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

Pull networking fixes from David Miller:

 1) Unbalanced locking in mwifiex_process_country_ie, from Brian Norris.

 2) Fix thermal zone registration in iwlwifi, from Andrei
    Otcheretianski.

 3) Fix double free_irq in sgi ioc3 eth, from Thomas Bogendoerfer.

 4) Use after free in mptcp, from Florian Westphal.

 5) Use after free in wireguard's root_remove_peer_lists, from Eric
    Dumazet.

 6) Properly access packets heads in bonding alb code, from Eric
    Dumazet.

 7) Fix data race in skb_queue_len(), from Qian Cai.

 8) Fix regression in r8169 on some chips, from Heiner Kallweit.

 9) Fix XDP program ref counting in hv_netvsc, from Haiyang Zhang.

10) Certain kinds of set link netlink operations can cause a NULL deref
    in the ipv6 addrconf code. Fix from Eric Dumazet.

11) Don't cancel uninitialized work queue in drop monitor, from Ido
    Schimmel.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (84 commits)
  net: thunderx: use proper interface type for RGMII
  mt76: mt7615: fix max_nss in mt7615_eeprom_parse_hw_cap
  bpf: Improve bucket_log calculation logic
  selftests/bpf: Test freeing sockmap/sockhash with a socket in it
  bpf, sockhash: Synchronize_rcu before free'ing map
  bpf, sockmap: Don't sleep while holding RCU lock on tear-down
  bpftool: Don't crash on missing xlated program instructions
  bpf, sockmap: Check update requirements after locking
  drop_monitor: Do not cancel uninitialized work item
  mlxsw: spectrum_dpipe: Add missing error path
  mlxsw: core: Add validation of hardware device types for MGPIR register
  mlxsw: spectrum_router: Clear offload indication from IPv6 nexthops on abort
  selftests: mlxsw: Add test cases for local table route replacement
  mlxsw: spectrum_router: Prevent incorrect replacement of local table routes
  net: dsa: microchip: enable module autoprobe
  ipv6/addrconf: fix potential NULL deref in inet6_set_link_af()
  dpaa_eth: support all modes with rate adapting PHYs
  net: stmmac: update pci platform data to use phy_interface
  net: stmmac: xgmac: fix missing IFF_MULTICAST checki in dwxgmac2_set_filter
  net: stmmac: fix missing IFF_MULTICAST check in dwmac4_set_filter
  ...

drivers/net/bonding/bond_alb.c

@@ -1383,26 +1383,31 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 	bool do_tx_balance = true;
 	u32 hash_index = 0;
 	const u8 *hash_start = NULL;
-	struct ipv6hdr *ip6hdr;
 
 	skb_reset_mac_header(skb);
 	eth_data = eth_hdr(skb);
 
 	switch (ntohs(skb->protocol)) {
 	case ETH_P_IP: {
-		const struct iphdr *iph = ip_hdr(skb);
+		const struct iphdr *iph;
 
 		if (is_broadcast_ether_addr(eth_data->h_dest) ||
-		    iph->daddr == ip_bcast ||
-		    iph->protocol == IPPROTO_IGMP) {
+		    !pskb_network_may_pull(skb, sizeof(*iph))) {
+			do_tx_balance = false;
+			break;
+		}
+		iph = ip_hdr(skb);
+		if (iph->daddr == ip_bcast || iph->protocol == IPPROTO_IGMP) {
 			do_tx_balance = false;
 			break;
 		}
 		hash_start = (char *)&(iph->daddr);
 		hash_size = sizeof(iph->daddr);
-	}
 		break;
-	case ETH_P_IPV6:
+	}
+	case ETH_P_IPV6: {
+		const struct ipv6hdr *ip6hdr;
+
 		/* IPv6 doesn't really use broadcast mac address, but leave
 		 * that here just in case.
 		 */
@@ -1419,7 +1424,11 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 			break;
 		}
 
-		/* Additianally, DAD probes should not be tx-balanced as that
+		if (!pskb_network_may_pull(skb, sizeof(*ip6hdr))) {
+			do_tx_balance = false;
+			break;
+		}
+		/* Additionally, DAD probes should not be tx-balanced as that
 		 * will lead to false positives for duplicate addresses and
 		 * prevent address configuration from working.
 		 */
@@ -1429,17 +1438,26 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 			break;
 		}
 
-		hash_start = (char *)&(ipv6_hdr(skb)->daddr);
-		hash_size = sizeof(ipv6_hdr(skb)->daddr);
+		hash_start = (char *)&ip6hdr->daddr;
+		hash_size = sizeof(ip6hdr->daddr);
 		break;
-	case ETH_P_IPX:
-		if (ipx_hdr(skb)->ipx_checksum != IPX_NO_CHECKSUM) {
+	}
+	case ETH_P_IPX: {
+		const struct ipxhdr *ipxhdr;
+
+		if (pskb_network_may_pull(skb, sizeof(*ipxhdr))) {
+			do_tx_balance = false;
+			break;
+		}
+		ipxhdr = (struct ipxhdr *)skb_network_header(skb);
+
+		if (ipxhdr->ipx_checksum != IPX_NO_CHECKSUM) {
 			/* something is wrong with this packet */
 			do_tx_balance = false;
 			break;
 		}
 
-		if (ipx_hdr(skb)->ipx_type != IPX_TYPE_NCP) {
+		if (ipxhdr->ipx_type != IPX_TYPE_NCP) {
 			/* The only protocol worth balancing in
 			 * this family since it has an "ARP" like
 			 * mechanism
@@ -1448,9 +1466,11 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 			break;
 		}
 
+		eth_data = eth_hdr(skb);
 		hash_start = (char *)eth_data->h_dest;
 		hash_size = ETH_ALEN;
 		break;
+	}
 	case ETH_P_ARP:
 		do_tx_balance = false;
 		if (bond_info->rlb_enabled)

drivers/net/dsa/b53/b53_common.c

@@ -693,7 +693,7 @@ int b53_configure_vlan(struct dsa_switch *ds)
 		b53_do_vlan_op(dev, VTA_CMD_CLEAR);
 	}
 
-	b53_enable_vlan(dev, false, ds->vlan_filtering);
+	b53_enable_vlan(dev, dev->vlan_enabled, ds->vlan_filtering);
 
 	b53_for_each_port(dev, i)
 		b53_write16(dev, B53_VLAN_PAGE,

drivers/net/dsa/bcm_sf2.c

@@ -68,7 +68,9 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port)
 
 		/* Force link status for IMP port */
 		reg = core_readl(priv, offset);
-		reg |= (MII_SW_OR | LINK_STS | GMII_SPEED_UP_2G);
+		reg |= (MII_SW_OR | LINK_STS);
+		if (priv->type == BCM7278_DEVICE_ID)
+			reg |= GMII_SPEED_UP_2G;
 		core_writel(priv, reg, offset);
 
 		/* Enable Broadcast, Multicast, Unicast forwarding to IMP port */

drivers/net/dsa/microchip/ksz9477_spi.c

@@ -101,6 +101,12 @@ static struct spi_driver ksz9477_spi_driver = {
 
 module_spi_driver(ksz9477_spi_driver);
 
+MODULE_ALIAS("spi:ksz9477");
+MODULE_ALIAS("spi:ksz9897");
+MODULE_ALIAS("spi:ksz9893");
+MODULE_ALIAS("spi:ksz9563");
+MODULE_ALIAS("spi:ksz8563");
+MODULE_ALIAS("spi:ksz9567");
 MODULE_AUTHOR("Woojung Huh <[email protected]>");
 MODULE_DESCRIPTION("Microchip KSZ9477 Series Switch SPI access Driver");
 MODULE_LICENSE("GPL");

drivers/net/ethernet/broadcom/bcmsysport.c

@@ -2736,6 +2736,9 @@ static int __maybe_unused bcm_sysport_resume(struct device *d)
 
 	umac_reset(priv);
 
+	/* Disable the UniMAC RX/TX */
+	umac_enable_set(priv, CMD_RX_EN | CMD_TX_EN, 0);
+
 	/* We may have been suspended and never received a WOL event that
 	 * would turn off MPD detection, take care of that now
 	 */

drivers/net/ethernet/cadence/macb_main.c

@@ -73,7 +73,11 @@ struct sifive_fu540_macb_mgmt {
 /* Max length of transmit frame must be a multiple of 8 bytes */
 #define MACB_TX_LEN_ALIGN	8
 #define MACB_MAX_TX_LEN		((unsigned int)((1 << MACB_TX_FRMLEN_SIZE) - 1) & ~((unsigned int)(MACB_TX_LEN_ALIGN - 1)))
-#define GEM_MAX_TX_LEN		((unsigned int)((1 << GEM_TX_FRMLEN_SIZE) - 1) & ~((unsigned int)(MACB_TX_LEN_ALIGN - 1)))
+/* Limit maximum TX length as per Cadence TSO errata. This is to avoid a
+ * false amba_error in TX path from the DMA assuming there is not enough
+ * space in the SRAM (16KB) even when there is.
+ */
+#define GEM_MAX_TX_LEN		(unsigned int)(0x3FC0)
 
 #define GEM_MTU_MIN_SIZE	ETH_MIN_MTU
 #define MACB_NETIF_LSO		NETIF_F_TSO
@@ -1791,16 +1795,14 @@ static netdev_features_t macb_features_check(struct sk_buff *skb,
 
 	/* Validate LSO compatibility */
 
-	/* there is only one buffer */
-	if (!skb_is_nonlinear(skb))
+	/* there is only one buffer or protocol is not UDP */
+	if (!skb_is_nonlinear(skb) || (ip_hdr(skb)->protocol != IPPROTO_UDP))
 		return features;
 
 	/* length of header */
 	hdrlen = skb_transport_offset(skb);
-	if (ip_hdr(skb)->protocol == IPPROTO_TCP)
-		hdrlen += tcp_hdrlen(skb);
 
-	/* For LSO:
+	/* For UFO only:
 	 * When software supplies two or more payload buffers all payload buffers
 	 * apart from the last must be a multiple of 8 bytes in size.
 	 */

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

@@ -1039,7 +1039,7 @@ static int phy_interface_mode(u8 lmac_type)
 	if (lmac_type == BGX_MODE_QSGMII)
 		return PHY_INTERFACE_MODE_QSGMII;
 	if (lmac_type == BGX_MODE_RGMII)
-		return PHY_INTERFACE_MODE_RGMII;
+		return PHY_INTERFACE_MODE_RGMII_RXID;
 
 	return PHY_INTERFACE_MODE_SGMII;
 }

drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c

@@ -3403,6 +3403,13 @@ static int chcr_stats_show(struct seq_file *seq, void *v)
 		   atomic_read(&adap->chcr_stats.fallback));
 	seq_printf(seq, "IPSec PDU: %10u\n",
 		   atomic_read(&adap->chcr_stats.ipsec_cnt));
+	seq_printf(seq, "TLS PDU Tx: %10u\n",
+		   atomic_read(&adap->chcr_stats.tls_pdu_tx));
+	seq_printf(seq, "TLS PDU Rx: %10u\n",
+		   atomic_read(&adap->chcr_stats.tls_pdu_rx));
+	seq_printf(seq, "TLS Keys (DDR) Count: %10u\n",
+		   atomic_read(&adap->chcr_stats.tls_key));
+
 	return 0;
 }
 DEFINE_SHOW_ATTRIBUTE(chcr_stats);

drivers/net/ethernet/dec/tulip/de2104x.c

@@ -417,7 +417,10 @@ static void de_rx (struct de_private *de)
 		if (status & DescOwn)
 			break;
 
-		len = ((status >> 16) & 0x7ff) - 4;
+		/* the length is actually a 15 bit value here according
+		 * to Table 4-1 in the DE2104x spec so mask is 0x7fff
+		 */
+		len = ((status >> 16) & 0x7fff) - 4;
 		mapping = de->rx_skb[rx_tail].mapping;
 
 		if (unlikely(drop)) {

drivers/net/ethernet/freescale/dpaa/dpaa_eth.c

@@ -2453,6 +2453,9 @@ static void dpaa_adjust_link(struct net_device *net_dev)
 	mac_dev->adjust_link(mac_dev);
 }
 
+/* The Aquantia PHYs are capable of performing rate adaptation */
+#define PHY_VEND_AQUANTIA	0x03a1b400
+
 static int dpaa_phy_init(struct net_device *net_dev)
 {
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
@@ -2471,9 +2474,14 @@ static int dpaa_phy_init(struct net_device *net_dev)
 		return -ENODEV;
 	}
 
-	/* Remove any features not supported by the controller */
-	ethtool_convert_legacy_u32_to_link_mode(mask, mac_dev->if_support);
-	linkmode_and(phy_dev->supported, phy_dev->supported, mask);
+	/* Unless the PHY is capable of rate adaptation */
+	if (mac_dev->phy_if != PHY_INTERFACE_MODE_XGMII ||
+	    ((phy_dev->drv->phy_id & GENMASK(31, 10)) != PHY_VEND_AQUANTIA)) {
+		/* remove any features not supported by the controller */
+		ethtool_convert_legacy_u32_to_link_mode(mask,
+							mac_dev->if_support);
+		linkmode_and(phy_dev->supported, phy_dev->supported, mask);
+	}
 
 	phy_support_asym_pause(phy_dev);
 

drivers/net/ethernet/intel/i40e/i40e_xsk.c

@@ -791,7 +791,7 @@ int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags)
 	struct i40e_ring *ring;
 
 	if (test_bit(__I40E_CONFIG_BUSY, pf->state))
-		return -ENETDOWN;
+		return -EAGAIN;
 
 	if (test_bit(__I40E_VSI_DOWN, vsi->state))
 		return -ENETDOWN;

drivers/net/ethernet/marvell/mvneta.c

@@ -401,6 +401,8 @@ struct mvneta_pcpu_stats {
 	struct	u64_stats_sync syncp;
 	u64	rx_packets;
 	u64	rx_bytes;
+	u64	rx_dropped;
+	u64	rx_errors;
 	u64	tx_packets;
 	u64	tx_bytes;
 };
@@ -738,6 +740,8 @@ mvneta_get_stats64(struct net_device *dev,
 		struct mvneta_pcpu_stats *cpu_stats;
 		u64 rx_packets;
 		u64 rx_bytes;
+		u64 rx_dropped;
+		u64 rx_errors;
 		u64 tx_packets;
 		u64 tx_bytes;
 
@@ -746,19 +750,20 @@ mvneta_get_stats64(struct net_device *dev,
 			start = u64_stats_fetch_begin_irq(&cpu_stats->syncp);
 			rx_packets = cpu_stats->rx_packets;
 			rx_bytes   = cpu_stats->rx_bytes;
+			rx_dropped = cpu_stats->rx_dropped;
+			rx_errors  = cpu_stats->rx_errors;
 			tx_packets = cpu_stats->tx_packets;
 			tx_bytes   = cpu_stats->tx_bytes;
 		} while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start));
 
 		stats->rx_packets += rx_packets;
 		stats->rx_bytes   += rx_bytes;
+		stats->rx_dropped += rx_dropped;
+		stats->rx_errors  += rx_errors;
 		stats->tx_packets += tx_packets;
 		stats->tx_bytes   += tx_bytes;
 	}
 
-	stats->rx_errors	= dev->stats.rx_errors;
-	stats->rx_dropped	= dev->stats.rx_dropped;
-
 	stats->tx_dropped	= dev->stats.tx_dropped;
 }
 
@@ -1736,8 +1741,14 @@ static u32 mvneta_txq_desc_csum(int l3_offs, int l3_proto,
 static void mvneta_rx_error(struct mvneta_port *pp,
 			    struct mvneta_rx_desc *rx_desc)
 {
+	struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
 	u32 status = rx_desc->status;
 
+	/* update per-cpu counter */
+	u64_stats_update_begin(&stats->syncp);
+	stats->rx_errors++;
+	u64_stats_update_end(&stats->syncp);
+
 	switch (status & MVNETA_RXD_ERR_CODE_MASK) {
 	case MVNETA_RXD_ERR_CRC:
 		netdev_err(pp->dev, "bad rx status %08x (crc error), size=%d\n",
@@ -2179,11 +2190,15 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp,
 
 	rxq->skb = build_skb(xdp->data_hard_start, PAGE_SIZE);
 	if (unlikely(!rxq->skb)) {
-		netdev_err(dev,
-			   "Can't allocate skb on queue %d\n",
-			   rxq->id);
-		dev->stats.rx_dropped++;
+		struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
+
+		netdev_err(dev, "Can't allocate skb on queue %d\n", rxq->id);
 		rxq->skb_alloc_err++;
+
+		u64_stats_update_begin(&stats->syncp);
+		stats->rx_dropped++;
+		u64_stats_update_end(&stats->syncp);
+
 		return -ENOMEM;
 	}
 	page_pool_release_page(rxq->page_pool, page);
@@ -2270,7 +2285,6 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 			/* Check errors only for FIRST descriptor */
 			if (rx_status & MVNETA_RXD_ERR_SUMMARY) {
 				mvneta_rx_error(pp, rx_desc);
-				dev->stats.rx_errors++;
 				/* leave the descriptor untouched */
 				continue;
 			}
@@ -2372,7 +2386,6 @@ static int mvneta_rx_hwbm(struct napi_struct *napi,
 			mvneta_bm_pool_put_bp(pp->bm_priv, bm_pool,
 					      rx_desc->buf_phys_addr);
 err_drop_frame:
-			dev->stats.rx_errors++;
 			mvneta_rx_error(pp, rx_desc);
 			/* leave the descriptor untouched */
 			continue;

drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h

@@ -45,7 +45,7 @@ void mlx5_ktls_destroy_key(struct mlx5_core_dev *mdev, u32 key_id);
 
 static inline bool mlx5_accel_is_ktls_device(struct mlx5_core_dev *mdev)
 {
-	if (!MLX5_CAP_GEN(mdev, tls))
+	if (!MLX5_CAP_GEN(mdev, tls_tx))
 		return false;
 
 	if (!MLX5_CAP_GEN(mdev, log_max_dek))

drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c

@@ -269,7 +269,7 @@ struct sk_buff *mlx5e_tls_handle_tx_skb(struct net_device *netdev,
 	int datalen;
 	u32 skb_seq;
 
-	if (MLX5_CAP_GEN(sq->channel->mdev, tls)) {
+	if (MLX5_CAP_GEN(sq->channel->mdev, tls_tx)) {
 		skb = mlx5e_ktls_handle_tx_skb(netdev, sq, skb, wqe, pi);
 		goto out;
 	}

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

@@ -613,13 +613,6 @@ void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
 
 		wqe_counter = be16_to_cpu(cqe->wqe_counter);
 
-		if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) {
-			netdev_WARN_ONCE(cq->channel->netdev,
-					 "Bad OP in ICOSQ CQE: 0x%x\n", get_cqe_opcode(cqe));
-			if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state))
-				queue_work(cq->channel->priv->wq, &sq->recover_work);
-			break;
-		}
 		do {
 			struct mlx5e_sq_wqe_info *wi;
 			u16 ci;
@@ -629,6 +622,15 @@ void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
 			ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
 			wi = &sq->db.ico_wqe[ci];
 
+			if (last_wqe && unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) {
+				netdev_WARN_ONCE(cq->channel->netdev,
+						 "Bad OP in ICOSQ CQE: 0x%x\n",
+						 get_cqe_opcode(cqe));
+				if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state))
+					queue_work(cq->channel->priv->wq, &sq->recover_work);
+				break;
+			}
+
 			if (likely(wi->opcode == MLX5_OPCODE_UMR)) {
 				sqcc += MLX5E_UMR_WQEBBS;
 				wi->umr.rq->mpwqe.umr_completed++;