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

xdp_umem.c had overlapping changes between the 64-bit math fix
for the calculation of npgs and the removal of the zerocopy
memory type which got rid of the chunk_size_nohdr member.

The mlx5 Kconfig conflict is a case where we just take the
net-next copy of the Kconfig entry dependency as it takes on
the ESWITCH dependency by one level of indirection which is
what the 'net' conflicting change is trying to ensure.

Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 152 insertions, 81 deletions

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index f048d0a188b7..123a6d39438f 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -276,6 +276,7 @@ static struct in_device *inetdev_init(struct net_device *dev)
 	err = devinet_sysctl_register(in_dev);
 	if (err) {
 		in_dev->dead = 1;
+		neigh_parms_release(&arp_tbl, in_dev->arp_parms);
 		in_dev_put(in_dev);
 		in_dev = NULL;
 		goto out;
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 731022cff600..d14133eac476 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -63,10 +63,8 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head,
 		sp->olen++;
 
 		xo = xfrm_offload(skb);
-		if (!xo) {
-			xfrm_state_put(x);
+		if (!xo)
 			goto out_reset;
-		}
 	}
 
 	xo->flags |= XFRM_GRO;
@@ -139,19 +137,27 @@ static struct sk_buff *xfrm4_beet_gso_segment(struct xfrm_state *x,
 	struct xfrm_offload *xo = xfrm_offload(skb);
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	const struct net_offload *ops;
-	int proto = xo->proto;
+	u8 proto = xo->proto;
 
 	skb->transport_header += x->props.header_len;
 
-	if (proto == IPPROTO_BEETPH) {
-		struct ip_beet_phdr *ph = (struct ip_beet_phdr *)skb->data;
+	if (x->sel.family != AF_INET6) {
+		if (proto == IPPROTO_BEETPH) {
+			struct ip_beet_phdr *ph =
+				(struct ip_beet_phdr *)skb->data;
+
+			skb->transport_header += ph->hdrlen * 8;
+			proto = ph->nexthdr;
+		} else {
+			skb->transport_header -= IPV4_BEET_PHMAXLEN;
+		}
+	} else {
+		__be16 frag;
 
-		skb->transport_header += ph->hdrlen * 8;
-		proto = ph->nexthdr;
-	} else if (x->sel.family != AF_INET6) {
-		skb->transport_header -= IPV4_BEET_PHMAXLEN;
-	} else if (proto == IPPROTO_TCP) {
-		skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4;
+		skb->transport_header +=
+			ipv6_skip_exthdr(skb, 0, &proto, &frag);
+		if (proto == IPPROTO_TCP)
+			skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4;
 	}
 
 	__skb_pull(skb, skb_transport_offset(skb));
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 1bf9da3a75f9..41079490a118 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -309,17 +309,18 @@ bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev)
 {
 	bool dev_match = false;
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-	int ret;
+	if (unlikely(fi->nh)) {
+		dev_match = nexthop_uses_dev(fi->nh, dev);
+	} else {
+		int ret;
 
-	for (ret = 0; ret < fib_info_num_path(fi); ret++) {
-		const struct fib_nh_common *nhc = fib_info_nhc(fi, ret);
+		for (ret = 0; ret < fib_info_num_path(fi); ret++) {
+			const struct fib_nh_common *nhc = fib_info_nhc(fi, ret);
 
-		if (nhc->nhc_dev == dev) {
-			dev_match = true;
-			break;
-		} else if (l3mdev_master_ifindex_rcu(nhc->nhc_dev) == dev->ifindex) {
-			dev_match = true;
-			break;
+			if (nhc_l3mdev_matches_dev(nhc, dev)) {
+				dev_match = true;
+				break;
+			}
 		}
 	}
 #else
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 4f334b425538..248f1c1959a6 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1371,6 +1371,26 @@ static inline t_key prefix_mismatch(t_key key, struct key_vector *n)
 	return (key ^ prefix) & (prefix | -prefix);
 }
 
+bool fib_lookup_good_nhc(const struct fib_nh_common *nhc, int fib_flags,
+			 const struct flowi4 *flp)
+{
+	if (nhc->nhc_flags & RTNH_F_DEAD)
+		return false;
+
+	if (ip_ignore_linkdown(nhc->nhc_dev) &&
+	    nhc->nhc_flags & RTNH_F_LINKDOWN &&
+	    !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE))
+		return false;
+
+	if (!(flp->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) {
+		if (flp->flowi4_oif &&
+		    flp->flowi4_oif != nhc->nhc_oif)
+			return false;
+	}
+
+	return true;
+}
+
 /* should be called with rcu_read_lock */
 int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp,
 		     struct fib_result *res, int fib_flags)
@@ -1503,6 +1523,7 @@ found:
 	/* Step 3: Process the leaf, if that fails fall back to backtracing */
 	hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) {
 		struct fib_info *fi = fa->fa_info;
+		struct fib_nh_common *nhc;
 		int nhsel, err;
 
 		if ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen < KEYLENGTH)) {
@@ -1528,26 +1549,25 @@ out_reject:
 		if (fi->fib_flags & RTNH_F_DEAD)
 			continue;
 
-		if (unlikely(fi->nh && nexthop_is_blackhole(fi->nh))) {
-			err = fib_props[RTN_BLACKHOLE].error;
-			goto out_reject;
+		if (unlikely(fi->nh)) {
+			if (nexthop_is_blackhole(fi->nh)) {
+				err = fib_props[RTN_BLACKHOLE].error;
+				goto out_reject;
+			}
+
+			nhc = nexthop_get_nhc_lookup(fi->nh, fib_flags, flp,
+						     &nhsel);
+			if (nhc)
+				goto set_result;
+			goto miss;
 		}
 
 		for (nhsel = 0; nhsel < fib_info_num_path(fi); nhsel++) {
-			struct fib_nh_common *nhc = fib_info_nhc(fi, nhsel);
+			nhc = fib_info_nhc(fi, nhsel);
 
-			if (nhc->nhc_flags & RTNH_F_DEAD)
+			if (!fib_lookup_good_nhc(nhc, fib_flags, flp))
 				continue;
-			if (ip_ignore_linkdown(nhc->nhc_dev) &&
-			    nhc->nhc_flags & RTNH_F_LINKDOWN &&
-			    !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE))
-				continue;
-			if (!(flp->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) {
-				if (flp->flowi4_oif &&
-				    flp->flowi4_oif != nhc->nhc_oif)
-					continue;
-			}
-
+set_result:
 			if (!(fib_flags & FIB_LOOKUP_NOREF))
 				refcount_inc(&fi->fib_clntref);
 
@@ -1568,6 +1588,7 @@ out_reject:
 			return err;
 		}
 	}
+miss:
 #ifdef CONFIG_IP_FIB_TRIE_STATS
 	this_cpu_inc(stats->semantic_match_miss);
 #endif
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index c8974360a99f..1d9c8cff5ac3 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -93,7 +93,28 @@ static int vti_rcv_proto(struct sk_buff *skb)
 
 static int vti_rcv_tunnel(struct sk_buff *skb)
 {
-	return vti_rcv(skb, ip_hdr(skb)->saddr, true);
+	struct ip_tunnel_net *itn = net_generic(dev_net(skb->dev), vti_net_id);
+	const struct iphdr *iph = ip_hdr(skb);
+	struct ip_tunnel *tunnel;
+
+	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+				  iph->saddr, iph->daddr, 0);
+	if (tunnel) {
+		struct tnl_ptk_info tpi = {
+			.proto = htons(ETH_P_IP),
+		};
+
+		if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+			goto drop;
+		if (iptunnel_pull_header(skb, 0, tpi.proto, false))
+			goto drop;
+		return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, false);
+	}
+
+	return -EINVAL;
+drop:
+	kfree_skb(skb);
+	return 0;
 }
 
 static int vti_rcv_cb(struct sk_buff *skb, int err)
diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c
index 3c25a467b3ef..7afde8828b4c 100644
--- a/net/ipv4/netfilter/nf_nat_pptp.c
+++ b/net/ipv4/netfilter/nf_nat_pptp.c
@@ -166,8 +166,7 @@ pptp_outbound_pkt(struct sk_buff *skb,
 		break;
 	default:
 		pr_debug("unknown outbound packet 0x%04x:%s\n", msg,
-			 msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] :
-					       pptp_msg_name[0]);
+			 pptp_msg_name(msg));
 		fallthrough;
 	case PPTP_SET_LINK_INFO:
 		/* only need to NAT in case PAC is behind NAT box */
@@ -268,9 +267,7 @@ pptp_inbound_pkt(struct sk_buff *skb,
 		pcid_off = offsetof(union pptp_ctrl_union, setlink.peersCallID);
 		break;
 	default:
-		pr_debug("unknown inbound packet %s\n",
-			 msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] :
-					       pptp_msg_name[0]);
+		pr_debug("unknown inbound packet %s\n", pptp_msg_name(msg));
 		fallthrough;
 	case PPTP_START_SESSION_REQUEST:
 	case PPTP_START_SESSION_REPLY:
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index ec1282858cb7..ebafa5ed91ac 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -75,9 +75,16 @@ static void nexthop_free_mpath(struct nexthop *nh)
 	int i;
 
 	nhg = rcu_dereference_raw(nh->nh_grp);
-	for (i = 0; i < nhg->num_nh; ++i)
-		WARN_ON(nhg->nh_entries[i].nh);
+	for (i = 0; i < nhg->num_nh; ++i) {
+		struct nh_grp_entry *nhge = &nhg->nh_entries[i];
+
+		WARN_ON(!list_empty(&nhge->nh_list));
+		nexthop_put(nhge->nh);
+	}
+
+	WARN_ON(nhg->spare == nhg);
 
+	kfree(nhg->spare);
 	kfree(nhg);
 }
 
@@ -758,41 +765,56 @@ static void nh_group_rebalance(struct nh_group *nhg)
 	}
 }
 
-static void remove_nh_grp_entry(struct nh_grp_entry *nhge,
-				struct nh_group *nhg,
+static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge,
 				struct nl_info *nlinfo)
 {
+	struct nh_grp_entry *nhges, *new_nhges;
+	struct nexthop *nhp = nhge->nh_parent;
 	struct nexthop *nh = nhge->nh;
-	struct nh_grp_entry *nhges;
-	bool found = false;
-	int i;
+	struct nh_group *nhg, *newg;
+	int i, j;
 
 	WARN_ON(!nh);
 
-	nhges = nhg->nh_entries;
-	for (i = 0; i < nhg->num_nh; ++i) {
-		if (found) {
-			nhges[i-1].nh = nhges[i].nh;
-			nhges[i-1].weight = nhges[i].weight;
-			list_del(&nhges[i].nh_list);
-			list_add(&nhges[i-1].nh_list, &nhges[i-1].nh->grp_list);
-		} else if (nhg->nh_entries[i].nh == nh) {
-			found = true;
-		}
-	}
+	nhg = rtnl_dereference(nhp->nh_grp);
+	newg = nhg->spare;
 
-	if (WARN_ON(!found))
+	/* last entry, keep it visible and remove the parent */
+	if (nhg->num_nh == 1) {
+		remove_nexthop(net, nhp, nlinfo);
 		return;
+	}
+
+	newg->has_v4 = nhg->has_v4;
+	newg->mpath = nhg->mpath;
+	newg->num_nh = nhg->num_nh;
 
-	nhg->num_nh--;
-	nhg->nh_entries[nhg->num_nh].nh = NULL;
+	/* copy old entries to new except the one getting removed */
+	nhges = nhg->nh_entries;
+	new_nhges = newg->nh_entries;
+	for (i = 0, j = 0; i < nhg->num_nh; ++i) {
+		/* current nexthop getting removed */
+		if (nhg->nh_entries[i].nh == nh) {
+			newg->num_nh--;
+			continue;
+		}
 
-	nh_group_rebalance(nhg);
+		list_del(&nhges[i].nh_list);
+		new_nhges[j].nh_parent = nhges[i].nh_parent;
+		new_nhges[j].nh = nhges[i].nh;
+		new_nhges[j].weight = nhges[i].weight;
+		list_add(&new_nhges[j].nh_list, &new_nhges[j].nh->grp_list);
+		j++;
+	}
 
-	nexthop_put(nh);
+	nh_group_rebalance(newg);
+	rcu_assign_pointer(nhp->nh_grp, newg);
+
+	list_del(&nhge->nh_list);
+	nexthop_put(nhge->nh);
 
 	if (nlinfo)
-		nexthop_notify(RTM_NEWNEXTHOP, nhge->nh_parent, nlinfo);
+		nexthop_notify(RTM_NEWNEXTHOP, nhp, nlinfo);
 }
 
 static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh,
@@ -800,17 +822,11 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh,
 {
 	struct nh_grp_entry *nhge, *tmp;
 
-	list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list) {
-		struct nh_group *nhg;
-
-		list_del(&nhge->nh_list);
-		nhg = rtnl_dereference(nhge->nh_parent->nh_grp);
-		remove_nh_grp_entry(nhge, nhg, nlinfo);
+	list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list)
+		remove_nh_grp_entry(net, nhge, nlinfo);
 
-		/* if this group has no more entries then remove it */
-		if (!nhg->num_nh)
-			remove_nexthop(net, nhge->nh_parent, nlinfo);
-	}
+	/* make sure all see the newly published array before releasing rtnl */
+	synchronize_rcu();
 }
 
 static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo)
@@ -824,10 +840,7 @@ static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo)
 		if (WARN_ON(!nhge->nh))
 			continue;
 
-		list_del(&nhge->nh_list);
-		nexthop_put(nhge->nh);
-		nhge->nh = NULL;
-		nhg->num_nh--;
+		list_del_init(&nhge->nh_list);
 	}
 }
 
@@ -1153,6 +1166,7 @@ static struct nexthop *nexthop_create_group(struct net *net,
 {
 	struct nlattr *grps_attr = cfg->nh_grp;
 	struct nexthop_grp *entry = nla_data(grps_attr);
+	u16 num_nh = nla_len(grps_attr) / sizeof(*entry);
 	struct nh_group *nhg;
 	struct nexthop *nh;
 	int i;
@@ -1163,12 +1177,21 @@ static struct nexthop *nexthop_create_group(struct net *net,
 
 	nh->is_group = 1;
 
-	nhg = nexthop_grp_alloc(nla_len(grps_attr) / sizeof(*entry));
+	nhg = nexthop_grp_alloc(num_nh);
 	if (!nhg) {
 		kfree(nh);
 		return ERR_PTR(-ENOMEM);
 	}
 
+	/* spare group used for removals */
+	nhg->spare = nexthop_grp_alloc(num_nh);
+	if (!nhg) {
+		kfree(nhg);
+		kfree(nh);
+		return NULL;
+	}
+	nhg->spare->spare = nhg;
+
 	for (i = 0; i < nhg->num_nh; ++i) {
 		struct nexthop *nhe;
 		struct nh_info *nhi;
@@ -1203,6 +1226,7 @@ out_no_nh:
 	for (; i >= 0; --i)
 		nexthop_put(nhg->nh_entries[i].nh);
 
+	kfree(nhg->spare);
 	kfree(nhg);
 	kfree(nh);