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

Merge in overtime fixes, no conflicts.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

26 files changed, 444 insertions, 162 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index e5ce4f60786e..949d0b49a0bd 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10770,7 +10770,6 @@ L7 BPF FRAMEWORK
 M:	John Fastabend <john.fastabend@gmail.com>
 M:	Daniel Borkmann <daniel@iogearbox.net>
 M:	Jakub Sitnicki <jakub@cloudflare.com>
-M:	Lorenz Bauer <lmb@cloudflare.com>
 L:	netdev@vger.kernel.org
 L:	bpf@vger.kernel.org
 S:	Maintained
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 9a41145dadfc..2dd79af9411b 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -76,7 +76,7 @@ static inline void bcmgenet_writel(u32 value, void __iomem *offset)
 	if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
 		__raw_writel(value, offset);
 	else
-		writel_relaxed(value, offset);
+		writel(value, offset);
 }
 
 static inline u32 bcmgenet_readl(void __iomem *offset)
@@ -84,7 +84,7 @@ static inline u32 bcmgenet_readl(void __iomem *offset)
 	if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
 		return __raw_readl(offset);
 	else
-		return readl_relaxed(offset);
+		return readl(offset);
 }
 
 static inline void dmadesc_set_length_status(struct bcmgenet_priv *priv,
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 869a4fe17c7c..77683909ca3d 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1430,6 +1430,15 @@ static int __ibmvnic_open(struct net_device *netdev)
 		return rc;
 	}
 
+	adapter->tx_queues_active = true;
+
+	/* Since queues were stopped until now, there shouldn't be any
+	 * one in ibmvnic_complete_tx() or ibmvnic_xmit() so maybe we
+	 * don't need the synchronize_rcu()? Leaving it for consistency
+	 * with setting ->tx_queues_active = false.
+	 */
+	synchronize_rcu();
+
 	netif_tx_start_all_queues(netdev);
 
 	if (prev_state == VNIC_CLOSED) {
@@ -1604,6 +1613,14 @@ static void ibmvnic_cleanup(struct net_device *netdev)
 	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
 
 	/* ensure that transmissions are stopped if called by do_reset */
+
+	adapter->tx_queues_active = false;
+
+	/* Ensure complete_tx() and ibmvnic_xmit() see ->tx_queues_active
+	 * update so they don't restart a queue after we stop it below.
+	 */
+	synchronize_rcu();
+
 	if (test_bit(0, &adapter->resetting))
 		netif_tx_disable(netdev);
 	else
@@ -1843,14 +1860,21 @@ static void ibmvnic_tx_scrq_clean_buffer(struct ibmvnic_adapter *adapter,
 		tx_buff->skb = NULL;
 		adapter->netdev->stats.tx_dropped++;
 	}
+
 	ind_bufp->index = 0;
+
 	if (atomic_sub_return(entries, &tx_scrq->used) <=
 	    (adapter->req_tx_entries_per_subcrq / 2) &&
-	    __netif_subqueue_stopped(adapter->netdev, queue_num) &&
-	    !test_bit(0, &adapter->resetting)) {
-		netif_wake_subqueue(adapter->netdev, queue_num);
-		netdev_dbg(adapter->netdev, "Started queue %d\n",
-			   queue_num);
+	    __netif_subqueue_stopped(adapter->netdev, queue_num)) {
+		rcu_read_lock();
+
+		if (adapter->tx_queues_active) {
+			netif_wake_subqueue(adapter->netdev, queue_num);
+			netdev_dbg(adapter->netdev, "Started queue %d\n",
+				   queue_num);
+		}
+
+		rcu_read_unlock();
 	}
 }
 
@@ -1905,11 +1929,12 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	int index = 0;
 	u8 proto = 0;
 
-	tx_scrq = adapter->tx_scrq[queue_num];
-	txq = netdev_get_tx_queue(netdev, queue_num);
-	ind_bufp = &tx_scrq->ind_buf;
-
-	if (test_bit(0, &adapter->resetting)) {
+	/* If a reset is in progress, drop the packet since
+	 * the scrqs may get torn down. Otherwise use the
+	 * rcu to ensure reset waits for us to complete.
+	 */
+	rcu_read_lock();
+	if (!adapter->tx_queues_active) {
 		dev_kfree_skb_any(skb);
 
 		tx_send_failed++;
@@ -1918,6 +1943,10 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 		goto out;
 	}
 
+	tx_scrq = adapter->tx_scrq[queue_num];
+	txq = netdev_get_tx_queue(netdev, queue_num);
+	ind_bufp = &tx_scrq->ind_buf;
+
 	if (ibmvnic_xmit_workarounds(skb, netdev)) {
 		tx_dropped++;
 		tx_send_failed++;
@@ -1925,6 +1954,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 		ibmvnic_tx_scrq_flush(adapter, tx_scrq);
 		goto out;
 	}
+
 	if (skb_is_gso(skb))
 		tx_pool = &adapter->tso_pool[queue_num];
 	else
@@ -2079,6 +2109,7 @@ tx_err:
 		netif_carrier_off(netdev);
 	}
 out:
+	rcu_read_unlock();
 	netdev->stats.tx_dropped += tx_dropped;
 	netdev->stats.tx_bytes += tx_bytes;
 	netdev->stats.tx_packets += tx_packets;
@@ -3749,9 +3780,15 @@ restart_loop:
 		    (adapter->req_tx_entries_per_subcrq / 2) &&
 		    __netif_subqueue_stopped(adapter->netdev,
 					     scrq->pool_index)) {
-			netif_wake_subqueue(adapter->netdev, scrq->pool_index);
-			netdev_dbg(adapter->netdev, "Started queue %d\n",
-				   scrq->pool_index);
+			rcu_read_lock();
+			if (adapter->tx_queues_active) {
+				netif_wake_subqueue(adapter->netdev,
+						    scrq->pool_index);
+				netdev_dbg(adapter->netdev,
+					   "Started queue %d\n",
+					   scrq->pool_index);
+			}
+			rcu_read_unlock();
 		}
 	}
 
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index fa2d607a7b1b..8f5cefb932dd 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -1006,11 +1006,14 @@ struct ibmvnic_adapter {
 	struct work_struct ibmvnic_reset;
 	struct delayed_work ibmvnic_delayed_reset;
 	unsigned long resetting;
-	bool napi_enabled, from_passive_init;
-	bool login_pending;
 	/* last device reset time */
 	unsigned long last_reset_time;
 
+	bool napi_enabled;
+	bool from_passive_init;
+	bool login_pending;
+	/* protected by rcu */
+	bool tx_queues_active;
 	bool failover_pending;
 	bool force_reset_recovery;
 
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index e9aa1fb43c3a..b0b27bfcd7a2 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -290,6 +290,7 @@ enum ice_pf_state {
 	ICE_LINK_DEFAULT_OVERRIDE_PENDING,
 	ICE_PHY_INIT_COMPLETE,
 	ICE_FD_VF_FLUSH_CTX,		/* set at FD Rx IRQ or timeout */
+	ICE_AUX_ERR_PENDING,
 	ICE_STATE_NBITS		/* must be last */
 };
 
@@ -557,6 +558,7 @@ struct ice_pf {
 	wait_queue_head_t reset_wait_queue;
 
 	u32 hw_csum_rx_error;
+	u32 oicr_err_reg;
 	u16 oicr_idx;		/* Other interrupt cause MSIX vector index */
 	u16 num_avail_sw_msix;	/* remaining MSIX SW vectors left unclaimed */
 	u16 max_pf_txqs;	/* Total Tx queues PF wide */
diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c
index 73aa520317d4..25a436d342c2 100644
--- a/drivers/net/ethernet/intel/ice/ice_idc.c
+++ b/drivers/net/ethernet/intel/ice/ice_idc.c
@@ -34,6 +34,9 @@ void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_event *event)
 {
 	struct iidc_auxiliary_drv *iadrv;
 
+	if (WARN_ON_ONCE(!in_task()))
+		return;
+
 	if (!pf->adev)
 		return;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 0a2e695f3bb9..b588d7995631 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2278,6 +2278,19 @@ static void ice_service_task(struct work_struct *work)
 		return;
 	}
 
+	if (test_and_clear_bit(ICE_AUX_ERR_PENDING, pf->state)) {
+		struct iidc_event *event;
+
+		event = kzalloc(sizeof(*event), GFP_KERNEL);
+		if (event) {
+			set_bit(IIDC_EVENT_CRIT_ERR, event->type);
+			/* report the entire OICR value to AUX driver */
+			swap(event->reg, pf->oicr_err_reg);
+			ice_send_event_to_aux(pf, event);
+			kfree(event);
+		}
+	}
+
 	if (test_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) {
 		/* Plug aux device per request */
 		ice_plug_aux_dev(pf);
@@ -3064,17 +3077,9 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 
 #define ICE_AUX_CRIT_ERR (PFINT_OICR_PE_CRITERR_M | PFINT_OICR_HMC_ERR_M | PFINT_OICR_PE_PUSH_M)
 	if (oicr & ICE_AUX_CRIT_ERR) {
-		struct iidc_event *event;
-
+		pf->oicr_err_reg |= oicr;
+		set_bit(ICE_AUX_ERR_PENDING, pf->state);
 		ena_mask &= ~ICE_AUX_CRIT_ERR;
-		event = kzalloc(sizeof(*event), GFP_ATOMIC);
-		if (event) {
-			set_bit(IIDC_EVENT_CRIT_ERR, event->type);
-			/* report the entire OICR value to AUX driver */
-			event->reg = oicr;
-			ice_send_event_to_aux(pf, event);
-			kfree(event);
-		}
 	}
 
 	/* Report any remaining unexpected interrupts */
diff --git a/drivers/net/wwan/qcom_bam_dmux.c b/drivers/net/wwan/qcom_bam_dmux.c
index 5dfa2eba6014..17d46f4d2913 100644
--- a/drivers/net/wwan/qcom_bam_dmux.c
+++ b/drivers/net/wwan/qcom_bam_dmux.c
@@ -755,7 +755,7 @@ static int __maybe_unused bam_dmux_runtime_resume(struct device *dev)
 		return 0;
 
 	dmux->tx = dma_request_chan(dev, "tx");
-	if (IS_ERR(dmux->rx)) {
+	if (IS_ERR(dmux->tx)) {
 		dev_err(dev, "Failed to request TX DMA channel: %pe\n", dmux->tx);
 		dmux->tx = NULL;
 		bam_dmux_runtime_suspend(dev);
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index bd59e950f4d6..64daafd1fc41 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -10,6 +10,8 @@
 #include <linux/netfilter/nf_conntrack_tuple_common.h>
 #include <net/flow_offload.h>
 #include <net/dst.h>
+#include <linux/if_pppox.h>
+#include <linux/ppp_defs.h>
 
 struct nf_flowtable;
 struct nf_flow_rule;
@@ -317,4 +319,20 @@ int nf_flow_rule_route_ipv6(struct net *net, const struct flow_offload *flow,
 int nf_flow_table_offload_init(void);
 void nf_flow_table_offload_exit(void);
 
+static inline __be16 nf_flow_pppoe_proto(const struct sk_buff *skb)
+{
+	__be16 proto;
+
+	proto = *((__be16 *)(skb_mac_header(skb) + ETH_HLEN +
+			     sizeof(struct pppoe_hdr)));
+	switch (proto) {
+	case htons(PPP_IP):
+		return htons(ETH_P_IP);
+	case htons(PPP_IPV6):
+		return htons(ETH_P_IPV6);
+	}
+
+	return 0;
+}
+
 #endif /* _NF_FLOW_TABLE_H */
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 6bd097180772..992b6e5d85d7 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -89,18 +89,20 @@ again:
 			sk = s->sk;
 			if (!sk) {
 				spin_unlock_bh(&ax25_list_lock);
-				s->ax25_dev = NULL;
 				ax25_disconnect(s, ENETUNREACH);
+				s->ax25_dev = NULL;
 				spin_lock_bh(&ax25_list_lock);
 				goto again;
 			}
 			sock_hold(sk);
 			spin_unlock_bh(&ax25_list_lock);
 			lock_sock(sk);
-			s->ax25_dev = NULL;
-			dev_put_track(ax25_dev->dev, &ax25_dev->dev_tracker);
-			ax25_dev_put(ax25_dev);
 			ax25_disconnect(s, ENETUNREACH);
+			s->ax25_dev = NULL;
+			if (sk->sk_socket) {
+				dev_put_track(ax25_dev->dev, &ax25_dev->dev_tracker);
+				ax25_dev_put(ax25_dev);
+			}
 			release_sock(sk);
 			spin_lock_bh(&ax25_list_lock);
 			sock_put(sk);
@@ -979,14 +981,20 @@ static int ax25_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
 	ax25_cb *ax25;
+	ax25_dev *ax25_dev;
 
 	if (sk == NULL)
 		return 0;
 
 	sock_hold(sk);
-	sock_orphan(sk);
 	lock_sock(sk);
+	sock_orphan(sk);
 	ax25 = sk_to_ax25(sk);
+	ax25_dev = ax25->ax25_dev;
+	if (ax25_dev) {
+		dev_put_track(ax25_dev->dev, &ax25_dev->dev_tracker);
+		ax25_dev_put(ax25_dev);
+	}
 
 	if (sk->sk_type == SOCK_SEQPACKET) {
 		switch (ax25->state) {
diff --git a/net/ax25/ax25_subr.c b/net/ax25/ax25_subr.c
index 15ab812c4fe4..3a476e4f6cd0 100644
--- a/net/ax25/ax25_subr.c
+++ b/net/ax25/ax25_subr.c
@@ -261,12 +261,20 @@ void ax25_disconnect(ax25_cb *ax25, int reason)
 {
 	ax25_clear_queues(ax25);
 
-	if (!ax25->sk || !sock_flag(ax25->sk, SOCK_DESTROY))
-		ax25_stop_heartbeat(ax25);
-	ax25_stop_t1timer(ax25);
-	ax25_stop_t2timer(ax25);
-	ax25_stop_t3timer(ax25);
-	ax25_stop_idletimer(ax25);
+	if (reason == ENETUNREACH) {
+		del_timer_sync(&ax25->timer);
+		del_timer_sync(&ax25->t1timer);
+		del_timer_sync(&ax25->t2timer);
+		del_timer_sync(&ax25->t3timer);
+		del_timer_sync(&ax25->idletimer);
+	} else {
+		if (!ax25->sk || !sock_flag(ax25->sk, SOCK_DESTROY))
+			ax25_stop_heartbeat(ax25);
+		ax25_stop_t1timer(ax25);
+		ax25_stop_t2timer(ax25);
+		ax25_stop_t3timer(ax25);
+		ax25_stop_idletimer(ax25);
+	}
 
 	ax25->state = AX25_STATE_0;
 
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 47b334226f4e..ca6af86964bc 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -1786,6 +1786,10 @@ void dsa_switch_shutdown(struct dsa_switch *ds)
 	struct dsa_port *dp;
 
 	mutex_lock(&dsa2_mutex);
+
+	if (!ds->setup)
+		goto out;
+
 	rtnl_lock();
 
 	dsa_switch_for_each_user_port(dp, ds) {
@@ -1802,6 +1806,7 @@ void dsa_switch_shutdown(struct dsa_switch *ds)
 		dp->master->dsa_ptr = NULL;
 
 	rtnl_unlock();
+out:
 	mutex_unlock(&dsa2_mutex);
 }
 EXPORT_SYMBOL_GPL(dsa_switch_shutdown);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 63f3256a407d..98c6f3429593 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -498,6 +498,15 @@ void __ip_select_ident(struct net *net, struct iphdr *iph, int segs)
 }
 EXPORT_SYMBOL(__ip_select_ident);
 
+static void ip_rt_fix_tos(struct flowi4 *fl4)
+{
+	__u8 tos = RT_FL_TOS(fl4);
+
+	fl4->flowi4_tos = tos & IPTOS_RT_MASK;
+	fl4->flowi4_scope = tos & RTO_ONLINK ?
+			    RT_SCOPE_LINK : RT_SCOPE_UNIVERSE;
+}
+
 static void __build_flow_key(const struct net *net, struct flowi4 *fl4,
 			     const struct sock *sk,
 			     const struct iphdr *iph,
@@ -823,6 +832,7 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf
 	rt = (struct rtable *) dst;
 
 	__build_flow_key(net, &fl4, sk, iph, oif, tos, prot, mark, 0);
+	ip_rt_fix_tos(&fl4);
 	__ip_do_redirect(rt, skb, &fl4, true);
 }
 
@@ -1047,6 +1057,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
 	struct flowi4 fl4;
 
 	ip_rt_build_flow_key(&fl4, sk, skb);
+	ip_rt_fix_tos(&fl4);
 
 	/* Don't make lookup fail for bridged encapsulations */
 	if (skb && netif_is_any_bridge_port(skb->dev))
@@ -1121,6 +1132,8 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 			goto out;
 
 		new = true;
+	} else {
+		ip_rt_fix_tos(&fl4);
 	}
 
 	__ip_rt_update_pmtu((struct rtable *)xfrm_dst_path(&rt->dst), &fl4, mtu);
@@ -2609,7 +2622,6 @@ add:
 struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
 					const struct sk_buff *skb)
 {
-	__u8 tos = RT_FL_TOS(fl4);
 	struct fib_result res = {
 		.type		= RTN_UNSPEC,
 		.fi		= NULL,
@@ -2619,9 +2631,7 @@ struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
 	struct rtable *rth;
 
 	fl4->flowi4_iif = LOOPBACK_IFINDEX;
-	fl4->flowi4_tos = tos & IPTOS_RT_MASK;
-	fl4->flowi4_scope = ((tos & RTO_ONLINK) ?
-			 RT_SCOPE_LINK : RT_SCOPE_UNIVERSE);
+	ip_rt_fix_tos(fl4);
 
 	rcu_read_lock();
 	rth = ip_route_output_key_hash_rcu(net, fl4, &res, skb);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 81aaa7da3e8c..9ede847f4199 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3730,6 +3730,7 @@ static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb)
  */
 static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 {
+	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_fastopen_request *fo = tp->fastopen_req;
 	int space, err = 0;
@@ -3744,8 +3745,10 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 	 * private TCP options. The cost is reduced data space in SYN :(
 	 */
 	tp->rx_opt.mss_clamp = tcp_mss_clamp(tp, tp->rx_opt.mss_clamp);
+	/* Sync mss_cache after updating the mss_clamp */
+	tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
 
-	space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) -
+	space = __tcp_mtu_to_mss(sk, icsk->icsk_pmtu_cookie) -
 		MAX_TCP_OPTION_SPACE;
 
 	space = min_t(size_t, space, fo->size);
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 101aeebeb9eb..0cbea3b6d0a4 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1199,6 +1199,7 @@ static struct sk_buff *__mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, g
 		tcp_skb_entail(ssk, skb);
 		return skb;
 	}
+	tcp_skb_tsorted_anchor_cleanup(skb);
 	kfree_skb(skb);
 	return NULL;
 }
diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c
index 5c57ade6bd05..0ccabf3fa6aa 100644
--- a/net/netfilter/nf_flow_table_inet.c
+++ b/net/netfilter/nf_flow_table_inet.c
@@ -6,12 +6,29 @@
 #include <linux/rhashtable.h>
 #include <net/netfilter/nf_flow_table.h>
 #include <net/netfilter/nf_tables.h>
+#include <linux/if_vlan.h>
 
 static unsigned int
 nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb,
 			  const struct nf_hook_state *state)
 {
+	struct vlan_ethhdr *veth;
+	__be16 proto;
+
 	switch (skb->protocol) {
+	case htons(ETH_P_8021Q):
+		veth = (struct vlan_ethhdr *)skb_mac_header(skb);
+		proto = veth->h_vlan_encapsulated_proto;
+		break;
+	case htons(ETH_P_PPP_SES):
+		proto = nf_flow_pppoe_proto(skb);
+		break;
+	default:
+		proto = skb->protocol;
+		break;
+	}
+
+	switch (proto) {
 	case htons(ETH_P_IP):
 		return nf_flow_offload_ip_hook(priv, skb, state);
 	case htons(ETH_P_IPV6):
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index 010b0b4eb05d..32c0eb1b4821 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -8,8 +8,6 @@
 #include <linux/ipv6.h>
 #include <linux/netdevice.h>
 #include <linux/if_ether.h>
-#include <linux/if_pppox.h>
-#include <linux/ppp_defs.h>
 #include <net/ip.h>
 #include <net/ipv6.h>
 #include <net/ip6_route.h>
@@ -260,22 +258,6 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb,
 	return NF_STOLEN;
 }
 
-static inline __be16 nf_flow_pppoe_proto(const struct sk_buff *skb)
-{
-	__be16 proto;
-
-	proto = *((__be16 *)(skb_mac_header(skb) + ETH_HLEN +
-			     sizeof(struct pppoe_hdr)));
-	switch (proto) {
-	case htons(PPP_IP):
-		return htons(ETH_P_IP);
-	case htons(PPP_IPV6):
-		return htons(ETH_P_IPV6);
-	}
-
-	return 0;
-}
-
 static bool nf_flow_skb_encap_protocol(const struct sk_buff *skb, __be16 proto,
 				       u32 *offset)
 {
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index a97e112fe406..c55ccd3cf2f8 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -9363,17 +9363,23 @@ int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest)
 }
 EXPORT_SYMBOL_GPL(nft_parse_u32_check);
 
-static unsigned int nft_parse_register(const struct nlattr *attr)
+static unsigned int nft_parse_register(const struct nlattr *attr, u32 *preg)
 {
 	unsigned int reg;
 
 	reg = ntohl(nla_get_be32(attr));
 	switch (reg) {
 	case NFT_REG_VERDICT...NFT_REG_4:
-		return reg * NFT_REG_SIZE / NFT_REG32_SIZE;
+		*preg = reg * NFT_REG_SIZE / NFT_REG32_SIZE;
+		break;
+	case NFT_REG32_00...NFT_REG32_15:
+		*preg = reg + NFT_REG_SIZE / NFT_REG32_SIZE - NFT_REG32_00;
+		break;
 	default:
-		return reg + NFT_REG_SIZE / NFT_REG32_SIZE - NFT_REG32_00;
+		return -ERANGE;
 	}
+
+	return 0;
 }
 
 /**
@@ -9415,7 +9421,10 @@ int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len)
 	u32 reg;
 	int err;
 
-	reg = nft_parse_register(attr);
+	err = nft_parse_register(attr, &reg);
+	if (err < 0)
+		return err;
+
 	err = nft_validate_register_load(reg, len);
 	if (err < 0)
 		return err;
@@ -9470,7 +9479,10 @@ int nft_parse_register_store(const struct nft_ctx *ctx,
 	int err;
 	u32 reg;
 
-	reg = nft_parse_register(attr);
+	err = nft_parse_register(attr, &reg);
+	if (err < 0)
+		return err;
+
 	err = nft_validate_register_store(ctx, reg, data, type, len);
 	if (err < 0)
 		return err;
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index c6c05b2412c4..53f40e473855 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -215,7 +215,7 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv)
 	const struct nft_rule_dp *rule, *last_rule;
 	const struct net *net = nft_net(pkt);
 	const struct nft_expr *expr, *last;
-	struct nft_regs regs;
+	struct nft_regs regs = {};
 	unsigned int stackptr = 0;
 	struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE];
 	bool genbit = READ_ONCE(net->nft.gencursor);
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 7b344035bfe3..47a876ccd288 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -159,6 +159,8 @@ EXPORT_SYMBOL(do_trace_netlink_extack);
 
 static inline u32 netlink_group_mask(u32 group)
 {
+	if (group > 32)
+		return 0;
 	return group ? 1 << (group - 1) : 0;
 }
 
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index c07afff57dd3..4a947c13c813 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -734,6 +734,57 @@ static bool skb_nfct_cached(struct net *net,
 }
 
 #if IS_ENABLED(CONFIG_NF_NAT)
+static void ovs_nat_update_key(struct sw_flow_key *key,
+			       const struct sk_buff *skb,
+			       enum nf_nat_manip_type maniptype)
+{
+	if (maniptype == NF_NAT_MANIP_SRC) {
+		__be16 src;
+
+		key->ct_state |= OVS_CS_F_SRC_NAT;
+		if (key->eth.type == htons(ETH_P_IP))
+			key->ipv4.addr.src = ip_hdr(skb)->saddr;
+		else if (key->eth.type == htons(ETH_P_IPV6))
+			memcpy(&key->ipv6.addr.src, &ipv6_hdr(skb)->saddr,
+			       sizeof(key->ipv6.addr.src));
+		else
+			return;
+
+		if (key->ip.proto == IPPROTO_UDP)
+			src = udp_hdr(skb)->source;
+		else if (key->ip.proto == IPPROTO_TCP)
+			src = tcp_hdr(skb)->source;
+		else if (key->ip.proto == IPPROTO_SCTP)
+			src = sctp_hdr(skb)->source;
+		else
+			return;
+
+		key->tp.src = src;
+	} else {
+		__be16 dst;
+
+		key->ct_state |= OVS_CS_F_DST_NAT;
+		if (key->eth.type == htons(ETH_P_IP))
+			key->ipv4.addr.dst = ip_hdr(skb)->daddr;
+		else if (key->eth.type == htons(ETH_P_IPV6))
+			memcpy(&key->ipv6.addr.dst, &ipv6_hdr(skb)->daddr,
+			       sizeof(key->ipv6.addr.dst));
+		else
+			return;
+
+		if (key->ip.proto == IPPROTO_UDP)
+			dst = udp_hdr(skb)->dest;
+		else if (key->ip.proto == IPPROTO_TCP)
+			dst = tcp_hdr(skb)->dest;
+		else if (key->ip.proto == IPPROTO_SCTP)
+			dst = sctp_hdr(skb)->dest;
+		else
+			return;
+
+		key->tp.dst = dst;
+	}
+}
+
 /* Modelled after nf_nat_ipv[46]_fn().
  * range is only used for new, uninitialized NAT state.
  * Returns either NF_ACCEPT or NF_DROP.
@@ -741,7 +792,7 @@ static bool skb_nfct_cached(struct net *net,
 static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
 			      enum ip_conntrack_info ctinfo,
 			      const struct nf_nat_range2 *range,
-			      enum nf_nat_manip_type maniptype)
+			      enum nf_nat_manip_type maniptype, struct sw_flow_key *key)
 {
 	int hooknum, nh_off, err = NF_ACCEPT;
 
@@ -813,58 +864,11 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
 push:
 	skb_push_rcsum(skb, nh_off);
 
-	return err;
-}
-
-static void ovs_nat_update_key(struct sw_flow_key *key,
-			       const struct sk_buff *skb,
-			       enum nf_nat_manip_type maniptype)
-{
-	if (maniptype == NF_NAT_MANIP_SRC) {
-		__be16 src;
-
-		key->ct_state |= OVS_CS_F_SRC_NAT;
-		if (key->eth.type == htons(ETH_P_IP))
-			key->ipv4.addr.src = ip_hdr(skb)->saddr;
-		else if (key->eth.type == htons(ETH_P_IPV6))
-			memcpy(&key->ipv6.addr.src, &ipv6_hdr(skb)->saddr,
-			       sizeof(key->ipv6.addr.src));
-		else
-			return;
-
-		if (key->ip.proto == IPPROTO_UDP)
-			src = udp_hdr(skb)->source;
-		else if (key->ip.proto == IPPROTO_TCP)
-			src = tcp_hdr(skb)->source;
-		else if (key->ip.proto == IPPROTO_SCTP)
-			src = sctp_hdr(skb)->source;
-		else
-			return;
-
-		key->tp.src = src;
-	} else {
-		__be16 dst;
-
-		key->ct_state |= OVS_CS_F_DST_NAT;
-		if (key->eth.type == htons(ETH_P_IP))
-			key->ipv4.addr.dst = ip_hdr(skb)->daddr;
-		else if (key->eth.type == htons(ETH_P_IPV6))
-			memcpy(&key->ipv6.addr.dst, &ipv6_hdr(skb)->daddr,
-			       sizeof(key->ipv6.addr.dst));
-		else
-			return;
-
-		if (key->ip.proto == IPPROTO_UDP)
-			dst = udp_hdr(skb)->dest;
-		else if (key->ip.proto == IPPROTO_TCP)
-			dst = tcp_hdr(skb)->dest;
-		else if (key->ip.proto == IPPROTO_SCTP)
-			dst = sctp_hdr(skb)->dest;
-		else
-			return;
+	/* Update the flow key if NAT successful. */
+	if (err == NF_ACCEPT)
+		ovs_nat_update_key(key, skb, maniptype);
 
-		key->tp.dst = dst;
-	}
+	return err;
 }
 
 /* Returns NF_DROP if the packet should be dropped, NF_ACCEPT otherwise. */
@@ -906,7 +910,7 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
 	} else {
 		return NF_ACCEPT; /* Connection is not NATed. */
 	}
-	err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype);
+	err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype, key);
 
 	if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) {
 		if (ct->status & IPS_SRC_NAT) {
@@ -916,17 +920,13 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
 				maniptype = NF_NAT_MANIP_SRC;
 
 			err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range,
-						 maniptype);
+						 maniptype, key);
 		} else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
 			err = ovs_ct_nat_execute(skb, ct, ctinfo, NULL,
-						 NF_NAT_MANIP_SRC);
+						 NF_NAT_MANIP_SRC, key);
 		}
 	}
 
-	/* Mark NAT done if successful and update the flow key. */
-	if (err == NF_ACCEPT)
-		ovs_nat_update_key(key, skb, maniptype);
-
 	return err;
 }
 #else /* !CONFIG_NF_NAT */
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 7545321c3440..17f8c523e33b 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2852,7 +2852,8 @@ static void tipc_sk_retry_connect(struct sock *sk, struct sk_buff_head *list)
 
 	/* Try again later if dest link is congested */
 	if (tsk->cong_link_cnt) {
-		sk_reset_timer(sk, &sk->sk_timer, msecs_to_jiffies(100));
+		sk_reset_timer(sk, &sk->sk_timer,
+			       jiffies + msecs_to_jiffies(100));
 		return;
 	}
 	/* Prepare SYN for retransmit */
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 4247c4134f31..e71a312faa1e 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2084,7 +2084,7 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other
 	if (ousk->oob_skb)
 		consume_skb(ousk->oob_skb);
 
-	ousk->oob_skb = skb;
+	WRITE_ONCE(ousk->oob_skb, skb);
 
 	scm_stat_add(other, skb);
 	skb_queue_tail(&other->sk_receive_queue, skb);
@@ -2602,9 +2602,8 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state)
 
 	oob_skb = u->oob_skb;
 
-	if (!(state->flags & MSG_PEEK)) {
-		u->oob_skb = NULL;
-	}
+	if (!(state->flags & MSG_PEEK))
+		WRITE_ONCE(u->oob_skb, NULL);
 
 	unix_state_unlock(sk);
 
@@ -2639,7 +2638,7 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 				skb = NULL;
 			} else if (sock_flag(sk, SOCK_URGINLINE)) {
 				if (!(flags & MSG_PEEK)) {
-					u->oob_skb = NULL;
+					WRITE_ONCE(u->oob_skb, NULL);
 					consume_skb(skb);
 				}
 			} else if (!(flags & MSG_PEEK)) {
@@ -3094,11 +3093,10 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	case SIOCATMARK:
 		{
 			struct sk_buff *skb;
-			struct unix_sock *u = unix_sk(sk);
 			int answ = 0;
 
 			skb = skb_peek(&sk->sk_receive_queue);
-			if (skb && skb == u->oob_skb)
+			if (skb && skb == READ_ONCE(unix_sk(sk)->oob_skb))
 				answ = 1;
 			err = put_user(answ, (int __user *)arg);
 		}
@@ -3139,6 +3137,10 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa
 		mask |= EPOLLIN | EPOLLRDNORM;
 	if (sk_is_readable(sk))
 		mask |= EPOLLIN | EPOLLRDNORM;
+#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
+	if (READ_ONCE(unix_sk(sk)->oob_skb))
+		mask |= EPOLLPRI;
+#endif
 
 	/* Connection-based need to check for termination and startup */
 	if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) &&
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 2abd64e4d589..2c34caee0fd1 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -402,18 +402,8 @@ EXPORT_SYMBOL(xsk_tx_peek_release_desc_batch);
 static int xsk_wakeup(struct xdp_sock *xs, u8 flags)
 {
 	struct net_device *dev = xs->dev;
-	int err;
-
-	rcu_read_lock();
-	err = dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, flags);
-	rcu_read_unlock();
-
-	return err;
-}
 
-static int xsk_zc_xmit(struct xdp_sock *xs)
-{
-	return xsk_wakeup(xs, XDP_WAKEUP_TX);
+	return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, flags);
 }
 
 static void xsk_destruct_skb(struct sk_buff *skb)
@@ -532,6 +522,12 @@ static int xsk_generic_xmit(struct sock *sk)
 
 	mutex_lock(&xs->mutex);
 
+	/* Since we dropped the RCU read lock, the socket state might have changed. */
+	if (unlikely(!xsk_is_bound(xs))) {
+		err = -ENXIO;
+		goto out;
+	}
+
 	if (xs->queue_id >= xs->dev->real_num_tx_queues)
 		goto out;
 
@@ -595,16 +591,26 @@ out:
 	return err;
 }
 
-static int __xsk_sendmsg(struct sock *sk)
+static int xsk_xmit(struct sock *sk)
 {
 	struct xdp_sock *xs = xdp_sk(sk);
+	int ret;
 
 	if (unlikely(!(xs->dev->flags & IFF_UP)))
 		return -ENETDOWN;
 	if (unlikely(!xs->tx))
 		return -ENOBUFS;
 
-	return xs->zc ? xsk_zc_xmit(xs) : xsk_generic_xmit(sk);
+	if (xs->zc)
+		return xsk_wakeup(xs, XDP_WAKEUP_TX);
+
+	/* Drop the RCU lock since the SKB path might sleep. */
+	rcu_read_unlock();
+	ret = xsk_generic_xmit(sk);
+	/* Reaquire RCU lock before going into common code. */
+	rcu_read_lock();
+
+	return ret;
 }
 
 static bool xsk_no_wakeup(struct sock *sk)
@@ -618,7 +624,7 @@ static bool xsk_no_wakeup(struct sock *sk)
 #endif
 }
 
-static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
+static int __xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 {
 	bool need_wait = !(m->msg_flags & MSG_DONTWAIT);
 	struct sock *sk = sock->sk;
@@ -638,11 +644,22 @@ static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 
 	pool = xs->pool;
 	if (pool->cached_need_wakeup & XDP_WAKEUP_TX)
-		return __xsk_sendmsg(sk);
+		return xsk_xmit(sk);
 	return 0;
 }
 
-static int xsk_recvmsg(struct socket *sock, struct msghdr *m, size_t len, int flags)
+static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
+{
+	int ret;
+
+	rcu_read_lock();
+	ret = __xsk_sendmsg(sock, m, total_len);
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static int __xsk_recvmsg(struct socket *sock, struct msghdr *m, size_t len, int flags)
 {
 	bool need_wait = !(flags & MSG_DONTWAIT);
 	struct sock *sk = sock->sk;
@@ -668,6 +685,17 @@ static int xsk_recvmsg(struct socket *sock, struct msghdr *m, size_t len, int fl
 	return 0;
 }
 
+static int xsk_recvmsg(struct socket *sock, struct msghdr *m, size_t len, int flags)
+{
+	int ret;
+
+	rcu_read_lock();
+	ret = __xsk_recvmsg(sock, m, len, flags);
+	rcu_read_unlock();
+
+	return ret;
+}
+
 static __poll_t xsk_poll(struct file *file, struct socket *sock,
 			     struct poll_table_struct *wait)
 {
@@ -678,8 +706,11 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock,
 
 	sock_poll_wait(file, sock, wait);
 
-	if (unlikely(!xsk_is_bound(xs)))
+	rcu_read_lock();
+	if (unlikely(!xsk_is_bound(xs))) {
+		rcu_read_unlock();
 		return mask;
+	}
 
 	pool = xs->pool;
 
@@ -688,7 +719,7 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock,
 			xsk_wakeup(xs, pool->cached_need_wakeup);
 		else
 			/* Poll needs to drive Tx also in copy mode */
-			__xsk_sendmsg(sk);
+			xsk_xmit(sk);
 	}
 
 	if (xs->rx && !xskq_prod_is_empty(xs->rx))
@@ -696,6 +727,7 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock,
 	if (xs->tx && xsk_tx_writeable(xs))
 		mask |= EPOLLOUT | EPOLLWRNORM;
 
+	rcu_read_unlock();
 	return mask;
 }
 
@@ -727,7 +759,6 @@ static void xsk_unbind_dev(struct xdp_sock *xs)
 
 	/* Wait for driver to stop using the xdp socket. */
 	xp_del_xsk(xs->pool, xs);
-	xs->dev = NULL;
 	synchronize_net();
 	dev_put(dev);
 }
diff --git a/tools/testing/selftests/net/af_unix/test_unix_oob.c b/tools/testing/selftests/net/af_unix/test_unix_oob.c
index 3dece8b29253..b57e91e1c3f2 100644
--- a/tools/testing/selftests/net/af_unix/test_unix_oob.c
+++ b/tools/testing/selftests/net/af_unix/test_unix_oob.c
@@ -218,10 +218,10 @@ main(int argc, char **argv)
 
 	/* Test 1:
 	 * veriyf that SIGURG is
-	 * delivered and 63 bytes are
-	 * read and oob is '@'
+	 * delivered, 63 bytes are
+	 * read, oob is '@', and POLLPRI works.
 	 */
-	wait_for_data(pfd, POLLIN | POLLPRI);
+	wait_for_data(pfd, POLLPRI);
 	read_oob(pfd, &oob);
 	len = read_data(pfd, buf, 1024);
 	if (!signal_recvd || len != 63 || oob != '@') {
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 694732e4b344..736e358dc549 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -26,6 +26,15 @@
 # - pmtu_ipv6
 #	Same as pmtu_ipv4, except for locked PMTU tests, using IPv6
 #
+# - pmtu_ipv4_dscp_icmp_exception
+#	Set up the same network topology as pmtu_ipv4, but use non-default
+#	routing table in A. A fib-rule is used to jump to this routing table
+#	based on DSCP. Send ICMPv4 packets with the expected DSCP value and
+#	verify that ECN doesn't interfere with the creation of PMTU exceptions.
+#
+# - pmtu_ipv4_dscp_udp_exception
+#	Same as pmtu_ipv4_dscp_icmp_exception, but use UDP instead of ICMP.
+#
 # - pmtu_ipv4_vxlan4_exception
 #	Set up the same network topology as pmtu_ipv4, create a VXLAN tunnel
 #	over IPv4 between A and B, routed via R1. On the link between R1 and B,
@@ -203,6 +212,8 @@ which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)
 tests="
 	pmtu_ipv4_exception		ipv4: PMTU exceptions			1
 	pmtu_ipv6_exception		ipv6: PMTU exceptions			1
+	pmtu_ipv4_dscp_icmp_exception	ICMPv4 with DSCP and ECN: PMTU exceptions	1
+	pmtu_ipv4_dscp_udp_exception	UDPv4 with DSCP and ECN: PMTU exceptions	1
 	pmtu_ipv4_vxlan4_exception	IPv4 over vxlan4: PMTU exceptions	1
 	pmtu_ipv6_vxlan4_exception	IPv6 over vxlan4: PMTU exceptions	1
 	pmtu_ipv4_vxlan6_exception	IPv4 over vxlan6: PMTU exceptions	1
@@ -323,6 +334,9 @@ routes_nh="
 	B	6	default			61
 "
 
+policy_mark=0x04
+rt_table=main
+
 veth4_a_addr="192.168.1.1"
 veth4_b_addr="192.168.1.2"
 veth4_c_addr="192.168.2.10"
@@ -346,6 +360,7 @@ dummy6_mask="64"
 err_buf=
 tcpdump_pids=
 nettest_pids=
+socat_pids=
 
 err() {
 	err_buf="${err_buf}${1}
@@ -723,7 +738,7 @@ setup_routing_old() {
 
 		ns_name="$(nsname ${ns})"
 
-		ip -n ${ns_name} route add ${addr} via ${gw}
+		ip -n "${ns_name}" route add "${addr}" table "${rt_table}" via "${gw}"
 
 		ns=""; addr=""; gw=""
 	done
@@ -753,7 +768,7 @@ setup_routing_new() {
 
 		ns_name="$(nsname ${ns})"
 
-		ip -n ${ns_name} -${fam} route add ${addr} nhid ${nhid}
+		ip -n "${ns_name}" -"${fam}" route add "${addr}" table "${rt_table}" nhid "${nhid}"
 
 		ns=""; fam=""; addr=""; nhid=""
 	done
@@ -798,6 +813,24 @@ setup_routing() {
 	return 0
 }
 
+setup_policy_routing() {
+	setup_routing
+
+	ip -netns "${NS_A}" -4 rule add dsfield "${policy_mark}" \
+		table "${rt_table}"
+
+	# Set the IPv4 Don't Fragment bit with tc, since socat doesn't seem to
+	# have an option do to it.
+	tc -netns "${NS_A}" qdisc replace dev veth_A-R1 root prio
+	tc -netns "${NS_A}" qdisc replace dev veth_A-R2 root prio
+	tc -netns "${NS_A}" filter add dev veth_A-R1                      \
+		protocol ipv4 flower ip_proto udp                         \
+		action pedit ex munge ip df set 0x40 pipe csum ip and udp
+	tc -netns "${NS_A}" filter add dev veth_A-R2                      \
+		protocol ipv4 flower ip_proto udp                         \
+		action pedit ex munge ip df set 0x40 pipe csum ip and udp
+}
+
 setup_bridge() {
 	run_cmd ${ns_a} ip link add br0 type bridge || return $ksft_skip
 	run_cmd ${ns_a} ip link set br0 up
@@ -903,6 +936,11 @@ cleanup() {
 	done
 	nettest_pids=
 
+	for pid in ${socat_pids}; do
+		kill "${pid}"
+	done
+	socat_pids=
+
 	for n in ${NS_A} ${NS_B} ${NS_C} ${NS_R1} ${NS_R2}; do
 		ip netns del ${n} 2> /dev/null
 	done
@@ -950,15 +988,21 @@ link_get_mtu() {
 route_get_dst_exception() {
 	ns_cmd="${1}"
 	dst="${2}"
+	dsfield="${3}"
 
-	${ns_cmd} ip route get "${dst}"
+	if [ -z "${dsfield}" ]; then
+		dsfield=0
+	fi
+
+	${ns_cmd} ip route get "${dst}" dsfield "${dsfield}"
 }
 
 route_get_dst_pmtu_from_exception() {
 	ns_cmd="${1}"
 	dst="${2}"
+	dsfield="${3}"
 
-	mtu_parse "$(route_get_dst_exception "${ns_cmd}" ${dst})"
+	mtu_parse "$(route_get_dst_exception "${ns_cmd}" "${dst}" "${dsfield}")"
 }
 
 check_pmtu_value() {
@@ -1068,6 +1112,95 @@ test_pmtu_ipv6_exception() {
 	test_pmtu_ipvX 6
 }
 
+test_pmtu_ipv4_dscp_icmp_exception() {
+	rt_table=100
+
+	setup namespaces policy_routing || return $ksft_skip
+	trace "${ns_a}"  veth_A-R1    "${ns_r1}" veth_R1-A \
+	      "${ns_r1}" veth_R1-B    "${ns_b}"  veth_B-R1 \
+	      "${ns_a}"  veth_A-R2    "${ns_r2}" veth_R2-A \
+	      "${ns_r2}" veth_R2-B    "${ns_b}"  veth_B-R2
+
+	# Set up initial MTU values
+	mtu "${ns_a}"  veth_A-R1 2000
+	mtu "${ns_r1}" veth_R1-A 2000
+	mtu "${ns_r1}" veth_R1-B 1400
+	mtu "${ns_b}"  veth_B-R1 1400
+
+	mtu "${ns_a}"  veth_A-R2 2000
+	mtu "${ns_r2}" veth_R2-A 2000
+	mtu "${ns_r2}" veth_R2-B 1500
+	mtu "${ns_b}"  veth_B-R2 1500
+
+	len=$((2000 - 20 - 8)) # Fills MTU of veth_A-R1
+
+	dst1="${prefix4}.${b_r1}.1"
+	dst2="${prefix4}.${b_r2}.1"
+
+	# Create route exceptions
+	dsfield=${policy_mark} # No ECN bit set (Not-ECT)
+	run_cmd "${ns_a}" ping -q -M want -Q "${dsfield}" -c 1 -w 1 -s "${len}" "${dst1}"
+
+	dsfield=$(printf "%#x" $((policy_mark + 0x02))) # ECN=2 (ECT(0))
+	run_cmd "${ns_a}" ping -q -M want -Q "${dsfield}" -c 1 -w 1 -s "${len}" "${dst2}"
+
+	# Check that exceptions have been created with the correct PMTU
+	pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" "${policy_mark}")"
+	check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1
+
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" "${policy_mark}")"
+	check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1
+}
+
+test_pmtu_ipv4_dscp_udp_exception() {
+	rt_table=100
+
+	if ! which socat > /dev/null 2>&1; then
+		echo "'socat' command not found; skipping tests"
+		return $ksft_skip
+	fi
+
+	setup namespaces policy_routing || return $ksft_skip
+	trace "${ns_a}"  veth_A-R1    "${ns_r1}" veth_R1-A \
+	      "${ns_r1}" veth_R1-B    "${ns_b}"  veth_B-R1 \
+	      "${ns_a}"  veth_A-R2    "${ns_r2}" veth_R2-A \
+	      "${ns_r2}" veth_R2-B    "${ns_b}"  veth_B-R2
+
+	# Set up initial MTU values
+	mtu "${ns_a}"  veth_A-R1 2000
+	mtu "${ns_r1}" veth_R1-A 2000
+	mtu "${ns_r1}" veth_R1-B 1400
+	mtu "${ns_b}"  veth_B-R1 1400
+
+	mtu "${ns_a}"  veth_A-R2 2000
+	mtu "${ns_r2}" veth_R2-A 2000
+	mtu "${ns_r2}" veth_R2-B 1500
+	mtu "${ns_b}"  veth_B-R2 1500
+
+	len=$((2000 - 20 - 8)) # Fills MTU of veth_A-R1
+
+	dst1="${prefix4}.${b_r1}.1"
+	dst2="${prefix4}.${b_r2}.1"
+
+	# Create route exceptions
+	run_cmd_bg "${ns_b}" socat UDP-LISTEN:50000 OPEN:/dev/null,wronly=1
+	socat_pids="${socat_pids} $!"
+
+	dsfield=${policy_mark} # No ECN bit set (Not-ECT)
+	run_cmd "${ns_a}" socat OPEN:/dev/zero,rdonly=1,readbytes="${len}" \
+		UDP:"${dst1}":50000,tos="${dsfield}"
+
+	dsfield=$(printf "%#x" $((policy_mark + 0x02))) # ECN=2 (ECT(0))
+	run_cmd "${ns_a}" socat OPEN:/dev/zero,rdonly=1,readbytes="${len}" \
+		UDP:"${dst2}":50000,tos="${dsfield}"
+
+	# Check that exceptions have been created with the correct PMTU
+	pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" "${policy_mark}")"
+	check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" "${policy_mark}")"
+	check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1
+}
+
 test_pmtu_ipvX_over_vxlanY_or_geneveY_exception() {
 	type=${1}
 	family=${2}