26 files changed, 255 insertions, 121 deletions

diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 0c00200c9cb2..788076b002b3 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -184,9 +184,6 @@ int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack)
 	if (err)
 		goto out_unregister_netdev;
 
-	/* Account for reference in struct vlan_dev_priv */
-	dev_hold(real_dev);
-
 	vlan_stacked_transfer_operstate(real_dev, dev, vlan);
 	linkwatch_fire_event(dev); /* _MUST_ call rfc2863_policy() */
 
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index e9499a7c19fe..866556e041b7 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -615,6 +615,9 @@ static int vlan_dev_init(struct net_device *dev)
 	if (!vlan->vlan_pcpu_stats)
 		return -ENOMEM;
 
+	/* Get vlan's reference to real_dev */
+	dev_hold(real_dev);
+
 	return 0;
 }
 
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 47931c8be04b..72ba027c34cf 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1779,6 +1779,7 @@ int neigh_table_clear(int index, struct neigh_table *tbl)
 {
 	neigh_tables[index] = NULL;
 	/* It is not clean... Fix it to unload IPv6 module safely */
+	cancel_delayed_work_sync(&tbl->managed_work);
 	cancel_delayed_work_sync(&tbl->gc_work);
 	del_timer_sync(&tbl->proxy_timer);
 	pneigh_queue_purge(&tbl->proxy_queue);
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index af2d4e022076..06d3866c69b4 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -1719,7 +1719,7 @@ static noinline_for_stack int ethtool_set_coalesce(struct net_device *dev,
 	struct ethtool_coalesce coalesce;
 	int ret;
 
-	if (!dev->ethtool_ops->set_coalesce && !dev->ethtool_ops->get_coalesce)
+	if (!dev->ethtool_ops->set_coalesce || !dev->ethtool_ops->get_coalesce)
 		return -EOPNOTSUPP;
 
 	ret = dev->ethtool_ops->get_coalesce(dev, &coalesce, &kernel_coalesce,
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 9e8100728d46..5dbd4b5505eb 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -1899,15 +1899,36 @@ static void remove_nexthop(struct net *net, struct nexthop *nh,
 /* if any FIB entries reference this nexthop, any dst entries
  * need to be regenerated
  */
-static void nh_rt_cache_flush(struct net *net, struct nexthop *nh)
+static void nh_rt_cache_flush(struct net *net, struct nexthop *nh,
+			      struct nexthop *replaced_nh)
 {
 	struct fib6_info *f6i;
+	struct nh_group *nhg;
+	int i;
 
 	if (!list_empty(&nh->fi_list))
 		rt_cache_flush(net);
 
 	list_for_each_entry(f6i, &nh->f6i_list, nh_list)
 		ipv6_stub->fib6_update_sernum(net, f6i);
+
+	/* if an IPv6 group was replaced, we have to release all old
+	 * dsts to make sure all refcounts are released
+	 */
+	if (!replaced_nh->is_group)
+		return;
+
+	/* new dsts must use only the new nexthop group */
+	synchronize_net();
+
+	nhg = rtnl_dereference(replaced_nh->nh_grp);
+	for (i = 0; i < nhg->num_nh; i++) {
+		struct nh_grp_entry *nhge = &nhg->nh_entries[i];
+		struct nh_info *nhi = rtnl_dereference(nhge->nh->nh_info);
+
+		if (nhi->family == AF_INET6)
+			ipv6_stub->fib6_nh_release_dsts(&nhi->fib6_nh);
+	}
 }
 
 static int replace_nexthop_grp(struct net *net, struct nexthop *old,
@@ -2247,7 +2268,7 @@ static int replace_nexthop(struct net *net, struct nexthop *old,
 		err = replace_nexthop_single(net, old, new, extack);
 
 	if (!err) {
-		nh_rt_cache_flush(net, old);
+		nh_rt_cache_flush(net, old, new);
 
 		__remove_nexthop(net, new, NULL);
 		nexthop_put(new);
@@ -2544,11 +2565,15 @@ static int nh_create_ipv6(struct net *net,  struct nexthop *nh,
 	/* sets nh_dev if successful */
 	err = ipv6_stub->fib6_nh_init(net, fib6_nh, &fib6_cfg, GFP_KERNEL,
 				      extack);
-	if (err)
+	if (err) {
+		/* IPv6 is not enabled, don't call fib6_nh_release */
+		if (err == -EAFNOSUPPORT)
+			goto out;
 		ipv6_stub->fib6_nh_release(fib6_nh);
-	else
+	} else {
 		nh->nh_flags = fib6_nh->fib_nh_flags;
-
+	}
+out:
 	return err;
 }
 
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 5e9d9c51164c..e07837e23b3f 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -330,8 +330,6 @@ static void cubictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 		return;
 
 	if (tcp_in_slow_start(tp)) {
-		if (hystart && after(ack, ca->end_seq))
-			bictcp_hystart_reset(sk);
 		acked = tcp_slow_start(tp, acked);
 		if (!acked)
 			return;
@@ -391,6 +389,9 @@ static void hystart_update(struct sock *sk, u32 delay)
 	struct bictcp *ca = inet_csk_ca(sk);
 	u32 threshold;
 
+	if (after(tp->snd_una, ca->end_seq))
+		bictcp_hystart_reset(sk);
+
 	if (hystart_detect & HYSTART_ACK_TRAIN) {
 		u32 now = bictcp_clock_us(sk);
 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 1f28c9820c2e..d1636425654e 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -1023,6 +1023,7 @@ static const struct ipv6_stub ipv6_stub_impl = {
 	.ip6_mtu_from_fib6 = ip6_mtu_from_fib6,
 	.fib6_nh_init	   = fib6_nh_init,
 	.fib6_nh_release   = fib6_nh_release,
+	.fib6_nh_release_dsts = fib6_nh_release_dsts,
 	.fib6_update_sernum = fib6_update_sernum_stub,
 	.fib6_rt_update	   = fib6_rt_update,
 	.ip6_del_rt	   = ip6_del_rt,
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 007e433d4d4d..2995f8d89e7e 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -174,7 +174,7 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff
 #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
 	/* Policy lookup after SNAT yielded a new policy */
 	if (skb_dst(skb)->xfrm) {
-		IPCB(skb)->flags |= IPSKB_REROUTED;
+		IP6CB(skb)->flags |= IP6SKB_REROUTED;
 		return dst_output(net, sk, skb);
 	}
 #endif
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ecc6df6592a8..62f1e16eea2b 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3678,6 +3678,25 @@ void fib6_nh_release(struct fib6_nh *fib6_nh)
 	fib_nh_common_release(&fib6_nh->nh_common);
 }
 
+void fib6_nh_release_dsts(struct fib6_nh *fib6_nh)
+{
+	int cpu;
+
+	if (!fib6_nh->rt6i_pcpu)
+		return;
+
+	for_each_possible_cpu(cpu) {
+		struct rt6_info *pcpu_rt, **ppcpu_rt;
+
+		ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu);
+		pcpu_rt = xchg(ppcpu_rt, NULL);
+		if (pcpu_rt) {
+			dst_dev_put(&pcpu_rt->dst);
+			dst_release(&pcpu_rt->dst);
+		}
+	}
+}
+
 static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 					      gfp_t gfp_flags,
 					      struct netlink_ext_ack *extack)
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 7c3420afb1a0..fe98e4f475ba 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -422,28 +422,6 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
 	return false;
 }
 
-/* MP_JOIN client subflow must wait for 4th ack before sending any data:
- * TCP can't schedule delack timer before the subflow is fully established.
- * MPTCP uses the delack timer to do 3rd ack retransmissions
- */
-static void schedule_3rdack_retransmission(struct sock *sk)
-{
-	struct inet_connection_sock *icsk = inet_csk(sk);
-	struct tcp_sock *tp = tcp_sk(sk);
-	unsigned long timeout;
-
-	/* reschedule with a timeout above RTT, as we must look only for drop */
-	if (tp->srtt_us)
-		timeout = tp->srtt_us << 1;
-	else
-		timeout = TCP_TIMEOUT_INIT;
-
-	WARN_ON_ONCE(icsk->icsk_ack.pending & ICSK_ACK_TIMER);
-	icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER;
-	icsk->icsk_ack.timeout = timeout;
-	sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout);
-}
-
 static void clear_3rdack_retransmission(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
@@ -526,7 +504,15 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
 		*size = TCPOLEN_MPTCP_MPJ_ACK;
 		pr_debug("subflow=%p", subflow);
 
-		schedule_3rdack_retransmission(sk);
+		/* we can use the full delegate action helper only from BH context
+		 * If we are in process context - sk is flushing the backlog at
+		 * socket lock release time - just set the appropriate flag, will
+		 * be handled by the release callback
+		 */
+		if (sock_owned_by_user(sk))
+			set_bit(MPTCP_DELEGATE_ACK, &subflow->delegated_status);
+		else
+			mptcp_subflow_delegate(subflow, MPTCP_DELEGATE_ACK);
 		return true;
 	}
 	return false;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 6db93da59843..b100048e43fe 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1596,7 +1596,8 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)
 			if (!xmit_ssk)
 				goto out;
 			if (xmit_ssk != ssk) {
-				mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk));
+				mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk),
+						       MPTCP_DELEGATE_SEND);
 				goto out;
 			}
 
@@ -2943,7 +2944,7 @@ void __mptcp_check_push(struct sock *sk, struct sock *ssk)
 		if (xmit_ssk == ssk)
 			__mptcp_subflow_push_pending(sk, ssk);
 		else if (xmit_ssk)
-			mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk));
+			mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk), MPTCP_DELEGATE_SEND);
 	} else {
 		set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags);
 	}
@@ -2993,18 +2994,50 @@ static void mptcp_release_cb(struct sock *sk)
 	__mptcp_update_rmem(sk);
 }
 
+/* MP_JOIN client subflow must wait for 4th ack before sending any data:
+ * TCP can't schedule delack timer before the subflow is fully established.
+ * MPTCP uses the delack timer to do 3rd ack retransmissions
+ */
+static void schedule_3rdack_retransmission(struct sock *ssk)
+{
+	struct inet_connection_sock *icsk = inet_csk(ssk);
+	struct tcp_sock *tp = tcp_sk(ssk);
+	unsigned long timeout;
+
+	if (mptcp_subflow_ctx(ssk)->fully_established)
+		return;
+
+	/* reschedule with a timeout above RTT, as we must look only for drop */
+	if (tp->srtt_us)
+		timeout = usecs_to_jiffies(tp->srtt_us >> (3 - 1));
+	else
+		timeout = TCP_TIMEOUT_INIT;
+	timeout += jiffies;
+
+	WARN_ON_ONCE(icsk->icsk_ack.pending & ICSK_ACK_TIMER);
+	icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER;
+	icsk->icsk_ack.timeout = timeout;
+	sk_reset_timer(ssk, &icsk->icsk_delack_timer, timeout);
+}
+
 void mptcp_subflow_process_delegated(struct sock *ssk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	struct sock *sk = subflow->conn;
 
-	mptcp_data_lock(sk);
-	if (!sock_owned_by_user(sk))
-		__mptcp_subflow_push_pending(sk, ssk);
-	else
-		set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags);
-	mptcp_data_unlock(sk);
-	mptcp_subflow_delegated_done(subflow);
+	if (test_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status)) {
+		mptcp_data_lock(sk);
+		if (!sock_owned_by_user(sk))
+			__mptcp_subflow_push_pending(sk, ssk);
+		else
+			set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags);
+		mptcp_data_unlock(sk);
+		mptcp_subflow_delegated_done(subflow, MPTCP_DELEGATE_SEND);
+	}
+	if (test_bit(MPTCP_DELEGATE_ACK, &subflow->delegated_status)) {
+		schedule_3rdack_retransmission(ssk);
+		mptcp_subflow_delegated_done(subflow, MPTCP_DELEGATE_ACK);
+	}
 }
 
 static int mptcp_hash(struct sock *sk)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 67a61ac48b20..d87cc040352e 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -387,6 +387,7 @@ struct mptcp_delegated_action {
 DECLARE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions);
 
 #define MPTCP_DELEGATE_SEND		0
+#define MPTCP_DELEGATE_ACK		1
 
 /* MPTCP subflow context */
 struct mptcp_subflow_context {
@@ -492,23 +493,23 @@ static inline void mptcp_add_pending_subflow(struct mptcp_sock *msk,
 
 void mptcp_subflow_process_delegated(struct sock *ssk);
 
-static inline void mptcp_subflow_delegate(struct mptcp_subflow_context *subflow)
+static inline void mptcp_subflow_delegate(struct mptcp_subflow_context *subflow, int action)
 {
 	struct mptcp_delegated_action *delegated;
 	bool schedule;
 
+	/* the caller held the subflow bh socket lock */
+	lockdep_assert_in_softirq();
+
 	/* The implied barrier pairs with mptcp_subflow_delegated_done(), and
 	 * ensures the below list check sees list updates done prior to status
 	 * bit changes
 	 */
-	if (!test_and_set_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status)) {
+	if (!test_and_set_bit(action, &subflow->delegated_status)) {
 		/* still on delegated list from previous scheduling */
 		if (!list_empty(&subflow->delegated_node))
 			return;
 
-		/* the caller held the subflow bh socket lock */
-		lockdep_assert_in_softirq();
-
 		delegated = this_cpu_ptr(&mptcp_delegated_actions);
 		schedule = list_empty(&delegated->head);
 		list_add_tail(&subflow->delegated_node, &delegated->head);
@@ -533,16 +534,16 @@ mptcp_subflow_delegated_next(struct mptcp_delegated_action *delegated)
 
 static inline bool mptcp_subflow_has_delegated_action(const struct mptcp_subflow_context *subflow)
 {
-	return test_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status);
+	return !!READ_ONCE(subflow->delegated_status);
 }
 
-static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *subflow)
+static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *subflow, int action)
 {
 	/* pairs with mptcp_subflow_delegate, ensures delegate_node is updated before
 	 * touching the status bit
 	 */
 	smp_wmb();
-	clear_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status);
+	clear_bit(action, &subflow->delegated_status);
 }
 
 int mptcp_is_enabled(const struct net *net);
diff --git a/net/ncsi/ncsi-cmd.c b/net/ncsi/ncsi-cmd.c
index ba9ae482141b..dda8b76b7798 100644
--- a/net/ncsi/ncsi-cmd.c
+++ b/net/ncsi/ncsi-cmd.c
@@ -18,6 +18,8 @@
 #include "internal.h"
 #include "ncsi-pkt.h"
 
+static const int padding_bytes = 26;
+
 u32 ncsi_calculate_checksum(unsigned char *data, int len)
 {
 	u32 checksum = 0;
@@ -213,12 +215,17 @@ static int ncsi_cmd_handler_oem(struct sk_buff *skb,
 {
 	struct ncsi_cmd_oem_pkt *cmd;
 	unsigned int len;
+	int payload;
+	/* NC-SI spec DSP_0222_1.2.0, section 8.2.2.2
+	 * requires payload to be padded with 0 to
+	 * 32-bit boundary before the checksum field.
+	 * Ensure the padding bytes are accounted for in
+	 * skb allocation
+	 */
 
+	payload = ALIGN(nca->payload, 4);
 	len = sizeof(struct ncsi_cmd_pkt_hdr) + 4;
-	if (nca->payload < 26)
-		len += 26;
-	else
-		len += nca->payload;
+	len += max(payload, padding_bytes);
 
 	cmd = skb_put_zero(skb, len);
 	memcpy(&cmd->mfr_id, nca->data, nca->payload);
@@ -272,6 +279,7 @@ static struct ncsi_request *ncsi_alloc_command(struct ncsi_cmd_arg *nca)
 	struct net_device *dev = nd->dev;
 	int hlen = LL_RESERVED_SPACE(dev);
 	int tlen = dev->needed_tailroom;
+	int payload;
 	int len = hlen + tlen;
 	struct sk_buff *skb;
 	struct ncsi_request *nr;
@@ -281,14 +289,14 @@ static struct ncsi_request *ncsi_alloc_command(struct ncsi_cmd_arg *nca)
 		return NULL;
 
 	/* NCSI command packet has 16-bytes header, payload, 4 bytes checksum.
+	 * Payload needs padding so that the checksum field following payload is
+	 * aligned to 32-bit boundary.
 	 * The packet needs padding if its payload is less than 26 bytes to
 	 * meet 64 bytes minimal ethernet frame length.
 	 */
 	len += sizeof(struct ncsi_cmd_pkt_hdr) + 4;
-	if (nca->payload < 26)
-		len += 26;
-	else
-		len += nca->payload;
+	payload = ALIGN(nca->payload, 4);
+	len += max(payload, padding_bytes);
 
 	/* Allocate skb */
 	skb = alloc_skb(len, GFP_ATOMIC);
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index e93c937a8bf0..51ad557a525b 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1919,7 +1919,6 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state
 	struct ip_vs_proto_data *pd;
 	struct ip_vs_conn *cp;
 	int ret, pkts;
-	int conn_reuse_mode;
 	struct sock *sk;
 	int af = state->pf;
 
@@ -1997,15 +1996,16 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state
 	cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto,
 			     ipvs, af, skb, &iph);
 
-	conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
-	if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) {
+	if (!iph.fragoffs && is_new_conn(skb, &iph) && cp) {
+		int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
 		bool old_ct = false, resched = false;
 
 		if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest &&
 		    unlikely(!atomic_read(&cp->dest->weight))) {
 			resched = true;
 			old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
-		} else if (is_new_conn_expected(cp, conn_reuse_mode)) {
+		} else if (conn_reuse_mode &&
+			   is_new_conn_expected(cp, conn_reuse_mode)) {
 			old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
 			if (!atomic_read(&cp->n_control)) {
 				resched = true;
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 3d6c8da3de1f..849fa7f4353c 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1011,11 +1011,9 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family)
 						   CTA_TUPLE_REPLY,
 						   filter->family,
 						   &filter->zone,
-						   filter->orig_flags);
-		if (err < 0) {
-			err = -EINVAL;
+						   filter->reply_flags);
+		if (err < 0)
 			goto err_filter;
-		}
 	}
 
 	return filter;
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index d6bf1b2cd541..b561e0a44a45 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -65,11 +65,11 @@ static void nf_flow_rule_lwt_match(struct nf_flow_match *match,
 		       sizeof(struct in6_addr));
 		if (memcmp(&key->enc_ipv6.src, &in6addr_any,
 			   sizeof(struct in6_addr)))
-			memset(&key->enc_ipv6.src, 0xff,
+			memset(&mask->enc_ipv6.src, 0xff,
 			       sizeof(struct in6_addr));
 		if (memcmp(&key->enc_ipv6.dst, &in6addr_any,
 			   sizeof(struct in6_addr)))
-			memset(&key->enc_ipv6.dst, 0xff,
+			memset(&mask->enc_ipv6.dst, 0xff,
 			       sizeof(struct in6_addr));
 		enc_keys |= BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS);
 		key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index cbfe4e4a4ad7..bd689938a2e0 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -22,7 +22,6 @@
 #include <linux/icmpv6.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
-#include <linux/ip.h>
 #include <net/sctp/checksum.h>
 
 static bool nft_payload_rebuild_vlan_hdr(const struct sk_buff *skb, int mac_off,
diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c
index 2f7cf5ecebf4..0f8bb0bf558f 100644
--- a/net/netfilter/xt_IDLETIMER.c
+++ b/net/netfilter/xt_IDLETIMER.c
@@ -85,9 +85,9 @@ static ssize_t idletimer_tg_show(struct device *dev,
 	mutex_unlock(&list_mutex);
 
 	if (time_after(expires, jiffies) || ktimespec.tv_sec > 0)
-		return snprintf(buf, PAGE_SIZE, "%ld\n", time_diff);
+		return sysfs_emit(buf, "%ld\n", time_diff);
 
-	return snprintf(buf, PAGE_SIZE, "0\n");
+	return sysfs_emit(buf, "0\n");
 }
 
 static void idletimer_tg_work(struct work_struct *work)
diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c
index 0eae9ff5edf6..e007fc75ef2f 100644
--- a/net/sched/sch_ets.c
+++ b/net/sched/sch_ets.c
@@ -665,12 +665,14 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt,
 			q->classes[i].deficit = quanta[i];
 		}
 	}
+	for (i = q->nbands; i < oldbands; i++) {
+		qdisc_tree_flush_backlog(q->classes[i].qdisc);
+		if (i >= q->nstrict)
+			list_del(&q->classes[i].alist);
+	}
 	q->nstrict = nstrict;
 	memcpy(q->prio2band, priomap, sizeof(priomap));
 
-	for (i = q->nbands; i < oldbands; i++)
-		qdisc_tree_flush_backlog(q->classes[i].qdisc);
-
 	for (i = 0; i < q->nbands; i++)
 		q->classes[i].quantum = quanta[i];
 
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 5e93a5aa347e..67a78bbf305f 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -585,7 +585,7 @@ static void smc_switch_to_fallback(struct smc_sock *smc, int reason_code)
 		 * to clcsocket->wq during the fallback.
 		 */
 		spin_lock_irqsave(&smc_wait->lock, flags);
-		spin_lock(&clc_wait->lock);
+		spin_lock_nested(&clc_wait->lock, SINGLE_DEPTH_NESTING);
 		list_splice_init(&smc_wait->head, &clc_wait->head);
 		spin_unlock(&clc_wait->lock);
 		spin_unlock_irqrestore(&smc_wait->lock, flags);
@@ -2134,8 +2134,10 @@ static int smc_listen(struct socket *sock, int backlog)
 	smc->clcsock->sk->sk_user_data =
 		(void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY);
 	rc = kernel_listen(smc->clcsock, backlog);
-	if (rc)
+	if (rc) {
+		smc->clcsock->sk->sk_data_ready = smc->clcsk_data_ready;
 		goto out;
+	}
 	sk->sk_max_ack_backlog = backlog;
 	sk->sk_ack_backlog = 0;
 	sk->sk_state = SMC_LISTEN;
@@ -2368,8 +2370,10 @@ static __poll_t smc_poll(struct file *file, struct socket *sock,
 static int smc_shutdown(struct socket *sock, int how)
 {
 	struct sock *sk = sock->sk;
+	bool do_shutdown = true;
 	struct smc_sock *smc;
 	int rc = -EINVAL;
+	int old_state;
 	int rc1 = 0;
 
 	smc = smc_sk(sk);
@@ -2396,7 +2400,11 @@ static int smc_shutdown(struct socket *sock, int how)
 	}
 	switch (how) {
 	case SHUT_RDWR:		/* shutdown in both directions */
+		old_state = sk->sk_state;
 		rc = smc_close_active(smc);
+		if (old_state == SMC_ACTIVE &&
+		    sk->sk_state == SMC_PEERCLOSEWAIT1)
+			do_shutdown = false;
 		break;
 	case SHUT_WR:
 		rc = smc_close_shutdown_write(smc);
@@ -2406,7 +2414,7 @@ static int smc_shutdown(struct socket *sock, int how)
 		/* nothing more to do because peer is not involved */
 		break;
 	}
-	if (smc->clcsock)
+	if (do_shutdown && smc->clcsock)
 		rc1 = kernel_sock_shutdown(smc->clcsock, how);
 	/* map sock_shutdown_cmd constants to sk_shutdown value range */
 	sk->sk_shutdown |= how + 1;
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index 0f9ffba07d26..3715d2f5ad55 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -228,6 +228,12 @@ again:
 			/* send close request */
 			rc = smc_close_final(conn);
 			sk->sk_state = SMC_PEERCLOSEWAIT1;
+
+			/* actively shutdown clcsock before peer close it,
+			 * prevent peer from entering TIME_WAIT state.
+			 */
+			if (smc->clcsock && smc->clcsock->sk)
+				rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR);
 		} else {
 			/* peer event has changed the state */
 			goto again;
@@ -354,9 +360,9 @@ static void smc_close_passive_work(struct work_struct *work)
 	if (rxflags->peer_conn_abort) {
 		/* peer has not received all data */
 		smc_close_passive_abort_received(smc);
-		release_sock(&smc->sk);
+		release_sock(sk);
 		cancel_delayed_work_sync(&conn->tx_work);
-		lock_sock(&smc->sk);
+		lock_sock(sk);
 		goto wakeup;
 	}
 
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 25ebd30feecd..bb52c8b5f148 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1672,14 +1672,26 @@ static void smc_link_down_work(struct work_struct *work)
 	mutex_unlock(&lgr->llc_conf_mutex);
 }
 
-/* Determine vlan of internal TCP socket.
- * @vlan_id: address to store the determined vlan id into
- */
+static int smc_vlan_by_tcpsk_walk(struct net_device *lower_dev,
+				  struct netdev_nested_priv *priv)
+{
+	unsigned short *vlan_id = (unsigned short *)priv->data;
+
+	if (is_vlan_dev(lower_dev)) {
+		*vlan_id = vlan_dev_vlan_id(lower_dev);
+		return 1;
+	}
+
+	return 0;
+}
+
+/* Determine vlan of internal TCP socket. */
 int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini)
 {
 	struct dst_entry *dst = sk_dst_get(clcsock->sk);
+	struct netdev_nested_priv priv;
 	struct net_device *ndev;
-	int i, nest_lvl, rc = 0;
+	int rc = 0;
 
 	ini->vlan_id = 0;
 	if (!dst) {
@@ -1697,20 +1709,9 @@ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini)
 		goto out_rel;
 	}
 
+	priv.data = (void *)&ini->vlan_id;
 	rtnl_lock();
-	nest_lvl = ndev->lower_level;
-	for (i = 0; i < nest_lvl; i++) {
-		struct list_head *lower = &ndev->adj_list.lower;
-
-		if (list_empty(lower))
-			break;
-		lower = lower->next;
-		ndev = (struct net_device *)netdev_lower_get_next(ndev, &lower);
-		if (is_vlan_dev(ndev)) {
-			ini->vlan_id = vlan_dev_vlan_id(ndev);
-			break;
-		}
-	}
+	netdev_walk_all_lower_dev(ndev, smc_vlan_by_tcpsk_walk, &priv);
 	rtnl_unlock();
 
 out_rel:
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index acfba9f1ba72..6bc2879ba637 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -61,7 +61,7 @@ static DEFINE_MUTEX(tcpv6_prot_mutex);
 static const struct proto *saved_tcpv4_prot;
 static DEFINE_MUTEX(tcpv4_prot_mutex);
 static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG];
-static struct proto_ops tls_sw_proto_ops;
+static struct proto_ops tls_proto_ops[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG];
 static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG],
 			 const struct proto *base);
 
@@ -71,6 +71,8 @@ void update_sk_prot(struct sock *sk, struct tls_context *ctx)
 
 	WRITE_ONCE(sk->sk_prot,
 		   &tls_prots[ip_ver][ctx->tx_conf][ctx->rx_conf]);
+	WRITE_ONCE(sk->sk_socket->ops,
+		   &tls_proto_ops[ip_ver][ctx->tx_conf][ctx->rx_conf]);
 }
 
 int wait_on_pending_writer(struct sock *sk, long *timeo)
@@ -669,8 +671,6 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval,
 	if (tx) {
 		ctx->sk_write_space = sk->sk_write_space;
 		sk->sk_write_space = tls_write_space;
-	} else {
-		sk->sk_socket->ops = &tls_sw_proto_ops;
 	}
 	goto out;
 
@@ -728,6 +728,39 @@ struct tls_context *tls_ctx_create(struct sock *sk)
 	return ctx;
 }
 
+static void build_proto_ops(struct proto_ops ops[TLS_NUM_CONFIG][TLS_NUM_CONFIG],
+			    const struct proto_ops *base)
+{
+	ops[TLS_BASE][TLS_BASE] = *base;
+
+	ops[TLS_SW  ][TLS_BASE] = ops[TLS_BASE][TLS_BASE];
+	ops[TLS_SW  ][TLS_BASE].sendpage_locked	= tls_sw_sendpage_locked;
+
+	ops[TLS_BASE][TLS_SW  ] = ops[TLS_BASE][TLS_BASE];
+	ops[TLS_BASE][TLS_SW  ].splice_read	= tls_sw_splice_read;
+
+	ops[TLS_SW  ][TLS_SW  ] = ops[TLS_SW  ][TLS_BASE];
+	ops[TLS_SW  ][TLS_SW  ].splice_read	= tls_sw_splice_read;
+
+#ifdef CONFIG_TLS_DEVICE
+	ops[TLS_HW  ][TLS_BASE] = ops[TLS_BASE][TLS_BASE];
+	ops[TLS_HW  ][TLS_BASE].sendpage_locked	= NULL;
+
+	ops[TLS_HW  ][TLS_SW  ] = ops[TLS_BASE][TLS_SW  ];
+	ops[TLS_HW  ][TLS_SW  ].sendpage_locked	= NULL;
+
+	ops[TLS_BASE][TLS_HW  ] = ops[TLS_BASE][TLS_SW  ];
+
+	ops[TLS_SW  ][TLS_HW  ] = ops[TLS_SW  ][TLS_SW  ];
+
+	ops[TLS_HW  ][TLS_HW  ] = ops[TLS_HW  ][TLS_SW  ];
+	ops[TLS_HW  ][TLS_HW  ].sendpage_locked	= NULL;
+#endif
+#ifdef CONFIG_TLS_TOE
+	ops[TLS_HW_RECORD][TLS_HW_RECORD] = *base;
+#endif
+}
+
 static void tls_build_proto(struct sock *sk)
 {
 	int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4;
@@ -739,6 +772,8 @@ static void tls_build_proto(struct sock *sk)
 		mutex_lock(&tcpv6_prot_mutex);
 		if (likely(prot != saved_tcpv6_prot)) {
 			build_protos(tls_prots[TLSV6], prot);
+			build_proto_ops(tls_proto_ops[TLSV6],
+					sk->sk_socket->ops);
 			smp_store_release(&saved_tcpv6_prot, prot);
 		}
 		mutex_unlock(&tcpv6_prot_mutex);
@@ -749,6 +784,8 @@ static void tls_build_proto(struct sock *sk)
 		mutex_lock(&tcpv4_prot_mutex);
 		if (likely(prot != saved_tcpv4_prot)) {
 			build_protos(tls_prots[TLSV4], prot);
+			build_proto_ops(tls_proto_ops[TLSV4],
+					sk->sk_socket->ops);
 			smp_store_release(&saved_tcpv4_prot, prot);
 		}
 		mutex_unlock(&tcpv4_prot_mutex);
@@ -959,10 +996,6 @@ static int __init tls_register(void)
 	if (err)
 		return err;
 
-	tls_sw_proto_ops = inet_stream_ops;
-	tls_sw_proto_ops.splice_read = tls_sw_splice_read;
-	tls_sw_proto_ops.sendpage_locked   = tls_sw_sendpage_locked;
-
 	tls_device_init();
 	tcp_register_ulp(&tcp_tls_ulp_ops);
 
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index d81564078557..d3e7ff90889e 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -2005,6 +2005,7 @@ ssize_t tls_sw_splice_read(struct socket *sock,  loff_t *ppos,
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb;
 	ssize_t copied = 0;
+	bool from_queue;
 	int err = 0;
 	long timeo;
 	int chunk;
@@ -2014,25 +2015,28 @@ ssize_t tls_sw_splice_read(struct socket *sock,  loff_t *ppos,
 
 	timeo = sock_rcvtimeo(sk, flags & SPLICE_F_NONBLOCK);
 
-	skb = tls_wait_data(sk, NULL, flags & SPLICE_F_NONBLOCK, timeo, &err);
-	if (!skb)
-		goto splice_read_end;
-
-	if (!ctx->decrypted) {
-		err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc, false);
-
-		/* splice does not support reading control messages */
-		if (ctx->control != TLS_RECORD_TYPE_DATA) {
-			err = -EINVAL;
+	from_queue = !skb_queue_empty(&ctx->rx_list);
+	if (from_queue) {
+		skb = __skb_dequeue(&ctx->rx_list);
+	} else {
+		skb = tls_wait_data(sk, NULL, flags & SPLICE_F_NONBLOCK, timeo,
+				    &err);
+		if (!skb)
 			goto splice_read_end;
-		}
 
+		err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc, false);
 		if (err < 0) {
 			tls_err_abort(sk, -EBADMSG);
 			goto splice_read_end;
 		}
-		ctx->decrypted = 1;
 	}
+
+	/* splice does not support reading control messages */
+	if (ctx->control != TLS_RECORD_TYPE_DATA) {
+		err = -EINVAL;
+		goto splice_read_end;
+	}
+
 	rxm = strp_msg(skb);
 
 	chunk = min_t(unsigned int, rxm->full_len, len);
@@ -2040,7 +2044,17 @@ ssize_t tls_sw_splice_read(struct socket *sock,  loff_t *ppos,
 	if (copied < 0)
 		goto splice_read_end;
 
-	tls_sw_advance_skb(sk, skb, copied);
+	if (!from_queue) {
+		ctx->recv_pkt = NULL;
+		__strp_unpause(&ctx->strp);
+	}
+	if (chunk < rxm->full_len) {
+		__skb_queue_head(&ctx->rx_list, skb);
+		rxm->offset += len;
+		rxm->full_len -= len;
+	} else {
+		consume_skb(skb);
+	}
 
 splice_read_end:
 	release_sock(sk);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 54e5553a150e..b9ff1f31f3af 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2878,9 +2878,6 @@ static int unix_shutdown(struct socket *sock, int mode)
 
 	unix_state_lock(sk);
 	sk->sk_shutdown |= mode;
-	if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) &&
-	    mode == SHUTDOWN_MASK)
-		sk->sk_state = TCP_CLOSE;
 	other = unix_peer(sk);
 	if (other)
 		sock_hold(other);
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 4f7c99dfd16c..3f82b2f1e6dd 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -731,6 +731,7 @@ static unsigned int features[] = {
 static struct virtio_driver virtio_vsock_driver = {
 	.feature_table = features,
 	.feature_table_size = ARRAY_SIZE(features),
+	.suppress_used_validation = true,
 	.driver.name = KBUILD_MODNAME,
 	.driver.owner = THIS_MODULE,
 	.id_table = id_table,