Merge tag 'net-5.16-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from.. Santa?

  No regressions on our radar at this point. The igc problem fixed here
  was the last one I was tracking but it was broken in previous
  releases, anyway. Mostly driver fixes and a couple of largish SMC
  fixes.

  Current release - regressions:

   - xsk: initialise xskb free_list_node, fixup for a -rc7 fix

  Current release - new code bugs:

   - mlx5: handful of minor fixes:

   - use first online CPU instead of hard coded CPU

   - fix some error handling paths in 'mlx5e_tc_add_fdb_flow()'

   - fix skb memory leak when TC classifier action offloads are disabled

   - fix memory leak with rules with internal OvS port

  Previous releases - regressions:

   - igc: do not enable crosstimestamping for i225-V models

  Previous releases - always broken:

   - udp: use datalen to cap ipv6 udp max gso segments

   - fix use-after-free in tw_timer_handler due to early free of stats

   - smc: fix kernel panic caused by race of smc_sock

   - smc: don't send CDC/LLC message if link not ready, avoid timeouts

   - sctp: use call_rcu to free endpoint, avoid UAF in sock diag

   - bridge: mcast: add and enforce query interval minimum

   - usb: pegasus: do not drop long Ethernet frames

   - mlx5e: fix ICOSQ recovery flow for XSK

   - nfc: uapi: use kernel size_t to fix user-space builds"

* tag 'net-5.16-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (47 commits)
  fsl/fman: Fix missing put_device() call in fman_port_probe
  selftests: net: using ping6 for IPv6 in udpgro_fwd.sh
  Documentation: fix outdated interpretation of ip_no_pmtu_disc
  net/ncsi: check for error return from call to nla_put_u32
  net: bridge: mcast: fix br_multicast_ctx_vlan_global_disabled helper
  net: fix use-after-free in tw_timer_handler
  selftests: net: Fix a typo in udpgro_fwd.sh
  selftests/net: udpgso_bench_tx: fix dst ip argument
  net: bridge: mcast: add and enforce startup query interval minimum
  net: bridge: mcast: add and enforce query interval minimum
  ipv6: raw: check passed optlen before reading
  xsk: Initialise xskb free_list_node
  net/mlx5e: Fix wrong features assignment in case of error
  net/mlx5e: TC, Fix memory leak with rules with internal port
  ionic: Initialize the 'lif->dbid_inuse' bitmap
  igc: Fix TX timestamp support for non-MSI-X platforms
  igc: Do not enable crosstimestamping for i225-V models
  net/smc: fix kernel panic caused by race of smc_sock
  net/smc: don't send CDC/LLC message if link not ready
  NFC: st21nfca: Fix memory leak in device probe and remove
  ...

58 files changed, 405 insertions, 237 deletions

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index c04431144f7a..2572eecc3e86 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -25,7 +25,8 @@ ip_default_ttl - INTEGER
 ip_no_pmtu_disc - INTEGER
 	Disable Path MTU Discovery. If enabled in mode 1 and a
 	fragmentation-required ICMP is received, the PMTU to this
-	destination will be set to min_pmtu (see below). You will need
+	destination will be set to the smallest of the old MTU to
+	this destination and min_pmtu (see below). You will need
 	to raise min_pmtu to the smallest interface MTU on your system
 	manually if you want to avoid locally generated fragments.
 
@@ -49,7 +50,8 @@ ip_no_pmtu_disc - INTEGER
 	Default: FALSE
 
 min_pmtu - INTEGER
-	default 552 - minimum discovered Path MTU
+	default 552 - minimum Path MTU. Unless this is changed mannually,
+	each cached pmtu will never be lower than this setting.
 
 ip_forward_use_pmtu - BOOLEAN
 	By default we don't trust protocol path MTUs while forwarding
diff --git a/drivers/isdn/mISDN/core.c b/drivers/isdn/mISDN/core.c
index 55891e420446..a41b4b264594 100644
--- a/drivers/isdn/mISDN/core.c
+++ b/drivers/isdn/mISDN/core.c
@@ -381,7 +381,7 @@ mISDNInit(void)
 	err = mISDN_inittimer(&debug);
 	if (err)
 		goto error2;
-	err = l1_init(&debug);
+	err = Isdnl1_Init(&debug);
 	if (err)
 		goto error3;
 	err = Isdnl2_Init(&debug);
@@ -395,7 +395,7 @@ mISDNInit(void)
 error5:
 	Isdnl2_cleanup();
 error4:
-	l1_cleanup();
+	Isdnl1_cleanup();
 error3:
 	mISDN_timer_cleanup();
 error2:
@@ -408,7 +408,7 @@ static void mISDN_cleanup(void)
 {
 	misdn_sock_cleanup();
 	Isdnl2_cleanup();
-	l1_cleanup();
+	Isdnl1_cleanup();
 	mISDN_timer_cleanup();
 	class_unregister(&mISDN_class);
 
diff --git a/drivers/isdn/mISDN/core.h b/drivers/isdn/mISDN/core.h
index 23b44d303327..42599f49c189 100644
--- a/drivers/isdn/mISDN/core.h
+++ b/drivers/isdn/mISDN/core.h
@@ -60,8 +60,8 @@ struct Bprotocol	*get_Bprotocol4id(u_int);
 extern int	mISDN_inittimer(u_int *);
 extern void	mISDN_timer_cleanup(void);
 
-extern int	l1_init(u_int *);
-extern void	l1_cleanup(void);
+extern int	Isdnl1_Init(u_int *);
+extern void	Isdnl1_cleanup(void);
 extern int	Isdnl2_Init(u_int *);
 extern void	Isdnl2_cleanup(void);
 
diff --git a/drivers/isdn/mISDN/layer1.c b/drivers/isdn/mISDN/layer1.c
index 98a3bc6c1700..7b31c25a550e 100644
--- a/drivers/isdn/mISDN/layer1.c
+++ b/drivers/isdn/mISDN/layer1.c
@@ -398,7 +398,7 @@ create_l1(struct dchannel *dch, dchannel_l1callback *dcb) {
 EXPORT_SYMBOL(create_l1);
 
 int
-l1_init(u_int *deb)
+Isdnl1_Init(u_int *deb)
 {
 	debug = deb;
 	l1fsm_s.state_count = L1S_STATE_COUNT;
@@ -409,7 +409,7 @@ l1_init(u_int *deb)
 }
 
 void
-l1_cleanup(void)
+Isdnl1_cleanup(void)
 {
 	mISDN_FsmFree(&l1fsm_s);
 }
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index 81b3756417ec..77e76c9efd32 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -366,6 +366,10 @@ int aq_ring_rx_clean(struct aq_ring_s *self,
 		if (!buff->is_eop) {
 			buff_ = buff;
 			do {
+				if (buff_->next >= self->size) {
+					err = -EIO;
+					goto err_exit;
+				}
 				next_ = buff_->next,
 				buff_ = &self->buff_ring[next_];
 				is_rsc_completed =
@@ -389,6 +393,10 @@ int aq_ring_rx_clean(struct aq_ring_s *self,
 			    (buff->is_lro && buff->is_cso_err)) {
 				buff_ = buff;
 				do {
+					if (buff_->next >= self->size) {
+						err = -EIO;
+						goto err_exit;
+					}
 					next_ = buff_->next,
 					buff_ = &self->buff_ring[next_];
 
diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index 88d2ab748399..4579ddf9c427 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -1913,15 +1913,12 @@ static int ag71xx_probe(struct platform_device *pdev)
 	ag->mac_reset = devm_reset_control_get(&pdev->dev, "mac");
 	if (IS_ERR(ag->mac_reset)) {
 		netif_err(ag, probe, ndev, "missing mac reset\n");
-		err = PTR_ERR(ag->mac_reset);
-		goto err_free;
+		return PTR_ERR(ag->mac_reset);
 	}
 
 	ag->mac_base = devm_ioremap(&pdev->dev, res->start, resource_size(res));
-	if (!ag->mac_base) {
-		err = -ENOMEM;
-		goto err_free;
-	}
+	if (!ag->mac_base)
+		return -ENOMEM;
 
 	ndev->irq = platform_get_irq(pdev, 0);
 	err = devm_request_irq(&pdev->dev, ndev->irq, ag71xx_interrupt,
@@ -1929,7 +1926,7 @@ static int ag71xx_probe(struct platform_device *pdev)
 	if (err) {
 		netif_err(ag, probe, ndev, "unable to request IRQ %d\n",
 			  ndev->irq);
-		goto err_free;
+		return err;
 	}
 
 	ndev->netdev_ops = &ag71xx_netdev_ops;
@@ -1957,10 +1954,8 @@ static int ag71xx_probe(struct platform_device *pdev)
 	ag->stop_desc = dmam_alloc_coherent(&pdev->dev,
 					    sizeof(struct ag71xx_desc),
 					    &ag->stop_desc_dma, GFP_KERNEL);
-	if (!ag->stop_desc) {
-		err = -ENOMEM;
-		goto err_free;
-	}
+	if (!ag->stop_desc)
+		return -ENOMEM;
 
 	ag->stop_desc->data = 0;
 	ag->stop_desc->ctrl = 0;
@@ -1975,7 +1970,7 @@ static int ag71xx_probe(struct platform_device *pdev)
 	err = of_get_phy_mode(np, &ag->phy_if_mode);
 	if (err) {
 		netif_err(ag, probe, ndev, "missing phy-mode property in DT\n");
-		goto err_free;
+		return err;
 	}
 
 	netif_napi_add(ndev, &ag->napi, ag71xx_poll, AG71XX_NAPI_WEIGHT);
@@ -1983,7 +1978,7 @@ static int ag71xx_probe(struct platform_device *pdev)
 	err = clk_prepare_enable(ag->clk_eth);
 	if (err) {
 		netif_err(ag, probe, ndev, "Failed to enable eth clk.\n");
-		goto err_free;
+		return err;
 	}
 
 	ag71xx_wr(ag, AG71XX_REG_MAC_CFG1, 0);
@@ -2019,8 +2014,6 @@ err_mdio_remove:
 	ag71xx_mdio_remove(ag);
 err_put_clk:
 	clk_disable_unprepare(ag->clk_eth);
-err_free:
-	free_netdev(ndev);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c
index d9baac0dbc7d..4c9d05c45c03 100644
--- a/drivers/net/ethernet/freescale/fman/fman_port.c
+++ b/drivers/net/ethernet/freescale/fman/fman_port.c
@@ -1805,7 +1805,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 	fman = dev_get_drvdata(&fm_pdev->dev);
 	if (!fman) {
 		err = -EINVAL;
-		goto return_err;
+		goto put_device;
 	}
 
 	err = of_property_read_u32(port_node, "cell-index", &val);
@@ -1813,7 +1813,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 		dev_err(port->dev, "%s: reading cell-index for %pOF failed\n",
 			__func__, port_node);
 		err = -EINVAL;
-		goto return_err;
+		goto put_device;
 	}
 	port_id = (u8)val;
 	port->dts_params.id = port_id;
@@ -1847,7 +1847,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 	}  else {
 		dev_err(port->dev, "%s: Illegal port type\n", __func__);
 		err = -EINVAL;
-		goto return_err;
+		goto put_device;
 	}
 
 	port->dts_params.type = port_type;
@@ -1861,7 +1861,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 			dev_err(port->dev, "%s: incorrect qman-channel-id\n",
 				__func__);
 			err = -EINVAL;
-			goto return_err;
+			goto put_device;
 		}
 		port->dts_params.qman_channel_id = qman_channel_id;
 	}
@@ -1871,7 +1871,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 		dev_err(port->dev, "%s: of_address_to_resource() failed\n",
 			__func__);
 		err = -ENOMEM;
-		goto return_err;
+		goto put_device;
 	}
 
 	port->dts_params.fman = fman;
@@ -1896,6 +1896,8 @@ static int fman_port_probe(struct platform_device *of_dev)
 
 	return 0;
 
+put_device:
+	put_device(&fm_pdev->dev);
 return_err:
 	of_node_put(port_node);
 free_port:
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 8e448288ee26..d28a80a00953 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -5467,6 +5467,9 @@ static irqreturn_t igc_intr_msi(int irq, void *data)
 			mod_timer(&adapter->watchdog_timer, jiffies + 1);
 	}
 
+	if (icr & IGC_ICR_TS)
+		igc_tsync_interrupt(adapter);
+
 	napi_schedule(&q_vector->napi);
 
 	return IRQ_HANDLED;
@@ -5510,6 +5513,9 @@ static irqreturn_t igc_intr(int irq, void *data)
 			mod_timer(&adapter->watchdog_timer, jiffies + 1);
 	}
 
+	if (icr & IGC_ICR_TS)
+		igc_tsync_interrupt(adapter);
+
 	napi_schedule(&q_vector->napi);
 
 	return IRQ_HANDLED;
diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index 30568e3544cd..4f9245aa79a1 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -768,7 +768,20 @@ int igc_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr)
  */
 static bool igc_is_crosststamp_supported(struct igc_adapter *adapter)
 {
-	return IS_ENABLED(CONFIG_X86_TSC) ? pcie_ptm_enabled(adapter->pdev) : false;
+	if (!IS_ENABLED(CONFIG_X86_TSC))
+		return false;
+
+	/* FIXME: it was noticed that enabling support for PCIe PTM in
+	 * some i225-V models could cause lockups when bringing the
+	 * interface up/down. There should be no downsides to
+	 * disabling crosstimestamping support for i225-V, as it
+	 * doesn't have any PTP support. That way we gain some time
+	 * while root causing the issue.
+	 */
+	if (adapter->pdev->device == IGC_DEV_ID_I225_V)
+		return false;
+
+	return pcie_ptm_enabled(adapter->pdev);
 }
 
 static struct system_counterval_t igc_device_tstamp_to_system(u64 tstamp)
diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c
index 96bd6f2b21ed..80bfaf2fec92 100644
--- a/drivers/net/ethernet/lantiq_xrx200.c
+++ b/drivers/net/ethernet/lantiq_xrx200.c
@@ -224,7 +224,7 @@ static int xrx200_hw_receive(struct xrx200_chan *ch)
 	skb->protocol = eth_type_trans(skb, net_dev);
 	netif_receive_skb(skb);
 	net_dev->stats.rx_packets++;
-	net_dev->stats.rx_bytes += len - ETH_FCS_LEN;
+	net_dev->stats.rx_bytes += len;
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index f0ac6b0d9653..b47a0d3ef22f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -783,6 +783,8 @@ struct mlx5e_channel {
 	DECLARE_BITMAP(state, MLX5E_CHANNEL_NUM_STATES);
 	int                        ix;
 	int                        cpu;
+	/* Sync between icosq recovery and XSK enable/disable. */
+	struct mutex               icosq_recovery_lock;
 };
 
 struct mlx5e_ptp;
@@ -1014,9 +1016,6 @@ int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param);
 void mlx5e_destroy_rq(struct mlx5e_rq *rq);
 
 struct mlx5e_sq_param;
-int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params,
-		     struct mlx5e_sq_param *param, struct mlx5e_icosq *sq);
-void mlx5e_close_icosq(struct mlx5e_icosq *sq);
 int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params,
 		     struct mlx5e_sq_param *param, struct xsk_buff_pool *xsk_pool,
 		     struct mlx5e_xdpsq *sq, bool is_redirect);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
index d5b7110a4265..0107e4e73bb0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
@@ -30,6 +30,8 @@ void mlx5e_reporter_rx_destroy(struct mlx5e_priv *priv);
 void mlx5e_reporter_icosq_cqe_err(struct mlx5e_icosq *icosq);
 void mlx5e_reporter_rq_cqe_err(struct mlx5e_rq *rq);
 void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq);
+void mlx5e_reporter_icosq_suspend_recovery(struct mlx5e_channel *c);
+void mlx5e_reporter_icosq_resume_recovery(struct mlx5e_channel *c);
 
 #define MLX5E_REPORTER_PER_Q_MAX_LEN 256
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h
index d6c7c81690eb..7c9dd3a75f8a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h
@@ -66,7 +66,7 @@ mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
 
 static inline void
 mlx5e_rep_tc_receive(struct mlx5_cqe64 *cqe, struct mlx5e_rq *rq,
-		     struct sk_buff *skb) {}
+		     struct sk_buff *skb) { napi_gro_receive(rq->cq.napi, skb); }
 
 #endif /* CONFIG_MLX5_CLS_ACT */
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
index 74086eb556ae..2684e9da9f41 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
@@ -62,6 +62,7 @@ static void mlx5e_reset_icosq_cc_pc(struct mlx5e_icosq *icosq)
 
 static int mlx5e_rx_reporter_err_icosq_cqe_recover(void *ctx)
 {
+	struct mlx5e_rq *xskrq = NULL;
 	struct mlx5_core_dev *mdev;
 	struct mlx5e_icosq *icosq;
 	struct net_device *dev;
@@ -70,7 +71,13 @@ static int mlx5e_rx_reporter_err_icosq_cqe_recover(void *ctx)
 	int err;
 
 	icosq = ctx;
+
+	mutex_lock(&icosq->channel->icosq_recovery_lock);
+
+	/* mlx5e_close_rq cancels this work before RQ and ICOSQ are killed. */
 	rq = &icosq->channel->rq;
+	if (test_bit(MLX5E_RQ_STATE_ENABLED, &icosq->channel->xskrq.state))
+		xskrq = &icosq->channel->xskrq;
 	mdev = icosq->channel->mdev;
 	dev = icosq->channel->netdev;
 	err = mlx5_core_query_sq_state(mdev, icosq->sqn, &state);
@@ -84,6 +91,9 @@ static int mlx5e_rx_reporter_err_icosq_cqe_recover(void *ctx)
 		goto out;
 
 	mlx5e_deactivate_rq(rq);
+	if (xskrq)
+		mlx5e_deactivate_rq(xskrq);
+
 	err = mlx5e_wait_for_icosq_flush(icosq);
 	if (err)
 		goto out;
@@ -97,15 +107,28 @@ static int mlx5e_rx_reporter_err_icosq_cqe_recover(void *ctx)
 		goto out;
 
 	mlx5e_reset_icosq_cc_pc(icosq);
+
 	mlx5e_free_rx_in_progress_descs(rq);
+	if (xskrq)
+		mlx5e_free_rx_in_progress_descs(xskrq);
+
 	clear_bit(MLX5E_SQ_STATE_RECOVERING, &icosq->state);
 	mlx5e_activate_icosq(icosq);
-	mlx5e_activate_rq(rq);
 
+	mlx5e_activate_rq(rq);
 	rq->stats->recover++;
+
+	if (xskrq) {
+		mlx5e_activate_rq(xskrq);
+		xskrq->stats->recover++;
+	}
+
+	mutex_unlock(&icosq->channel->icosq_recovery_lock);
+
 	return 0;
 out:
 	clear_bit(MLX5E_SQ_STATE_RECOVERING, &icosq->state);
+	mutex_unlock(&icosq->channel->icosq_recovery_lock);
 	return err;
 }
 
@@ -706,6 +729,16 @@ void mlx5e_reporter_icosq_cqe_err(struct mlx5e_icosq *icosq)
 	mlx5e_health_report(priv, priv->rx_reporter, err_str, &err_ctx);
 }
 
+void mlx5e_reporter_icosq_suspend_recovery(struct mlx5e_channel *c)
+{
+	mutex_lock(&c->icosq_recovery_lock);
+}
+
+void mlx5e_reporter_icosq_resume_recovery(struct mlx5e_channel *c)
+{
+	mutex_unlock(&c->icosq_recovery_lock);
+}
+
 static const struct devlink_health_reporter_ops mlx5_rx_reporter_ops = {
 	.name = "rx",
 	.recover = mlx5e_rx_reporter_recover,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 4f4bc8726ec4..614cd9477600 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -466,6 +466,14 @@ static int mlx5e_tx_reporter_dump_sq(struct mlx5e_priv *priv, struct devlink_fms
 	return mlx5e_health_fmsg_named_obj_nest_end(fmsg);
 }
 
+static int mlx5e_tx_reporter_timeout_dump(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg,
+					  void *ctx)
+{
+	struct mlx5e_tx_timeout_ctx *to_ctx = ctx;
+
+	return mlx5e_tx_reporter_dump_sq(priv, fmsg, to_ctx->sq);
+}
+
 static int mlx5e_tx_reporter_dump_all_sqs(struct mlx5e_priv *priv,
 					  struct devlink_fmsg *fmsg)
 {
@@ -561,7 +569,7 @@ int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq)
 	to_ctx.sq = sq;
 	err_ctx.ctx = &to_ctx;
 	err_ctx.recover = mlx5e_tx_reporter_timeout_recover;
-	err_ctx.dump = mlx5e_tx_reporter_dump_sq;
+	err_ctx.dump = mlx5e_tx_reporter_timeout_dump;
 	snprintf(err_str, sizeof(err_str),
 		 "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u",
 		 sq->ch_ix, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
index 538bc2419bd8..8526a5fbbf0b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -4,6 +4,7 @@
 #include "setup.h"
 #include "en/params.h"
 #include "en/txrx.h"
+#include "en/health.h"
 
 /* It matches XDP_UMEM_MIN_CHUNK_SIZE, but as this constant is private and may
  * change unexpectedly, and mlx5e has a minimum valid stride size for striding
@@ -170,7 +171,13 @@ void mlx5e_close_xsk(struct mlx5e_channel *c)
 
 void mlx5e_activate_xsk(struct mlx5e_channel *c)
 {
+	/* ICOSQ recovery deactivates RQs. Suspend the recovery to avoid
+	 * activating XSKRQ in the middle of recovery.
+	 */
+	mlx5e_reporter_icosq_suspend_recovery(c);
 	set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state);
+	mlx5e_reporter_icosq_resume_recovery(c);
+
 	/* TX queue is created active. */
 
 	spin_lock_bh(&c->async_icosq_lock);
@@ -180,6 +187,13 @@ void mlx5e_activate_xsk(struct mlx5e_channel *c)
 
 void mlx5e_deactivate_xsk(struct mlx5e_channel *c)
 {
-	mlx5e_deactivate_rq(&c->xskrq);
+	/* ICOSQ recovery may reactivate XSKRQ if clear_bit is called in the
+	 * middle of recovery. Suspend the recovery to avoid it.
+	 */
+	mlx5e_reporter_icosq_suspend_recovery(c);
+	clear_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state);
+	mlx5e_reporter_icosq_resume_recovery(c);
+	synchronize_net(); /* Sync with NAPI to prevent mlx5e_post_rx_wqes. */
+
 	/* TX queue is disabled on close. */
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 65571593ec5c..41379844eee1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1087,8 +1087,6 @@ void mlx5e_deactivate_rq(struct mlx5e_rq *rq)
 void mlx5e_close_rq(struct mlx5e_rq *rq)
 {
 	cancel_work_sync(&rq->dim.work);
-	if (rq->icosq)
-		cancel_work_sync(&rq->icosq->recover_work);
 	cancel_work_sync(&rq->recover_work);
 	mlx5e_destroy_rq(rq);
 	mlx5e_free_rx_descs(rq);
@@ -1216,9 +1214,20 @@ static void mlx5e_icosq_err_cqe_work(struct work_struct *recover_work)
 	mlx5e_reporter_icosq_cqe_err(sq);
 }
 
+static void mlx5e_async_icosq_err_cqe_work(struct work_struct *recover_work)
+{
+	struct mlx5e_icosq *sq = container_of(recover_work, struct mlx5e_icosq,
+					      recover_work);
+
+	/* Not implemented yet. */
+
+	netdev_warn(sq->channel->netdev, "async_icosq recovery is not implemented\n");
+}
+
 static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
 			     struct mlx5e_sq_param *param,
-			     struct mlx5e_icosq *sq)
+			     struct mlx5e_icosq *sq,
+			     work_func_t recover_work_func)
 {
 	void *sqc_wq               = MLX5_ADDR_OF(sqc, param->sqc, wq);
 	struct mlx5_core_dev *mdev = c->mdev;
@@ -1239,7 +1248,7 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
 	if (err)
 		goto err_sq_wq_destroy;
 
-	INIT_WORK(&sq->recover_work, mlx5e_icosq_err_cqe_work);
+	INIT_WORK(&sq->recover_work, recover_work_func);
 
 	return 0;
 
@@ -1575,13 +1584,14 @@ void mlx5e_tx_err_cqe_work(struct work_struct *recover_work)
 	mlx5e_reporter_tx_err_cqe(sq);
 }
 
-int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params,
-		     struct mlx5e_sq_param *param, struct mlx5e_icosq *sq)
+static int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params,
+			    struct mlx5e_sq_param *param, struct mlx5e_icosq *sq,
+			    work_func_t recover_work_func)
 {
 	struct mlx5e_create_sq_param csp = {};
 	int err;
 
-	err = mlx5e_alloc_icosq(c, param, sq);
+	err = mlx5e_alloc_icosq(c, param, sq, recover_work_func);
 	if (err)
 		return err;
 
@@ -1620,7 +1630,7 @@ void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq)
 	synchronize_net(); /* Sync with NAPI. */
 }
 
-void mlx5e_close_icosq(struct mlx5e_icosq *sq)
+static void mlx5e_close_icosq(struct mlx5e_icosq *sq)
 {
 	struct mlx5e_channel *c = sq->channel;
 
@@ -2084,11 +2094,15 @@ static int mlx5e_open_queues(struct mlx5e_channel *c,
 
 	spin_lock_init(&c->async_icosq_lock);
 
-	err = mlx5e_open_icosq(c, params, &cparam->async_icosq, &c->async_icosq);
+	err = mlx5e_open_icosq(c, params, &cparam->async_icosq, &c->async_icosq,
+			       mlx5e_async_icosq_err_cqe_work);
 	if (err)
 		goto err_close_xdpsq_cq;
 
-	err = mlx5e_open_icosq(c, params, &cparam->icosq, &c->icosq);
+	mutex_init(&c->icosq_recovery_lock);
+
+	err = mlx5e_open_icosq(c, params, &cparam->icosq, &c->icosq,
+			       mlx5e_icosq_err_cqe_work);
 	if (err)
 		goto err_close_async_icosq;
 
@@ -2156,9 +2170,12 @@ static void mlx5e_close_queues(struct mlx5e_channel *c)
 	mlx5e_close_xdpsq(&c->xdpsq);
 	if (c->xdp)
 		mlx5e_close_xdpsq(&c->rq_xdpsq);
+	/* The same ICOSQ is used for UMRs for both RQ and XSKRQ. */
+	cancel_work_sync(&c->icosq.recover_work);
 	mlx5e_close_rq(&c->rq);
 	mlx5e_close_sqs(c);
 	mlx5e_close_icosq(&c->icosq);
+	mutex_destroy(&c->icosq_recovery_lock);
 	mlx5e_close_icosq(&c->async_icosq);
 	if (c->xdp)
 		mlx5e_close_cq(&c->rq_xdpsq.cq);
@@ -3724,12 +3741,11 @@ static int set_feature_arfs(struct net_device *netdev, bool enable)
 
 static int mlx5e_handle_feature(struct net_device *netdev,
 				netdev_features_t *features,
-				netdev_features_t wanted_features,
 				netdev_features_t feature,
 				mlx5e_feature_handler feature_handler)
 {
-	netdev_features_t changes = wanted_features ^ netdev->features;
-	bool enable = !!(wanted_features & feature);
+	netdev_features_t changes = *features ^ netdev->features;
+	bool enable = !!(*features & feature);
 	int err;
 
 	if (!(changes & feature))
@@ -3737,22 +3753,22 @@ static int mlx5e_handle_feature(struct net_device *netdev,
 
 	err = feature_handler(netdev, enable);
 	if (err) {
+		MLX5E_SET_FEATURE(features, feature, !enable);
 		netdev_err(netdev, "%s feature %pNF failed, err %d\n",
 			   enable ? "Enable" : "Disable", &feature, err);
 		return err;
 	}
 
-	MLX5E_SET_FEATURE(features, feature, enable);
 	return 0;
 }
 
 int mlx5e_set_features(struct net_device *netdev, netdev_features_t features)
 {
-	netdev_features_t oper_features = netdev->features;
+	netdev_features_t oper_features = features;
 	int err = 0;
 
 #define MLX5E_HANDLE_FEATURE(feature, handler) \
-	mlx5e_handle_feature(netdev, &oper_features, features, feature, handler)
+	mlx5e_handle_feature(netdev, &oper_features, feature, handler)
 
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_LRO, set_feature_lro);
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_GRO_HW, set_feature_hw_gro);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 3d45f4ae80c0..5e454a14428f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1196,21 +1196,16 @@ void mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw,
 	if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH)
 		goto offload_rule_0;
 
-	if (flow_flag_test(flow, CT)) {
-		mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), flow, attr);
-		return;
-	}
-
-	if (flow_flag_test(flow, SAMPLE)) {
-		mlx5e_tc_sample_unoffload(get_sample_priv(flow->priv), flow->rule[0], attr);
-		return;
-	}
-
 	if (attr->esw_attr->split_count)
 		mlx5_eswitch_del_fwd_rule(esw, flow->rule[1], attr);
 
+	if (flow_flag_test(flow, CT))
+		mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), flow, attr);
+	else if (flow_flag_test(flow, SAMPLE))
+		mlx5e_tc_sample_unoffload(get_sample_priv(flow->priv), flow->rule[0], attr);
+	else
 offload_rule_0:
-	mlx5_eswitch_del_offloaded_rule(esw, flow->rule[0], attr);
+		mlx5_eswitch_del_offloaded_rule(esw, flow->rule[0], attr);
 }
 
 struct mlx5_flow_handle *
@@ -1445,7 +1440,9 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 							MLX5_FLOW_NAMESPACE_FDB, VPORT_TO_REG,
 							metadata);
 			if (err)
-				return err;
+				goto err_out;
+
+			attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
 		}
 	}
 
@@ -1461,13 +1458,15 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 		if (attr->chain) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Internal port rule is only supported on chain 0");
-			return -EOPNOTSUPP;
+			err = -EOPNOTSUPP;
+			goto err_out;
 		}
 
 		if (attr->dest_chain) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Internal port rule offload doesn't support goto action");
-			return -EOPNOTSUPP;
+			err = -EOPNOTSUPP;
+			goto err_out;
 		}
 
 		int_port = mlx5e_tc_int_port_get(mlx5e_get_int_port_priv(priv),
@@ -1475,8 +1474,10 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 						 flow_flag_test(flow, EGRESS) ?
 						 MLX5E_TC_INT_PORT_EGRESS :
 						 MLX5E_TC_INT_PORT_INGRESS);
-		if (IS_ERR(int_port))
-			return PTR_ERR(int_port);
+		if (IS_ERR(int_port)) {
+			err = PTR_ERR(int_port);
+			goto err_out;
+		}
 
 		esw_attr->int_port = int_port;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
index 97e5845b4cfd..d5e47630e284 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
@@ -121,6 +121,9 @@ u32 mlx5_chains_get_nf_ft_chain(struct mlx5_fs_chains *chains)
 
 u32 mlx5_chains_get_prio_range(struct mlx5_fs_chains *chains)
 {
+	if (!mlx5_chains_prios_supported(chains))
+		return 1;
+
 	if (mlx5_chains_ignore_flow_level_supported(chains))
 		return UINT_MAX;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 7df9c7f8d9c8..65083496f913 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1809,12 +1809,13 @@ void mlx5_disable_device(struct mlx5_core_dev *dev)
 
 int mlx5_recover_device(struct mlx5_core_dev *dev)
 {
-	int ret = -EIO;
+	if (!mlx5_core_is_sf(dev)) {
+		mlx5_pci_disable_device(dev);
+		if (mlx5_pci_slot_reset(dev->pdev) != PCI_ERS_RESULT_RECOVERED)
+			return -EIO;
+	}
 
-	mlx5_pci_disable_device(dev);
-	if (mlx5_pci_slot_reset(dev->pdev) == PCI_ERS_RESULT_RECOVERED)
-		ret = mlx5_load_one(dev);
-	return ret;
+	return mlx5_load_one(dev);
 }
 
 static struct pci_driver mlx5_core_driver = {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index 830444f927d4..bcee30f5de0a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -356,8 +356,8 @@ static struct mlx5_irq *irq_pool_request_affinity(struct mlx5_irq_pool *pool,
 	new_irq = irq_pool_create_irq(pool, affinity);
 	if (IS_ERR(new_irq)) {
 		if (!least_loaded_irq) {
-			mlx5_core_err(pool->dev, "Didn't find IRQ for cpu = %u\n",
-				      cpumask_first(affinity));
+			mlx5_core_err(pool->dev, "Didn't find a matching IRQ. err = %ld\n",
+				      PTR_ERR(new_irq));
 			mutex_unlock(&pool->lock);
 			return new_irq;
 		}
@@ -398,7 +398,7 @@ irq_pool_request_vector(struct mlx5_irq_pool *pool, int vecidx,
 	cpumask_copy(irq->mask, affinity);
 	if (!irq_pool_is_sf_pool(pool) && !pool->xa_num_irqs.max &&
 	    cpumask_empty(irq->mask))
-		cpumask_set_cpu(0, irq->mask);
+		cpumask_set_cpu(cpumask_first(cpu_online_mask), irq->mask);
 	irq_set_affinity_hint(irq->irqn, irq->mask);
 unlock:
 	mutex_unlock(&pool->lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
index 8cbd36c82b3b..c54cc45f63dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2019 Mellanox Technologies. */
 
 #include <linux/mlx5/eswitch.h>
+#include <linux/err.h>
 #include "dr_types.h"
 
 #define DR_DOMAIN_SW_STEERING_SUPPORTED(dmn, dmn_type)	\
@@ -72,9 +73,9 @@ static int dr_domain_init_resources(struct mlx5dr_domain *dmn)
 	}
 
 	dmn->uar = mlx5_get_uars_page(dmn->mdev);
-	if (!dmn->uar) {
+	if (IS_ERR(dmn->uar)) {
 		mlx5dr_err(dmn, "Couldn't allocate UAR\n");
-		ret = -ENOMEM;
+		ret = PTR_ERR(dmn->uar);
 		goto clean_pd;
 	}
 
@@ -163,9 +164,7 @@ static int dr_domain_query_vport(struct mlx5dr_domain *dmn,
 
 static int dr_domain_query_esw_mngr(struct mlx5dr_domain *dmn)
 {
-	return dr_domain_query_vport(dmn,
-				     dmn->info.caps.is_ecpf ? MLX5_VPORT_ECPF : 0,
-				     false,
+	return dr_domain_query_vport(dmn, 0, false,
 				     &dmn->info.caps.vports.esw_manager_caps);
 }
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 63f8a8163b5f..2ff7be17e5af 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -3135,7 +3135,7 @@ int ionic_lif_init(struct ionic_lif *lif)
 		return -EINVAL;
 	}
 
-	lif->dbid_inuse = bitmap_alloc(lif->dbid_count, GFP_KERNEL);
+	lif->dbid_inuse = bitmap_zalloc(lif->dbid_count, GFP_KERNEL);
 	if (!lif->dbid_inuse) {
 		dev_err(dev, "Failed alloc doorbell id bitmap, aborting\n");
 		return -ENOMEM;
diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c
index c65fb5f5d2dc..a0c256bd5441 100644
--- a/drivers/net/phy/fixed_phy.c
+++ b/drivers/net/phy/fixed_phy.c
@@ -239,8 +239,8 @@ static struct phy_device *__fixed_phy_register(unsigned int irq,
 	/* Check if we have a GPIO associated with this fixed phy */
 	if (!gpiod) {
 		gpiod = fixed_phy_get_gpiod(np);
-		if (IS_ERR(gpiod))
-			return ERR_CAST(gpiod);
+		if (!gpiod)
+			return ERR_PTR(-EINVAL);
 	}
 
 	/* Get the next available PHY address, up to PHY_MAX_ADDR */
diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c
index c4cd40b090fd..feb247e355f7 100644
--- a/drivers/net/usb/pegasus.c
+++ b/drivers/net/usb/pegasus.c
@@ -493,11 +493,11 @@ static void read_bulk_callback(struct urb *urb)
 		goto goon;
 
 	rx_status = buf[count - 2];
-	if (rx_status & 0x1e) {
+	if (rx_status & 0x1c) {
 		netif_dbg(pegasus, rx_err, net,
 			  "RX packet error %x\n", rx_status);
 		net->stats.rx_errors++;
-		if (rx_status & 0x06)	/* long or runt	*/
+		if (rx_status & 0x04)	/* runt	*/
 			net->stats.rx_length_errors++;
 		if (rx_status & 0x08)
 			net->stats.rx_crc_errors++;
diff --git a/drivers/nfc/st21nfca/i2c.c b/drivers/nfc/st21nfca/i2c.c
index f126ce96a7df..35b32fb90906 100644
--- a/drivers/nfc/st21nfca/i2c.c
+++ b/drivers/nfc/st21nfca/i2c.c
@@ -524,7 +524,8 @@ static int st21nfca_hci_i2c_probe(struct i2c_client *client,
 	phy->gpiod_ena = devm_gpiod_get(dev, "enable", GPIOD_OUT_LOW);
 	if (IS_ERR(phy->gpiod_ena)) {
 		nfc_err(dev, "Unable to get ENABLE GPIO\n");
-		return PTR_ERR(phy->gpiod_ena);
+		r = PTR_ERR(phy->gpiod_ena);
+		goto out_free;
 	}
 
 	phy->se_status.is_ese_present =
@@ -535,7 +536,7 @@ static int st21nfca_hci_i2c_probe(struct i2c_client *client,
 	r = st21nfca_hci_platform_init(phy);
 	if (r < 0) {
 		nfc_err(&client->dev, "Unable to reboot st21nfca\n");
-		return r;
+		goto out_free;
 	}
 
 	r = devm_request_threaded_irq(&client->dev, client->irq, NULL,
@@ -544,15 +545,23 @@ static int st21nfca_hci_i2c_probe(struct i2c_client *client,
 				ST21NFCA_HCI_DRIVER_NAME, phy);
 	if (r < 0) {
 		nfc_err(&client->dev, "Unable to register IRQ handler\n");
-		return r;
+		goto out_free;
 	}
 
-	return st21nfca_hci_probe(phy, &i2c_phy_ops, LLC_SHDLC_NAME,
-					ST21NFCA_FRAME_HEADROOM,
-					ST21NFCA_FRAME_TAILROOM,
-					ST21NFCA_HCI_LLC_MAX_PAYLOAD,
-					&phy->hdev,
-					&phy->se_status);
+	r = st21nfca_hci_probe(phy, &i2c_phy_ops, LLC_SHDLC_NAME,
+			       ST21NFCA_FRAME_HEADROOM,
+			       ST21NFCA_FRAME_TAILROOM,
+			       ST21NFCA_HCI_LLC_MAX_PAYLOAD,
+			       &phy->hdev,
+			       &phy->se_status);
+	if (r)
+		goto out_free;
+
+	return 0;
+
+out_free:
+	kfree_skb(phy->pending_skb);
+	return r;
 }
 
 static int st21nfca_hci_i2c_remove(struct i2c_client *client)
@@ -563,6 +572,8 @@ static int st21nfca_hci_i2c_remove(struct i2c_client *client)
 
 	if (phy->powered)
 		st21nfca_hci_i2c_disable(phy);
+	if (phy->pending_skb)
+		kfree_skb(phy->pending_skb);
 
 	return 0;
 }
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 189fdb9db162..d314a180ab93 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -105,6 +105,7 @@ extern struct percpu_counter sctp_sockets_allocated;
 int sctp_asconf_mgmt(struct sctp_sock *, struct sctp_sockaddr_entry *);
 struct sk_buff *sctp_skb_recv_datagram(struct sock *, int, int, int *);
 
+typedef int (*sctp_callback_t)(struct sctp_endpoint *, struct sctp_transport *, void *);
 void sctp_transport_walk_start(struct rhashtable_iter *iter);
 void sctp_transport_walk_stop(struct rhashtable_iter *iter);
 struct sctp_transport *sctp_transport_get_next(struct net *net,
@@ -115,9 +116,8 @@ int sctp_transport_lookup_process(int (*cb)(struct sctp_transport *, void *),
 				  struct net *net,
 				  const union sctp_addr *laddr,
 				  const union sctp_addr *paddr, void *p);
-int sctp_for_each_transport(int (*cb)(struct sctp_transport *, void *),
-			    int (*cb_done)(struct sctp_transport *, void *),
-			    struct net *net, int *pos, void *p);
+int sctp_transport_traverse_process(sctp_callback_t cb, sctp_callback_t cb_done,
+				    struct net *net, int *pos, void *p);
 int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *), void *p);
 int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc,
 		       struct sctp_info *info);
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 899c29c326ba..8dabd8800006 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1355,6 +1355,7 @@ struct sctp_endpoint {
 	      reconf_enable:1;
 
 	__u8  strreset_enable;
+	struct rcu_head rcu;
 };
 
 /* Recover the outter endpoint structure. */
@@ -1370,7 +1371,7 @@ static inline struct sctp_endpoint *sctp_ep(struct sctp_ep_common *base)
 struct sctp_endpoint *sctp_endpoint_new(struct sock *, gfp_t);
 void sctp_endpoint_free(struct sctp_endpoint *);
 void sctp_endpoint_put(struct sctp_endpoint *);
-void sctp_endpoint_hold(struct sctp_endpoint *);
+int sctp_endpoint_hold(struct sctp_endpoint *ep);
 void sctp_endpoint_add_asoc(struct sctp_endpoint *, struct sctp_association *);
 struct sctp_association *sctp_endpoint_lookup_assoc(
 	const struct sctp_endpoint *ep,
diff --git a/include/uapi/linux/nfc.h b/include/uapi/linux/nfc.h
index f6e3c8c9c744..4fa4e979e948 100644
--- a/include/uapi/linux/nfc.h
+++ b/include/uapi/linux/nfc.h
@@ -263,7 +263,7 @@ enum nfc_sdp_attr {
 #define NFC_SE_ENABLED  0x1
 
 struct sockaddr_nfc {
-	sa_family_t sa_family;
+	__kernel_sa_family_t sa_family;
 	__u32 dev_idx;
 	__u32 target_idx;
 	__u32 nfc_protocol;
@@ -271,14 +271,14 @@ struct sockaddr_nfc {
 
 #define NFC_LLCP_MAX_SERVICE_NAME 63
 struct sockaddr_nfc_llcp {
-	sa_family_t sa_family;
+	__kernel_sa_family_t sa_family;
 	__u32 dev_idx;
 	__u32 target_idx;
 	__u32 nfc_protocol;
 	__u8 dsap; /* Destination SAP, if known */
 	__u8 ssap; /* Source SAP to be bound to */
 	char service_name[NFC_LLCP_MAX_SERVICE_NAME]; /* Service name URI */;
-	size_t service_name_len;
+	__kernel_size_t service_name_len;
 };
 
 /* NFC socket protocols */
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index f3d751105343..de2409889489 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -4522,6 +4522,38 @@ int br_multicast_set_mld_version(struct net_bridge_mcast *brmctx,
 }
 #endif
 
+void br_multicast_set_query_intvl(struct net_bridge_mcast *brmctx,
+				  unsigned long val)
+{
+	unsigned long intvl_jiffies = clock_t_to_jiffies(val);
+
+	if (intvl_jiffies < BR_MULTICAST_QUERY_INTVL_MIN) {
+		br_info(brmctx->br,
+			"trying to set multicast query interval below minimum, setting to %lu (%ums)\n",
+			jiffies_to_clock_t(BR_MULTICAST_QUERY_INTVL_MIN),
+			jiffies_to_msecs(BR_MULTICAST_QUERY_INTVL_MIN));
+		intvl_jiffies = BR_MULTICAST_QUERY_INTVL_MIN;
+	}
+
+	brmctx->multicast_query_interval = intvl_jiffies;
+}
+
+void br_multicast_set_startup_query_intvl(struct net_bridge_mcast *brmctx,
+					  unsigned long val)
+{
+	unsigned long intvl_jiffies = clock_t_to_jiffies(val);
+
+	if (intvl_jiffies < BR_MULTICAST_STARTUP_QUERY_INTVL_MIN) {
+		br_info(brmctx->br,
+			"trying to set multicast startup query interval below minimum, setting to %lu (%ums)\n",
+			jiffies_to_clock_t(BR_MULTICAST_STARTUP_QUERY_INTVL_MIN),
+			jiffies_to_msecs(BR_MULTICAST_STARTUP_QUERY_INTVL_MIN));
+		intvl_jiffies = BR_MULTICAST_STARTUP_QUERY_INTVL_MIN;
+	}
+
+	brmctx->multicast_startup_query_interval = intvl_jiffies;
+}
+
 /**
  * br_multicast_list_adjacent - Returns snooped multicast addresses
  * @dev:	The bridge port adjacent to which to retrieve addresses
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 0c8b5f1a15bc..2ff83d84230d 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -1357,7 +1357,7 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
 	if (data[IFLA_BR_MCAST_QUERY_INTVL]) {
 		u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERY_INTVL]);
 
-		br->multicast_ctx.multicast_query_interval = clock_t_to_jiffies(val);
+		br_multicast_set_query_intvl(&br->multicast_ctx, val);
 	}
 
 	if (data[IFLA_BR_MCAST_QUERY_RESPONSE_INTVL]) {
@@ -1369,7 +1369,7 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
 	if (data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]) {
 		u64 val = nla_get_u64(data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]);
 
-		br->multicast_ctx.multicast_startup_query_interval = clock_t_to_jiffies(val);
+		br_multicast_set_startup_query_intvl(&br->multicast_ctx, val);
 	}
 
 	if (data[IFLA_BR_MCAST_STATS_ENABLED]) {
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index c0efd697865a..e8c6ee322c71 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -28,6 +28,8 @@
 #define BR_MAX_PORTS	(1<<BR_PORT_BITS)
 
 #define BR_MULTICAST_DEFAULT_HASH_MAX 4096
+#define BR_MULTICAST_QUERY_INTVL_MIN msecs_to_jiffies(1000)
+#define BR_MULTICAST_STARTUP_QUERY_INTVL_MIN BR_MULTICAST_QUERY_INTVL_MIN
 
 #define BR_HWDOM_MAX BITS_PER_LONG
 
@@ -963,6 +965,10 @@ int br_multicast_dump_querier_state(struct sk_buff *skb,
 				    int nest_attr);
 size_t br_multicast_querier_state_size(void);
 size_t br_rports_size(const struct net_bridge_mcast *brmctx);
+void br_multicast_set_query_intvl(struct net_bridge_mcast *brmctx,
+				  unsigned long val);
+void br_multicast_set_startup_query_intvl(struct net_bridge_mcast *brmctx,
+					  unsigned long val);
 
 static inline bool br_group_is_l2(const struct br_ip *group)
 {
@@ -1147,9 +1153,9 @@ br_multicast_port_ctx_get_global(const struct net_bridge_mcast_port *pmctx)
 static inline bool
 br_multicast_ctx_vlan_global_disabled(const struct net_bridge_mcast *brmctx)
 {
-	return br_opt_get(brmctx->br, BROPT_MCAST_VLAN_SNOOPING_ENABLED) &&
-	       br_multicast_ctx_is_vlan(brmctx) &&
-	       !(brmctx->vlan->priv_flags & BR_VLFLAG_GLOBAL_MCAST_ENABLED);
+	return br_multicast_ctx_is_vlan(brmctx) &&
+	       (!br_opt_get(brmctx->br, BROPT_MCAST_VLAN_SNOOPING_ENABLED) ||
+		!(brmctx->vlan->priv_flags & BR_VLFLAG_GLOBAL_MCAST_ENABLED));
 }
 
 static inline bool
diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c
index d9a89ddd0331..7b0c19772111 100644
--- a/net/bridge/br_sysfs_br.c
+++ b/net/bridge/br_sysfs_br.c
@@ -658,7 +658,7 @@ static ssize_t multicast_query_interval_show(struct device *d,
 static int set_query_interval(struct net_bridge *br, unsigned long val,
 			      struct netlink_ext_ack *extack)
 {
-	br->multicast_ctx.multicast_query_interval = clock_t_to_jiffies(val);
+	br_multicast_set_query_intvl(&br->multicast_ctx, val);
 	return 0;
 }
 
@@ -706,7 +706,7 @@ static ssize_t multicast_startup_query_interval_show(
 static int set_startup_query_interval(struct net_bridge *br, unsigned long val,
 				      struct netlink_ext_ack *extack)
 {
-	br->multicast_ctx.multicast_startup_query_interval = clock_t_to_jiffies(val);
+	br_multicast_set_startup_query_intvl(&br->multicast_ctx, val);
 	return 0;
 }
 
diff --git a/net/bridge/br_vlan_options.c b/net/bridge/br_vlan_options.c
index 8ffd4ed2563c..a6382973b3e7 100644
--- a/net/bridge/br_vlan_options.c
+++ b/net/bridge/br_vlan_options.c
@@ -521,7 +521,7 @@ static int br_vlan_process_global_one_opts(const struct net_bridge *br,
 		u64 val;
 
 		val = nla_get_u64(tb[BRIDGE_VLANDB_GOPTS_MCAST_QUERY_INTVL]);
-		v->br_mcast_ctx.multicast_query_interval = clock_t_to_jiffies(val);
+		br_multicast_set_query_intvl(&v->br_mcast_ctx, val);
 		*changed = true;
 	}
 	if (tb[BRIDGE_VLANDB_GOPTS_MCAST_QUERY_RESPONSE_INTVL]) {
@@ -535,7 +535,7 @@ static int br_vlan_process_global_one_opts(const struct net_bridge *br,
 		u64 val;
 
 		val = nla_get_u64(tb[BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_INTVL]);
-		v->br_mcast_ctx.multicast_startup_query_interval = clock_t_to_jiffies(val);
+		br_multicast_set_startup_query_intvl(&v->br_mcast_ctx, val);
 		*changed = true;
 	}
 	if (tb[BRIDGE_VLANDB_GOPTS_MCAST_QUERIER]) {
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 6b5956500436..5f70ffdae1b5 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1994,6 +1994,10 @@ static int __init inet_init(void)
 
 	ip_init();
 
+	/* Initialise per-cpu ipv4 mibs */
+	if (init_ipv4_mibs())
+		panic("%s: Cannot init ipv4 mibs\n", __func__);
+
 	/* Setup TCP slab cache for open requests. */
 	tcp_init();
 
@@ -2024,12 +2028,6 @@ static int __init inet_init(void)
 
 	if (init_inet_pernet_ops())
 		pr_crit("%s: Cannot init ipv4 inet pernet ops\n", __func__);
-	/*
-	 *	Initialise per-cpu ipv4 mibs
-	 */
-
-	if (init_ipv4_mibs())
-		pr_crit("%s: Cannot init ipv4 mibs\n", __func__);
 
 	ipv4_proc_init();
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 15c6b450b8db..0cd6b857e7ec 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -3075,7 +3075,7 @@ int udp4_seq_show(struct seq_file *seq, void *v)
 {
 	seq_setwidth(seq, 127);
 	if (v == SEQ_START_TOKEN)
-		seq_puts(seq, "  sl  local_address rem_address   st tx_queue "
+		seq_puts(seq, "   sl  local_address rem_address   st tx_queue "
 			   "rx_queue tr tm->when retrnsmt   uid  timeout "
 			   "inode ref pointer drops");
 	else {
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 527e9ead7449..5e9474bc54fc 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -808,6 +808,8 @@ vti6_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data
 	struct net *net = dev_net(dev);
 	struct vti6_net *ip6n = net_generic(net, vti6_net_id);
 
+	memset(&p1, 0, sizeof(p1));
+
 	switch (cmd) {
 	case SIOCGETTUNNEL:
 		if (dev == ip6n->fb_tnl_dev) {
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 60f1e4f5be5a..c51d5ce3711c 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -1020,6 +1020,9 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname,
 	struct raw6_sock *rp = raw6_sk(sk);
 	int val;
 
+	if (optlen < sizeof(val))
+		return -EINVAL;
+
 	if (copy_from_sockptr(&val, optval, sizeof(val)))
 		return -EFAULT;
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index a2caca6ccf11..8cde9efd7919 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1204,7 +1204,7 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
 			kfree_skb(skb);
 			return -EINVAL;
 		}
-		if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) {
+		if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) {
 			kfree_skb(skb);
 			return -EINVAL;
 		}
diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c
index bb5f1650f11c..c189b4c8a182 100644
--- a/net/ncsi/ncsi-netlink.c
+++ b/net/ncsi/ncsi-netlink.c
@@ -112,7 +112,11 @@ static int ncsi_write_package_info(struct sk_buff *skb,
 		pnest = nla_nest_start_noflag(skb, NCSI_PKG_ATTR);
 		if (!pnest)
 			return -ENOMEM;
-		nla_put_u32(skb, NCSI_PKG_ATTR_ID, np->id);
+		rc = nla_put_u32(skb, NCSI_PKG_ATTR_ID, np->id);
+		if (rc) {
+			nla_nest_cancel(skb, pnest);
+			return rc;
+		}
 		if ((0x1 << np->id) == ndp->package_whitelist)
 			nla_put_flag(skb, NCSI_PKG_ATTR_FORCED);
 		cnest = nla_nest_start_noflag(skb, NCSI_PKG_ATTR_CHANNEL_LIST);
diff --git a/net/sctp/diag.c b/net/sctp/diag.c
index 760b367644c1..a7d623171501 100644
--- a/net/sctp/diag.c
+++ b/net/sctp/diag.c
@@ -290,9 +290,8 @@ out:
 	return err;
 }
 
-static int sctp_sock_dump(struct sctp_transport *tsp, void *p)
+static int sctp_sock_dump(struct sctp_endpoint *ep, struct sctp_transport *tsp, void *p)
 {
-	struct sctp_endpoint *ep = tsp->asoc->ep;
 	struct sctp_comm_param *commp = p;
 	struct sock *sk = ep->base.sk;
 	struct sk_buff *skb = commp->skb;
@@ -302,6 +301,8 @@ static int sctp_sock_dump(struct sctp_transport *tsp, void *p)
 	int err = 0;
 
 	lock_sock(sk);
+	if (ep != tsp->asoc->ep)
+		goto release;
 	list_for_each_entry(assoc, &ep->asocs, asocs) {
 		if (cb->args[4] < cb->args[1])
 			goto next;
@@ -344,9 +345,8 @@ release:
 	return err;
 }
 
-static int sctp_sock_filter(struct sctp_transport *tsp, void *p)
+static int sctp_sock_filter(struct sctp_endpoint *ep, struct sctp_transport *tsp, void *p)
 {
-	struct sctp_endpoint *ep = tsp->asoc->ep;
 	struct sctp_comm_param *commp = p;
 	struct sock *sk = ep->base.sk;
 	const struct inet_diag_req_v2 *r = commp->r;
@@ -505,8 +505,8 @@ skip:
 	if (!(idiag_states & ~(TCPF_LISTEN | TCPF_CLOSE)))
 		goto done;
 
-	sctp_for_each_transport(sctp_sock_filter, sctp_sock_dump,
-				net, &pos, &commp);
+	sctp_transport_traverse_process(sctp_sock_filter, sctp_sock_dump,
+					net, &pos, &commp);
 	cb->args[2] = pos;
 
 done:
diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index 48c9c2c7602f..efffde7f2328 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -184,6 +184,18 @@ void sctp_endpoint_free(struct sctp_endpoint *ep)
 }
 
 /* Final destructor for endpoint.  */
+static void sctp_endpoint_destroy_rcu(struct rcu_head *head)
+{
+	struct sctp_endpoint *ep = container_of(head, struct sctp_endpoint, rcu);
+	struct sock *sk = ep->base.sk;
+
+	sctp_sk(sk)->ep = NULL;
+	sock_put(sk);
+
+	kfree(ep);
+	SCTP_DBG_OBJCNT_DEC(ep);
+}
+
 static void sctp_endpoint_destroy(struct sctp_endpoint *ep)
 {
 	struct sock *sk;
@@ -213,18 +225,13 @@ static void sctp_endpoint_destroy(struct sctp_endpoint *ep)
 	if (sctp_sk(sk)->bind_hash)
 		sctp_put_port(sk);
 
-	sctp_sk(sk)->ep = NULL;
-	/* Give up our hold on the sock */
-	sock_put(sk);
-
-	kfree(ep);
-	SCTP_DBG_OBJCNT_DEC(ep);
+	call_rcu(&ep->rcu, sctp_endpoint_destroy_rcu);
 }
 
 /* Hold a reference to an endpoint. */
-void sctp_endpoint_hold(struct sctp_endpoint *ep)
+int sctp_endpoint_hold(struct sctp_endpoint *ep)
 {
-	refcount_inc(&ep->base.refcnt);
+	return refcount_inc_not_zero(&ep->base.refcnt);
 }
 
 /* Release a reference to an endpoint and clean up if there are
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 33391254fa82..ad5028a07b18 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -5338,11 +5338,12 @@ int sctp_transport_lookup_process(int (*cb)(struct sctp_transport *, void *),
 }
 EXPORT_SYMBOL_GPL(sctp_transport_lookup_process);
 
-int sctp_for_each_transport(int (*cb)(struct sctp_transport *, void *),
-			    int (*cb_done)(struct sctp_transport *, void *),
-			    struct net *net, int *pos, void *p) {
+int sctp_transport_traverse_process(sctp_callback_t cb, sctp_callback_t cb_done,
+				    struct net *net, int *pos, void *p)
+{
 	struct rhashtable_iter hti;
 	struct sctp_transport *tsp;
+	struct sctp_endpoint *ep;
 	int ret;
 
 again:
@@ -5351,26 +5352,32 @@ again:
 
 	tsp = sctp_transport_get_idx(net, &hti, *pos + 1);
 	for (; !IS_ERR_OR_NULL(tsp); tsp = sctp_transport_get_next(net, &hti)) {
-		ret = cb(tsp, p);
-		if (ret)
-			break;
+		ep = tsp->asoc->ep;
+		if (sctp_endpoint_hold(ep)) { /* asoc can be peeled off */
+			ret = cb(ep, tsp, p);
+			if (ret)
+				break;
+			sctp_endpoint_put(ep);
+		}
 		(*pos)++;
 		sctp_transport_put(tsp);
 	}
 	sctp_transport_walk_stop(&hti);
 
 	if (ret) {
-		if (cb_done && !cb_done(tsp, p)) {
+		if (cb_done && !cb_done(ep, tsp, p)) {
 			(*pos)++;
+			sctp_endpoint_put(ep);
 			sctp_transport_put(tsp);
 			goto again;
 		}
+		sctp_endpoint_put(ep);
 		sctp_transport_put(tsp);
 	}
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(sctp_for_each_transport);
+EXPORT_SYMBOL_GPL(sctp_transport_traverse_process);
 
 /* 7.2.1 Association Status (SCTP_STATUS)
 
diff --git a/net/smc/smc.h b/net/smc/smc.h
index f4286ca1f228..1a4fc1c6c4ab 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -180,6 +180,11 @@ struct smc_connection {
 	u16			tx_cdc_seq;	/* sequence # for CDC send */
 	u16			tx_cdc_seq_fin;	/* sequence # - tx completed */
 	spinlock_t		send_lock;	/* protect wr_sends */
+	atomic_t		cdc_pend_tx_wr; /* number of pending tx CDC wqe
+						 * - inc when post wqe,
+						 * - dec on polled tx cqe
+						 */
+	wait_queue_head_t	cdc_pend_tx_wq; /* wakeup on no cdc_pend_tx_wr*/
 	struct delayed_work	tx_work;	/* retry of smc_cdc_msg_send */
 	u32			tx_off;		/* base offset in peer rmb */
 
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index 99acd337ba90..84c8a4374fdd 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -31,10 +31,6 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
 	struct smc_sock *smc;
 	int diff;
 
-	if (!conn)
-		/* already dismissed */
-		return;
-
 	smc = container_of(conn, struct smc_sock, conn);
 	bh_lock_sock(&smc->sk);
 	if (!wc_status) {
@@ -51,6 +47,12 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
 			      conn);
 		conn->tx_cdc_seq_fin = cdcpend->ctrl_seq;
 	}
+
+	if (atomic_dec_and_test(&conn->cdc_pend_tx_wr) &&
+	    unlikely(wq_has_sleeper(&conn->cdc_pend_tx_wq)))
+		wake_up(&conn->cdc_pend_tx_wq);
+	WARN_ON(atomic_read(&conn->cdc_pend_tx_wr) < 0);
+
 	smc_tx_sndbuf_nonfull(smc);
 	bh_unlock_sock(&smc->sk);
 }
@@ -107,6 +109,10 @@ int smc_cdc_msg_send(struct smc_connection *conn,
 	conn->tx_cdc_seq++;
 	conn->local_tx_ctrl.seqno = conn->tx_cdc_seq;
 	smc_host_msg_to_cdc((struct smc_cdc_msg *)wr_buf, conn, &cfed);
+
+	atomic_inc(&conn->cdc_pend_tx_wr);
+	smp_mb__after_atomic(); /* Make sure cdc_pend_tx_wr added before post */
+
 	rc = smc_wr_tx_send(link, (struct smc_wr_tx_pend_priv *)pend);
 	if (!rc) {
 		smc_curs_copy(&conn->rx_curs_confirmed, &cfed, conn);
@@ -114,6 +120,7 @@ int smc_cdc_msg_send(struct smc_connection *conn,
 	} else {
 		conn->tx_cdc_seq--;
 		conn->local_tx_ctrl.seqno = conn->tx_cdc_seq;
+		atomic_dec(&conn->cdc_pend_tx_wr);
 	}
 
 	return rc;
@@ -136,7 +143,18 @@ int smcr_cdc_msg_send_validation(struct smc_connection *conn,
 	peer->token = htonl(local->token);
 	peer->prod_flags.failover_validation = 1;
 
+	/* We need to set pend->conn here to make sure smc_cdc_tx_handler()
+	 * can handle properly
+	 */
+	smc_cdc_add_pending_send(conn, pend);
+
+	atomic_inc(&conn->cdc_pend_tx_wr);
+	smp_mb__after_atomic(); /* Make sure cdc_pend_tx_wr added before post */
+
 	rc = smc_wr_tx_send(link, (struct smc_wr_tx_pend_priv *)pend);
+	if (unlikely(rc))
+		atomic_dec(&conn->cdc_pend_tx_wr);
+
 	return rc;
 }
 
@@ -193,31 +211,9 @@ int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn)
 	return rc;
 }
 
-static bool smc_cdc_tx_filter(struct smc_wr_tx_pend_priv *tx_pend,
-			      unsigned long data)
+void smc_cdc_wait_pend_tx_wr(struct smc_connection *conn)
 {
-	struct smc_connection *conn = (struct smc_connection *)data;
-	struct smc_cdc_tx_pend *cdc_pend =
-		(struct smc_cdc_tx_pend *)tx_pend;
-
-	return cdc_pend->conn == conn;
-}
-
-static void smc_cdc_tx_dismisser(struct smc_wr_tx_pend_priv *tx_pend)
-{
-	struct smc_cdc_tx_pend *cdc_pend =
-		(struct smc_cdc_tx_pend *)tx_pend;
-
-	cdc_pend->conn = NULL;
-}
-
-void smc_cdc_tx_dismiss_slots(struct smc_connection *conn)
-{
-	struct smc_link *link = conn->lnk;
-
-	smc_wr_tx_dismiss_slots(link, SMC_CDC_MSG_TYPE,
-				smc_cdc_tx_filter, smc_cdc_tx_dismisser,
-				(unsigned long)conn);
+	wait_event(conn->cdc_pend_tx_wq, !atomic_read(&conn->cdc_pend_tx_wr));
 }
 
 /* Send a SMC-D CDC header.
diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h
index 0a0a89abd38b..696cc11f2303 100644
--- a/net/smc/smc_cdc.h
+++ b/net/smc/smc_cdc.h
@@ -291,7 +291,7 @@ int smc_cdc_get_free_slot(struct smc_connection *conn,
 			  struct smc_wr_buf **wr_buf,
 			  struct smc_rdma_wr **wr_rdma_buf,
 			  struct smc_cdc_tx_pend **pend);
-void smc_cdc_tx_dismiss_slots(struct smc_connection *conn);
+void smc_cdc_wait_pend_tx_wr(struct smc_connection *conn);
 int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf,
 		     struct smc_cdc_tx_pend *pend);
 int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn);
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 387d28b2f8dd..a6849362f4dd 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -647,7 +647,7 @@ static void smcr_lgr_link_deactivate_all(struct smc_link_group *lgr)
 	for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
 		struct smc_link *lnk = &lgr->lnk[i];
 
-		if (smc_link_usable(lnk))
+		if (smc_link_sendable(lnk))
 			lnk->state = SMC_LNK_INACTIVE;
 	}
 	wake_up_all(&lgr->llc_msg_waiter);
@@ -1127,7 +1127,7 @@ void smc_conn_free(struct smc_connection *conn)
 			smc_ism_unset_conn(conn);
 		tasklet_kill(&conn->rx_tsklet);
 	} else {
-		smc_cdc_tx_dismiss_slots(conn);
+		smc_cdc_wait_pend_tx_wr(conn);
 		if (current_work() != &conn->abort_work)
 			cancel_work_sync(&conn->abort_work);
 	}
@@ -1204,7 +1204,7 @@ void smcr_link_clear(struct smc_link *lnk, bool log)
 	smc_llc_link_clear(lnk, log);
 	smcr_buf_unmap_lgr(lnk);
 	smcr_rtoken_clear_link(lnk);
-	smc_ib_modify_qp_reset(lnk);
+	smc_ib_modify_qp_error(lnk);
 	smc_wr_free_link(lnk);
 	smc_ib_destroy_queue_pair(lnk);
 	smc_ib_dealloc_protection_domain(lnk);
@@ -1336,7 +1336,7 @@ static void smc_conn_kill(struct smc_connection *conn, bool soft)
 		else
 			tasklet_unlock_wait(&conn->rx_tsklet);
 	} else {
-		smc_cdc_tx_dismiss_slots(conn);
+		smc_cdc_wait_pend_tx_wr(conn);
 	}
 	smc_lgr_unregister_conn(conn);
 	smc_close_active_abort(smc);
@@ -1459,11 +1459,16 @@ void smc_smcd_terminate_all(struct smcd_dev *smcd)
 /* Called when an SMCR device is removed or the smc module is unloaded.
  * If smcibdev is given, all SMCR link groups using this device are terminated.
  * If smcibdev is NULL, all SMCR link groups are terminated.
+ *
+ * We must wait here for QPs been destroyed before we destroy the CQs,
+ * or we won't received any CQEs and cdc_pend_tx_wr cannot reach 0 thus
+ * smc_sock cannot be released.
  */
 void smc_smcr_terminate_all(struct smc_ib_device *smcibdev)
 {
 	struct smc_link_group *lgr, *lg;
 	LIST_HEAD(lgr_free_list);
+	LIST_HEAD(lgr_linkdown_list);
 	int i;
 
 	spin_lock_bh(&smc_lgr_list.lock);
@@ -1475,7 +1480,7 @@ void smc_smcr_terminate_all(struct smc_ib_device *smcibdev)
 		list_for_each_entry_safe(lgr, lg, &smc_lgr_list.list, list) {
 			for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
 				if (lgr->lnk[i].smcibdev == smcibdev)
-					smcr_link_down_cond_sched(&lgr->lnk[i]);
+					list_move_tail(&lgr->list, &lgr_linkdown_list);
 			}
 		}
 	}
@@ -1487,6 +1492,16 @@ void smc_smcr_terminate_all(struct smc_ib_device *smcibdev)
 		__smc_lgr_terminate(lgr, false);
 	}
 
+	list_for_each_entry_safe(lgr, lg, &lgr_linkdown_list, list) {
+		for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
+			if (lgr->lnk[i].smcibdev == smcibdev) {
+				mutex_lock(&lgr->llc_conf_mutex);
+				smcr_link_down_cond(&lgr->lnk[i]);
+				mutex_unlock(&lgr->llc_conf_mutex);
+			}
+		}
+	}
+
 	if (smcibdev) {
 		if (atomic_read(&smcibdev->lnk_cnt))
 			wait_event(smcibdev->lnks_deleted,
@@ -1586,7 +1601,6 @@ static void smcr_link_down(struct smc_link *lnk)
 	if (!lgr || lnk->state == SMC_LNK_UNUSED || list_empty(&lgr->list))
 		return;
 
-	smc_ib_modify_qp_reset(lnk);
 	to_lnk = smc_switch_conns(lgr, lnk, true);
 	if (!to_lnk) { /* no backup link available */
 		smcr_link_clear(lnk, true);
@@ -1824,6 +1838,7 @@ create:
 	conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE;
 	conn->local_tx_ctrl.len = SMC_WR_TX_SIZE;
 	conn->urg_state = SMC_URG_READ;
+	init_waitqueue_head(&conn->cdc_pend_tx_wq);
 	INIT_WORK(&smc->conn.abort_work, smc_conn_abort_work);
 	if (ini->is_smcd) {
 		conn->rx_off = sizeof(struct smcd_cdc_msg);
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 59cef3b830d8..d63b08274197 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -415,6 +415,12 @@ static inline bool smc_link_usable(struct smc_link *lnk)
 	return true;
 }
 
+static inline bool smc_link_sendable(struct smc_link *lnk)
+{
+	return smc_link_usable(lnk) &&
+		lnk->qp_attr.cur_qp_state == IB_QPS_RTS;
+}
+
 static inline bool smc_link_active(struct smc_link *lnk)
 {
 	return lnk->state == SMC_LNK_ACTIVE;
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index d93055ec17ae..fe5d5399c4e8 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -109,12 +109,12 @@ int smc_ib_modify_qp_rts(struct smc_link *lnk)
 			    IB_QP_MAX_QP_RD_ATOMIC);
 }
 
-int smc_ib_modify_qp_reset(struct smc_link *lnk)
+int smc_ib_modify_qp_error(struct smc_link *lnk)
 {
 	struct ib_qp_attr qp_attr;
 
 	memset(&qp_attr, 0, sizeof(qp_attr));
-	qp_attr.qp_state = IB_QPS_RESET;
+	qp_attr.qp_state = IB_QPS_ERR;
 	return ib_modify_qp(lnk->roce_qp, &qp_attr, IB_QP_STATE);
 }
 
diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h
index 07585937370e..bfa1c6bf6313 100644
--- a/net/smc/smc_ib.h
+++ b/net/smc/smc_ib.h
@@ -90,6 +90,7 @@ int smc_ib_create_queue_pair(struct smc_link *lnk);
 int smc_ib_ready_link(struct smc_link *lnk);
 int smc_ib_modify_qp_rts(struct smc_link *lnk);
 int smc_ib_modify_qp_reset(struct smc_link *lnk);
+int smc_ib_modify_qp_error(struct smc_link *lnk);
 long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev);
 int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags,
 			     struct smc_buf_desc *buf_slot, u8 link_idx);
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index b102680296b8..3e9fd8a3124c 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -1630,7 +1630,7 @@ void smc_llc_send_link_delete_all(struct smc_link_group *lgr, bool ord, u32 rsn)
 	delllc.reason = htonl(rsn);
 
 	for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
-		if (!smc_link_usable(&lgr->lnk[i]))
+		if (!smc_link_sendable(&lgr->lnk[i]))
 			continue;
 		if (!smc_llc_send_message_wait(&lgr->lnk[i], &delllc))
 			break;
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index 600ab5889227..c6cfdea8b71b 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -62,13 +62,9 @@ static inline bool smc_wr_is_tx_pend(struct smc_link *link)
 }
 
 /* wait till all pending tx work requests on the given link are completed */
-int smc_wr_tx_wait_no_pending_sends(struct smc_link *link)
+void smc_wr_tx_wait_no_pending_sends(struct smc_link *link)
 {
-	if (wait_event_timeout(link->wr_tx_wait, !smc_wr_is_tx_pend(link),
-			       SMC_WR_TX_WAIT_PENDING_TIME))
-		return 0;
-	else /* timeout */
-		return -EPIPE;
+	wait_event(link->wr_tx_wait, !smc_wr_is_tx_pend(link));
 }
 
 static inline int smc_wr_tx_find_pending_index(struct smc_link *link, u64 wr_id)
@@ -87,7 +83,6 @@ static inline void smc_wr_tx_process_cqe(struct ib_wc *wc)
 	struct smc_wr_tx_pend pnd_snd;
 	struct smc_link *link;
 	u32 pnd_snd_idx;
-	int i;
 
 	link = wc->qp->qp_context;
 
@@ -128,14 +123,6 @@ static inline void smc_wr_tx_process_cqe(struct ib_wc *wc)
 	}
 
 	if (wc->status) {
-		for_each_set_bit(i, link->wr_tx_mask, link->wr_tx_cnt) {
-			/* clear full struct smc_wr_tx_pend including .priv */
-			memset(&link->wr_tx_pends[i], 0,
-			       sizeof(link->wr_tx_pends[i]));
-			memset(&link->wr_tx_bufs[i], 0,
-			       sizeof(link->wr_tx_bufs[i]));
-			clear_bit(i, link->wr_tx_mask);
-		}
 		if (link->lgr->smc_version == SMC_V2) {
 			memset(link->wr_tx_v2_pend, 0,
 			       sizeof(*link->wr_tx_v2_pend));
@@ -188,7 +175,7 @@ void smc_wr_tx_cq_handler(struct ib_cq *ib_cq, void *cq_context)
 static inline int smc_wr_tx_get_free_slot_index(struct smc_link *link, u32 *idx)
 {
 	*idx = link->wr_tx_cnt;
-	if (!smc_link_usable(link))
+	if (!smc_link_sendable(link))
 		return -ENOLINK;
 	for_each_clear_bit(*idx, link->wr_tx_mask, link->wr_tx_cnt) {
 		if (!test_and_set_bit(*idx, link->wr_tx_mask))
@@ -231,7 +218,7 @@ int smc_wr_tx_get_free_slot(struct smc_link *link,
 	} else {
 		rc = wait_event_interruptible_timeout(
 			link->wr_tx_wait,
-			!smc_link_usable(link) ||
+			!smc_link_sendable(link) ||
 			lgr->terminating ||
 			(smc_wr_tx_get_free_slot_index(link, &idx) != -EBUSY),
 			SMC_WR_TX_WAIT_FREE_SLOT_TIME);
@@ -358,18 +345,20 @@ int smc_wr_tx_send_wait(struct smc_link *link, struct smc_wr_tx_pend_priv *priv,
 			unsigned long timeout)
 {
 	struct smc_wr_tx_pend *pend;
+	u32 pnd_idx;
 	int rc;
 
 	pend = container_of(priv, struct smc_wr_tx_pend, priv);
 	pend->compl_requested = 1;
-	init_completion(&link->wr_tx_compl[pend->idx]);
+	pnd_idx = pend->idx;
+	init_completion(&link->wr_tx_compl[pnd_idx]);
 
 	rc = smc_wr_tx_send(link, priv);
 	if (rc)
 		return rc;
 	/* wait for completion by smc_wr_tx_process_cqe() */
 	rc = wait_for_completion_interruptible_timeout(
-					&link->wr_tx_compl[pend->idx], timeout);
+					&link->wr_tx_compl[pnd_idx], timeout);
 	if (rc <= 0)
 		rc = -ENODATA;
 	if (rc > 0)
@@ -419,25 +408,6 @@ int smc_wr_reg_send(struct smc_link *link, struct ib_mr *mr)
 	return rc;
 }
 
-void smc_wr_tx_dismiss_slots(struct smc_link *link, u8 wr_tx_hdr_type,
-			     smc_wr_tx_filter filter,
-			     smc_wr_tx_dismisser dismisser,
-			     unsigned long data)
-{
-	struct smc_wr_tx_pend_priv *tx_pend;
-	struct smc_wr_rx_hdr *wr_tx;
-	int i;
-
-	for_each_set_bit(i, link->wr_tx_mask, link->wr_tx_cnt) {
-		wr_tx = (struct smc_wr_rx_hdr *)&link->wr_tx_bufs[i];
-		if (wr_tx->type != wr_tx_hdr_type)
-			continue;
-		tx_pend = &link->wr_tx_pends[i].priv;
-		if (filter(tx_pend, data))
-			dismisser(tx_pend);
-	}
-}
-
 /****************************** receive queue ********************************/
 
 int smc_wr_rx_register_handler(struct smc_wr_rx_handler *handler)
@@ -673,10 +643,7 @@ void smc_wr_free_link(struct smc_link *lnk)
 	smc_wr_wakeup_reg_wait(lnk);
 	smc_wr_wakeup_tx_wait(lnk);
 
-	if (smc_wr_tx_wait_no_pending_sends(lnk))
-		memset(lnk->wr_tx_mask, 0,
-		       BITS_TO_LONGS(SMC_WR_BUF_CNT) *
-						sizeof(*lnk->wr_tx_mask));
+	smc_wr_tx_wait_no_pending_sends(lnk);
 	wait_event(lnk->wr_reg_wait, (!atomic_read(&lnk->wr_reg_refcnt)));
 	wait_event(lnk->wr_tx_wait, (!atomic_read(&lnk->wr_tx_refcnt)));
 
diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h
index f353311e6f84..47512ccce5ef 100644
--- a/net/smc/smc_wr.h
+++ b/net/smc/smc_wr.h
@@ -22,7 +22,6 @@
 #define SMC_WR_BUF_CNT 16	/* # of ctrl buffers per link */
 
 #define SMC_WR_TX_WAIT_FREE_SLOT_TIME	(10 * HZ)
-#define SMC_WR_TX_WAIT_PENDING_TIME	(5 * HZ)
 
 #define SMC_WR_TX_SIZE 44 /* actual size of wr_send data (<=SMC_WR_BUF_SIZE) */
 
@@ -62,7 +61,7 @@ static inline void smc_wr_tx_set_wr_id(atomic_long_t *wr_tx_id, long val)
 
 static inline bool smc_wr_tx_link_hold(struct smc_link *link)
 {
-	if (!smc_link_usable(link))
+	if (!smc_link_sendable(link))
 		return false;
 	atomic_inc(&link->wr_tx_refcnt);
 	return true;
@@ -130,7 +129,7 @@ void smc_wr_tx_dismiss_slots(struct smc_link *lnk, u8 wr_rx_hdr_type,
 			     smc_wr_tx_filter filter,
 			     smc_wr_tx_dismisser dismisser,
 			     unsigned long data);
-int smc_wr_tx_wait_no_pending_sends(struct smc_link *link);
+void smc_wr_tx_wait_no_pending_sends(struct smc_link *link);
 
 int smc_wr_rx_register_handler(struct smc_wr_rx_handler *handler);
 int smc_wr_rx_post_init(struct smc_link *link);
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index bc4ad48ea4f0..fd39bb660ebc 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -83,6 +83,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 		xskb = &pool->heads[i];
 		xskb->pool = pool;
 		xskb->xdp.frame_sz = umem->chunk_size - umem->headroom;
+		INIT_LIST_HEAD(&xskb->free_list_node);
 		if (pool->unaligned)
 			pool->free_heads[i] = xskb;
 		else
diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config
index 0faaccd21447..2b82628decb1 100644
--- a/tools/testing/selftests/net/mptcp/config
+++ b/tools/testing/selftests/net/mptcp/config
@@ -9,7 +9,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_ADVANCED=y
 CONFIG_NETFILTER_NETLINK=m
 CONFIG_NF_TABLES=m
-CONFIG_NFT_COUNTER=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XTABLES=m
 CONFIG_NETFILTER_XT_MATCH_BPF=m
diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh
index 7f26591f236b..3ea73013d956 100755
--- a/tools/testing/selftests/net/udpgro_fwd.sh
+++ b/tools/testing/selftests/net/udpgro_fwd.sh
@@ -132,7 +132,7 @@ run_test() {
 	local rcv=`ip netns exec $NS_DST $ipt"-save" -c | grep 'dport 8000' | \
 							  sed -e 's/\[//' -e 's/:.*//'`
 	if [ $rcv != $pkts ]; then
-		echo " fail - received $rvs packets, expected $pkts"
+		echo " fail - received $rcv packets, expected $pkts"
 		ret=1
 		return
 	fi
@@ -185,6 +185,7 @@ for family in 4 6; do
 	IPT=iptables
 	SUFFIX=24
 	VXDEV=vxlan
+	PING=ping
 
 	if [ $family = 6 ]; then
 		BM_NET=$BM_NET_V6
@@ -192,6 +193,7 @@ for family in 4 6; do
 		SUFFIX="64 nodad"
 		VXDEV=vxlan6
 		IPT=ip6tables
+		PING="ping6"
 	fi
 
 	echo "IPv$family"
@@ -237,7 +239,7 @@ for family in 4 6; do
 
 	# load arp cache before running the test to reduce the amount of
 	# stray traffic on top of the UDP tunnel
-	ip netns exec $NS_SRC ping -q -c 1 $OL_NET$DST_NAT >/dev/null
+	ip netns exec $NS_SRC $PING -q -c 1 $OL_NET$DST_NAT >/dev/null
 	run_test "GRO fwd over UDP tunnel" $OL_NET$DST_NAT 1 1 $OL_NET$DST
 	cleanup
 
diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c
index c66da6ffd6d8..7badaf215de2 100644
--- a/tools/testing/selftests/net/udpgso.c
+++ b/tools/testing/selftests/net/udpgso.c
@@ -156,13 +156,13 @@ struct testcase testcases_v4[] = {
 	},
 	{
 		/* send max number of min sized segments */
-		.tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V4,
+		.tlen = UDP_MAX_SEGMENTS,
 		.gso_len = 1,
-		.r_num_mss = UDP_MAX_SEGMENTS - CONST_HDRLEN_V4,
+		.r_num_mss = UDP_MAX_SEGMENTS,
 	},
 	{
 		/* send max number + 1 of min sized segments: fail */
-		.tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V4 + 1,
+		.tlen = UDP_MAX_SEGMENTS + 1,
 		.gso_len = 1,
 		.tfail = true,
 	},
@@ -259,13 +259,13 @@ struct testcase testcases_v6[] = {
 	},
 	{
 		/* send max number of min sized segments */
-		.tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V6,
+		.tlen = UDP_MAX_SEGMENTS,
 		.gso_len = 1,
-		.r_num_mss = UDP_MAX_SEGMENTS - CONST_HDRLEN_V6,
+		.r_num_mss = UDP_MAX_SEGMENTS,
 	},
 	{
 		/* send max number + 1 of min sized segments: fail */
-		.tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V6 + 1,
+		.tlen = UDP_MAX_SEGMENTS + 1,
 		.gso_len = 1,
 		.tfail = true,
 	},
diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c
index 17512a43885e..f1fdaa270291 100644
--- a/tools/testing/selftests/net/udpgso_bench_tx.c
+++ b/tools/testing/selftests/net/udpgso_bench_tx.c
@@ -419,6 +419,7 @@ static void usage(const char *filepath)
 
 static void parse_opts(int argc, char **argv)
 {
+	const char *bind_addr = NULL;
 	int max_len, hdrlen;
 	int c;
 
@@ -446,7 +447,7 @@ static void parse_opts(int argc, char **argv)
 			cfg_cpu = strtol(optarg, NULL, 0);
 			break;
 		case 'D':
-			setup_sockaddr(cfg_family, optarg, &cfg_dst_addr);
+			bind_addr = optarg;
 			break;
 		case 'l':
 			cfg_runtime_ms = strtoul(optarg, NULL, 10) * 1000;
@@ -492,6 +493,11 @@ static void parse_opts(int argc, char **argv)
 		}
 	}
 
+	if (!bind_addr)
+		bind_addr = cfg_family == PF_INET6 ? "::" : "0.0.0.0";
+
+	setup_sockaddr(cfg_family, bind_addr, &cfg_dst_addr);
+
 	if (optind != argc)
 		usage(argv[0]);