Merge tag 'net-6.19-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

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

  Current release - regressions:

   - netfilter: nf_conncount: fix leaked ct in error paths

   - sched: act_mirred: fix loop detection

   - sctp: fix potential deadlock in sctp_clone_sock()

   - can: fix build dependency

   - eth: mlx5e: do not update BQL of old txqs during channel
     reconfiguration

  Previous releases - regressions:

   - sched: ets: always remove class from active list before deleting it

   - inet: frags: flush pending skbs in fqdir_pre_exit()

   - netfilter: nf_nat: remove bogus direction check

   - mptcp:
      - schedule rtx timer only after pushing data
      - avoid deadlock on fallback while reinjecting

   - can: gs_usb: fix error handling

   - eth:
      - mlx5e:
         - avoid unregistering PSP twice
         - fix double unregister of HCA_PORTS component
      - bnxt_en: fix XDP_TX path
      - mlxsw: fix use-after-free when updating multicast route stats

  Previous releases - always broken:

   - ethtool: avoid overflowing userspace buffer on stats query

   - openvswitch: fix middle attribute validation in push_nsh() action

   - eth:
      - mlx5: fw_tracer, validate format string parameters
      - mlxsw: spectrum_router: fix neighbour use-after-free
      - ipvlan: ignore PACKET_LOOPBACK in handle_mode_l2()

  Misc:

   - Jozsef Kadlecsik retires from maintaining netfilter

   - tools: ynl: fix build on systems with old kernel headers"

* tag 'net-6.19-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (83 commits)
  net: hns3: add VLAN id validation before using
  net: hns3: using the num_tqps to check whether tqp_index is out of range when vf get ring info from mbx
  net: hns3: using the num_tqps in the vf driver to apply for resources
  net: enetc: do not transmit redirected XDP frames when the link is down
  selftests/tc-testing: Test case exercising potential mirred redirect deadlock
  net/sched: act_mirred: fix loop detection
  sctp: Clear inet_opt in sctp_v6_copy_ip_options().
  sctp: Fetch inet6_sk() after setting ->pinet6 in sctp_clone_sock().
  net/handshake: duplicate handshake cancellations leak socket
  net/mlx5e: Don't include PSP in the hard MTU calculations
  net/mlx5e: Do not update BQL of old txqs during channel reconfiguration
  net/mlx5e: Trigger neighbor resolution for unresolved destinations
  net/mlx5e: Use ip6_dst_lookup instead of ipv6_dst_lookup_flow for MAC init
  net/mlx5: Serialize firmware reset with devlink
  net/mlx5: fw_tracer, Handle escaped percent properly
  net/mlx5: fw_tracer, Validate format string parameters
  net/mlx5: Drain firmware reset in shutdown callback
  net/mlx5: fw reset, clear reset requested on drain_fw_reset
  net: dsa: mxl-gsw1xx: manually clear RANEG bit
  net: dsa: mxl-gsw1xx: fix .shutdown driver operation
  ...

CREDITS

@@ -1987,6 +1987,7 @@ D: netfilter: TCP window tracking code
 D: netfilter: raw table
 D: netfilter: iprange match
 D: netfilter: new logging interfaces
+D: netfilter: ipset
 D: netfilter: various other hacks
 S: Tata
 S: Hungary

MAINTAINERS

@@ -18028,7 +18028,6 @@ F:	drivers/net/ethernet/neterion/
 
 NETFILTER
 M:	Pablo Neira Ayuso <pablo@netfilter.org>
-M:	Jozsef Kadlecsik <kadlec@netfilter.org>
 M:	Florian Westphal <fw@strlen.de>
 R:	Phil Sutter <phil@nwl.cc>
 L:	netfilter-devel@vger.kernel.org

drivers/net/can/Kconfig

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
 menuconfig CAN_DEV
-	tristate "CAN Device Drivers"
+	bool "CAN Device Drivers"
 	default y
 	depends on CAN
 	help
@@ -17,10 +17,7 @@ menuconfig CAN_DEV
 	  virtual ones. If you own such devices or plan to use the virtual CAN
 	  interfaces to develop applications, say Y here.
 
-	  To compile as a module, choose M here: the module will be called
-	  can-dev.
-
-if CAN_DEV
+if CAN_DEV && CAN
 
 config CAN_VCAN
 	tristate "Virtual Local CAN Interface (vcan)"

drivers/net/can/Makefile

@@ -7,7 +7,7 @@ obj-$(CONFIG_CAN_VCAN)		+= vcan.o
 obj-$(CONFIG_CAN_VXCAN)		+= vxcan.o
 obj-$(CONFIG_CAN_SLCAN)		+= slcan/
 
-obj-y				+= dev/
+obj-$(CONFIG_CAN_DEV)		+= dev/
 obj-y				+= esd/
 obj-y				+= rcar/
 obj-y				+= rockchip/

drivers/net/can/dev/Makefile

@@ -1,9 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 
-obj-$(CONFIG_CAN_DEV) += can-dev.o
-
-can-dev-y += skb.o
+obj-$(CONFIG_CAN) += can-dev.o
 
+can-dev-$(CONFIG_CAN_DEV) += skb.o
 can-dev-$(CONFIG_CAN_CALC_BITTIMING) += calc_bittiming.o
 can-dev-$(CONFIG_CAN_NETLINK) += bittiming.o
 can-dev-$(CONFIG_CAN_NETLINK) += dev.o

drivers/net/can/usb/gs_usb.c

@@ -1074,7 +1074,7 @@ static int gs_can_open(struct net_device *netdev)
 	usb_free_urb(urb);
 out_usb_kill_anchored_urbs:
 	if (!parent->active_channels) {
-		usb_kill_anchored_urbs(&dev->tx_submitted);
+		usb_kill_anchored_urbs(&parent->rx_submitted);
 
 		if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP)
 			gs_usb_timestamp_stop(parent);

drivers/net/dsa/lantiq/lantiq_gswip.c

@@ -444,9 +444,6 @@ static void gswip_remove(struct platform_device *pdev)
 	if (!priv)
 		return;
 
-	/* disable the switch */
-	gswip_disable_switch(priv);
-
 	dsa_unregister_switch(priv->ds);
 
 	for (i = 0; i < priv->num_gphy_fw; i++)

drivers/net/dsa/lantiq/lantiq_gswip.h

@@ -294,8 +294,6 @@ struct gswip_priv {
 	u16 version;
 };
 
-void gswip_disable_switch(struct gswip_priv *priv);
-
 int gswip_probe_common(struct gswip_priv *priv, u32 version);
 
 #endif /* __LANTIQ_GSWIP_H */

drivers/net/dsa/lantiq/lantiq_gswip_common.c

@@ -752,6 +752,13 @@ static int gswip_setup(struct dsa_switch *ds)
 	return 0;
 }
 
+static void gswip_teardown(struct dsa_switch *ds)
+{
+	struct gswip_priv *priv = ds->priv;
+
+	regmap_clear_bits(priv->mdio, GSWIP_MDIO_GLOB, GSWIP_MDIO_GLOB_ENABLE);
+}
+
 static enum dsa_tag_protocol gswip_get_tag_protocol(struct dsa_switch *ds,
 						    int port,
 						    enum dsa_tag_protocol mp)
@@ -1629,6 +1636,7 @@ static const struct phylink_mac_ops gswip_phylink_mac_ops = {
 static const struct dsa_switch_ops gswip_switch_ops = {
 	.get_tag_protocol	= gswip_get_tag_protocol,
 	.setup			= gswip_setup,
+	.teardown		= gswip_teardown,
 	.port_setup		= gswip_port_setup,
 	.port_enable		= gswip_port_enable,
 	.port_disable		= gswip_port_disable,
@@ -1656,12 +1664,6 @@ static const struct dsa_switch_ops gswip_switch_ops = {
 	.port_hsr_leave		= dsa_port_simple_hsr_leave,
 };
 
-void gswip_disable_switch(struct gswip_priv *priv)
-{
-	regmap_clear_bits(priv->mdio, GSWIP_MDIO_GLOB, GSWIP_MDIO_GLOB_ENABLE);
-}
-EXPORT_SYMBOL_GPL(gswip_disable_switch);
-
 static int gswip_validate_cpu_port(struct dsa_switch *ds)
 {
 	struct gswip_priv *priv = ds->priv;
@@ -1718,15 +1720,14 @@ int gswip_probe_common(struct gswip_priv *priv, u32 version)
 
 	err = gswip_validate_cpu_port(priv->ds);
 	if (err)
-		goto disable_switch;
+		goto unregister_switch;
 
 	dev_info(priv->dev, "probed GSWIP version %lx mod %lx\n",
 		 GSWIP_VERSION_REV(version), GSWIP_VERSION_MOD(version));
 
 	return 0;
 
-disable_switch:
-	gswip_disable_switch(priv);
+unregister_switch:
 	dsa_unregister_switch(priv->ds);
 
 	return err;

drivers/net/dsa/lantiq/mxl-gsw1xx.c

@@ -11,10 +11,12 @@
 
 #include <linux/bits.h>
 #include <linux/delay.h>
+#include <linux/jiffies.h>
 #include <linux/module.h>
 #include <linux/of_device.h>
 #include <linux/of_mdio.h>
 #include <linux/regmap.h>
+#include <linux/workqueue.h>
 #include <net/dsa.h>
 
 #include "lantiq_gswip.h"
@@ -29,6 +31,7 @@ struct gsw1xx_priv {
 	struct			regmap *clk;
 	struct			regmap *shell;
 	struct			phylink_pcs pcs;
+	struct delayed_work	clear_raneg;
 	phy_interface_t		tbi_interface;
 	struct gswip_priv	gswip;
 };
@@ -145,7 +148,9 @@ static void gsw1xx_pcs_disable(struct phylink_pcs *pcs)
 {
 	struct gsw1xx_priv *priv = pcs_to_gsw1xx(pcs);
 
-	/* Assert SGMII shell reset */
+	cancel_delayed_work_sync(&priv->clear_raneg);
+
+	/* Assert SGMII shell reset (will also clear RANEG bit) */
 	regmap_set_bits(priv->shell, GSW1XX_SHELL_RST_REQ,
 			GSW1XX_RST_REQ_SGMII_SHELL);
 
@@ -255,10 +260,16 @@ static int gsw1xx_pcs_reset(struct gsw1xx_priv *priv)
 	      FIELD_PREP(GSW1XX_SGMII_PHY_RX0_CFG2_FILT_CNT,
 			 GSW1XX_SGMII_PHY_RX0_CFG2_FILT_CNT_DEF);
 
-	/* TODO: Take care of inverted RX pair once generic property is
+	/* RX lane seems to be inverted internally, so bit
+	 * GSW1XX_SGMII_PHY_RX0_CFG2_INVERT needs to be set for normal
+	 * (ie. non-inverted) operation.
+	 *
+	 * TODO: Take care of inverted RX pair once generic property is
 	 *       available
 	 */
 
+	val |= GSW1XX_SGMII_PHY_RX0_CFG2_INVERT;
+
 	ret = regmap_write(priv->sgmii, GSW1XX_SGMII_PHY_RX0_CFG2, val);
 	if (ret < 0)
 		return ret;
@@ -422,12 +433,29 @@ static int gsw1xx_pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode,
 	return 0;
 }
 
+static void gsw1xx_pcs_clear_raneg(struct work_struct *work)
+{
+	struct gsw1xx_priv *priv =
+		container_of(work, struct gsw1xx_priv, clear_raneg.work);
+
+	regmap_clear_bits(priv->sgmii, GSW1XX_SGMII_TBI_ANEGCTL,
+			  GSW1XX_SGMII_TBI_ANEGCTL_RANEG);
+}
+
 static void gsw1xx_pcs_an_restart(struct phylink_pcs *pcs)
 {
 	struct gsw1xx_priv *priv = pcs_to_gsw1xx(pcs);
 
+	cancel_delayed_work_sync(&priv->clear_raneg);
+
 	regmap_set_bits(priv->sgmii, GSW1XX_SGMII_TBI_ANEGCTL,
 			GSW1XX_SGMII_TBI_ANEGCTL_RANEG);
+
+	/* despite being documented as self-clearing, the RANEG bit
+	 * sometimes remains set, preventing auto-negotiation from happening.
+	 * MaxLinear advises to manually clear the bit after 10ms.
+	 */
+	schedule_delayed_work(&priv->clear_raneg, msecs_to_jiffies(10));
 }
 
 static void gsw1xx_pcs_link_up(struct phylink_pcs *pcs,
@@ -630,6 +658,8 @@ static int gsw1xx_probe(struct mdio_device *mdiodev)
 	if (ret)
 		return ret;
 
+	INIT_DELAYED_WORK(&priv->clear_raneg, gsw1xx_pcs_clear_raneg);
+
 	ret = gswip_probe_common(&priv->gswip, version);
 	if (ret)
 		return ret;
@@ -642,25 +672,31 @@ static int gsw1xx_probe(struct mdio_device *mdiodev)
 static void gsw1xx_remove(struct mdio_device *mdiodev)
 {
 	struct gswip_priv *priv = dev_get_drvdata(&mdiodev->dev);
+	struct gsw1xx_priv *gsw1xx_priv;
 
 	if (!priv)
 		return;
 
-	gswip_disable_switch(priv);
-
 	dsa_unregister_switch(priv->ds);
+
+	gsw1xx_priv = container_of(priv, struct gsw1xx_priv, gswip);
+	cancel_delayed_work_sync(&gsw1xx_priv->clear_raneg);
 }
 
 static void gsw1xx_shutdown(struct mdio_device *mdiodev)
 {
 	struct gswip_priv *priv = dev_get_drvdata(&mdiodev->dev);
+	struct gsw1xx_priv *gsw1xx_priv;
 
 	if (!priv)
 		return;
 
+	dsa_switch_shutdown(priv->ds);
+
 	dev_set_drvdata(&mdiodev->dev, NULL);
 
-	gswip_disable_switch(priv);
+	gsw1xx_priv = container_of(priv, struct gsw1xx_priv, gswip);
+	cancel_delayed_work_sync(&gsw1xx_priv->clear_raneg);
 }
 
 static const struct gswip_hw_info gsw12x_data = {

drivers/net/ethernet/broadcom/b44.c

@@ -1790,6 +1790,9 @@ static int b44_nway_reset(struct net_device *dev)
 	u32 bmcr;
 	int r;
 
+	if (bp->flags & B44_FLAG_EXTERNAL_PHY)
+		return phy_ethtool_nway_reset(dev);
+
 	spin_lock_irq(&bp->lock);
 	b44_readphy(bp, MII_BMCR, &bmcr);
 	b44_readphy(bp, MII_BMCR, &bmcr);

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

@@ -268,13 +268,11 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 	case XDP_TX:
 		rx_buf = &rxr->rx_buf_ring[cons];
 		mapping = rx_buf->mapping - bp->rx_dma_offset;
-		*event &= BNXT_TX_CMP_EVENT;
 
 		if (unlikely(xdp_buff_has_frags(xdp))) {
 			struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
 
 			tx_needed += sinfo->nr_frags;
-			*event = BNXT_AGG_EVENT;
 		}
 
 		if (tx_avail < tx_needed) {
@@ -287,6 +285,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 		dma_sync_single_for_device(&pdev->dev, mapping + offset, *len,
 					   bp->rx_dir);
 
+		*event &= ~BNXT_RX_EVENT;
 		*event |= BNXT_TX_EVENT;
 		__bnxt_xmit_xdp(bp, txr, mapping + offset, *len,
 				NEXT_RX(rxr->rx_prod), xdp);

drivers/net/ethernet/freescale/enetc/enetc.c

@@ -1787,7 +1787,8 @@ int enetc_xdp_xmit(struct net_device *ndev, int num_frames,
 	int xdp_tx_bd_cnt, i, k;
 	int xdp_tx_frm_cnt = 0;
 
-	if (unlikely(test_bit(ENETC_TX_DOWN, &priv->flags)))
+	if (unlikely(test_bit(ENETC_TX_DOWN, &priv->flags) ||
+		     !netif_carrier_ok(ndev)))
 		return -ENETDOWN;
 
 	enetc_lock_mdio();

drivers/net/ethernet/freescale/fec_main.c

@@ -3933,6 +3933,11 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep,
 	txq->bd.cur = bdp;
 
 	/* Trigger transmission start */
+	if (!(fep->quirks & FEC_QUIRK_ERR007885) ||
+	    !readl(txq->bd.reg_desc_active) ||
+	    !readl(txq->bd.reg_desc_active) ||
+	    !readl(txq->bd.reg_desc_active) ||
+	    !readl(txq->bd.reg_desc_active))
 		writel(0, txq->bd.reg_desc_active);
 
 	return 0;

drivers/net/ethernet/google/gve/gve_main.c

@@ -647,12 +647,9 @@ static int gve_setup_device_resources(struct gve_priv *priv)
 	err = gve_alloc_counter_array(priv);
 	if (err)
 		goto abort_with_rss_config_cache;
-	err = gve_init_clock(priv);
-	if (err)
-		goto abort_with_counter;
 	err = gve_alloc_notify_blocks(priv);
 	if (err)
-		goto abort_with_clock;
+		goto abort_with_counter;
 	err = gve_alloc_stats_report(priv);
 	if (err)
 		goto abort_with_ntfy_blocks;
@@ -683,10 +680,16 @@ static int gve_setup_device_resources(struct gve_priv *priv)
 		}
 	}
 
+	err = gve_init_clock(priv);
+	if (err) {
+		dev_err(&priv->pdev->dev, "Failed to init clock");
+		goto abort_with_ptype_lut;
+	}
+
 	err = gve_init_rss_config(priv, priv->rx_cfg.num_queues);
 	if (err) {
 		dev_err(&priv->pdev->dev, "Failed to init RSS config");
-		goto abort_with_ptype_lut;
+		goto abort_with_clock;
 	}
 
 	err = gve_adminq_report_stats(priv, priv->stats_report_len,
@@ -698,6 +701,8 @@ static int gve_setup_device_resources(struct gve_priv *priv)
 	gve_set_device_resources_ok(priv);
 	return 0;
 
+abort_with_clock:
+	gve_teardown_clock(priv);
 abort_with_ptype_lut:
 	kvfree(priv->ptype_lut_dqo);
 	priv->ptype_lut_dqo = NULL;
@@ -705,8 +710,6 @@ static int gve_setup_device_resources(struct gve_priv *priv)
 	gve_free_stats_report(priv);
 abort_with_ntfy_blocks:
 	gve_free_notify_blocks(priv);
-abort_with_clock:
-	gve_teardown_clock(priv);
 abort_with_counter:
 	gve_free_counter_array(priv);
 abort_with_rss_config_cache:

drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c

@@ -10555,6 +10555,9 @@ int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto,
 	bool writen_to_tbl = false;
 	int ret = 0;
 
+	if (vlan_id >= VLAN_N_VID)
+		return -EINVAL;
+
 	/* When device is resetting or reset failed, firmware is unable to
 	 * handle mailbox. Just record the vlan id, and remove it after
 	 * reset finished.

drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c

@@ -193,10 +193,10 @@ static int hclge_get_ring_chain_from_mbx(
 		return -EINVAL;
 
 	for (i = 0; i < ring_num; i++) {
-		if (req->msg.param[i].tqp_index >= vport->nic.kinfo.rss_size) {
+		if (req->msg.param[i].tqp_index >= vport->nic.kinfo.num_tqps) {
 			dev_err(&hdev->pdev->dev, "tqp index(%u) is out of range(0-%u)\n",
 				req->msg.param[i].tqp_index,
-				vport->nic.kinfo.rss_size - 1U);
+				vport->nic.kinfo.num_tqps - 1U);
 			return -EINVAL;
 		}
 	}

drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c

@@ -368,12 +368,12 @@ static int hclgevf_knic_setup(struct hclgevf_dev *hdev)
 	new_tqps = kinfo->rss_size * num_tc;
 	kinfo->num_tqps = min(new_tqps, hdev->num_tqps);
 
-	kinfo->tqp = devm_kcalloc(&hdev->pdev->dev, kinfo->num_tqps,
+	kinfo->tqp = devm_kcalloc(&hdev->pdev->dev, hdev->num_tqps,
 				  sizeof(struct hnae3_queue *), GFP_KERNEL);
 	if (!kinfo->tqp)
 		return -ENOMEM;
 
-	for (i = 0; i < kinfo->num_tqps; i++) {
+	for (i = 0; i < hdev->num_tqps; i++) {
 		hdev->htqp[i].q.handle = &hdev->nic;
 		hdev->htqp[i].q.tqp_index = i;
 		kinfo->tqp[i] = &hdev->htqp[i].q;

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

@@ -197,6 +197,11 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change,
 	struct pci_dev *pdev = dev->pdev;
 	int ret = 0;
 
+	if (mlx5_fw_reset_in_progress(dev)) {
+		NL_SET_ERR_MSG_MOD(extack, "Can't reload during firmware reset");
+		return -EBUSY;
+	}
+
 	if (mlx5_dev_is_lightweight(dev)) {
 		if (action != DEVLINK_RELOAD_ACTION_DRIVER_REINIT)
 			return -EOPNOTSUPP;

drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c

@@ -33,6 +33,7 @@
 #include "lib/eq.h"
 #include "fw_tracer.h"
 #include "fw_tracer_tracepoint.h"
+#include <linux/ctype.h>
 
 static int mlx5_query_mtrc_caps(struct mlx5_fw_tracer *tracer)
 {
@@ -358,6 +359,47 @@ static const char *VAL_PARM		= "%llx";
 static const char *REPLACE_64_VAL_PARM	= "%x%x";
 static const char *PARAM_CHAR		= "%";
 
+static bool mlx5_is_valid_spec(const char *str)
+{
+	/* Parse format specifiers to find the actual type.
+	 * Structure: %[flags][width][.precision][length]type
+	 * Skip flags, width, precision & length.
+	 */
+	while (isdigit(*str) || *str == '#' || *str == '.' || *str == 'l')
+		str++;
+
+	/* Check if it's a valid integer/hex specifier or %%:
+	 * Valid formats: %x, %d, %i, %u, etc.
+	 */
+	if (*str != 'x' && *str != 'X' && *str != 'd' && *str != 'i' &&
+	    *str != 'u' && *str != 'c' && *str != '%')
+		return false;
+
+	return true;
+}
+
+static bool mlx5_tracer_validate_params(const char *str)
+{
+	const char *substr = str;
+
+	if (!str)
+		return false;
+
+	substr = strstr(substr, PARAM_CHAR);
+	while (substr) {
+		if (!mlx5_is_valid_spec(substr + 1))
+			return false;
+
+		if (*(substr + 1) == '%')
+			substr = strstr(substr + 2, PARAM_CHAR);
+		else
+			substr = strstr(substr + 1, PARAM_CHAR);
+
+	}
+
+	return true;
+}
+
 static int mlx5_tracer_message_hash(u32 message_id)
 {
 	return jhash_1word(message_id, 0) & (MESSAGE_HASH_SIZE - 1);
@@ -419,6 +461,10 @@ static int mlx5_tracer_get_num_of_params(char *str)
 	char *substr, *pstr = str;
 	int num_of_params = 0;
 
+	/* Validate that all parameters are valid before processing */
+	if (!mlx5_tracer_validate_params(str))
+		return -EINVAL;
+
 	/* replace %llx with %x%x */
 	substr = strstr(pstr, VAL_PARM);
 	while (substr) {
@@ -427,11 +473,15 @@ static int mlx5_tracer_get_num_of_params(char *str)
 		substr = strstr(pstr, VAL_PARM);
 	}
 
-	/* count all the % characters */
+	/* count all the % characters, but skip %% (escaped percent) */
 	substr = strstr(str, PARAM_CHAR);
 	while (substr) {
+		if (*(substr + 1) != '%') {
 			num_of_params += 1;
 			str = substr + 1;
+		} else {
+			str = substr + 2;
+		}
 		substr = strstr(str, PARAM_CHAR);
 	}
 
@@ -570,6 +620,9 @@ void mlx5_tracer_print_trace(struct tracer_string_format *str_frmt,
 {
 	char	tmp[512];
 
+	if (str_frmt->invalid_string)
+		snprintf(tmp, sizeof(tmp), "BAD_FORMAT: %s", str_frmt->string);
+	else
 		snprintf(tmp, sizeof(tmp), str_frmt->string,
 			 str_frmt->params[0],
 			 str_frmt->params[1],
@@ -609,6 +662,13 @@ static int mlx5_tracer_handle_raw_string(struct mlx5_fw_tracer *tracer,
 	return 0;
 }
 
+static void mlx5_tracer_handle_bad_format_string(struct mlx5_fw_tracer *tracer,
+						 struct tracer_string_format *cur_string)
+{
+	cur_string->invalid_string = true;
+	list_add_tail(&cur_string->list, &tracer->ready_strings_list);
+}
+
 static int mlx5_tracer_handle_string_trace(struct mlx5_fw_tracer *tracer,
 					   struct tracer_event *tracer_event)
 {
@@ -619,12 +679,18 @@ static int mlx5_tracer_handle_string_trace(struct mlx5_fw_tracer *tracer,
 		if (!cur_string)
 			return mlx5_tracer_handle_raw_string(tracer, tracer_event);
 
-		cur_string->num_of_params = mlx5_tracer_get_num_of_params(cur_string->string);
-		cur_string->last_param_num = 0;
 		cur_string->event_id = tracer_event->event_id;
 		cur_string->tmsn = tracer_event->string_event.tmsn;
 		cur_string->timestamp = tracer_event->string_event.timestamp;
 		cur_string->lost = tracer_event->lost_event;
+		cur_string->last_param_num = 0;
+		cur_string->num_of_params = mlx5_tracer_get_num_of_params(cur_string->string);
+		if (cur_string->num_of_params < 0) {
+			pr_debug("%s Invalid format string parameters\n",
+				 __func__);
+			mlx5_tracer_handle_bad_format_string(tracer, cur_string);
+			return 0;
+		}
 		if (cur_string->num_of_params == 0) /* trace with no params */
 			list_add_tail(&cur_string->list, &tracer->ready_strings_list);
 	} else {
@@ -634,6 +700,11 @@ static int mlx5_tracer_handle_string_trace(struct mlx5_fw_tracer *tracer,
 				 __func__, tracer_event->string_event.tmsn);
 			return mlx5_tracer_handle_raw_string(tracer, tracer_event);
 		}
+		if (cur_string->num_of_params < 0) {
+			pr_debug("%s string parameter of invalid string, dumping\n",
+				 __func__);
+			return 0;
+		}
 		cur_string->last_param_num += 1;
 		if (cur_string->last_param_num > TRACER_MAX_PARAMS) {
 			pr_debug("%s Number of params exceeds the max (%d)\n",

drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h

@@ -125,6 +125,7 @@ struct tracer_string_format {
 	struct list_head list;
 	u32 timestamp;
 	bool lost;
+	bool invalid_string;
 };
 
 enum mlx5_fw_tracer_ownership_state {

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

@@ -69,7 +69,7 @@ struct page_pool;
 #define MLX5E_METADATA_ETHER_TYPE (0x8CE4)
 #define MLX5E_METADATA_ETHER_LEN 8
 
-#define MLX5E_ETH_HARD_MTU (ETH_HLEN + PSP_ENCAP_HLEN + PSP_TRL_SIZE + VLAN_HLEN + ETH_FCS_LEN)
+#define MLX5E_ETH_HARD_MTU (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN)
 
 #define MLX5E_HW2SW_MTU(params, hwmtu) ((hwmtu) - ((params)->hard_mtu))
 #define MLX5E_SW2HW_MTU(params, swmtu) ((swmtu) + ((params)->hard_mtu))

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

@@ -342,9 +342,8 @@ static void mlx5e_ipsec_init_macs(struct mlx5e_ipsec_sa_entry *sa_entry,
 		rt_dst_entry = &rt->dst;
 		break;
 	case AF_INET6:
-		rt_dst_entry = ipv6_stub->ipv6_dst_lookup_flow(
-			dev_net(netdev), NULL, &fl6, NULL);
-		if (IS_ERR(rt_dst_entry))
+		if (!IS_ENABLED(CONFIG_IPV6) ||
+		    ip6_dst_lookup(dev_net(netdev), NULL, &rt_dst_entry, &fl6))
 			goto neigh;
 		break;
 	default:
@@ -359,6 +358,9 @@ static void mlx5e_ipsec_init_macs(struct mlx5e_ipsec_sa_entry *sa_entry,
 
 	neigh_ha_snapshot(addr, n, netdev);
 	ether_addr_copy(dst, addr);
+	if (attrs->dir == XFRM_DEV_OFFLOAD_OUT &&
+	    is_zero_ether_addr(addr))
+		neigh_event_send(n, NULL);
 	dst_release(rt_dst_entry);
 	neigh_release(n);
 	return;

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

@@ -6825,7 +6825,6 @@ static void _mlx5e_remove(struct auxiliary_device *adev)
 	 * is already unregistered before changing to NIC profile.
 	 */
 	if (priv->netdev->reg_state == NETREG_REGISTERED) {
-		mlx5e_psp_unregister(priv);
 		unregister_netdev(priv->netdev);
 		_mlx5e_suspend(adev, false);
 	} else {

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

@@ -939,6 +939,10 @@ void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq)
 	sq->dma_fifo_cc = dma_fifo_cc;
 	sq->cc = sqcc;
 
+	/* Do not update BQL for TXQs that got replaced by new active ones, as
+	 * netdev_tx_reset_queue() is called for them in mlx5e_activate_txqsq().
+	 */
+	if (sq == sq->priv->txq2sq[sq->txq_ix])
 		netdev_tx_completed_queue(sq->txq, npkts, nbytes);
 }
 

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

@@ -52,6 +52,7 @@
 #include "devlink.h"
 #include "lag/lag.h"
 #include "en/tc/post_meter.h"
+#include "fw_reset.h"
 
 /* There are two match-all miss flows, one for unicast dst mac and
  * one for multicast.
@@ -3991,6 +3992,11 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
 	if (IS_ERR(esw))
 		return PTR_ERR(esw);
 
+	if (mlx5_fw_reset_in_progress(esw->dev)) {
+		NL_SET_ERR_MSG_MOD(extack, "Can't change eswitch mode during firmware reset");
+		return -EBUSY;
+	}
+
 	if (esw_mode_from_devlink(mode, &mlx5_mode))
 		return -EINVAL;
 

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

@@ -15,6 +15,7 @@ enum {
 	MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS,
 	MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED,
 	MLX5_FW_RESET_FLAGS_UNLOAD_EVENT,
+	MLX5_FW_RESET_FLAGS_RESET_IN_PROGRESS,
 };
 
 struct mlx5_fw_reset {
@@ -128,6 +129,16 @@ int mlx5_fw_reset_query(struct mlx5_core_dev *dev, u8 *reset_level, u8 *reset_ty
 	return mlx5_reg_mfrl_query(dev, reset_level, reset_type, NULL, NULL);
 }
 
+bool mlx5_fw_reset_in_progress(struct mlx5_core_dev *dev)
+{
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+
+	if (!fw_reset)
+		return false;
+
+	return test_bit(MLX5_FW_RESET_FLAGS_RESET_IN_PROGRESS, &fw_reset->reset_flags);
+}
+
 static int mlx5_fw_reset_get_reset_method(struct mlx5_core_dev *dev,
 					  u8 *reset_method)
 {
@@ -243,6 +254,8 @@ static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev)
 							BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE));
 		devl_unlock(devlink);
 	}
+
+	clear_bit(MLX5_FW_RESET_FLAGS_RESET_IN_PROGRESS, &fw_reset->reset_flags);
 }
 
 static void mlx5_stop_sync_reset_poll(struct mlx5_core_dev *dev)
@@ -462,27 +475,48 @@ static void mlx5_sync_reset_request_event(struct work_struct *work)
 	struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset,
 						      reset_request_work);
 	struct mlx5_core_dev *dev = fw_reset->dev;
+	bool nack_request = false;
+	struct devlink *devlink;
 	int err;
 
 	err = mlx5_fw_reset_get_reset_method(dev, &fw_reset->reset_method);
-	if (err)
+	if (err) {
+		nack_request = true;
 		mlx5_core_warn(dev, "Failed reading MFRL, err %d\n", err);
+	} else if (!mlx5_is_reset_now_capable(dev, fw_reset->reset_method) ||
+		   test_bit(MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST,
+			    &fw_reset->reset_flags)) {
+		nack_request = true;
+	}
 
-	if (err || test_bit(MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST, &fw_reset->reset_flags) ||
-	    !mlx5_is_reset_now_capable(dev, fw_reset->reset_method)) {
+	devlink = priv_to_devlink(dev);
+	/* For external resets, try to acquire devl_lock. Skip if devlink reset is
+	 * pending (lock already held)
+	 */
+	if (nack_request ||
+	    (!test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP,
+		       &fw_reset->reset_flags) &&
+	     !devl_trylock(devlink))) {
 		err = mlx5_fw_reset_set_reset_sync_nack(dev);
 		mlx5_core_warn(dev, "PCI Sync FW Update Reset Nack %s",
 			       err ? "Failed" : "Sent");
 		return;
 	}
+
 	if (mlx5_sync_reset_set_reset_requested(dev))
-		return;
+		goto unlock;
+
+	set_bit(MLX5_FW_RESET_FLAGS_RESET_IN_PROGRESS, &fw_reset->reset_flags);
 
 	err = mlx5_fw_reset_set_reset_sync_ack(dev);
 	if (err)
 		mlx5_core_warn(dev, "PCI Sync FW Update Reset Ack Failed. Error code: %d\n", err);
 	else
 		mlx5_core_warn(dev, "PCI Sync FW Update Reset Ack. Device reset is expected.\n");
+
+unlock:
+	if (!test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags))
+		devl_unlock(devlink);
 }
 
 static int mlx5_pci_link_toggle(struct mlx5_core_dev *dev, u16 dev_id)
@@ -722,6 +756,8 @@ static void mlx5_sync_reset_abort_event(struct work_struct *work)
 
 	if (mlx5_sync_reset_clear_reset_requested(dev, true))
 		return;
+
+	clear_bit(MLX5_FW_RESET_FLAGS_RESET_IN_PROGRESS, &fw_reset->reset_flags);
 	mlx5_core_warn(dev, "PCI Sync FW Update Reset Aborted.\n");
 }
 
@@ -758,6 +794,7 @@ static void mlx5_sync_reset_timeout_work(struct work_struct *work)
 
 	if (mlx5_sync_reset_clear_reset_requested(dev, true))
 		return;
+	clear_bit(MLX5_FW_RESET_FLAGS_RESET_IN_PROGRESS, &fw_reset->reset_flags);
 	mlx5_core_warn(dev, "PCI Sync FW Update Reset Timeout.\n");
 }
 
@@ -844,7 +881,8 @@ void mlx5_drain_fw_reset(struct mlx5_core_dev *dev)
 	cancel_work_sync(&fw_reset->reset_reload_work);
 	cancel_work_sync(&fw_reset->reset_now_work);
 	cancel_work_sync(&fw_reset->reset_abort_work);
-	cancel_delayed_work(&fw_reset->reset_timeout_work);
+	if (test_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags))
+		mlx5_sync_reset_clear_reset_requested(dev, true);
 }
 
 static const struct devlink_param mlx5_fw_reset_devlink_params[] = {

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

@@ -10,6 +10,7 @@ int mlx5_fw_reset_query(struct mlx5_core_dev *dev, u8 *reset_level, u8 *reset_ty
 int mlx5_fw_reset_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel,
 				 struct netlink_ext_ack *extack);
 int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev);
+bool mlx5_fw_reset_in_progress(struct mlx5_core_dev *dev);
 
 int mlx5_fw_reset_wait_reset_done(struct mlx5_core_dev *dev);
 void mlx5_sync_reset_unload_flow(struct mlx5_core_dev *dev, bool locked);

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

@@ -1413,6 +1413,7 @@ static int __mlx5_lag_dev_add_mdev(struct mlx5_core_dev *dev)
 static void mlx5_lag_unregister_hca_devcom_comp(struct mlx5_core_dev *dev)
 {
 	mlx5_devcom_unregister_component(dev->priv.hca_devcom_comp);
+	dev->priv.hca_devcom_comp = NULL;
 }
 
 static int mlx5_lag_register_hca_devcom_comp(struct mlx5_core_dev *dev)

drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c

@@ -67,12 +67,19 @@ static int mlx5_mpesw_metadata_set(struct mlx5_lag *ldev)
 
 static int enable_mpesw(struct mlx5_lag *ldev)
 {
-	int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
 	struct mlx5_core_dev *dev0;
 	int err;
+	int idx;
 	int i;
 
-	if (idx < 0 || ldev->mode != MLX5_LAG_MODE_NONE)
+	if (ldev->mode == MLX5_LAG_MODE_MPESW)
+		return 0;
+
+	if (ldev->mode != MLX5_LAG_MODE_NONE)
+		return -EINVAL;
+
+	idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
+	if (idx < 0)
 		return -EINVAL;
 
 	dev0 = ldev->pf[idx].dev;

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

@@ -2231,6 +2231,7 @@ static void shutdown(struct pci_dev *pdev)
 
 	mlx5_core_info(dev, "Shutdown was called\n");
 	set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state);
+	mlx5_drain_fw_reset(dev);
 	mlx5_drain_health_wq(dev);
 	err = mlx5_try_fast_unload(dev);
 	if (err)

drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c

@@ -440,7 +440,9 @@ int mlxsw_sp_mr_route_add(struct mlxsw_sp_mr_table *mr_table,
 		rhashtable_remove_fast(&mr_table->route_ht,
 				       &mr_orig_route->ht_node,
 				       mlxsw_sp_mr_route_ht_params);
+		mutex_lock(&mr_table->route_list_lock);
 		list_del(&mr_orig_route->node);
+		mutex_unlock(&mr_table->route_list_lock);
 		mlxsw_sp_mr_route_destroy(mr_table, mr_orig_route);
 	}
 

drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c

@@ -2265,6 +2265,7 @@ mlxsw_sp_neigh_entry_alloc(struct mlxsw_sp *mlxsw_sp, struct neighbour *n,
 	if (!neigh_entry)
 		return NULL;
 
+	neigh_hold(n);
 	neigh_entry->key.n = n;
 	neigh_entry->rif = rif;
 	INIT_LIST_HEAD(&neigh_entry->nexthop_list);
@@ -2274,6 +2275,7 @@ mlxsw_sp_neigh_entry_alloc(struct mlxsw_sp *mlxsw_sp, struct neighbour *n,
 
 static void mlxsw_sp_neigh_entry_free(struct mlxsw_sp_neigh_entry *neigh_entry)
 {
+	neigh_release(neigh_entry->key.n);
 	kfree(neigh_entry);
 }
 
@@ -2858,6 +2860,11 @@ static int mlxsw_sp_router_schedule_work(struct net *net,
 	if (!net_work)
 		return NOTIFY_BAD;
 
+	/* Take a reference to ensure the neighbour won't be destructed until
+	 * we drop the reference in the work item.
+	 */
+	neigh_clone(n);
+
 	INIT_WORK(&net_work->work, cb);
 	net_work->mlxsw_sp = router->mlxsw_sp;
 	net_work->n = n;
@@ -2881,11 +2888,6 @@ static int mlxsw_sp_router_schedule_neigh_work(struct mlxsw_sp_router *router,
 	struct net *net;
 
 	net = neigh_parms_net(n->parms);
-
-	/* Take a reference to ensure the neighbour won't be destructed until we
-	 * drop the reference in delayed work.
-	 */
-	neigh_clone(n);
 	return mlxsw_sp_router_schedule_work(net, router, n,
 					     mlxsw_sp_router_neigh_event_work);
 }
@@ -4320,6 +4322,8 @@ mlxsw_sp_nexthop_dead_neigh_replace(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_neigh_entry_insert;
 
+	neigh_release(old_n);
+
 	read_lock_bh(&n->lock);
 	nud_state = n->nud_state;
 	dead = n->dead;
@@ -4328,14 +4332,10 @@ mlxsw_sp_nexthop_dead_neigh_replace(struct mlxsw_sp *mlxsw_sp,
 
 	list_for_each_entry(nh, &neigh_entry->nexthop_list,
 			    neigh_list_node) {
-		neigh_release(old_n);
-		neigh_clone(n);
 		__mlxsw_sp_nexthop_neigh_update(nh, !entry_connected);
 		mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nhgi->nh_grp);
 	}
 
-	neigh_release(n);
-
 	return 0;
 
 err_neigh_entry_insert:
@@ -4428,6 +4428,11 @@ static int mlxsw_sp_nexthop_neigh_init(struct mlxsw_sp *mlxsw_sp,
 		}
 	}
 
+	/* Release the reference taken by neigh_lookup() / neigh_create() since
+	 * neigh_entry already holds one.
+	 */
+	neigh_release(n);
+
 	/* If that is the first nexthop connected to that neigh, add to
 	 * nexthop_neighs_list
 	 */
@@ -4454,11 +4459,9 @@ static void mlxsw_sp_nexthop_neigh_fini(struct mlxsw_sp *mlxsw_sp,
 					struct mlxsw_sp_nexthop *nh)
 {
 	struct mlxsw_sp_neigh_entry *neigh_entry = nh->neigh_entry;
-	struct neighbour *n;
 
 	if (!neigh_entry)
 		return;
-	n = neigh_entry->key.n;
 
 	__mlxsw_sp_nexthop_neigh_update(nh, true);
 	list_del(&nh->neigh_list_node);
@@ -4472,8 +4475,6 @@ static void mlxsw_sp_nexthop_neigh_fini(struct mlxsw_sp *mlxsw_sp,
 
 	if (!neigh_entry->connected && list_empty(&neigh_entry->nexthop_list))
 		mlxsw_sp_neigh_entry_destroy(mlxsw_sp, neigh_entry);
-
-	neigh_release(n);
 }
 
 static bool mlxsw_sp_ipip_netdev_ul_up(struct net_device *ol_dev)

drivers/net/ethernet/realtek/r8169_main.c

@@ -2655,9 +2655,6 @@ static void rtl_wol_enable_rx(struct rtl8169_private *tp)
 
 static void rtl_prepare_power_down(struct rtl8169_private *tp)
 {
-	if (tp->dash_enabled)
-		return;
-
 	if (tp->mac_version == RTL_GIGA_MAC_VER_32 ||
 	    tp->mac_version == RTL_GIGA_MAC_VER_33)
 		rtl_ephy_write(tp, 0x19, 0xff64);
@@ -4812,7 +4809,7 @@ static void rtl8169_down(struct rtl8169_private *tp)
 	rtl_disable_exit_l1(tp);
 	rtl_prepare_power_down(tp);
 
-	if (tp->dash_type != RTL_DASH_NONE)
+	if (tp->dash_type != RTL_DASH_NONE && !tp->saved_wolopts)
 		rtl8168_driver_stop(tp);
 }
 

drivers/net/ethernet/ti/Kconfig

@@ -209,6 +209,7 @@ config TI_ICSSG_PRUETH_SR1
 	depends on PRU_REMOTEPROC
 	depends on NET_SWITCHDEV
 	depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER
+	depends on PTP_1588_CLOCK_OPTIONAL
 	help
 	  Support dual Gigabit Ethernet ports over the ICSSG PRU Subsystem.
 	  This subsystem is available on the AM65 SR1.0 platform.
@@ -234,7 +235,7 @@ config TI_PRUETH
 	depends on PRU_REMOTEPROC
 	depends on NET_SWITCHDEV
 	select TI_ICSS_IEP
-	imply PTP_1588_CLOCK
+	depends on PTP_1588_CLOCK_OPTIONAL
 	help
 	  Some TI SoCs has Programmable Realtime Unit (PRU) cores which can
 	  support Single or Dual Ethernet ports with the help of firmware code

drivers/net/ipvlan/ipvlan_core.c

@@ -737,6 +737,9 @@ static rx_handler_result_t ipvlan_handle_mode_l2(struct sk_buff **pskb,
 	struct ethhdr *eth = eth_hdr(skb);
 	rx_handler_result_t ret = RX_HANDLER_PASS;
 
+	if (unlikely(skb->pkt_type == PACKET_LOOPBACK))
+		return RX_HANDLER_PASS;
+
 	if (is_multicast_ether_addr(eth->h_dest)) {
 		if (ipvlan_external_frame(skb, port)) {
 			struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);

drivers/net/phy/marvell-88q2xxx.c

@@ -698,7 +698,7 @@ static int mv88q2xxx_hwmon_write(struct device *dev,
 
 	switch (attr) {
 	case hwmon_temp_max:
-		clamp_val(val, -75000, 180000);
+		val = clamp(val, -75000, 180000);
 		val = (val / 1000) + 75;
 		val = FIELD_PREP(MDIO_MMD_PCS_MV_TEMP_SENSOR3_INT_THRESH_MASK,
 				 val);

drivers/net/phy/realtek/realtek_main.c

@@ -691,10 +691,6 @@ static int rtl8211f_config_aldps(struct phy_device *phydev)
 
 static int rtl8211f_config_phy_eee(struct phy_device *phydev)
 {
-	/* RTL8211FVD has no PHYCR2 register */
-	if (phydev->drv->phy_id == RTL_8211FVD_PHYID)
-		return 0;
-
 	/* Disable PHY-mode EEE so LPI is passed to the MAC */
 	return phy_modify_paged(phydev, RTL8211F_PHYCR_PAGE, RTL8211F_PHYCR2,
 				RTL8211F_PHYCR2_PHY_EEE_ENABLE, 0);

drivers/net/phy/sfp.c

@@ -497,6 +497,8 @@ static const struct sfp_quirk sfp_quirks[] = {
 	SFP_QUIRK("ALCATELLUCENT", "3FE46541AA", sfp_quirk_2500basex,
 		  sfp_fixup_nokia),
 
+	SFP_QUIRK_F("BIDB", "X-ONU-SFPP", sfp_fixup_potron),
+
 	// FLYPRO SFP-10GT-CS-30M uses Rollball protocol to talk to the PHY.
 	SFP_QUIRK_F("FLYPRO", "SFP-10GT-CS-30M", sfp_fixup_rollball),
 

drivers/nfc/pn533/usb.c

@@ -406,7 +406,7 @@ static int pn533_acr122_poweron_rdr(struct pn533_usb_phy *phy)
 	if (rc || (transferred != sizeof(cmd))) {
 		nfc_err(&phy->udev->dev,
 			"Reader power on cmd error %d\n", rc);
-		return rc;
+		return rc ?: -EINVAL;
 	}
 
 	rc =  usb_submit_urb(phy->in_urb, GFP_KERNEL);

include/net/inet_frag.h

@@ -123,26 +123,14 @@ void inet_frags_fini(struct inet_frags *);
 
 int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net);
 
-static inline void fqdir_pre_exit(struct fqdir *fqdir)
-{
-	/* Prevent creation of new frags.
-	 * Pairs with READ_ONCE() in inet_frag_find().
-	 */
-	WRITE_ONCE(fqdir->high_thresh, 0);
-
-	/* Pairs with READ_ONCE() in inet_frag_kill(), ip_expire()
-	 * and ip6frag_expire_frag_queue().
-	 */
-	WRITE_ONCE(fqdir->dead, true);
-}
+void fqdir_pre_exit(struct fqdir *fqdir);
 void fqdir_exit(struct fqdir *fqdir);
 
 void inet_frag_kill(struct inet_frag_queue *q, int *refs);
 void inet_frag_destroy(struct inet_frag_queue *q);
 struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key);
 
-/* Free all skbs in the queue; return the sum of their truesizes. */
-unsigned int inet_frag_rbtree_purge(struct rb_root *root,
+void inet_frag_queue_flush(struct inet_frag_queue *q,
 			   enum skb_drop_reason reason);
 
 static inline void inet_frag_putn(struct inet_frag_queue *q, int refs)

include/net/ipv6_frag.h

@@ -69,9 +69,6 @@ ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq)
 	int refs = 1;
 
 	rcu_read_lock();
-	/* Paired with the WRITE_ONCE() in fqdir_pre_exit(). */
-	if (READ_ONCE(fq->q.fqdir->dead))
-		goto out_rcu_unlock;
 	spin_lock(&fq->q.lock);
 
 	if (fq->q.flags & INET_FRAG_COMPLETE)
@@ -80,6 +77,12 @@ ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq)
 	fq->q.flags |= INET_FRAG_DROP;
 	inet_frag_kill(&fq->q, &refs);
 
+	/* Paired with the WRITE_ONCE() in fqdir_pre_exit(). */
+	if (READ_ONCE(fq->q.fqdir->dead)) {
+		inet_frag_queue_flush(&fq->q, 0);
+		goto out;
+	}
+
 	dev = dev_get_by_index_rcu(net, fq->iif);
 	if (!dev)
 		goto out;

include/net/netfilter/nf_tables.h

@@ -1091,6 +1091,29 @@ struct nft_rule_blob {
 		__attribute__((aligned(__alignof__(struct nft_rule_dp))));
 };
 
+enum nft_chain_types {
+	NFT_CHAIN_T_DEFAULT = 0,
+	NFT_CHAIN_T_ROUTE,
+	NFT_CHAIN_T_NAT,
+	NFT_CHAIN_T_MAX
+};
+
+/**
+ *	struct nft_chain_validate_state - validation state
+ *
+ *	If a chain is encountered again during table validation it is
+ *	possible to avoid revalidation provided the calling context is
+ *	compatible.  This structure stores relevant calling context of
+ *	previous validations.
+ *
+ *	@hook_mask: the hook numbers and locations the chain is linked to
+ *	@depth: the deepest call chain level the chain is linked to
+ */
+struct nft_chain_validate_state {
+	u8			hook_mask[NFT_CHAIN_T_MAX];
+	u8			depth;
+};
+
 /**
  *	struct nft_chain - nf_tables chain
  *
@@ -1109,6 +1132,7 @@ struct nft_rule_blob {
  *	@udlen: user data length
  *	@udata: user data in the chain
  *	@blob_next: rule blob pointer to the next in the chain
+ *	@vstate: validation state
  */
 struct nft_chain {
 	struct nft_rule_blob		__rcu *blob_gen_0;
@@ -1128,9 +1152,10 @@ struct nft_chain {
 
 	/* Only used during control plane commit phase: */
 	struct nft_rule_blob		*blob_next;
+	struct nft_chain_validate_state vstate;
 };
 
-int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain);
+int nft_chain_validate(const struct nft_ctx *ctx, struct nft_chain *chain);
 int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set,
 			 const struct nft_set_iter *iter,
 			 struct nft_elem_priv *elem_priv);
@@ -1138,13 +1163,6 @@ int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set);
 int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain);
 void nf_tables_unbind_chain(const struct nft_ctx *ctx, struct nft_chain *chain);
 
-enum nft_chain_types {
-	NFT_CHAIN_T_DEFAULT = 0,
-	NFT_CHAIN_T_ROUTE,
-	NFT_CHAIN_T_NAT,
-	NFT_CHAIN_T_MAX
-};
-
 /**
  * 	struct nft_chain_type - nf_tables chain type info
  *

include/uapi/linux/energy_model.h

@@ -2,6 +2,7 @@
 /* Do not edit directly, auto-generated from: */
 /*	Documentation/netlink/specs/em.yaml */
 /* YNL-GEN uapi header */
+/* To regenerate run: tools/net/ynl/ynl-regen.sh */
 
 #ifndef _UAPI_LINUX_ENERGY_MODEL_H
 #define _UAPI_LINUX_ENERGY_MODEL_H

include/uapi/linux/mptcp.h

@@ -40,6 +40,7 @@
 #define MPTCP_PM_ADDR_FLAG_FULLMESH		_BITUL(3)
 #define MPTCP_PM_ADDR_FLAG_IMPLICIT		_BITUL(4)
 #define MPTCP_PM_ADDR_FLAG_LAMINAR		_BITUL(5)
+#define MPTCP_PM_ADDR_FLAGS_MASK		GENMASK(5, 0)
 
 struct mptcp_info {
 	__u8	mptcpi_subflows;

kernel/power/em_netlink_autogen.c

@@ -2,6 +2,7 @@
 /* Do not edit directly, auto-generated from: */
 /*	Documentation/netlink/specs/em.yaml */
 /* YNL-GEN kernel source */
+/* To regenerate run: tools/net/ynl/ynl-regen.sh */
 
 #include <net/netlink.h>
 #include <net/genetlink.h>

kernel/power/em_netlink_autogen.h

@@ -2,6 +2,7 @@
 /* Do not edit directly, auto-generated from: */
 /*	Documentation/netlink/specs/em.yaml */
 /* YNL-GEN kernel header */
+/* To regenerate run: tools/net/ynl/ynl-regen.sh */
 
 #ifndef _LINUX_EM_GEN_H
 #define _LINUX_EM_GEN_H

net/caif/cffrml.c

@@ -92,8 +92,15 @@ static int cffrml_receive(struct cflayer *layr, struct cfpkt *pkt)
 	len = le16_to_cpu(tmp);
 
 	/* Subtract for FCS on length if FCS is not used. */
-	if (!this->dofcs)
+	if (!this->dofcs) {
+		if (len < 2) {
+			++cffrml_rcv_error;
+			pr_err("Invalid frame length (%d)\n", len);
+			cfpkt_destroy(pkt);
+			return -EPROTO;
+		}
 		len -= 2;
+	}
 
 	if (cfpkt_setlen(pkt, len) < 0) {
 		++cffrml_rcv_error;

net/can/Kconfig

@@ -5,7 +5,6 @@
 
 menuconfig CAN
 	tristate "CAN bus subsystem support"
-	select CAN_DEV
 	help
 	  Controller Area Network (CAN) is a slow (up to 1Mbit/s) serial
 	  communications protocol. Development of the CAN bus started in

net/can/j1939/socket.c

@@ -482,6 +482,12 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr_unsized *uaddr, in
 			goto out_release_sock;
 		}
 
+		if (ndev->reg_state != NETREG_REGISTERED) {
+			dev_put(ndev);
+			ret = -ENODEV;
+			goto out_release_sock;
+		}
+
 		can_ml = can_get_ml_priv(ndev);
 		if (!can_ml) {
 			dev_put(ndev);

net/can/j1939/transport.c

@@ -1567,6 +1567,8 @@ int j1939_session_activate(struct j1939_session *session)
 	if (active) {
 		j1939_session_put(active);
 		ret = -EAGAIN;
+	} else if (priv->ndev->reg_state != NETREG_REGISTERED) {
+		ret = -ENODEV;
 	} else {
 		WARN_ON_ONCE(session->state != J1939_SESSION_NEW);
 		list_add_tail(&session->active_session_list_entry,

net/ethtool/ioctl.c

@@ -2383,6 +2383,9 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr)
 		return -ENOMEM;
 	WARN_ON_ONCE(!ret);
 
+	if (gstrings.len && gstrings.len != ret)
+		gstrings.len = 0;
+	else
 		gstrings.len = ret;
 
 	if (gstrings.len) {
@@ -2509,10 +2512,13 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr)
 	if (copy_from_user(&stats, useraddr, sizeof(stats)))
 		return -EFAULT;
 
+	if (stats.n_stats && stats.n_stats != n_stats)
+		stats.n_stats = 0;
+	else
 		stats.n_stats = n_stats;
 
-	if (n_stats) {
-		data = vzalloc(array_size(n_stats, sizeof(u64)));
+	if (stats.n_stats) {
+		data = vzalloc(array_size(stats.n_stats, sizeof(u64)));
 		if (!data)
 			return -ENOMEM;
 		ops->get_ethtool_stats(dev, &stats, data);
@@ -2524,7 +2530,9 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr)
 	if (copy_to_user(useraddr, &stats, sizeof(stats)))
 		goto out;
 	useraddr += sizeof(stats);
-	if (n_stats && copy_to_user(useraddr, data, array_size(n_stats, sizeof(u64))))
+	if (stats.n_stats &&
+	    copy_to_user(useraddr, data,
+			 array_size(stats.n_stats, sizeof(u64))))
 		goto out;
 	ret = 0;
 
@@ -2560,6 +2568,10 @@ static int ethtool_get_phy_stats_phydev(struct phy_device *phydev,
 		return -EOPNOTSUPP;
 
 	n_stats = phy_ops->get_sset_count(phydev);
+	if (stats->n_stats && stats->n_stats != n_stats) {
+		stats->n_stats = 0;
+		return 0;
+	}
 
 	ret = ethtool_vzalloc_stats_array(n_stats, data);
 	if (ret)
@@ -2580,6 +2592,10 @@ static int ethtool_get_phy_stats_ethtool(struct net_device *dev,
 		return -EOPNOTSUPP;
 
 	n_stats = ops->get_sset_count(dev, ETH_SS_PHY_STATS);
+	if (stats->n_stats && stats->n_stats != n_stats) {
+		stats->n_stats = 0;
+		return 0;
+	}
 
 	ret = ethtool_vzalloc_stats_array(n_stats, data);
 	if (ret)
@@ -2616,7 +2632,9 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
 	}
 
 	useraddr += sizeof(stats);
-	if (copy_to_user(useraddr, data, array_size(stats.n_stats, sizeof(u64))))
+	if (stats.n_stats &&
+	    copy_to_user(useraddr, data,
+			 array_size(stats.n_stats, sizeof(u64))))
 		ret = -EFAULT;
 
  out:

net/handshake/request.c

@@ -276,6 +276,8 @@ int handshake_req_submit(struct socket *sock, struct handshake_req *req,
 out_unlock:
 	spin_unlock(&hn->hn_lock);
 out_err:
+	/* Restore original destructor so socket teardown still runs on failure */
+	req->hr_sk->sk_destruct = req->hr_odestruct;
 	trace_handshake_submit_err(net, req, req->hr_sk, ret);
 	handshake_req_destroy(req);
 	return ret;
@@ -324,7 +326,11 @@ bool handshake_req_cancel(struct sock *sk)
 
 	hn = handshake_pernet(net);
 	if (hn && remove_pending(hn, req)) {
-		/* Request hadn't been accepted */
+		/* Request hadn't been accepted - mark cancelled */
+		if (test_and_set_bit(HANDSHAKE_F_REQ_COMPLETED, &req->hr_flags)) {
+			trace_handshake_cancel_busy(net, req, sk);
+			return false;
+		}
 		goto out_true;
 	}
 	if (test_and_set_bit(HANDSHAKE_F_REQ_COMPLETED, &req->hr_flags)) {

net/hsr/hsr_forward.c

@@ -205,6 +205,8 @@ struct sk_buff *prp_get_untagged_frame(struct hsr_frame_info *frame,
 				__pskb_copy(frame->skb_prp,
 					    skb_headroom(frame->skb_prp),
 					    GFP_ATOMIC);
+			if (!frame->skb_std)
+				return NULL;
 		} else {
 			/* Unexpected */
 			WARN_ONCE(1, "%s:%d: Unexpected frame received (port_src %s)\n",

net/ipv4/inet_fragment.c

@@ -218,6 +218,41 @@ static int __init inet_frag_wq_init(void)
 
 pure_initcall(inet_frag_wq_init);
 
+void fqdir_pre_exit(struct fqdir *fqdir)
+{
+	struct inet_frag_queue *fq;
+	struct rhashtable_iter hti;
+
+	/* Prevent creation of new frags.
+	 * Pairs with READ_ONCE() in inet_frag_find().
+	 */
+	WRITE_ONCE(fqdir->high_thresh, 0);
+
+	/* Pairs with READ_ONCE() in inet_frag_kill(), ip_expire()
+	 * and ip6frag_expire_frag_queue().
+	 */
+	WRITE_ONCE(fqdir->dead, true);
+
+	rhashtable_walk_enter(&fqdir->rhashtable, &hti);
+	rhashtable_walk_start(&hti);
+
+	while ((fq = rhashtable_walk_next(&hti))) {
+		if (IS_ERR(fq)) {
+			if (PTR_ERR(fq) != -EAGAIN)
+				break;
+			continue;
+		}
+		spin_lock_bh(&fq->lock);
+		if (!(fq->flags & INET_FRAG_COMPLETE))
+			inet_frag_queue_flush(fq, 0);
+		spin_unlock_bh(&fq->lock);
+	}
+
+	rhashtable_walk_stop(&hti);
+	rhashtable_walk_exit(&hti);
+}
+EXPORT_SYMBOL(fqdir_pre_exit);
+
 void fqdir_exit(struct fqdir *fqdir)
 {
 	INIT_WORK(&fqdir->destroy_work, fqdir_work_fn);
@@ -263,8 +298,8 @@ static void inet_frag_destroy_rcu(struct rcu_head *head)
 	kmem_cache_free(f->frags_cachep, q);
 }
 
-unsigned int inet_frag_rbtree_purge(struct rb_root *root,
-				    enum skb_drop_reason reason)
+static unsigned int
+inet_frag_rbtree_purge(struct rb_root *root, enum skb_drop_reason reason)
 {
 	struct rb_node *p = rb_first(root);
 	unsigned int sum = 0;
@@ -284,7 +319,17 @@ unsigned int inet_frag_rbtree_purge(struct rb_root *root,
 	}
 	return sum;
 }
-EXPORT_SYMBOL(inet_frag_rbtree_purge);
+
+void inet_frag_queue_flush(struct inet_frag_queue *q,
+			   enum skb_drop_reason reason)
+{
+	unsigned int sum;
+
+	reason = reason ?: SKB_DROP_REASON_FRAG_REASM_TIMEOUT;
+	sum = inet_frag_rbtree_purge(&q->rb_fragments, reason);
+	sub_frag_mem_limit(q->fqdir, sum);
+}
+EXPORT_SYMBOL(inet_frag_queue_flush);
 
 void inet_frag_destroy(struct inet_frag_queue *q)
 {
@@ -327,7 +372,9 @@ static struct inet_frag_queue *inet_frag_alloc(struct fqdir *fqdir,
 
 	timer_setup(&q->timer, f->frag_expire, 0);
 	spin_lock_init(&q->lock);
-	/* One reference for the timer, one for the hash table. */
+	/* One reference for the timer, one for the hash table.
+	 * We never take any extra references, only decrement this field.
+	 */
 	refcount_set(&q->refcnt, 2);
 
 	return q;

net/ipv4/ip_fragment.c

@@ -134,11 +134,6 @@ static void ip_expire(struct timer_list *t)
 	net = qp->q.fqdir->net;
 
 	rcu_read_lock();
-
-	/* Paired with WRITE_ONCE() in fqdir_pre_exit(). */
-	if (READ_ONCE(qp->q.fqdir->dead))
-		goto out_rcu_unlock;
-
 	spin_lock(&qp->q.lock);
 
 	if (qp->q.flags & INET_FRAG_COMPLETE)
@@ -146,6 +141,13 @@ static void ip_expire(struct timer_list *t)
 
 	qp->q.flags |= INET_FRAG_DROP;
 	inet_frag_kill(&qp->q, &refs);
+
+	/* Paired with WRITE_ONCE() in fqdir_pre_exit(). */
+	if (READ_ONCE(qp->q.fqdir->dead)) {
+		inet_frag_queue_flush(&qp->q, 0);
+		goto out;
+	}
+
 	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
 	__IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
 
@@ -240,16 +242,10 @@ static int ip_frag_too_far(struct ipq *qp)
 
 static int ip_frag_reinit(struct ipq *qp)
 {
-	unsigned int sum_truesize = 0;
-
-	if (!mod_timer(&qp->q.timer, jiffies + qp->q.fqdir->timeout)) {
-		refcount_inc(&qp->q.refcnt);
+	if (!mod_timer_pending(&qp->q.timer, jiffies + qp->q.fqdir->timeout))
 		return -ETIMEDOUT;
-	}
 
-	sum_truesize = inet_frag_rbtree_purge(&qp->q.rb_fragments,
-					      SKB_DROP_REASON_FRAG_TOO_FAR);
-	sub_frag_mem_limit(qp->q.fqdir, sum_truesize);
+	inet_frag_queue_flush(&qp->q, SKB_DROP_REASON_FRAG_TOO_FAR);
 
 	qp->q.flags = 0;
 	qp->q.len = 0;

net/mptcp/Kconfig

@@ -4,7 +4,7 @@ config MPTCP
 	depends on INET
 	select SKB_EXTENSIONS
 	select CRYPTO_LIB_SHA256
-	select CRYPTO
+	select CRYPTO_LIB_UTILS
 	help
 	  Multipath TCP (MPTCP) connections send and receive data over multiple
 	  subflows in order to utilize multiple network paths. Each subflow

net/mptcp/pm_netlink.c

@@ -119,7 +119,8 @@ int mptcp_pm_parse_entry(struct nlattr *attr, struct genl_info *info,
 	}
 
 	if (tb[MPTCP_PM_ADDR_ATTR_FLAGS])
-		entry->flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]);
+		entry->flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]) &
+			       MPTCP_PM_ADDR_FLAGS_MASK;
 
 	if (tb[MPTCP_PM_ADDR_ATTR_PORT])
 		entry->addr.port = htons(nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_PORT]));

net/mptcp/protocol.c

@@ -1623,7 +1623,7 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 	struct mptcp_sendmsg_info info = {
 				.flags = flags,
 	};
-	bool do_check_data_fin = false;
+	bool copied = false;
 	int push_count = 1;
 
 	while (mptcp_send_head(sk) && (push_count > 0)) {
@@ -1665,7 +1665,7 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 						push_count--;
 					continue;
 				}
-				do_check_data_fin = true;
+				copied = true;
 			}
 		}
 	}
@@ -1674,12 +1674,15 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 	if (ssk)
 		mptcp_push_release(ssk, &info);
 
-	/* ensure the rtx timer is running */
+	/* Avoid scheduling the rtx timer if no data has been pushed; the timer
+	 * will be updated on positive acks by __mptcp_cleanup_una().
+	 */
+	if (copied) {
 		if (!mptcp_rtx_timer_pending(sk))
 			mptcp_reset_rtx_timer(sk);
-	if (do_check_data_fin)
 		mptcp_check_send_data_fin(sk);
 	}
+}
 
 static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool first)
 {
@@ -2766,10 +2769,13 @@ static void __mptcp_retrans(struct sock *sk)
 
 			/*
 			 * make the whole retrans decision, xmit, disallow
-			 * fallback atomic
+			 * fallback atomic, note that we can't retrans even
+			 * when an infinite fallback is in progress, i.e. new
+			 * subflows are disallowed.
 			 */
 			spin_lock_bh(&msk->fallback_lock);
-			if (__mptcp_check_fallback(msk)) {
+			if (__mptcp_check_fallback(msk) ||
+			    !msk->allow_subflows) {
 				spin_unlock_bh(&msk->fallback_lock);
 				release_sock(ssk);
 				goto clear_scheduled;

net/netfilter/ipvs/ip_vs_xmit.c

@@ -408,6 +408,9 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
 	return -1;
 
 err_unreach:
+	if (!skb->dev)
+		skb->dev = skb_dst(skb)->dev;
+
 	dst_link_failure(skb);
 	return -1;
 }

net/netfilter/nf_conncount.c

@@ -172,14 +172,14 @@ static int __nf_conncount_add(struct net *net,
 	struct nf_conn *found_ct;
 	unsigned int collect = 0;
 	bool refcounted = false;
+	int err = 0;
 
 	if (!get_ct_or_tuple_from_skb(net, skb, l3num, &ct, &tuple, &zone, &refcounted))
 		return -ENOENT;
 
 	if (ct && nf_ct_is_confirmed(ct)) {
-		if (refcounted)
-			nf_ct_put(ct);
-		return -EEXIST;
+		err = -EEXIST;
+		goto out_put;
 	}
 
 	if ((u32)jiffies == list->last_gc)
@@ -231,12 +231,16 @@ static int __nf_conncount_add(struct net *net,
 	}
 
 add_new_node:
-	if (WARN_ON_ONCE(list->count > INT_MAX))
-		return -EOVERFLOW;
+	if (WARN_ON_ONCE(list->count > INT_MAX)) {
+		err = -EOVERFLOW;
+		goto out_put;
+	}
 
 	conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC);
-	if (conn == NULL)
-		return -ENOMEM;
+	if (conn == NULL) {
+		err = -ENOMEM;
+		goto out_put;
+	}
 
 	conn->tuple = tuple;
 	conn->zone = *zone;
@@ -249,7 +253,7 @@ static int __nf_conncount_add(struct net *net,
 out_put:
 	if (refcounted)
 		nf_ct_put(ct);
-	return 0;
+	return err;
 }
 
 int nf_conncount_add_skb(struct net *net,
@@ -456,11 +460,10 @@ insert_tree(struct net *net,
 
 		rb_link_node_rcu(&rbconn->node, parent, rbnode);
 		rb_insert_color(&rbconn->node, root);
-
-		if (refcounted)
-			nf_ct_put(ct);
 	}
 out_unlock:
+	if (refcounted)
+		nf_ct_put(ct);
 	spin_unlock_bh(&nf_conncount_locks[hash]);
 	return count;
 }

net/netfilter/nf_conntrack_core.c

@@ -2487,6 +2487,7 @@ void nf_conntrack_cleanup_net(struct net *net)
 void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list)
 {
 	struct nf_ct_iter_data iter_data = {};
+	unsigned long start = jiffies;
 	struct net *net;
 	int busy;
 
@@ -2507,6 +2508,8 @@ void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list)
 			busy = 1;
 	}
 	if (busy) {
+		DEBUG_NET_WARN_ONCE(time_after(jiffies, start + 60 * HZ),
+				    "conntrack cleanup blocked for 60s");
 		schedule();
 		goto i_see_dead_people;
 	}

net/netfilter/nf_flow_table_path.c

@@ -250,6 +250,9 @@ static void nft_dev_forward_path(const struct nft_pktinfo *pkt,
 	if (nft_dev_fill_forward_path(route, dst, ct, dir, ha, &stack) >= 0)
 		nft_dev_path_info(&stack, &info, ha, &ft->data);
 
+	if (info.outdev)
+		route->tuple[dir].out.ifindex = info.outdev->ifindex;
+
 	if (!info.indev || !nft_flowtable_find_dev(info.indev, ft))
 		return;
 
@@ -269,7 +272,6 @@ static void nft_dev_forward_path(const struct nft_pktinfo *pkt,
 
 	route->tuple[!dir].in.num_encaps = info.num_encaps;
 	route->tuple[!dir].in.ingress_vlans = info.ingress_vlans;
-	route->tuple[dir].out.ifindex = info.outdev->ifindex;
 
 	if (info.xmit_type == FLOW_OFFLOAD_XMIT_DIRECT) {
 		memcpy(route->tuple[dir].out.h_source, info.h_source, ETH_ALEN);

net/netfilter/nf_nat_core.c

@@ -294,25 +294,13 @@ nf_nat_used_tuple_new(const struct nf_conntrack_tuple *tuple,
 
 	ct = nf_ct_tuplehash_to_ctrack(thash);
 
-	/* NB: IP_CT_DIR_ORIGINAL should be impossible because
-	 * nf_nat_used_tuple() handles origin collisions.
-	 *
-	 * Handle remote chance other CPU confirmed its ct right after.
-	 */
-	if (thash->tuple.dst.dir != IP_CT_DIR_REPLY)
-		goto out;
-
 	/* clashing connection subject to NAT? Retry with new tuple. */
 	if (READ_ONCE(ct->status) & uses_nat)
 		goto out;
 
 	if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
-			      &ignored_ct->tuplehash[IP_CT_DIR_REPLY].tuple) &&
-	    nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple,
-			      &ignored_ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple)) {
+			      &ignored_ct->tuplehash[IP_CT_DIR_REPLY].tuple))
 		taken = false;
-		goto out;
-	}
 out:
 	nf_ct_put(ct);
 	return taken;

net/netfilter/nf_tables_api.c

@@ -123,6 +123,29 @@ static void nft_validate_state_update(struct nft_table *table, u8 new_validate_s
 
 	table->validate_state = new_validate_state;
 }
+
+static bool nft_chain_vstate_valid(const struct nft_ctx *ctx,
+				   const struct nft_chain *chain)
+{
+	const struct nft_base_chain *base_chain;
+	enum nft_chain_types type;
+	u8 hooknum;
+
+	if (WARN_ON_ONCE(!nft_is_base_chain(ctx->chain)))
+		return false;
+
+	base_chain = nft_base_chain(ctx->chain);
+	hooknum = base_chain->ops.hooknum;
+	type = base_chain->type->type;
+
+	/* chain is already validated for this call depth */
+	if (chain->vstate.depth >= ctx->level &&
+	    chain->vstate.hook_mask[type] & BIT(hooknum))
+		return true;
+
+	return false;
+}
+
 static void nf_tables_trans_destroy_work(struct work_struct *w);
 
 static void nft_trans_gc_work(struct work_struct *work);
@@ -4079,6 +4102,29 @@ static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *r
 	nf_tables_rule_destroy(ctx, rule);
 }
 
+static void nft_chain_vstate_update(const struct nft_ctx *ctx, struct nft_chain *chain)
+{
+	const struct nft_base_chain *base_chain;
+	enum nft_chain_types type;
+	u8 hooknum;
+
+	/* ctx->chain must hold the calling base chain. */
+	if (WARN_ON_ONCE(!nft_is_base_chain(ctx->chain))) {
+		memset(&chain->vstate, 0, sizeof(chain->vstate));
+		return;
+	}
+
+	base_chain = nft_base_chain(ctx->chain);
+	hooknum = base_chain->ops.hooknum;
+	type = base_chain->type->type;
+
+	BUILD_BUG_ON(BIT(NF_INET_NUMHOOKS) > U8_MAX);
+
+	chain->vstate.hook_mask[type] |= BIT(hooknum);
+	if (chain->vstate.depth < ctx->level)
+		chain->vstate.depth = ctx->level;
+}
+
 /** nft_chain_validate - loop detection and hook validation
  *
  * @ctx: context containing call depth and base chain
@@ -4088,15 +4134,25 @@ static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *r
  * and set lookups until either the jump limit is hit or all reachable
  * chains have been validated.
  */
-int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain)
+int nft_chain_validate(const struct nft_ctx *ctx, struct nft_chain *chain)
 {
 	struct nft_expr *expr, *last;
 	struct nft_rule *rule;
 	int err;
 
+	BUILD_BUG_ON(NFT_JUMP_STACK_SIZE > 255);
 	if (ctx->level == NFT_JUMP_STACK_SIZE)
 		return -EMLINK;
 
+	if (ctx->level > 0) {
+		/* jumps to base chains are not allowed. */
+		if (nft_is_base_chain(chain))
+			return -ELOOP;
+
+		if (nft_chain_vstate_valid(ctx, chain))
+			return 0;
+	}
+
 	list_for_each_entry(rule, &chain->rules, list) {
 		if (fatal_signal_pending(current))
 			return -EINTR;
@@ -4115,8 +4171,11 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain)
 			if (err < 0)
 				return err;
 		}
+
+		cond_resched();
 	}
 
+	nft_chain_vstate_update(ctx, chain);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(nft_chain_validate);
@@ -4128,7 +4187,7 @@ static int nft_table_validate(struct net *net, const struct nft_table *table)
 		.net	= net,
 		.family	= table->family,
 	};
-	int err;
+	int err = 0;
 
 	list_for_each_entry(chain, &table->chains, list) {
 		if (!nft_is_base_chain(chain))
@@ -4137,12 +4196,14 @@ static int nft_table_validate(struct net *net, const struct nft_table *table)
 		ctx.chain = chain;
 		err = nft_chain_validate(&ctx, chain);
 		if (err < 0)
-			return err;
-
-		cond_resched();
+			goto err;
 	}
 
-	return 0;
+err:
+	list_for_each_entry(chain, &table->chains, list)
+		memset(&chain->vstate, 0, sizeof(chain->vstate));
+
+	return err;
 }
 
 int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set,
@@ -11676,21 +11737,10 @@ static int nft_validate_register_store(const struct nft_ctx *ctx,
 				       enum nft_data_types type,
 				       unsigned int len)
 {
-	int err;
-
 	switch (reg) {
 	case NFT_REG_VERDICT:
 		if (type != NFT_DATA_VERDICT)
 			return -EINVAL;
-
-		if (data != NULL &&
-		    (data->verdict.code == NFT_GOTO ||
-		     data->verdict.code == NFT_JUMP)) {
-			err = nft_chain_validate(ctx, data->verdict.chain);
-			if (err < 0)
-				return err;
-		}
-
 		break;
 	default:
 		if (type != NFT_DATA_VALUE)

net/netrom/nr_out.c

@@ -43,8 +43,10 @@ void nr_output(struct sock *sk, struct sk_buff *skb)
 		frontlen = skb_headroom(skb);
 
 		while (skb->len > 0) {
-			if ((skbn = sock_alloc_send_skb(sk, frontlen + NR_MAX_PACKET_SIZE, 0, &err)) == NULL)
+			if ((skbn = sock_alloc_send_skb(sk, frontlen + NR_MAX_PACKET_SIZE, 0, &err)) == NULL) {
+				kfree_skb(skb);
 				return;
+			}
 
 			skb_reserve(skbn, frontlen);
 

net/openvswitch/flow_netlink.c

@@ -2802,13 +2802,20 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 	return err;
 }
 
-static bool validate_push_nsh(const struct nlattr *attr, bool log)
+static bool validate_push_nsh(const struct nlattr *a, bool log)
 {
+	struct nlattr *nsh_key = nla_data(a);
 	struct sw_flow_match match;
 	struct sw_flow_key key;
 
+	/* There must be one and only one NSH header. */
+	if (!nla_ok(nsh_key, nla_len(a)) ||
+	    nla_total_size(nla_len(nsh_key)) != nla_len(a) ||
+	    nla_type(nsh_key) != OVS_KEY_ATTR_NSH)
+		return false;
+
 	ovs_match_init(&match, &key, true, NULL);
-	return !nsh_key_put_from_nlattr(attr, &match, false, true, log);
+	return !nsh_key_put_from_nlattr(nsh_key, &match, false, true, log);
 }
 
 /* Return false if there are any non-masked bits set.
@@ -3389,7 +3396,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 					return -EINVAL;
 			}
 			mac_proto = MAC_PROTO_NONE;
-			if (!validate_push_nsh(nla_data(a), log))
+			if (!validate_push_nsh(a, log))
 				return -EINVAL;
 			break;
 

net/sched/act_mirred.c

@@ -281,6 +281,15 @@ static int tcf_mirred_to_dev(struct sk_buff *skb, struct tcf_mirred *m,
 
 	want_ingress = tcf_mirred_act_wants_ingress(m_eaction);
 
+	if (dev == skb->dev && want_ingress == at_ingress) {
+		pr_notice_once("tc mirred: Loop (%s:%s --> %s:%s)\n",
+			       netdev_name(skb->dev),
+			       at_ingress ? "ingress" : "egress",
+			       netdev_name(dev),
+			       want_ingress ? "ingress" : "egress");
+		goto err_cant_do;
+	}
+
 	/* All mirred/redirected skbs should clear previous ct info */
 	nf_reset_ct(skb_to_send);
 	if (want_ingress && !at_ingress) /* drop dst for egress -> ingress */

net/sched/sch_ets.c

@@ -652,7 +652,7 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt,
 	sch_tree_lock(sch);
 
 	for (i = nbands; i < oldbands; i++) {
-		if (i >= q->nstrict && q->classes[i].qdisc->q.qlen)
+		if (cl_is_active(&q->classes[i]))
 			list_del_init(&q->classes[i].alist);
 		qdisc_purge_queue(q->classes[i].qdisc);
 	}
@@ -664,6 +664,10 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt,
 			q->classes[i].deficit = quanta[i];
 		}
 	}
+	for (i = q->nstrict; i < nstrict; i++) {
+		if (cl_is_active(&q->classes[i]))
+			list_del_init(&q->classes[i].alist);
+	}
 	WRITE_ONCE(q->nstrict, nstrict);
 	memcpy(q->prio2band, priomap, sizeof(priomap));
 

net/sctp/ipv6.c

@@ -492,6 +492,8 @@ static void sctp_v6_copy_ip_options(struct sock *sk, struct sock *newsk)
 	struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
 	struct ipv6_txoptions *opt;
 
+	inet_sk(newsk)->inet_opt = NULL;
+
 	newnp = inet6_sk(newsk);
 
 	rcu_read_lock();

net/sctp/socket.c

@@ -4863,8 +4863,6 @@ static struct sock *sctp_clone_sock(struct sock *sk,
 
 	newsp->pf->to_sk_daddr(&asoc->peer.primary_addr, newsk);
 	newinet->inet_dport = htons(asoc->peer.port);
-
-	newsp->pf->copy_ip_options(sk, newsk);
 	atomic_set(&newinet->inet_id, get_random_u16());
 
 	inet_set_bit(MC_LOOP, newsk);
@@ -4874,17 +4872,20 @@ static struct sock *sctp_clone_sock(struct sock *sk,
 
 #if IS_ENABLED(CONFIG_IPV6)
 	if (sk->sk_family == AF_INET6) {
-		struct ipv6_pinfo *newnp = inet6_sk(newsk);
+		struct ipv6_pinfo *newnp;
 
 		newinet->pinet6 = &((struct sctp6_sock *)newsk)->inet6;
 		newinet->ipv6_fl_list = NULL;
 
+		newnp = inet6_sk(newsk);
 		memcpy(newnp, inet6_sk(sk), sizeof(struct ipv6_pinfo));
 		newnp->ipv6_mc_list = NULL;
 		newnp->ipv6_ac_list = NULL;
 	}
 #endif
 
+	newsp->pf->copy_ip_options(sk, newsk);
+
 	newsp->do_auto_asconf = 0;
 	skb_queue_head_init(&newsp->pd_lobby);
 

net/unix/garbage.c

@@ -199,7 +199,7 @@ static void unix_free_vertices(struct scm_fp_list *fpl)
 	}
 }
 
-static DEFINE_SPINLOCK(unix_gc_lock);
+static __cacheline_aligned_in_smp DEFINE_SPINLOCK(unix_gc_lock);
 
 void unix_add_edges(struct scm_fp_list *fpl, struct unix_sock *receiver)
 {

tools/net/ynl/Makefile.deps

@@ -13,6 +13,7 @@ UAPI_PATH:=../../../../include/uapi/
 # need the explicit -D matching what's in /usr, to avoid multiple definitions.
 
 get_hdr_inc=-D$(1) -include $(UAPI_PATH)/linux/$(2)
+get_hdr_inc2=-D$(1) -D$(2) -include $(UAPI_PATH)/linux/$(3)
 
 CFLAGS_devlink:=$(call get_hdr_inc,_LINUX_DEVLINK_H_,devlink.h)
 CFLAGS_dpll:=$(call get_hdr_inc,_LINUX_DPLL_H,dpll.h)
@@ -48,3 +49,4 @@ CFLAGS_tc:= $(call get_hdr_inc,__LINUX_RTNETLINK_H,rtnetlink.h) \
 	$(call get_hdr_inc,_TC_SKBEDIT_H,tc_act/tc_skbedit.h) \
 	$(call get_hdr_inc,_TC_TUNNEL_KEY_H,tc_act/tc_tunnel_key.h)
 CFLAGS_tcp_metrics:=$(call get_hdr_inc,_LINUX_TCP_METRICS_H,tcp_metrics.h)
+CFLAGS_wireguard:=$(call get_hdr_inc2,_LINUX_WIREGUARD_H,_WG_UAPI_WIREGUARD_H,wireguard.h)

tools/testing/selftests/net/af_unix/Makefile

@@ -1,4 +1,9 @@
-CFLAGS += $(KHDR_INCLUDES) -Wall -Wflex-array-member-not-at-end
+top_srcdir := ../../../../..
+include $(top_srcdir)/scripts/Makefile.compiler
+
+cc-option = $(call __cc-option, $(CC),,$(1),$(2))
+
+CFLAGS += $(KHDR_INCLUDES) -Wall $(call cc-option,-Wflex-array-member-not-at-end)
 
 TEST_GEN_PROGS := \
 	diag_uid \

tools/testing/selftests/net/forwarding/config

@@ -29,6 +29,7 @@ CONFIG_NET_ACT_VLAN=m
 CONFIG_NET_CLS_BASIC=m
 CONFIG_NET_CLS_FLOWER=m
 CONFIG_NET_CLS_MATCHALL=m
+CONFIG_NET_CLS_U32=m
 CONFIG_NET_EMATCH=y
 CONFIG_NET_EMATCH_META=m
 CONFIG_NETFILTER=y

tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh

@@ -138,12 +138,17 @@ install_capture()
 	defer tc qdisc del dev "$dev" clsact
 
 	tc filter add dev "$dev" ingress proto ip pref 104 \
-	   flower skip_hw ip_proto udp dst_port "$VXPORT" \
+	   u32 match ip protocol 0x11 0xff \
+	       match u16 "$VXPORT" 0xffff at 0x16 \
+	       match u16 0x0800 0xffff at 0x30 \
 	       action pass
 	defer tc filter del dev "$dev" ingress proto ip pref 104
 
 	tc filter add dev "$dev" ingress proto ipv6 pref 106 \
-	   flower skip_hw ip_proto udp dst_port "$VXPORT" \
+	   u32 match ip6 protocol 0x11 0xff \
+	       match u16 "$VXPORT" 0xffff at 0x2a \
+	       match u16 0x86dd 0xffff at 0x44 \
+	       match u8 0x11 0xff at 0x4c \
 	       action pass
 	defer tc filter del dev "$dev" ingress proto ipv6 pref 106
 }
@@ -248,13 +253,6 @@ vx_create()
 }
 export -f vx_create
 
-vx_wait()
-{
-	# Wait for all the ARP, IGMP etc. noise to settle down so that the
-	# tunnel is clear for measurements.
-	sleep 10
-}
-
 vx10_create()
 {
 	vx_create vx10 10 id 1000 "$@"
@@ -267,18 +265,6 @@ vx20_create()
 }
 export -f vx20_create
 
-vx10_create_wait()
-{
-	vx10_create "$@"
-	vx_wait
-}
-
-vx20_create_wait()
-{
-	vx20_create "$@"
-	vx_wait
-}
-
 ns_init_common()
 {
 	local ns=$1; shift
@@ -554,7 +540,7 @@ ipv4_nomcroute()
 	# Install a misleading (S,G) rule to attempt to trick the system into
 	# pushing the packets elsewhere.
 	adf_install_broken_sg
-	vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$swp2"
+	vx10_create local 192.0.2.100 group "$GROUP4" dev "$swp2"
 	do_test 4 10 0 "IPv4 nomcroute"
 }
 
@@ -562,7 +548,7 @@ ipv6_nomcroute()
 {
 	# Like for IPv4, install a misleading (S,G).
 	adf_install_broken_sg
-	vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$swp2"
+	vx20_create local 2001:db8:4::1 group "$GROUP6" dev "$swp2"
 	do_test 6 10 0 "IPv6 nomcroute"
 }
 
@@ -581,35 +567,35 @@ ipv6_nomcroute_rx()
 ipv4_mcroute()
 {
 	adf_install_sg
-	vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute
+	vx10_create local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute
 	do_test 4 10 10 "IPv4 mcroute"
 }
 
 ipv6_mcroute()
 {
 	adf_install_sg
-	vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute
+	vx20_create local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute
 	do_test 6 10 10 "IPv6 mcroute"
 }
 
 ipv4_mcroute_rx()
 {
 	adf_install_sg
-	vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute
+	vx10_create local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute
 	ipv4_do_test_rx 0 "IPv4 mcroute ping"
 }
 
 ipv6_mcroute_rx()
 {
 	adf_install_sg
-	vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute
+	vx20_create local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute
 	ipv6_do_test_rx 0 "IPv6 mcroute ping"
 }
 
 ipv4_mcroute_changelink()
 {
 	adf_install_sg
-	vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR"
+	vx10_create local 192.0.2.100 group "$GROUP4" dev "$IPMR"
 	ip link set dev vx10 type vxlan mcroute
 	sleep 1
 	do_test 4 10 10 "IPv4 mcroute changelink"
@@ -618,7 +604,7 @@ ipv4_mcroute_changelink()
 ipv6_mcroute_changelink()
 {
 	adf_install_sg
-	vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute
+	vx20_create local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute
 	ip link set dev vx20 type vxlan mcroute
 	sleep 1
 	do_test 6 10 10 "IPv6 mcroute changelink"
@@ -627,47 +613,47 @@ ipv6_mcroute_changelink()
 ipv4_mcroute_starg()
 {
 	adf_install_starg
-	vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute
+	vx10_create local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute
 	do_test 4 10 10 "IPv4 mcroute (*,G)"
 }
 
 ipv6_mcroute_starg()
 {
 	adf_install_starg
-	vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute
+	vx20_create local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute
 	do_test 6 10 10 "IPv6 mcroute (*,G)"
 }
 
 ipv4_mcroute_starg_rx()
 {
 	adf_install_starg
-	vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute
+	vx10_create local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute
 	ipv4_do_test_rx 0 "IPv4 mcroute (*,G) ping"
 }
 
 ipv6_mcroute_starg_rx()
 {
 	adf_install_starg
-	vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute
+	vx20_create local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute
 	ipv6_do_test_rx 0 "IPv6 mcroute (*,G) ping"
 }
 
 ipv4_mcroute_noroute()
 {
-	vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute
+	vx10_create local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute
 	do_test 4 0 0 "IPv4 mcroute, no route"
 }
 
 ipv6_mcroute_noroute()
 {
-	vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute
+	vx20_create local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute
 	do_test 6 0 0 "IPv6 mcroute, no route"
 }
 
 ipv4_mcroute_fdb()
 {
 	adf_install_sg
-	vx10_create_wait local 192.0.2.100 dev "$IPMR" mcroute
+	vx10_create local 192.0.2.100 dev "$IPMR" mcroute
 	bridge fdb add dev vx10 \
 		00:00:00:00:00:00 self static dst "$GROUP4" via "$IPMR"
 	do_test 4 10 10 "IPv4 mcroute FDB"
@@ -676,7 +662,7 @@ ipv4_mcroute_fdb()
 ipv6_mcroute_fdb()
 {
 	adf_install_sg
-	vx20_create_wait local 2001:db8:4::1 dev "$IPMR" mcroute
+	vx20_create local 2001:db8:4::1 dev "$IPMR" mcroute
 	bridge -6 fdb add dev vx20 \
 		00:00:00:00:00:00 self static dst "$GROUP6" via "$IPMR"
 	do_test 6 10 10 "IPv6 mcroute FDB"
@@ -686,7 +672,7 @@ ipv6_mcroute_fdb()
 ipv4_mcroute_fdb_oif0()
 {
 	adf_install_sg
-	vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute
+	vx10_create local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute
 	bridge fdb del dev vx10 00:00:00:00:00:00
 	bridge fdb add dev vx10 00:00:00:00:00:00 self static dst "$GROUP4"
 	do_test 4 10 10 "IPv4 mcroute oif=0"
@@ -703,7 +689,7 @@ ipv6_mcroute_fdb_oif0()
 	defer ip -6 route del table local multicast "$GROUP6/128" dev "$IPMR"
 
 	adf_install_sg
-	vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute
+	vx20_create local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute
 	bridge -6 fdb del dev vx20 00:00:00:00:00:00
 	bridge -6 fdb add dev vx20 00:00:00:00:00:00 self static dst "$GROUP6"
 	do_test 6 10 10 "IPv6 mcroute oif=0"
@@ -716,7 +702,7 @@ ipv4_mcroute_fdb_oif0_sep()
 	adf_install_sg_sep
 
 	adf_ip_addr_add lo 192.0.2.120/28
-	vx10_create_wait local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute
+	vx10_create local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute
 	bridge fdb del dev vx10 00:00:00:00:00:00
 	bridge fdb add dev vx10 00:00:00:00:00:00 self static dst "$GROUP4"
 	do_test 4 10 10 "IPv4 mcroute TX!=RX oif=0"
@@ -727,7 +713,7 @@ ipv4_mcroute_fdb_oif0_sep_rx()
 	adf_install_sg_sep_rx lo
 
 	adf_ip_addr_add lo 192.0.2.120/28
-	vx10_create_wait local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute
+	vx10_create local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute
 	bridge fdb del dev vx10 00:00:00:00:00:00
 	bridge fdb add dev vx10 00:00:00:00:00:00 self static dst "$GROUP4"
 	ipv4_do_test_rx 0 "IPv4 mcroute TX!=RX oif=0 ping"
@@ -738,7 +724,7 @@ ipv4_mcroute_fdb_sep_rx()
 	adf_install_sg_sep_rx lo
 
 	adf_ip_addr_add lo 192.0.2.120/28
-	vx10_create_wait local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute
+	vx10_create local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute
 	bridge fdb del dev vx10 00:00:00:00:00:00
 	bridge fdb add \
 	       dev vx10 00:00:00:00:00:00 self static dst "$GROUP4" via lo
@@ -750,7 +736,7 @@ ipv6_mcroute_fdb_sep_rx()
 	adf_install_sg_sep_rx "X$IPMR"
 
 	adf_ip_addr_add "X$IPMR" 2001:db8:5::1/64
-	vx20_create_wait local 2001:db8:5::1 group "$GROUP6" dev "$IPMR" mcroute
+	vx20_create local 2001:db8:5::1 group "$GROUP6" dev "$IPMR" mcroute
 	bridge -6 fdb del dev vx20 00:00:00:00:00:00
 	bridge -6 fdb add dev vx20 00:00:00:00:00:00 \
 			  self static dst "$GROUP6" via "X$IPMR"

tools/testing/selftests/net/lib.sh

@@ -280,7 +280,8 @@ tc_rule_stats_get()
 	local selector=${1:-.packets}; shift
 
 	tc -j -s filter show dev $dev $dir pref $pref \
-	    | jq ".[1].options.actions[].stats$selector"
+	    | jq ".[] | select(.options.actions) |
+		  .options.actions[].stats$selector"
 }
 
 tc_rule_handle_stats_get()

tools/testing/selftests/net/lib/ksft.h

@@ -24,7 +24,8 @@ static inline void ksft_ready(void)
 		fd = STDOUT_FILENO;
 	}
 
-	write(fd, msg, sizeof(msg));
+	if (write(fd, msg, sizeof(msg)) < 0)
+		perror("write()");
 	if (fd != STDOUT_FILENO)
 		close(fd);
 }
@@ -48,7 +49,8 @@ static inline void ksft_wait(void)
 		fd = STDIN_FILENO;
 	}
 
-	read(fd, &byte, sizeof(byte));
+	if (read(fd, &byte, sizeof(byte)) < 0)
+		perror("read()");
 	if (fd != STDIN_FILENO)
 		close(fd);
 }

tools/testing/selftests/net/mptcp/pm_netlink.sh

@@ -192,6 +192,10 @@ check "show_endpoints" \
 flush_endpoint
 check "show_endpoints" "" "flush addrs"
 
+add_endpoint 10.0.1.1 flags unknown
+check "show_endpoints" "$(format_endpoints "1,10.0.1.1")" "ignore unknown flags"
+flush_endpoint
+
 set_limits 9 1 2>/dev/null
 check "get_limits" "${default_limits}" "rcv addrs above hard limit"
 

tools/testing/selftests/net/mptcp/pm_nl_ctl.c

@@ -24,6 +24,8 @@
 #define IPPROTO_MPTCP 262
 #endif
 
+#define MPTCP_PM_ADDR_FLAG_UNKNOWN _BITUL(7)
+
 static void syntax(char *argv[])
 {
 	fprintf(stderr, "%s add|ann|rem|csf|dsf|get|set|del|flush|dump|events|listen|accept [<args>]\n", argv[0]);
@@ -836,6 +838,8 @@ int add_addr(int fd, int pm_family, int argc, char *argv[])
 					flags |= MPTCP_PM_ADDR_FLAG_BACKUP;
 				else if (!strcmp(tok, "fullmesh"))
 					flags |= MPTCP_PM_ADDR_FLAG_FULLMESH;
+				else if (!strcmp(tok, "unknown"))
+					flags |= MPTCP_PM_ADDR_FLAG_UNKNOWN;
 				else
 					error(1, errno,
 					      "unknown flag %s", argv[arg]);
@@ -1048,6 +1052,13 @@ static void print_addr(struct rtattr *attrs, int len)
 					printf(",");
 			}
 
+			if (flags & MPTCP_PM_ADDR_FLAG_UNKNOWN) {
+				printf("unknown");
+				flags &= ~MPTCP_PM_ADDR_FLAG_UNKNOWN;
+				if (flags)
+					printf(",");
+			}
+
 			/* bump unknown flags, if any */
 			if (flags)
 				printf("0x%x", flags);

tools/testing/selftests/net/netfilter/conntrack_clash.sh

@@ -116,7 +116,7 @@ run_one_clash_test()
 	# not a failure: clash resolution logic did not trigger.
 	# With right timing, xmit completed sequentially and
 	# no parallel insertion occurs.
-	return $ksft_skip
+	return $ksft_xfail
 }
 
 run_clash_test()
@@ -133,12 +133,12 @@ run_clash_test()
 		if [ $rv -eq 0 ];then
 			echo "PASS: clash resolution test for $daddr:$dport on attempt $i"
 			return 0
-		elif [ $rv -eq $ksft_skip ]; then
+		elif [ $rv -eq $ksft_xfail ]; then
 			softerr=1
 		fi
 	done
 
-	[ $softerr -eq 1 ] && echo "SKIP: clash resolution for $daddr:$dport did not trigger"
+	[ $softerr -eq 1 ] && echo "XFAIL: clash resolution for $daddr:$dport did not trigger"
 }
 
 ip link add veth0 netns "$nsclient1" type veth peer name veth0 netns "$nsrouter"
@@ -167,8 +167,7 @@ load_simple_ruleset "$nsclient2"
 run_clash_test "$nsclient2" "$nsclient2" 127.0.0.1 9001
 
 if [ $clash_resolution_active -eq 0 ];then
-	[ "$ret" -eq 0 ] && ret=$ksft_skip
-	echo "SKIP: Clash resolution did not trigger"
+	[ "$ret" -eq 0 ] && ret=$ksft_xfail
 fi
 
 exit $ret

tools/testing/selftests/net/netfilter/conntrack_reverse_clash.c

@@ -33,9 +33,14 @@ static void die(const char *e)
 	exit(111);
 }
 
-static void die_port(uint16_t got, uint16_t want)
+static void die_port(const struct sockaddr_in *sin, uint16_t want)
 {
-	fprintf(stderr, "Port number changed, wanted %d got %d\n", want, ntohs(got));
+	uint16_t got = ntohs(sin->sin_port);
+	char str[INET_ADDRSTRLEN];
+
+	inet_ntop(AF_INET, &sin->sin_addr, str, sizeof(str));
+
+	fprintf(stderr, "Port number changed, wanted %d got %d from %s\n", want, got, str);
 	exit(1);
 }
 
@@ -100,7 +105,7 @@ int main(int argc, char *argv[])
 				die("child recvfrom");
 
 			if (peer.sin_port != htons(PORT))
-				die_port(peer.sin_port, PORT);
+				die_port(&peer, PORT);
 		} else {
 			if (sendto(s2, buf, LEN, 0, (struct sockaddr *)&sa1, sizeof(sa1)) != LEN)
 				continue;
@@ -109,7 +114,7 @@ int main(int argc, char *argv[])
 				die("parent recvfrom");
 
 			if (peer.sin_port != htons((PORT + 1)))
-				die_port(peer.sin_port, PORT + 1);
+				die_port(&peer, PORT + 1);
 		}
 	}
 

tools/testing/selftests/net/netfilter/conntrack_reverse_clash.sh

@@ -45,6 +45,8 @@ if ip netns exec "$ns0" ./conntrack_reverse_clash; then
 	echo "PASS: No SNAT performed for null bindings"
 else
 	echo "ERROR: SNAT performed without any matching snat rule"
+	ip netns exec "$ns0" conntrack -L
+	ip netns exec "$ns0" conntrack -S
 	exit 1
 fi
 

tools/testing/selftests/net/netfilter/packetdrill/conntrack_syn_challenge_ack.pkt

@@ -26,7 +26,7 @@
 
 +0.01 > R 643160523:643160523(0) win 0
 
-+0.01 `conntrack -f $NFCT_IP_VERSION -L -p tcp --dport 8080 2>/dev/null | grep UNREPLIED | grep -q SYN_SENT`
++0.1 `conntrack -f $NFCT_IP_VERSION -L -p tcp --dport 8080 2>/dev/null | grep UNREPLIED | grep -q SYN_SENT`
 
 // Must go through.
 +0.01 > S 0:0(0) win 65535 <mss 1460,sackOK,TS val 1 ecr 0,nop,wscale 8>

tools/testing/selftests/net/tfo.c

@@ -81,7 +81,8 @@ static void run_server(void)
 	if (getsockopt(connfd, SOL_SOCKET, SO_INCOMING_NAPI_ID, &opt, &len) < 0)
 		error(1, errno, "getsockopt(SO_INCOMING_NAPI_ID)");
 
-	read(connfd, buf, 64);
+	if (read(connfd, buf, 64) < 0)
+		perror("read()");
 	fprintf(outfile, "%d\n", opt);
 
 	fclose(outfile);

tools/testing/selftests/net/tls.c

@@ -2786,10 +2786,10 @@ TEST_F(tls_err, epoll_partial_rec)
 TEST_F(tls_err, poll_partial_rec_async)
 {
 	struct pollfd pfd = { };
+	char token = '\0';
 	ssize_t rec_len;
 	char rec[256];
 	char buf[128];
-	char token;
 	int p[2];
 	int ret;
 

tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json

@@ -1052,5 +1052,51 @@
             "$TC qdisc del dev $DEV1 ingress_block 21 clsact",
             "$TC actions flush action mirred"
         ]
+    },
+    {
+        "id": "7eba",
+        "name": "Redirect multiport: dummy egress ->  dummy egress (Loop)",
+        "category": [
+            "filter",
+            "mirred"
+        ],
+        "plugins": {
+            "requires": [
+                "nsPlugin"
+            ]
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY handle 1: root drr",
+            "$TC filter add dev $DUMMY parent 1: protocol ip prio 10 matchall action mirred egress redirect dev $DUMMY index 1"
+        ],
+        "cmdUnderTest": "ping -c1 -W0.01 -I $DUMMY 10.10.10.1",
+        "expExitCode": "1",
+        "verifyCmd": "$TC -j -s actions get action mirred index 1",
+        "matchJSON": [
+            {
+                "total acts": 0
+            },
+            {
+                "actions": [
+                    {
+                        "order": 1,
+                        "kind": "mirred",
+                        "mirred_action": "redirect",
+                        "direction": "egress",
+                        "index": 1,
+                        "stats": {
+                            "packets": 1,
+                            "overlimits": 1
+                        },
+                        "not_in_hw": true
+                    }
+                ]
+            }
+        ],
+        "teardown": [
+            "$TC qdisc del dev $DUMMY root"
+        ]
     }
 ]

tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json

@@ -1033,5 +1033,83 @@
         "teardown": [
             "$TC qdisc del dev $DUMMY handle 1: root"
         ]
+    },
+    {
+        "id": "6e4f",
+        "name": "Try to delete ets drr class' qdisc while still keeping it in the active list",
+        "category": [
+            "qdisc",
+            "ets",
+            "tbf"
+        ],
+        "plugins": {
+            "requires": [
+                "nsPlugin",
+                "scapyPlugin"
+            ]
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.11.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY root handle 1: ets bands 2 strict 1",
+            "$TC qdisc add dev $DUMMY parent 1:2 handle 20: tbf rate 8bit burst 100b latency 1s",
+            "$TC filter add dev $DUMMY parent 1: basic classid 1:2",
+            "ping -c2 -W0.01 -s 56 -I $DUMMY 10.10.11.11 || true",
+            "$TC qdisc change dev $DUMMY root handle 1: ets bands 2 strict 2",
+            "$TC qdisc change dev $DUMMY root handle 1: ets bands 1 strict 1"
+        ],
+        "cmdUnderTest": "ping -c1 -W0.01 -s 56 -I $DUMMY 10.10.11.11",
+        "expExitCode": "1",
+        "verifyCmd": "$TC -s -j qdisc ls dev $DUMMY root",
+        "matchJSON": [
+            {
+                "kind": "ets",
+                "handle": "1:",
+                "bytes": 196,
+                "packets": 2
+            }
+        ],
+        "teardown": [
+            "$TC qdisc del dev $DUMMY root handle 1:"
+        ]
+    },
+    {
+        "id": "0b8f",
+        "name": "Try to add ets class to the active list twice",
+        "category": [
+            "qdisc",
+            "ets",
+            "tbf"
+        ],
+        "plugins": {
+            "requires": [
+                "nsPlugin",
+                "scapyPlugin"
+            ]
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.11.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY root handle 1: ets bands 2 strict 1",
+            "$TC qdisc add dev $DUMMY parent 1:2 handle 20: tbf rate 8bit burst 100b latency 1s",
+            "$TC filter add dev $DUMMY parent 1: basic classid 1:2",
+            "ping -c2 -W0.01 -s 56 -I $DUMMY 10.10.11.11 || true",
+            "$TC qdisc change dev $DUMMY root handle 1: ets bands 2 strict 2",
+            "$TC qdisc change dev $DUMMY root handle 1: ets bands 2 strict 1"
+        ],
+        "cmdUnderTest": "ping -c1 -W0.01 -s 56 -I $DUMMY 10.10.11.11",
+        "expExitCode": "1",
+        "verifyCmd": "$TC -s -j qdisc ls dev $DUMMY root",
+        "matchJSON": [
+            {
+                "kind": "ets",
+                "handle": "1:",
+                "bytes": 98,
+                "packets": 1
+            }
+        ],
+        "teardown": [
+            "$TC qdisc del dev $DUMMY root handle 1:"
+        ]
     }
 ]