Merge 2b414a95b8 ("Merge tag 's390-7.1-5' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux") into android-mainline

Steps on the way to v7.1-rc8

Change-Id: Ie5d3d5bb80cf42a89f8b40b7a22af4db31cf8255
Signed-off-by: Carlos Llamas <cmllamas@google.com>

net/bridge/netfilter/ebt_dnat.c

@@ -39,7 +39,9 @@ ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par)
 			dev = xt_in(par);
 			break;
 		case NF_BR_PRE_ROUTING:
-			dev = br_port_get_rcu(xt_in(par))->br->dev;
+			dev = netdev_master_upper_dev_get_rcu(xt_in(par));
+			if (!dev) /* bridge port removed? */
+				return EBT_DROP;
 			break;
 		default:
 			dev = NULL;

net/bridge/netfilter/ebt_redirect.c

@@ -24,12 +24,18 @@ ebt_redirect_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	if (skb_ensure_writable(skb, 0))
 		return EBT_DROP;
 
-	if (xt_hooknum(par) != NF_BR_BROUTING)
-		/* rcu_read_lock()ed by nf_hook_thresh */
-		ether_addr_copy(eth_hdr(skb)->h_dest,
-				br_port_get_rcu(xt_in(par))->br->dev->dev_addr);
-	else
+	if (xt_hooknum(par) != NF_BR_BROUTING) {
+		const struct net_device *dev;
+
+		dev = netdev_master_upper_dev_get_rcu(xt_in(par));
+		if (!dev)
+			return EBT_DROP;
+
+		ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr);
+	} else {
 		ether_addr_copy(eth_hdr(skb)->h_dest, xt_in(par)->dev_addr);
+	}
+
 	skb->pkt_type = PACKET_HOST;
 	return info->target;
 }

net/bridge/netfilter/nft_meta_bridge.c

@@ -64,6 +64,8 @@ static void nft_meta_bridge_get_eval(const struct nft_expr *expr,
 		if (!br_dev)
 			goto err;
 
+		/* ETH_ALEN (6) is shorter than the destination register span (8) */
+		dest[1] = 0;
 		memcpy(dest, br_dev->dev_addr, ETH_ALEN);
 		return;
 	default:

net/core/gro.c

@@ -232,6 +232,11 @@ int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb)
 	if (unlikely(p->len + skb->len >= 65536))
 		return -E2BIG;
 
+	if (!pskb_may_pull(skb, skb_gro_offset(skb))) {
+		NAPI_GRO_CB(skb)->flush = 1;
+		return -ENOMEM;
+	}
+
 	if (NAPI_GRO_CB(p)->last == p)
 		skb_shinfo(p)->frag_list = skb;
 	else

net/core/netdev-genl.c

@@ -1095,8 +1095,6 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 	genlmsg_end(rsp, hdr);
 
 	err = genlmsg_reply(rsp, info);
-	if (err)
-		goto err_unbind;
 
 	bitmap_free(rxq_bitmap);
 
@@ -1104,7 +1102,7 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 
 	mutex_unlock(&priv->lock);
 
-	return 0;
+	return err < 0 ? err : 0;
 
 err_unbind:
 	net_devmem_unbind_dmabuf(binding);

net/core/skbuff.c

@@ -5450,7 +5450,7 @@ int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer)
 }
 EXPORT_SYMBOL_GPL(skb_cow_data);
 
-static void sock_rmem_free(struct sk_buff *skb)
+void sock_rmem_free(struct sk_buff *skb)
 {
 	struct sock *sk = skb->sk;
 
@@ -5459,8 +5459,8 @@ static void sock_rmem_free(struct sk_buff *skb)
 
 static void skb_set_err_queue(struct sk_buff *skb)
 {
-	/* pkt_type of skbs received on local sockets is never PACKET_OUTGOING.
-	 * So, it is safe to (mis)use it to mark skbs on the error queue.
+	/* The error-queue test in skb_is_err_queue() matches this marker
+	 * with the sock_rmem_free destructor installed by sock_queue_err_skb().
 	 */
 	skb->pkt_type = PACKET_OUTGOING;
 	BUILD_BUG_ON(PACKET_OUTGOING == 0);

net/core/sock.c

@@ -1466,6 +1466,11 @@ set_sndbuf:
 	case SO_ATTACH_FILTER: {
 		struct sock_fprog fprog;
 
+		if (sk_is_tcp(sk) &&
+		    !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+			ret = -EPERM;
+			break;
+		}
 		ret = copy_bpf_fprog_from_user(&fprog, optval, optlen);
 		if (!ret)
 			ret = sk_attach_filter(&fprog, sk);

net/ipv4/esp4.c

@@ -96,7 +96,7 @@ 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, struct sk_buff *skb)
+static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb, bool already_unref)
 {
 	struct crypto_aead *aead = x->data;
 	int extralen = 0;
@@ -113,10 +113,13 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb)
 	/* Unref skb_frag_pages in the src scatterlist if necessary.
 	 * Skip the first sg which comes from skb->data.
 	 */
-	if (req->src != req->dst)
-		for (sg = sg_next(req->src); sg; sg = sg_next(sg))
+	if (already_unref || req->src != req->dst) {
+		struct scatterlist *src = already_unref ? esp_req_sg(aead, req) : req->src;
+
+		for (sg = sg_next(src); sg; sg = sg_next(sg))
 			skb_page_unref(page_to_netmem(sg_page(sg)),
 				       skb->pp_recycle);
+	}
 }
 
 #ifdef CONFIG_INET_ESPINTCP
@@ -220,7 +223,7 @@ static void esp_output_done(void *data, int err)
 	}
 
 	tmp = ESP_SKB_CB(skb)->tmp;
-	esp_ssg_unref(x, tmp, skb);
+	esp_ssg_unref(x, tmp, skb, false);
 	kfree(tmp);
 
 	if (xo && (xo->flags & XFRM_DEV_RESUME)) {
@@ -569,8 +572,10 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 		err = skb_to_sgvec(skb, dsg,
 			           (unsigned char *)esph - skb->data,
 			           assoclen + ivlen + esp->clen + alen);
-		if (unlikely(err < 0))
+		if (unlikely(err < 0)) {
+			esp_ssg_unref(x, tmp, skb, true);
 			goto error_free;
+		}
 	}
 
 	if ((x->props.flags & XFRM_STATE_ESN))
@@ -602,7 +607,7 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 	}
 
 	if (sg != dsg)
-		esp_ssg_unref(x, tmp, skb);
+		esp_ssg_unref(x, tmp, skb, false);
 
 	if (!err && x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP)
 		err = esp_output_tail_tcp(x, skb);

net/ipv4/inet_fragment.c

@@ -328,6 +328,9 @@ void inet_frag_queue_flush(struct inet_frag_queue *q,
 	reason = reason ?: SKB_DROP_REASON_FRAG_REASM_TIMEOUT;
 	sum = inet_frag_rbtree_purge(&q->rb_fragments, reason);
 	sub_frag_mem_limit(q->fqdir, sum);
+	q->rb_fragments = RB_ROOT;
+	q->fragments_tail = NULL;
+	q->last_run_head = NULL;
 }
 EXPORT_SYMBOL(inet_frag_queue_flush);
 

net/ipv4/ip_fragment.c

@@ -250,9 +250,6 @@ static int ip_frag_reinit(struct ipq *qp)
 	qp->q.flags = 0;
 	qp->q.len = 0;
 	qp->q.meat = 0;
-	qp->q.rb_fragments = RB_ROOT;
-	qp->q.fragments_tail = NULL;
-	qp->q.last_run_head = NULL;
 	qp->iif = 0;
 	qp->ecn = 0;
 

net/ipv4/netfilter/arp_tables.c

@@ -702,14 +702,12 @@ static int copy_entries_to_user(unsigned int total_size,
 		const struct xt_entry_target *t;
 
 		e = loc_cpu_entry + off;
-		if (copy_to_user(userptr + off, e, sizeof(*e))) {
-			ret = -EFAULT;
-			goto free_counters;
-		}
-		if (copy_to_user(userptr + off
+		if (copy_to_user(userptr + off, e,
+				 offsetof(struct arpt_entry, counters)) ||
+		    copy_to_user(userptr + off
 				 + offsetof(struct arpt_entry, counters),
 				 &counters[num],
-				 sizeof(counters[num])) != 0) {
+				 sizeof(counters[num]))) {
 			ret = -EFAULT;
 			goto free_counters;
 		}
@@ -1327,9 +1325,8 @@ static int compat_copy_entry_to_user(struct arpt_entry *e, void __user **dstptr,
 
 	origsize = *size;
 	ce = *dstptr;
-	if (copy_to_user(ce, e, sizeof(struct arpt_entry)) != 0 ||
-	    copy_to_user(&ce->counters, &counters[i],
-	    sizeof(counters[i])) != 0)
+	if (copy_to_user(ce, e, offsetof(struct compat_arpt_entry, counters)) ||
+	    copy_to_user(&ce->counters, &counters[i], sizeof(counters[i])))
 		return -EFAULT;
 
 	*dstptr += sizeof(struct compat_arpt_entry);

net/ipv4/netfilter/ip_tables.c

@@ -832,14 +832,12 @@ copy_entries_to_user(unsigned int total_size,
 		const struct xt_entry_target *t;
 
 		e = loc_cpu_entry + off;
-		if (copy_to_user(userptr + off, e, sizeof(*e))) {
-			ret = -EFAULT;
-			goto free_counters;
-		}
-		if (copy_to_user(userptr + off
+		if (copy_to_user(userptr + off, e,
+				 offsetof(struct ipt_entry, counters)) ||
+		    copy_to_user(userptr + off
 				 + offsetof(struct ipt_entry, counters),
 				 &counters[num],
-				 sizeof(counters[num])) != 0) {
+				 sizeof(counters[num]))) {
 			ret = -EFAULT;
 			goto free_counters;
 		}
@@ -1228,9 +1226,8 @@ compat_copy_entry_to_user(struct ipt_entry *e, void __user **dstptr,
 
 	origsize = *size;
 	ce = *dstptr;
-	if (copy_to_user(ce, e, sizeof(struct ipt_entry)) != 0 ||
-	    copy_to_user(&ce->counters, &counters[i],
-	    sizeof(counters[i])) != 0)
+	if (copy_to_user(ce, e, offsetof(struct compat_ipt_entry, counters)) ||
+	    copy_to_user(&ce->counters, &counters[i], sizeof(counters[i])))
 		return -EFAULT;
 
 	*dstptr += sizeof(struct compat_ipt_entry);

net/ipv4/netfilter/nf_nat_h323.c

@@ -555,6 +555,8 @@ static void __exit nf_nat_h323_fini(void)
 	nf_ct_helper_expectfn_unregister(&q931_nat);
 	nf_ct_helper_expectfn_unregister(&callforwarding_nat);
 	synchronize_rcu();
+	nf_ct_helper_expectfn_destroy(&q931_nat);
+	nf_ct_helper_expectfn_destroy(&callforwarding_nat);
 }
 
 /****************************************************************************/

net/ipv4/netfilter/nft_fib_ipv4.c

@@ -128,7 +128,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
 		fl4.saddr = get_saddr(iph->daddr);
 	}
 
-	*dest = 0;
+	nft_fib_store_result(dest, priv, NULL);
 
 	if (fib_lookup(nft_net(pkt), &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE))
 		return;

net/ipv6/addrconf.c

@@ -1267,6 +1267,7 @@ static void
 cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires,
 		     bool del_rt, bool del_peer)
 {
+	struct net *net = dev_net(ifp->idev->dev);
 	struct fib6_table *table;
 	struct fib6_info *f6i;
 
@@ -1275,9 +1276,10 @@ cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires,
 					ifp->idev->dev, 0, RTF_DEFAULT, true);
 	if (f6i) {
 		if (del_rt)
-			ip6_del_rt(dev_net(ifp->idev->dev), f6i, false);
+			ip6_del_rt(net, f6i, false);
 		else {
-			if (!(f6i->fib6_flags & RTF_EXPIRES)) {
+			if (f6i != net->ipv6.fib6_null_entry &&
+			    !(f6i->fib6_flags & RTF_EXPIRES)) {
 				table = f6i->fib6_table;
 				spin_lock_bh(&table->tb6_lock);
 

net/ipv6/esp6.c

@@ -113,7 +113,7 @@ 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, struct sk_buff *skb)
+static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb, bool already_unref)
 {
 	struct crypto_aead *aead = x->data;
 	int extralen = 0;
@@ -130,10 +130,13 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb)
 	/* Unref skb_frag_pages in the src scatterlist if necessary.
 	 * Skip the first sg which comes from skb->data.
 	 */
-	if (req->src != req->dst)
-		for (sg = sg_next(req->src); sg; sg = sg_next(sg))
+	if (already_unref || req->src != req->dst) {
+		struct scatterlist *src = already_unref ? esp_req_sg(aead, req) : req->src;
+
+		for (sg = sg_next(src); sg; sg = sg_next(sg))
 			skb_page_unref(page_to_netmem(sg_page(sg)),
 				       skb->pp_recycle);
+	}
 }
 
 #ifdef CONFIG_INET6_ESPINTCP
@@ -254,7 +257,7 @@ static void esp_output_done(void *data, int err)
 	}
 
 	tmp = ESP_SKB_CB(skb)->tmp;
-	esp_ssg_unref(x, tmp, skb);
+	esp_ssg_unref(x, tmp, skb, false);
 	kfree(tmp);
 
 	esp_output_encap_csum(skb);
@@ -600,8 +603,10 @@ int esp6_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info
 		err = skb_to_sgvec(skb, dsg,
 			           (unsigned char *)esph - skb->data,
 			           assoclen + ivlen + esp->clen + alen);
-		if (unlikely(err < 0))
+		if (unlikely(err < 0)) {
+			esp_ssg_unref(x, tmp, skb, true);
 			goto error_free;
+		}
 	}
 
 	if ((x->props.flags & XFRM_STATE_ESN))
@@ -634,7 +639,7 @@ int esp6_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info
 	}
 
 	if (sg != dsg)
-		esp_ssg_unref(x, tmp, skb);
+		esp_ssg_unref(x, tmp, skb, false);
 
 	if (!err && x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP)
 		err = esp_output_tail_tcp(x, skb);

net/ipv6/ip6_vti.c

@@ -106,6 +106,7 @@ vti6_tnl_lookup(struct net *net, const struct in6_addr *remote,
 	hash = HASH(&any, local);
 	for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
 		if (ipv6_addr_equal(local, &t->parms.laddr) &&
+		    ipv6_addr_any(&t->parms.raddr) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
@@ -113,6 +114,7 @@ vti6_tnl_lookup(struct net *net, const struct in6_addr *remote,
 	hash = HASH(remote, &any);
 	for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
 		if (ipv6_addr_equal(remote, &t->parms.raddr) &&
+		    ipv6_addr_any(&t->parms.laddr) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
@@ -1159,6 +1161,7 @@ static int __net_init vti6_init_net(struct net *net)
 		goto err_alloc_dev;
 	dev_net_set(ip6n->fb_tnl_dev, net);
 	ip6n->fb_tnl_dev->rtnl_link_ops = &vti6_link_ops;
+	ip6n->fb_tnl_dev->netns_immutable = true;
 
 	err = vti6_fb_tnl_dev_init(ip6n->fb_tnl_dev);
 	if (err < 0)

net/ipv6/netfilter/ip6_tables.c

@@ -848,14 +848,12 @@ copy_entries_to_user(unsigned int total_size,
 		const struct xt_entry_target *t;
 
 		e = loc_cpu_entry + off;
-		if (copy_to_user(userptr + off, e, sizeof(*e))) {
-			ret = -EFAULT;
-			goto free_counters;
-		}
-		if (copy_to_user(userptr + off
+		if (copy_to_user(userptr + off, e,
+				 offsetof(struct ip6t_entry, counters)) ||
+		    copy_to_user(userptr + off
 				 + offsetof(struct ip6t_entry, counters),
 				 &counters[num],
-				 sizeof(counters[num])) != 0) {
+				 sizeof(counters[num]))) {
 			ret = -EFAULT;
 			goto free_counters;
 		}
@@ -1244,9 +1242,8 @@ compat_copy_entry_to_user(struct ip6t_entry *e, void __user **dstptr,
 
 	origsize = *size;
 	ce = *dstptr;
-	if (copy_to_user(ce, e, sizeof(struct ip6t_entry)) != 0 ||
-	    copy_to_user(&ce->counters, &counters[i],
-	    sizeof(counters[i])) != 0)
+	if (copy_to_user(ce, e, offsetof(struct compat_ip6t_entry, counters)) ||
+	    copy_to_user(&ce->counters, &counters[i], sizeof(counters[i])))
 		return -EFAULT;
 
 	*dstptr += sizeof(struct compat_ip6t_entry);

net/ipv6/netfilter/nft_fib_ipv6.c

@@ -239,7 +239,7 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
 
 	lookup_flags = nft_fib6_flowi_init(&fl6, priv, pkt, oif, iph);
 
-	*dest = 0;
+	nft_fib_store_result(dest, priv, NULL);
 	ret = nft_fib6_lookup(nft_net(pkt), &fl6, &res, lookup_flags);
 	if (ret || res.fib6_flags & (RTF_REJECT | RTF_ANYCAST | RTF_LOCAL))
 		return;

net/ipv6/sit.c

@@ -961,6 +961,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		ip_rt_put(rt);
 		goto tx_error;
 	}
+	iph6 = ipv6_hdr(skb);
 
 	if (df) {
 		mtu = dst4_mtu(&rt->dst) - t_hlen;

net/netfilter/nf_conntrack_helper.c

@@ -283,6 +283,25 @@ void nf_ct_helper_expectfn_unregister(struct nf_ct_helper_expectfn *n)
 }
 EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_unregister);
 
+static bool expect_iter_expectfn(struct nf_conntrack_expect *exp, void *data)
+{
+	const struct nf_ct_helper_expectfn *n = data;
+
+	/* Relies on registered expectfn descriptors having unique ->expectfn
+	 * pointers, which holds for the in-tree NAT helpers.
+	 */
+	return exp->expectfn == n->expectfn;
+}
+
+/* Destroy expectations still pointing at @n->expectfn; call after the
+ * caller's RCU grace period so none outlives the (often modular) callback.
+ */
+void nf_ct_helper_expectfn_destroy(const struct nf_ct_helper_expectfn *n)
+{
+	nf_ct_expect_iterate_destroy(expect_iter_expectfn, (void *)n);
+}
+EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_destroy);
+
 /* Caller should hold the rcu lock */
 struct nf_ct_helper_expectfn *
 nf_ct_helper_expectfn_find_by_name(const char *name)

net/netfilter/nf_dup_netdev.c

@@ -74,16 +74,18 @@ int nft_fwd_dup_netdev_offload(struct nft_offload_ctx *ctx,
 	struct flow_action_entry *entry;
 	struct net_device *dev;
 
-	/* nft_flow_rule_destroy() releases the reference on this device. */
 	dev = dev_get_by_index(ctx->net, oif);
 	if (!dev)
 		return -EOPNOTSUPP;
 
 	entry = nft_flow_action_entry_next(ctx, flow);
-	if (!entry)
+	if (!entry) {
+		dev_put(dev);
 		return -E2BIG;
+	}
 
 	entry->id = id;
+	/* nft_flow_rule_destroy() releases the reference on this device. */
 	entry->dev = dev;
 
 	return 0;

net/netfilter/nf_log_syslog.c

@@ -815,8 +815,8 @@ static void dump_mac_header(struct nf_log_buf *m,
 
 fallback:
 	nf_log_buf_add(m, "MAC=");
-	if (dev->hard_header_len &&
-	    skb->mac_header != skb->network_header) {
+	if (dev->hard_header_len && skb_mac_header_was_set(skb) &&
+	    skb_mac_header_len(skb) != 0) {
 		const unsigned char *p = skb_mac_header(skb);
 		unsigned int i;
 

net/netfilter/nf_nat_core.c

@@ -1341,6 +1341,7 @@ static int __init nf_nat_init(void)
 		RCU_INIT_POINTER(nf_nat_hook, NULL);
 		nf_ct_helper_expectfn_unregister(&follow_master_nat);
 		synchronize_net();
+		nf_ct_helper_expectfn_destroy(&follow_master_nat);
 		unregister_pernet_subsys(&nat_net_ops);
 		kvfree(nf_nat_bysource);
 	}
@@ -1358,6 +1359,7 @@ static void __exit nf_nat_cleanup(void)
 	RCU_INIT_POINTER(nf_nat_hook, NULL);
 
 	synchronize_net();
+	nf_ct_helper_expectfn_destroy(&follow_master_nat);
 	kvfree(nf_nat_bysource);
 	unregister_pernet_subsys(&nat_net_ops);
 }

net/netfilter/nf_nat_sip.c

@@ -655,6 +655,7 @@ static void __exit nf_nat_sip_fini(void)
 	RCU_INIT_POINTER(nf_nat_sip_hooks, NULL);
 	nf_ct_helper_expectfn_unregister(&sip_nat);
 	synchronize_rcu();
+	nf_ct_helper_expectfn_destroy(&sip_nat);
 }
 
 static const struct nf_nat_sip_hooks sip_hooks = {

net/netfilter/nfnetlink_log.c

@@ -451,6 +451,23 @@ nla_put_failure:
 	return -1;
 }
 
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+static int nflog_put_master_ifindex(struct sk_buff *nlskb, int attr,
+				    const struct net_device *dev)
+{
+	const struct net_device *upper;
+
+	if (dev && !netif_is_bridge_port(dev))
+		return 0;
+
+	upper = netdev_master_upper_dev_get_rcu((struct net_device *)dev);
+	if (upper && nla_put_be32(nlskb, attr, htonl(upper->ifindex)))
+		return -EMSGSIZE;
+
+	return 0;
+}
+#endif
+
 /* This is an inline function, we don't really care about a long
  * list of arguments */
 static inline int
@@ -505,8 +522,7 @@ __build_packet_message(struct nfnl_log_net *log,
 			/* rcu_read_lock()ed by nf_hook_thresh or
 			 * nf_log_packet.
 			 */
-			    nla_put_be32(inst->skb, NFULA_IFINDEX_INDEV,
-					 htonl(br_port_get_rcu(indev)->br->dev->ifindex)))
+			    nflog_put_master_ifindex(inst->skb, NFULA_IFINDEX_INDEV, indev))
 				goto nla_put_failure;
 		} else {
 			int physinif;
@@ -542,8 +558,7 @@ __build_packet_message(struct nfnl_log_net *log,
 			/* rcu_read_lock()ed by nf_hook_thresh or
 			 * nf_log_packet.
 			 */
-			    nla_put_be32(inst->skb, NFULA_IFINDEX_OUTDEV,
-					 htonl(br_port_get_rcu(outdev)->br->dev->ifindex)))
+			    nflog_put_master_ifindex(inst->skb, NFULA_IFINDEX_OUTDEV, outdev))
 				goto nla_put_failure;
 		} else {
 			struct net_device *physoutdev;

net/netfilter/nfnetlink_queue.c

@@ -440,10 +440,47 @@ static bool nf_ct_drop_unconfirmed(const struct nf_queue_entry *entry, bool *is_
 	return false;
 }
 
+static bool nf_bridge_port_valid(const struct net_device *dev)
+{
+	if (!dev)
+		return true;
+
+	return netif_is_bridge_port(dev);
+}
+
+/* queued skbs leave rcu protection.  We bump device refcount so that
+ * the device cannot go away.  However, while packet was out the port
+ * could have been removed from the bridge.
+ *
+ * Ensure in+outdev are still part of a bridge at reinject time.
+ *
+ * The device rx_handler_data could even be pointing at data that is
+ * not a net_bridge_port structure.
+ */
+static bool nf_bridge_ports_valid(const struct nf_queue_entry *entry)
+{
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+	if (!nf_bridge_port_valid(entry->physin) ||
+	    !nf_bridge_port_valid(entry->physout))
+		return false;
+#endif
+	if (entry->state.pf != PF_BRIDGE)
+		return true;
+
+	if (!nf_bridge_port_valid(entry->state.in) ||
+	    !nf_bridge_port_valid(entry->state.out))
+		return false;
+
+	return true;
+}
+
 static void nfqnl_reinject(struct nf_queue_entry *entry, unsigned int verdict)
 {
 	const struct nf_ct_hook *ct_hook;
 
+	if (!nf_bridge_ports_valid(entry))
+		verdict = NF_DROP;
+
 	if (verdict == NF_ACCEPT ||
 	    verdict == NF_REPEAT ||
 	    verdict == NF_STOP) {
@@ -636,6 +673,23 @@ static int nf_queue_checksum_help(struct sk_buff *entskb)
 	return skb_checksum_help(entskb);
 }
 
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+static int nfqnl_put_master_ifindex(struct sk_buff *nlskb, int attr,
+				    const struct net_device *dev)
+{
+	const struct net_device *upper;
+
+	if (dev && !netif_is_bridge_port(dev))
+		return 0;
+
+	upper = netdev_master_upper_dev_get_rcu((struct net_device *)dev);
+	if (upper && nla_put_be32(nlskb, attr, htonl(upper->ifindex)))
+		return -EMSGSIZE;
+
+	return 0;
+}
+#endif
+
 static struct sk_buff *
 nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 			   struct nf_queue_entry *entry,
@@ -771,10 +825,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 			 * netfilter_bridge) */
 			if (nla_put_be32(skb, NFQA_IFINDEX_PHYSINDEV,
 					 htonl(indev->ifindex)) ||
-			/* this is the bridge group "brX" */
-			/* rcu_read_lock()ed by __nf_queue */
-			    nla_put_be32(skb, NFQA_IFINDEX_INDEV,
-					 htonl(br_port_get_rcu(indev)->br->dev->ifindex)))
+			    nfqnl_put_master_ifindex(skb, NFQA_IFINDEX_INDEV, indev))
 				goto nla_put_failure;
 		} else {
 			int physinif;
@@ -805,10 +856,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 			 * netfilter_bridge) */
 			if (nla_put_be32(skb, NFQA_IFINDEX_PHYSOUTDEV,
 					 htonl(outdev->ifindex)) ||
-			/* this is the bridge group "brX" */
-			/* rcu_read_lock()ed by __nf_queue */
-			    nla_put_be32(skb, NFQA_IFINDEX_OUTDEV,
-					 htonl(br_port_get_rcu(outdev)->br->dev->ifindex)))
+			    nfqnl_put_master_ifindex(skb, NFQA_IFINDEX_OUTDEV, outdev))
 				goto nla_put_failure;
 		} else {
 			int physoutif;

net/netfilter/nft_exthdr.c

@@ -532,6 +532,9 @@ static int nft_exthdr_init(const struct nft_ctx *ctx,
 			return err;
 	}
 
+	if ((flags & NFT_EXTHDR_F_PRESENT) && len != 1)
+		return -EINVAL;
+
 	priv->type   = nla_get_u8(tb[NFTA_EXTHDR_TYPE]);
 	priv->offset = offset;
 	priv->len    = len;

net/netfilter/nft_fib.c

@@ -107,6 +107,12 @@ int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		return -EINVAL;
 	}
 
+	if (priv->flags & NFTA_FIB_F_PRESENT) {
+		if (priv->result != NFT_FIB_RESULT_OIF)
+			return -EINVAL;
+		len = sizeof(u8);
+	}
+
 	err = nft_parse_register_store(ctx, tb[NFTA_FIB_DREG], &priv->dreg,
 				       NULL, NFT_DATA_VALUE, len);
 	if (err < 0)

net/netlabel/netlabel_unlabeled.c

@@ -114,14 +114,14 @@ static struct genl_family netlbl_unlabel_gnl_family;
 /* NetLabel Netlink attribute policy */
 static const struct nla_policy netlbl_unlabel_genl_policy[NLBL_UNLABEL_A_MAX + 1] = {
 	[NLBL_UNLABEL_A_ACPTFLG] = { .type = NLA_U8 },
-	[NLBL_UNLABEL_A_IPV6ADDR] = { .type = NLA_BINARY,
-				      .len = sizeof(struct in6_addr) },
-	[NLBL_UNLABEL_A_IPV6MASK] = { .type = NLA_BINARY,
-				      .len = sizeof(struct in6_addr) },
-	[NLBL_UNLABEL_A_IPV4ADDR] = { .type = NLA_BINARY,
-				      .len = sizeof(struct in_addr) },
-	[NLBL_UNLABEL_A_IPV4MASK] = { .type = NLA_BINARY,
-				      .len = sizeof(struct in_addr) },
+	[NLBL_UNLABEL_A_IPV6ADDR] =
+		NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
+	[NLBL_UNLABEL_A_IPV6MASK] =
+		NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
+	[NLBL_UNLABEL_A_IPV4ADDR] =
+		NLA_POLICY_EXACT_LEN(sizeof(struct in_addr)),
+	[NLBL_UNLABEL_A_IPV4MASK] =
+		NLA_POLICY_EXACT_LEN(sizeof(struct in_addr)),
 	[NLBL_UNLABEL_A_IFACE] = { .type = NLA_NUL_STRING,
 				   .len = IFNAMSIZ - 1 },
 	[NLBL_UNLABEL_A_SECCTX] = { .type = NLA_BINARY }
@@ -757,24 +757,14 @@ static int netlbl_unlabel_addrinfo_get(struct genl_info *info,
 				       void **mask,
 				       u32 *len)
 {
-	u32 addr_len;
-
 	if (info->attrs[NLBL_UNLABEL_A_IPV4ADDR] &&
 	    info->attrs[NLBL_UNLABEL_A_IPV4MASK]) {
-		addr_len = nla_len(info->attrs[NLBL_UNLABEL_A_IPV4ADDR]);
-		if (addr_len != sizeof(struct in_addr) &&
-		    addr_len != nla_len(info->attrs[NLBL_UNLABEL_A_IPV4MASK]))
-			return -EINVAL;
-		*len = addr_len;
+		*len = sizeof(struct in_addr);
 		*addr = nla_data(info->attrs[NLBL_UNLABEL_A_IPV4ADDR]);
 		*mask = nla_data(info->attrs[NLBL_UNLABEL_A_IPV4MASK]);
 		return 0;
 	} else if (info->attrs[NLBL_UNLABEL_A_IPV6ADDR]) {
-		addr_len = nla_len(info->attrs[NLBL_UNLABEL_A_IPV6ADDR]);
-		if (addr_len != sizeof(struct in6_addr) &&
-		    addr_len != nla_len(info->attrs[NLBL_UNLABEL_A_IPV6MASK]))
-			return -EINVAL;
-		*len = addr_len;
+		*len = sizeof(struct in6_addr);
 		*addr = nla_data(info->attrs[NLBL_UNLABEL_A_IPV6ADDR]);
 		*mask = nla_data(info->attrs[NLBL_UNLABEL_A_IPV6MASK]);
 		return 0;

net/openvswitch/datapath.c

@@ -1316,6 +1316,7 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
 
 		if (IS_ERR(reply)) {
 			error = PTR_ERR(reply);
+			reply = NULL;
 			goto err_unlock_ovs;
 		}
 	}

net/phonet/pn_dev.c

@@ -108,7 +108,7 @@ static void phonet_device_destroy(struct net_device *dev)
 		for_each_set_bit(addr, pnd->addrs, 64)
 			phonet_address_notify(net, RTM_DELADDR, ifindex, addr);
 
-		kfree(pnd);
+		kfree_rcu(pnd, rcu);
 	}
 }
 

net/qrtr/af_qrtr.c

@@ -707,13 +707,13 @@ static void qrtr_port_remove(struct qrtr_sock *ipc)
 	if (port == QRTR_PORT_CTRL)
 		port = 0;
 
-	__sock_put(&ipc->sk);
-
 	xa_erase(&qrtr_ports, port);
 
 	/* Ensure that if qrtr_port_lookup() did enter the RCU read section we
 	 * wait for it to up increment the refcount */
 	synchronize_rcu();
+
+	__sock_put(&ipc->sk);
 }
 
 /* Assign port number to socket.

net/rds/ib_send.c

@@ -170,6 +170,8 @@ static struct rds_message *rds_ib_send_unmap_op(struct rds_ib_connection *ic,
 		break;
 	case IB_WR_ATOMIC_FETCH_AND_ADD:
 	case IB_WR_ATOMIC_CMP_AND_SWP:
+	case IB_WR_MASKED_ATOMIC_FETCH_AND_ADD:
+	case IB_WR_MASKED_ATOMIC_CMP_AND_SWP:
 		if (send->s_op) {
 			rm = container_of(send->s_op, struct rds_message, atomic);
 			rds_ib_send_unmap_atomic(ic, send->s_op, wc_status);

net/rds/info.c

@@ -235,7 +235,7 @@ call_func:
 
 out:
 	if (pages)
-		unpin_user_pages(pages, nr_pages);
+		unpin_user_pages_dirty_lock(pages, nr_pages, true);
 	kfree(pages);
 
 	return ret;

net/rxrpc/input.c

@@ -963,23 +963,34 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call,
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	struct rxrpc_txqueue *tq = call->tx_queue;
 	unsigned long extracted = ~0UL;
-	unsigned int nr = 0;
+	unsigned int nr = 0, nsack;
 	rxrpc_seq_t seq = call->acks_hard_ack + 1;
 	rxrpc_seq_t lowest_nak = seq + sp->ack.nr_acks;
-	u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket);
+	u8 sack[256] __aligned(sizeof(unsigned long));
+	u8 *acks = sack;
 
 	_enter("%x,%x,%u", tq->qbase, seq, sp->ack.nr_acks);
 
 	while (after(seq, tq->qbase + RXRPC_NR_TXQUEUE - 1))
 		tq = tq->next;
 
+	/* Extract an individual SACK table.  A normal SACK table is up to 255
+	 * bytes with 1 ACK flag per byte, but an extended SACK table can be up
+	 * to 256 bytes with up to 8 ACK/NACK flags per byte.  The ACK flags go
+	 * across all bit 0's then all bit 1's, then all bit 2's, ...
+	 */
+	memset(sack, 0, sizeof(sack));
+	nsack = umin(sp->ack.nr_acks, 256);
+	if (skb_copy_bits(skb,
+			  sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket),
+			  sack, nsack) < 0)
+		return;
+
 	for (unsigned int i = 0; i < sp->ack.nr_acks; i++) {
 		/* Decant ACKs until we hit a txqueue boundary. */
+		if ((i & 255) == 0)
+			acks = sack;
 		shiftr_adv_rotr(acks, extracted);
-		if (i == 256) {
-			acks -= i;
-			i = 0;
-		}
 		seq++;
 		nr++;
 		if ((seq & RXRPC_TXQ_MASK) != 0)
@@ -1117,9 +1128,6 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	    skb_copy_bits(skb, ioffset, &trailer, sizeof(trailer)) < 0)
 		return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack_trailer);
 
-	if (nr_acks > 0)
-		skb_condense(skb);
-
 	call->acks_latest_ts = ktime_get_real();
 	call->acks_hard_ack = hard_ack;
 	call->acks_prev_seq = prev_pkt;

net/sctp/bind_addr.c

@@ -275,6 +275,16 @@ int sctp_raw_to_bind_addrs(struct sctp_bind_addr *bp, __u8 *raw_addr_list,
 		param = (struct sctp_paramhdr *)raw_addr_list;
 		rawaddr = (union sctp_addr_param *)raw_addr_list;
 
+		if (addrs_len < sizeof(*param)) {
+			retval = -EINVAL;
+			goto out_err;
+		}
+		len = ntohs(param->length);
+		if (addrs_len < len) {
+			retval = -EINVAL;
+			goto out_err;
+		}
+
 		af = sctp_get_af_specific(param_type2af(param->type));
 		if (unlikely(!af) ||
 		    !af->from_addr_param(&addr, rawaddr, htons(port), 0)) {
@@ -291,7 +301,6 @@ int sctp_raw_to_bind_addrs(struct sctp_bind_addr *bp, __u8 *raw_addr_list,
 			goto out_err;
 
 next:
-		len = ntohs(param->length);
 		addrs_len -= len;
 		raw_addr_list += len;
 	}

net/sctp/input.c

@@ -1204,6 +1204,14 @@ static struct sctp_association *__sctp_rcv_asconf_lookup(
 	/* Skip over the ADDIP header and find the Address parameter */
 	param = (union sctp_addr_param *)(asconf + 1);
 
+	/* The whole address parameter must lie within the chunk before
+	 * af->from_addr_param() reads the variable-length address; otherwise a
+	 * truncated trailing ASCONF chunk lets it read uninitialized bytes past
+	 * the parameter.
+	 */
+	if (sizeof(*asconf) + ntohs(param->p.length) > ntohs(ch->length))
+		return NULL;
+
 	af = sctp_get_af_specific(param_type2af(param->p.type));
 	if (unlikely(!af))
 		return NULL;

net/sctp/sm_make_chunk.c

@@ -1731,8 +1731,8 @@ struct sctp_association *sctp_unpack_cookie(
 	struct sk_buff *skb = chunk->skb;
 	struct sctp_cookie *bear_cookie;
 	struct sctp_chunkhdr *ch;
+	unsigned int len, chlen;
 	enum sctp_scope scope;
-	unsigned int len;
 	ktime_t kt;
 
 	/* Header size is static data prior to the actual cookie, including
@@ -1761,7 +1761,12 @@ struct sctp_association *sctp_unpack_cookie(
 	bear_cookie = &cookie->c;
 
 	ch = (struct sctp_chunkhdr *)(bear_cookie + 1);
-	if (ntohs(ch->length) > len - fixed_size)
+	chlen = ntohs(ch->length);
+	if (chlen < sizeof(struct sctp_init_chunk))
+		goto malformed;
+	if (chlen > len - fixed_size)
+		goto malformed;
+	if (bear_cookie->raw_addr_list_len > len - fixed_size - chlen)
 		goto malformed;
 
 	/* Verify the cookie's MAC, if cookie authentication is enabled. */

net/sctp/stream.c

@@ -1038,6 +1038,7 @@ struct sctp_chunk *sctp_process_strreset_resp(
 			stsn, rtsn, GFP_ATOMIC);
 	} else if (req->type == SCTP_PARAM_RESET_ADD_OUT_STREAMS) {
 		struct sctp_strreset_addstrm *addstrm;
+		const struct sctp_sched_ops *sched;
 		__u16 number;
 
 		addstrm = (struct sctp_strreset_addstrm *)req;
@@ -1048,7 +1049,10 @@ struct sctp_chunk *sctp_process_strreset_resp(
 			for (i = number; i < stream->outcnt; i++)
 				SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN;
 		} else {
-			sctp_stream_shrink_out(stream, number);
+			sched = sctp_sched_ops_from_stream(stream);
+			sched->unsched_all(stream);
+			sctp_stream_outq_migrate(stream, NULL, number);
+			sched->sched_all(stream);
 			stream->outcnt = number;
 		}
 

net/socket.c

@@ -852,12 +852,13 @@ EXPORT_SYMBOL(kernel_sendmsg);
 
 static bool skb_is_err_queue(const struct sk_buff *skb)
 {
-	/* pkt_type of skbs enqueued on the error queue are set to
-	 * PACKET_OUTGOING in skb_set_err_queue(). This is only safe to do
-	 * in recvmsg, since skbs received on a local socket will never
-	 * have a pkt_type of PACKET_OUTGOING.
+	/* Error-queue skbs are marked as PACKET_OUTGOING in
+	 * skb_set_err_queue() and use the destructor installed by
+	 * sock_queue_err_skb(). PACKET_OUTGOING alone is not unique:
+	 * AF_PACKET outgoing taps use the same pkt_type.
 	 */
-	return skb->pkt_type == PACKET_OUTGOING;
+	return skb->pkt_type == PACKET_OUTGOING &&
+	       skb->destructor == sock_rmem_free;
 }
 
 /* On transmit, software and hardware timestamps are returned independently.

net/xfrm/espintcp.c

@@ -346,6 +346,10 @@ static int espintcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 			err = -ENOBUFS;
 		goto unlock;
 	}
+	if (emsg->len) {
+		err = -ENOBUFS;
+		goto unlock;
+	}
 
 	sk_msg_init(&emsg->skmsg);
 	while (1) {

net/xfrm/xfrm_iptfs.c

@@ -954,6 +954,7 @@ static bool __input_process_payload(struct xfrm_state *x, u32 data,
 	u32 first_iplen, iphlen, iplen, remaining, tail;
 	u32 capturelen;
 	u64 seq;
+	bool first_skb_partial = false;
 
 	xtfs = x->mode_data;
 	net = xs_net(x);
@@ -1161,6 +1162,7 @@ static bool __input_process_payload(struct xfrm_state *x, u32 data,
 
 			spin_unlock(&xtfs->drop_lock);
 
+			first_skb_partial = (first_skb == skb);
 			break;
 		}
 
@@ -1172,7 +1174,7 @@ static bool __input_process_payload(struct xfrm_state *x, u32 data,
 		/* this should not happen from the above code */
 		XFRM_INC_STATS(net, LINUX_MIB_XFRMINIPTFSERROR);
 
-	if (first_skb && first_iplen && !defer && first_skb != xtfs->ra_newskb) {
+	if (first_skb && first_iplen && !defer && !first_skb_partial) {
 		/* first_skb is queued b/c !defer and not partial */
 		if (pskb_trim(first_skb, first_iplen)) {
 			/* error trimming */
@@ -2168,6 +2170,8 @@ static void iptfs_consume_frags(struct sk_buff *to, struct sk_buff *from)
 	memcpy(&toi->frags[toi->nr_frags], fromi->frags,
 	       sizeof(fromi->frags[0]) * fromi->nr_frags);
 	toi->nr_frags += fromi->nr_frags;
+	if (fromi->nr_frags)
+		toi->flags |= fromi->flags & SKBFL_SHARED_FRAG;
 	fromi->nr_frags = 0;
 	from->data_len = 0;
 	from->len = 0;
@@ -2726,8 +2730,9 @@ static void iptfs_destroy_state(struct xfrm_state *x)
 	if (!xtfs)
 		return;
 
-	spin_lock_bh(&xtfs->x->lock);
 	hrtimer_cancel(&xtfs->iptfs_timer);
+
+	spin_lock_bh(&xtfs->x->lock);
 	__skb_queue_head_init(&list);
 	skb_queue_splice_init(&xtfs->queue, &list);
 	spin_unlock_bh(&xtfs->x->lock);
@@ -2735,9 +2740,7 @@ static void iptfs_destroy_state(struct xfrm_state *x)
 	while ((skb = __skb_dequeue(&list)))
 		kfree_skb(skb);
 
-	spin_lock_bh(&xtfs->drop_lock);
 	hrtimer_cancel(&xtfs->drop_timer);
-	spin_unlock_bh(&xtfs->drop_lock);
 
 	if (xtfs->ra_newskb)
 		kfree_skb(xtfs->ra_newskb);

net/xfrm/xfrm_policy.c

@@ -1156,15 +1156,6 @@ static void __xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b, bool
 	}
 }
 
-static void xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b)
-{
-	struct net *net = read_pnet(&b->k.net);
-
-	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
-	__xfrm_policy_inexact_prune_bin(b, false);
-	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
-}
-
 static void __xfrm_policy_inexact_flush(struct net *net)
 {
 	struct xfrm_pol_inexact_bin *bin, *t;
@@ -1707,12 +1698,12 @@ xfrm_policy_bysel_ctx(struct net *net, const struct xfrm_mark *mark, u32 if_id,
 		}
 		ret = pol;
 	}
+	if (bin && delete)
+		__xfrm_policy_inexact_prune_bin(bin, false);
 	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	if (ret && delete)
 		xfrm_policy_kill(ret);
-	if (bin && delete)
-		xfrm_policy_inexact_prune_bin(bin);
 	return ret;
 }
 EXPORT_SYMBOL(xfrm_policy_bysel_ctx);