Merge tag 'net-5.18-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from can, xfrm and netfilter subtrees.

  Notably this reverts a recent TCP/DCCP netns-related change to address
  a possible UaF.

  Current release - regressions:

   - tcp: revert "tcp/dccp: get rid of inet_twsk_purge()"

   - xfrm: set dst dev to blackhole_netdev instead of loopback_dev in
     ifdown

  Previous releases - regressions:

   - netfilter: flowtable: fix TCP flow teardown

   - can: revert "can: m_can: pci: use custom bit timings for Elkhart
     Lake"

   - xfrm: check encryption module availability consistency

   - eth: vmxnet3: fix possible use-after-free bugs in
     vmxnet3_rq_alloc_rx_buf()

   - eth: mlx5: initialize flow steering during driver probe

   - eth: ice: fix crash when writing timestamp on RX rings

  Previous releases - always broken:

   - mptcp: fix checksum byte order

   - eth: lan966x: fix assignment of the MAC address

   - eth: mlx5: remove HW-GRO from reported features

   - eth: ftgmac100: disable hardware checksum on AST2600"

* tag 'net-5.18-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (50 commits)
  net: bridge: Clear offload_fwd_mark when passing frame up bridge interface.
  ptp: ocp: change sysfs attr group handling
  selftests: forwarding: fix missing backslash
  netfilter: nf_tables: disable expression reduction infra
  netfilter: flowtable: move dst_check to packet path
  netfilter: flowtable: fix TCP flow teardown
  net: ftgmac100: Disable hardware checksum on AST2600
  igb: skip phy status check where unavailable
  nfc: pn533: Fix buggy cleanup order
  mptcp: Do TCP fallback on early DSS checksum failure
  mptcp: fix checksum byte order
  net: af_key: check encryption module availability consistency
  net: af_key: add check for pfkey_broadcast in function pfkey_process
  net/mlx5: Drain fw_reset when removing device
  net/mlx5e: CT: Fix setting flow_source for smfs ct tuples
  net/mlx5e: CT: Fix support for GRE tuples
  net/mlx5e: Remove HW-GRO from reported features
  net/mlx5e: Properly block HW GRO when XDP is enabled
  net/mlx5e: Properly block LRO when XDP is enabled
  net/mlx5e: Block rx-gro-hw feature in switchdev mode
  ...

21 files changed, 231 insertions, 116 deletions

diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 196417859c4a..68b3e850bcb9 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -39,6 +39,13 @@ static int br_pass_frame_up(struct sk_buff *skb)
 	dev_sw_netstats_rx_add(brdev, skb->len);
 
 	vg = br_vlan_group_rcu(br);
+
+	/* Reset the offload_fwd_mark because there could be a stacked
+	 * bridge above, and it should not think this bridge it doing
+	 * that bridge's work forwarding out its ports.
+	 */
+	br_switchdev_frame_unmark(skb);
+
 	/* Bridge is just like any other port.  Make sure the
 	 * packet is allowed except in promisc mode when someone
 	 * may be running packet capture.
diff --git a/net/core/dev.c b/net/core/dev.c
index 1461c2d9dec8..2771fd22dc6a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -681,11 +681,11 @@ int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr,
 	const struct net_device *last_dev;
 	struct net_device_path_ctx ctx = {
 		.dev	= dev,
-		.daddr	= daddr,
 	};
 	struct net_device_path *path;
 	int ret = 0;
 
+	memcpy(ctx.daddr, daddr, sizeof(ctx.daddr));
 	stack->num_paths = 0;
 	while (ctx.dev && ctx.dev->netdev_ops->ndo_fill_forward_path) {
 		last_dev = ctx.dev;
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index ae662567a6cb..0ea29270d7e5 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -1030,9 +1030,15 @@ static void __net_exit dccp_v4_exit_net(struct net *net)
 	inet_ctl_sock_destroy(pn->v4_ctl_sk);
 }
 
+static void __net_exit dccp_v4_exit_batch(struct list_head *net_exit_list)
+{
+	inet_twsk_purge(&dccp_hashinfo, AF_INET);
+}
+
 static struct pernet_operations dccp_v4_ops = {
 	.init	= dccp_v4_init_net,
 	.exit	= dccp_v4_exit_net,
+	.exit_batch = dccp_v4_exit_batch,
 	.id	= &dccp_v4_pernet_id,
 	.size   = sizeof(struct dccp_v4_pernet),
 };
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index eab3bd1ee9a0..fa663518fa0e 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -1115,9 +1115,15 @@ static void __net_exit dccp_v6_exit_net(struct net *net)
 	inet_ctl_sock_destroy(pn->v6_ctl_sk);
 }
 
+static void __net_exit dccp_v6_exit_batch(struct list_head *net_exit_list)
+{
+	inet_twsk_purge(&dccp_hashinfo, AF_INET6);
+}
+
 static struct pernet_operations dccp_v6_ops = {
 	.init   = dccp_v6_init_net,
 	.exit   = dccp_v6_exit_net,
+	.exit_batch = dccp_v6_exit_batch,
 	.id	= &dccp_v6_pernet_id,
 	.size   = sizeof(struct dccp_v6_pernet),
 };
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 9e0bbd026560..0ec501845cb3 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -52,7 +52,8 @@ static void inet_twsk_kill(struct inet_timewait_sock *tw)
 	spin_unlock(lock);
 
 	/* Disassociate with bind bucket. */
-	bhead = &hashinfo->bhash[tw->tw_bslot];
+	bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num,
+			hashinfo->bhash_size)];
 
 	spin_lock(&bhead->lock);
 	inet_twsk_bind_unhash(tw, hashinfo);
@@ -111,12 +112,8 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 	   Note, that any socket with inet->num != 0 MUST be bound in
 	   binding cache, even if it is closed.
 	 */
-	/* Cache inet_bhashfn(), because 'struct net' might be no longer
-	 * available later in inet_twsk_kill().
-	 */
-	tw->tw_bslot = inet_bhashfn(twsk_net(tw), inet->inet_num,
-				    hashinfo->bhash_size);
-	bhead = &hashinfo->bhash[tw->tw_bslot];
+	bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num,
+			hashinfo->bhash_size)];
 	spin_lock(&bhead->lock);
 	tw->tw_tb = icsk->icsk_bind_hash;
 	WARN_ON(!icsk->icsk_bind_hash);
@@ -257,3 +254,50 @@ void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm)
 	}
 }
 EXPORT_SYMBOL_GPL(__inet_twsk_schedule);
+
+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;
+
+	for (slot = 0; slot <= hashinfo->ehash_mask; slot++) {
+		struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
+restart_rcu:
+		cond_resched();
+		rcu_read_lock();
+restart:
+		sk_nulls_for_each_rcu(sk, node, &head->chain) {
+			if (sk->sk_state != TCP_TIME_WAIT)
+				continue;
+			tw = inet_twsk(sk);
+			if ((tw->tw_family != family) ||
+				refcount_read(&twsk_net(tw)->ns.count))
+				continue;
+
+			if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt)))
+				continue;
+
+			if (unlikely((tw->tw_family != family) ||
+				     refcount_read(&twsk_net(tw)->ns.count))) {
+				inet_twsk_put(tw);
+				goto restart;
+			}
+
+			rcu_read_unlock();
+			local_bh_disable();
+			inet_twsk_deschedule_put(tw);
+			local_bh_enable();
+			goto restart_rcu;
+		}
+		/* If the nulls value we got at the end of this lookup is
+		 * not the expected one, we must restart lookup.
+		 * We probably met an item that was moved to another chain.
+		 */
+		if (get_nulls_value(node) != slot)
+			goto restart;
+		rcu_read_unlock();
+	}
+}
+EXPORT_SYMBOL_GPL(inet_twsk_purge);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 57abd27e842c..ed01063d8f30 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1726,6 +1726,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	struct in_device *in_dev = __in_dev_get_rcu(dev);
 	unsigned int flags = RTCF_MULTICAST;
 	struct rtable *rth;
+	bool no_policy;
 	u32 itag = 0;
 	int err;
 
@@ -1736,8 +1737,12 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	if (our)
 		flags |= RTCF_LOCAL;
 
+	no_policy = IN_DEV_ORCONF(in_dev, NOPOLICY);
+	if (no_policy)
+		IPCB(skb)->flags |= IPSKB_NOPOLICY;
+
 	rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST,
-			   IN_DEV_ORCONF(in_dev, NOPOLICY), false);
+			   no_policy, false);
 	if (!rth)
 		return -ENOBUFS;
 
@@ -1796,7 +1801,7 @@ static int __mkroute_input(struct sk_buff *skb,
 	struct rtable *rth;
 	int err;
 	struct in_device *out_dev;
-	bool do_cache;
+	bool do_cache, no_policy;
 	u32 itag = 0;
 
 	/* get a working reference to the output device */
@@ -1841,6 +1846,10 @@ static int __mkroute_input(struct sk_buff *skb,
 		}
 	}
 
+	no_policy = IN_DEV_ORCONF(in_dev, NOPOLICY);
+	if (no_policy)
+		IPCB(skb)->flags |= IPSKB_NOPOLICY;
+
 	fnhe = find_exception(nhc, daddr);
 	if (do_cache) {
 		if (fnhe)
@@ -1853,8 +1862,7 @@ static int __mkroute_input(struct sk_buff *skb,
 		}
 	}
 
-	rth = rt_dst_alloc(out_dev->dev, 0, res->type,
-			   IN_DEV_ORCONF(in_dev, NOPOLICY),
+	rth = rt_dst_alloc(out_dev->dev, 0, res->type, no_policy,
 			   IN_DEV_ORCONF(out_dev, NOXFRM));
 	if (!rth) {
 		err = -ENOBUFS;
@@ -2229,6 +2237,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	struct rtable	*rth;
 	struct flowi4	fl4;
 	bool do_cache = true;
+	bool no_policy;
 
 	/* IP on this device is disabled. */
 
@@ -2347,6 +2356,10 @@ brd_input:
 	RT_CACHE_STAT_INC(in_brd);
 
 local_input:
+	no_policy = IN_DEV_ORCONF(in_dev, NOPOLICY);
+	if (no_policy)
+		IPCB(skb)->flags |= IPSKB_NOPOLICY;
+
 	do_cache &= res->fi && !itag;
 	if (do_cache) {
 		struct fib_nh_common *nhc = FIB_RES_NHC(*res);
@@ -2361,7 +2374,7 @@ local_input:
 
 	rth = rt_dst_alloc(ip_rt_get_dev(net, res),
 			   flags | RTCF_LOCAL, res->type,
-			   IN_DEV_ORCONF(in_dev, NOPOLICY), false);
+			   no_policy, false);
 	if (!rth)
 		goto e_nobufs;
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index f9cec624068d..457f5b5d5d4a 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -3173,6 +3173,8 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
 {
 	struct net *net;
 
+	inet_twsk_purge(&tcp_hashinfo, AF_INET);
+
 	list_for_each_entry(net, net_exit_list, exit_list)
 		tcp_fastopen_ctx_destroy(net);
 }
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 13678d3908fa..faaddaf43c90 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -2207,9 +2207,15 @@ static void __net_exit tcpv6_net_exit(struct net *net)
 	inet_ctl_sock_destroy(net->ipv6.tcp_sk);
 }
 
+static void __net_exit tcpv6_net_exit_batch(struct list_head *net_exit_list)
+{
+	inet_twsk_purge(&tcp_hashinfo, AF_INET6);
+}
+
 static struct pernet_operations tcpv6_net_ops = {
 	.init	    = tcpv6_net_init,
 	.exit	    = tcpv6_net_exit,
+	.exit_batch = tcpv6_net_exit_batch,
 };
 
 int __init tcpv6_init(void)
diff --git a/net/key/af_key.c b/net/key/af_key.c
index fd51db3be91c..339d95df19d3 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -2826,8 +2826,10 @@ static int pfkey_process(struct sock *sk, struct sk_buff *skb, const struct sadb
 	void *ext_hdrs[SADB_EXT_MAX];
 	int err;
 
-	pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL,
-			BROADCAST_PROMISC_ONLY, NULL, sock_net(sk));
+	err = pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL,
+			      BROADCAST_PROMISC_ONLY, NULL, sock_net(sk));
+	if (err)
+		return err;
 
 	memset(ext_hdrs, 0, sizeof(ext_hdrs));
 	err = parse_exthdrs(skb, hdr, ext_hdrs);
@@ -2898,7 +2900,7 @@ static int count_ah_combs(const struct xfrm_tmpl *t)
 			break;
 		if (!aalg->pfkey_supported)
 			continue;
-		if (aalg_tmpl_set(t, aalg))
+		if (aalg_tmpl_set(t, aalg) && aalg->available)
 			sz += sizeof(struct sadb_comb);
 	}
 	return sz + sizeof(struct sadb_prop);
@@ -2916,7 +2918,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t)
 		if (!ealg->pfkey_supported)
 			continue;
 
-		if (!(ealg_tmpl_set(t, ealg)))
+		if (!(ealg_tmpl_set(t, ealg) && ealg->available))
 			continue;
 
 		for (k = 1; ; k++) {
@@ -2927,7 +2929,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t)
 			if (!aalg->pfkey_supported)
 				continue;
 
-			if (aalg_tmpl_set(t, aalg))
+			if (aalg_tmpl_set(t, aalg) && aalg->available)
 				sz += sizeof(struct sadb_comb);
 		}
 	}
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 325383646f5c..b548cec86c9d 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -107,7 +107,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 			ptr += 2;
 		}
 		if (opsize == TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM) {
-			mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr);
+			mp_opt->csum = get_unaligned((__force __sum16 *)ptr);
 			mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD;
 			ptr += 2;
 		}
@@ -221,7 +221,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 
 			if (opsize == expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) {
 				mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD;
-				mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr);
+				mp_opt->csum = get_unaligned((__force __sum16 *)ptr);
 				ptr += 2;
 			}
 
@@ -1240,7 +1240,7 @@ static void mptcp_set_rwin(const struct tcp_sock *tp)
 		WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
 }
 
-u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum)
+__sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum)
 {
 	struct csum_pseudo_header header;
 	__wsum csum;
@@ -1256,15 +1256,25 @@ u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum)
 	header.csum = 0;
 
 	csum = csum_partial(&header, sizeof(header), sum);
-	return (__force u16)csum_fold(csum);
+	return csum_fold(csum);
 }
 
-static u16 mptcp_make_csum(const struct mptcp_ext *mpext)
+static __sum16 mptcp_make_csum(const struct mptcp_ext *mpext)
 {
 	return __mptcp_make_csum(mpext->data_seq, mpext->subflow_seq, mpext->data_len,
 				 ~csum_unfold(mpext->csum));
 }
 
+static void put_len_csum(u16 len, __sum16 csum, void *data)
+{
+	__sum16 *sumptr = data + 2;
+	__be16 *ptr = data;
+
+	put_unaligned_be16(len, ptr);
+
+	put_unaligned(csum, sumptr);
+}
+
 void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
 			 struct mptcp_out_options *opts)
 {
@@ -1340,8 +1350,9 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
 			put_unaligned_be32(mpext->subflow_seq, ptr);
 			ptr += 1;
 			if (opts->csum_reqd) {
-				put_unaligned_be32(mpext->data_len << 16 |
-						   mptcp_make_csum(mpext), ptr);
+				put_len_csum(mpext->data_len,
+					     mptcp_make_csum(mpext),
+					     ptr);
 			} else {
 				put_unaligned_be32(mpext->data_len << 16 |
 						   TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
@@ -1392,11 +1403,12 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
 			goto mp_capable_done;
 
 		if (opts->csum_reqd) {
-			put_unaligned_be32(opts->data_len << 16 |
-					   __mptcp_make_csum(opts->data_seq,
-							     opts->subflow_seq,
-							     opts->data_len,
-							     ~csum_unfold(opts->csum)), ptr);
+			put_len_csum(opts->data_len,
+				     __mptcp_make_csum(opts->data_seq,
+						       opts->subflow_seq,
+						       opts->data_len,
+						       ~csum_unfold(opts->csum)),
+				     ptr);
 		} else {
 			put_unaligned_be32(opts->data_len << 16 |
 					   TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 01809eef29b4..aa51b100e033 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -178,14 +178,13 @@ void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct sock *ssk,
 	struct mptcp_pm_data *pm = &msk->pm;
 	bool update_subflows;
 
-	update_subflows = (ssk->sk_state == TCP_CLOSE) &&
-			  (subflow->request_join || subflow->mp_join);
+	update_subflows = subflow->request_join || subflow->mp_join;
 	if (!READ_ONCE(pm->work_pending) && !update_subflows)
 		return;
 
 	spin_lock_bh(&pm->lock);
 	if (update_subflows)
-		pm->subflows--;
+		__mptcp_pm_close_subflow(msk);
 
 	/* Even if this subflow is not really established, tell the PM to try
 	 * to pick the next ones, if possible.
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 3c1a3036550f..5655a63aa6a8 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -443,7 +443,8 @@ struct mptcp_subflow_context {
 		can_ack : 1,        /* only after processing the remote a key */
 		disposable : 1,	    /* ctx can be free at ulp release time */
 		stale : 1,	    /* unable to snd/rcv data, do not use for xmit */
-		local_id_valid : 1; /* local_id is correctly initialized */
+		local_id_valid : 1, /* local_id is correctly initialized */
+		valid_csum_seen : 1;        /* at least one csum validated */
 	enum mptcp_data_avail data_avail;
 	u32	remote_nonce;
 	u64	thmac;
@@ -723,7 +724,7 @@ void mptcp_token_destroy(struct mptcp_sock *msk);
 void mptcp_crypto_key_sha(u64 key, u32 *token, u64 *idsn);
 
 void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac);
-u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum);
+__sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum);
 
 void __init mptcp_pm_init(void);
 void mptcp_pm_data_init(struct mptcp_sock *msk);
@@ -833,6 +834,20 @@ unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk);
 unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk);
 unsigned int mptcp_pm_get_local_addr_max(const struct mptcp_sock *msk);
 
+/* called under PM lock */
+static inline void __mptcp_pm_close_subflow(struct mptcp_sock *msk)
+{
+	if (--msk->pm.subflows < mptcp_pm_get_subflows_max(msk))
+		WRITE_ONCE(msk->pm.accept_subflow, true);
+}
+
+static inline void mptcp_pm_close_subflow(struct mptcp_sock *msk)
+{
+	spin_lock_bh(&msk->pm.lock);
+	__mptcp_pm_close_subflow(msk);
+	spin_unlock_bh(&msk->pm.lock);
+}
+
 void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk);
 void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk);
 
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index aba260f547da..be76ada89d96 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -888,7 +888,7 @@ static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff *
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	u32 offset, seq, delta;
-	u16 csum;
+	__sum16 csum;
 	int len;
 
 	if (!csum_reqd)
@@ -955,11 +955,14 @@ static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff *
 				 subflow->map_data_csum);
 	if (unlikely(csum)) {
 		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DATACSUMERR);
-		subflow->send_mp_fail = 1;
-		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPFAILTX);
+		if (subflow->mp_join || subflow->valid_csum_seen) {
+			subflow->send_mp_fail = 1;
+			MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPFAILTX);
+		}
 		return subflow->mp_join ? MAPPING_INVALID : MAPPING_DUMMY;
 	}
 
+	subflow->valid_csum_seen = 1;
 	return MAPPING_OK;
 }
 
@@ -1141,6 +1144,18 @@ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ss
 	}
 }
 
+static bool subflow_can_fallback(struct mptcp_subflow_context *subflow)
+{
+	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+
+	if (subflow->mp_join)
+		return false;
+	else if (READ_ONCE(msk->csum_enabled))
+		return !subflow->valid_csum_seen;
+	else
+		return !subflow->fully_established;
+}
+
 static bool subflow_check_data_avail(struct sock *ssk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
@@ -1218,7 +1233,7 @@ fallback:
 		return true;
 	}
 
-	if (subflow->mp_join || subflow->fully_established) {
+	if (!subflow_can_fallback(subflow)) {
 		/* fatal protocol error, close the socket.
 		 * subflow_error_report() will introduce the appropriate barriers
 		 */
@@ -1422,20 +1437,20 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 	struct sockaddr_storage addr;
 	int remote_id = remote->id;
 	int local_id = loc->id;
+	int err = -ENOTCONN;
 	struct socket *sf;
 	struct sock *ssk;
 	u32 remote_token;
 	int addrlen;
 	int ifindex;
 	u8 flags;
-	int err;
 
 	if (!mptcp_is_fully_established(sk))
-		return -ENOTCONN;
+		goto err_out;
 
 	err = mptcp_subflow_create_socket(sk, &sf);
 	if (err)
-		return err;
+		goto err_out;
 
 	ssk = sf->sk;
 	subflow = mptcp_subflow_ctx(ssk);
@@ -1492,6 +1507,12 @@ failed_unlink:
 failed:
 	subflow->disposable = 1;
 	sock_release(sf);
+
+err_out:
+	/* we account subflows before the creation, and this failures will not
+	 * be caught by sk_state_change()
+	 */
+	mptcp_pm_close_subflow(msk);
 	return err;
 }
 
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 3db256da919b..f2def06d1070 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -179,12 +179,11 @@ EXPORT_SYMBOL_GPL(flow_offload_route_init);
 
 static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp)
 {
-	tcp->state = TCP_CONNTRACK_ESTABLISHED;
 	tcp->seen[0].td_maxwin = 0;
 	tcp->seen[1].td_maxwin = 0;
 }
 
-static void flow_offload_fixup_ct_timeout(struct nf_conn *ct)
+static void flow_offload_fixup_ct(struct nf_conn *ct)
 {
 	struct net *net = nf_ct_net(ct);
 	int l4num = nf_ct_protonum(ct);
@@ -193,7 +192,9 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct)
 	if (l4num == IPPROTO_TCP) {
 		struct nf_tcp_net *tn = nf_tcp_pernet(net);
 
-		timeout = tn->timeouts[TCP_CONNTRACK_ESTABLISHED];
+		flow_offload_fixup_tcp(&ct->proto.tcp);
+
+		timeout = tn->timeouts[ct->proto.tcp.state];
 		timeout -= tn->offload_timeout;
 	} else if (l4num == IPPROTO_UDP) {
 		struct nf_udp_net *tn = nf_udp_pernet(net);
@@ -211,18 +212,6 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct)
 		WRITE_ONCE(ct->timeout, nfct_time_stamp + timeout);
 }
 
-static void flow_offload_fixup_ct_state(struct nf_conn *ct)
-{
-	if (nf_ct_protonum(ct) == IPPROTO_TCP)
-		flow_offload_fixup_tcp(&ct->proto.tcp);
-}
-
-static void flow_offload_fixup_ct(struct nf_conn *ct)
-{
-	flow_offload_fixup_ct_state(ct);
-	flow_offload_fixup_ct_timeout(ct);
-}
-
 static void flow_offload_route_release(struct flow_offload *flow)
 {
 	nft_flow_dst_release(flow, FLOW_OFFLOAD_DIR_ORIGINAL);
@@ -335,8 +324,10 @@ void flow_offload_refresh(struct nf_flowtable *flow_table,
 	u32 timeout;
 
 	timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow);
-	if (READ_ONCE(flow->timeout) != timeout)
+	if (timeout - READ_ONCE(flow->timeout) > HZ)
 		WRITE_ONCE(flow->timeout, timeout);
+	else
+		return;
 
 	if (likely(!nf_flowtable_hw_offload(flow_table)))
 		return;
@@ -359,22 +350,14 @@ static void flow_offload_del(struct nf_flowtable *flow_table,
 	rhashtable_remove_fast(&flow_table->rhashtable,
 			       &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node,
 			       nf_flow_offload_rhash_params);
-
-	clear_bit(IPS_OFFLOAD_BIT, &flow->ct->status);
-
-	if (nf_flow_has_expired(flow))
-		flow_offload_fixup_ct(flow->ct);
-	else
-		flow_offload_fixup_ct_timeout(flow->ct);
-
 	flow_offload_free(flow);
 }
 
 void flow_offload_teardown(struct flow_offload *flow)
 {
+	clear_bit(IPS_OFFLOAD_BIT, &flow->ct->status);
 	set_bit(NF_FLOW_TEARDOWN, &flow->flags);
-
-	flow_offload_fixup_ct_state(flow->ct);
+	flow_offload_fixup_ct(flow->ct);
 }
 EXPORT_SYMBOL_GPL(flow_offload_teardown);
 
@@ -438,33 +421,12 @@ nf_flow_table_iterate(struct nf_flowtable *flow_table,
 	return err;
 }
 
-static bool flow_offload_stale_dst(struct flow_offload_tuple *tuple)
-{
-	struct dst_entry *dst;
-
-	if (tuple->xmit_type == FLOW_OFFLOAD_XMIT_NEIGH ||
-	    tuple->xmit_type == FLOW_OFFLOAD_XMIT_XFRM) {
-		dst = tuple->dst_cache;
-		if (!dst_check(dst, tuple->dst_cookie))
-			return true;
-	}
-
-	return false;
-}
-
-static bool nf_flow_has_stale_dst(struct flow_offload *flow)
-{
-	return flow_offload_stale_dst(&flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple) ||
-	       flow_offload_stale_dst(&flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple);
-}
-
 static void nf_flow_offload_gc_step(struct nf_flowtable *flow_table,
 				    struct flow_offload *flow, void *data)
 {
 	if (nf_flow_has_expired(flow) ||
-	    nf_ct_is_dying(flow->ct) ||
-	    nf_flow_has_stale_dst(flow))
-		set_bit(NF_FLOW_TEARDOWN, &flow->flags);
+	    nf_ct_is_dying(flow->ct))
+		flow_offload_teardown(flow);
 
 	if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) {
 		if (test_bit(NF_FLOW_HW, &flow->flags)) {
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index 32c0eb1b4821..b350fe9d00b0 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -248,6 +248,15 @@ static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
 	return true;
 }
 
+static inline bool nf_flow_dst_check(struct flow_offload_tuple *tuple)
+{
+	if (tuple->xmit_type != FLOW_OFFLOAD_XMIT_NEIGH &&
+	    tuple->xmit_type != FLOW_OFFLOAD_XMIT_XFRM)
+		return true;
+
+	return dst_check(tuple->dst_cache, tuple->dst_cookie);
+}
+
 static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb,
 				      const struct nf_hook_state *state,
 				      struct dst_entry *dst)
@@ -367,6 +376,11 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 	if (nf_flow_state_check(flow, iph->protocol, skb, thoff))
 		return NF_ACCEPT;
 
+	if (!nf_flow_dst_check(&tuplehash->tuple)) {
+		flow_offload_teardown(flow);
+		return NF_ACCEPT;
+	}
+
 	if (skb_try_make_writable(skb, thoff + hdrsize))
 		return NF_DROP;
 
@@ -624,6 +638,11 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 	if (nf_flow_state_check(flow, ip6h->nexthdr, skb, thoff))
 		return NF_ACCEPT;
 
+	if (!nf_flow_dst_check(&tuplehash->tuple)) {
+		flow_offload_teardown(flow);
+		return NF_ACCEPT;
+	}
+
 	if (skb_try_make_writable(skb, thoff + hdrsize))
 		return NF_DROP;
 
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 16c3a39689f4..a096b9fbbbdf 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -8342,16 +8342,7 @@ EXPORT_SYMBOL_GPL(nf_tables_trans_destroy_flush_work);
 static bool nft_expr_reduce(struct nft_regs_track *track,
 			    const struct nft_expr *expr)
 {
-	if (!expr->ops->reduce) {
-		pr_warn_once("missing reduce for expression %s ",
-			     expr->ops->type->name);
-		return false;
-	}
-
-	if (nft_reduce_is_readonly(expr))
-		return false;
-
-	return expr->ops->reduce(track, expr);
+	return false;
 }
 
 static int nf_tables_commit_chain_prepare(struct net *net, struct nft_chain *chain)
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index 900d48c810a1..6f0b07fe648d 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -36,6 +36,15 @@ static void nft_default_forward_path(struct nf_flow_route *route,
 	route->tuple[dir].xmit_type	= nft_xmit_type(dst_cache);
 }
 
+static bool nft_is_valid_ether_device(const struct net_device *dev)
+{
+	if (!dev || (dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER ||
+	    dev->addr_len != ETH_ALEN || !is_valid_ether_addr(dev->dev_addr))
+		return false;
+
+	return true;
+}
+
 static int nft_dev_fill_forward_path(const struct nf_flow_route *route,
 				     const struct dst_entry *dst_cache,
 				     const struct nf_conn *ct,
@@ -47,6 +56,9 @@ static int nft_dev_fill_forward_path(const struct nf_flow_route *route,
 	struct neighbour *n;
 	u8 nud_state;
 
+	if (!nft_is_valid_ether_device(dev))
+		goto out;
+
 	n = dst_neigh_lookup(dst_cache, daddr);
 	if (!n)
 		return -1;
@@ -60,6 +72,7 @@ static int nft_dev_fill_forward_path(const struct nf_flow_route *route,
 	if (!(nud_state & NUD_VALID))
 		return -1;
 
+out:
 	return dev_fill_forward_path(dev, ha, stack);
 }
 
@@ -78,15 +91,6 @@ struct nft_forward_info {
 	enum flow_offload_xmit_type xmit_type;
 };
 
-static bool nft_is_valid_ether_device(const struct net_device *dev)
-{
-	if (!dev || (dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER ||
-	    dev->addr_len != ETH_ALEN || !is_valid_ether_addr(dev->dev_addr))
-		return false;
-
-	return true;
-}
-
 static void nft_dev_path_info(const struct net_device_path_stack *stack,
 			      struct nft_forward_info *info,
 			      unsigned char *ha, struct nf_flowtable *flowtable)
@@ -119,7 +123,8 @@ static void nft_dev_path_info(const struct net_device_path_stack *stack,
 				info->indev = NULL;
 				break;
 			}
-			info->outdev = path->dev;
+			if (!info->outdev)
+				info->outdev = path->dev;
 			info->encap[info->num_encaps].id = path->encap.id;
 			info->encap[info->num_encaps].proto = path->encap.proto;
 			info->num_encaps++;
@@ -293,7 +298,8 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
 	case IPPROTO_TCP:
 		tcph = skb_header_pointer(pkt->skb, nft_thoff(pkt),
 					  sizeof(_tcph), &_tcph);
-		if (unlikely(!tcph || tcph->fin || tcph->rst))
+		if (unlikely(!tcph || tcph->fin || tcph->rst ||
+			     !nf_conntrack_tcp_established(ct)))
 			goto out;
 		break;
 	case IPPROTO_UDP:
diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c
index 6055dc9a82aa..aa5e712adf07 100644
--- a/net/nfc/nci/data.c
+++ b/net/nfc/nci/data.c
@@ -118,7 +118,7 @@ static int nci_queue_tx_data_frags(struct nci_dev *ndev,
 
 		skb_frag = nci_skb_alloc(ndev,
 					 (NCI_DATA_HDR_SIZE + frag_len),
-					 GFP_KERNEL);
+					 GFP_ATOMIC);
 		if (skb_frag == NULL) {
 			rc = -ENOMEM;
 			goto free_exit;
diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c
index 19703a649b5a..78c4b6addf15 100644
--- a/net/nfc/nci/hci.c
+++ b/net/nfc/nci/hci.c
@@ -153,7 +153,7 @@ static int nci_hci_send_data(struct nci_dev *ndev, u8 pipe,
 
 	i = 0;
 	skb = nci_skb_alloc(ndev, conn_info->max_pkt_payload_len +
-			    NCI_DATA_HDR_SIZE, GFP_KERNEL);
+			    NCI_DATA_HDR_SIZE, GFP_ATOMIC);
 	if (!skb)
 		return -ENOMEM;
 
@@ -184,7 +184,7 @@ static int nci_hci_send_data(struct nci_dev *ndev, u8 pipe,
 		if (i < data_len) {
 			skb = nci_skb_alloc(ndev,
 					    conn_info->max_pkt_payload_len +
-					    NCI_DATA_HDR_SIZE, GFP_KERNEL);
+					    NCI_DATA_HDR_SIZE, GFP_ATOMIC);
 			if (!skb)
 				return -ENOMEM;
 
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 0eaaf1f45de1..211c757bfc3c 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -232,6 +232,10 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	for (i = 0; i < p->tcfp_nkeys; ++i) {
 		u32 cur = p->tcfp_keys[i].off;
 
+		/* sanitize the shift value for any later use */
+		p->tcfp_keys[i].shift = min_t(size_t, BITS_PER_TYPE(int) - 1,
+					      p->tcfp_keys[i].shift);
+
 		/* The AT option can read a single byte, we can bound the actual
 		 * value with uchar max.
 		 */
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 00bd0ecff5a1..f1876ea61fdc 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -3744,7 +3744,7 @@ static int stale_bundle(struct dst_entry *dst)
 void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev)
 {
 	while ((dst = xfrm_dst_child(dst)) && dst->xfrm && dst->dev == dev) {
-		dst->dev = dev_net(dev)->loopback_dev;
+		dst->dev = blackhole_netdev;
 		dev_hold(dst->dev);
 		dev_put(dev);
 	}