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

Cross-merge networking fixes after downstream PR.

Conflicts:

drivers/net/ethernet/sfc/tc.c
  fa165e194997 ("sfc: don't unregister flow_indr if it was never registered")
  3bf969e88ada ("sfc: add MAE table machinery for conntrack table")
https://lore.kernel.org/all/20230818112159.7430e9b4@canb.auug.org.au/

No adjacent changes.

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

19 files changed, 113 insertions, 67 deletions

diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index b3662119ddbc..e40aa3e3641c 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -384,7 +384,8 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
 			dev->name);
 		vlan_vid_add(dev, htons(ETH_P_8021Q), 0);
 	}
-	if (event == NETDEV_DOWN)
+	if (event == NETDEV_DOWN &&
+	    (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER))
 		vlan_vid_del(dev, htons(ETH_P_8021Q), 0);
 
 	vlan_info = rtnl_dereference(dev->vlan_info);
diff --git a/net/core/sock.c b/net/core/sock.c
index 22d94394335f..a0722954e4a8 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3160,7 +3160,7 @@ void __sk_mem_reduce_allocated(struct sock *sk, int amount)
 	if (mem_cgroup_sockets_enabled && sk->sk_memcg)
 		mem_cgroup_uncharge_skmem(sk->sk_memcg, amount);
 
-	if (sk_under_memory_pressure(sk) &&
+	if (sk_under_global_memory_pressure(sk) &&
 	    (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)))
 		sk_leave_memory_pressure(sk);
 }
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 53bfd8af6920..d1e7d0ceb7ed 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -287,12 +287,12 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
-		xfrm_decode_session(skb, &fl, AF_INET);
 		memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+		xfrm_decode_session(skb, &fl, AF_INET);
 		break;
 	case htons(ETH_P_IPV6):
-		xfrm_decode_session(skb, &fl, AF_INET6);
 		memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+		xfrm_decode_session(skb, &fl, AF_INET6);
 		break;
 	default:
 		goto tx_err;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 74c70fc1003c..984ab4a0421e 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -618,7 +618,9 @@ out_reset_timer:
 	    tcp_stream_is_thin(tp) &&
 	    icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) {
 		icsk->icsk_backoff = 0;
-		icsk->icsk_rto = min(__tcp_set_rto(tp), TCP_RTO_MAX);
+		icsk->icsk_rto = clamp(__tcp_set_rto(tp),
+				       tcp_rto_min(sk),
+				       TCP_RTO_MAX);
 	} else if (sk->sk_state != TCP_SYN_SENT ||
 		   icsk->icsk_backoff >
 		   READ_ONCE(net->ipv4.sysctl_tcp_syn_linear_timeouts)) {
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index 658bfed1df8b..08d4b7132d4c 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -152,7 +152,7 @@ config INET6_TUNNEL
 	default n
 
 config IPV6_VTI
-tristate "Virtual (secure) IPv6: tunneling"
+	tristate "Virtual (secure) IPv6: tunneling"
 	select IPV6_TUNNEL
 	select NET_IP_TUNNEL
 	select XFRM
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 10b222865d46..73c85d4e0e9c 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -568,12 +568,12 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 		    vti6_addr_conflict(t, ipv6_hdr(skb)))
 			goto tx_err;
 
-		xfrm_decode_session(skb, &fl, AF_INET6);
 		memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+		xfrm_decode_session(skb, &fl, AF_INET6);
 		break;
 	case htons(ETH_P_IP):
-		xfrm_decode_session(skb, &fl, AF_INET);
 		memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+		xfrm_decode_session(skb, &fl, AF_INET);
 		break;
 	default:
 		goto tx_err;
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 542439b6a59c..d68d01804dc7 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -1847,9 +1847,9 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms
 	if (ext_hdrs[SADB_X_EXT_FILTER - 1]) {
 		struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1];
 
-		if ((xfilter->sadb_x_filter_splen >=
+		if ((xfilter->sadb_x_filter_splen >
 			(sizeof(xfrm_address_t) << 3)) ||
-		    (xfilter->sadb_x_filter_dplen >=
+		    (xfilter->sadb_x_filter_dplen >
 			(sizeof(xfrm_address_t) << 3))) {
 			mutex_unlock(&pfk->dump_lock);
 			return -EINVAL;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 62606fb44d02..4bb0d90eca1c 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1876,6 +1876,7 @@ static int
 proc_do_sync_threshold(struct ctl_table *table, int write,
 		       void *buffer, size_t *lenp, loff_t *ppos)
 {
+	struct netns_ipvs *ipvs = table->extra2;
 	int *valp = table->data;
 	int val[2];
 	int rc;
@@ -1885,6 +1886,7 @@ proc_do_sync_threshold(struct ctl_table *table, int write,
 		.mode = table->mode,
 	};
 
+	mutex_lock(&ipvs->sync_mutex);
 	memcpy(val, valp, sizeof(val));
 	rc = proc_dointvec(&tmp, write, buffer, lenp, ppos);
 	if (write) {
@@ -1894,6 +1896,7 @@ proc_do_sync_threshold(struct ctl_table *table, int write,
 		else
 			memcpy(valp, val, sizeof(val));
 	}
+	mutex_unlock(&ipvs->sync_mutex);
 	return rc;
 }
 
@@ -4321,6 +4324,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs)
 	ipvs->sysctl_sync_threshold[0] = DEFAULT_SYNC_THRESHOLD;
 	ipvs->sysctl_sync_threshold[1] = DEFAULT_SYNC_PERIOD;
 	tbl[idx].data = &ipvs->sysctl_sync_threshold;
+	tbl[idx].extra2 = ipvs;
 	tbl[idx++].maxlen = sizeof(ipvs->sysctl_sync_threshold);
 	ipvs->sysctl_sync_refresh_period = DEFAULT_SYNC_REFRESH_PERIOD;
 	tbl[idx++].data = &ipvs->sysctl_sync_refresh_period;
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 91eacc9b0b98..b6bcc8f2f46b 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -49,8 +49,8 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = {
 	[SCTP_CONNTRACK_COOKIE_WAIT]		= 3 SECS,
 	[SCTP_CONNTRACK_COOKIE_ECHOED]		= 3 SECS,
 	[SCTP_CONNTRACK_ESTABLISHED]		= 210 SECS,
-	[SCTP_CONNTRACK_SHUTDOWN_SENT]		= 300 SECS / 1000,
-	[SCTP_CONNTRACK_SHUTDOWN_RECD]		= 300 SECS / 1000,
+	[SCTP_CONNTRACK_SHUTDOWN_SENT]		= 3 SECS,
+	[SCTP_CONNTRACK_SHUTDOWN_RECD]		= 3 SECS,
 	[SCTP_CONNTRACK_SHUTDOWN_ACK_SENT]	= 3 SECS,
 	[SCTP_CONNTRACK_HEARTBEAT_SENT]		= 30 SECS,
 };
@@ -105,7 +105,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = {
 	{
 /*	ORIGINAL	*/
 /*                  sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS */
-/* init         */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW},
+/* init         */ {sCL, sCL, sCW, sCE, sES, sCL, sCL, sSA, sCW},
 /* init_ack     */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},
 /* abort        */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL},
 /* shutdown     */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL},
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index c62227ae7746..3e841e45f2c0 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -7091,6 +7091,7 @@ static int nft_set_catchall_flush(const struct nft_ctx *ctx,
 		ret = __nft_set_catchall_flush(ctx, set, &elem);
 		if (ret < 0)
 			break;
+		nft_set_elem_change_active(ctx->net, set, ext);
 	}
 
 	return ret;
@@ -9480,9 +9481,14 @@ struct nft_trans_gc *nft_trans_gc_alloc(struct nft_set *set,
 	if (!trans)
 		return NULL;
 
+	trans->net = maybe_get_net(net);
+	if (!trans->net) {
+		kfree(trans);
+		return NULL;
+	}
+
 	refcount_inc(&set->refs);
 	trans->set = set;
-	trans->net = get_net(net);
 	trans->seq = gc_seq;
 
 	return trans;
@@ -9738,6 +9744,22 @@ static void nft_set_commit_update(struct list_head *set_update_list)
 	}
 }
 
+static unsigned int nft_gc_seq_begin(struct nftables_pernet *nft_net)
+{
+	unsigned int gc_seq;
+
+	/* Bump gc counter, it becomes odd, this is the busy mark. */
+	gc_seq = READ_ONCE(nft_net->gc_seq);
+	WRITE_ONCE(nft_net->gc_seq, ++gc_seq);
+
+	return gc_seq;
+}
+
+static void nft_gc_seq_end(struct nftables_pernet *nft_net, unsigned int gc_seq)
+{
+	WRITE_ONCE(nft_net->gc_seq, ++gc_seq);
+}
+
 static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 {
 	struct nftables_pernet *nft_net = nft_pernet(net);
@@ -9823,9 +9845,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 
 	WRITE_ONCE(nft_net->base_seq, base_seq);
 
-	/* Bump gc counter, it becomes odd, this is the busy mark. */
-	gc_seq = READ_ONCE(nft_net->gc_seq);
-	WRITE_ONCE(nft_net->gc_seq, ++gc_seq);
+	gc_seq = nft_gc_seq_begin(nft_net);
 
 	/* step 3. Start new generation, rules_gen_X now in use. */
 	net->nft.gencursor = nft_gencursor_next(net);
@@ -10038,7 +10058,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 	nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN);
 	nf_tables_commit_audit_log(&adl, nft_net->base_seq);
 
-	WRITE_ONCE(nft_net->gc_seq, ++gc_seq);
+	nft_gc_seq_end(nft_net, gc_seq);
 	nf_tables_commit_release(net);
 
 	return 0;
@@ -11039,6 +11059,7 @@ static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event,
 	struct net *net = n->net;
 	unsigned int deleted;
 	bool restart = false;
+	unsigned int gc_seq;
 
 	if (event != NETLINK_URELEASE || n->protocol != NETLINK_NETFILTER)
 		return NOTIFY_DONE;
@@ -11046,6 +11067,9 @@ static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event,
 	nft_net = nft_pernet(net);
 	deleted = 0;
 	mutex_lock(&nft_net->commit_mutex);
+
+	gc_seq = nft_gc_seq_begin(nft_net);
+
 	if (!list_empty(&nf_tables_destroy_list))
 		rcu_barrier();
 again:
@@ -11068,6 +11092,8 @@ again:
 		if (restart)
 			goto again;
 	}
+	nft_gc_seq_end(nft_net, gc_seq);
+
 	mutex_unlock(&nft_net->commit_mutex);
 
 	return NOTIFY_DONE;
@@ -11105,12 +11131,20 @@ static void __net_exit nf_tables_pre_exit_net(struct net *net)
 static void __net_exit nf_tables_exit_net(struct net *net)
 {
 	struct nftables_pernet *nft_net = nft_pernet(net);
+	unsigned int gc_seq;
 
 	mutex_lock(&nft_net->commit_mutex);
+
+	gc_seq = nft_gc_seq_begin(nft_net);
+
 	if (!list_empty(&nft_net->commit_list) ||
 	    !list_empty(&nft_net->module_list))
 		__nf_tables_abort(net, NFNL_ABORT_NONE);
+
 	__nft_release_tables(net);
+
+	nft_gc_seq_end(nft_net, gc_seq);
+
 	mutex_unlock(&nft_net->commit_mutex);
 	WARN_ON_ONCE(!list_empty(&nft_net->tables));
 	WARN_ON_ONCE(!list_empty(&nft_net->module_list));
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 4fb34d76dbea..5c5cc01c73c5 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -191,6 +191,9 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 	if (IS_ERR(set))
 		return PTR_ERR(set);
 
+	if (set->flags & NFT_SET_OBJECT)
+		return -EOPNOTSUPP;
+
 	if (set->ops->update == NULL)
 		return -EOPNOTSUPP;
 
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index a5b8301afe4a..3757fcc55723 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -566,6 +566,8 @@ next_match:
 			goto out;
 
 		if (last) {
+			if (nft_set_elem_expired(&f->mt[b].e->ext))
+				goto next_match;
 			if ((genmask &&
 			     !nft_set_elem_active(&f->mt[b].e->ext, genmask)))
 				goto next_match;
@@ -600,17 +602,8 @@ out:
 static void *nft_pipapo_get(const struct net *net, const struct nft_set *set,
 			    const struct nft_set_elem *elem, unsigned int flags)
 {
-	struct nft_pipapo_elem *ret;
-
-	ret = pipapo_get(net, set, (const u8 *)elem->key.val.data,
+	return pipapo_get(net, set, (const u8 *)elem->key.val.data,
 			 nft_genmask_cur(net));
-	if (IS_ERR(ret))
-		return ret;
-
-	if (nft_set_elem_expired(&ret->ext))
-		return ERR_PTR(-ENOENT);
-
-	return ret;
 }
 
 /**
@@ -1549,7 +1542,7 @@ static void nft_pipapo_gc_deactivate(struct net *net, struct nft_set *set,
 
 /**
  * pipapo_gc() - Drop expired entries from set, destroy start and end elements
- * @set:	nftables API set representation
+ * @_set:	nftables API set representation
  * @m:		Matching data
  */
 static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m)
@@ -1697,6 +1690,17 @@ static void nft_pipapo_commit(const struct nft_set *set)
 	priv->clone = new_clone;
 }
 
+static bool nft_pipapo_transaction_mutex_held(const struct nft_set *set)
+{
+#ifdef CONFIG_PROVE_LOCKING
+	const struct net *net = read_pnet(&set->net);
+
+	return lockdep_is_held(&nft_pernet(net)->commit_mutex);
+#else
+	return true;
+#endif
+}
+
 static void nft_pipapo_abort(const struct nft_set *set)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
@@ -1705,7 +1709,7 @@ static void nft_pipapo_abort(const struct nft_set *set)
 	if (!priv->dirty)
 		return;
 
-	m = rcu_dereference(priv->match);
+	m = rcu_dereference_protected(priv->match, nft_pipapo_transaction_mutex_held(set));
 
 	new_clone = pipapo_clone(m);
 	if (IS_ERR(new_clone))
@@ -1732,11 +1736,7 @@ static void nft_pipapo_activate(const struct net *net,
 				const struct nft_set *set,
 				const struct nft_set_elem *elem)
 {
-	struct nft_pipapo_elem *e;
-
-	e = pipapo_get(net, set, (const u8 *)elem->key.val.data, 0);
-	if (IS_ERR(e))
-		return;
+	struct nft_pipapo_elem *e = elem->priv;
 
 	nft_set_elem_change_active(net, set, &e->ext);
 }
@@ -1950,10 +1950,6 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set,
 
 	data = (const u8 *)nft_set_ext_key(&e->ext);
 
-	e = pipapo_get(net, set, data, 0);
-	if (IS_ERR(e))
-		return;
-
 	while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) {
 		union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS];
 		const u8 *match_start, *match_end;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 0a974eeef76e..11c69415c605 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1830,7 +1830,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	parms.port_no = OVSP_LOCAL;
 	parms.upcall_portids = a[OVS_DP_ATTR_UPCALL_PID];
 	parms.desired_ifindex = a[OVS_DP_ATTR_IFINDEX]
-		? nla_get_u32(a[OVS_DP_ATTR_IFINDEX]) : 0;
+		? nla_get_s32(a[OVS_DP_ATTR_IFINDEX]) : 0;
 
 	/* So far only local changes have been made, now need the lock. */
 	ovs_lock();
@@ -2053,7 +2053,7 @@ static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = {
 	[OVS_DP_ATTR_USER_FEATURES] = { .type = NLA_U32 },
 	[OVS_DP_ATTR_MASKS_CACHE_SIZE] =  NLA_POLICY_RANGE(NLA_U32, 0,
 		PCPU_MIN_UNIT_SIZE / sizeof(struct mask_cache_entry)),
-	[OVS_DP_ATTR_IFINDEX] = {.type = NLA_U32 },
+	[OVS_DP_ATTR_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 0),
 };
 
 static const struct genl_small_ops dp_datapath_genl_ops[] = {
@@ -2306,7 +2306,7 @@ restart:
 	parms.port_no = port_no;
 	parms.upcall_portids = a[OVS_VPORT_ATTR_UPCALL_PID];
 	parms.desired_ifindex = a[OVS_VPORT_ATTR_IFINDEX]
-		? nla_get_u32(a[OVS_VPORT_ATTR_IFINDEX]) : 0;
+		? nla_get_s32(a[OVS_VPORT_ATTR_IFINDEX]) : 0;
 
 	vport = new_vport(&parms);
 	err = PTR_ERR(vport);
@@ -2543,7 +2543,7 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = {
 	[OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 },
 	[OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_UNSPEC },
 	[OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED },
-	[OVS_VPORT_ATTR_IFINDEX] = { .type = NLA_U32 },
+	[OVS_VPORT_ATTR_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 0),
 	[OVS_VPORT_ATTR_NETNSID] = { .type = NLA_S32 },
 	[OVS_VPORT_ATTR_UPCALL_STATS] = { .type = NLA_NESTED },
 };
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 2ed29e40c6a9..8c9a8ee76aa0 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1248,6 +1248,9 @@ static int svc_tcp_sendmsg(struct socket *sock, struct xdr_buf *xdr,
 	if (ret != head->iov_len)
 		goto out;
 
+	if (xdr_buf_pagecount(xdr))
+		xdr->bvec[0].bv_offset = offset_in_page(xdr->page_base);
+
 	msg.msg_flags = MSG_SPLICE_PAGES;
 	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, xdr->bvec,
 		      xdr_buf_pagecount(xdr), xdr->page_len);
diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c
index 8cbf45a8bcdc..655fe4ff8621 100644
--- a/net/xfrm/xfrm_compat.c
+++ b/net/xfrm/xfrm_compat.c
@@ -108,7 +108,7 @@ static const struct nla_policy compat_policy[XFRMA_MAX+1] = {
 	[XFRMA_ALG_COMP]	= { .len = sizeof(struct xfrm_algo) },
 	[XFRMA_ENCAP]		= { .len = sizeof(struct xfrm_encap_tmpl) },
 	[XFRMA_TMPL]		= { .len = sizeof(struct xfrm_user_tmpl) },
-	[XFRMA_SEC_CTX]		= { .len = sizeof(struct xfrm_sec_ctx) },
+	[XFRMA_SEC_CTX]		= { .len = sizeof(struct xfrm_user_sec_ctx) },
 	[XFRMA_LTIME_VAL]	= { .len = sizeof(struct xfrm_lifetime_cur) },
 	[XFRMA_REPLAY_VAL]	= { .len = sizeof(struct xfrm_replay_state) },
 	[XFRMA_REPLAY_THRESH]	= { .type = NLA_U32 },
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 815b38080401..d5ee96789d4b 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -180,6 +180,8 @@ static int xfrm4_remove_beet_encap(struct xfrm_state *x, struct sk_buff *skb)
 	int optlen = 0;
 	int err = -EINVAL;
 
+	skb->protocol = htons(ETH_P_IP);
+
 	if (unlikely(XFRM_MODE_SKB_CB(skb)->protocol == IPPROTO_BEETPH)) {
 		struct ip_beet_phdr *ph;
 		int phlen;
@@ -232,6 +234,8 @@ static int xfrm4_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb)
 {
 	int err = -EINVAL;
 
+	skb->protocol = htons(ETH_P_IP);
+
 	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
 		goto out;
 
@@ -267,6 +271,8 @@ static int xfrm6_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb)
 {
 	int err = -EINVAL;
 
+	skb->protocol = htons(ETH_P_IPV6);
+
 	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
 		goto out;
 
@@ -296,6 +302,8 @@ static int xfrm6_remove_beet_encap(struct xfrm_state *x, struct sk_buff *skb)
 	int size = sizeof(struct ipv6hdr);
 	int err;
 
+	skb->protocol = htons(ETH_P_IPV6);
+
 	err = skb_cow_head(skb, size + skb->mac_len);
 	if (err)
 		goto out;
@@ -346,6 +354,7 @@ xfrm_inner_mode_encap_remove(struct xfrm_state *x,
 			return xfrm6_remove_tunnel_encap(x, skb);
 		break;
 		}
+		return -EINVAL;
 	}
 
 	WARN_ON_ONCE(1);
@@ -366,19 +375,6 @@ static int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb)
 		return -EAFNOSUPPORT;
 	}
 
-	switch (XFRM_MODE_SKB_CB(skb)->protocol) {
-	case IPPROTO_IPIP:
-	case IPPROTO_BEETPH:
-		skb->protocol = htons(ETH_P_IP);
-		break;
-	case IPPROTO_IPV6:
-		skb->protocol = htons(ETH_P_IPV6);
-		break;
-	default:
-		WARN_ON_ONCE(1);
-		break;
-	}
-
 	return xfrm_inner_mode_encap_remove(x, skb);
 }
 
diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c
index a3319965470a..b86474084690 100644
--- a/net/xfrm/xfrm_interface_core.c
+++ b/net/xfrm/xfrm_interface_core.c
@@ -537,8 +537,8 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	switch (skb->protocol) {
 	case htons(ETH_P_IPV6):
-		xfrm_decode_session(skb, &fl, AF_INET6);
 		memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+		xfrm_decode_session(skb, &fl, AF_INET6);
 		if (!dst) {
 			fl.u.ip6.flowi6_oif = dev->ifindex;
 			fl.u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC;
@@ -552,8 +552,8 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 		break;
 	case htons(ETH_P_IP):
-		xfrm_decode_session(skb, &fl, AF_INET);
 		memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+		xfrm_decode_session(skb, &fl, AF_INET);
 		if (!dst) {
 			struct rtable *rt;
 
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 49e63eea841d..bda5327bf34d 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1324,12 +1324,8 @@ found:
 			struct xfrm_dev_offload *xso = &x->xso;
 
 			if (xso->type == XFRM_DEV_OFFLOAD_PACKET) {
-				xso->dev->xfrmdev_ops->xdo_dev_state_delete(x);
-				xso->dir = 0;
-				netdev_put(xso->dev, &xso->dev_tracker);
-				xso->dev = NULL;
-				xso->real_dev = NULL;
-				xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED;
+				xfrm_dev_state_delete(x);
+				xfrm_dev_state_free(x);
 			}
 #endif
 			x->km.state = XFRM_STATE_DEAD;
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index c34a2a06ca94..ad01997c3aa9 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -628,7 +628,7 @@ static void xfrm_update_ae_params(struct xfrm_state *x, struct nlattr **attrs,
 	struct nlattr *rt = attrs[XFRMA_REPLAY_THRESH];
 	struct nlattr *mt = attrs[XFRMA_MTIMER_THRESH];
 
-	if (re) {
+	if (re && x->replay_esn && x->preplay_esn) {
 		struct xfrm_replay_state_esn *replay_esn;
 		replay_esn = nla_data(re);
 		memcpy(x->replay_esn, replay_esn,
@@ -1267,6 +1267,15 @@ static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb)
 					 sizeof(*filter), GFP_KERNEL);
 			if (filter == NULL)
 				return -ENOMEM;
+
+			/* see addr_match(), (prefix length >> 5) << 2
+			 * will be used to compare xfrm_address_t
+			 */
+			if (filter->splen > (sizeof(xfrm_address_t) << 3) ||
+			    filter->dplen > (sizeof(xfrm_address_t) << 3)) {
+				kfree(filter);
+				return -EINVAL;
+			}
 		}
 
 		if (attrs[XFRMA_PROTO])
@@ -2336,6 +2345,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
 					    NETLINK_CB(skb).portid);
 		}
 	} else {
+		xfrm_dev_policy_delete(xp);
 		xfrm_audit_policy_delete(xp, err ? 0 : 1, true);
 
 		if (err != 0)
@@ -3015,7 +3025,7 @@ const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
 	[XFRMA_ALG_COMP]	= { .len = sizeof(struct xfrm_algo) },
 	[XFRMA_ENCAP]		= { .len = sizeof(struct xfrm_encap_tmpl) },
 	[XFRMA_TMPL]		= { .len = sizeof(struct xfrm_user_tmpl) },
-	[XFRMA_SEC_CTX]		= { .len = sizeof(struct xfrm_sec_ctx) },
+	[XFRMA_SEC_CTX]		= { .len = sizeof(struct xfrm_user_sec_ctx) },
 	[XFRMA_LTIME_VAL]	= { .len = sizeof(struct xfrm_lifetime_cur) },
 	[XFRMA_REPLAY_VAL]	= { .len = sizeof(struct xfrm_replay_state) },
 	[XFRMA_REPLAY_THRESH]	= { .type = NLA_U32 },
@@ -3035,6 +3045,7 @@ const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
 	[XFRMA_SET_MARK]	= { .type = NLA_U32 },
 	[XFRMA_SET_MARK_MASK]	= { .type = NLA_U32 },
 	[XFRMA_IF_ID]		= { .type = NLA_U32 },
+	[XFRMA_MTIMER_THRESH]   = { .type = NLA_U32 },
 };
 EXPORT_SYMBOL_GPL(xfrma_policy);