Networking fixes for 6.4-rc2, including fixes from netfilter

Current release - regressions:
 
   - mtk_eth_soc: fix NULL pointer dereference
 
 Previous releases - regressions:
 
   - core:
     - skb_partial_csum_set() fix against transport header magic value
     - fix load-tearing on sk->sk_stamp in sock_recv_cmsgs().
     - annotate sk->sk_err write from do_recvmmsg()
     - add vlan_get_protocol_and_depth() helper
 
   - netlink: annotate accesses to nlk->cb_running
 
   - netfilter: always release netdev hooks from notifier
 
 Previous releases - always broken:
 
   - core: deal with most data-races in sk_wait_event()
 
   - netfilter: fix possible bug_on with enable_hooks=1
 
   - eth: bonding: fix send_peer_notif overflow
 
   - eth: xpcs: fix incorrect number of interfaces
 
   - eth: ipvlan: fix out-of-bounds caused by unclear skb->cb
 
   - eth: stmmac: Initialize MAC_ONEUS_TIC_COUNTER register
 
 Signed-off-by: Paolo Abeni <pabeni@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQJGBAABCAAwFiEEg1AjqC77wbdLX2LbKSR5jcyPE6QFAmRcxawSHHBhYmVuaUBy
 ZWRoYXQuY29tAAoJECkkeY3MjxOkv6wQAJgfOBlDAkZNKHzwtMuFiLxECeEMWY9h
 wJCyiq0qXnz9p5ZqjdmTmA8B+jUp9VkpgN5Z3lid5hXDfzDrvXL1KGZW4pc4ooz9
 GUzrp0EUzO5UsyrlZRS9vJ9mbCGN5M1ZWtWH93g8OzGJPRnLs0Q/Tr4IFTBVKzVb
 GmJPy/ZYWYDjnvx3BgewRDuYeH3Rt9lsIt4Pxq/E+D8W3ypvVM0m3GvrO5eEzMeu
 EfeilAdmJGJUufeoGguKt0hheqILS3kNCjQO25XS2Lq1OqetnR/wqTwXaaVxL2du
 Eb2ca7wKkihDpl2l8bQ3ss6vqM0HEpZ63Y2PJaNBS8ASdLsMq4n2L6j2JMfT8hWY
 RG3nJS7F2UFLyYmCJjNL1/I+Z9XeMyFKnHORzHK1dAkMlhd+8NauKWAxdjlxMbxX
 p1msyTl54bG0g6FrU/zAirCWNAAZYCPdZG/XvA/2Jj9mdy64OlGlv/QdJvfjcx+C
 L6nkwZfwXU7QUwKeeTfP8abte2SLrXIxkJrnNEAntPnFOSmd16+/yvQ8JVlbWTMd
 JugJrSAIxjOglIr/1fsnUuV+Ab+JDYQv/wkoyzvtcY2tjhTAHzgmTwwSfeYiCTJE
 rEbjyVvVgMcLTUIk/R9QC5/k6nX/7/KRDHxPOMBX4boOsuA0ARVjzt8uKRvv/7cS
 dRV98RwvCKvD
 =MoPD
 -----END PGP SIGNATURE-----

Merge tag 'net-6.4-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

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

  Current release - regressions:

   - mtk_eth_soc: fix NULL pointer dereference

  Previous releases - regressions:

   - core:
      - skb_partial_csum_set() fix against transport header magic value
      - fix load-tearing on sk->sk_stamp in sock_recv_cmsgs().
      - annotate sk->sk_err write from do_recvmmsg()
      - add vlan_get_protocol_and_depth() helper

   - netlink: annotate accesses to nlk->cb_running

   - netfilter: always release netdev hooks from notifier

  Previous releases - always broken:

   - core: deal with most data-races in sk_wait_event()

   - netfilter: fix possible bug_on with enable_hooks=1

   - eth: bonding: fix send_peer_notif overflow

   - eth: xpcs: fix incorrect number of interfaces

   - eth: ipvlan: fix out-of-bounds caused by unclear skb->cb

   - eth: stmmac: Initialize MAC_ONEUS_TIC_COUNTER register"

* tag 'net-6.4-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (31 commits)
  af_unix: Fix data races around sk->sk_shutdown.
  af_unix: Fix a data race of sk->sk_receive_queue->qlen.
  net: datagram: fix data-races in datagram_poll()
  net: mscc: ocelot: fix stat counter register values
  ipvlan:Fix out-of-bounds caused by unclear skb->cb
  docs: networking: fix x25-iface.rst heading & index order
  gve: Remove the code of clearing PBA bit
  tcp: add annotations around sk->sk_shutdown accesses
  net: add vlan_get_protocol_and_depth() helper
  net: pcs: xpcs: fix incorrect number of interfaces
  net: deal with most data-races in sk_wait_event()
  net: annotate sk->sk_err write from do_recvmmsg()
  netlink: annotate accesses to nlk->cb_running
  kselftest: bonding: add num_grat_arp test
  selftests: forwarding: lib: add netns support for tc rule handle stats get
  Documentation: bonding: fix the doc of peer_notif_delay
  bonding: fix send_peer_notif overflow
  net: ethernet: mtk_eth_soc: fix NULL pointer dereference
  selftests: nft_flowtable.sh: check ingress/egress chain too
  selftests: nft_flowtable.sh: monitor result file sizes
  ...

Documentation/networking/bonding.rst

@@ -776,10 +776,11 @@ peer_notif_delay
 	Specify the delay, in milliseconds, between each peer
 	notification (gratuitous ARP and unsolicited IPv6 Neighbor
 	Advertisement) when they are issued after a failover event.
-	This delay should be a multiple of the link monitor interval
+	This delay should be a multiple of the MII link monitor interval
-	(arp_interval or miimon, whichever is active). The default
+	(miimon).
-	value is 0 which means to match the value of the link monitor
+
-	interval.
+	The valid range is 0 - 300000. The default value is 0, which means
+	to match the value of the MII link monitor interval.
 
 prio
 	Slave priority. A higher number means higher priority.

Documentation/networking/index.rst

@@ -116,8 +116,8 @@ Contents:
    udplite
    vrf
    vxlan
-   x25-iface
    x25
+   x25-iface
    xfrm_device
    xfrm_proc
    xfrm_sync

Documentation/networking/x25-iface.rst

@@ -1,8 +1,7 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-============================-
 X.25 Device Driver Interface
-============================-
+============================
 
 Version 1.1
 

drivers/net/bonding/bond_netlink.c

@@ -84,6 +84,11 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
+/* Limit the max delay range to 300s */
+static struct netlink_range_validation delay_range = {
+	.max = 300000,
+};
+
 static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_MODE]		= { .type = NLA_U8 },
 	[IFLA_BOND_ACTIVE_SLAVE]	= { .type = NLA_U32 },
@@ -114,7 +119,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_AD_ACTOR_SYSTEM]	= { .type = NLA_BINARY,
 					    .len  = ETH_ALEN },
 	[IFLA_BOND_TLB_DYNAMIC_LB]	= { .type = NLA_U8 },
-	[IFLA_BOND_PEER_NOTIF_DELAY]    = { .type = NLA_U32 },
+	[IFLA_BOND_PEER_NOTIF_DELAY]    = NLA_POLICY_FULL_RANGE(NLA_U32, &delay_range),
 	[IFLA_BOND_MISSED_MAX]		= { .type = NLA_U8 },
 	[IFLA_BOND_NS_IP6_TARGET]	= { .type = NLA_NESTED },
 };

drivers/net/bonding/bond_options.c

@@ -169,6 +169,12 @@ static const struct bond_opt_value bond_num_peer_notif_tbl[] = {
 	{ NULL,      -1,  0}
 };
 
+static const struct bond_opt_value bond_peer_notif_delay_tbl[] = {
+	{ "off",     0,   0},
+	{ "maxval",  300000, BOND_VALFLAG_MAX},
+	{ NULL,      -1,  0}
+};
+
 static const struct bond_opt_value bond_primary_reselect_tbl[] = {
 	{ "always",  BOND_PRI_RESELECT_ALWAYS,  BOND_VALFLAG_DEFAULT},
 	{ "better",  BOND_PRI_RESELECT_BETTER,  0},
@@ -488,7 +494,7 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = {
 		.id = BOND_OPT_PEER_NOTIF_DELAY,
 		.name = "peer_notif_delay",
 		.desc = "Delay between each peer notification on failover event, in milliseconds",
-		.values = bond_intmax_tbl,
+		.values = bond_peer_notif_delay_tbl,
 		.set = bond_option_peer_notif_delay_set
 	}
 };

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

@@ -294,19 +294,6 @@ static int gve_napi_poll_dqo(struct napi_struct *napi, int budget)
 	bool reschedule = false;
 	int work_done = 0;
 
-	/* Clear PCI MSI-X Pending Bit Array (PBA)
-	 *
-	 * This bit is set if an interrupt event occurs while the vector is
-	 * masked. If this bit is set and we reenable the interrupt, it will
-	 * fire again. Since we're just about to poll the queue state, we don't
-	 * need it to fire again.
-	 *
-	 * Under high softirq load, it's possible that the interrupt condition
-	 * is triggered twice before we got the chance to process it.
-	 */
-	gve_write_irq_doorbell_dqo(priv, block,
-				   GVE_ITR_NO_UPDATE_DQO | GVE_ITR_CLEAR_PBA_BIT_DQO);
-
 	if (block->tx)
 		reschedule |= gve_tx_poll_dqo(block, /*do_clean=*/true);
 

drivers/net/ethernet/mediatek/mtk_wed.c

@@ -654,7 +654,7 @@ __mtk_wed_detach(struct mtk_wed_device *dev)
 					   BIT(hw->index), BIT(hw->index));
 	}
 
-	if (!hw_list[!hw->index]->wed_dev &&
+	if ((!hw_list[!hw->index] || !hw_list[!hw->index]->wed_dev) &&
 	    hw->eth->dma_dev != hw->eth->dev)
 		mtk_eth_set_dma_device(hw->eth, hw->eth->dev);
 

drivers/net/ethernet/mscc/vsc7514_regs.c

@@ -307,15 +307,15 @@ static const u32 vsc7514_sys_regmap[] = {
 	REG(SYS_COUNT_DROP_YELLOW_PRIO_4,		0x000218),
 	REG(SYS_COUNT_DROP_YELLOW_PRIO_5,		0x00021c),
 	REG(SYS_COUNT_DROP_YELLOW_PRIO_6,		0x000220),
-	REG(SYS_COUNT_DROP_YELLOW_PRIO_7,		0x000214),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_7,		0x000224),
-	REG(SYS_COUNT_DROP_GREEN_PRIO_0,		0x000218),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_0,		0x000228),
-	REG(SYS_COUNT_DROP_GREEN_PRIO_1,		0x00021c),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_1,		0x00022c),
-	REG(SYS_COUNT_DROP_GREEN_PRIO_2,		0x000220),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_2,		0x000230),
-	REG(SYS_COUNT_DROP_GREEN_PRIO_3,		0x000224),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_3,		0x000234),
-	REG(SYS_COUNT_DROP_GREEN_PRIO_4,		0x000228),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_4,		0x000238),
-	REG(SYS_COUNT_DROP_GREEN_PRIO_5,		0x00022c),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_5,		0x00023c),
-	REG(SYS_COUNT_DROP_GREEN_PRIO_6,		0x000230),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_6,		0x000240),
-	REG(SYS_COUNT_DROP_GREEN_PRIO_7,		0x000234),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_7,		0x000244),
 	REG(SYS_RESET_CFG,				0x000508),
 	REG(SYS_CMID,					0x00050c),
 	REG(SYS_VLAN_ETYPE_CFG,				0x000510),

drivers/net/ethernet/stmicro/stmmac/dwmac4.h

@@ -181,6 +181,7 @@ enum power_event {
 #define GMAC4_LPI_CTRL_STATUS	0xd0
 #define GMAC4_LPI_TIMER_CTRL	0xd4
 #define GMAC4_LPI_ENTRY_TIMER	0xd8
+#define GMAC4_MAC_ONEUS_TIC_COUNTER	0xdc
 
 /* LPI control and status defines */
 #define GMAC4_LPI_CTRL_STATUS_LPITCSE	BIT(21)	/* LPI Tx Clock Stop Enable */

drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c

@@ -25,6 +25,7 @@ static void dwmac4_core_init(struct mac_device_info *hw,
 	struct stmmac_priv *priv = netdev_priv(dev);
 	void __iomem *ioaddr = hw->pcsr;
 	u32 value = readl(ioaddr + GMAC_CONFIG);
+	u32 clk_rate;
 
 	value |= GMAC_CORE_INIT;
 
@@ -47,6 +48,10 @@ static void dwmac4_core_init(struct mac_device_info *hw,
 
 	writel(value, ioaddr + GMAC_CONFIG);
 
+	/* Configure LPI 1us counter to number of CSR clock ticks in 1us - 1 */
+	clk_rate = clk_get_rate(priv->plat->stmmac_clk);
+	writel((clk_rate / 1000000) - 1, ioaddr + GMAC4_MAC_ONEUS_TIC_COUNTER);
+
 	/* Enable GMAC interrupts */
 	value = GMAC_INT_DEFAULT_ENABLE;
 

drivers/net/ipvlan/ipvlan_core.c

@@ -436,6 +436,9 @@ static int ipvlan_process_v4_outbound(struct sk_buff *skb)
 		goto err;
 	}
 	skb_dst_set(skb, &rt->dst);
+
+	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+
 	err = ip_local_out(net, skb->sk, skb);
 	if (unlikely(net_xmit_eval(err)))
 		dev->stats.tx_errors++;
@@ -474,6 +477,9 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb)
 		goto err;
 	}
 	skb_dst_set(skb, dst);
+
+	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+
 	err = ip6_local_out(net, skb->sk, skb);
 	if (unlikely(net_xmit_eval(err)))
 		dev->stats.tx_errors++;

drivers/net/mdio/mdio-mvusb.c

@@ -67,6 +67,7 @@ static int mvusb_mdio_probe(struct usb_interface *interface,
 	struct device *dev = &interface->dev;
 	struct mvusb_mdio *mvusb;
 	struct mii_bus *mdio;
+	int ret;
 
 	mdio = devm_mdiobus_alloc_size(dev, sizeof(*mvusb));
 	if (!mdio)
@@ -87,7 +88,15 @@ static int mvusb_mdio_probe(struct usb_interface *interface,
 	mdio->write = mvusb_mdio_write;
 
 	usb_set_intfdata(interface, mvusb);
-	return of_mdiobus_register(mdio, dev->of_node);
+	ret = of_mdiobus_register(mdio, dev->of_node);
+	if (ret)
+		goto put_dev;
+
+	return 0;
+
+put_dev:
+	usb_put_dev(mvusb->udev);
+	return ret;
 }
 
 static void mvusb_mdio_disconnect(struct usb_interface *interface)

drivers/net/pcs/pcs-xpcs.c

@@ -1203,7 +1203,7 @@ static const struct xpcs_compat synopsys_xpcs_compat[DW_XPCS_INTERFACE_MAX] = {
 	[DW_XPCS_2500BASEX] = {
 		.supported = xpcs_2500basex_features,
 		.interface = xpcs_2500basex_interfaces,
-		.num_interfaces = ARRAY_SIZE(xpcs_2500basex_features),
+		.num_interfaces = ARRAY_SIZE(xpcs_2500basex_interfaces),
 		.an_mode = DW_2500BASEX,
 	},
 };

drivers/net/phy/bcm-phy-lib.h

@@ -40,6 +40,11 @@ static inline int bcm_phy_write_exp_sel(struct phy_device *phydev,
 	return bcm_phy_write_exp(phydev, reg | MII_BCM54XX_EXP_SEL_ER, val);
 }
 
+static inline int bcm_phy_read_exp_sel(struct phy_device *phydev, u16 reg)
+{
+	return bcm_phy_read_exp(phydev, reg | MII_BCM54XX_EXP_SEL_ER);
+}
+
 int bcm54xx_auxctl_write(struct phy_device *phydev, u16 regnum, u16 val);
 int bcm54xx_auxctl_read(struct phy_device *phydev, u16 regnum);
 

drivers/net/phy/bcm7xxx.c

@@ -486,7 +486,7 @@ static int bcm7xxx_16nm_ephy_afe_config(struct phy_device *phydev)
 	bcm_phy_write_misc(phydev, 0x0038, 0x0002, 0xede0);
 
 	/* Read CORE_EXPA9 */
-	tmp = bcm_phy_read_exp(phydev, 0x00a9);
+	tmp = bcm_phy_read_exp_sel(phydev, 0x00a9);
 	/* CORE_EXPA9[6:1] is rcalcode[5:0] */
 	rcalcode = (tmp & 0x7e) / 2;
 	/* Correct RCAL code + 1 is -1% rprogr, LP: +16 */

drivers/net/tap.c

@@ -742,7 +742,7 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control,
 
 	/* Move network header to the right position for VLAN tagged packets */
 	if (eth_type_vlan(skb->protocol) &&
-	    __vlan_get_protocol(skb, skb->protocol, &depth) != 0)
+	    vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0)
 		skb_set_network_header(skb, depth);
 
 	/* copy skb_ubuf_info for callback when skb has no error */
@@ -1197,7 +1197,7 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp)
 
 	/* Move network header to the right position for VLAN tagged packets */
 	if (eth_type_vlan(skb->protocol) &&
-	    __vlan_get_protocol(skb, skb->protocol, &depth) != 0)
+	    vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0)
 		skb_set_network_header(skb, depth);
 
 	rcu_read_lock();

include/linux/dim.h

@@ -236,8 +236,9 @@ void dim_park_tired(struct dim *dim);
  *
  * Calculate the delta between two samples (in data rates).
  * Takes into consideration counter wrap-around.
+ * Returned boolean indicates whether curr_stats are reliable.
  */
-void dim_calc_stats(struct dim_sample *start, struct dim_sample *end,
+bool dim_calc_stats(struct dim_sample *start, struct dim_sample *end,
 		    struct dim_stats *curr_stats);
 
 /**

include/linux/if_vlan.h

@@ -637,6 +637,23 @@ static inline __be16 vlan_get_protocol(const struct sk_buff *skb)
 	return __vlan_get_protocol(skb, skb->protocol, NULL);
 }
 
+/* This version of __vlan_get_protocol() also pulls mac header in skb->head */
+static inline __be16 vlan_get_protocol_and_depth(struct sk_buff *skb,
+						 __be16 type, int *depth)
+{
+	int maclen;
+
+	type = __vlan_get_protocol(skb, type, &maclen);
+
+	if (type) {
+		if (!pskb_may_pull(skb, maclen))
+			type = 0;
+		else if (depth)
+			*depth = maclen;
+	}
+	return type;
+}
+
 /* A getter for the SKB protocol field which will handle VLAN tags consistently
  * whether VLAN acceleration is enabled or not.
  */

include/net/bonding.h

@@ -233,7 +233,7 @@ struct bonding {
 	 */
 	spinlock_t mode_lock;
 	spinlock_t stats_lock;
-	u8	 send_peer_notif;
+	u32	 send_peer_notif;
 	u8       igmp_retrans;
 #ifdef CONFIG_PROC_FS
 	struct   proc_dir_entry *proc_entry;

include/net/sock.h

@@ -2718,7 +2718,7 @@ static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk,
 		__sock_recv_cmsgs(msg, sk, skb);
 	else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP)))
 		sock_write_timestamp(sk, skb->tstamp);
-	else if (unlikely(sk->sk_stamp == SK_DEFAULT_STAMP))
+	else if (unlikely(sock_read_timestamp(sk) == SK_DEFAULT_STAMP))
 		sock_write_timestamp(sk, 0);
 }
 

lib/dim/dim.c

@@ -54,7 +54,7 @@ void dim_park_tired(struct dim *dim)
 }
 EXPORT_SYMBOL(dim_park_tired);
 
-void dim_calc_stats(struct dim_sample *start, struct dim_sample *end,
+bool dim_calc_stats(struct dim_sample *start, struct dim_sample *end,
 		    struct dim_stats *curr_stats)
 {
 	/* u32 holds up to 71 minutes, should be enough */
@@ -66,7 +66,7 @@ void dim_calc_stats(struct dim_sample *start, struct dim_sample *end,
 			     start->comp_ctr);
 
 	if (!delta_us)
-		return;
+		return false;
 
 	curr_stats->ppms = DIV_ROUND_UP(npkts * USEC_PER_MSEC, delta_us);
 	curr_stats->bpms = DIV_ROUND_UP(nbytes * USEC_PER_MSEC, delta_us);
@@ -79,5 +79,6 @@ void dim_calc_stats(struct dim_sample *start, struct dim_sample *end,
 	else
 		curr_stats->cpe_ratio = 0;
 
+	return true;
 }
 EXPORT_SYMBOL(dim_calc_stats);

lib/dim/net_dim.c

@@ -227,7 +227,8 @@ void net_dim(struct dim *dim, struct dim_sample end_sample)
 				  dim->start_sample.event_ctr);
 		if (nevents < DIM_NEVENTS)
 			break;
-		dim_calc_stats(&dim->start_sample, &end_sample, &curr_stats);
+		if (!dim_calc_stats(&dim->start_sample, &end_sample, &curr_stats))
+			break;
 		if (net_dim_decision(&curr_stats, dim)) {
 			dim->state = DIM_APPLY_NEW_PROFILE;
 			schedule_work(&dim->work);

lib/dim/rdma_dim.c

@@ -88,7 +88,8 @@ void rdma_dim(struct dim *dim, u64 completions)
 		nevents = curr_sample->event_ctr - dim->start_sample.event_ctr;
 		if (nevents < DIM_NEVENTS)
 			break;
-		dim_calc_stats(&dim->start_sample, curr_sample, &curr_stats);
+		if (!dim_calc_stats(&dim->start_sample, curr_sample, &curr_stats))
+			break;
 		if (rdma_dim_decision(&curr_stats, dim)) {
 			dim->state = DIM_APPLY_NEW_PROFILE;
 			schedule_work(&dim->work);

net/bridge/br_forward.c

@@ -42,7 +42,7 @@ int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb
 	    eth_type_vlan(skb->protocol)) {
 		int depth;
 
-		if (!__vlan_get_protocol(skb, skb->protocol, &depth))
+		if (!vlan_get_protocol_and_depth(skb, skb->protocol, &depth))
 			goto drop;
 
 		skb_set_network_header(skb, depth);

net/core/datagram.c

@@ -807,18 +807,21 @@ __poll_t datagram_poll(struct file *file, struct socket *sock,
 {
 	struct sock *sk = sock->sk;
 	__poll_t mask;
+	u8 shutdown;
 
 	sock_poll_wait(file, sock, wait);
 	mask = 0;
 
 	/* exceptional events? */
-	if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
+	if (READ_ONCE(sk->sk_err) ||
+	    !skb_queue_empty_lockless(&sk->sk_error_queue))
 		mask |= EPOLLERR |
 			(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
 
-	if (sk->sk_shutdown & RCV_SHUTDOWN)
+	shutdown = READ_ONCE(sk->sk_shutdown);
+	if (shutdown & RCV_SHUTDOWN)
 		mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
-	if (sk->sk_shutdown == SHUTDOWN_MASK)
+	if (shutdown == SHUTDOWN_MASK)
 		mask |= EPOLLHUP;
 
 	/* readable? */
@@ -827,10 +830,12 @@ __poll_t datagram_poll(struct file *file, struct socket *sock,
 
 	/* Connection-based need to check for termination and startup */
 	if (connection_based(sk)) {
-		if (sk->sk_state == TCP_CLOSE)
+		int state = READ_ONCE(sk->sk_state);
+
+		if (state == TCP_CLOSE)
 			mask |= EPOLLHUP;
 		/* connection hasn't started yet? */
-		if (sk->sk_state == TCP_SYN_SENT)
+		if (state == TCP_SYN_SENT)
 			return mask;
 	}
 

net/core/dev.c

@@ -3335,7 +3335,7 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth)
 		type = eth->h_proto;
 	}
 
-	return __vlan_get_protocol(skb, type, depth);
+	return vlan_get_protocol_and_depth(skb, type, depth);
 }
 
 /* openvswitch calls this on rx path, so we need a different check.

net/core/skbuff.c

@@ -5298,7 +5298,7 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off)
 	u32 csum_end = (u32)start + (u32)off + sizeof(__sum16);
 	u32 csum_start = skb_headroom(skb) + (u32)start;
 
-	if (unlikely(csum_start > U16_MAX || csum_end > skb_headlen(skb))) {
+	if (unlikely(csum_start >= U16_MAX || csum_end > skb_headlen(skb))) {
 		net_warn_ratelimited("bad partial csum: csum=%u/%u headroom=%u headlen=%u\n",
 				     start, off, skb_headroom(skb), skb_headlen(skb));
 		return false;
@@ -5306,7 +5306,7 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off)
 	skb->ip_summed = CHECKSUM_PARTIAL;
 	skb->csum_start = csum_start;
 	skb->csum_offset = off;
-	skb_set_transport_header(skb, start);
+	skb->transport_header = csum_start;
 	return true;
 }
 EXPORT_SYMBOL_GPL(skb_partial_csum_set);

net/core/stream.c

@@ -73,8 +73,8 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p)
 		add_wait_queue(sk_sleep(sk), &wait);
 		sk->sk_write_pending++;
 		done = sk_wait_event(sk, timeo_p,
-				     !sk->sk_err &&
+				     !READ_ONCE(sk->sk_err) &&
-				     !((1 << sk->sk_state) &
+				     !((1 << READ_ONCE(sk->sk_state)) &
 				       ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)), &wait);
 		remove_wait_queue(sk_sleep(sk), &wait);
 		sk->sk_write_pending--;
@@ -87,9 +87,9 @@ EXPORT_SYMBOL(sk_stream_wait_connect);
  * sk_stream_closing - Return 1 if we still have things to send in our buffers.
  * @sk: socket to verify
  */
-static inline int sk_stream_closing(struct sock *sk)
+static int sk_stream_closing(const struct sock *sk)
 {
-	return (1 << sk->sk_state) &
+	return (1 << READ_ONCE(sk->sk_state)) &
 	       (TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK);
 }
 
@@ -142,8 +142,8 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
 
 		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 		sk->sk_write_pending++;
-		sk_wait_event(sk, &current_timeo, sk->sk_err ||
+		sk_wait_event(sk, &current_timeo, READ_ONCE(sk->sk_err) ||
-						  (sk->sk_shutdown & SEND_SHUTDOWN) ||
+						  (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) ||
 						  (sk_stream_memory_free(sk) &&
 						  !vm_wait), &wait);
 		sk->sk_write_pending--;

net/ipv4/af_inet.c

@@ -894,7 +894,7 @@ int inet_shutdown(struct socket *sock, int how)
 		   EPOLLHUP, even on eg. unconnected UDP sockets -- RR */
 		fallthrough;
 	default:
-		sk->sk_shutdown |= how;
+		WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | how);
 		if (sk->sk_prot->shutdown)
 			sk->sk_prot->shutdown(sk, how);
 		break;

net/ipv4/tcp.c

@@ -498,6 +498,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	__poll_t mask;
 	struct sock *sk = sock->sk;
 	const struct tcp_sock *tp = tcp_sk(sk);
+	u8 shutdown;
 	int state;
 
 	sock_poll_wait(file, sock, wait);
@@ -540,9 +541,10 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	 * NOTE. Check for TCP_CLOSE is added. The goal is to prevent
 	 * blocking on fresh not-connected or disconnected socket. --ANK
 	 */
-	if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE)
+	shutdown = READ_ONCE(sk->sk_shutdown);
+	if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE)
 		mask |= EPOLLHUP;
-	if (sk->sk_shutdown & RCV_SHUTDOWN)
+	if (shutdown & RCV_SHUTDOWN)
 		mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
 
 	/* Connected or passive Fast Open socket? */
@@ -559,7 +561,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 		if (tcp_stream_is_readable(sk, target))
 			mask |= EPOLLIN | EPOLLRDNORM;
 
-		if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
+		if (!(shutdown & SEND_SHUTDOWN)) {
 			if (__sk_stream_is_writeable(sk, 1)) {
 				mask |= EPOLLOUT | EPOLLWRNORM;
 			} else {  /* send SIGIO later */
@@ -2867,7 +2869,7 @@ void __tcp_close(struct sock *sk, long timeout)
 	int data_was_unread = 0;
 	int state;
 
-	sk->sk_shutdown = SHUTDOWN_MASK;
+	WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
 
 	if (sk->sk_state == TCP_LISTEN) {
 		tcp_set_state(sk, TCP_CLOSE);
@@ -3119,7 +3121,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 
 	inet_bhash2_reset_saddr(sk);
 
-	sk->sk_shutdown = 0;
+	WRITE_ONCE(sk->sk_shutdown, 0);
 	sock_reset_flag(sk, SOCK_DONE);
 	tp->srtt_us = 0;
 	tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
@@ -4649,7 +4651,7 @@ void tcp_done(struct sock *sk)
 	if (req)
 		reqsk_fastopen_remove(sk, req, false);
 
-	sk->sk_shutdown = SHUTDOWN_MASK;
+	WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
 
 	if (!sock_flag(sk, SOCK_DEAD))
 		sk->sk_state_change(sk);

net/ipv4/tcp_bpf.c

@@ -168,7 +168,7 @@ static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock,
 	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 	ret = sk_wait_event(sk, &timeo,
 			    !list_empty(&psock->ingress_msg) ||
-			    !skb_queue_empty(&sk->sk_receive_queue), &wait);
+			    !skb_queue_empty_lockless(&sk->sk_receive_queue), &wait);
 	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 	remove_wait_queue(sk_sleep(sk), &wait);
 	return ret;

net/ipv4/tcp_input.c

@@ -4362,7 +4362,7 @@ void tcp_fin(struct sock *sk)
 
 	inet_csk_schedule_ack(sk);
 
-	sk->sk_shutdown |= RCV_SHUTDOWN;
+	WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN);
 	sock_set_flag(sk, SOCK_DONE);
 
 	switch (sk->sk_state) {
@@ -6599,7 +6599,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 			break;
 
 		tcp_set_state(sk, TCP_FIN_WAIT2);
-		sk->sk_shutdown |= SEND_SHUTDOWN;
+		WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | SEND_SHUTDOWN);
 
 		sk_dst_confirm(sk);
 

net/llc/af_llc.c

@@ -583,7 +583,8 @@ static int llc_ui_wait_for_disc(struct sock *sk, long timeout)
 
 	add_wait_queue(sk_sleep(sk), &wait);
 	while (1) {
-		if (sk_wait_event(sk, &timeout, sk->sk_state == TCP_CLOSE, &wait))
+		if (sk_wait_event(sk, &timeout,
+				  READ_ONCE(sk->sk_state) == TCP_CLOSE, &wait))
 			break;
 		rc = -ERESTARTSYS;
 		if (signal_pending(current))
@@ -603,7 +604,8 @@ static bool llc_ui_wait_for_conn(struct sock *sk, long timeout)
 
 	add_wait_queue(sk_sleep(sk), &wait);
 	while (1) {
-		if (sk_wait_event(sk, &timeout, sk->sk_state != TCP_SYN_SENT, &wait))
+		if (sk_wait_event(sk, &timeout,
+				  READ_ONCE(sk->sk_state) != TCP_SYN_SENT, &wait))
 			break;
 		if (signal_pending(current) || !timeout)
 			break;
@@ -622,7 +624,7 @@ static int llc_ui_wait_for_busy_core(struct sock *sk, long timeout)
 	while (1) {
 		rc = 0;
 		if (sk_wait_event(sk, &timeout,
-				  (sk->sk_shutdown & RCV_SHUTDOWN) ||
+				  (READ_ONCE(sk->sk_shutdown) & RCV_SHUTDOWN) ||
 				  (!llc_data_accept_state(llc->state) &&
 				   !llc->remote_busy_flag &&
 				   !llc->p_flag), &wait))

net/netfilter/core.c

@@ -711,9 +711,11 @@ void nf_conntrack_destroy(struct nf_conntrack *nfct)
 
 	rcu_read_lock();
 	ct_hook = rcu_dereference(nf_ct_hook);
-	BUG_ON(ct_hook == NULL);
+	if (ct_hook)
-	ct_hook->destroy(nfct);
+		ct_hook->destroy(nfct);
 	rcu_read_unlock();
+
+	WARN_ON(!ct_hook);
 }
 EXPORT_SYMBOL(nf_conntrack_destroy);
 

net/netfilter/nf_conntrack_standalone.c

@@ -1218,11 +1218,12 @@ static int __init nf_conntrack_standalone_init(void)
 	nf_conntrack_htable_size_user = nf_conntrack_htable_size;
 #endif
 
+	nf_conntrack_init_end();
+
 	ret = register_pernet_subsys(&nf_conntrack_net_ops);
 	if (ret < 0)
 		goto out_pernet;
 
-	nf_conntrack_init_end();
 	return 0;
 
 out_pernet:

net/netfilter/nft_chain_filter.c

@@ -344,6 +344,12 @@ static void nft_netdev_event(unsigned long event, struct net_device *dev,
 		return;
 	}
 
+	/* UNREGISTER events are also happening on netns exit.
+	 *
+	 * Although nf_tables core releases all tables/chains, only this event
+	 * handler provides guarantee that hook->ops.dev is still accessible,
+	 * so we cannot skip exiting net namespaces.
+	 */
 	__nft_release_basechain(ctx);
 }
 
@@ -362,9 +368,6 @@ static int nf_tables_netdev_event(struct notifier_block *this,
 	    event != NETDEV_CHANGENAME)
 		return NOTIFY_DONE;
 
-	if (!check_net(ctx.net))
-		return NOTIFY_DONE;
-
 	nft_net = nft_pernet(ctx.net);
 	mutex_lock(&nft_net->commit_mutex);
 	list_for_each_entry(table, &nft_net->tables, list) {

net/netlink/af_netlink.c

@@ -1990,7 +1990,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 
 	skb_free_datagram(sk, skb);
 
-	if (nlk->cb_running &&
+	if (READ_ONCE(nlk->cb_running) &&
 	    atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) {
 		ret = netlink_dump(sk);
 		if (ret) {
@@ -2302,7 +2302,7 @@ static int netlink_dump(struct sock *sk)
 	if (cb->done)
 		cb->done(cb);
 
-	nlk->cb_running = false;
+	WRITE_ONCE(nlk->cb_running, false);
 	module = cb->module;
 	skb = cb->skb;
 	mutex_unlock(nlk->cb_mutex);
@@ -2365,7 +2365,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 			goto error_put;
 	}
 
-	nlk->cb_running = true;
+	WRITE_ONCE(nlk->cb_running, true);
 	nlk->dump_done_errno = INT_MAX;
 
 	mutex_unlock(nlk->cb_mutex);
@@ -2703,7 +2703,7 @@ static int netlink_native_seq_show(struct seq_file *seq, void *v)
 			   nlk->groups ? (u32)nlk->groups[0] : 0,
 			   sk_rmem_alloc_get(s),
 			   sk_wmem_alloc_get(s),
-			   nlk->cb_running,
+			   READ_ONCE(nlk->cb_running),
 			   refcount_read(&s->sk_refcnt),
 			   atomic_read(&s->sk_drops),
 			   sock_i_ino(s)

net/packet/af_packet.c

@@ -1934,10 +1934,8 @@ static void packet_parse_headers(struct sk_buff *skb, struct socket *sock)
 	/* Move network header to the right position for VLAN tagged packets */
 	if (likely(skb->dev->type == ARPHRD_ETHER) &&
 	    eth_type_vlan(skb->protocol) &&
-	    __vlan_get_protocol(skb, skb->protocol, &depth) != 0) {
+	    vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0)
-		if (pskb_may_pull(skb, depth))
+		skb_set_network_header(skb, depth);
-			skb_set_network_header(skb, depth);
-	}
 
 	skb_probe_transport_header(skb);
 }

net/smc/smc_close.c

@@ -67,8 +67,8 @@ static void smc_close_stream_wait(struct smc_sock *smc, long timeout)
 
 		rc = sk_wait_event(sk, &timeout,
 				   !smc_tx_prepared_sends(&smc->conn) ||
-				   sk->sk_err == ECONNABORTED ||
+				   READ_ONCE(sk->sk_err) == ECONNABORTED ||
-				   sk->sk_err == ECONNRESET ||
+				   READ_ONCE(sk->sk_err) == ECONNRESET ||
 				   smc->conn.killed,
 				   &wait);
 		if (rc)

net/smc/smc_rx.c

@@ -267,9 +267,9 @@ int smc_rx_wait(struct smc_sock *smc, long *timeo,
 	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 	add_wait_queue(sk_sleep(sk), &wait);
 	rc = sk_wait_event(sk, timeo,
-			   sk->sk_err ||
+			   READ_ONCE(sk->sk_err) ||
 			   cflags->peer_conn_abort ||
-			   sk->sk_shutdown & RCV_SHUTDOWN ||
+			   READ_ONCE(sk->sk_shutdown) & RCV_SHUTDOWN ||
 			   conn->killed ||
 			   fcrit(conn),
 			   &wait);

net/smc/smc_tx.c

@@ -113,8 +113,8 @@ static int smc_tx_wait(struct smc_sock *smc, int flags)
 			break; /* at least 1 byte of free & no urgent data */
 		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 		sk_wait_event(sk, &timeo,
-			      sk->sk_err ||
+			      READ_ONCE(sk->sk_err) ||
-			      (sk->sk_shutdown & SEND_SHUTDOWN) ||
+			      (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) ||
 			      smc_cdc_rxed_any_close(conn) ||
 			      (atomic_read(&conn->sndbuf_space) &&
 			       !conn->urg_tx_pend),

net/socket.c

@@ -2911,7 +2911,7 @@ static int do_recvmmsg(int fd, struct mmsghdr __user *mmsg,
 		 * error to return on the next call or if the
 		 * app asks about it using getsockopt(SO_ERROR).
 		 */
-		sock->sk->sk_err = -err;
+		WRITE_ONCE(sock->sk->sk_err, -err);
 	}
 out_put:
 	fput_light(sock->file, fput_needed);

net/tipc/socket.c

@@ -314,9 +314,9 @@ static void tsk_rej_rx_queue(struct sock *sk, int error)
 		tipc_sk_respond(sk, skb, error);
 }
 
-static bool tipc_sk_connected(struct sock *sk)
+static bool tipc_sk_connected(const struct sock *sk)
 {
-	return sk->sk_state == TIPC_ESTABLISHED;
+	return READ_ONCE(sk->sk_state) == TIPC_ESTABLISHED;
 }
 
 /* tipc_sk_type_connectionless - check if the socket is datagram socket

net/tls/tls_main.c

@@ -111,7 +111,8 @@ int wait_on_pending_writer(struct sock *sk, long *timeo)
 			break;
 		}
 
-		if (sk_wait_event(sk, timeo, !sk->sk_write_pending, &wait))
+		if (sk_wait_event(sk, timeo,
+				  !READ_ONCE(sk->sk_write_pending), &wait))
 			break;
 	}
 	remove_wait_queue(sk_sleep(sk), &wait);

net/unix/af_unix.c

@@ -603,7 +603,7 @@ static void unix_release_sock(struct sock *sk, int embrion)
 	/* Clear state */
 	unix_state_lock(sk);
 	sock_orphan(sk);
-	sk->sk_shutdown = SHUTDOWN_MASK;
+	WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
 	path	     = u->path;
 	u->path.dentry = NULL;
 	u->path.mnt = NULL;
@@ -628,7 +628,7 @@ static void unix_release_sock(struct sock *sk, int embrion)
 		if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) {
 			unix_state_lock(skpair);
 			/* No more writes */
-			skpair->sk_shutdown = SHUTDOWN_MASK;
+			WRITE_ONCE(skpair->sk_shutdown, SHUTDOWN_MASK);
 			if (!skb_queue_empty(&sk->sk_receive_queue) || embrion)
 				WRITE_ONCE(skpair->sk_err, ECONNRESET);
 			unix_state_unlock(skpair);
@@ -1442,7 +1442,7 @@ static long unix_wait_for_peer(struct sock *other, long timeo)
 
 	sched = !sock_flag(other, SOCK_DEAD) &&
 		!(other->sk_shutdown & RCV_SHUTDOWN) &&
-		unix_recvq_full(other);
+		unix_recvq_full_lockless(other);
 
 	unix_state_unlock(other);
 
@@ -3008,7 +3008,7 @@ static int unix_shutdown(struct socket *sock, int mode)
 	++mode;
 
 	unix_state_lock(sk);
-	sk->sk_shutdown |= mode;
+	WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | mode);
 	other = unix_peer(sk);
 	if (other)
 		sock_hold(other);
@@ -3028,7 +3028,7 @@ static int unix_shutdown(struct socket *sock, int mode)
 		if (mode&SEND_SHUTDOWN)
 			peer_mode |= RCV_SHUTDOWN;
 		unix_state_lock(other);
-		other->sk_shutdown |= peer_mode;
+		WRITE_ONCE(other->sk_shutdown, other->sk_shutdown | peer_mode);
 		unix_state_unlock(other);
 		other->sk_state_change(other);
 		if (peer_mode == SHUTDOWN_MASK)
@@ -3160,16 +3160,18 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa
 {
 	struct sock *sk = sock->sk;
 	__poll_t mask;
+	u8 shutdown;
 
 	sock_poll_wait(file, sock, wait);
 	mask = 0;
+	shutdown = READ_ONCE(sk->sk_shutdown);
 
 	/* exceptional events? */
 	if (READ_ONCE(sk->sk_err))
 		mask |= EPOLLERR;
-	if (sk->sk_shutdown == SHUTDOWN_MASK)
+	if (shutdown == SHUTDOWN_MASK)
 		mask |= EPOLLHUP;
-	if (sk->sk_shutdown & RCV_SHUTDOWN)
+	if (shutdown & RCV_SHUTDOWN)
 		mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
 
 	/* readable? */
@@ -3203,9 +3205,11 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
 	struct sock *sk = sock->sk, *other;
 	unsigned int writable;
 	__poll_t mask;
+	u8 shutdown;
 
 	sock_poll_wait(file, sock, wait);
 	mask = 0;
+	shutdown = READ_ONCE(sk->sk_shutdown);
 
 	/* exceptional events? */
 	if (READ_ONCE(sk->sk_err) ||
@@ -3213,9 +3217,9 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
 		mask |= EPOLLERR |
 			(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
 
-	if (sk->sk_shutdown & RCV_SHUTDOWN)
+	if (shutdown & RCV_SHUTDOWN)
 		mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
-	if (sk->sk_shutdown == SHUTDOWN_MASK)
+	if (shutdown == SHUTDOWN_MASK)
 		mask |= EPOLLHUP;
 
 	/* readable? */

tools/testing/selftests/drivers/net/bonding/bond_options.sh

@@ -6,6 +6,7 @@
 ALL_TESTS="
 	prio
 	arp_validate
+	num_grat_arp
 "
 
 REQUIRE_MZ=no
@@ -255,6 +256,55 @@ arp_validate()
 	arp_validate_ns "active-backup"
 }
 
+garp_test()
+{
+	local param="$1"
+	local active_slave exp_num real_num i
+	RET=0
+
+	# create bond
+	bond_reset "${param}"
+
+	bond_check_connection
+	[ $RET -ne 0 ] && log_test "num_grat_arp" "$retmsg"
+
+
+	# Add tc rules to count GARP number
+	for i in $(seq 0 2); do
+		tc -n ${g_ns} filter add dev s$i ingress protocol arp pref 1 handle 101 \
+			flower skip_hw arp_op request arp_sip ${s_ip4} arp_tip ${s_ip4} action pass
+	done
+
+	# Do failover
+	active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave")
+	ip -n ${s_ns} link set ${active_slave} down
+
+	exp_num=$(echo "${param}" | cut -f6 -d ' ')
+	sleep $((exp_num + 2))
+
+	active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave")
+
+	# check result
+	real_num=$(tc_rule_handle_stats_get "dev s${active_slave#eth} ingress" 101 ".packets" "-n ${g_ns}")
+	if [ "${real_num}" -ne "${exp_num}" ]; then
+		echo "$real_num garp packets sent on active slave ${active_slave}"
+		RET=1
+	fi
+
+	for i in $(seq 0 2); do
+		tc -n ${g_ns} filter del dev s$i ingress
+	done
+}
+
+num_grat_arp()
+{
+	local val
+	for val in 10 20 30 50; do
+		garp_test "mode active-backup miimon 100 num_grat_arp $val peer_notify_delay 1000"
+		log_test "num_grat_arp" "active-backup miimon num_grat_arp $val"
+	done
+}
+
 trap cleanup EXIT
 
 setup_prepare

tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh

@@ -61,6 +61,8 @@ server_create()
 		ip -n ${g_ns} link set s${i} up
 		ip -n ${g_ns} link set s${i} master br0
 		ip -n ${s_ns} link set eth${i} master bond0
+
+		tc -n ${g_ns} qdisc add dev s${i} clsact
 	done
 
 	ip -n ${s_ns} link set bond0 up

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

@@ -791,8 +791,9 @@ tc_rule_handle_stats_get()
 	local id=$1; shift
 	local handle=$1; shift
 	local selector=${1:-.packets}; shift
+	local netns=${1:-""}; shift
 
-	tc -j -s filter show $id \
+	tc $netns -j -s filter show $id \
 	    | jq ".[] | select(.options.handle == $handle) | \
 		  .options.actions[0].stats$selector"
 }

tools/testing/selftests/netfilter/nft_flowtable.sh

@@ -188,6 +188,26 @@ if [ $? -ne 0 ]; then
 	exit $ksft_skip
 fi
 
+ip netns exec $ns2 nft -f - <<EOF
+table inet filter {
+   counter ip4dscp0 { }
+   counter ip4dscp3 { }
+
+   chain input {
+      type filter hook input priority 0; policy accept;
+      meta l4proto tcp goto {
+	      ip dscp cs3 counter name ip4dscp3 accept
+	      ip dscp 0 counter name ip4dscp0 accept
+      }
+   }
+}
+EOF
+
+if [ $? -ne 0 ]; then
+	echo "SKIP: Could not load nft ruleset"
+	exit $ksft_skip
+fi
+
 # test basic connectivity
 if ! ip netns exec $ns1 ping -c 1 -q 10.0.2.99 > /dev/null; then
   echo "ERROR: $ns1 cannot reach ns2" 1>&2
@@ -255,6 +275,60 @@ check_counters()
 	fi
 }
 
+check_dscp()
+{
+	local what=$1
+	local ok=1
+
+	local counter=$(ip netns exec $ns2 nft reset counter inet filter ip4dscp3 | grep packets)
+
+	local pc4=${counter%*bytes*}
+	local pc4=${pc4#*packets}
+
+	local counter=$(ip netns exec $ns2 nft reset counter inet filter ip4dscp0 | grep packets)
+	local pc4z=${counter%*bytes*}
+	local pc4z=${pc4z#*packets}
+
+	case "$what" in
+	"dscp_none")
+		if [ $pc4 -gt 0 ] || [ $pc4z -eq 0 ]; then
+			echo "FAIL: dscp counters do not match, expected dscp3 == 0, dscp0 > 0, but got $pc4,$pc4z" 1>&2
+			ret=1
+			ok=0
+		fi
+		;;
+	"dscp_fwd")
+		if [ $pc4 -eq 0 ] || [ $pc4z -eq 0 ]; then
+			echo "FAIL: dscp counters do not match, expected dscp3 and dscp0 > 0 but got $pc4,$pc4z" 1>&2
+			ret=1
+			ok=0
+		fi
+		;;
+	"dscp_ingress")
+		if [ $pc4 -eq 0 ] || [ $pc4z -gt 0 ]; then
+			echo "FAIL: dscp counters do not match, expected dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2
+			ret=1
+			ok=0
+		fi
+		;;
+	"dscp_egress")
+		if [ $pc4 -eq 0 ] || [ $pc4z -gt 0 ]; then
+			echo "FAIL: dscp counters do not match, expected dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2
+			ret=1
+			ok=0
+		fi
+		;;
+	*)
+		echo "FAIL: Unknown DSCP check" 1>&2
+		ret=1
+		ok=0
+	esac
+
+	if [ $ok -eq 1 ] ;then
+		echo "PASS: $what: dscp packet counters match"
+	fi
+}
+
 check_transfer()
 {
 	in=$1
@@ -286,17 +360,26 @@ test_tcp_forwarding_ip()
 	ip netns exec $nsa nc -w 4 "$dstip" "$dstport" < "$nsin" > "$ns1out" &
 	cpid=$!
 
-	sleep 3
+	sleep 1
 
-	if ps -p $lpid > /dev/null;then
+	prev="$(ls -l $ns1out $ns2out)"
+	sleep 1
+
+	while [[ "$prev" != "$(ls -l $ns1out $ns2out)" ]]; do
+		sleep 1;
+		prev="$(ls -l $ns1out $ns2out)"
+	done
+
+	if test -d /proc/"$lpid"/; then
 		kill $lpid
 	fi
 
-	if ps -p $cpid > /dev/null;then
+	if test -d /proc/"$cpid"/; then
 		kill $cpid
 	fi
 
-	wait
+	wait $lpid
+	wait $cpid
 
 	if ! check_transfer "$nsin" "$ns2out" "ns1 -> ns2"; then
 		lret=1
@@ -316,6 +399,51 @@ test_tcp_forwarding()
 	return $?
 }
 
+test_tcp_forwarding_set_dscp()
+{
+	check_dscp "dscp_none"
+
+ip netns exec $nsr1 nft -f - <<EOF
+table netdev dscpmangle {
+   chain setdscp0 {
+      type filter hook ingress device "veth0" priority 0; policy accept
+	ip dscp set cs3
+  }
+}
+EOF
+if [ $? -eq 0 ]; then
+	test_tcp_forwarding_ip "$1" "$2"  10.0.2.99 12345
+	check_dscp "dscp_ingress"
+
+	ip netns exec $nsr1 nft delete table netdev dscpmangle
+else
+	echo "SKIP: Could not load netdev:ingress for veth0"
+fi
+
+ip netns exec $nsr1 nft -f - <<EOF
+table netdev dscpmangle {
+   chain setdscp0 {
+      type filter hook egress device "veth1" priority 0; policy accept
+      ip dscp set cs3
+  }
+}
+EOF
+if [ $? -eq 0 ]; then
+	test_tcp_forwarding_ip "$1" "$2"  10.0.2.99 12345
+	check_dscp "dscp_egress"
+
+	ip netns exec $nsr1 nft flush table netdev dscpmangle
+else
+	echo "SKIP: Could not load netdev:egress for veth1"
+fi
+
+	# partial.  If flowtable really works, then both dscp-is-0 and dscp-is-cs3
+	# counters should have seen packets (before and after ft offload kicks in).
+	ip netns exec $nsr1 nft -a insert rule inet filter forward ip dscp set cs3
+	test_tcp_forwarding_ip "$1" "$2"  10.0.2.99 12345
+	check_dscp "dscp_fwd"
+}
+
 test_tcp_forwarding_nat()
 {
 	local lret
@@ -385,6 +513,11 @@ table ip nat {
 }
 EOF
 
+if ! test_tcp_forwarding_set_dscp $ns1 $ns2 0 ""; then
+	echo "FAIL: flow offload for ns1/ns2 with dscp update" 1>&2
+	exit 0
+fi
+
 if ! test_tcp_forwarding_nat $ns1 $ns2 0 ""; then
 	echo "FAIL: flow offload for ns1/ns2 with NAT" 1>&2
 	ip netns exec $nsr1 nft list ruleset
@@ -489,8 +622,8 @@ ip -net $nsr1 addr add 10.0.1.1/24 dev veth0
 ip -net $nsr1 addr add dead:1::1/64 dev veth0
 ip -net $nsr1 link set up dev veth0
 
-KEY_SHA="0x"$(ps -xaf | sha1sum | cut -d " " -f 1)
+KEY_SHA="0x"$(ps -af | sha1sum | cut -d " " -f 1)
-KEY_AES="0x"$(ps -xaf | md5sum | cut -d " " -f 1)
+KEY_AES="0x"$(ps -af | md5sum | cut -d " " -f 1)
 SPI1=$RANDOM
 SPI2=$RANDOM