Merge tag 'net-6.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Quite smaller than usual. Notably it includes the fix for the unix
  regression from the past weeks. The TCP window fix will require some
  follow-up, already queued.

  Current release - regressions:

   - af_unix: fix garbage collection of embryos

  Previous releases - regressions:

   - af_unix: fix race between GC and receive path

   - ipv6: sr: fix missing sk_buff release in seg6_input_core

   - tcp: remove 64 KByte limit for initial tp->rcv_wnd value

   - eth: r8169: fix rx hangup

   - eth: lan966x: remove ptp traps in case the ptp is not enabled

   - eth: ixgbe: fix link breakage vs cisco switches

   - eth: ice: prevent ethtool from corrupting the channels

  Previous releases - always broken:

   - openvswitch: set the skbuff pkt_type for proper pmtud support

   - tcp: Fix shift-out-of-bounds in dctcp_update_alpha()

  Misc:

   - a bunch of selftests stabilization patches"

* tag 'net-6.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (25 commits)
  r8169: Fix possible ring buffer corruption on fragmented Tx packets.
  idpf: Interpret .set_channels() input differently
  ice: Interpret .set_channels() input differently
  nfc: nci: Fix handling of zero-length payload packets in nci_rx_work()
  net: relax socket state check at accept time.
  tcp: remove 64 KByte limit for initial tp->rcv_wnd value
  net: ti: icssg_prueth: Fix NULL pointer dereference in prueth_probe()
  tls: fix missing memory barrier in tls_init
  net: fec: avoid lock evasion when reading pps_enable
  Revert "ixgbe: Manual AN-37 for troublesome link partners for X550 SFI"
  testing: net-drv: use stats64 for testing
  net: mana: Fix the extra HZ in mana_hwc_send_request
  net: lan966x: Remove ptp traps in case the ptp is not enabled.
  openvswitch: Set the skbuff pkt_type for proper pmtud support.
  selftest: af_unix: Make SCM_RIGHTS into OOB data.
  af_unix: Fix garbage collection of embryos carrying OOB with SCM_RIGHTS
  tcp: Fix shift-out-of-bounds in dctcp_update_alpha().
  selftests/net: use tc rule to filter the na packet
  ipv6: sr: fix memleak in seg6_hmac_init_algo
  af_unix: Update unix_sk(sk)->oob_skb under sk_receive_queue lock.
  ...

drivers/net/Makefile

@@ -49,7 +49,9 @@ obj-$(CONFIG_MHI_NET) += mhi_net.o
 obj-$(CONFIG_ARCNET) += arcnet/
 obj-$(CONFIG_CAIF) += caif/
 obj-$(CONFIG_CAN) += can/
-obj-$(CONFIG_NET_DSA) += dsa/
+ifdef CONFIG_NET_DSA
+obj-y += dsa/
+endif
 obj-$(CONFIG_ETHERNET) += ethernet/
 obj-$(CONFIG_FDDI) += fddi/
 obj-$(CONFIG_HIPPI) += hippi/

drivers/net/ethernet/freescale/fec_ptp.c

@@ -104,14 +104,13 @@ static int fec_ptp_enable_pps(struct fec_enet_private *fep, uint enable)
 	struct timespec64 ts;
 	u64 ns;
 
-	if (fep->pps_enable == enable)
-		return 0;
-
-	fep->pps_channel = DEFAULT_PPS_CHANNEL;
-	fep->reload_period = PPS_OUPUT_RELOAD_PERIOD;
-
 	spin_lock_irqsave(&fep->tmreg_lock, flags);
 
+	if (fep->pps_enable == enable) {
+		spin_unlock_irqrestore(&fep->tmreg_lock, flags);
+		return 0;
+	}
+
 	if (enable) {
 		/* clear capture or output compare interrupt status if have.
 		 */
@@ -532,6 +531,9 @@ static int fec_ptp_enable(struct ptp_clock_info *ptp,
 	int ret = 0;
 
 	if (rq->type == PTP_CLK_REQ_PPS) {
+		fep->pps_channel = DEFAULT_PPS_CHANNEL;
+		fep->reload_period = PPS_OUPUT_RELOAD_PERIOD;
+
 		ret = fec_ptp_enable_pps(fep, on);
 
 		return ret;

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

@@ -3593,7 +3593,6 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch)
 	struct ice_pf *pf = vsi->back;
 	int new_rx = 0, new_tx = 0;
 	bool locked = false;
-	u32 curr_combined;
 	int ret = 0;
 
 	/* do not support changing channels in Safe Mode */
@@ -3615,22 +3614,8 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch)
 		return -EOPNOTSUPP;
 	}
 
-	curr_combined = ice_get_combined_cnt(vsi);
-
-	/* these checks are for cases where user didn't specify a particular
-	 * value on cmd line but we get non-zero value anyway via
-	 * get_channels(); look at ethtool.c in ethtool repository (the user
-	 * space part), particularly, do_schannels() routine
-	 */
-	if (ch->rx_count == vsi->num_rxq - curr_combined)
-		ch->rx_count = 0;
-	if (ch->tx_count == vsi->num_txq - curr_combined)
-		ch->tx_count = 0;
-	if (ch->combined_count == curr_combined)
-		ch->combined_count = 0;
-
-	if (!(ch->combined_count || (ch->rx_count && ch->tx_count))) {
-		netdev_err(dev, "Please specify at least 1 Rx and 1 Tx channel\n");
+	if (ch->rx_count && ch->tx_count) {
+		netdev_err(dev, "Dedicated RX or TX channels cannot be used simultaneously\n");
 		return -EINVAL;
 	}
 

drivers/net/ethernet/intel/idpf/idpf_ethtool.c

@@ -222,14 +222,19 @@ static int idpf_set_channels(struct net_device *netdev,
 			     struct ethtool_channels *ch)
 {
 	struct idpf_vport_config *vport_config;
-	u16 combined, num_txq, num_rxq;
 	unsigned int num_req_tx_q;
 	unsigned int num_req_rx_q;
 	struct idpf_vport *vport;
+	u16 num_txq, num_rxq;
 	struct device *dev;
 	int err = 0;
 	u16 idx;
 
+	if (ch->rx_count && ch->tx_count) {
+		netdev_err(netdev, "Dedicated RX or TX channels cannot be used simultaneously\n");
+		return -EINVAL;
+	}
+
 	idpf_vport_ctrl_lock(netdev);
 	vport = idpf_netdev_to_vport(netdev);
 
@@ -239,20 +244,6 @@ static int idpf_set_channels(struct net_device *netdev,
 	num_txq = vport_config->user_config.num_req_tx_qs;
 	num_rxq = vport_config->user_config.num_req_rx_qs;
 
-	combined = min(num_txq, num_rxq);
-
-	/* these checks are for cases where user didn't specify a particular
-	 * value on cmd line but we get non-zero value anyway via
-	 * get_channels(); look at ethtool.c in ethtool repository (the user
-	 * space part), particularly, do_schannels() routine
-	 */
-	if (ch->combined_count == combined)
-		ch->combined_count = 0;
-	if (ch->combined_count && ch->rx_count == num_rxq - combined)
-		ch->rx_count = 0;
-	if (ch->combined_count && ch->tx_count == num_txq - combined)
-		ch->tx_count = 0;
-
 	num_req_tx_q = ch->combined_count + ch->tx_count;
 	num_req_rx_q = ch->combined_count + ch->rx_count;
 

drivers/net/ethernet/intel/ixgbe/ixgbe_type.h

@@ -3675,9 +3675,7 @@ struct ixgbe_info {
 #define IXGBE_KRM_LINK_S1(P)		((P) ? 0x8200 : 0x4200)
 #define IXGBE_KRM_LINK_CTRL_1(P)	((P) ? 0x820C : 0x420C)
 #define IXGBE_KRM_AN_CNTL_1(P)		((P) ? 0x822C : 0x422C)
-#define IXGBE_KRM_AN_CNTL_4(P)		((P) ? 0x8238 : 0x4238)
 #define IXGBE_KRM_AN_CNTL_8(P)		((P) ? 0x8248 : 0x4248)
-#define IXGBE_KRM_PCS_KX_AN(P)		((P) ? 0x9918 : 0x5918)
 #define IXGBE_KRM_SGMII_CTRL(P)		((P) ? 0x82A0 : 0x42A0)
 #define IXGBE_KRM_LP_BASE_PAGE_HIGH(P)	((P) ? 0x836C : 0x436C)
 #define IXGBE_KRM_DSP_TXFFE_STATE_4(P)	((P) ? 0x8634 : 0x4634)
@@ -3687,7 +3685,6 @@ struct ixgbe_info {
 #define IXGBE_KRM_PMD_FLX_MASK_ST20(P)	((P) ? 0x9054 : 0x5054)
 #define IXGBE_KRM_TX_COEFF_CTRL_1(P)	((P) ? 0x9520 : 0x5520)
 #define IXGBE_KRM_RX_ANA_CTL(P)		((P) ? 0x9A00 : 0x5A00)
-#define IXGBE_KRM_FLX_TMRS_CTRL_ST31(P)	((P) ? 0x9180 : 0x5180)
 
 #define IXGBE_KRM_PMD_FLX_MASK_ST20_SFI_10G_DA		~(0x3 << 20)
 #define IXGBE_KRM_PMD_FLX_MASK_ST20_SFI_10G_SR		BIT(20)

drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c

@@ -1722,59 +1722,9 @@ static int ixgbe_setup_sfi_x550a(struct ixgbe_hw *hw, ixgbe_link_speed *speed)
 		return -EINVAL;
 	}
 
-	(void)mac->ops.write_iosf_sb_reg(hw,
-			IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id),
-			IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
-
-	/* change mode enforcement rules to hybrid */
-	(void)mac->ops.read_iosf_sb_reg(hw,
-			IXGBE_KRM_FLX_TMRS_CTRL_ST31(hw->bus.lan_id),
-			IXGBE_SB_IOSF_TARGET_KR_PHY, &reg_val);
-	reg_val |= 0x0400;
-
-	(void)mac->ops.write_iosf_sb_reg(hw,
-			IXGBE_KRM_FLX_TMRS_CTRL_ST31(hw->bus.lan_id),
-			IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
-
-	/* manually control the config */
-	(void)mac->ops.read_iosf_sb_reg(hw,
-			IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id),
-			IXGBE_SB_IOSF_TARGET_KR_PHY, &reg_val);
-	reg_val |= 0x20002240;
-
-	(void)mac->ops.write_iosf_sb_reg(hw,
-			IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id),
-			IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
-
-	/* move the AN base page values */
-	(void)mac->ops.read_iosf_sb_reg(hw,
-			IXGBE_KRM_PCS_KX_AN(hw->bus.lan_id),
-			IXGBE_SB_IOSF_TARGET_KR_PHY, &reg_val);
-	reg_val |= 0x1;
-
-	(void)mac->ops.write_iosf_sb_reg(hw,
-			IXGBE_KRM_PCS_KX_AN(hw->bus.lan_id),
-			IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
-
-	/* set the AN37 over CB mode */
-	(void)mac->ops.read_iosf_sb_reg(hw,
-			IXGBE_KRM_AN_CNTL_4(hw->bus.lan_id),
-			IXGBE_SB_IOSF_TARGET_KR_PHY, &reg_val);
-	reg_val |= 0x20000000;
-
-	(void)mac->ops.write_iosf_sb_reg(hw,
-			IXGBE_KRM_AN_CNTL_4(hw->bus.lan_id),
-			IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
-
-	/* restart AN manually */
-	(void)mac->ops.read_iosf_sb_reg(hw,
-			IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id),
-			IXGBE_SB_IOSF_TARGET_KR_PHY, &reg_val);
-	reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_RESTART;
-
-	(void)mac->ops.write_iosf_sb_reg(hw,
-			IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id),
-			IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
+	status = mac->ops.write_iosf_sb_reg(hw,
+				IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id),
+				IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
 
 	/* Toggle port SW reset by AN reset. */
 	status = ixgbe_restart_an_internal_phy_x550em(hw);

drivers/net/ethernet/microchip/lan966x/lan966x_main.c

@@ -474,14 +474,14 @@ static int lan966x_port_hwtstamp_set(struct net_device *dev,
 	    cfg->source != HWTSTAMP_SOURCE_PHYLIB)
 		return -EOPNOTSUPP;
 
+	if (cfg->source == HWTSTAMP_SOURCE_NETDEV && !port->lan966x->ptp)
+		return -EOPNOTSUPP;
+
 	err = lan966x_ptp_setup_traps(port, cfg);
 	if (err)
 		return err;
 
 	if (cfg->source == HWTSTAMP_SOURCE_NETDEV) {
-		if (!port->lan966x->ptp)
-			return -EOPNOTSUPP;
-
 		err = lan966x_ptp_hwtstamp_set(port, cfg, extack);
 		if (err) {
 			lan966x_ptp_del_traps(port);

drivers/net/ethernet/microsoft/mana/hw_channel.c

@@ -849,7 +849,7 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,
 	}
 
 	if (!wait_for_completion_timeout(&ctx->comp_event,
-					 (msecs_to_jiffies(hwc->hwc_timeout) * HZ))) {
+					 (msecs_to_jiffies(hwc->hwc_timeout)))) {
 		dev_err(hwc->dev, "HWC: Request timed out!\n");
 		err = -ETIMEDOUT;
 		goto out;

drivers/net/ethernet/realtek/r8169_main.c

@@ -4337,11 +4337,11 @@ static void rtl8169_doorbell(struct rtl8169_private *tp)
 static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 				      struct net_device *dev)
 {
-	unsigned int frags = skb_shinfo(skb)->nr_frags;
 	struct rtl8169_private *tp = netdev_priv(dev);
 	unsigned int entry = tp->cur_tx % NUM_TX_DESC;
 	struct TxDesc *txd_first, *txd_last;
 	bool stop_queue, door_bell;
+	unsigned int frags;
 	u32 opts[2];
 
 	if (unlikely(!rtl_tx_slots_avail(tp))) {
@@ -4364,6 +4364,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 
 	txd_first = tp->TxDescArray + entry;
 
+	frags = skb_shinfo(skb)->nr_frags;
 	if (frags) {
 		if (rtl8169_xmit_frags(tp, skb, opts, entry))
 			goto err_dma_1;
@@ -4657,10 +4658,8 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance)
 		rtl_schedule_task(tp, RTL_FLAG_TASK_RESET_PENDING);
 	}
 
-	if (napi_schedule_prep(&tp->napi)) {
-		rtl_irq_disable(tp);
-		__napi_schedule(&tp->napi);
-	}
+	rtl_irq_disable(tp);
+	napi_schedule(&tp->napi);
 out:
 	rtl_ack_events(tp, status);
 

drivers/net/ethernet/ti/icssg/icssg_prueth.c

@@ -1039,7 +1039,12 @@ static int prueth_probe(struct platform_device *pdev)
 
 		prueth->registered_netdevs[PRUETH_MAC0] = prueth->emac[PRUETH_MAC0]->ndev;
 
-		emac_phy_connect(prueth->emac[PRUETH_MAC0]);
+		ret = emac_phy_connect(prueth->emac[PRUETH_MAC0]);
+		if (ret) {
+			dev_err(dev,
+				"can't connect to MII0 PHY, error -%d", ret);
+			goto netdev_unregister;
+		}
 		phy_attached_info(prueth->emac[PRUETH_MAC0]->ndev->phydev);
 	}
 
@@ -1051,7 +1056,12 @@ static int prueth_probe(struct platform_device *pdev)
 		}
 
 		prueth->registered_netdevs[PRUETH_MAC1] = prueth->emac[PRUETH_MAC1]->ndev;
-		emac_phy_connect(prueth->emac[PRUETH_MAC1]);
+		ret = emac_phy_connect(prueth->emac[PRUETH_MAC1]);
+		if (ret) {
+			dev_err(dev,
+				"can't connect to MII1 PHY, error %d", ret);
+			goto netdev_unregister;
+		}
 		phy_attached_info(prueth->emac[PRUETH_MAC1]->ndev->phydev);
 	}
 

net/ipv4/af_inet.c

@@ -758,7 +758,9 @@ void __inet_accept(struct socket *sock, struct socket *newsock, struct sock *new
 	sock_rps_record_flow(newsk);
 	WARN_ON(!((1 << newsk->sk_state) &
 		  (TCPF_ESTABLISHED | TCPF_SYN_RECV |
-		  TCPF_CLOSE_WAIT | TCPF_CLOSE)));
+		   TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 |
+		   TCPF_CLOSING | TCPF_CLOSE_WAIT |
+		   TCPF_CLOSE)));
 
 	if (test_bit(SOCK_SUPPORT_ZC, &sock->flags))
 		set_bit(SOCK_SUPPORT_ZC, &newsock->flags);

net/ipv4/tcp_dctcp.c

@@ -58,7 +58,18 @@ struct dctcp {
 };
 
 static unsigned int dctcp_shift_g __read_mostly = 4; /* g = 1/2^4 */
-module_param(dctcp_shift_g, uint, 0644);
+
+static int dctcp_shift_g_set(const char *val, const struct kernel_param *kp)
+{
+	return param_set_uint_minmax(val, kp, 0, 10);
+}
+
+static const struct kernel_param_ops dctcp_shift_g_ops = {
+	.set = dctcp_shift_g_set,
+	.get = param_get_uint,
+};
+
+module_param_cb(dctcp_shift_g, &dctcp_shift_g_ops, &dctcp_shift_g, 0644);
 MODULE_PARM_DESC(dctcp_shift_g, "parameter g for updating dctcp_alpha");
 
 static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA;

net/ipv4/tcp_output.c

@@ -232,7 +232,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
 	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows))
 		(*rcv_wnd) = min(space, MAX_TCP_WINDOW);
 	else
-		(*rcv_wnd) = min_t(u32, space, U16_MAX);
+		(*rcv_wnd) = space;
 
 	if (init_rcv_wnd)
 		*rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss);

net/ipv6/seg6_hmac.c

@@ -356,6 +356,7 @@ static int seg6_hmac_init_algo(void)
 	struct crypto_shash *tfm;
 	struct shash_desc *shash;
 	int i, alg_count, cpu;
+	int ret = -ENOMEM;
 
 	alg_count = ARRAY_SIZE(hmac_algos);
 
@@ -366,12 +367,14 @@ static int seg6_hmac_init_algo(void)
 		algo = &hmac_algos[i];
 		algo->tfms = alloc_percpu(struct crypto_shash *);
 		if (!algo->tfms)
-			return -ENOMEM;
+			goto error_out;
 
 		for_each_possible_cpu(cpu) {
 			tfm = crypto_alloc_shash(algo->name, 0, 0);
-			if (IS_ERR(tfm))
-				return PTR_ERR(tfm);
+			if (IS_ERR(tfm)) {
+				ret = PTR_ERR(tfm);
+				goto error_out;
+			}
 			p_tfm = per_cpu_ptr(algo->tfms, cpu);
 			*p_tfm = tfm;
 		}
@@ -383,18 +386,22 @@ static int seg6_hmac_init_algo(void)
 
 		algo->shashs = alloc_percpu(struct shash_desc *);
 		if (!algo->shashs)
-			return -ENOMEM;
+			goto error_out;
 
 		for_each_possible_cpu(cpu) {
 			shash = kzalloc_node(shsize, GFP_KERNEL,
 					     cpu_to_node(cpu));
 			if (!shash)
-				return -ENOMEM;
+				goto error_out;
 			*per_cpu_ptr(algo->shashs, cpu) = shash;
 		}
 	}
 
 	return 0;
+
+error_out:
+	seg6_hmac_exit();
+	return ret;
 }
 
 int __init seg6_hmac_init(void)
@@ -412,22 +419,29 @@ int __net_init seg6_hmac_net_init(struct net *net)
 void seg6_hmac_exit(void)
 {
 	struct seg6_hmac_algo *algo = NULL;
+	struct crypto_shash *tfm;
+	struct shash_desc *shash;
 	int i, alg_count, cpu;
 
 	alg_count = ARRAY_SIZE(hmac_algos);
 	for (i = 0; i < alg_count; i++) {
 		algo = &hmac_algos[i];
-		for_each_possible_cpu(cpu) {
-			struct crypto_shash *tfm;
-			struct shash_desc *shash;
 
-			shash = *per_cpu_ptr(algo->shashs, cpu);
-			kfree(shash);
-			tfm = *per_cpu_ptr(algo->tfms, cpu);
-			crypto_free_shash(tfm);
+		if (algo->shashs) {
+			for_each_possible_cpu(cpu) {
+				shash = *per_cpu_ptr(algo->shashs, cpu);
+				kfree(shash);
+			}
+			free_percpu(algo->shashs);
+		}
+
+		if (algo->tfms) {
+			for_each_possible_cpu(cpu) {
+				tfm = *per_cpu_ptr(algo->tfms, cpu);
+				crypto_free_shash(tfm);
+			}
+			free_percpu(algo->tfms);
 		}
-		free_percpu(algo->tfms);
-		free_percpu(algo->shashs);
 	}
 }
 EXPORT_SYMBOL(seg6_hmac_exit);

net/ipv6/seg6_iptunnel.c

@@ -459,10 +459,8 @@ static int seg6_input_core(struct net *net, struct sock *sk,
 	int err;
 
 	err = seg6_do_srh(skb);
-	if (unlikely(err)) {
-		kfree_skb(skb);
-		return err;
-	}
+	if (unlikely(err))
+		goto drop;
 
 	slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
 
@@ -486,7 +484,7 @@ static int seg6_input_core(struct net *net, struct sock *sk,
 
 	err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
 	if (unlikely(err))
-		return err;
+		goto drop;
 
 	if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
 		return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
@@ -494,6 +492,9 @@ static int seg6_input_core(struct net *net, struct sock *sk,
 			       skb_dst(skb)->dev, seg6_input_finish);
 
 	return seg6_input_finish(dev_net(skb->dev), NULL, skb);
+drop:
+	kfree_skb(skb);
+	return err;
 }
 
 static int seg6_input_nf(struct sk_buff *skb)

net/nfc/nci/core.c

@@ -1463,6 +1463,19 @@ int nci_core_ntf_packet(struct nci_dev *ndev, __u16 opcode,
 				 ndev->ops->n_core_ops);
 }
 
+static bool nci_valid_size(struct sk_buff *skb)
+{
+	BUILD_BUG_ON(NCI_CTRL_HDR_SIZE != NCI_DATA_HDR_SIZE);
+	unsigned int hdr_size = NCI_CTRL_HDR_SIZE;
+
+	if (skb->len < hdr_size ||
+	    !nci_plen(skb->data) ||
+	    skb->len < hdr_size + nci_plen(skb->data)) {
+		return false;
+	}
+	return true;
+}
+
 /* ---- NCI TX Data worker thread ---- */
 
 static void nci_tx_work(struct work_struct *work)
@@ -1516,10 +1529,9 @@ static void nci_rx_work(struct work_struct *work)
 		nfc_send_to_raw_sock(ndev->nfc_dev, skb,
 				     RAW_PAYLOAD_NCI, NFC_DIRECTION_RX);
 
-		if (!nci_plen(skb->data)) {
+		if (!nci_valid_size(skb)) {
 			kfree_skb(skb);
-			kcov_remote_stop();
-			break;
+			continue;
 		}
 
 		/* Process frame */

net/openvswitch/actions.c

@@ -936,6 +936,12 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
 				pskb_trim(skb, ovs_mac_header_len(key));
 		}
 
+		/* Need to set the pkt_type to involve the routing layer.  The
+		 * packet movement through the OVS datapath doesn't generally
+		 * use routing, but this is needed for tunnel cases.
+		 */
+		skb->pkt_type = PACKET_OUTGOING;
+
 		if (likely(!mru ||
 		           (skb->len <= mru + vport->dev->hard_header_len))) {
 			ovs_vport_send(vport, skb, ovs_key_mac_proto(key));

net/tls/tls_main.c

@@ -816,9 +816,17 @@ struct tls_context *tls_ctx_create(struct sock *sk)
 		return NULL;
 
 	mutex_init(&ctx->tx_lock);
-	rcu_assign_pointer(icsk->icsk_ulp_data, ctx);
 	ctx->sk_proto = READ_ONCE(sk->sk_prot);
 	ctx->sk = sk;
+	/* Release semantic of rcu_assign_pointer() ensures that
+	 * ctx->sk_proto is visible before changing sk->sk_prot in
+	 * update_sk_prot(), and prevents reading uninitialized value in
+	 * tls_{getsockopt, setsockopt}. Note that we do not need a
+	 * read barrier in tls_{getsockopt,setsockopt} as there is an
+	 * address dependency between sk->sk_proto->{getsockopt,setsockopt}
+	 * and ctx->sk_proto.
+	 */
+	rcu_assign_pointer(icsk->icsk_ulp_data, ctx);
 	return ctx;
 }
 

net/unix/af_unix.c

@@ -2170,13 +2170,15 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other
 	maybe_add_creds(skb, sock, other);
 	skb_get(skb);
 
+	scm_stat_add(other, skb);
+
+	spin_lock(&other->sk_receive_queue.lock);
 	if (ousk->oob_skb)
 		consume_skb(ousk->oob_skb);
-
 	WRITE_ONCE(ousk->oob_skb, skb);
+	__skb_queue_tail(&other->sk_receive_queue, skb);
+	spin_unlock(&other->sk_receive_queue.lock);
 
-	scm_stat_add(other, skb);
-	skb_queue_tail(&other->sk_receive_queue, skb);
 	sk_send_sigurg(other);
 	unix_state_unlock(other);
 	other->sk_data_ready(other);
@@ -2567,8 +2569,10 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state)
 
 	mutex_lock(&u->iolock);
 	unix_state_lock(sk);
+	spin_lock(&sk->sk_receive_queue.lock);
 
 	if (sock_flag(sk, SOCK_URGINLINE) || !u->oob_skb) {
+		spin_unlock(&sk->sk_receive_queue.lock);
 		unix_state_unlock(sk);
 		mutex_unlock(&u->iolock);
 		return -EINVAL;
@@ -2580,6 +2584,8 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state)
 		WRITE_ONCE(u->oob_skb, NULL);
 	else
 		skb_get(oob_skb);
+
+	spin_unlock(&sk->sk_receive_queue.lock);
 	unix_state_unlock(sk);
 
 	chunk = state->recv_actor(oob_skb, 0, chunk, state);
@@ -2608,6 +2614,10 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 		consume_skb(skb);
 		skb = NULL;
 	} else {
+		struct sk_buff *unlinked_skb = NULL;
+
+		spin_lock(&sk->sk_receive_queue.lock);
+
 		if (skb == u->oob_skb) {
 			if (copied) {
 				skb = NULL;
@@ -2619,13 +2629,19 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 			} else if (flags & MSG_PEEK) {
 				skb = NULL;
 			} else {
-				skb_unlink(skb, &sk->sk_receive_queue);
+				__skb_unlink(skb, &sk->sk_receive_queue);
 				WRITE_ONCE(u->oob_skb, NULL);
-				if (!WARN_ON_ONCE(skb_unref(skb)))
-					kfree_skb(skb);
+				unlinked_skb = skb;
 				skb = skb_peek(&sk->sk_receive_queue);
 			}
 		}
+
+		spin_unlock(&sk->sk_receive_queue.lock);
+
+		if (unlinked_skb) {
+			WARN_ON_ONCE(skb_unref(unlinked_skb));
+			kfree_skb(unlinked_skb);
+		}
 	}
 	return skb;
 }

net/unix/garbage.c

@@ -342,6 +342,18 @@ enum unix_recv_queue_lock_class {
 	U_RECVQ_LOCK_EMBRYO,
 };
 
+static void unix_collect_queue(struct unix_sock *u, struct sk_buff_head *hitlist)
+{
+	skb_queue_splice_init(&u->sk.sk_receive_queue, hitlist);
+
+#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
+	if (u->oob_skb) {
+		WARN_ON_ONCE(skb_unref(u->oob_skb));
+		u->oob_skb = NULL;
+	}
+#endif
+}
+
 static void unix_collect_skb(struct list_head *scc, struct sk_buff_head *hitlist)
 {
 	struct unix_vertex *vertex;
@@ -365,18 +377,11 @@ static void unix_collect_skb(struct list_head *scc, struct sk_buff_head *hitlist
 
 				/* listener -> embryo order, the inversion never happens. */
 				spin_lock_nested(&embryo_queue->lock, U_RECVQ_LOCK_EMBRYO);
-				skb_queue_splice_init(embryo_queue, hitlist);
+				unix_collect_queue(unix_sk(skb->sk), hitlist);
 				spin_unlock(&embryo_queue->lock);
 			}
 		} else {
-			skb_queue_splice_init(queue, hitlist);
-
-#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
-			if (u->oob_skb) {
-				kfree_skb(u->oob_skb);
-				u->oob_skb = NULL;
-			}
-#endif
+			unix_collect_queue(u, hitlist);
 		}
 
 		spin_unlock(&queue->lock);

tools/testing/selftests/drivers/net/stats.py

@@ -69,7 +69,7 @@ def pkt_byte_sum(cfg) -> None:
         return 0
 
     for _ in range(10):
-        rtstat = rtnl.getlink({"ifi-index": cfg.ifindex})['stats']
+        rtstat = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64']
         if stat_cmp(rtstat, qstat) < 0:
             raise Exception("RTNL stats are lower, fetched later")
         qstat = get_qstat(cfg)

tools/testing/selftests/net/af_unix/scm_rights.c

@@ -197,8 +197,8 @@ void __send_fd(struct __test_metadata *_metadata,
 	       const FIXTURE_VARIANT(scm_rights) *variant,
 	       int inflight, int receiver)
 {
-#define MSG "nop"
-#define MSGLEN 3
+#define MSG "x"
+#define MSGLEN 1
 	struct {
 		struct cmsghdr cmsghdr;
 		int fd[2];

tools/testing/selftests/net/amt.sh

@@ -77,6 +77,7 @@ readonly LISTENER=$(mktemp -u listener-XXXXXXXX)
 readonly GATEWAY=$(mktemp -u gateway-XXXXXXXX)
 readonly RELAY=$(mktemp -u relay-XXXXXXXX)
 readonly SOURCE=$(mktemp -u source-XXXXXXXX)
+readonly SMCROUTEDIR="$(mktemp -d)"
 ERR=4
 err=0
 
@@ -85,6 +86,11 @@ exit_cleanup()
 	for ns in "$@"; do
 		ip netns delete "${ns}" 2>/dev/null || true
 	done
+	if [ -f "$SMCROUTEDIR/amt.pid" ]; then
+		smcpid=$(< $SMCROUTEDIR/amt.pid)
+		kill $smcpid
+	fi
+	rm -rf $SMCROUTEDIR
 
 	exit $ERR
 }
@@ -167,7 +173,7 @@ setup_iptables()
 
 setup_mcast_routing()
 {
-	ip netns exec "${RELAY}" smcrouted
+	ip netns exec "${RELAY}" smcrouted -P $SMCROUTEDIR/amt.pid
 	ip netns exec "${RELAY}" smcroutectl a relay_src \
 		172.17.0.2 239.0.0.1 amtr
 	ip netns exec "${RELAY}" smcroutectl a relay_src \

tools/testing/selftests/net/arp_ndisc_untracked_subnets.sh

@@ -73,25 +73,19 @@ setup_v6() {
 	# namespaces. veth0 is veth-router, veth1 is veth-host.
 	# first, set up the inteface's link to the namespace
 	# then, set the interface "up"
-	ip -6 -netns ${ROUTER_NS_V6} link add name ${ROUTER_INTF} \
-		type veth peer name ${HOST_INTF}
-
-	ip -6 -netns ${ROUTER_NS_V6} link set dev ${ROUTER_INTF} up
-	ip -6 -netns ${ROUTER_NS_V6} link set dev ${HOST_INTF} netns \
-		${HOST_NS_V6}
+	ip -n ${ROUTER_NS_V6} link add name ${ROUTER_INTF} \
+		type veth peer name ${HOST_INTF} netns ${HOST_NS_V6}
 
-	ip -6 -netns ${HOST_NS_V6} link set dev ${HOST_INTF} up
-	ip -6 -netns ${ROUTER_NS_V6} addr add \
-		${ROUTER_ADDR_V6}/${PREFIX_WIDTH_V6} dev ${ROUTER_INTF} nodad
+	# Add tc rule to filter out host na message
+	tc -n ${ROUTER_NS_V6} qdisc add dev ${ROUTER_INTF} clsact
+	tc -n ${ROUTER_NS_V6} filter add dev ${ROUTER_INTF} \
+		ingress protocol ipv6 pref 1 handle 101 \
+		flower src_ip ${HOST_ADDR_V6} ip_proto icmpv6 type 136 skip_hw action pass
 
 	HOST_CONF=net.ipv6.conf.${HOST_INTF}
 	ip netns exec ${HOST_NS_V6} sysctl -qw ${HOST_CONF}.ndisc_notify=1
 	ip netns exec ${HOST_NS_V6} sysctl -qw ${HOST_CONF}.disable_ipv6=0
-	ip -6 -netns ${HOST_NS_V6} addr add ${HOST_ADDR_V6}/${PREFIX_WIDTH_V6} \
-		dev ${HOST_INTF}
-
 	ROUTER_CONF=net.ipv6.conf.${ROUTER_INTF}
-
 	ip netns exec ${ROUTER_NS_V6} sysctl -w \
 		${ROUTER_CONF}.forwarding=1 >/dev/null 2>&1
 	ip netns exec ${ROUTER_NS_V6} sysctl -w \
@@ -99,6 +93,13 @@ setup_v6() {
 	ip netns exec ${ROUTER_NS_V6} sysctl -w \
 		${ROUTER_CONF}.accept_untracked_na=${accept_untracked_na} \
 		>/dev/null 2>&1
+
+	ip -n ${ROUTER_NS_V6} link set dev ${ROUTER_INTF} up
+	ip -n ${HOST_NS_V6} link set dev ${HOST_INTF} up
+	ip -n ${ROUTER_NS_V6} addr add ${ROUTER_ADDR_V6}/${PREFIX_WIDTH_V6} \
+		dev ${ROUTER_INTF} nodad
+	ip -n ${HOST_NS_V6} addr add ${HOST_ADDR_V6}/${PREFIX_WIDTH_V6} \
+		dev ${HOST_INTF}
 	set +e
 }
 
@@ -162,26 +163,6 @@ arp_test_gratuitous_combinations() {
 	arp_test_gratuitous 2 1
 }
 
-cleanup_tcpdump() {
-	set -e
-	[[ ! -z  ${tcpdump_stdout} ]] && rm -f ${tcpdump_stdout}
-	[[ ! -z  ${tcpdump_stderr} ]] && rm -f ${tcpdump_stderr}
-	tcpdump_stdout=
-	tcpdump_stderr=
-	set +e
-}
-
-start_tcpdump() {
-	set -e
-	tcpdump_stdout=`mktemp`
-	tcpdump_stderr=`mktemp`
-	ip netns exec ${ROUTER_NS_V6} timeout 15s \
-		tcpdump --immediate-mode -tpni ${ROUTER_INTF} -c 1 \
-		"icmp6 && icmp6[0] == 136 && src ${HOST_ADDR_V6}" \
-		> ${tcpdump_stdout} 2> /dev/null
-	set +e
-}
-
 verify_ndisc() {
 	local accept_untracked_na=$1
 	local same_subnet=$2
@@ -222,8 +203,9 @@ ndisc_test_untracked_advertisements() {
 			HOST_ADDR_V6=2001:db8:abcd:0012::3
 		fi
 	fi
-	setup_v6 $1 $2
-	start_tcpdump
+	setup_v6 $1
+	slowwait_for_counter 15 1 \
+		tc_rule_handle_stats_get "dev ${ROUTER_INTF} ingress" 101 ".packets" "-n ${ROUTER_NS_V6}"
 
 	if verify_ndisc $1 $2; then
 		printf "    TEST: %-60s  [ OK ]\n" "${test_msg[*]}"
@@ -231,7 +213,6 @@ ndisc_test_untracked_advertisements() {
 		printf "    TEST: %-60s  [FAIL]\n" "${test_msg[*]}"
 	fi
 
-	cleanup_tcpdump
 	cleanup_v6
 	set +e
 }

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

@@ -129,14 +129,6 @@ fi
 
 source "$net_forwarding_dir/../lib.sh"
 
-# timeout in seconds
-slowwait()
-{
-	local timeout_sec=$1; shift
-
-	loopy_wait "sleep 0.1" "$((timeout_sec * 1000))" "$@"
-}
-
 ##############################################################################
 # Sanity checks
 
@@ -678,33 +670,6 @@ wait_for_trap()
 	"$@" | grep -q trap
 }
 
-until_counter_is()
-{
-	local expr=$1; shift
-	local current=$("$@")
-
-	echo $((current))
-	((current $expr))
-}
-
-busywait_for_counter()
-{
-	local timeout=$1; shift
-	local delta=$1; shift
-
-	local base=$("$@")
-	busywait "$timeout" until_counter_is ">= $((base + delta))" "$@"
-}
-
-slowwait_for_counter()
-{
-	local timeout=$1; shift
-	local delta=$1; shift
-
-	local base=$("$@")
-	slowwait "$timeout" until_counter_is ">= $((base + delta))" "$@"
-}
-
 setup_wait_dev()
 {
 	local dev=$1; shift
@@ -1023,29 +988,6 @@ link_stats_rx_errors_get()
 	link_stats_get $1 rx errors
 }
 
-tc_rule_stats_get()
-{
-	local dev=$1; shift
-	local pref=$1; shift
-	local dir=$1; shift
-	local selector=${1:-.packets}; shift
-
-	tc -j -s filter show dev $dev ${dir:-ingress} pref $pref \
-	    | jq ".[1].options.actions[].stats$selector"
-}
-
-tc_rule_handle_stats_get()
-{
-	local id=$1; shift
-	local handle=$1; shift
-	local selector=${1:-.packets}; shift
-	local netns=${1:-""}; shift
-
-	tc $netns -j -s filter show $id \
-	    | jq ".[] | select(.options.handle == $handle) | \
-		  .options.actions[0].stats$selector"
-}
-
 ethtool_stats_get()
 {
 	local dev=$1; shift

tools/testing/selftests/net/lib.sh

@@ -91,6 +91,41 @@ busywait()
 	loopy_wait : "$timeout_ms" "$@"
 }
 
+# timeout in seconds
+slowwait()
+{
+	local timeout_sec=$1; shift
+
+	loopy_wait "sleep 0.1" "$((timeout_sec * 1000))" "$@"
+}
+
+until_counter_is()
+{
+	local expr=$1; shift
+	local current=$("$@")
+
+	echo $((current))
+	((current $expr))
+}
+
+busywait_for_counter()
+{
+	local timeout=$1; shift
+	local delta=$1; shift
+
+	local base=$("$@")
+	busywait "$timeout" until_counter_is ">= $((base + delta))" "$@"
+}
+
+slowwait_for_counter()
+{
+	local timeout=$1; shift
+	local delta=$1; shift
+
+	local base=$("$@")
+	slowwait "$timeout" until_counter_is ">= $((base + delta))" "$@"
+}
+
 cleanup_ns()
 {
 	local ns=""
@@ -150,3 +185,26 @@ setup_ns()
 	done
 	NS_LIST="$NS_LIST $ns_list"
 }
+
+tc_rule_stats_get()
+{
+	local dev=$1; shift
+	local pref=$1; shift
+	local dir=$1; shift
+	local selector=${1:-.packets}; shift
+
+	tc -j -s filter show dev $dev ${dir:-ingress} pref $pref \
+	    | jq ".[1].options.actions[].stats$selector"
+}
+
+tc_rule_handle_stats_get()
+{
+	local id=$1; shift
+	local handle=$1; shift
+	local selector=${1:-.packets}; shift
+	local netns=${1:-""}; shift
+
+	tc $netns -j -s filter show $id \
+	    | jq ".[] | select(.options.handle == $handle) | \
+		  .options.actions[0].stats$selector"
+}