Merge tag 'net-6.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from CAN, netfilter, wireguard and IPsec.

  I'd like to highlight [ lowlight? - Linus ] Florian W stepping down as
  a netfilter maintainer due to constant stream of bug reports. Not sure
  what we can do but IIUC this is not the first such case.

  Current release - regressions:

   - rxrpc: fix use of page_frag_alloc_align(), it changed semantics and
     we added a new caller in a different subtree

   - xfrm: allow UDP encapsulation only in offload modes

  Current release - new code bugs:

   - tcp: fix refcnt handling in __inet_hash_connect()

   - Revert "net: Re-use and set mono_delivery_time bit for userspace
     tstamp packets", conflicted with some expectations in BPF uAPI

  Previous releases - regressions:

   - ipv4: raw: fix sending packets from raw sockets via IPsec tunnels

   - devlink: fix devlink's parallel command processing

   - veth: do not manipulate GRO when using XDP

   - esp: fix bad handling of pages from page_pool

  Previous releases - always broken:

   - report RCU QS for busy network kthreads (with Paul McK's blessing)

   - tcp/rds: fix use-after-free on netns with kernel TCP reqsk

   - virt: vmxnet3: fix missing reserved tailroom with XDP

  Misc:

   - couple of build fixes for Documentation"

* tag 'net-6.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (59 commits)
  selftests: forwarding: Fix ping failure due to short timeout
  MAINTAINERS: step down as netfilter maintainer
  netfilter: nf_tables: Fix a memory leak in nf_tables_updchain
  net: dsa: mt7530: fix handling of all link-local frames
  net: dsa: mt7530: fix link-local frames that ingress vlan filtering ports
  bpf: report RCU QS in cpumap kthread
  net: report RCU QS on threaded NAPI repolling
  rcu: add a helper to report consolidated flavor QS
  ionic: update documentation for XDP support
  lib/bitmap: Fix bitmap_scatter() and bitmap_gather() kernel doc
  netfilter: nf_tables: do not compare internal table flags on updates
  netfilter: nft_set_pipapo: release elements in clone only from destroy path
  octeontx2-af: Use separate handlers for interrupts
  octeontx2-pf: Send UP messages to VF only when VF is up.
  octeontx2-pf: Use default max_active works instead of one
  octeontx2-pf: Wait till detach_resources msg is complete
  octeontx2: Detect the mbox up or down message via register
  devlink: fix port new reply cmd type
  tcp: Clear req->syncookie in reqsk_alloc().
  net/bnx2x: Prevent access to a freed page in page_pool
  ...

26 files changed, 104 insertions, 91 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 0766a245816b..9a67003e49db 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2245,7 +2245,7 @@ void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
 	rcu_read_lock();
 again:
 	list_for_each_entry_rcu(ptype, ptype_list, list) {
-		if (ptype->ignore_outgoing)
+		if (READ_ONCE(ptype->ignore_outgoing))
 			continue;
 
 		/* Never send packets back to the socket
@@ -6743,6 +6743,8 @@ static int napi_threaded_poll(void *data)
 	void *have;
 
 	while (!napi_thread_wait(napi)) {
+		unsigned long last_qs = jiffies;
+
 		for (;;) {
 			bool repoll = false;
 
@@ -6767,6 +6769,7 @@ static int napi_threaded_poll(void *data)
 			if (!repoll)
 				break;
 
+			rcu_softirq_qs_periodic(last_qs);
 			cond_resched();
 		}
 	}
@@ -11665,11 +11668,12 @@ static void __init net_dev_struct_check(void)
 
 	/* TXRX read-mostly hotpath */
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, lstats);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, state);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, flags);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, hard_header_len);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, features);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, ip6_ptr);
-	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 38);
+	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 46);
 
 	/* RX read-mostly hotpath */
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ptype_specific);
diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c
index 499885c8b9ca..593605c1b1ef 100644
--- a/net/devlink/netlink.c
+++ b/net/devlink/netlink.c
@@ -193,12 +193,13 @@ devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs,
 	devname = nla_data(attrs[DEVLINK_ATTR_DEV_NAME]);
 
 	devlinks_xa_for_each_registered_get(net, index, devlink) {
-		devl_dev_lock(devlink, dev_lock);
-		if (devl_is_registered(devlink) &&
-		    strcmp(devlink->dev->bus->name, busname) == 0 &&
-		    strcmp(dev_name(devlink->dev), devname) == 0)
-			return devlink;
-		devl_dev_unlock(devlink, dev_lock);
+		if (strcmp(devlink->dev->bus->name, busname) == 0 &&
+		    strcmp(dev_name(devlink->dev), devname) == 0) {
+			devl_dev_lock(devlink, dev_lock);
+			if (devl_is_registered(devlink))
+				return devlink;
+			devl_dev_unlock(devlink, dev_lock);
+		}
 		devlink_put(devlink);
 	}
 
diff --git a/net/devlink/port.c b/net/devlink/port.c
index 4b2d46ccfe48..118d130d2afd 100644
--- a/net/devlink/port.c
+++ b/net/devlink/port.c
@@ -889,7 +889,7 @@ int devlink_nl_port_new_doit(struct sk_buff *skb, struct genl_info *info)
 		err = -ENOMEM;
 		goto err_out_port_del;
 	}
-	err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_NEW,
+	err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_PORT_NEW,
 				   info->snd_portid, info->snd_seq, 0, NULL);
 	if (WARN_ON_ONCE(err))
 		goto err_out_msg_free;
diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c
index 6d14d935ee82..26329db09210 100644
--- a/net/hsr/hsr_framereg.c
+++ b/net/hsr/hsr_framereg.c
@@ -228,6 +228,10 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct list_head *node_db,
 	 */
 	if (ethhdr->h_proto == htons(ETH_P_PRP) ||
 	    ethhdr->h_proto == htons(ETH_P_HSR)) {
+		/* Check if skb contains hsr_ethhdr */
+		if (skb->mac_len < sizeof(struct hsr_ethhdr))
+			return NULL;
+
 		/* Use the existing sequence_nr from the tag as starting point
 		 * for filtering duplicate frames.
 		 */
diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c
index cb83c8feb746..9756e657bab9 100644
--- a/net/hsr/hsr_main.c
+++ b/net/hsr/hsr_main.c
@@ -148,14 +148,21 @@ static struct notifier_block hsr_nb = {
 
 static int __init hsr_init(void)
 {
-	int res;
+	int err;
 
 	BUILD_BUG_ON(sizeof(struct hsr_tag) != HSR_HLEN);
 
-	register_netdevice_notifier(&hsr_nb);
-	res = hsr_netlink_init();
+	err = register_netdevice_notifier(&hsr_nb);
+	if (err)
+		return err;
+
+	err = hsr_netlink_init();
+	if (err) {
+		unregister_netdevice_notifier(&hsr_nb);
+		return err;
+	}
 
-	return res;
+	return 0;
 }
 
 static void __exit hsr_exit(void)
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 4dd9e5040672..d33d12421814 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -95,7 +95,7 @@ static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead,
 			     __alignof__(struct scatterlist));
 }
 
-static void esp_ssg_unref(struct xfrm_state *x, void *tmp)
+static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb)
 {
 	struct crypto_aead *aead = x->data;
 	int extralen = 0;
@@ -114,7 +114,7 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp)
 	 */
 	if (req->src != req->dst)
 		for (sg = sg_next(req->src); sg; sg = sg_next(sg))
-			put_page(sg_page(sg));
+			skb_page_unref(skb, sg_page(sg), false);
 }
 
 #ifdef CONFIG_INET_ESPINTCP
@@ -260,7 +260,7 @@ static void esp_output_done(void *data, int err)
 	}
 
 	tmp = ESP_SKB_CB(skb)->tmp;
-	esp_ssg_unref(x, tmp);
+	esp_ssg_unref(x, tmp, skb);
 	kfree(tmp);
 
 	if (xo && (xo->flags & XFRM_DEV_RESUME)) {
@@ -639,7 +639,7 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 	}
 
 	if (sg != dsg)
-		esp_ssg_unref(x, tmp);
+		esp_ssg_unref(x, tmp, skb);
 
 	if (!err && x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP)
 		err = esp_output_tail_tcp(x, skb);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 7498af320164..cf88eca5f1b4 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -1135,7 +1135,7 @@ error:
 		sock_prot_inuse_add(net, sk->sk_prot, -1);
 
 		spin_lock(lock);
-		sk_nulls_del_node_init_rcu(sk);
+		__sk_nulls_del_node_init_rcu(sk);
 		spin_unlock(lock);
 
 		sk->sk_hash = 0;
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 5befa4de5b24..e8de45d34d56 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -263,12 +263,12 @@ void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm)
 }
 EXPORT_SYMBOL_GPL(__inet_twsk_schedule);
 
+/* Remove all non full sockets (TIME_WAIT and NEW_SYN_RECV) for dead netns */
 void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family)
 {
-	struct inet_timewait_sock *tw;
-	struct sock *sk;
 	struct hlist_nulls_node *node;
 	unsigned int slot;
+	struct sock *sk;
 
 	for (slot = 0; slot <= hashinfo->ehash_mask; slot++) {
 		struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
@@ -277,38 +277,35 @@ restart_rcu:
 		rcu_read_lock();
 restart:
 		sk_nulls_for_each_rcu(sk, node, &head->chain) {
-			if (sk->sk_state != TCP_TIME_WAIT) {
-				/* A kernel listener socket might not hold refcnt for net,
-				 * so reqsk_timer_handler() could be fired after net is
-				 * freed.  Userspace listener and reqsk never exist here.
-				 */
-				if (unlikely(sk->sk_state == TCP_NEW_SYN_RECV &&
-					     hashinfo->pernet)) {
-					struct request_sock *req = inet_reqsk(sk);
-
-					inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, req);
-				}
+			int state = inet_sk_state_load(sk);
 
+			if ((1 << state) & ~(TCPF_TIME_WAIT |
+					     TCPF_NEW_SYN_RECV))
 				continue;
-			}
 
-			tw = inet_twsk(sk);
-			if ((tw->tw_family != family) ||
-				refcount_read(&twsk_net(tw)->ns.count))
+			if (sk->sk_family != family ||
+			    refcount_read(&sock_net(sk)->ns.count))
 				continue;
 
-			if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt)))
+			if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
 				continue;
 
-			if (unlikely((tw->tw_family != family) ||
-				     refcount_read(&twsk_net(tw)->ns.count))) {
-				inet_twsk_put(tw);
+			if (unlikely(sk->sk_family != family ||
+				     refcount_read(&sock_net(sk)->ns.count))) {
+				sock_gen_put(sk);
 				goto restart;
 			}
 
 			rcu_read_unlock();
 			local_bh_disable();
-			inet_twsk_deschedule_put(tw);
+			if (state == TCP_TIME_WAIT) {
+				inet_twsk_deschedule_put(inet_twsk(sk));
+			} else {
+				struct request_sock *req = inet_reqsk(sk);
+
+				inet_csk_reqsk_queue_drop_and_put(req->rsk_listener,
+								  req);
+			}
 			local_bh_enable();
 			goto restart_rcu;
 		}
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 33f93dc730a3..1fe794967211 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1458,7 +1458,6 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	skb->priority = (cork->tos != -1) ? cork->priority: READ_ONCE(sk->sk_priority);
 	skb->mark = cork->mark;
 	skb->tstamp = cork->transmit_time;
-	skb->mono_delivery_time = !!skb->tstamp;
 	/*
 	 * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec
 	 * on dst refcount
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 42ac434cfcfa..dcb11f22cbf2 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -357,10 +357,10 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 		goto error;
 	skb_reserve(skb, hlen);
 
+	skb->protocol = htons(ETH_P_IP);
 	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = sockc->mark;
 	skb->tstamp = sockc->transmit_time;
-	skb->mono_delivery_time = !!skb->tstamp;
 	skb_dst_set(skb, &rt->dst);
 	*rtp = NULL;
 
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 7972ad3d7c73..500f665f98cb 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -474,6 +474,9 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 				  ireq->wscale_ok, &rcv_wscale,
 				  dst_metric(&rt->dst, RTAX_INITRWND));
 
+	/* req->syncookie is set true only if ACK is validated
+	 * by BPF kfunc, then, rcv_wscale is already configured.
+	 */
 	if (!req->syncookie)
 		ireq->rcv_wscale = rcv_wscale;
 	ireq->ecn_ok &= cookie_ecn_ok(net, &rt->dst);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 52040b0e2616..f0761f060a83 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -398,10 +398,6 @@ void tcp_twsk_purge(struct list_head *net_exit_list, int family)
 			/* Even if tw_refcount == 1, we must clean up kernel reqsk */
 			inet_twsk_purge(net->ipv4.tcp_death_row.hashinfo, family);
 		} else if (!purged_once) {
-			/* The last refcount is decremented in tcp_sk_exit_batch() */
-			if (refcount_read(&net->ipv4.tcp_death_row.tw_refcount) == 1)
-				continue;
-
 			inet_twsk_purge(&tcp_hashinfo, family);
 			purged_once = true;
 		}
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 6e6efe026cdc..7371886d4f9f 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -112,7 +112,7 @@ static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead,
 			     __alignof__(struct scatterlist));
 }
 
-static void esp_ssg_unref(struct xfrm_state *x, void *tmp)
+static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb)
 {
 	struct crypto_aead *aead = x->data;
 	int extralen = 0;
@@ -131,7 +131,7 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp)
 	 */
 	if (req->src != req->dst)
 		for (sg = sg_next(req->src); sg; sg = sg_next(sg))
-			put_page(sg_page(sg));
+			skb_page_unref(skb, sg_page(sg), false);
 }
 
 #ifdef CONFIG_INET6_ESPINTCP
@@ -294,7 +294,7 @@ static void esp_output_done(void *data, int err)
 	}
 
 	tmp = ESP_SKB_CB(skb)->tmp;
-	esp_ssg_unref(x, tmp);
+	esp_ssg_unref(x, tmp, skb);
 	kfree(tmp);
 
 	esp_output_encap_csum(skb);
@@ -677,7 +677,7 @@ int esp6_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info
 	}
 
 	if (sg != dsg)
-		esp_ssg_unref(x, tmp);
+		esp_ssg_unref(x, tmp, skb);
 
 	if (!err && x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP)
 		err = esp_output_tail_tcp(x, skb);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 02eeca5492cd..b9dd3a66e423 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1925,7 +1925,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
 	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = cork->base.mark;
 	skb->tstamp = cork->base.transmit_time;
-	skb->mono_delivery_time = !!skb->tstamp;
+
 	ip6_cork_steal_dst(skb, cork);
 	IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS);
 	if (proto == IPPROTO_ICMPV6) {
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index ca49e6617afa..0d896ca7b589 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -622,7 +622,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
 	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = sockc->mark;
 	skb->tstamp = sockc->transmit_time;
-	skb->mono_delivery_time = !!skb->tstamp;
+
 	skb_put(skb, length);
 	skb_reset_network_header(skb);
 	iph = ipv6_hdr(skb);
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 8bad0a44a0a6..6d8286c299c9 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -258,6 +258,9 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 				  ireq->wscale_ok, &rcv_wscale,
 				  dst_metric(dst, RTAX_INITRWND));
 
+	/* req->syncookie is set true only if ACK is validated
+	 * by BPF kfunc, then, rcv_wscale is already configured.
+	 */
 	if (!req->syncookie)
 		ireq->rcv_wscale = rcv_wscale;
 	ireq->ecn_ok &= cookie_ecn_ok(net, dst);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index e93f905e60b6..5fa3d3540c93 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1213,7 +1213,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx)
 	if (flags & ~NFT_TABLE_F_MASK)
 		return -EOPNOTSUPP;
 
-	if (flags == ctx->table->flags)
+	if (flags == (ctx->table->flags & NFT_TABLE_F_MASK))
 		return 0;
 
 	if ((nft_table_has_owner(ctx->table) &&
@@ -2631,19 +2631,6 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
 		}
 	}
 
-	if (nla[NFTA_CHAIN_COUNTERS]) {
-		if (!nft_is_base_chain(chain)) {
-			err = -EOPNOTSUPP;
-			goto err_hooks;
-		}
-
-		stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]);
-		if (IS_ERR(stats)) {
-			err = PTR_ERR(stats);
-			goto err_hooks;
-		}
-	}
-
 	if (!(table->flags & NFT_TABLE_F_DORMANT) &&
 	    nft_is_base_chain(chain) &&
 	    !list_empty(&hook.list)) {
@@ -2658,6 +2645,20 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
 	}
 
 	unregister = true;
+
+	if (nla[NFTA_CHAIN_COUNTERS]) {
+		if (!nft_is_base_chain(chain)) {
+			err = -EOPNOTSUPP;
+			goto err_hooks;
+		}
+
+		stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]);
+		if (IS_ERR(stats)) {
+			err = PTR_ERR(stats);
+			goto err_hooks;
+		}
+	}
+
 	err = -ENOMEM;
 	trans = nft_trans_alloc(ctx, NFT_MSG_NEWCHAIN,
 				sizeof(struct nft_trans_chain));
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index c0ceea068936..df8de5090246 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -2329,8 +2329,6 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx,
 	if (m) {
 		rcu_barrier();
 
-		nft_set_pipapo_match_destroy(ctx, set, m);
-
 		for_each_possible_cpu(cpu)
 			pipapo_free_scratch(m, cpu);
 		free_percpu(m->scratch);
@@ -2342,8 +2340,7 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx,
 	if (priv->clone) {
 		m = priv->clone;
 
-		if (priv->dirty)
-			nft_set_pipapo_match_destroy(ctx, set, m);
+		nft_set_pipapo_match_destroy(ctx, set, m);
 
 		for_each_possible_cpu(cpu)
 			pipapo_free_scratch(priv->clone, cpu);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 61270826b9ac..18f616f487ea 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2057,7 +2057,7 @@ retry:
 	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = READ_ONCE(sk->sk_mark);
 	skb->tstamp = sockc.transmit_time;
-	skb->mono_delivery_time = !!skb->tstamp;
+
 	skb_setup_tx_timestamp(skb, sockc.tsflags);
 
 	if (unlikely(extra_len == 4))
@@ -2586,7 +2586,6 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 	skb->priority = READ_ONCE(po->sk.sk_priority);
 	skb->mark = READ_ONCE(po->sk.sk_mark);
 	skb->tstamp = sockc->transmit_time;
-	skb->mono_delivery_time = !!skb->tstamp;
 	skb_setup_tx_timestamp(skb, sockc->tsflags);
 	skb_zcopy_set_nouarg(skb, ph.raw);
 
@@ -3065,7 +3064,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = sockc.mark;
 	skb->tstamp = sockc.transmit_time;
-	skb->mono_delivery_time = !!skb->tstamp;
 
 	if (unlikely(extra_len == 4))
 		skb->no_fcs = 1;
@@ -4000,7 +3998,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval,
 		if (val < 0 || val > 1)
 			return -EINVAL;
 
-		po->prot_hook.ignore_outgoing = !!val;
+		WRITE_ONCE(po->prot_hook.ignore_outgoing, !!val);
 		return 0;
 	}
 	case PACKET_TX_HAS_OFF:
@@ -4134,7 +4132,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 		       0);
 		break;
 	case PACKET_IGNORE_OUTGOING:
-		val = po->prot_hook.ignore_outgoing;
+		val = READ_ONCE(po->prot_hook.ignore_outgoing);
 		break;
 	case PACKET_ROLLOVER_STATS:
 		if (!po->rollover)
diff --git a/net/rds/send.c b/net/rds/send.c
index 2899def23865..09a280110654 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -103,13 +103,12 @@ EXPORT_SYMBOL_GPL(rds_send_path_reset);
 
 static int acquire_in_xmit(struct rds_conn_path *cp)
 {
-	return test_and_set_bit(RDS_IN_XMIT, &cp->cp_flags) == 0;
+	return test_and_set_bit_lock(RDS_IN_XMIT, &cp->cp_flags) == 0;
 }
 
 static void release_in_xmit(struct rds_conn_path *cp)
 {
-	clear_bit(RDS_IN_XMIT, &cp->cp_flags);
-	smp_mb__after_atomic();
+	clear_bit_unlock(RDS_IN_XMIT, &cp->cp_flags);
 	/*
 	 * We don't use wait_on_bit()/wake_up_bit() because our waking is in a
 	 * hot path and finding waiters is very rare.  We don't want to walk
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 6f765768c49c..894b8fa68e5e 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -349,8 +349,8 @@ reload:
 			 */
 			remain = more ? INT_MAX : msg_data_left(msg);
 			txb = call->conn->security->alloc_txbuf(call, remain, sk->sk_allocation);
-			if (IS_ERR(txb)) {
-				ret = PTR_ERR(txb);
+			if (!txb) {
+				ret = -ENOMEM;
 				goto maybe_error;
 			}
 		}
diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c
index b2a82ab756c2..e0679658d9de 100644
--- a/net/rxrpc/txbuf.c
+++ b/net/rxrpc/txbuf.c
@@ -33,8 +33,8 @@ struct rxrpc_txbuf *rxrpc_alloc_data_txbuf(struct rxrpc_call *call, size_t data_
 	total = hoff + sizeof(*whdr) + data_size;
 
 	mutex_lock(&call->conn->tx_data_alloc_lock);
-	buf = page_frag_alloc_align(&call->conn->tx_data_alloc, total, gfp,
-				    ~(data_align - 1) & ~(L1_CACHE_BYTES - 1));
+	buf = __page_frag_alloc_align(&call->conn->tx_data_alloc, total, gfp,
+				      ~(data_align - 1) & ~(L1_CACHE_BYTES - 1));
 	mutex_unlock(&call->conn->tx_data_alloc_lock);
 	if (!buf) {
 		kfree(txb);
diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c
index 5b595773e59b..358cf304f4c9 100644
--- a/net/sched/sch_fq_pie.c
+++ b/net/sched/sch_fq_pie.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/jhash.h>
+#include <linux/module.h>
 #include <linux/sizes.h>
 #include <linux/vmalloc.h>
 #include <net/pkt_cls.h>
@@ -563,6 +564,7 @@ static struct Qdisc_ops fq_pie_qdisc_ops __read_mostly = {
 	.dump_stats	= fq_pie_dump_stats,
 	.owner		= THIS_MODULE,
 };
+MODULE_ALIAS_NET_SCH("fq_pie");
 
 static int __init fq_pie_module_init(void)
 {
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index c5de70efdc86..a0d54b422186 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -997,7 +997,8 @@ static const struct nla_policy entry_policy[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = {
 };
 
 static const struct nla_policy taprio_tc_policy[TCA_TAPRIO_TC_ENTRY_MAX + 1] = {
-	[TCA_TAPRIO_TC_ENTRY_INDEX]	   = { .type = NLA_U32 },
+	[TCA_TAPRIO_TC_ENTRY_INDEX]	   = NLA_POLICY_MAX(NLA_U32,
+							    TC_QOPT_MAX_QUEUE),
 	[TCA_TAPRIO_TC_ENTRY_MAX_SDU]	   = { .type = NLA_U32 },
 	[TCA_TAPRIO_TC_ENTRY_FP]	   = NLA_POLICY_RANGE(NLA_U32,
 							      TC_FP_EXPRESS,
diff --git a/net/socket.c b/net/socket.c
index 7e9c8fc9a5b4..e5f3af49a8b6 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2600,9 +2600,9 @@ out:
 	return err;
 }
 
-int sendmsg_copy_msghdr(struct msghdr *msg,
-			struct user_msghdr __user *umsg, unsigned flags,
-			struct iovec **iov)
+static int sendmsg_copy_msghdr(struct msghdr *msg,
+			       struct user_msghdr __user *umsg, unsigned flags,
+			       struct iovec **iov)
 {
 	int err;
 
@@ -2753,10 +2753,10 @@ SYSCALL_DEFINE4(sendmmsg, int, fd, struct mmsghdr __user *, mmsg,
 	return __sys_sendmmsg(fd, mmsg, vlen, flags, true);
 }
 
-int recvmsg_copy_msghdr(struct msghdr *msg,
-			struct user_msghdr __user *umsg, unsigned flags,
-			struct sockaddr __user **uaddr,
-			struct iovec **iov)
+static int recvmsg_copy_msghdr(struct msghdr *msg,
+			       struct user_msghdr __user *umsg, unsigned flags,
+			       struct sockaddr __user **uaddr,
+			       struct iovec **iov)
 {
 	ssize_t err;
 
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 653e51ae3964..6346690d5c69 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -407,7 +407,8 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x)
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 	struct net_device *dev = x->xso.dev;
 
-	if (!x->type_offload)
+	if (!x->type_offload ||
+	    (x->xso.type == XFRM_DEV_OFFLOAD_UNSPECIFIED && x->encap))
 		return false;
 
 	if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET ||