RST && next_state == MLX5_RQC_STATE_RDY)
+		mlx5e_rqwq_reset(rq);
+
 	rqc = MLX5_ADDR_OF(modify_rq_in, in, ctx);
 
 	MLX5_SET(modify_rq_in, in, rq_state, curr_state);

drivers/net/ethernet/mellanox/mlx5/core/eswitch.c

···
 
 static int esw_legacy_enable(struct mlx5_eswitch *esw)
 {
-	int ret;
+	struct mlx5_vport *vport;
+	int ret, i;
 
 	ret = esw_create_legacy_table(esw);
 	if (ret)
 		return ret;
+
+	mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs)
+		vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO;
 
 	ret = mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_LEGACY_SRIOV_VPORT_EVENTS);
 	if (ret)
···
 
 int mlx5_eswitch_get_vepa(struct mlx5_eswitch *esw, u8 *setting)
 {
-	int err = 0;
-
 	if (!esw)
 		return -EOPNOTSUPP;
 
 	if (!ESW_ALLOWED(esw))
 		return -EPERM;
 
-	mutex_lock(&esw->state_lock);
-	if (esw->mode != MLX5_ESWITCH_LEGACY) {
-		err = -EOPNOTSUPP;
-		goto out;
-	}
+	if (esw->mode != MLX5_ESWITCH_LEGACY)
+		return -EOPNOTSUPP;
 
 	*setting = esw->fdb_table.legacy.vepa_uplink_rule ? 1 : 0;
-
-out:
-	mutex_unlock(&esw->state_lock);
-	return err;
+	return 0;
 }
 
 int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw,

drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c

···
 		return -EINVAL;
 	}
 
-	mlx5_eswitch_disable(esw, true);
+	mlx5_eswitch_disable(esw, false);
 	mlx5_eswitch_update_num_of_vfs(esw, esw->dev->priv.sriov.num_vfs);
 	err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_OFFLOADS);
 	if (err) {
···
 {
 	int err, err1;
 
-	mlx5_eswitch_disable(esw, true);
+	mlx5_eswitch_disable(esw, false);
 	err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_LEGACY);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to legacy");

drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.c

···
 static const unsigned int ESW_POOLS[] = { 4 * 1024 * 1024,
 					  1 * 1024 * 1024,
 					  64 * 1024,
-					  4 * 1024, };
+					  128 };
 
 struct mlx5_esw_chains_priv {
 	struct rhashtable chains_ht;

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c

···
 	struct mlx5dr_cmd_vport_cap *vport_cap;
 	struct mlx5dr_domain *dmn = sb->dmn;
 	struct mlx5dr_cmd_caps *caps;
+	u8 *bit_mask = sb->bit_mask;
 	u8 *tag = hw_ste->tag;
+	bool source_gvmi_set;
 
 	DR_STE_SET_TAG(src_gvmi_qp, tag, source_qp, misc, source_sqn);
 
···
 	if (!vport_cap)
 		return -EINVAL;
 
-	if (vport_cap->vport_gvmi)
+	source_gvmi_set = MLX5_GET(ste_src_gvmi_qp, bit_mask, source_gvmi);
+	if (vport_cap->vport_gvmi && source_gvmi_set)
 		MLX5_SET(ste_src_gvmi_qp, tag, source_gvmi, vport_cap->vport_gvmi);
 
 	misc->source_eswitch_owner_vhca_id = 0;

drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c

···
 					 struct mlx5_flow_table *next_ft)
 {
 	struct mlx5dr_table *tbl;
+	u32 flags;
 	int err;
 
 	if (mlx5_dr_is_fw_table(ft->flags))
 		return mlx5_fs_cmd_get_fw_cmds()->create_flow_table(ns, ft,
 								    log_size,
 								    next_ft);
+	flags = ft->flags;
+	/* turn off encap/decap if not supported for sw-str by fw */
+	if (!MLX5_CAP_FLOWTABLE(ns->dev, sw_owner_reformat_supported))
+		flags = ft->flags & ~(MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT |
+				      MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);
 
-	tbl = mlx5dr_table_create(ns->fs_dr_domain.dr_domain,
-				  ft->level, ft->flags);
+	tbl = mlx5dr_table_create(ns->fs_dr_domain.dr_domain, ft->level, flags);
 	if (!tbl) {
 		mlx5_core_err(ns->dev, "Failed creating dr flow_table\n");
 		return -EINVAL;

drivers/net/ethernet/mellanox/mlx5/core/wq.c

···
 	print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET, 16, 1, wqe, len, false);
 }
 
+void mlx5_wq_cyc_reset(struct mlx5_wq_cyc *wq)
+{
+	wq->wqe_ctr = 0;
+	wq->cur_sz = 0;
+	mlx5_wq_cyc_update_db_record(wq);
+}
+
 int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *qpc, struct mlx5_wq_qp *wq,
 		      struct mlx5_wq_ctrl *wq_ctrl)
···
 	return err;
 }
 
+static void mlx5_wq_ll_init_list(struct mlx5_wq_ll *wq)
+{
+	struct mlx5_wqe_srq_next_seg *next_seg;
+	int i;
+
+	for (i = 0; i < wq->fbc.sz_m1; i++) {
+		next_seg = mlx5_wq_ll_get_wqe(wq, i);
+		next_seg->next_wqe_index = cpu_to_be16(i + 1);
+	}
+	next_seg = mlx5_wq_ll_get_wqe(wq, i);
+	wq->tail_next = &next_seg->next_wqe_index;
+}
+
 int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *wqc, struct mlx5_wq_ll *wq,
 		      struct mlx5_wq_ctrl *wq_ctrl)
···
 	u8 log_wq_stride = MLX5_GET(wq, wqc, log_wq_stride);
 	u8 log_wq_sz     = MLX5_GET(wq, wqc, log_wq_sz);
 	struct mlx5_frag_buf_ctrl *fbc = &wq->fbc;
-	struct mlx5_wqe_srq_next_seg *next_seg;
 	int err;
-	int i;
 
 	err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node);
 	if (err) {
···
 
 	mlx5_init_fbc(wq_ctrl->buf.frags, log_wq_stride, log_wq_sz, fbc);
 
-	for (i = 0; i < fbc->sz_m1; i++) {
-		next_seg = mlx5_wq_ll_get_wqe(wq, i);
-		next_seg->next_wqe_index = cpu_to_be16(i + 1);
-	}
-	next_seg = mlx5_wq_ll_get_wqe(wq, i);
-	wq->tail_next = &next_seg->next_wqe_index;
-
+	mlx5_wq_ll_init_list(wq);
 	wq_ctrl->mdev = mdev;
 
 	return 0;
···
 	mlx5_db_free(mdev, &wq_ctrl->db);
 
 	return err;
+}
+
+void mlx5_wq_ll_reset(struct mlx5_wq_ll *wq)
+{
+	wq->head = 0;
+	wq->wqe_ctr = 0;
+	wq->cur_sz = 0;
+	mlx5_wq_ll_init_list(wq);
+	mlx5_wq_ll_update_db_record(wq);
 }
 
 void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl)

drivers/net/ethernet/mellanox/mlx5/core/wq.h

···
 		       void *wqc, struct mlx5_wq_cyc *wq,
 		       struct mlx5_wq_ctrl *wq_ctrl);
 void mlx5_wq_cyc_wqe_dump(struct mlx5_wq_cyc *wq, u16 ix, u8 nstrides);
+void mlx5_wq_cyc_reset(struct mlx5_wq_cyc *wq);
 
 int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *qpc, struct mlx5_wq_qp *wq,
···
 int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *wqc, struct mlx5_wq_ll *wq,
 		      struct mlx5_wq_ctrl *wq_ctrl);
+void mlx5_wq_ll_reset(struct mlx5_wq_ll *wq);
 
 void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl);
 

drivers/net/ethernet/micrel/ks8851_mll.c

···
  */
 
 /**
- * ks_rdreg8 - read 8 bit register from device
- * @ks	  : The chip information
- * @offset: The register address
- *
- * Read a 8bit register from the chip, returning the result
- */
-static u8 ks_rdreg8(struct ks_net *ks, int offset)
-{
-	u16 data;
-	u8 shift_bit = offset & 0x03;
-	u8 shift_data = (offset & 1) << 3;
-	ks->cmd_reg_cache = (u16) offset | (u16)(BE0 << shift_bit);
-	iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd);
-	data  = ioread16(ks->hw_addr);
-	return (u8)(data >> shift_data);
-}
-
-/**
  * ks_rdreg16 - read 16 bit register from device
  * @ks	  : The chip information
  * @offset: The register address
···
 
 static u16 ks_rdreg16(struct ks_net *ks, int offset)
 {
-	ks->cmd_reg_cache = (u16)offset | ((BE1 | BE0) << (offset & 0x02));
+	ks->cmd_reg_cache = (u16)offset | ((BE3 | BE2) >> (offset & 0x02));
 	iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd);
 	return ioread16(ks->hw_addr);
-}
-
-/**
- * ks_wrreg8 - write 8bit register value to chip
- * @ks: The chip information
- * @offset: The register address
- * @value: The value to write
- *
- */
-static void ks_wrreg8(struct ks_net *ks, int offset, u8 value)
-{
-	u8  shift_bit = (offset & 0x03);
-	u16 value_write = (u16)(value << ((offset & 1) << 3));
-	ks->cmd_reg_cache = (u16)offset | (BE0 << shift_bit);
-	iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd);
-	iowrite16(value_write, ks->hw_addr);
 }
 
 /**
···
 
 static void ks_wrreg16(struct ks_net *ks, int offset, u16 value)
 {
-	ks->cmd_reg_cache = (u16)offset | ((BE1 | BE0) << (offset & 0x02));
+	ks->cmd_reg_cache = (u16)offset | ((BE3 | BE2) >> (offset & 0x02));
 	iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd);
 	iowrite16(value, ks->hw_addr);
 }
···
 {
 	len >>= 1;
 	while (len--)
-		*wptr++ = (u16)ioread16(ks->hw_addr);
+		*wptr++ = be16_to_cpu(ioread16(ks->hw_addr));
 }
 
 /**
···
 {
 	len >>= 1;
 	while (len--)
-		iowrite16(*wptr++, ks->hw_addr);
+		iowrite16(cpu_to_be16(*wptr++), ks->hw_addr);
 }
 
 static void ks_disable_int(struct ks_net *ks)
···
 	u16 reg_data = 0;
 
 	/* Regardless of bus width, 8 bit read should always work.*/
-	reg_data = ks_rdreg8(ks, KS_CCR) & 0x00FF;
-	reg_data |= ks_rdreg8(ks, KS_CCR+1) << 8;
+	reg_data = ks_rdreg16(ks, KS_CCR);
 
 	/* addr/data bus are multiplexed */
 	ks->sharedbus = (reg_data & CCR_SHARED) == CCR_SHARED;
···
 
 	/* 1. set sudo DMA mode */
 	ks_wrreg16(ks, KS_RXFDPR, RXFDPR_RXFPAI);
-	ks_wrreg8(ks, KS_RXQCR, (ks->rc_rxqcr | RXQCR_SDA) & 0xff);
+	ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA);
 
 	/* 2. read prepend data */
 	/**
···
 	ks_inblk(ks, buf, ALIGN(len, 4));
 
 	/* 4. reset sudo DMA Mode */
-	ks_wrreg8(ks, KS_RXQCR, ks->rc_rxqcr);
+	ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr);
 }
 
 /**
···
 	ks->txh.txw[1] = cpu_to_le16(len);
 
 	/* 1. set sudo-DMA mode */
-	ks_wrreg8(ks, KS_RXQCR, (ks->rc_rxqcr | RXQCR_SDA) & 0xff);
+	ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA);
 	/* 2. write status/lenth info */
 	ks_outblk(ks, ks->txh.txw, 4);
 	/* 3. write pkt data */
 	ks_outblk(ks, (u16 *)pdata, ALIGN(len, 4));
 	/* 4. reset sudo-DMA mode */
-	ks_wrreg8(ks, KS_RXQCR, ks->rc_rxqcr);
+	ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr);
 	/* 5. Enqueue Tx(move the pkt from TX buffer into TXQ) */
 	ks_wrreg16(ks, KS_TXQCR, TXQCR_METFE);
 	/* 6. wait until TXQCR_METFE is auto-cleared */

drivers/net/ethernet/mscc/ocelot_board.c

···
 		if (err != 4)
 			break;
 
+		/* At this point the IFH was read correctly, so it is safe to
+		 * presume that there is no error. The err needs to be reset
+		 * otherwise a frame could come in CPU queue between the while
+		 * condition and the check for error later on. And in that case
+		 * the new frame is just removed and not processed.
+		 */
+		err = 0;
+
 		ocelot_parse_ifh(ifh, &info);
 
 		ocelot_port = ocelot->ports[info.port];

drivers/net/ethernet/pensando/ionic/ionic_dev.c

···
 {
 	struct ionic_dev *idev = &ionic->idev;
 	unsigned long hb_time;
-	u32 fw_status;
+	u8 fw_status;
 	u32 hb;
 
 	/* wait a little more than one second before testing again */
···
 	if (time_before(hb_time, (idev->last_hb_time + ionic->watchdog_period)))
 		return 0;
 
-	/* firmware is useful only if fw_status is non-zero */
-	fw_status = ioread32(&idev->dev_info_regs->fw_status);
-	if (!fw_status)
+	/* firmware is useful only if the running bit is set and
+	 * fw_status != 0xff (bad PCI read)
+	 */
+	fw_status = ioread8(&idev->dev_info_regs->fw_status);
+	if (fw_status == 0xff ||
+	    !(fw_status & IONIC_FW_STS_F_RUNNING))
 		return -ENXIO;
 
 	/* early FW has no heartbeat, else FW will return non-zero */

drivers/net/ethernet/pensando/ionic/ionic_if.h

···
 		u8     version;
 		u8     asic_type;
 		u8     asic_rev;
+#define IONIC_FW_STS_F_RUNNING	0x1
 		u8     fw_status;
 		u32    fw_heartbeat;
 		char   fw_version[IONIC_DEVINFO_FWVERS_BUFLEN];

drivers/net/ethernet/qlogic/qede/qede.h

···
 	struct list_head entry;
 	struct list_head rdma_event_list;
 	struct workqueue_struct *rdma_wq;
+	struct kref refcnt;
+	struct completion event_comp;
 	bool exp_recovery;
 };
 

drivers/net/ethernet/qlogic/qede/qede_rdma.c

···
 static int qede_rdma_create_wq(struct qede_dev *edev)
 {
 	INIT_LIST_HEAD(&edev->rdma_info.rdma_event_list);
+	kref_init(&edev->rdma_info.refcnt);
+	init_completion(&edev->rdma_info.event_comp);
+
 	edev->rdma_info.rdma_wq = create_singlethread_workqueue("rdma_wq");
 	if (!edev->rdma_info.rdma_wq) {
 		DP_NOTICE(edev, "qedr: Could not create workqueue\n");
···
 	}
 }
 
+static void qede_rdma_complete_event(struct kref *ref)
+{
+	struct qede_rdma_dev *rdma_dev =
+		container_of(ref, struct qede_rdma_dev, refcnt);
+
+	/* no more events will be added after this */
+	complete(&rdma_dev->event_comp);
+}
+
 static void qede_rdma_destroy_wq(struct qede_dev *edev)
 {
+	/* Avoid race with add_event flow, make sure it finishes before
+	 * we start accessing the list and cleaning up the work
+	 */
+	kref_put(&edev->rdma_info.refcnt, qede_rdma_complete_event);
+	wait_for_completion(&edev->rdma_info.event_comp);
+
 	qede_rdma_cleanup_event(edev);
 	destroy_workqueue(edev->rdma_info.rdma_wq);
 }
···
 	if (!edev->rdma_info.qedr_dev)
 		return;
 
+	/* We don't want the cleanup flow to start while we're allocating and
+	 * scheduling the work
+	 */
+	if (!kref_get_unless_zero(&edev->rdma_info.refcnt))
+		return; /* already being destroyed */
+
 	event_node = qede_rdma_get_free_event_node(edev);
 	if (!event_node)
-		return;
+		goto out;
 
 	event_node->event = event;
 	event_node->ptr = edev;
 
 	INIT_WORK(&event_node->work, qede_rdma_handle_event);
 	queue_work(edev->rdma_info.rdma_wq, &event_node->work);
+
+out:
+	kref_put(&edev->rdma_info.refcnt, qede_rdma_complete_event);
 }
 
 void qede_rdma_dev_event_open(struct qede_dev *edev)

drivers/net/phy/broadcom.c

···
 	struct device_node *np = phydev->mdio.dev.of_node;
 	int ret;
 
-	/* Aneg firsly. */
+	/* Aneg firstly. */
 	ret = genphy_config_aneg(phydev);
 
 	/* Then we can set up the delay. */
···
 {
 	int ret;
 
-	/* Aneg firsly. */
+	/* Aneg firstly. */
 	if (phydev->dev_flags & PHY_BCM_FLAGS_MODE_1000BX)
 		ret = genphy_c37_config_aneg(phydev);
 	else

drivers/net/phy/mdio-bcm-iproc.c

···
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+int iproc_mdio_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct iproc_mdio_priv *priv = platform_get_drvdata(pdev);
+
+	/* restore the mii clock configuration */
+	iproc_mdio_config_clk(priv->base);
+
+	return 0;
+}
+
+static const struct dev_pm_ops iproc_mdio_pm_ops = {
+	.resume = iproc_mdio_resume
+};
+#endif /* CONFIG_PM_SLEEP */
+
 static const struct of_device_id iproc_mdio_of_match[] = {
 	{ .compatible = "brcm,iproc-mdio", },
 	{ /* sentinel */ },
···
 	.driver = {
 		.name = "iproc-mdio",
 		.of_match_table = iproc_mdio_of_match,
+#ifdef CONFIG_PM_SLEEP
+		.pm = &iproc_mdio_pm_ops,
+#endif
 	},
 	.probe = iproc_mdio_probe,
 	.remove = iproc_mdio_remove,

drivers/net/wireguard/device.c

···
 	enum { WG_NETDEV_FEATURES = NETIF_F_HW_CSUM | NETIF_F_RXCSUM |
 				    NETIF_F_SG | NETIF_F_GSO |
 				    NETIF_F_GSO_SOFTWARE | NETIF_F_HIGHDMA };
+	const int overhead = MESSAGE_MINIMUM_LENGTH + sizeof(struct udphdr) +
+			     max(sizeof(struct ipv6hdr), sizeof(struct iphdr));
 
 	dev->netdev_ops = &netdev_ops;
 	dev->hard_header_len = 0;
···
 	dev->features |= WG_NETDEV_FEATURES;
 	dev->hw_features |= WG_NETDEV_FEATURES;
 	dev->hw_enc_features |= WG_NETDEV_FEATURES;
-	dev->mtu = ETH_DATA_LEN - MESSAGE_MINIMUM_LENGTH -
-		   sizeof(struct udphdr) -
-		   max(sizeof(struct ipv6hdr), sizeof(struct iphdr));
+	dev->mtu = ETH_DATA_LEN - overhead;
+	dev->max_mtu = round_down(INT_MAX, MESSAGE_PADDING_MULTIPLE) - overhead;
 
 	SET_NETDEV_DEVTYPE(dev, &device_type);
 

drivers/net/wireguard/receive.c

···
 
 	under_load = skb_queue_len(&wg->incoming_handshakes) >=
 		     MAX_QUEUED_INCOMING_HANDSHAKES / 8;
-	if (under_load)
+	if (under_load) {
 		last_under_load = ktime_get_coarse_boottime_ns();
-	else if (last_under_load)
+	} else if (last_under_load) {
 		under_load = !wg_birthdate_has_expired(last_under_load, 1);
+		if (!under_load)
+			last_under_load = 0;
+	}
 	mac_state = wg_cookie_validate_packet(&wg->cookie_checker, skb,
 					      under_load);
 	if ((under_load && mac_state == VALID_MAC_WITH_COOKIE) ||

drivers/net/wireguard/send.c

···
 
 static unsigned int calculate_skb_padding(struct sk_buff *skb)
 {
+	unsigned int padded_size, last_unit = skb->len;
+
+	if (unlikely(!PACKET_CB(skb)->mtu))
+		return ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE) - last_unit;
+
 	/* We do this modulo business with the MTU, just in case the networking
 	 * layer gives us a packet that's bigger than the MTU. In that case, we
 	 * wouldn't want the final subtraction to overflow in the case of the
-	 * padded_size being clamped.
+	 * padded_size being clamped. Fortunately, that's very rarely the case,
+	 * so we optimize for that not happening.
 	 */
-	unsigned int last_unit = skb->len % PACKET_CB(skb)->mtu;
-	unsigned int padded_size = ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE);
+	if (unlikely(last_unit > PACKET_CB(skb)->mtu))
+		last_unit %= PACKET_CB(skb)->mtu;
 
-	if (padded_size > PACKET_CB(skb)->mtu)
-		padded_size = PACKET_CB(skb)->mtu;
+	padded_size = min(PACKET_CB(skb)->mtu,
+			  ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE));
 	return padded_size - last_unit;
 }
 

drivers/net/wireguard/socket.c

···
 		wg->incoming_port = ntohs(inet_sk(new4)->inet_sport);
 	mutex_unlock(&wg->socket_update_lock);
 	synchronize_rcu();
-	synchronize_net();
 	sock_free(old4);
 	sock_free(old6);
 }

drivers/nfc/pn544/i2c.c

···
 
 out:
 	gpiod_set_value_cansleep(phy->gpiod_en, !phy->en_polarity);
+	usleep_range(10000, 15000);
 }
 
 static void pn544_hci_i2c_enable_mode(struct pn544_i2c_phy *phy, int run_mode)

drivers/nfc/pn544/pn544.c

···
 static int pn544_hci_check_presence(struct nfc_hci_dev *hdev,
 				   struct nfc_target *target)
 {
-	pr_debug("supported protocol %d\b", target->supported_protocols);
+	pr_debug("supported protocol %d\n", target->supported_protocols);
 	if (target->supported_protocols & (NFC_PROTO_ISO14443_MASK |
 					NFC_PROTO_ISO14443_B_MASK)) {
 		return nfc_hci_send_cmd(hdev, target->hci_reader_gate,

drivers/s390/net/qeth_core_main.c

···
 	}
 
 	use_rx_sg = (card->options.cq == QETH_CQ_ENABLED) ||
-		    ((skb_len >= card->options.rx_sg_cb) &&
+		    (skb_len > card->options.rx_sg_cb &&
 		     !atomic_read(&card->force_alloc_skb) &&
 		     !IS_OSN(card));
 
···
 {
 	int work_done = 0;
 
-	WARN_ON_ONCE(!budget);
 	*done = false;
 
 	while (budget) {

drivers/s390/net/qeth_l2_main.c

···
 
 	QETH_CARD_TEXT(card, 2, "vniccsch");
 
-	/* do not change anything if BridgePort is enabled */
-	if (qeth_bridgeport_is_in_use(card))
-		return -EBUSY;
-
 	/* check if characteristic and enable/disable are supported */
 	if (!(card->options.vnicc.sup_chars & vnicc) ||
 	    !(card->options.vnicc.set_char_sup & vnicc))
 		return -EOPNOTSUPP;
+
+	if (qeth_bridgeport_is_in_use(card))
+		return -EBUSY;
 
 	/* set enable/disable command and store wanted characteristic */
 	if (state) {
···
 
 	QETH_CARD_TEXT(card, 2, "vniccgch");
 
-	/* do not get anything if BridgePort is enabled */
-	if (qeth_bridgeport_is_in_use(card))
-		return -EBUSY;
-
 	/* check if characteristic is supported */
 	if (!(card->options.vnicc.sup_chars & vnicc))
 		return -EOPNOTSUPP;
+
+	if (qeth_bridgeport_is_in_use(card))
+		return -EBUSY;
 
 	/* if card is ready, query current VNICC state */
 	if (qeth_card_hw_is_reachable(card))
···
 
 	QETH_CARD_TEXT(card, 2, "vniccsto");
 
-	/* do not change anything if BridgePort is enabled */
-	if (qeth_bridgeport_is_in_use(card))
-		return -EBUSY;
-
 	/* check if characteristic and set_timeout are supported */
 	if (!(card->options.vnicc.sup_chars & QETH_VNICC_LEARNING) ||
 	    !(card->options.vnicc.getset_timeout_sup & QETH_VNICC_LEARNING))
 		return -EOPNOTSUPP;
+
+	if (qeth_bridgeport_is_in_use(card))
+		return -EBUSY;
 
 	/* do we need to do anything? */
 	if (card->options.vnicc.learning_timeout == timeout)
···
 
 	QETH_CARD_TEXT(card, 2, "vniccgto");
 
-	/* do not get anything if BridgePort is enabled */
-	if (qeth_bridgeport_is_in_use(card))
-		return -EBUSY;
-
 	/* check if characteristic and get_timeout are supported */
 	if (!(card->options.vnicc.sup_chars & QETH_VNICC_LEARNING) ||
 	    !(card->options.vnicc.getset_timeout_sup & QETH_VNICC_LEARNING))
 		return -EOPNOTSUPP;
+
+	if (qeth_bridgeport_is_in_use(card))
+		return -EBUSY;
+
 	/* if card is ready, get timeout. Otherwise, just return stored value */
 	*timeout = card->options.vnicc.learning_timeout;
 	if (qeth_card_hw_is_reachable(card))

include/linux/mlx5/mlx5_ifc.h

···
 	u8         nic_rx_multi_path_tirs[0x1];
 	u8         nic_rx_multi_path_tirs_fts[0x1];
 	u8         allow_sniffer_and_nic_rx_shared_tir[0x1];
-	u8	   reserved_at_3[0x1d];
+	u8	   reserved_at_3[0x4];
+	u8	   sw_owner_reformat_supported[0x1];
+	u8	   reserved_at_8[0x18];
+
 	u8	   encap_general_header[0x1];
 	u8	   reserved_at_21[0xa];
 	u8	   log_max_packet_reformat_context[0x5];

include/linux/netdevice.h

···
 #define NET_RX_SUCCESS		0	/* keep 'em coming, baby */
 #define NET_RX_DROP		1	/* packet dropped */
 
+#define MAX_NEST_DEV 8
+
 /*
  * Transmit return codes: transmit return codes originate from three different
  * namespaces:
···
 	     ldev; \
 	     ldev = netdev_lower_get_next(dev, &(iter)))
 
-struct net_device *netdev_all_lower_get_next(struct net_device *dev,
+struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
 					     struct list_head **iter);
-struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
-						 struct list_head **iter);
-
 int netdev_walk_all_lower_dev(struct net_device *dev,
 			      int (*fn)(struct net_device *lower_dev,
 					void *data),

include/linux/rculist_nulls.h

···
 	}
 }
 
+/* after that hlist_nulls_del will work */
+static inline void hlist_nulls_add_fake(struct hlist_nulls_node *n)
+{
+	n->pprev = &n->next;
+	n->next = (struct hlist_nulls_node *)NULLS_MARKER(NULL);
+}
+
 /**
  * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type
  * @tpos:	the type * to use as a loop cursor.

include/linux/skbuff.h

···
  *	@next: Next buffer in list
  *	@prev: Previous buffer in list
  *	@tstamp: Time we arrived/left
+ *	@skb_mstamp_ns: (aka @tstamp) earliest departure time; start point
+ *		for retransmit timer
  *	@rbnode: RB tree node, alternative to next/prev for netem/tcp
+ *	@list: queue head
  *	@sk: Socket we are owned by
+ *	@ip_defrag_offset: (aka @sk) alternate use of @sk, used in
+ *		fragmentation management
  *	@dev: Device we arrived on/are leaving by
+ *	@dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL
  *	@cb: Control buffer. Free for use by every layer. Put private vars here
  *	@_skb_refdst: destination entry (with norefcount bit)
  *	@sp: the security path, used for xfrm
···
  *	@pkt_type: Packet class
  *	@fclone: skbuff clone status
  *	@ipvs_property: skbuff is owned by ipvs
+ *	@inner_protocol_type: whether the inner protocol is
+ *		ENCAP_TYPE_ETHER or ENCAP_TYPE_IPPROTO
+ *	@remcsum_offload: remote checksum offload is enabled
  *	@offload_fwd_mark: Packet was L2-forwarded in hardware
  *	@offload_l3_fwd_mark: Packet was L3-forwarded in hardware
  *	@tc_skip_classify: do not classify packet. set by IFB device
···
  *	@tc_index: Traffic control index
  *	@hash: the packet hash
  *	@queue_mapping: Queue mapping for multiqueue devices
+ *	@head_frag: skb was allocated from page fragments,
+ *		not allocated by kmalloc() or vmalloc().
  *	@pfmemalloc: skbuff was allocated from PFMEMALLOC reserves
  *	@active_extensions: active extensions (skb_ext_id types)
  *	@ndisc_nodetype: router type (from link layer)
···
  *	@wifi_acked_valid: wifi_acked was set
  *	@wifi_acked: whether frame was acked on wifi or not
  *	@no_fcs:  Request NIC to treat last 4 bytes as Ethernet FCS
+ *	@encapsulation: indicates the inner headers in the skbuff are valid
+ *	@encap_hdr_csum: software checksum is needed
+ *	@csum_valid: checksum is already valid
  *	@csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL
+ *	@csum_complete_sw: checksum was completed by software
+ *	@csum_level: indicates the number of consecutive checksums found in
+ *		the packet minus one that have been verified as
+ *		CHECKSUM_UNNECESSARY (max 3)
  *	@dst_pending_confirm: need to confirm neighbour
  *	@decrypted: Decrypted SKB
  *	@napi_id: id of the NAPI struct this skb came from
+ *	@sender_cpu: (aka @napi_id) source CPU in XPS
  *	@secmark: security marking
  *	@mark: Generic packet mark
+ *	@reserved_tailroom: (aka @mark) number of bytes of free space available
+ *		at the tail of an sk_buff
+ *	@vlan_present: VLAN tag is present
  *	@vlan_proto: vlan encapsulation protocol
  *	@vlan_tci: vlan tag control information
  *	@inner_protocol: Protocol (encapsulation)
+ *	@inner_ipproto: (aka @inner_protocol) stores ipproto when
+ *		skb->inner_protocol_type == ENCAP_TYPE_IPPROTO;
  *	@inner_transport_header: Inner transport layer header (encapsulation)
  *	@inner_network_header: Network layer header (encapsulation)
  *	@inner_mac_header: Link layer header (encapsulation)
···
 #endif
 #define CLONED_OFFSET()		offsetof(struct sk_buff, __cloned_offset)
 
+	/* private: */
 	__u8			__cloned_offset[0];
+	/* public: */
 	__u8			cloned:1,
 				nohdr:1,
 				fclone:2,
···
 #endif
 #define PKT_TYPE_OFFSET()	offsetof(struct sk_buff, __pkt_type_offset)
 
+	/* private: */
 	__u8			__pkt_type_offset[0];
+	/* public: */
 	__u8			pkt_type:3;
 	__u8			ignore_df:1;
 	__u8			nf_trace:1;
···
 #define PKT_VLAN_PRESENT_BIT	0
 #endif
 #define PKT_VLAN_PRESENT_OFFSET()	offsetof(struct sk_buff, __pkt_vlan_present_offset)
+	/* private: */
 	__u8			__pkt_vlan_present_offset[0];
+	/* public: */
 	__u8			vlan_present:1;
 	__u8			csum_complete_sw:1;
 	__u8			csum_level:2;

include/net/flow_dissector.h

···
 #include <linux/types.h>
 #include <linux/in6.h>
 #include <linux/siphash.h>
+#include <linux/string.h>
 #include <uapi/linux/if_ether.h>
 
 struct sk_buff;
···
 	void			*data;
 	void			*data_end;
 };
+
+static inline void
+flow_dissector_init_keys(struct flow_dissector_key_control *key_control,
+			 struct flow_dissector_key_basic *key_basic)
+{
+	memset(key_control, 0, sizeof(*key_control));
+	memset(key_basic, 0, sizeof(*key_basic));
+}
 
 #endif

include/net/sock.h

···
  *	struct sock_common - minimal network layer representation of sockets
  *	@skc_daddr: Foreign IPv4 addr
  *	@skc_rcv_saddr: Bound local IPv4 addr
+ *	@skc_addrpair: 8-byte-aligned __u64 union of @skc_daddr & @skc_rcv_saddr
  *	@skc_hash: hash value used with various protocol lookup tables
  *	@skc_u16hashes: two u16 hash values used by UDP lookup tables
  *	@skc_dport: placeholder for inet_dport/tw_dport
  *	@skc_num: placeholder for inet_num/tw_num
+ *	@skc_portpair: __u32 union of @skc_dport & @skc_num
  *	@skc_family: network address family
  *	@skc_state: Connection state
  *	@skc_reuse: %SO_REUSEADDR setting
  *	@skc_reuseport: %SO_REUSEPORT setting
+ *	@skc_ipv6only: socket is IPV6 only
+ *	@skc_net_refcnt: socket is using net ref counting
  *	@skc_bound_dev_if: bound device index if != 0
  *	@skc_bind_node: bind hash linkage for various protocol lookup tables
  *	@skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol
  *	@skc_prot: protocol handlers inside a network family
  *	@skc_net: reference to the network namespace of this socket
+ *	@skc_v6_daddr: IPV6 destination address
+ *	@skc_v6_rcv_saddr: IPV6 source address
+ *	@skc_cookie: socket's cookie value
  *	@skc_node: main hash linkage for various protocol lookup tables
  *	@skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol
  *	@skc_tx_queue_mapping: tx queue number for this connection
···
  *	@skc_flags: place holder for sk_flags
  *		%SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
  *		%SO_OOBINLINE settings, %SO_TIMESTAMPING settings
+ *	@skc_listener: connection request listener socket (aka rsk_listener)
+ *		[union with @skc_flags]
+ *	@skc_tw_dr: (aka tw_dr) ptr to &struct inet_timewait_death_row
+ *		[union with @skc_flags]
  *	@skc_incoming_cpu: record/match cpu processing incoming packets
+ *	@skc_rcv_wnd: (aka rsk_rcv_wnd) TCP receive window size (possibly scaled)
+ *		[union with @skc_incoming_cpu]
+ *	@skc_tw_rcv_nxt: (aka tw_rcv_nxt) TCP window next expected seq number
+ *		[union with @skc_incoming_cpu]
  *	@skc_refcnt: reference count
  *
  *	This is the minimal network layer representation of sockets, the header
···
   *	@sk_dst_cache: destination cache
   *	@sk_dst_pending_confirm: need to confirm neighbour
   *	@sk_policy: flow policy
+  *	@sk_rx_skb_cache: cache copy of recently accessed RX skb
   *	@sk_receive_queue: incoming packets
   *	@sk_wmem_alloc: transmit queue bytes committed
   *	@sk_tsq_flags: TCP Small Queues flags
···
   *	@sk_no_check_rx: allow zero checksum in RX packets
   *	@sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
   *	@sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK)
+  *	@sk_route_forced_caps: static, forced route capabilities
+  *		(set in tcp_init_sock())
   *	@sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
   *	@sk_gso_max_size: Maximum GSO segment size to build
   *	@sk_gso_max_segs: Maximum number of GSO segments
···
   *	@sk_frag: cached page frag
   *	@sk_peek_off: current peek_offset value
   *	@sk_send_head: front of stuff to transmit
+  *	@tcp_rtx_queue: TCP re-transmit queue [union with @sk_send_head]
+  *	@sk_tx_skb_cache: cache copy of recently accessed TX skb
   *	@sk_security: used by security modules
   *	@sk_mark: generic packet mark
   *	@sk_cgrp_data: cgroup data for this cgroup
···
   *	@sk_write_space: callback to indicate there is bf sending space available
   *	@sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE)
   *	@sk_backlog_rcv: callback to process the backlog
+  *	@sk_validate_xmit_skb: ptr to an optional validate function
   *	@sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
   *	@sk_reuseport_cb: reuseport group container
+  *	@sk_bpf_storage: ptr to cache and control for bpf_sk_storage
   *	@sk_rcu: used during RCU grace period
   *	@sk_clockid: clockid used by time-based scheduling (SO_TXTIME)
   *	@sk_txtime_deadline_mode: set deadline mode for SO_TXTIME
+  *	@sk_txtime_report_errors: set report errors mode for SO_TXTIME
   *	@sk_txtime_unused: unused txtime flags
   */
 struct sock {
···
 	struct sk_filter __rcu	*sk_filter;
 	union {
 		struct socket_wq __rcu	*sk_wq;
+		/* private: */
 		struct socket_wq	*sk_wq_raw;
+		/* public: */
 	};
 #ifdef CONFIG_XFRM
 	struct xfrm_policy __rcu *sk_policy[2];
···
  * sk_wmem_alloc_get - returns write allocations
  * @sk: socket
  *
- * Returns sk_wmem_alloc minus initial offset of one
+ * Return: sk_wmem_alloc minus initial offset of one
  */
 static inline int sk_wmem_alloc_get(const struct sock *sk)
 {
···
  * sk_rmem_alloc_get - returns read allocations
  * @sk: socket
  *
- * Returns sk_rmem_alloc
+ * Return: sk_rmem_alloc
  */
 static inline int sk_rmem_alloc_get(const struct sock *sk)
 {
···
  * sk_has_allocations - check if allocations are outstanding
  * @sk: socket
  *
- * Returns true if socket has write or read allocations
+ * Return: true if socket has write or read allocations
  */
 static inline bool sk_has_allocations(const struct sock *sk)
 {
···
  * skwq_has_sleeper - check if there are any waiting processes
  * @wq: struct socket_wq
  *
- * Returns true if socket_wq has waiting processes
+ * Return: true if socket_wq has waiting processes
  *
  * The purpose of the skwq_has_sleeper and sock_poll_wait is to wrap the memory
  * barrier call. They were added due to the race found within the tcp code.
···
  * gfpflags_allow_blocking() isn't enough here as direct reclaim may nest
  * inside other socket operations and end up recursing into sk_page_frag()
  * while it's already in use.
+ *
+ * Return: a per task page_frag if context allows that,
+ * otherwise a per socket one.
  */
 static inline struct page_frag *sk_page_frag(struct sock *sk)
 {
···
 			   &skb_shinfo(skb)->tskey);
 }
 
+DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key);
 /**
  * sk_eat_skb - Release a skb if it is no longer needed
  * @sk: socket to eat this skb from
···
  * This routine must be called with interrupts disabled or with the socket
  * locked so that the sk_buff queue operation is ok.
 */
-DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key);
 static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb)
 {
 	__skb_unlink(skb, &sk->sk_receive_queue);

include/uapi/linux/bpf.h

···
  * 		supports redirection to the egress interface, and accepts no
  * 		flag at all.
  *
- * 		The same effect can be attained with the more generic
- * 		**bpf_redirect_map**\ (), which requires specific maps to be
- * 		used but offers better performance.
+ * 		The same effect can also be attained with the more generic
+ * 		**bpf_redirect_map**\ (), which uses a BPF map to store the
+ * 		redirect target instead of providing it directly to the helper.
  * 	Return
  * 		For XDP, the helper returns **XDP_REDIRECT** on success or
  * 		**XDP_ABORTED** on error. For other program types, the values
···
  * 		the caller. Any higher bits in the *flags* argument must be
  * 		unset.
  *
- * 		When used to redirect packets to net devices, this helper
- * 		provides a high performance increase over **bpf_redirect**\ ().
- * 		This is due to various implementation details of the underlying
- * 		mechanisms, one of which is the fact that **bpf_redirect_map**\
- * 		() tries to send packet as a "bulk" to the device.
+ * 		See also bpf_redirect(), which only supports redirecting to an
+ * 		ifindex, but doesn't require a map to do so.
  * 	Return
- * 		**XDP_REDIRECT** on success, or **XDP_ABORTED** on error.
+ * 		**XDP_REDIRECT** on success, or the value of the two lower bits
+ * 		of the **flags* argument on error.
  *
  * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags)
  * 	Description

include/uapi/linux/netfilter/nf_conntrack_common.h

···
 	IPS_UNTRACKED_BIT = 12,
 	IPS_UNTRACKED = (1 << IPS_UNTRACKED_BIT),
 
+#ifdef __KERNEL__
+	/* Re-purposed for in-kernel use:
+	 * Tags a conntrack entry that clashed with an existing entry
+	 * on insert.
+	 */
+	IPS_NAT_CLASH_BIT = IPS_UNTRACKED_BIT,
+	IPS_NAT_CLASH = IPS_UNTRACKED,
+#endif
+
 	/* Conntrack got a helper explicitly attached via CT target. */
 	IPS_HELPER_BIT = 13,
 	IPS_HELPER = (1 << IPS_HELPER_BIT),
···
 	 */
 	IPS_UNCHANGEABLE_MASK = (IPS_NAT_DONE_MASK | IPS_NAT_MASK |
 				 IPS_EXPECTED | IPS_CONFIRMED | IPS_DYING |
-				 IPS_SEQ_ADJUST | IPS_TEMPLATE | IPS_OFFLOAD),
+				 IPS_SEQ_ADJUST | IPS_TEMPLATE | IPS_UNTRACKED |
+				 IPS_OFFLOAD),
 
 	__IPS_MAX_BIT = 15,
 };

kernel/bpf/btf.c

···
  * EFAULT - verifier bug
  * 0 - 99% match. The last 1% is validated by the verifier.
  */
-int btf_check_func_type_match(struct bpf_verifier_log *log,
-			      struct btf *btf1, const struct btf_type *t1,
-			      struct btf *btf2, const struct btf_type *t2)
+static int btf_check_func_type_match(struct bpf_verifier_log *log,
+				     struct btf *btf1, const struct btf_type *t1,
+				     struct btf *btf2, const struct btf_type *t2)
 {
 	const struct btf_param *args1, *args2;
 	const char *fn1, *fn2, *s1, *s2;

kernel/bpf/hashtab.c

···
 			union {
 				struct bpf_htab *htab;
 				struct pcpu_freelist_node fnode;
+				struct htab_elem *batch_flink;
 			};
 		};
 	};
···
 	bpf_map_area_free(htab->elems);
 }
 
+/* The LRU list has a lock (lru_lock). Each htab bucket has a lock
+ * (bucket_lock). If both locks need to be acquired together, the lock
+ * order is always lru_lock -> bucket_lock and this only happens in
+ * bpf_lru_list.c logic. For example, certain code path of
+ * bpf_lru_pop_free(), which is called by function prealloc_lru_pop(),
+ * will acquire lru_lock first followed by acquiring bucket_lock.
+ *
+ * In hashtab.c, to avoid deadlock, lock acquisition of
+ * bucket_lock followed by lru_lock is not allowed. In such cases,
+ * bucket_lock needs to be released first before acquiring lru_lock.
+ */
 static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key,
 					  u32 hash)
 {
···
 	void __user *ukeys = u64_to_user_ptr(attr->batch.keys);
 	void *ubatch = u64_to_user_ptr(attr->batch.in_batch);
 	u32 batch, max_count, size, bucket_size;
+	struct htab_elem *node_to_free = NULL;
 	u64 elem_map_flags, map_flags;
 	struct hlist_nulls_head *head;
 	struct hlist_nulls_node *n;
-	unsigned long flags;
+	unsigned long flags = 0;
+	bool locked = false;
 	struct htab_elem *l;
 	struct bucket *b;
 	int ret = 0;
···
 	dst_val = values;
 	b = &htab->buckets[batch];
 	head = &b->head;
-	raw_spin_lock_irqsave(&b->lock, flags);
+	/* do not grab the lock unless need it (bucket_cnt > 0). */
+	if (locked)
+		raw_spin_lock_irqsave(&b->lock, flags);
 
 	bucket_cnt = 0;
 	hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
 		bucket_cnt++;
 
+	if (bucket_cnt && !locked) {
+		locked = true;
+		goto again_nocopy;
+	}
+
 	if (bucket_cnt > (max_count - total)) {
 		if (total == 0)
 			ret = -ENOSPC;
+		/* Note that since bucket_cnt > 0 here, it is implicit
+		 * that the locked was grabbed, so release it.
+		 */
 		raw_spin_unlock_irqrestore(&b->lock, flags);
 		rcu_read_unlock();
 		this_cpu_dec(bpf_prog_active);
···
 
 	if (bucket_cnt > bucket_size) {
 		bucket_size = bucket_cnt;
+		/* Note that since bucket_cnt > 0 here, it is implicit
+		 * that the locked was grabbed, so release it.
+		 */
 		raw_spin_unlock_irqrestore(&b->lock, flags);
 		rcu_read_unlock();
 		this_cpu_dec(bpf_prog_active);
···
 		kvfree(values);
 		goto alloc;
 	}
+
+	/* Next block is only safe to run if you have grabbed the lock */
+	if (!locked)
+		goto next_batch;
 
 	hlist_nulls_for_each_entry_safe(l, n, head, hash_node) {
 		memcpy(dst_key, l->key, key_size);
···
 		}
 		if (do_delete) {
 			hlist_nulls_del_rcu(&l->hash_node);
-			if (is_lru_map)
-				bpf_lru_push_free(&htab->lru, &l->lru_node);
-			else
+
+			/* bpf_lru_push_free() will acquire lru_lock, which
+			 * may cause deadlock. See comments in function
+			 * prealloc_lru_pop(). Let us do bpf_lru_push_free()
+			 * after releasing the bucket lock.
+			 */
+			if (is_lru_map) {
+				l->batch_flink = node_to_free;
+				node_to_free = l;
+			} else {
 				free_htab_elem(htab, l);
+			}
 		}
 		dst_key += key_size;
 		dst_val += value_size;
 	}
 
 	raw_spin_unlock_irqrestore(&b->lock, flags);
+	locked = false;
+
+	while (node_to_free) {
+		l = node_to_free;
+		node_to_free = node_to_free->batch_flink;
+		bpf_lru_push_free(&htab->lru, &l->lru_node);
+	}
+
+next_batch:
 	/* If we are not copying data, we can go to next bucket and avoid
 	 * unlocking the rcu.
 	 */

kernel/bpf/offload.c

···
 
 	ulen = info->jited_prog_len;
 	info->jited_prog_len = aux->offload->jited_len;
-	if (info->jited_prog_len & ulen) {
+	if (info->jited_prog_len && ulen) {
 		uinsns = u64_to_user_ptr(info->jited_prog_insns);
 		ulen = min_t(u32, info->jited_prog_len, ulen);
 		if (copy_to_user(uinsns, aux->offload->jited_image, ulen)) {

net/Kconfig

···
 	depends on NETFILTER_ADVANCED
 	select NETFILTER_FAMILY_BRIDGE
 	select SKB_EXTENSIONS
-	default m
 	---help---
 	  Enabling this option will let arptables resp. iptables see bridged
 	  ARP resp. IP traffic. If you want a bridging firewall, you probably

net/bridge/br_stp.c

···
 {
 	struct net_bridge_port *p;
 
-	list_for_each_entry_rcu(p, &br->port_list, list) {
+	list_for_each_entry_rcu(p, &br->port_list, list,
+				lockdep_is_held(&br->lock)) {
 		if (p->port_no == port_no)
 			return p;
 	}

net/core/dev.c

···
 #include "net-sysfs.h"
 
 #define MAX_GRO_SKBS 8
-#define MAX_NEST_DEV 8
 
 /* This should be increased if a protocol with a bigger head is added. */
 #define GRO_MAX_HEAD (MAX_HEADER + 128)
···
 	name_node = netdev_name_node_lookup(net, name);
 	if (!name_node)
 		return -ENOENT;
+	/* lookup might have found our primary name or a name belonging
+	 * to another device.
+	 */
+	if (name_node == dev->name_node || name_node->dev != dev)
+		return -EINVAL;
+
 	__netdev_name_node_alt_destroy(name_node);
 
 	return 0;
···
 	qdisc_calculate_pkt_len(skb, q);
 
 	if (q->flags & TCQ_F_NOLOCK) {
-		if ((q->flags & TCQ_F_CAN_BYPASS) && READ_ONCE(q->empty) &&
-		    qdisc_run_begin(q)) {
-			if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED,
-					      &q->state))) {
-				__qdisc_drop(skb, &to_free);
-				rc = NET_XMIT_DROP;
-				goto end_run;
-			}
-			qdisc_bstats_cpu_update(q, skb);
-
-			rc = NET_XMIT_SUCCESS;
-			if (sch_direct_xmit(skb, q, dev, txq, NULL, true))
-				__qdisc_run(q);
-
-end_run:
-			qdisc_run_end(q);
-		} else {
-			rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
-			qdisc_run(q);
-		}
+		rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
+		qdisc_run(q);
 
 		if (unlikely(to_free))
 			kfree_skb_list(to_free);
···
 	return 0;
 }
 
-static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
-						    struct list_head **iter)
+struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
+					     struct list_head **iter)
 {
 	struct netdev_adjacent *lower;
 
···
 
 	return lower->dev;
 }
+EXPORT_SYMBOL(netdev_next_lower_dev_rcu);
 
 static u8 __netdev_upper_depth(struct net_device *dev)
 {

net/core/fib_rules.c

···
 
 	frh = nlmsg_data(nlh);
 	frh->family = ops->family;
-	frh->table = rule->table;
+	frh->table = rule->table < 256 ? rule->table : RT_TABLE_COMPAT;
 	if (nla_put_u32(skb, FRA_TABLE, rule->table))
 		goto nla_put_failure;
 	if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen))

net/core/rtnetlink.c

···
 	if (err)
 		return err;
 
-	alt_ifname = nla_data(attr);
+	alt_ifname = nla_strdup(attr, GFP_KERNEL);
+	if (!alt_ifname)
+		return -ENOMEM;
+
 	if (cmd == RTM_NEWLINKPROP) {
-		alt_ifname = kstrdup(alt_ifname, GFP_KERNEL);
-		if (!alt_ifname)
-			return -ENOMEM;
 		err = netdev_name_node_alt_create(dev, alt_ifname);
-		if (err) {
-			kfree(alt_ifname);
-			return err;
-		}
+		if (!err)
+			alt_ifname = NULL;
 	} else if (cmd == RTM_DELLINKPROP) {
 		err = netdev_name_node_alt_destroy(dev, alt_ifname);
-		if (err)
-			return err;
 	} else {
-		WARN_ON(1);
-		return 0;
+		WARN_ON_ONCE(1);
+		err = -EINVAL;
 	}
 
-	*changed = true;
-	return 0;
+	kfree(alt_ifname);
+	if (!err)
+		*changed = true;
+	return err;
 }
 
 static int rtnl_linkprop(int cmd, struct sk_buff *skb, struct nlmsghdr *nlh,

net/core/skbuff.c

···
 		return NULL;
 	}
 
-	/* use OR instead of assignment to avoid clearing of bits in mask */
 	if (pfmemalloc)
 		skb->pfmemalloc = 1;
 	skb->head_frag = 1;
···
 		return NULL;
 	}
 
-	/* use OR instead of assignment to avoid clearing of bits in mask */
 	if (nc->page.pfmemalloc)
 		skb->pfmemalloc = 1;
 	skb->head_frag = 1;
···
 				      typeof(IPPROTO_IP) proto,
 				      unsigned int off)
 {
-	switch (proto) {
-		int err;
+	int err;
 
+	switch (proto) {
 	case IPPROTO_TCP:
 		err = skb_maybe_pull_tail(skb, off + sizeof(struct tcphdr),
 					  off + MAX_TCP_HDR_LEN);

net/ethtool/bitset.c

···
 				    "mask only allowed in compact bitset");
 		return -EINVAL;
 	}
+
 	no_mask = tb[ETHTOOL_A_BITSET_NOMASK];
+	if (no_mask)
+		ethnl_bitmap32_clear(bitmap, 0, nbits, mod);
 
 	nla_for_each_nested(bit_attr, tb[ETHTOOL_A_BITSET_BITS], rem) {
 		bool old_val, new_val;

net/hsr/hsr_framereg.c

···
 		new_node->seq_out[i] = seq_out;
 
 	spin_lock_bh(&hsr->list_lock);
-	list_for_each_entry_rcu(node, node_db, mac_list) {
+	list_for_each_entry_rcu(node, node_db, mac_list,
+				lockdep_is_held(&hsr->list_lock)) {
 		if (ether_addr_equal(node->macaddress_A, addr))
 			goto out;
 		if (ether_addr_equal(node->macaddress_B, addr))

net/ipv4/udp.c

···
 	inet->inet_dport = 0;
 	sock_rps_reset_rxhash(sk);
 	sk->sk_bound_dev_if = 0;
-	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
+	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) {
 		inet_reset_saddr(sk);
+		if (sk->sk_prot->rehash &&
+		    (sk->sk_userlocks & SOCK_BINDPORT_LOCK))
+			sk->sk_prot->rehash(sk);
+	}
 
 	if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) {
 		sk->sk_prot->unhash(sk);

net/ipv6/ip6_fib.c

···
 					found++;
 					break;
 				}
-				if (rt_can_ecmp)
-					fallback_ins = fallback_ins ?: ins;
+				fallback_ins = fallback_ins ?: ins;
 				goto next_iter;
 			}
 
···
 	}
 
 	if (fallback_ins && !found) {
-		/* No ECMP-able route found, replace first non-ECMP one */
+		/* No matching route with same ecmp-able-ness found, replace
+		 * first matching route
+		 */
 		ins = fallback_ins;
 		iter = rcu_dereference_protected(*ins,
 				    lockdep_is_held(&rt->fib6_table->tb6_lock));

net/ipv6/ip6_gre.c

···
 		return -ENOENT;
 
 	switch (type) {
-		struct ipv6_tlv_tnl_enc_lim *tel;
-		__u32 teli;
 	case ICMPV6_DEST_UNREACH:
 		net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n",
 				    t->parms.name);
···
 			break;
 		}
 		return 0;
-	case ICMPV6_PARAMPROB:
+	case ICMPV6_PARAMPROB: {
+		struct ipv6_tlv_tnl_enc_lim *tel;
+		__u32 teli;
+
 		teli = 0;
 		if (code == ICMPV6_HDR_FIELD)
 			teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data);
···
 					    t->parms.name);
 		}
 		return 0;
+	}
 	case ICMPV6_PKT_TOOBIG:
 		ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
 		return 0;

net/ipv6/ip6_tunnel.c

···
 	err = 0;
 
 	switch (*type) {
-		struct ipv6_tlv_tnl_enc_lim *tel;
-		__u32 mtu, teli;
 	case ICMPV6_DEST_UNREACH:
 		net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n",
 				    t->parms.name);
···
 			rel_msg = 1;
 		}
 		break;
-	case ICMPV6_PARAMPROB:
+	case ICMPV6_PARAMPROB: {
+		struct ipv6_tlv_tnl_enc_lim *tel;
+		__u32 teli;
+
 		teli = 0;
 		if ((*code) == ICMPV6_HDR_FIELD)
 			teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data);
···
 					    t->parms.name);
 		}
 		break;
-	case ICMPV6_PKT_TOOBIG:
+	}
+	case ICMPV6_PKT_TOOBIG: {
+		__u32 mtu;
+
 		ip6_update_pmtu(skb, net, htonl(*info), 0, 0,
 				sock_net_uid(net, NULL));
 		mtu = *info - offset;
···
 			rel_msg = 1;
 		}
 		break;
+	}
 	case NDISC_REDIRECT:
 		ip6_redirect(skb, net, skb->dev->ifindex, 0,
 			     sock_net_uid(net, NULL));

net/ipv6/route.c

···
 		 */
 		cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL |
 						     NLM_F_REPLACE);
+		cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE;
 		nhn++;
 	}
 

net/mptcp/Kconfig

···
 	depends on INET
 	select SKB_EXTENSIONS
 	select CRYPTO_LIB_SHA256
+	select CRYPTO
 	help
 	  Multipath TCP (MPTCP) connections send and receive data over multiple
 	  subflows in order to utilize multiple network paths. Each subflow

net/mptcp/protocol.c

···
 			    char __user *optval, unsigned int optlen)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
-	int ret = -EOPNOTSUPP;
 	struct socket *ssock;
-	struct sock *ssk;
 
 	pr_debug("msk=%p", msk);
 
 	/* @@ the meaning of setsockopt() when the socket is connected and
-	 * there are multiple subflows is not defined.
+	 * there are multiple subflows is not yet defined. It is up to the
+	 * MPTCP-level socket to configure the subflows until the subflow
+	 * is in TCP fallback, when TCP socket options are passed through
+	 * to the one remaining subflow.
 	 */
 	lock_sock(sk);
-	ssock = __mptcp_socket_create(msk, MPTCP_SAME_STATE);
-	if (IS_ERR(ssock)) {
-		release_sock(sk);
-		return ret;
-	}
+	ssock = __mptcp_tcp_fallback(msk);
+	if (ssock)
+		return tcp_setsockopt(ssock->sk, level, optname, optval,
+				      optlen);
 
-	ssk = ssock->sk;
-	sock_hold(ssk);
 	release_sock(sk);
 
-	ret = tcp_setsockopt(ssk, level, optname, optval, optlen);
-	sock_put(ssk);
-
-	return ret;
+	return -EOPNOTSUPP;
 }
 
 static int mptcp_getsockopt(struct sock *sk, int level, int optname,
 			    char __user *optval, int __user *option)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
-	int ret = -EOPNOTSUPP;
 	struct socket *ssock;
-	struct sock *ssk;
 
 	pr_debug("msk=%p", msk);
 
-	/* @@ the meaning of getsockopt() when the socket is connected and
-	 * there are multiple subflows is not defined.
+	/* @@ the meaning of setsockopt() when the socket is connected and
+	 * there are multiple subflows is not yet defined. It is up to the
+	 * MPTCP-level socket to configure the subflows until the subflow
+	 * is in TCP fallback, when socket options are passed through
+	 * to the one remaining subflow.
 	 */
 	lock_sock(sk);
-	ssock = __mptcp_socket_create(msk, MPTCP_SAME_STATE);
-	if (IS_ERR(ssock)) {
-		release_sock(sk);
-		return ret;
-	}
+	ssock = __mptcp_tcp_fallback(msk);
+	if (ssock)
+		return tcp_getsockopt(ssock->sk, level, optname, optval,
+				      option);
 
-	ssk = ssock->sk;
-	sock_hold(ssk);
 	release_sock(sk);
 
-	ret = tcp_getsockopt(ssk, level, optname, optval, option);
-	sock_put(ssk);
-
-	return ret;
+	return -EOPNOTSUPP;
 }
 
 static int mptcp_get_port(struct sock *sk, unsigned short snum)

net/mptcp/protocol.h

···
 #define MPTCP_DSS_FLAG_MASK	(0x1F)
 
 /* MPTCP socket flags */
-#define MPTCP_DATA_READY	BIT(0)
-#define MPTCP_SEND_SPACE	BIT(1)
+#define MPTCP_DATA_READY	0
+#define MPTCP_SEND_SPACE	1
 
 /* MPTCP connection sock */
 struct mptcp_sock {

net/netfilter/nf_conntrack_core.c

···
 	}
 }
 
-/* Resolve race on insertion if this protocol allows this. */
+static void __nf_conntrack_insert_prepare(struct nf_conn *ct)
+{
+	struct nf_conn_tstamp *tstamp;
+
+	atomic_inc(&ct->ct_general.use);
+	ct->status |= IPS_CONFIRMED;
+
+	/* set conntrack timestamp, if enabled. */
+	tstamp = nf_conn_tstamp_find(ct);
+	if (tstamp)
+		tstamp->start = ktime_get_real_ns();
+}
+
+static int __nf_ct_resolve_clash(struct sk_buff *skb,
+				 struct nf_conntrack_tuple_hash *h)
+{
+	/* This is the conntrack entry already in hashes that won race. */
+	struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *loser_ct;
+
+	loser_ct = nf_ct_get(skb, &ctinfo);
+
+	if (nf_ct_is_dying(ct))
+		return NF_DROP;
+
+	if (!atomic_inc_not_zero(&ct->ct_general.use))
+		return NF_DROP;
+
+	if (((ct->status & IPS_NAT_DONE_MASK) == 0) ||
+	    nf_ct_match(ct, loser_ct)) {
+		struct net *net = nf_ct_net(ct);
+
+		nf_ct_acct_merge(ct, ctinfo, loser_ct);
+		nf_ct_add_to_dying_list(loser_ct);
+		nf_conntrack_put(&loser_ct->ct_general);
+		nf_ct_set(skb, ct, ctinfo);
+
+		NF_CT_STAT_INC(net, insert_failed);
+		return NF_ACCEPT;
+	}
+
+	nf_ct_put(ct);
+	return NF_DROP;
+}
+
+/**
+ * nf_ct_resolve_clash_harder - attempt to insert clashing conntrack entry
+ *
+ * @skb: skb that causes the collision
+ * @repl_idx: hash slot for reply direction
+ *
+ * Called when origin or reply direction had a clash.
+ * The skb can be handled without packet drop provided the reply direction
+ * is unique or there the existing entry has the identical tuple in both
+ * directions.
+ *
+ * Caller must hold conntrack table locks to prevent concurrent updates.
+ *
+ * Returns NF_DROP if the clash could not be handled.
+ */
+static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx)
+{
+	struct nf_conn *loser_ct = (struct nf_conn *)skb_nfct(skb);
+	const struct nf_conntrack_zone *zone;
+	struct nf_conntrack_tuple_hash *h;
+	struct hlist_nulls_node *n;
+	struct net *net;
+
+	zone = nf_ct_zone(loser_ct);
+	net = nf_ct_net(loser_ct);
+
+	/* Reply direction must never result in a clash, unless both origin
+	 * and reply tuples are identical.
+	 */
+	hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[repl_idx], hnnode) {
+		if (nf_ct_key_equal(h,
+				    &loser_ct->tuplehash[IP_CT_DIR_REPLY].tuple,
+				    zone, net))
+			return __nf_ct_resolve_clash(skb, h);
+	}
+
+	/* We want the clashing entry to go away real soon: 1 second timeout. */
+	loser_ct->timeout = nfct_time_stamp + HZ;
+
+	/* IPS_NAT_CLASH removes the entry automatically on the first
+	 * reply.  Also prevents UDP tracker from moving the entry to
+	 * ASSURED state, i.e. the entry can always be evicted under
+	 * pressure.
+	 */
+	loser_ct->status |= IPS_FIXED_TIMEOUT | IPS_NAT_CLASH;
+
+	__nf_conntrack_insert_prepare(loser_ct);
+
+	/* fake add for ORIGINAL dir: we want lookups to only find the entry
+	 * already in the table.  This also hides the clashing entry from
+	 * ctnetlink iteration, i.e. conntrack -L won't show them.
+	 */
+	hlist_nulls_add_fake(&loser_ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
+
+	hlist_nulls_add_head_rcu(&loser_ct->tuplehash[IP_CT_DIR_REPLY].hnnode,
+				 &nf_conntrack_hash[repl_idx]);
+	return NF_ACCEPT;
+}
+
+/**
+ * nf_ct_resolve_clash - attempt to handle clash without packet drop
+ *
+ * @skb: skb that causes the clash
+ * @h: tuplehash of the clashing entry already in table
+ * @hash_reply: hash slot for reply direction
+ *
+ * A conntrack entry can be inserted to the connection tracking table
+ * if there is no existing entry with an identical tuple.
+ *
+ * If there is one, @skb (and the assocated, unconfirmed conntrack) has
+ * to be dropped.  In case @skb is retransmitted, next conntrack lookup
+ * will find the already-existing entry.
+ *
+ * The major problem with such packet drop is the extra delay added by
+ * the packet loss -- it will take some time for a retransmit to occur
+ * (or the sender to time out when waiting for a reply).
+ *
+ * This function attempts to handle the situation without packet drop.
+ *
+ * If @skb has no NAT transformation or if the colliding entries are
+ * exactly the same, only the to-be-confirmed conntrack entry is discarded
+ * and @skb is associated with the conntrack entry already in the table.
+ *
+ * Failing that, the new, unconfirmed conntrack is still added to the table
+ * provided that the collision only occurs in the ORIGINAL direction.
+ * The new entry will be added after the existing one in the hash list,
+ * so packets in the ORIGINAL direction will continue to match the existing
+ * entry.  The new entry will also have a fixed timeout so it expires --
+ * due to the collision, it will not see bidirectional traffic.
+ *
+ * Returns NF_DROP if the clash could not be resolved.
+ */
 static __cold noinline int
-nf_ct_resolve_clash(struct net *net, struct sk_buff *skb,
-		    enum ip_conntrack_info ctinfo,
-		    struct nf_conntrack_tuple_hash *h)
+nf_ct_resolve_clash(struct sk_buff *skb, struct nf_conntrack_tuple_hash *h,
+		    u32 reply_hash)
 {
 	/* This is the conntrack entry already in hashes that won race. */
 	struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
 	const struct nf_conntrack_l4proto *l4proto;
-	enum ip_conntrack_info oldinfo;
-	struct nf_conn *loser_ct = nf_ct_get(skb, &oldinfo);
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *loser_ct;
+	struct net *net;
+	int ret;
+
+	loser_ct = nf_ct_get(skb, &ctinfo);
+	net = nf_ct_net(loser_ct);
 
 	l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct));
-	if (l4proto->allow_clash &&
-	    !nf_ct_is_dying(ct) &&
-	    atomic_inc_not_zero(&ct->ct_general.use)) {
-		if (((ct->status & IPS_NAT_DONE_MASK) == 0) ||
-		    nf_ct_match(ct, loser_ct)) {
-			nf_ct_acct_merge(ct, ctinfo, loser_ct);
-			nf_conntrack_put(&loser_ct->ct_general);
-			nf_ct_set(skb, ct, oldinfo);
-			return NF_ACCEPT;
-		}
-		nf_ct_put(ct);
-	}
+	if (!l4proto->allow_clash)
+		goto drop;
+
+	ret = __nf_ct_resolve_clash(skb, h);
+	if (ret == NF_ACCEPT)
+		return ret;
+
+	ret = nf_ct_resolve_clash_harder(skb, reply_hash);
+	if (ret == NF_ACCEPT)
+		return ret;
+
+drop:
+	nf_ct_add_to_dying_list(loser_ct);
 	NF_CT_STAT_INC(net, drop);
+	NF_CT_STAT_INC(net, insert_failed);
 	return NF_DROP;
 }
 
···
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conn *ct;
 	struct nf_conn_help *help;
-	struct nf_conn_tstamp *tstamp;
 	struct hlist_nulls_node *n;
 	enum ip_conntrack_info ctinfo;
 	struct net *net;
···
 
 	if (unlikely(nf_ct_is_dying(ct))) {
 		nf_ct_add_to_dying_list(ct);
+		NF_CT_STAT_INC(net, insert_failed);
 		goto dying;
 	}
 
···
 	   setting time, otherwise we'd get timer wrap in
 	   weird delay cases. */
 	ct->timeout += nfct_time_stamp;
-	atomic_inc(&ct->ct_general.use);
-	ct->status |= IPS_CONFIRMED;
 
-	/* set conntrack timestamp, if enabled. */
-	tstamp = nf_conn_tstamp_find(ct);
-	if (tstamp)
-		tstamp->start = ktime_get_real_ns();
+	__nf_conntrack_insert_prepare(ct);
 
 	/* Since the lookup is lockless, hash insertion must be done after
 	 * starting the timer and setting the CONFIRMED bit. The RCU barriers
···
 	return NF_ACCEPT;
 
 out:
-	nf_ct_add_to_dying_list(ct);
-	ret = nf_ct_resolve_clash(net, skb, ctinfo, h);
+	ret = nf_ct_resolve_clash(skb, h, reply_hash);
 dying:
 	nf_conntrack_double_unlock(hash, reply_hash);
-	NF_CT_STAT_INC(net, insert_failed);
 	local_bh_enable();
 	return ret;
 }

net/netfilter/nf_conntrack_proto_udp.c

···
 	return false;
 }
 
+static void nf_conntrack_udp_refresh_unreplied(struct nf_conn *ct,
+					       struct sk_buff *skb,
+					       enum ip_conntrack_info ctinfo,
+					       u32 extra_jiffies)
+{
+	if (unlikely(ctinfo == IP_CT_ESTABLISHED_REPLY &&
+		     ct->status & IPS_NAT_CLASH))
+		nf_ct_kill(ct);
+	else
+		nf_ct_refresh_acct(ct, ctinfo, skb, extra_jiffies);
+}
+
 /* Returns verdict for packet, and may modify conntracktype */
 int nf_conntrack_udp_packet(struct nf_conn *ct,
 			    struct sk_buff *skb,
···
 		if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status))
 			nf_conntrack_event_cache(IPCT_ASSURED, ct);
 	} else {
-		nf_ct_refresh_acct(ct, ctinfo, skb,
-				   timeouts[UDP_CT_UNREPLIED]);
+		nf_conntrack_udp_refresh_unreplied(ct, skb, ctinfo,
+						   timeouts[UDP_CT_UNREPLIED]);
 	}
 	return NF_ACCEPT;
 }
···
 		if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status))
 			nf_conntrack_event_cache(IPCT_ASSURED, ct);
 	} else {
-		nf_ct_refresh_acct(ct, ctinfo, skb,
-				   timeouts[UDP_CT_UNREPLIED]);
+		nf_conntrack_udp_refresh_unreplied(ct, skb, ctinfo,
+						   timeouts[UDP_CT_UNREPLIED]);
 	}
 	return NF_ACCEPT;
 }

net/netfilter/nf_flow_table_offload.c

···
 {
 	int err;
 
-	if (!nf_flowtable_hw_offload(flowtable))
-		return 0;
-
 	if (!dev->netdev_ops->ndo_setup_tc)
 		return -EOPNOTSUPP;
 
···
 	struct netlink_ext_ack extack = {};
 	struct flow_block_offload bo;
 	int err;
+
+	if (!nf_flowtable_hw_offload(flowtable))
+		return 0;
 
 	err = nf_flow_table_offload_cmd(&bo, flowtable, dev, cmd, &extack);
 	if (err < 0)

net/netfilter/nft_set_pipapo.c

···
  * ::
  *
  *       rule indices in last field:    0    1
- *       map to elements:             0x42  0x66
+ *       map to elements:             0x66  0x42
  *
  *
  * Matching
···
  * ::
  *
  *       rule indices in last field:    0    1
- *       map to elements:             0x42  0x66
+ *       map to elements:             0x66  0x42
  *
  *      the matching element is at 0x42.
  *
···
 				return -1;
 			}
 
-			if (unlikely(match_only)) {
+			if (match_only) {
 				bitmap_clear(map, i, 1);
 				return i;
 			}

net/netfilter/xt_hashlimit.c

···
 #include <linux/netfilter_ipv6/ip6_tables.h>
 #include <linux/mutex.h>
 #include <linux/kernel.h>
+#include <linux/refcount.h>
 #include <uapi/linux/netfilter/xt_hashlimit.h>
 
 #define XT_HASHLIMIT_ALL (XT_HASHLIMIT_HASH_DIP | XT_HASHLIMIT_HASH_DPT | \
···
 
 struct xt_hashlimit_htable {
 	struct hlist_node node;		/* global list of all htables */
-	int use;
+	refcount_t use;
 	u_int8_t family;
 	bool rnd_initialized;
 
···
 	for (i = 0; i < hinfo->cfg.size; i++)
 		INIT_HLIST_HEAD(&hinfo->hash[i]);
 
-	hinfo->use = 1;
+	refcount_set(&hinfo->use, 1);
 	hinfo->count = 0;
 	hinfo->family = family;
 	hinfo->rnd_initialized = false;
···
 	hlist_for_each_entry(hinfo, &hashlimit_net->htables, node) {
 		if (!strcmp(name, hinfo->name) &&
 		    hinfo->family == family) {
-			hinfo->use++;
+			refcount_inc(&hinfo->use);
 			return hinfo;
 		}
 	}
···
 
 static void htable_put(struct xt_hashlimit_htable *hinfo)
 {
-	mutex_lock(&hashlimit_mutex);
-	if (--hinfo->use == 0) {
+	if (refcount_dec_and_mutex_lock(&hinfo->use, &hashlimit_mutex)) {
 		hlist_del(&hinfo->node);
+		mutex_unlock(&hashlimit_mutex);
 		htable_destroy(hinfo);
 	}
-	mutex_unlock(&hashlimit_mutex);
 }
 
 /* The algorithm used is the Simple Token Bucket Filter (TBF)
···
 	return hashlimit_mt_common(skb, par, hinfo, &info->cfg, 3);
 }
 
+#define HASHLIMIT_MAX_SIZE 1048576
+
 static int hashlimit_mt_check_common(const struct xt_mtchk_param *par,
 				     struct xt_hashlimit_htable **hinfo,
 				     struct hashlimit_cfg3 *cfg,
···
 
 	if (cfg->gc_interval == 0 || cfg->expire == 0)
 		return -EINVAL;
+	if (cfg->size > HASHLIMIT_MAX_SIZE) {
+		cfg->size = HASHLIMIT_MAX_SIZE;
+		pr_info_ratelimited("size too large, truncated to %u\n", cfg->size);
+	}
+	if (cfg->max > HASHLIMIT_MAX_SIZE) {
+		cfg->max = HASHLIMIT_MAX_SIZE;
+		pr_info_ratelimited("max too large, truncated to %u\n", cfg->max);
+	}
 	if (par->family == NFPROTO_IPV4) {
 		if (cfg->srcmask > 32 || cfg->dstmask > 32)
 			return -EINVAL;

net/netlabel/netlabel_domainhash.c

···
 	if (domain != NULL) {
 		bkt = netlbl_domhsh_hash(domain);
 		bkt_list = &netlbl_domhsh_rcu_deref(netlbl_domhsh)->tbl[bkt];
-		list_for_each_entry_rcu(iter, bkt_list, list)
+		list_for_each_entry_rcu(iter, bkt_list, list,
+					lockdep_is_held(&netlbl_domhsh_lock))
 			if (iter->valid &&
 			    netlbl_family_match(iter->family, family) &&
 			    strcmp(iter->domain, domain) == 0)

net/netlabel/netlabel_unlabeled.c

···
 
 	bkt = netlbl_unlhsh_hash(ifindex);
 	bkt_list = &netlbl_unlhsh_rcu_deref(netlbl_unlhsh)->tbl[bkt];
-	list_for_each_entry_rcu(iter, bkt_list, list)
+	list_for_each_entry_rcu(iter, bkt_list, list,
+				lockdep_is_held(&netlbl_unlhsh_lock))
 		if (iter->valid && iter->ifindex == ifindex)
 			return iter;
 

net/netlink/af_netlink.c

···
 	if (nlk->netlink_bind && groups) {
 		int group;
 
-		for (group = 0; group < nlk->ngroups; group++) {
+		/* nl_groups is a u32, so cap the maximum groups we can bind */
+		for (group = 0; group < BITS_PER_TYPE(u32); group++) {
 			if (!test_bit(group, &groups))
 				continue;
 			err = nlk->netlink_bind(net, group + 1);
···
 			netlink_insert(sk, nladdr->nl_pid) :
 			netlink_autobind(sock);
 		if (err) {
-			netlink_undo_bind(nlk->ngroups, groups, sk);
+			netlink_undo_bind(BITS_PER_TYPE(u32), groups, sk);
 			goto unlock;
 		}
 	}

net/openvswitch/datapath.c

···
 	struct hlist_head *head;
 
 	head = vport_hash_bucket(dp, port_no);
-	hlist_for_each_entry_rcu(vport, head, dp_hash_node) {
+	hlist_for_each_entry_rcu(vport, head, dp_hash_node,
+				lockdep_ovsl_is_held()) {
 		if (vport->port_no == port_no)
 			return vport;
 	}
···
 	int i;
 
 	for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) {
-		hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node) {
+		hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node,
+					lockdep_ovsl_is_held()) {
 			dev = vport->dev;
 			dev_headroom = netdev_get_fwd_headroom(dev);
 			if (dev_headroom > max_headroom)
···
 
 	dp->max_headroom = new_headroom;
 	for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++)
-		hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node)
+		hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node,
+					lockdep_ovsl_is_held())
 			netdev_set_rx_headroom(vport->dev, new_headroom);
 }
 

net/openvswitch/flow_netlink.c

···
 		return -EINVAL;
 
 	switch (key_type) {
-	const struct ovs_key_ipv4 *ipv4_key;
-	const struct ovs_key_ipv6 *ipv6_key;
-	int err;
-
 	case OVS_KEY_ATTR_PRIORITY:
 	case OVS_KEY_ATTR_SKB_MARK:
 	case OVS_KEY_ATTR_CT_MARK:
···
 			return -EINVAL;
 		break;
 
-	case OVS_KEY_ATTR_TUNNEL:
+	case OVS_KEY_ATTR_TUNNEL: {
+		int err;
+
 		if (masked)
 			return -EINVAL; /* Masked tunnel set not supported. */
 
···
 		if (err)
 			return err;
 		break;
+	}
+	case OVS_KEY_ATTR_IPV4: {
+		const struct ovs_key_ipv4 *ipv4_key;
 
-	case OVS_KEY_ATTR_IPV4:
 		if (eth_type != htons(ETH_P_IP))
 			return -EINVAL;
 
···
 				return -EINVAL;
 		}
 		break;
+	}
+	case OVS_KEY_ATTR_IPV6: {
+		const struct ovs_key_ipv6 *ipv6_key;
 
-	case OVS_KEY_ATTR_IPV6:
 		if (eth_type != htons(ETH_P_IPV6))
 			return -EINVAL;
 
···
 			return -EINVAL;
 
 		break;
-
+	}
 	case OVS_KEY_ATTR_TCP:
 		if ((eth_type != htons(ETH_P_IP) &&
 		     eth_type != htons(ETH_P_IPV6)) ||

net/openvswitch/flow_table.c

···
 	head = find_bucket(ti, hash);
 	(*n_mask_hit)++;
 
-	hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver]) {
+	hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver],
+				lockdep_ovsl_is_held()) {
 		if (flow->mask == mask && flow->flow_table.hash == hash &&
 		    flow_cmp_masked_key(flow, &masked_key, &mask->range))
 			return flow;
···
 
 	hash = ufid_hash(ufid);
 	head = find_bucket(ti, hash);
-	hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver]) {
+	hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver],
+				lockdep_ovsl_is_held()) {
 		if (flow->ufid_table.hash == hash &&
 		    ovs_flow_cmp_ufid(flow, ufid))
 			return flow;

net/openvswitch/meter.c

···
 	struct hlist_head *head;
 
 	head = meter_hash_bucket(dp, meter_id);
-	hlist_for_each_entry_rcu(meter, head, dp_hash_node) {
+	hlist_for_each_entry_rcu(meter, head, dp_hash_node,
+				lockdep_ovsl_is_held()) {
 		if (meter->id == meter_id)
 			return meter;
 	}

net/openvswitch/vport.c

···
 	struct hlist_head *bucket = hash_bucket(net, name);
 	struct vport *vport;
 
-	hlist_for_each_entry_rcu(vport, bucket, hash_node)
+	hlist_for_each_entry_rcu(vport, bucket, hash_node,
+				lockdep_ovsl_is_held())
 		if (!strcmp(name, ovs_vport_name(vport)) &&
 		    net_eq(ovs_dp_get_net(vport->dp), net))
 			return vport;

net/rds/rdma.c

···
 	if (write)
 		gup_flags |= FOLL_WRITE;
 
-	ret = get_user_pages_fast(user_addr, nr_pages, gup_flags, pages);
+	ret = pin_user_pages_fast(user_addr, nr_pages, gup_flags, pages);
 	if (ret >= 0 && ret < nr_pages) {
-		while (ret--)
-			put_page(pages[ret]);
+		unpin_user_pages(pages, ret);
 		ret = -EFAULT;
 	}
 
···
 		 * to release anything.
 		 */
 		if (!need_odp) {
-			for (i = 0 ; i < nents; i++)
-				put_page(sg_page(&sg[i]));
+			unpin_user_pages(pages, nr_pages);
 			kfree(sg);
 		}
 		ret = PTR_ERR(trans_private);
···
 	if (cookie_ret)
 		*cookie_ret = cookie;
 
-	if (args->cookie_addr && put_user(cookie, (u64 __user *)(unsigned long) args->cookie_addr)) {
+	if (args->cookie_addr &&
+	    put_user(cookie, (u64 __user *)(unsigned long)args->cookie_addr)) {
+		if (!need_odp) {
+			unpin_user_pages(pages, nr_pages);
+			kfree(sg);
+		}
 		ret = -EFAULT;
 		goto out;
 	}
···
 			 * is the case for a RDMA_READ which copies from remote
 			 * to local memory
 			 */
-			if (!ro->op_write)
-				set_page_dirty(page);
-			put_page(page);
+			unpin_user_pages_dirty_lock(&page, 1, !ro->op_write);
 		}
 	}
 
···
 	/* Mark page dirty if it was possibly modified, which
 	 * is the case for a RDMA_READ which copies from remote
 	 * to local memory */
-	set_page_dirty(page);
-	put_page(page);
+	unpin_user_pages_dirty_lock(&page, 1, true);
 
 	kfree(ao->op_notifier);
 	ao->op_notifier = NULL;
···
 	return ret;
 err:
 	if (page)
-		put_page(page);
+		unpin_user_page(page);
 	rm->atomic.op_active = 0;
 	kfree(rm->atomic.op_notifier);
 

net/sched/cls_flower.c

···
 	struct cls_fl_filter *f;
 
 	list_for_each_entry_rcu(mask, &head->masks, list) {
+		flow_dissector_init_keys(&skb_key.control, &skb_key.basic);
 		fl_clear_masked_range(&skb_key, mask);
 
 		skb_flow_dissect_meta(skb, &mask->dissector, &skb_key);

net/sctp/sm_statefuns.c

···
 	return true;
 }
 
+/* Check for format error in an ABORT chunk */
+static inline bool sctp_err_chunk_valid(struct sctp_chunk *chunk)
+{
+	struct sctp_errhdr *err;
+
+	sctp_walk_errors(err, chunk->chunk_hdr);
+
+	return (void *)err == (void *)chunk->chunk_end;
+}
+
 /**********************************************************
  * These are the state functions for handling chunk events.
  **********************************************************/
···
 		    sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
 		return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
 
+	if (!sctp_err_chunk_valid(chunk))
+		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
 	return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands);
 }
 
···
 	if (SCTP_ADDR_DEL ==
 		    sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
 		return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
+
+	if (!sctp_err_chunk_valid(chunk))
+		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
 
 	/* Stop the T2-shutdown timer. */
 	sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
···
 		    sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
 		return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
 
+	if (!sctp_err_chunk_valid(chunk))
+		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
 	return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands);
 }
 
···
 
 	/* See if we have an error cause code in the chunk.  */
 	len = ntohs(chunk->chunk_hdr->length);
-	if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) {
-		struct sctp_errhdr *err;
-
-		sctp_walk_errors(err, chunk->chunk_hdr);
-		if ((void *)err != (void *)chunk->chunk_end)
-			return sctp_sf_pdiscard(net, ep, asoc, type, arg,
-						commands);
-
+	if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr))
 		error = ((struct sctp_errhdr *)chunk->skb->data)->cause;
-	}
 
 	sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNRESET));
 	/* ASSOC_FAILED will DELETE_TCB. */

net/tls/tls_device.c

···
 				       u32 seq, u64 *p_record_sn)
 {
 	u64 record_sn = context->hint_record_sn;
-	struct tls_record_info *info;
+	struct tls_record_info *info, *last;
 
 	info = context->retransmit_hint;
 	if (!info ||
···
 						struct tls_record_info, list);
 		if (!info)
 			return NULL;
+		/* send the start_marker record if seq number is before the
+		 * tls offload start marker sequence number. This record is
+		 * required to handle TCP packets which are before TLS offload
+		 * started.
+		 *  And if it's not start marker, look if this seq number
+		 * belongs to the list.
+		 */
+		if (likely(!tls_record_is_start_marker(info))) {
+			/* we have the first record, get the last record to see
+			 * if this seq number belongs to the list.
+			 */
+			last = list_last_entry(&context->records_list,
+					       struct tls_record_info, list);
+
+			if (!between(seq, tls_record_start_seq(info),
+				     last->end_seq))
+				return NULL;
+		}
 		record_sn = context->unacked_record_sn;
 	}
 

net/xdp/xsk.c

···
 static void xsk_flush(struct xdp_sock *xs)
 {
 	xskq_prod_submit(xs->rx);
+	__xskq_cons_release(xs->umem->fq);
 	sock_def_readable(&xs->sk);
 }
 
···
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(xs, &umem->xsk_list, list) {
+		__xskq_cons_release(xs->tx);
 		xs->sk.sk_write_space(&xs->sk);
 	}
 	rcu_read_unlock();

net/xdp/xsk_queue.h

···
 {
 	/* To improve performance, only update local state here.
 	 * Reflect this to global state when we get new entries
-	 * from the ring in xskq_cons_get_entries().
+	 * from the ring in xskq_cons_get_entries() and whenever
+	 * Rx or Tx processing are completed in the NAPI loop.
 	 */
 	q->cached_cons++;
 }

tools/include/uapi/linux/bpf.h

···
  * 		supports redirection to the egress interface, and accepts no
  * 		flag at all.
  *
- * 		The same effect can be attained with the more generic
- * 		**bpf_redirect_map**\ (), which requires specific maps to be
- * 		used but offers better performance.
+ * 		The same effect can also be attained with the more generic
+ * 		**bpf_redirect_map**\ (), which uses a BPF map to store the
+ * 		redirect target instead of providing it directly to the helper.
  * 	Return
  * 		For XDP, the helper returns **XDP_REDIRECT** on success or
  * 		**XDP_ABORTED** on error. For other program types, the values
···
  * 		the caller. Any higher bits in the *flags* argument must be
  * 		unset.
  *
- * 		When used to redirect packets to net devices, this helper
- * 		provides a high performance increase over **bpf_redirect**\ ().
- * 		This is due to various implementation details of the underlying
- * 		mechanisms, one of which is the fact that **bpf_redirect_map**\
- * 		() tries to send packet as a "bulk" to the device.
+ * 		See also bpf_redirect(), which only supports redirecting to an
+ * 		ifindex, but doesn't require a map to do so.
  * 	Return
- * 		**XDP_REDIRECT** on success, or **XDP_ABORTED** on error.
+ * 		**XDP_REDIRECT** on success, or the value of the two lower bits
+ * 		of the **flags* argument on error.
  *
  * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags)
  * 	Description

tools/lib/bpf/libbpf.c

···
 #include <endian.h>
 #include <fcntl.h>
 #include <errno.h>
+#include <ctype.h>
 #include <asm/unistd.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
···
 static char *internal_map_name(struct bpf_object *obj,
 			       enum libbpf_map_type type)
 {
-	char map_name[BPF_OBJ_NAME_LEN];
+	char map_name[BPF_OBJ_NAME_LEN], *p;
 	const char *sfx = libbpf_type_to_btf_name[type];
 	int sfx_len = max((size_t)7, strlen(sfx));
 	int pfx_len = min((size_t)BPF_OBJ_NAME_LEN - sfx_len - 1,
···
 
 	snprintf(map_name, sizeof(map_name), "%.*s%.*s", pfx_len, obj->name,
 		 sfx_len, libbpf_type_to_btf_name[type]);
+
+	/* sanitise map name to characters allowed by kernel */
+	for (p = map_name; *p && p < map_name + sizeof(map_name); p++)
+		if (!isalnum(*p) && *p != '_' && *p != '.')
+			*p = '_';
 
 	return strdup(map_name);
 }

tools/testing/selftests/bpf/prog_tests/select_reuseport.c

···
 		.pass_on_failure = 0,
 	};
 
-	if (type != SOCK_STREAM)
+	if (type != SOCK_STREAM) {
+		test__skip();
 		return;
+	}
 
 	/*
 	 * +1 for TCP-SYN and
···
 		goto out;
 
 	saved_tcp_fo = read_int_sysctl(TCP_FO_SYSCTL);
+	if (saved_tcp_fo < 0)
+		goto out;
 	saved_tcp_syncookie = read_int_sysctl(TCP_SYNCOOKIE_SYSCTL);
-	if (saved_tcp_syncookie < 0 || saved_tcp_syncookie < 0)
+	if (saved_tcp_syncookie < 0)
 		goto out;
 
 	if (enable_fastopen())

tools/testing/selftests/bpf/prog_tests/sockmap_basic.c

···
 
 #include "test_progs.h"
 
+#define TCP_REPAIR		19	/* TCP sock is under repair right now */
+
+#define TCP_REPAIR_ON		1
+#define TCP_REPAIR_OFF_NO_WP	-1	/* Turn off without window probes */
+
 static int connected_socket_v4(void)
 {
 	struct sockaddr_in addr = {

tools/testing/selftests/net/fib_tests.sh

···
 	check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024"
 	log_test $? 0 "Multipath with single path via multipath attribute"
 
+	# multipath with dev-only
+	add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+	run_cmd "$IP -6 ro replace 2001:db8:104::/64 dev veth1"
+	check_route6 "2001:db8:104::/64 dev veth1 metric 1024"
+	log_test $? 0 "Multipath with dev-only"
+
 	# route replace fails - invalid nexthop 1
 	add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
 	run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:111::3 nexthop via 2001:db8:103::3"

tools/testing/selftests/net/forwarding/mirror_gre.sh

···
 {
 	local tundev=$1; shift
 	local direction=$1; shift
-	local prot=$1; shift
 	local what=$1; shift
 
-	local swp3mac=$(mac_get $swp3)
-	local h3mac=$(mac_get $h3)
+	case "$direction" in
+	ingress) local src_mac=$(mac_get $h1); local dst_mac=$(mac_get $h2)
+		;;
+	egress) local src_mac=$(mac_get $h2); local dst_mac=$(mac_get $h1)
+		;;
+	esac
 
 	RET=0
 
 	mirror_install $swp1 $direction $tundev "matchall $tcflags"
-	tc filter add dev $h3 ingress pref 77 prot $prot \
-		flower ip_proto 0x2f src_mac $swp3mac dst_mac $h3mac \
-		action pass
+	icmp_capture_install h3-${tundev} "src_mac $src_mac dst_mac $dst_mac"
 
-	mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 10
+	mirror_test v$h1 192.0.2.1 192.0.2.2 h3-${tundev} 100 10
 
-	tc filter del dev $h3 ingress pref 77
+	icmp_capture_uninstall h3-${tundev}
 	mirror_uninstall $swp1 $direction
 
 	log_test "$direction $what: envelope MAC ($tcflags)"
···
 
 test_gretap_mac()
 {
-	test_span_gre_mac gt4 ingress ip "mirror to gretap"
-	test_span_gre_mac gt4 egress ip "mirror to gretap"
+	test_span_gre_mac gt4 ingress "mirror to gretap"
+	test_span_gre_mac gt4 egress "mirror to gretap"
 }
 
 test_ip6gretap_mac()
 {
-	test_span_gre_mac gt6 ingress ipv6 "mirror to ip6gretap"
-	test_span_gre_mac gt6 egress ipv6 "mirror to ip6gretap"
+	test_span_gre_mac gt6 ingress "mirror to ip6gretap"
+	test_span_gre_mac gt6 egress "mirror to ip6gretap"
 }
 
 test_all()

tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh

···
 	RET=0
 
 	tc filter add dev v1 egress pref 77 prot ip \
-		flower ip_tos 0x40 action pass
-	vxlan_ping_test $h1 192.0.2.3 "-Q 0x40" v1 egress 77 10
-	vxlan_ping_test $h1 192.0.2.3 "-Q 0x30" v1 egress 77 0
+		flower ip_tos 0x14 action pass
+	vxlan_ping_test $h1 192.0.2.3 "-Q 0x14" v1 egress 77 10
+	vxlan_ping_test $h1 192.0.2.3 "-Q 0x18" v1 egress 77 0
 	tc filter del dev v1 egress pref 77 prot ip
 
 	log_test "VXLAN: envelope TOS inheritance"

tools/testing/selftests/wireguard/qemu/Makefile

···
 define file_download =
 $(DISTFILES_PATH)/$(1):
 	mkdir -p $(DISTFILES_PATH)
-	flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp'
-	if echo "$(3)  $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi
+	flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp; [ -f $$@.tmp ] || exit 1; if echo "$(3)  $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi'
 endef
 
 $(eval $(call tar_download,MUSL,musl,1.1.24,.tar.gz,https://www.musl-libc.org/releases/,1370c9a812b2cf2a7d92802510cca0058cc37e66a7bedd70051f0a34015022a3))
-$(eval $(call tar_download,LIBMNL,libmnl,1.0.4,.tar.bz2,https://www.netfilter.org/projects/libmnl/files/,171f89699f286a5854b72b91d06e8f8e3683064c5901fb09d954a9ab6f551f81))
 $(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c))
 $(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d))
 $(eval $(call tar_download,IPROUTE2,iproute2,5.4.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,fe97aa60a0d4c5ac830be18937e18dc3400ca713a33a89ad896ff1e3d46086ae))
 $(eval $(call tar_download,IPTABLES,iptables,1.8.4,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,993a3a5490a544c2cbf2ef15cf7e7ed21af1845baf228318d5c36ef8827e157c))
 $(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a0e42099e12e4bf7a68ebe6fde05553383a682e816a7ec9256ab4773faa))
 $(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a))
-$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20191226,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,aa8af0fdc9872d369d8c890a84dbc2a2466b55795dccd5b47721b2d97644b04f))
+$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20200206,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,f5207248c6a3c3e3bfc9ab30b91c1897b00802ed861e1f9faaed873366078c64))
 
 KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug)
 rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d))
···
 	$(MAKE) -C $(IPERF_PATH)
 	$(STRIP) -s $@
 
-$(LIBMNL_PATH)/.installed: $(LIBMNL_TAR)
-	flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
-	touch $@
-
-$(LIBMNL_PATH)/src/.libs/libmnl.a: | $(LIBMNL_PATH)/.installed $(USERSPACE_DEPS)
-	cd $(LIBMNL_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared
-	$(MAKE) -C $(LIBMNL_PATH)
-	sed -i 's:prefix=.*:prefix=$(LIBMNL_PATH):' $(LIBMNL_PATH)/libmnl.pc
-
 $(WIREGUARD_TOOLS_PATH)/.installed: $(WIREGUARD_TOOLS_TAR)
+	mkdir -p $(BUILD_PATH)
 	flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
 	touch $@
 
-$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
-	LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src LIBMNL_CFLAGS="-I$(LIBMNL_PATH)/include" LIBMNL_LDLIBS="-lmnl" wg
+$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(USERSPACE_DEPS)
+	$(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src wg
 	$(STRIP) -s $@
 
 $(BUILD_PATH)/init: init.c | $(USERSPACE_DEPS)
···
 $(IPROUTE2_PATH)/.installed: $(IPROUTE2_TAR)
 	mkdir -p $(BUILD_PATH)
 	flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
-	printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=y\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS -DHAVE_LIBMNL -I$(LIBMNL_PATH)/include\nLDLIBS+=-lmnl' > $(IPROUTE2_PATH)/config.mk
+	printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=n\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS\n' > $(IPROUTE2_PATH)/config.mk
 	printf 'lib: snapshot\n\t$$(MAKE) -C lib\nip/ip: lib\n\t$$(MAKE) -C ip ip\nmisc/ss: lib\n\t$$(MAKE) -C misc ss\n' >> $(IPROUTE2_PATH)/Makefile
 	touch $@
 
-$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
-	LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip
-	$(STRIP) -s $(IPROUTE2_PATH)/ip/ip
+$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS)
+	$(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip
+	$(STRIP) -s $@
 
-$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
-	LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss
-	$(STRIP) -s $(IPROUTE2_PATH)/misc/ss
+$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS)
+	$(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss
+	$(STRIP) -s $@
 
 $(IPTABLES_PATH)/.installed: $(IPTABLES_TAR)
 	mkdir -p $(BUILD_PATH)
···
 	sed -i -e "/nfnetlink=[01]/s:=[01]:=0:" -e "/nfconntrack=[01]/s:=[01]:=0:" $(IPTABLES_PATH)/configure
 	touch $@
 
-$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
-	cd $(IPTABLES_PATH) && PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --with-kernel=$(BUILD_PATH)/include
+$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(USERSPACE_DEPS)
+	cd $(IPTABLES_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --disable-connlabel --with-kernel=$(BUILD_PATH)/include
 	$(MAKE) -C $(IPTABLES_PATH)
 	$(STRIP) -s $@