From 4ffcf5ca81c3b83180473eb0d3c010a1a7c6c4de Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 17 Sep 2024 23:07:46 +0200
Subject: [PATCH 01/16] netfilter: nf_tables: use rcu chain hook list iterator
 from netlink dump path

Lockless iteration over hook list is possible from netlink dump path,
use rcu variant to iterate over the hook list as is done with flowtable
hooks.

Fixes: b9703ed44ffb ("netfilter: nf_tables: support for adding new devices to an existing netdev chain")
Reported-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 042080aeb46c..8f073e6c772a 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1849,7 +1849,7 @@ static int nft_dump_basechain_hook(struct sk_buff *skb, int family,
 		if (!hook_list)
 			hook_list = &basechain->hook_list;
 
-		list_for_each_entry(hook, hook_list, list) {
+		list_for_each_entry_rcu(hook, hook_list, list) {
 			if (!first)
 				first = hook;
 
-- 
2.51.0


From 69e687cea79fc99a17dfb0116c8644b9391b915e Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 18 Sep 2024 14:19:45 +0200
Subject: [PATCH 02/16] netfilter: nf_tables: missing objects with no memcg
 accounting

Several ruleset objects are still not using GFP_KERNEL_ACCOUNT for
memory accounting, update them. This includes:

- catchall elements
- compat match large info area
- log prefix
- meta secctx
- numgen counters
- pipapo set backend datastructure
- tunnel private objects

Fixes: 33758c891479 ("memcg: enable accounting for nft objects")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c  |  2 +-
 net/netfilter/nft_compat.c     |  6 +++---
 net/netfilter/nft_log.c        |  2 +-
 net/netfilter/nft_meta.c       |  2 +-
 net/netfilter/nft_numgen.c     |  2 +-
 net/netfilter/nft_set_pipapo.c | 13 +++++++------
 net/netfilter/nft_tunnel.c     |  5 +++--
 7 files changed, 17 insertions(+), 15 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 8f073e6c772a..a24fe62650a7 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -6684,7 +6684,7 @@ static int nft_setelem_catchall_insert(const struct net *net,
 		}
 	}
 
-	catchall = kmalloc(sizeof(*catchall), GFP_KERNEL);
+	catchall = kmalloc(sizeof(*catchall), GFP_KERNEL_ACCOUNT);
 	if (!catchall)
 		return -ENOMEM;
 
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 52cdfee17f73..7ca4f0d21fe2 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -535,7 +535,7 @@ nft_match_large_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	struct xt_match *m = expr->ops->data;
 	int ret;
 
-	priv->info = kmalloc(XT_ALIGN(m->matchsize), GFP_KERNEL);
+	priv->info = kmalloc(XT_ALIGN(m->matchsize), GFP_KERNEL_ACCOUNT);
 	if (!priv->info)
 		return -ENOMEM;
 
@@ -808,7 +808,7 @@ nft_match_select_ops(const struct nft_ctx *ctx,
 		goto err;
 	}
 
-	ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL);
+	ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL_ACCOUNT);
 	if (!ops) {
 		err = -ENOMEM;
 		goto err;
@@ -898,7 +898,7 @@ nft_target_select_ops(const struct nft_ctx *ctx,
 		goto err;
 	}
 
-	ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL);
+	ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL_ACCOUNT);
 	if (!ops) {
 		err = -ENOMEM;
 		goto err;
diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c
index 5defe6e4fd98..e35588137995 100644
--- a/net/netfilter/nft_log.c
+++ b/net/netfilter/nft_log.c
@@ -163,7 +163,7 @@ static int nft_log_init(const struct nft_ctx *ctx,
 
 	nla = tb[NFTA_LOG_PREFIX];
 	if (nla != NULL) {
-		priv->prefix = kmalloc(nla_len(nla) + 1, GFP_KERNEL);
+		priv->prefix = kmalloc(nla_len(nla) + 1, GFP_KERNEL_ACCOUNT);
 		if (priv->prefix == NULL)
 			return -ENOMEM;
 		nla_strscpy(priv->prefix, nla, nla_len(nla) + 1);
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 8c8eb14d647b..05cd1e6e6a2f 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -952,7 +952,7 @@ static int nft_secmark_obj_init(const struct nft_ctx *ctx,
 	if (tb[NFTA_SECMARK_CTX] == NULL)
 		return -EINVAL;
 
-	priv->ctx = nla_strdup(tb[NFTA_SECMARK_CTX], GFP_KERNEL);
+	priv->ctx = nla_strdup(tb[NFTA_SECMARK_CTX], GFP_KERNEL_ACCOUNT);
 	if (!priv->ctx)
 		return -ENOMEM;
 
diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c
index 7d29db7c2ac0..bd058babfc82 100644
--- a/net/netfilter/nft_numgen.c
+++ b/net/netfilter/nft_numgen.c
@@ -66,7 +66,7 @@ static int nft_ng_inc_init(const struct nft_ctx *ctx,
 	if (priv->offset + priv->modulus - 1 < priv->offset)
 		return -EOVERFLOW;
 
-	priv->counter = kmalloc(sizeof(*priv->counter), GFP_KERNEL);
+	priv->counter = kmalloc(sizeof(*priv->counter), GFP_KERNEL_ACCOUNT);
 	if (!priv->counter)
 		return -ENOMEM;
 
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index eb4c4a4ac7ac..7be342b495f5 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -663,7 +663,7 @@ static int pipapo_realloc_mt(struct nft_pipapo_field *f,
 	    check_add_overflow(rules, extra, &rules_alloc))
 		return -EOVERFLOW;
 
-	new_mt = kvmalloc_array(rules_alloc, sizeof(*new_mt), GFP_KERNEL);
+	new_mt = kvmalloc_array(rules_alloc, sizeof(*new_mt), GFP_KERNEL_ACCOUNT);
 	if (!new_mt)
 		return -ENOMEM;
 
@@ -936,7 +936,7 @@ static void pipapo_lt_bits_adjust(struct nft_pipapo_field *f)
 		return;
 	}
 
-	new_lt = kvzalloc(lt_size + NFT_PIPAPO_ALIGN_HEADROOM, GFP_KERNEL);
+	new_lt = kvzalloc(lt_size + NFT_PIPAPO_ALIGN_HEADROOM, GFP_KERNEL_ACCOUNT);
 	if (!new_lt)
 		return;
 
@@ -1212,7 +1212,7 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone,
 		scratch = kzalloc_node(struct_size(scratch, map,
 						   bsize_max * 2) +
 				       NFT_PIPAPO_ALIGN_HEADROOM,
-				       GFP_KERNEL, cpu_to_node(i));
+				       GFP_KERNEL_ACCOUNT, cpu_to_node(i));
 		if (!scratch) {
 			/* On failure, there's no need to undo previous
 			 * allocations: this means that some scratch maps have
@@ -1427,7 +1427,7 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old)
 	struct nft_pipapo_match *new;
 	int i;
 
-	new = kmalloc(struct_size(new, f, old->field_count), GFP_KERNEL);
+	new = kmalloc(struct_size(new, f, old->field_count), GFP_KERNEL_ACCOUNT);
 	if (!new)
 		return NULL;
 
@@ -1457,7 +1457,7 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old)
 		new_lt = kvzalloc(src->groups * NFT_PIPAPO_BUCKETS(src->bb) *
 				  src->bsize * sizeof(*dst->lt) +
 				  NFT_PIPAPO_ALIGN_HEADROOM,
-				  GFP_KERNEL);
+				  GFP_KERNEL_ACCOUNT);
 		if (!new_lt)
 			goto out_lt;
 
@@ -1470,7 +1470,8 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old)
 
 		if (src->rules > 0) {
 			dst->mt = kvmalloc_array(src->rules_alloc,
-						 sizeof(*src->mt), GFP_KERNEL);
+						 sizeof(*src->mt),
+						 GFP_KERNEL_ACCOUNT);
 			if (!dst->mt)
 				goto out_mt;
 
diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c
index 60a76e6e348e..5c6ed68cc6e0 100644
--- a/net/netfilter/nft_tunnel.c
+++ b/net/netfilter/nft_tunnel.c
@@ -509,13 +509,14 @@ static int nft_tunnel_obj_init(const struct nft_ctx *ctx,
 			return err;
 	}
 
-	md = metadata_dst_alloc(priv->opts.len, METADATA_IP_TUNNEL, GFP_KERNEL);
+	md = metadata_dst_alloc(priv->opts.len, METADATA_IP_TUNNEL,
+				GFP_KERNEL_ACCOUNT);
 	if (!md)
 		return -ENOMEM;
 
 	memcpy(&md->u.tun_info, &info, sizeof(info));
 #ifdef CONFIG_DST_CACHE
-	err = dst_cache_init(&md->u.tun_info.dst_cache, GFP_KERNEL);
+	err = dst_cache_init(&md->u.tun_info.dst_cache, GFP_KERNEL_ACCOUNT);
 	if (err < 0) {
 		metadata_dst_free(md);
 		return err;
-- 
2.51.0


From 8af79d3edb5fd2dce35ea0a71595b6d4f9962350 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 18 Sep 2024 15:13:39 +0200
Subject: [PATCH 03/16] netfilter: nfnetlink_queue: remove old clash resolution
 logic

For historical reasons there are two clash resolution spots in
netfilter, one in nfnetlink_queue and one in conntrack core.

nfnetlink_queue one was added first: If a colliding entry is found, NAT
NAT transformation is reversed by calling nat engine again with altered
tuple.

See commit 368982cd7d1b ("netfilter: nfnetlink_queue: resolve clash for
unconfirmed conntracks") for details.

One problem is that nf_reroute() won't take an action if the queueing
doesn't occur in the OUTPUT hook, i.e. when queueing in forward or
postrouting, packet will be sent via the wrong path.

Another problem is that the scenario addressed (2nd UDP packet sent with
identical addresses while first packet is still being processed) can also
occur without any nfqueue involvement due to threaded resolvers doing
A and AAAA requests back-to-back.

This lead us to add clash resolution logic to the conntrack core, see
commit 6a757c07e51f ("netfilter: conntrack: allow insertion of clashing
entries").  Instead of fixing the nfqueue based logic, lets remove it
and let conntrack core handle this instead.

Retain the ->update hook for sake of nfqueue based conntrack helpers.
We could axe this hook completely but we'd have to split confirm and
helper logic again, see commit ee04805ff54a ("netfilter: conntrack: make
conntrack userspace helpers work again").

This SHOULD NOT be backported to kernels earlier than v5.6; they lack
adequate clash resolution handling.

Patch was originally written by Pablo Neira Ayuso.

Reported-by: Antonio Ojea <aojea@google.com>
Closes: https://bugzilla.netfilter.org/show_bug.cgi?id=1766
Signed-off-by: Florian Westphal <fw@strlen.de>
Tested-by: Antonio Ojea <aojea@google.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter.h         |  4 --
 net/netfilter/nf_conntrack_core.c | 85 -------------------------------
 net/netfilter/nf_nat_core.c       |  1 -
 3 files changed, 90 deletions(-)

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 2683b2b77612..2b8aac2c70ad 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -376,15 +376,11 @@ int nf_route(struct net *net, struct dst_entry **dst, struct flowi *fl,
 struct nf_conn;
 enum nf_nat_manip_type;
 struct nlattr;
-enum ip_conntrack_dir;
 
 struct nf_nat_hook {
 	int (*parse_nat_setup)(struct nf_conn *ct, enum nf_nat_manip_type manip,
 			       const struct nlattr *attr);
 	void (*decode_session)(struct sk_buff *skb, struct flowi *fl);
-	unsigned int (*manip_pkt)(struct sk_buff *skb, struct nf_conn *ct,
-				  enum nf_nat_manip_type mtype,
-				  enum ip_conntrack_dir dir);
 	void (*remove_nat_bysrc)(struct nf_conn *ct);
 };
 
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 7c63fbfb8c1d..9db3e2b0b1c3 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -2197,80 +2197,6 @@ static void nf_conntrack_attach(struct sk_buff *nskb, const struct sk_buff *skb)
 	nf_conntrack_get(skb_nfct(nskb));
 }
 
-static int __nf_conntrack_update(struct net *net, struct sk_buff *skb,
-				 struct nf_conn *ct,
-				 enum ip_conntrack_info ctinfo)
-{
-	const struct nf_nat_hook *nat_hook;
-	struct nf_conntrack_tuple_hash *h;
-	struct nf_conntrack_tuple tuple;
-	unsigned int status;
-	int dataoff;
-	u16 l3num;
-	u8 l4num;
-
-	l3num = nf_ct_l3num(ct);
-
-	dataoff = get_l4proto(skb, skb_network_offset(skb), l3num, &l4num);
-	if (dataoff <= 0)
-		return NF_DROP;
-
-	if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, l3num,
-			     l4num, net, &tuple))
-		return NF_DROP;
-
-	if (ct->status & IPS_SRC_NAT) {
-		memcpy(tuple.src.u3.all,
-		       ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.all,
-		       sizeof(tuple.src.u3.all));
-		tuple.src.u.all =
-			ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.all;
-	}
-
-	if (ct->status & IPS_DST_NAT) {
-		memcpy(tuple.dst.u3.all,
-		       ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.all,
-		       sizeof(tuple.dst.u3.all));
-		tuple.dst.u.all =
-			ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.all;
-	}
-
-	h = nf_conntrack_find_get(net, nf_ct_zone(ct), &tuple);
-	if (!h)
-		return NF_ACCEPT;
-
-	/* Store status bits of the conntrack that is clashing to re-do NAT
-	 * mangling according to what it has been done already to this packet.
-	 */
-	status = ct->status;
-
-	nf_ct_put(ct);
-	ct = nf_ct_tuplehash_to_ctrack(h);
-	nf_ct_set(skb, ct, ctinfo);
-
-	nat_hook = rcu_dereference(nf_nat_hook);
-	if (!nat_hook)
-		return NF_ACCEPT;
-
-	if (status & IPS_SRC_NAT) {
-		unsigned int verdict = nat_hook->manip_pkt(skb, ct,
-							   NF_NAT_MANIP_SRC,
-							   IP_CT_DIR_ORIGINAL);
-		if (verdict != NF_ACCEPT)
-			return verdict;
-	}
-
-	if (status & IPS_DST_NAT) {
-		unsigned int verdict = nat_hook->manip_pkt(skb, ct,
-							   NF_NAT_MANIP_DST,
-							   IP_CT_DIR_ORIGINAL);
-		if (verdict != NF_ACCEPT)
-			return verdict;
-	}
-
-	return NF_ACCEPT;
-}
-
 /* This packet is coming from userspace via nf_queue, complete the packet
  * processing after the helper invocation in nf_confirm().
  */
@@ -2334,17 +2260,6 @@ static int nf_conntrack_update(struct net *net, struct sk_buff *skb)
 	if (!ct)
 		return NF_ACCEPT;
 
-	if (!nf_ct_is_confirmed(ct)) {
-		int ret = __nf_conntrack_update(net, skb, ct, ctinfo);
-
-		if (ret != NF_ACCEPT)
-			return ret;
-
-		ct = nf_ct_get(skb, &ctinfo);
-		if (!ct)
-			return NF_ACCEPT;
-	}
-
 	return nf_confirm_cthelper(skb, ct, ctinfo);
 }
 
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index d9ea2c26f309..4085c436e306 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -1324,7 +1324,6 @@ static const struct nf_nat_hook nat_hook = {
 #ifdef CONFIG_XFRM
 	.decode_session		= __nf_nat_decode_session,
 #endif
-	.manip_pkt		= nf_nat_manip_pkt,
 	.remove_nat_bysrc	= nf_nat_cleanup_conntrack,
 };
 
-- 
2.51.0


From e306e3739d9a35c89176281f9ff6c600fcc859a4 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 18 Sep 2024 15:16:33 +0200
Subject: [PATCH 04/16] kselftest: add test for nfqueue induced conntrack race

The netfilter race happens when two packets with the same tuple are DNATed
and enqueued with nfqueue in the postrouting hook.

Once one of the packet is reinjected it may be DNATed again to a different
destination, but the conntrack entry remains the same and the return packet
was dropped.

Based on earlier patch from Antonio Ojea.

Link: https://bugzilla.netfilter.org/show_bug.cgi?id=1766
Co-developed-by: Antonio Ojea <aojea@google.com>
Signed-off-by: Antonio Ojea <aojea@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 .../selftests/net/netfilter/nft_queue.sh      | 92 ++++++++++++++++++-
 1 file changed, 91 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/netfilter/nft_queue.sh b/tools/testing/selftests/net/netfilter/nft_queue.sh
index d66e3c4dfec6..a9d109fcc15c 100755
--- a/tools/testing/selftests/net/netfilter/nft_queue.sh
+++ b/tools/testing/selftests/net/netfilter/nft_queue.sh
@@ -31,7 +31,7 @@ modprobe -q sctp
 
 trap cleanup EXIT
 
-setup_ns ns1 ns2 nsrouter
+setup_ns ns1 ns2 ns3 nsrouter
 
 TMPFILE0=$(mktemp)
 TMPFILE1=$(mktemp)
@@ -48,6 +48,7 @@ if ! ip link add veth0 netns "$nsrouter" type veth peer name eth0 netns "$ns1" >
     exit $ksft_skip
 fi
 ip link add veth1 netns "$nsrouter" type veth peer name eth0 netns "$ns2"
+ip link add veth2 netns "$nsrouter" type veth peer name eth0 netns "$ns3"
 
 ip -net "$nsrouter" link set veth0 up
 ip -net "$nsrouter" addr add 10.0.1.1/24 dev veth0
@@ -57,8 +58,13 @@ ip -net "$nsrouter" link set veth1 up
 ip -net "$nsrouter" addr add 10.0.2.1/24 dev veth1
 ip -net "$nsrouter" addr add dead:2::1/64 dev veth1 nodad
 
+ip -net "$nsrouter" link set veth2 up
+ip -net "$nsrouter" addr add 10.0.3.1/24 dev veth2
+ip -net "$nsrouter" addr add dead:3::1/64 dev veth2 nodad
+
 ip -net "$ns1" link set eth0 up
 ip -net "$ns2" link set eth0 up
+ip -net "$ns3" link set eth0 up
 
 ip -net "$ns1" addr add 10.0.1.99/24 dev eth0
 ip -net "$ns1" addr add dead:1::99/64 dev eth0 nodad
@@ -70,6 +76,11 @@ ip -net "$ns2" addr add dead:2::99/64 dev eth0 nodad
 ip -net "$ns2" route add default via 10.0.2.1
 ip -net "$ns2" route add default via dead:2::1
 
+ip -net "$ns3" addr add 10.0.3.99/24 dev eth0
+ip -net "$ns3" addr add dead:3::99/64 dev eth0 nodad
+ip -net "$ns3" route add default via 10.0.3.1
+ip -net "$ns3" route add default via dead:3::1
+
 load_ruleset() {
 	local name=$1
 	local prio=$2
@@ -473,6 +484,83 @@ EOF
 	check_output_files "$TMPINPUT" "$TMPFILE1" "sctp output"
 }
 
+udp_listener_ready()
+{
+	ss -S -N "$1" -uln -o "sport = :12345" | grep -q 12345
+}
+
+output_files_written()
+{
+	test -s "$1" && test -s "$2"
+}
+
+test_udp_ct_race()
+{
+        ip netns exec "$nsrouter" nft -f /dev/stdin <<EOF
+flush ruleset
+table inet udpq {
+	chain prerouting {
+		type nat hook prerouting priority dstnat - 5; policy accept;
+		ip daddr 10.6.6.6 udp dport 12345 counter dnat to numgen inc mod 2 map { 0 : 10.0.2.99, 1 : 10.0.3.99 }
+	}
+        chain postrouting {
+		type filter hook postrouting priority srcnat - 5; policy accept;
+		udp dport 12345 counter queue num 12
+        }
+}
+EOF
+	:> "$TMPFILE1"
+	:> "$TMPFILE2"
+
+	timeout 10 ip netns exec "$ns2" socat UDP-LISTEN:12345,fork OPEN:"$TMPFILE1",trunc &
+	local rpid1=$!
+
+	timeout 10 ip netns exec "$ns3" socat UDP-LISTEN:12345,fork OPEN:"$TMPFILE2",trunc &
+	local rpid2=$!
+
+	ip netns exec "$nsrouter" ./nf_queue -q 12 -d 1000 &
+	local nfqpid=$!
+
+	busywait "$BUSYWAIT_TIMEOUT" udp_listener_ready "$ns2"
+	busywait "$BUSYWAIT_TIMEOUT" udp_listener_ready "$ns3"
+	busywait "$BUSYWAIT_TIMEOUT" nf_queue_wait "$nsrouter" 12
+
+	# Send two packets, one should end up in ns1, other in ns2.
+	# This is because nfqueue will delay packet for long enough so that
+	# second packet will not find existing conntrack entry.
+	echo "Packet 1" | ip netns exec "$ns1" socat STDIN UDP-DATAGRAM:10.6.6.6:12345,bind=0.0.0.0:55221
+	echo "Packet 2" | ip netns exec "$ns1" socat STDIN UDP-DATAGRAM:10.6.6.6:12345,bind=0.0.0.0:55221
+
+	busywait 10000 output_files_written "$TMPFILE1" "$TMPFILE2"
+
+	kill "$nfqpid"
+
+	if ! ip netns exec "$nsrouter" bash -c 'conntrack -L -p udp --dport 12345 2>/dev/null | wc -l | grep -q "^1"'; then
+		echo "FAIL: Expected One udp conntrack entry"
+		ip netns exec "$nsrouter" conntrack -L -p udp --dport 12345
+		ret=1
+	fi
+
+	if ! ip netns exec "$nsrouter" nft delete table inet udpq; then
+		echo "FAIL: Could not delete udpq table"
+		ret=1
+		return
+	fi
+
+	NUMLINES1=$(wc -l < "$TMPFILE1")
+	NUMLINES2=$(wc -l < "$TMPFILE2")
+
+	if [ "$NUMLINES1" -ne 1 ] || [ "$NUMLINES2" -ne 1 ]; then
+		ret=1
+		echo "FAIL: uneven udp packet distribution: $NUMLINES1 $NUMLINES2"
+		echo -n "$TMPFILE1: ";cat "$TMPFILE1"
+		echo -n "$TMPFILE2: ";cat "$TMPFILE2"
+		return
+	fi
+
+	echo "PASS: both udp receivers got one packet each"
+}
+
 test_queue_removal()
 {
 	read tainted_then < /proc/sys/kernel/tainted
@@ -512,6 +600,7 @@ EOF
 ip netns exec "$nsrouter" sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
 ip netns exec "$nsrouter" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
 ip netns exec "$nsrouter" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+ip netns exec "$nsrouter" sysctl net.ipv4.conf.veth2.forwarding=1 > /dev/null
 
 load_ruleset "filter" 0
 
@@ -549,6 +638,7 @@ test_tcp_localhost_connectclose
 test_tcp_localhost_requeue
 test_sctp_forward
 test_sctp_output
+test_udp_ct_race
 
 # should be last, adds vrf device in ns1 and changes routes
 test_icmp_vrf
-- 
2.51.0


From fc786304ad9803e8bb86b8599bc64d1c1746c75f Mon Sep 17 00:00:00 2001
From: Phil Sutter <phil@nwl.cc>
Date: Thu, 19 Sep 2024 14:40:00 +0200
Subject: [PATCH 05/16] selftests: netfilter: Avoid hanging ipvs.sh

If the client can't reach the server, the latter remains listening
forever. Kill it after 5s of waiting.

Fixes: 867d2190799a ("selftests: netfilter: add ipvs test script")
Signed-off-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 tools/testing/selftests/net/netfilter/ipvs.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/netfilter/ipvs.sh b/tools/testing/selftests/net/netfilter/ipvs.sh
index 4ceee9fb3949..d3edb16cd4b3 100755
--- a/tools/testing/selftests/net/netfilter/ipvs.sh
+++ b/tools/testing/selftests/net/netfilter/ipvs.sh
@@ -97,7 +97,7 @@ cleanup() {
 }
 
 server_listen() {
-	ip netns exec "$ns2" socat -u -4 TCP-LISTEN:8080,reuseaddr STDOUT > "${outfile}" &
+	ip netns exec "$ns2" timeout 5 socat -u -4 TCP-LISTEN:8080,reuseaddr STDOUT > "${outfile}" &
 	server_pid=$!
 	sleep 0.2
 }
-- 
2.51.0


From c824deb1a89755f70156b5cdaf569fca80698719 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Mon, 23 Sep 2024 13:26:00 +0100
Subject: [PATCH 06/16] cxgb4: clip_tbl: Fix spelling mistake "wont" -> "won't"

There are spelling mistakes in dev_err and dev_info messages. Fix them.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c
index 163efab27e9b..5060d3998889 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c
@@ -120,7 +120,7 @@ int cxgb4_clip_get(const struct net_device *dev, const u32 *lip, u8 v6)
 				write_unlock_bh(&ctbl->lock);
 				dev_err(adap->pdev_dev,
 					"CLIP FW cmd failed with error %d, "
-					"Connections using %pI6c wont be "
+					"Connections using %pI6c won't be "
 					"offloaded",
 					ret, ce->addr6.sin6_addr.s6_addr);
 				return ret;
@@ -133,7 +133,7 @@ int cxgb4_clip_get(const struct net_device *dev, const u32 *lip, u8 v6)
 	} else {
 		write_unlock_bh(&ctbl->lock);
 		dev_info(adap->pdev_dev, "CLIP table overflow, "
-			 "Connections using %pI6c wont be offloaded",
+			 "Connections using %pI6c won't be offloaded",
 			 (void *)lip);
 		return -ENOMEM;
 	}
-- 
2.51.0


From 83752e12896a72b24845c94f000e4c51b2bc5b50 Mon Sep 17 00:00:00 2001
From: Nicolas Rybowski <nicolas.rybowski@tessares.net>
Date: Thu, 26 Sep 2024 19:30:22 +0200
Subject: [PATCH 07/16] selftests/bpf: Add mptcp subflow example

Move Nicolas' patch into bpf selftests directory. This example adds a
different mark (SO_MARK) on each subflow, and changes the TCP CC only on
the first subflow.

From the userspace, an application can do a setsockopt() on an MPTCP
socket, and typically the same value will be propagated to all subflows
(paths). If someone wants to have different values per subflow, the
recommended way is to use BPF. So it is good to add such example here,
and make sure there is no regressions.

This example shows how it is possible to:

    Identify the parent msk of an MPTCP subflow.
    Put different sockopt for each subflow of a same MPTCP connection.

Here especially, two different behaviours are implemented:

    A socket mark (SOL_SOCKET SO_MARK) is put on each subflow of a same
    MPTCP connection. The order of creation of the current subflow defines
    its mark. The TCP CC algorithm of the very first subflow of an MPTCP
    connection is set to "reno".

This is just to show it is possible to identify an MPTCP connection, and
set socket options, from different SOL levels, per subflow. "reno" has
been picked because it is built-in and usually not set as default one.
It is easy to verify with 'ss' that these modifications have been
applied correctly. That's what the next patch is going to do.

Nicolas' code comes from:

    commit 4d120186e4d6 ("bpf:examples: update mptcp_set_mark_kern.c")

from the MPTCP repo https://github.com/multipath-tcp/mptcp_net-next (the
"scripts" branch), and it has been adapted by Geliang.

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/76
Co-developed-by: Geliang Tang <tanggeliang@kylinos.cn>
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Signed-off-by: Nicolas Rybowski <nicolas.rybowski@tessares.net>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240926-upstream-bpf-next-20240506-mptcp-subflow-test-v7-1-d26029e15cdd@kernel.org
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../selftests/bpf/progs/mptcp_subflow.c       | 59 +++++++++++++++++++
 1 file changed, 59 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/mptcp_subflow.c

diff --git a/tools/testing/selftests/bpf/progs/mptcp_subflow.c b/tools/testing/selftests/bpf/progs/mptcp_subflow.c
new file mode 100644
index 000000000000..2e28f4a215b5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/mptcp_subflow.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020, Tessares SA. */
+/* Copyright (c) 2024, Kylin Software */
+
+/* vmlinux.h, bpf_helpers.h and other 'define' */
+#include "bpf_tracing_net.h"
+
+char _license[] SEC("license") = "GPL";
+
+char cc[TCP_CA_NAME_MAX] = "reno";
+
+/* Associate a subflow counter to each token */
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+	__uint(max_entries, 100);
+} mptcp_sf SEC(".maps");
+
+SEC("sockops")
+int mptcp_subflow(struct bpf_sock_ops *skops)
+{
+	__u32 init = 1, key, mark, *cnt;
+	struct mptcp_sock *msk;
+	struct bpf_sock *sk;
+	int err;
+
+	if (skops->op != BPF_SOCK_OPS_TCP_CONNECT_CB)
+		return 1;
+
+	sk = skops->sk;
+	if (!sk)
+		return 1;
+
+	msk = bpf_skc_to_mptcp_sock(sk);
+	if (!msk)
+		return 1;
+
+	key = msk->token;
+	cnt = bpf_map_lookup_elem(&mptcp_sf, &key);
+	if (cnt) {
+		/* A new subflow is added to an existing MPTCP connection */
+		__sync_fetch_and_add(cnt, 1);
+		mark = *cnt;
+	} else {
+		/* A new MPTCP connection is just initiated and this is its primary subflow */
+		bpf_map_update_elem(&mptcp_sf, &key, &init, BPF_ANY);
+		mark = init;
+	}
+
+	/* Set the mark of the subflow's socket based on appearance order */
+	err = bpf_setsockopt(skops, SOL_SOCKET, SO_MARK, &mark, sizeof(mark));
+	if (err < 0)
+		return 1;
+	if (mark == 2)
+		err = bpf_setsockopt(skops, SOL_TCP, TCP_CONGESTION, cc, TCP_CA_NAME_MAX);
+
+	return 1;
+}
-- 
2.51.0


From cd19b885106e0a24c28ef72fccc4c020782e6e7e Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 26 Sep 2024 19:30:23 +0200
Subject: [PATCH 08/16] selftests/bpf: Add getsockopt to inspect mptcp subflow

This patch adds a "cgroup/getsockopt" way to inspect the subflows of an
MPTCP socket, and verify the modifications done by the same BPF program
in the previous commit: a different mark per subflow, and a different
TCP CC set on the second one. This new hook will be used by the next
commit to verify the socket options set on each subflow.

This extra "cgroup/getsockopt" prog walks the msk->conn_list and use
bpf_core_cast to cast a pointer for readonly. It allows to inspect all
the fields of a structure.

Note that on the kernel side, the MPTCP socket stores a list of subflows
under 'msk->conn_list'. They can be iterated using the generic 'list'
helpers. They have been imported here, with a small difference:
list_for_each_entry() uses 'can_loop' to limit the number of iterations,
and ease its use. Because only data need to be read here, it is enough
to use this technique. It is planned to use bpf_iter, when BPF programs
will be used to modify data from the different subflows.
mptcp_subflow_tcp_sock() and mptcp_for_each_stubflow() helpers have also
be imported.

Suggested-by: Martin KaFai Lau <martin.lau@kernel.org>
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240926-upstream-bpf-next-20240506-mptcp-subflow-test-v7-2-d26029e15cdd@kernel.org
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 MAINTAINERS                                   |  2 +-
 tools/testing/selftests/bpf/progs/mptcp_bpf.h | 42 +++++++++++
 .../selftests/bpf/progs/mptcp_subflow.c       | 69 +++++++++++++++++++
 3 files changed, 112 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/progs/mptcp_bpf.h

diff --git a/MAINTAINERS b/MAINTAINERS
index e71d066dc919..f02b7485b215 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16281,7 +16281,7 @@ F:	include/net/mptcp.h
 F:	include/trace/events/mptcp.h
 F:	include/uapi/linux/mptcp*.h
 F:	net/mptcp/
-F:	tools/testing/selftests/bpf/*/*mptcp*.c
+F:	tools/testing/selftests/bpf/*/*mptcp*.[ch]
 F:	tools/testing/selftests/net/mptcp/
 
 NETWORKING [TCP]
diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf.h b/tools/testing/selftests/bpf/progs/mptcp_bpf.h
new file mode 100644
index 000000000000..3b188ccdcc40
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __MPTCP_BPF_H__
+#define __MPTCP_BPF_H__
+
+#include "bpf_experimental.h"
+
+/* list helpers from include/linux/list.h */
+static inline int list_is_head(const struct list_head *list,
+			       const struct list_head *head)
+{
+	return list == head;
+}
+
+#define list_entry(ptr, type, member)					\
+	container_of(ptr, type, member)
+
+#define list_first_entry(ptr, type, member)				\
+	list_entry((ptr)->next, type, member)
+
+#define list_next_entry(pos, member)					\
+	list_entry((pos)->member.next, typeof(*(pos)), member)
+
+#define list_entry_is_head(pos, head, member)				\
+	list_is_head(&pos->member, (head))
+
+/* small difference: 'can_loop' has been added in the conditions */
+#define list_for_each_entry(pos, head, member)				\
+	for (pos = list_first_entry(head, typeof(*pos), member);	\
+	     !list_entry_is_head(pos, head, member) && can_loop;	\
+	     pos = list_next_entry(pos, member))
+
+/* mptcp helpers from protocol.h */
+#define mptcp_for_each_subflow(__msk, __subflow)			\
+	list_for_each_entry(__subflow, &((__msk)->conn_list), node)
+
+static __always_inline struct sock *
+mptcp_subflow_tcp_sock(const struct mptcp_subflow_context *subflow)
+{
+	return subflow->tcp_sock;
+}
+
+#endif
diff --git a/tools/testing/selftests/bpf/progs/mptcp_subflow.c b/tools/testing/selftests/bpf/progs/mptcp_subflow.c
index 2e28f4a215b5..70302477e326 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_subflow.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_subflow.c
@@ -4,10 +4,12 @@
 
 /* vmlinux.h, bpf_helpers.h and other 'define' */
 #include "bpf_tracing_net.h"
+#include "mptcp_bpf.h"
 
 char _license[] SEC("license") = "GPL";
 
 char cc[TCP_CA_NAME_MAX] = "reno";
+int pid;
 
 /* Associate a subflow counter to each token */
 struct {
@@ -57,3 +59,70 @@ int mptcp_subflow(struct bpf_sock_ops *skops)
 
 	return 1;
 }
+
+static int _check_getsockopt_subflow_mark(struct mptcp_sock *msk, struct bpf_sockopt *ctx)
+{
+	struct mptcp_subflow_context *subflow;
+	int i = 0;
+
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk;
+
+		ssk = mptcp_subflow_tcp_sock(bpf_core_cast(subflow,
+							   struct mptcp_subflow_context));
+
+		if (ssk->sk_mark != ++i) {
+			ctx->retval = -2;
+			break;
+		}
+	}
+
+	return 1;
+}
+
+static int _check_getsockopt_subflow_cc(struct mptcp_sock *msk, struct bpf_sockopt *ctx)
+{
+	struct mptcp_subflow_context *subflow;
+
+	mptcp_for_each_subflow(msk, subflow) {
+		struct inet_connection_sock *icsk;
+		struct sock *ssk;
+
+		ssk = mptcp_subflow_tcp_sock(bpf_core_cast(subflow,
+							   struct mptcp_subflow_context));
+		icsk = bpf_core_cast(ssk, struct inet_connection_sock);
+
+		if (ssk->sk_mark == 2 &&
+		    __builtin_memcmp(icsk->icsk_ca_ops->name, cc, TCP_CA_NAME_MAX)) {
+			ctx->retval = -2;
+			break;
+		}
+	}
+
+	return 1;
+}
+
+SEC("cgroup/getsockopt")
+int _getsockopt_subflow(struct bpf_sockopt *ctx)
+{
+	struct bpf_sock *sk = ctx->sk;
+	struct mptcp_sock *msk;
+
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 1;
+
+	if (!sk || sk->protocol != IPPROTO_MPTCP ||
+	    (!(ctx->level == SOL_SOCKET && ctx->optname == SO_MARK) &&
+	     !(ctx->level == SOL_TCP && ctx->optname == TCP_CONGESTION)))
+		return 1;
+
+	msk = bpf_core_cast(sk, struct mptcp_sock);
+	if (msk->pm.subflows != 1) {
+		ctx->retval = -1;
+		return 1;
+	}
+
+	if (ctx->optname == SO_MARK)
+		return _check_getsockopt_subflow_mark(msk, ctx);
+	return _check_getsockopt_subflow_cc(msk, ctx);
+}
-- 
2.51.0


From 9b85f11efa02f3dc78c60961c0b9cff166516464 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 26 Sep 2024 19:30:24 +0200
Subject: [PATCH 09/16] selftests/bpf: Add mptcp subflow subtest

This patch adds a subtest named test_subflow in test_mptcp to load and
verify the newly added MPTCP subflow BPF program. To goal is to make
sure it is possible to set different socket options per subflows, while
the userspace socket interface only lets the application to set the same
socket options for the whole MPTCP connection and its multiple subflows.

To check that, a client and a server are started in a dedicated netns,
with veth interfaces to simulate multiple paths. They will exchange data
to allow the creation of an additional subflow.

When the different subflows are being created, the new MPTCP subflow BPF
program will set some socket options: marks and TCP CC. The validation
is done by the same program, when the userspace checks the value of the
modified socket options. On the userspace side, it will see that the
default values are still being used on the MPTCP connection, while the
BPF program will see different options set per subflow of the same MPTCP
connection.

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/76
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240926-upstream-bpf-next-20240506-mptcp-subflow-test-v7-3-d26029e15cdd@kernel.org
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../testing/selftests/bpf/prog_tests/mptcp.c  | 121 ++++++++++++++++++
 1 file changed, 121 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index d2ca32fa3b21..be3cad2aff77 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -5,12 +5,17 @@
 #include <linux/const.h>
 #include <netinet/in.h>
 #include <test_progs.h>
+#include <unistd.h>
 #include "cgroup_helpers.h"
 #include "network_helpers.h"
 #include "mptcp_sock.skel.h"
 #include "mptcpify.skel.h"
+#include "mptcp_subflow.skel.h"
 
 #define NS_TEST "mptcp_ns"
+#define ADDR_1	"10.0.1.1"
+#define ADDR_2	"10.0.1.2"
+#define PORT_1	10001
 
 #ifndef IPPROTO_MPTCP
 #define IPPROTO_MPTCP 262
@@ -335,10 +340,126 @@ fail:
 	close(cgroup_fd);
 }
 
+static int endpoint_init(char *flags)
+{
+	SYS(fail, "ip -net %s link add veth1 type veth peer name veth2", NS_TEST);
+	SYS(fail, "ip -net %s addr add %s/24 dev veth1", NS_TEST, ADDR_1);
+	SYS(fail, "ip -net %s link set dev veth1 up", NS_TEST);
+	SYS(fail, "ip -net %s addr add %s/24 dev veth2", NS_TEST, ADDR_2);
+	SYS(fail, "ip -net %s link set dev veth2 up", NS_TEST);
+	if (SYS_NOFAIL("ip -net %s mptcp endpoint add %s %s", NS_TEST, ADDR_2, flags)) {
+		printf("'ip mptcp' not supported, skip this test.\n");
+		test__skip();
+		goto fail;
+	}
+
+	return 0;
+fail:
+	return -1;
+}
+
+static void wait_for_new_subflows(int fd)
+{
+	socklen_t len;
+	u8 subflows;
+	int err, i;
+
+	len = sizeof(subflows);
+	/* Wait max 5 sec for new subflows to be created */
+	for (i = 0; i < 50; i++) {
+		err = getsockopt(fd, SOL_MPTCP, MPTCP_INFO, &subflows, &len);
+		if (!err && subflows > 0)
+			break;
+
+		usleep(100000); /* 0.1s */
+	}
+}
+
+static void run_subflow(void)
+{
+	int server_fd, client_fd, err;
+	char new[TCP_CA_NAME_MAX];
+	char cc[TCP_CA_NAME_MAX];
+	unsigned int mark;
+	socklen_t len;
+
+	server_fd = start_mptcp_server(AF_INET, ADDR_1, PORT_1, 0);
+	if (!ASSERT_OK_FD(server_fd, "start_mptcp_server"))
+		return;
+
+	client_fd = connect_to_fd(server_fd, 0);
+	if (!ASSERT_OK_FD(client_fd, "connect_to_fd"))
+		goto close_server;
+
+	send_byte(client_fd);
+	wait_for_new_subflows(client_fd);
+
+	len = sizeof(mark);
+	err = getsockopt(client_fd, SOL_SOCKET, SO_MARK, &mark, &len);
+	if (ASSERT_OK(err, "getsockopt(client_fd, SO_MARK)"))
+		ASSERT_EQ(mark, 0, "mark");
+
+	len = sizeof(new);
+	err = getsockopt(client_fd, SOL_TCP, TCP_CONGESTION, new, &len);
+	if (ASSERT_OK(err, "getsockopt(client_fd, TCP_CONGESTION)")) {
+		get_msk_ca_name(cc);
+		ASSERT_STREQ(new, cc, "cc");
+	}
+
+	close(client_fd);
+close_server:
+	close(server_fd);
+}
+
+static void test_subflow(void)
+{
+	struct mptcp_subflow *skel;
+	struct nstoken *nstoken;
+	int cgroup_fd;
+
+	cgroup_fd = test__join_cgroup("/mptcp_subflow");
+	if (!ASSERT_OK_FD(cgroup_fd, "join_cgroup: mptcp_subflow"))
+		return;
+
+	skel = mptcp_subflow__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_load: mptcp_subflow"))
+		goto close_cgroup;
+
+	skel->bss->pid = getpid();
+
+	skel->links.mptcp_subflow =
+		bpf_program__attach_cgroup(skel->progs.mptcp_subflow, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.mptcp_subflow, "attach mptcp_subflow"))
+		goto skel_destroy;
+
+	skel->links._getsockopt_subflow =
+		bpf_program__attach_cgroup(skel->progs._getsockopt_subflow, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links._getsockopt_subflow, "attach _getsockopt_subflow"))
+		goto skel_destroy;
+
+	nstoken = create_netns();
+	if (!ASSERT_OK_PTR(nstoken, "create_netns: mptcp_subflow"))
+		goto skel_destroy;
+
+	if (endpoint_init("subflow") < 0)
+		goto close_netns;
+
+	run_subflow();
+
+close_netns:
+	cleanup_netns(nstoken);
+skel_destroy:
+	mptcp_subflow__destroy(skel);
+close_cgroup:
+	close(cgroup_fd);
+}
+
 void test_mptcp(void)
 {
 	if (test__start_subtest("base"))
 		test_base();
 	if (test__start_subtest("mptcpify"))
 		test_mptcpify();
+	if (test__start_subtest("subflow"))
+		test_subflow();
 }
-- 
2.51.0


From 8f5b408d7661e33157b16c4e4d232f483e8e4f79 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 1 Oct 2024 22:06:05 +0200
Subject: [PATCH 10/16] bpf: Remove unused macro

Commit 7aebfa1b3885 ("bpf: Support narrow loads from bpf_sock_addr.user_port")
removed one and only SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD callsite but kept
the macro. Remove it to clean up the code base. Found while getting lost in
the BPF code.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20241001200605.249526-1-maciej.fijalkowski@intel.com
---
 net/core/filter.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index cd3524cb326b..e61ac225c41b 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -10241,10 +10241,6 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
 		}							       \
 	} while (0)
 
-#define SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD(S, NS, F, NF, TF)		       \
-	SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF(			       \
-		S, NS, F, NF, BPF_FIELD_SIZEOF(NS, NF), 0, TF)
-
 static u32 sock_addr_convert_ctx_access(enum bpf_access_type type,
 					const struct bpf_insn *si,
 					struct bpf_insn *insn_buf,
-- 
2.51.0


From 83134ef4609388f6b9ca31a384f531155196c2a7 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 4 Oct 2024 12:13:31 +0200
Subject: [PATCH 11/16] netkit: Add option for scrubbing skb meta data

Jordan reported that when running Cilium with netkit in per-endpoint-routes
mode, network policy misclassifies traffic. In this direct routing mode
of Cilium which is used in case of GKE/EKS/AKS, the Pod's BPF program to
enforce policy sits on the netkit primary device's egress side.

The issue here is that in case of netkit's netkit_prep_forward(), it will
clear meta data such as skb->mark and skb->priority before executing the
BPF program. Thus, identity data stored in there from earlier BPF programs
(e.g. from tcx ingress on the physical device) gets cleared instead of
being made available for the primary's program to process. While for traffic
egressing the Pod via the peer device this might be desired, this is
different for the primary one where compared to tcx egress on the host
veth this information would be available.

To address this, add a new parameter for the device orchestration to
allow control of skb->mark and skb->priority scrubbing, to make the two
accessible from BPF (and eventually leave it up to the program to scrub).
By default, the current behavior is retained. For netkit peer this also
enables the use case where applications could cooperate/signal intent to
the BPF program.

Note that struct netkit has a 4 byte hole between policy and bundle which
is used here, in other words, struct netkit's first cacheline content used
in fast-path does not get moved around.

Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device")
Reported-by: Jordan Rife <jrife@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://github.com/cilium/cilium/issues/34042
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20241004101335.117711-1-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 drivers/net/netkit.c         | 68 +++++++++++++++++++++++++++++-------
 include/uapi/linux/if_link.h | 15 ++++++++
 2 files changed, 70 insertions(+), 13 deletions(-)

diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c
index 059269557d92..fba2c734f0ec 100644
--- a/drivers/net/netkit.c
+++ b/drivers/net/netkit.c
@@ -20,6 +20,7 @@ struct netkit {
 	struct net_device __rcu *peer;
 	struct bpf_mprog_entry __rcu *active;
 	enum netkit_action policy;
+	enum netkit_scrub scrub;
 	struct bpf_mprog_bundle	bundle;
 
 	/* Needed in slow-path */
@@ -50,12 +51,24 @@ netkit_run(const struct bpf_mprog_entry *entry, struct sk_buff *skb,
 	return ret;
 }
 
-static void netkit_prep_forward(struct sk_buff *skb, bool xnet)
+static void netkit_xnet(struct sk_buff *skb)
 {
-	skb_scrub_packet(skb, xnet);
 	skb->priority = 0;
+	skb->mark = 0;
+}
+
+static void netkit_prep_forward(struct sk_buff *skb,
+				bool xnet, bool xnet_scrub)
+{
+	skb_scrub_packet(skb, false);
 	nf_skip_egress(skb, true);
 	skb_reset_mac_header(skb);
+	if (!xnet)
+		return;
+	ipvs_reset(skb);
+	skb_clear_tstamp(skb);
+	if (xnet_scrub)
+		netkit_xnet(skb);
 }
 
 static struct netkit *netkit_priv(const struct net_device *dev)
@@ -80,7 +93,8 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev)
 		     !pskb_may_pull(skb, ETH_HLEN) ||
 		     skb_orphan_frags(skb, GFP_ATOMIC)))
 		goto drop;
-	netkit_prep_forward(skb, !net_eq(dev_net(dev), dev_net(peer)));
+	netkit_prep_forward(skb, !net_eq(dev_net(dev), dev_net(peer)),
+			    nk->scrub);
 	eth_skb_pkt_type(skb, peer);
 	skb->dev = peer;
 	entry = rcu_dereference(nk->active);
@@ -332,8 +346,10 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev,
 			   struct netlink_ext_ack *extack)
 {
 	struct nlattr *peer_tb[IFLA_MAX + 1], **tbp = tb, *attr;
-	enum netkit_action default_prim = NETKIT_PASS;
-	enum netkit_action default_peer = NETKIT_PASS;
+	enum netkit_action policy_prim = NETKIT_PASS;
+	enum netkit_action policy_peer = NETKIT_PASS;
+	enum netkit_scrub scrub_prim = NETKIT_SCRUB_DEFAULT;
+	enum netkit_scrub scrub_peer = NETKIT_SCRUB_DEFAULT;
 	enum netkit_mode mode = NETKIT_L3;
 	unsigned char ifname_assign_type;
 	struct ifinfomsg *ifmp = NULL;
@@ -362,17 +378,21 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev,
 				return err;
 			tbp = peer_tb;
 		}
+		if (data[IFLA_NETKIT_SCRUB])
+			scrub_prim = nla_get_u32(data[IFLA_NETKIT_SCRUB]);
+		if (data[IFLA_NETKIT_PEER_SCRUB])
+			scrub_peer = nla_get_u32(data[IFLA_NETKIT_PEER_SCRUB]);
 		if (data[IFLA_NETKIT_POLICY]) {
 			attr = data[IFLA_NETKIT_POLICY];
-			default_prim = nla_get_u32(attr);
-			err = netkit_check_policy(default_prim, attr, extack);
+			policy_prim = nla_get_u32(attr);
+			err = netkit_check_policy(policy_prim, attr, extack);
 			if (err < 0)
 				return err;
 		}
 		if (data[IFLA_NETKIT_PEER_POLICY]) {
 			attr = data[IFLA_NETKIT_PEER_POLICY];
-			default_peer = nla_get_u32(attr);
-			err = netkit_check_policy(default_peer, attr, extack);
+			policy_peer = nla_get_u32(attr);
+			err = netkit_check_policy(policy_peer, attr, extack);
 			if (err < 0)
 				return err;
 		}
@@ -409,7 +429,8 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev,
 
 	nk = netkit_priv(peer);
 	nk->primary = false;
-	nk->policy = default_peer;
+	nk->policy = policy_peer;
+	nk->scrub = scrub_peer;
 	nk->mode = mode;
 	bpf_mprog_bundle_init(&nk->bundle);
 
@@ -434,7 +455,8 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev,
 
 	nk = netkit_priv(dev);
 	nk->primary = true;
-	nk->policy = default_prim;
+	nk->policy = policy_prim;
+	nk->scrub = scrub_prim;
 	nk->mode = mode;
 	bpf_mprog_bundle_init(&nk->bundle);
 
@@ -874,6 +896,18 @@ static int netkit_change_link(struct net_device *dev, struct nlattr *tb[],
 		return -EACCES;
 	}
 
+	if (data[IFLA_NETKIT_SCRUB]) {
+		NL_SET_ERR_MSG_ATTR(extack, data[IFLA_NETKIT_SCRUB],
+				    "netkit scrubbing cannot be changed after device creation");
+		return -EACCES;
+	}
+
+	if (data[IFLA_NETKIT_PEER_SCRUB]) {
+		NL_SET_ERR_MSG_ATTR(extack, data[IFLA_NETKIT_PEER_SCRUB],
+				    "netkit scrubbing cannot be changed after device creation");
+		return -EACCES;
+	}
+
 	if (data[IFLA_NETKIT_PEER_INFO]) {
 		NL_SET_ERR_MSG_ATTR(extack, data[IFLA_NETKIT_PEER_INFO],
 				    "netkit peer info cannot be changed after device creation");
@@ -908,8 +942,10 @@ static size_t netkit_get_size(const struct net_device *dev)
 {
 	return nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_POLICY */
 	       nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_PEER_POLICY */
-	       nla_total_size(sizeof(u8))  + /* IFLA_NETKIT_PRIMARY */
+	       nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_SCRUB */
+	       nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_PEER_SCRUB */
 	       nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_MODE */
+	       nla_total_size(sizeof(u8))  + /* IFLA_NETKIT_PRIMARY */
 	       0;
 }
 
@@ -924,11 +960,15 @@ static int netkit_fill_info(struct sk_buff *skb, const struct net_device *dev)
 		return -EMSGSIZE;
 	if (nla_put_u32(skb, IFLA_NETKIT_MODE, nk->mode))
 		return -EMSGSIZE;
+	if (nla_put_u32(skb, IFLA_NETKIT_SCRUB, nk->scrub))
+		return -EMSGSIZE;
 
 	if (peer) {
 		nk = netkit_priv(peer);
 		if (nla_put_u32(skb, IFLA_NETKIT_PEER_POLICY, nk->policy))
 			return -EMSGSIZE;
+		if (nla_put_u32(skb, IFLA_NETKIT_PEER_SCRUB, nk->scrub))
+			return -EMSGSIZE;
 	}
 
 	return 0;
@@ -936,9 +976,11 @@ static int netkit_fill_info(struct sk_buff *skb, const struct net_device *dev)
 
 static const struct nla_policy netkit_policy[IFLA_NETKIT_MAX + 1] = {
 	[IFLA_NETKIT_PEER_INFO]		= { .len = sizeof(struct ifinfomsg) },
-	[IFLA_NETKIT_POLICY]		= { .type = NLA_U32 },
 	[IFLA_NETKIT_MODE]		= { .type = NLA_U32 },
+	[IFLA_NETKIT_POLICY]		= { .type = NLA_U32 },
 	[IFLA_NETKIT_PEER_POLICY]	= { .type = NLA_U32 },
+	[IFLA_NETKIT_SCRUB]		= NLA_POLICY_MAX(NLA_U32, NETKIT_SCRUB_DEFAULT),
+	[IFLA_NETKIT_PEER_SCRUB]	= NLA_POLICY_MAX(NLA_U32, NETKIT_SCRUB_DEFAULT),
 	[IFLA_NETKIT_PRIMARY]		= { .type = NLA_REJECT,
 					    .reject_message = "Primary attribute is read-only" },
 };
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 6dc258993b17..2acc7687e017 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -1292,6 +1292,19 @@ enum netkit_mode {
 	NETKIT_L3,
 };
 
+/* NETKIT_SCRUB_NONE leaves clearing skb->{mark,priority} up to
+ * the BPF program if attached. This also means the latter can
+ * consume the two fields if they were populated earlier.
+ *
+ * NETKIT_SCRUB_DEFAULT zeroes skb->{mark,priority} fields before
+ * invoking the attached BPF program when the peer device resides
+ * in a different network namespace. This is the default behavior.
+ */
+enum netkit_scrub {
+	NETKIT_SCRUB_NONE,
+	NETKIT_SCRUB_DEFAULT,
+};
+
 enum {
 	IFLA_NETKIT_UNSPEC,
 	IFLA_NETKIT_PEER_INFO,
@@ -1299,6 +1312,8 @@ enum {
 	IFLA_NETKIT_POLICY,
 	IFLA_NETKIT_PEER_POLICY,
 	IFLA_NETKIT_MODE,
+	IFLA_NETKIT_SCRUB,
+	IFLA_NETKIT_PEER_SCRUB,
 	__IFLA_NETKIT_MAX,
 };
 #define IFLA_NETKIT_MAX	(__IFLA_NETKIT_MAX - 1)
-- 
2.51.0


From 0ebe224ffce83b3c2b331295d473296220d9fc36 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 4 Oct 2024 12:13:32 +0200
Subject: [PATCH 12/16] netkit: Simplify netkit mode over to use NLA_POLICY_MAX

Jakub suggested to rely on netlink policy validation via NLA_POLICY_MAX()
instead of open-coding it. netkit_check_mode() is a candidate which can
be simplified through this as well aside from the netkit scrubbing one.

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20241004101335.117711-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 drivers/net/netkit.c | 25 +++----------------------
 1 file changed, 3 insertions(+), 22 deletions(-)

diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c
index fba2c734f0ec..cd8360b9bbde 100644
--- a/drivers/net/netkit.c
+++ b/drivers/net/netkit.c
@@ -311,20 +311,6 @@ static int netkit_check_policy(int policy, struct nlattr *tb,
 	}
 }
 
-static int netkit_check_mode(int mode, struct nlattr *tb,
-			     struct netlink_ext_ack *extack)
-{
-	switch (mode) {
-	case NETKIT_L2:
-	case NETKIT_L3:
-		return 0;
-	default:
-		NL_SET_ERR_MSG_ATTR(extack, tb,
-				    "Provided device mode can only be L2 or L3");
-		return -EINVAL;
-	}
-}
-
 static int netkit_validate(struct nlattr *tb[], struct nlattr *data[],
 			   struct netlink_ext_ack *extack)
 {
@@ -360,13 +346,8 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev,
 	int err;
 
 	if (data) {
-		if (data[IFLA_NETKIT_MODE]) {
-			attr = data[IFLA_NETKIT_MODE];
-			mode = nla_get_u32(attr);
-			err = netkit_check_mode(mode, attr, extack);
-			if (err < 0)
-				return err;
-		}
+		if (data[IFLA_NETKIT_MODE])
+			mode = nla_get_u32(data[IFLA_NETKIT_MODE]);
 		if (data[IFLA_NETKIT_PEER_INFO]) {
 			attr = data[IFLA_NETKIT_PEER_INFO];
 			ifmp = nla_data(attr);
@@ -976,7 +957,7 @@ static int netkit_fill_info(struct sk_buff *skb, const struct net_device *dev)
 
 static const struct nla_policy netkit_policy[IFLA_NETKIT_MAX + 1] = {
 	[IFLA_NETKIT_PEER_INFO]		= { .len = sizeof(struct ifinfomsg) },
-	[IFLA_NETKIT_MODE]		= { .type = NLA_U32 },
+	[IFLA_NETKIT_MODE]		= NLA_POLICY_MAX(NLA_U32, NETKIT_L3),
 	[IFLA_NETKIT_POLICY]		= { .type = NLA_U32 },
 	[IFLA_NETKIT_PEER_POLICY]	= { .type = NLA_U32 },
 	[IFLA_NETKIT_SCRUB]		= NLA_POLICY_MAX(NLA_U32, NETKIT_SCRUB_DEFAULT),
-- 
2.51.0


From 7b9b713b8ef3aa4f8fa90419edbbabd29d7398cd Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 4 Oct 2024 12:13:33 +0200
Subject: [PATCH 13/16] netkit: Add add netkit scrub support to rt_link.yaml

Add netkit scrub attribute support to the rt_link.yaml spec file.

Example:

  # ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/rt_link.yaml \
   --do getlink --json '{"ifname": "nk0"}' --output-json | jq
  [...]
  "linkinfo": {
    "kind": "netkit",
    "data": {
      "primary": 0,
      "policy": "forward",
      "mode": "l3",
      "scrub": "default",
      "peer-policy": "forward",
      "peer-scrub": "default"
    }
  },
  [...]

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20241004101335.117711-3-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 Documentation/netlink/specs/rt_link.yaml | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/Documentation/netlink/specs/rt_link.yaml b/Documentation/netlink/specs/rt_link.yaml
index 0c4d5d40cae9..59c51cf6df31 100644
--- a/Documentation/netlink/specs/rt_link.yaml
+++ b/Documentation/netlink/specs/rt_link.yaml
@@ -920,6 +920,13 @@ definitions:
       - name: l2
       - name: l3
 
+  -
+    name: netkit-scrub
+    type: enum
+    entries:
+      - name: none
+      - name: default
+
 attribute-sets:
   -
     name: link-attrs
@@ -2147,6 +2154,14 @@ attribute-sets:
         name: mode
         type: u32
         enum: netkit-mode
+      -
+        name: scrub
+        type: u32
+        enum: netkit-scrub
+      -
+        name: peer-scrub
+        type: u32
+        enum: netkit-scrub
 
 sub-messages:
   -
-- 
2.51.0


From 107525833bcedb9d7c2c6a21abb8b9747410f364 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 4 Oct 2024 12:13:34 +0200
Subject: [PATCH 14/16] tools: Sync if_link.h uapi tooling header

Sync if_link uapi header to the latest version as we need the refresher
in tooling for netkit device. Given it's been a while since the last sync
and the diff is fairly big, it has been done as its own commit.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20241004101335.117711-4-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/include/uapi/linux/if_link.h | 553 ++++++++++++++++++++++++++++-
 1 file changed, 552 insertions(+), 1 deletion(-)

diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index f0d71b2a3f1e..2acc7687e017 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -461,6 +461,286 @@ enum in6_addr_gen_mode {
 
 /* Bridge section */
 
+/**
+ * DOC: Bridge enum definition
+ *
+ * Please *note* that the timer values in the following section are expected
+ * in clock_t format, which is seconds multiplied by USER_HZ (generally
+ * defined as 100).
+ *
+ * @IFLA_BR_FORWARD_DELAY
+ *   The bridge forwarding delay is the time spent in LISTENING state
+ *   (before moving to LEARNING) and in LEARNING state (before moving
+ *   to FORWARDING). Only relevant if STP is enabled.
+ *
+ *   The valid values are between (2 * USER_HZ) and (30 * USER_HZ).
+ *   The default value is (15 * USER_HZ).
+ *
+ * @IFLA_BR_HELLO_TIME
+ *   The time between hello packets sent by the bridge, when it is a root
+ *   bridge or a designated bridge. Only relevant if STP is enabled.
+ *
+ *   The valid values are between (1 * USER_HZ) and (10 * USER_HZ).
+ *   The default value is (2 * USER_HZ).
+ *
+ * @IFLA_BR_MAX_AGE
+ *   The hello packet timeout is the time until another bridge in the
+ *   spanning tree is assumed to be dead, after reception of its last hello
+ *   message. Only relevant if STP is enabled.
+ *
+ *   The valid values are between (6 * USER_HZ) and (40 * USER_HZ).
+ *   The default value is (20 * USER_HZ).
+ *
+ * @IFLA_BR_AGEING_TIME
+ *   Configure the bridge's FDB entries aging time. It is the time a MAC
+ *   address will be kept in the FDB after a packet has been received from
+ *   that address. After this time has passed, entries are cleaned up.
+ *   Allow values outside the 802.1 standard specification for special cases:
+ *
+ *     * 0 - entry never ages (all permanent)
+ *     * 1 - entry disappears (no persistence)
+ *
+ *   The default value is (300 * USER_HZ).
+ *
+ * @IFLA_BR_STP_STATE
+ *   Turn spanning tree protocol on (*IFLA_BR_STP_STATE* > 0) or off
+ *   (*IFLA_BR_STP_STATE* == 0) for this bridge.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_PRIORITY
+ *   Set this bridge's spanning tree priority, used during STP root bridge
+ *   election.
+ *
+ *   The valid values are between 0 and 65535.
+ *
+ * @IFLA_BR_VLAN_FILTERING
+ *   Turn VLAN filtering on (*IFLA_BR_VLAN_FILTERING* > 0) or off
+ *   (*IFLA_BR_VLAN_FILTERING* == 0). When disabled, the bridge will not
+ *   consider the VLAN tag when handling packets.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_VLAN_PROTOCOL
+ *   Set the protocol used for VLAN filtering.
+ *
+ *   The valid values are 0x8100(802.1Q) or 0x88A8(802.1AD). The default value
+ *   is 0x8100(802.1Q).
+ *
+ * @IFLA_BR_GROUP_FWD_MASK
+ *   The group forwarding mask. This is the bitmask that is applied to
+ *   decide whether to forward incoming frames destined to link-local
+ *   addresses (of the form 01:80:C2:00:00:0X).
+ *
+ *   The default value is 0, which means the bridge does not forward any
+ *   link-local frames coming on this port.
+ *
+ * @IFLA_BR_ROOT_ID
+ *   The bridge root id, read only.
+ *
+ * @IFLA_BR_BRIDGE_ID
+ *   The bridge id, read only.
+ *
+ * @IFLA_BR_ROOT_PORT
+ *   The bridge root port, read only.
+ *
+ * @IFLA_BR_ROOT_PATH_COST
+ *   The bridge root path cost, read only.
+ *
+ * @IFLA_BR_TOPOLOGY_CHANGE
+ *   The bridge topology change, read only.
+ *
+ * @IFLA_BR_TOPOLOGY_CHANGE_DETECTED
+ *   The bridge topology change detected, read only.
+ *
+ * @IFLA_BR_HELLO_TIMER
+ *   The bridge hello timer, read only.
+ *
+ * @IFLA_BR_TCN_TIMER
+ *   The bridge tcn timer, read only.
+ *
+ * @IFLA_BR_TOPOLOGY_CHANGE_TIMER
+ *   The bridge topology change timer, read only.
+ *
+ * @IFLA_BR_GC_TIMER
+ *   The bridge gc timer, read only.
+ *
+ * @IFLA_BR_GROUP_ADDR
+ *   Set the MAC address of the multicast group this bridge uses for STP.
+ *   The address must be a link-local address in standard Ethernet MAC address
+ *   format. It is an address of the form 01:80:C2:00:00:0X, with X in [0, 4..f].
+ *
+ *   The default value is 0.
+ *
+ * @IFLA_BR_FDB_FLUSH
+ *   Flush bridge's fdb dynamic entries.
+ *
+ * @IFLA_BR_MCAST_ROUTER
+ *   Set bridge's multicast router if IGMP snooping is enabled.
+ *   The valid values are:
+ *
+ *     * 0 - disabled.
+ *     * 1 - automatic (queried).
+ *     * 2 - permanently enabled.
+ *
+ *   The default value is 1.
+ *
+ * @IFLA_BR_MCAST_SNOOPING
+ *   Turn multicast snooping on (*IFLA_BR_MCAST_SNOOPING* > 0) or off
+ *   (*IFLA_BR_MCAST_SNOOPING* == 0).
+ *
+ *   The default value is 1.
+ *
+ * @IFLA_BR_MCAST_QUERY_USE_IFADDR
+ *   If enabled use the bridge's own IP address as source address for IGMP
+ *   queries (*IFLA_BR_MCAST_QUERY_USE_IFADDR* > 0) or the default of 0.0.0.0
+ *   (*IFLA_BR_MCAST_QUERY_USE_IFADDR* == 0).
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MCAST_QUERIER
+ *   Enable (*IFLA_BR_MULTICAST_QUERIER* > 0) or disable
+ *   (*IFLA_BR_MULTICAST_QUERIER* == 0) IGMP querier, ie sending of multicast
+ *   queries by the bridge.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MCAST_HASH_ELASTICITY
+ *   Set multicast database hash elasticity, It is the maximum chain length in
+ *   the multicast hash table. This attribute is *deprecated* and the value
+ *   is always 16.
+ *
+ * @IFLA_BR_MCAST_HASH_MAX
+ *   Set maximum size of the multicast hash table
+ *
+ *   The default value is 4096, the value must be a power of 2.
+ *
+ * @IFLA_BR_MCAST_LAST_MEMBER_CNT
+ *   The Last Member Query Count is the number of Group-Specific Queries
+ *   sent before the router assumes there are no local members. The Last
+ *   Member Query Count is also the number of Group-and-Source-Specific
+ *   Queries sent before the router assumes there are no listeners for a
+ *   particular source.
+ *
+ *   The default value is 2.
+ *
+ * @IFLA_BR_MCAST_STARTUP_QUERY_CNT
+ *   The Startup Query Count is the number of Queries sent out on startup,
+ *   separated by the Startup Query Interval.
+ *
+ *   The default value is 2.
+ *
+ * @IFLA_BR_MCAST_LAST_MEMBER_INTVL
+ *   The Last Member Query Interval is the Max Response Time inserted into
+ *   Group-Specific Queries sent in response to Leave Group messages, and
+ *   is also the amount of time between Group-Specific Query messages.
+ *
+ *   The default value is (1 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_MEMBERSHIP_INTVL
+ *   The interval after which the bridge will leave a group, if no membership
+ *   reports for this group are received.
+ *
+ *   The default value is (260 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_QUERIER_INTVL
+ *   The interval between queries sent by other routers. if no queries are
+ *   seen after this delay has passed, the bridge will start to send its own
+ *   queries (as if *IFLA_BR_MCAST_QUERIER_INTVL* was enabled).
+ *
+ *   The default value is (255 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_QUERY_INTVL
+ *   The Query Interval is the interval between General Queries sent by
+ *   the Querier.
+ *
+ *   The default value is (125 * USER_HZ). The minimum value is (1 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_QUERY_RESPONSE_INTVL
+ *   The Max Response Time used to calculate the Max Resp Code inserted
+ *   into the periodic General Queries.
+ *
+ *   The default value is (10 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_STARTUP_QUERY_INTVL
+ *   The interval between queries in the startup phase.
+ *
+ *   The default value is (125 * USER_HZ) / 4. The minimum value is (1 * USER_HZ).
+ *
+ * @IFLA_BR_NF_CALL_IPTABLES
+ *   Enable (*NF_CALL_IPTABLES* > 0) or disable (*NF_CALL_IPTABLES* == 0)
+ *   iptables hooks on the bridge.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_NF_CALL_IP6TABLES
+ *   Enable (*NF_CALL_IP6TABLES* > 0) or disable (*NF_CALL_IP6TABLES* == 0)
+ *   ip6tables hooks on the bridge.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_NF_CALL_ARPTABLES
+ *   Enable (*NF_CALL_ARPTABLES* > 0) or disable (*NF_CALL_ARPTABLES* == 0)
+ *   arptables hooks on the bridge.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_VLAN_DEFAULT_PVID
+ *   VLAN ID applied to untagged and priority-tagged incoming packets.
+ *
+ *   The default value is 1. Setting to the special value 0 makes all ports of
+ *   this bridge not have a PVID by default, which means that they will
+ *   not accept VLAN-untagged traffic.
+ *
+ * @IFLA_BR_PAD
+ *   Bridge attribute padding type for netlink message.
+ *
+ * @IFLA_BR_VLAN_STATS_ENABLED
+ *   Enable (*IFLA_BR_VLAN_STATS_ENABLED* == 1) or disable
+ *   (*IFLA_BR_VLAN_STATS_ENABLED* == 0) per-VLAN stats accounting.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MCAST_STATS_ENABLED
+ *   Enable (*IFLA_BR_MCAST_STATS_ENABLED* > 0) or disable
+ *   (*IFLA_BR_MCAST_STATS_ENABLED* == 0) multicast (IGMP/MLD) stats
+ *   accounting.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MCAST_IGMP_VERSION
+ *   Set the IGMP version.
+ *
+ *   The valid values are 2 and 3. The default value is 2.
+ *
+ * @IFLA_BR_MCAST_MLD_VERSION
+ *   Set the MLD version.
+ *
+ *   The valid values are 1 and 2. The default value is 1.
+ *
+ * @IFLA_BR_VLAN_STATS_PER_PORT
+ *   Enable (*IFLA_BR_VLAN_STATS_PER_PORT* == 1) or disable
+ *   (*IFLA_BR_VLAN_STATS_PER_PORT* == 0) per-VLAN per-port stats accounting.
+ *   Can be changed only when there are no port VLANs configured.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MULTI_BOOLOPT
+ *   The multi_boolopt is used to control new boolean options to avoid adding
+ *   new netlink attributes. You can look at ``enum br_boolopt_id`` for those
+ *   options.
+ *
+ * @IFLA_BR_MCAST_QUERIER_STATE
+ *   Bridge mcast querier states, read only.
+ *
+ * @IFLA_BR_FDB_N_LEARNED
+ *   The number of dynamically learned FDB entries for the current bridge,
+ *   read only.
+ *
+ * @IFLA_BR_FDB_MAX_LEARNED
+ *   Set the number of max dynamically learned FDB entries for the current
+ *   bridge.
+ */
 enum {
 	IFLA_BR_UNSPEC,
 	IFLA_BR_FORWARD_DELAY,
@@ -510,6 +790,8 @@ enum {
 	IFLA_BR_VLAN_STATS_PER_PORT,
 	IFLA_BR_MULTI_BOOLOPT,
 	IFLA_BR_MCAST_QUERIER_STATE,
+	IFLA_BR_FDB_N_LEARNED,
+	IFLA_BR_FDB_MAX_LEARNED,
 	__IFLA_BR_MAX,
 };
 
@@ -520,11 +802,252 @@ struct ifla_bridge_id {
 	__u8	addr[6]; /* ETH_ALEN */
 };
 
+/**
+ * DOC: Bridge mode enum definition
+ *
+ * @BRIDGE_MODE_HAIRPIN
+ *   Controls whether traffic may be sent back out of the port on which it
+ *   was received. This option is also called reflective relay mode, and is
+ *   used to support basic VEPA (Virtual Ethernet Port Aggregator)
+ *   capabilities. By default, this flag is turned off and the bridge will
+ *   not forward traffic back out of the receiving port.
+ */
 enum {
 	BRIDGE_MODE_UNSPEC,
 	BRIDGE_MODE_HAIRPIN,
 };
 
+/**
+ * DOC: Bridge port enum definition
+ *
+ * @IFLA_BRPORT_STATE
+ *   The operation state of the port. Here are the valid values.
+ *
+ *     * 0 - port is in STP *DISABLED* state. Make this port completely
+ *       inactive for STP. This is also called BPDU filter and could be used
+ *       to disable STP on an untrusted port, like a leaf virtual device.
+ *       The traffic forwarding is also stopped on this port.
+ *     * 1 - port is in STP *LISTENING* state. Only valid if STP is enabled
+ *       on the bridge. In this state the port listens for STP BPDUs and
+ *       drops all other traffic frames.
+ *     * 2 - port is in STP *LEARNING* state. Only valid if STP is enabled on
+ *       the bridge. In this state the port will accept traffic only for the
+ *       purpose of updating MAC address tables.
+ *     * 3 - port is in STP *FORWARDING* state. Port is fully active.
+ *     * 4 - port is in STP *BLOCKING* state. Only valid if STP is enabled on
+ *       the bridge. This state is used during the STP election process.
+ *       In this state, port will only process STP BPDUs.
+ *
+ * @IFLA_BRPORT_PRIORITY
+ *   The STP port priority. The valid values are between 0 and 255.
+ *
+ * @IFLA_BRPORT_COST
+ *   The STP path cost of the port. The valid values are between 1 and 65535.
+ *
+ * @IFLA_BRPORT_MODE
+ *   Set the bridge port mode. See *BRIDGE_MODE_HAIRPIN* for more details.
+ *
+ * @IFLA_BRPORT_GUARD
+ *   Controls whether STP BPDUs will be processed by the bridge port. By
+ *   default, the flag is turned off to allow BPDU processing. Turning this
+ *   flag on will disable the bridge port if a STP BPDU packet is received.
+ *
+ *   If the bridge has Spanning Tree enabled, hostile devices on the network
+ *   may send BPDU on a port and cause network failure. Setting *guard on*
+ *   will detect and stop this by disabling the port. The port will be
+ *   restarted if the link is brought down, or removed and reattached.
+ *
+ * @IFLA_BRPORT_PROTECT
+ *   Controls whether a given port is allowed to become a root port or not.
+ *   Only used when STP is enabled on the bridge. By default the flag is off.
+ *
+ *   This feature is also called root port guard. If BPDU is received from a
+ *   leaf (edge) port, it should not be elected as root port. This could
+ *   be used if using STP on a bridge and the downstream bridges are not fully
+ *   trusted; this prevents a hostile guest from rerouting traffic.
+ *
+ * @IFLA_BRPORT_FAST_LEAVE
+ *   This flag allows the bridge to immediately stop multicast traffic
+ *   forwarding on a port that receives an IGMP Leave message. It is only used
+ *   when IGMP snooping is enabled on the bridge. By default the flag is off.
+ *
+ * @IFLA_BRPORT_LEARNING
+ *   Controls whether a given port will learn *source* MAC addresses from
+ *   received traffic or not. Also controls whether dynamic FDB entries
+ *   (which can also be added by software) will be refreshed by incoming
+ *   traffic. By default this flag is on.
+ *
+ * @IFLA_BRPORT_UNICAST_FLOOD
+ *   Controls whether unicast traffic for which there is no FDB entry will
+ *   be flooded towards this port. By default this flag is on.
+ *
+ * @IFLA_BRPORT_PROXYARP
+ *   Enable proxy ARP on this port.
+ *
+ * @IFLA_BRPORT_LEARNING_SYNC
+ *   Controls whether a given port will sync MAC addresses learned on device
+ *   port to bridge FDB.
+ *
+ * @IFLA_BRPORT_PROXYARP_WIFI
+ *   Enable proxy ARP on this port which meets extended requirements by
+ *   IEEE 802.11 and Hotspot 2.0 specifications.
+ *
+ * @IFLA_BRPORT_ROOT_ID
+ *
+ * @IFLA_BRPORT_BRIDGE_ID
+ *
+ * @IFLA_BRPORT_DESIGNATED_PORT
+ *
+ * @IFLA_BRPORT_DESIGNATED_COST
+ *
+ * @IFLA_BRPORT_ID
+ *
+ * @IFLA_BRPORT_NO
+ *
+ * @IFLA_BRPORT_TOPOLOGY_CHANGE_ACK
+ *
+ * @IFLA_BRPORT_CONFIG_PENDING
+ *
+ * @IFLA_BRPORT_MESSAGE_AGE_TIMER
+ *
+ * @IFLA_BRPORT_FORWARD_DELAY_TIMER
+ *
+ * @IFLA_BRPORT_HOLD_TIMER
+ *
+ * @IFLA_BRPORT_FLUSH
+ *   Flush bridge ports' fdb dynamic entries.
+ *
+ * @IFLA_BRPORT_MULTICAST_ROUTER
+ *   Configure the port's multicast router presence. A port with
+ *   a multicast router will receive all multicast traffic.
+ *   The valid values are:
+ *
+ *     * 0 disable multicast routers on this port
+ *     * 1 let the system detect the presence of routers (default)
+ *     * 2 permanently enable multicast traffic forwarding on this port
+ *     * 3 enable multicast routers temporarily on this port, not depending
+ *         on incoming queries.
+ *
+ * @IFLA_BRPORT_PAD
+ *
+ * @IFLA_BRPORT_MCAST_FLOOD
+ *   Controls whether a given port will flood multicast traffic for which
+ *   there is no MDB entry. By default this flag is on.
+ *
+ * @IFLA_BRPORT_MCAST_TO_UCAST
+ *   Controls whether a given port will replicate packets using unicast
+ *   instead of multicast. By default this flag is off.
+ *
+ *   This is done by copying the packet per host and changing the multicast
+ *   destination MAC to a unicast one accordingly.
+ *
+ *   *mcast_to_unicast* works on top of the multicast snooping feature of the
+ *   bridge. Which means unicast copies are only delivered to hosts which
+ *   are interested in unicast and signaled this via IGMP/MLD reports previously.
+ *
+ *   This feature is intended for interface types which have a more reliable
+ *   and/or efficient way to deliver unicast packets than broadcast ones
+ *   (e.g. WiFi).
+ *
+ *   However, it should only be enabled on interfaces where no IGMPv2/MLDv1
+ *   report suppression takes place. IGMP/MLD report suppression issue is
+ *   usually overcome by the network daemon (supplicant) enabling AP isolation
+ *   and by that separating all STAs.
+ *
+ *   Delivery of STA-to-STA IP multicast is made possible again by enabling
+ *   and utilizing the bridge hairpin mode, which considers the incoming port
+ *   as a potential outgoing port, too (see *BRIDGE_MODE_HAIRPIN* option).
+ *   Hairpin mode is performed after multicast snooping, therefore leading
+ *   to only deliver reports to STAs running a multicast router.
+ *
+ * @IFLA_BRPORT_VLAN_TUNNEL
+ *   Controls whether vlan to tunnel mapping is enabled on the port.
+ *   By default this flag is off.
+ *
+ * @IFLA_BRPORT_BCAST_FLOOD
+ *   Controls flooding of broadcast traffic on the given port. By default
+ *   this flag is on.
+ *
+ * @IFLA_BRPORT_GROUP_FWD_MASK
+ *   Set the group forward mask. This is a bitmask that is applied to
+ *   decide whether to forward incoming frames destined to link-local
+ *   addresses. The addresses of the form are 01:80:C2:00:00:0X (defaults
+ *   to 0, which means the bridge does not forward any link-local frames
+ *   coming on this port).
+ *
+ * @IFLA_BRPORT_NEIGH_SUPPRESS
+ *   Controls whether neighbor discovery (arp and nd) proxy and suppression
+ *   is enabled on the port. By default this flag is off.
+ *
+ * @IFLA_BRPORT_ISOLATED
+ *   Controls whether a given port will be isolated, which means it will be
+ *   able to communicate with non-isolated ports only. By default this
+ *   flag is off.
+ *
+ * @IFLA_BRPORT_BACKUP_PORT
+ *   Set a backup port. If the port loses carrier all traffic will be
+ *   redirected to the configured backup port. Set the value to 0 to disable
+ *   it.
+ *
+ * @IFLA_BRPORT_MRP_RING_OPEN
+ *
+ * @IFLA_BRPORT_MRP_IN_OPEN
+ *
+ * @IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT
+ *   The number of per-port EHT hosts limit. The default value is 512.
+ *   Setting to 0 is not allowed.
+ *
+ * @IFLA_BRPORT_MCAST_EHT_HOSTS_CNT
+ *   The current number of tracked hosts, read only.
+ *
+ * @IFLA_BRPORT_LOCKED
+ *   Controls whether a port will be locked, meaning that hosts behind the
+ *   port will not be able to communicate through the port unless an FDB
+ *   entry with the unit's MAC address is in the FDB. The common use case is
+ *   that hosts are allowed access through authentication with the IEEE 802.1X
+ *   protocol or based on whitelists. By default this flag is off.
+ *
+ *   Please note that secure 802.1X deployments should always use the
+ *   *BR_BOOLOPT_NO_LL_LEARN* flag, to not permit the bridge to populate its
+ *   FDB based on link-local (EAPOL) traffic received on the port.
+ *
+ * @IFLA_BRPORT_MAB
+ *   Controls whether a port will use MAC Authentication Bypass (MAB), a
+ *   technique through which select MAC addresses may be allowed on a locked
+ *   port, without using 802.1X authentication. Packets with an unknown source
+ *   MAC address generates a "locked" FDB entry on the incoming bridge port.
+ *   The common use case is for user space to react to these bridge FDB
+ *   notifications and optionally replace the locked FDB entry with a normal
+ *   one, allowing traffic to pass for whitelisted MAC addresses.
+ *
+ *   Setting this flag also requires *IFLA_BRPORT_LOCKED* and
+ *   *IFLA_BRPORT_LEARNING*. *IFLA_BRPORT_LOCKED* ensures that unauthorized
+ *   data packets are dropped, and *IFLA_BRPORT_LEARNING* allows the dynamic
+ *   FDB entries installed by user space (as replacements for the locked FDB
+ *   entries) to be refreshed and/or aged out.
+ *
+ * @IFLA_BRPORT_MCAST_N_GROUPS
+ *
+ * @IFLA_BRPORT_MCAST_MAX_GROUPS
+ *   Sets the maximum number of MDB entries that can be registered for a
+ *   given port. Attempts to register more MDB entries at the port than this
+ *   limit allows will be rejected, whether they are done through netlink
+ *   (e.g. the bridge tool), or IGMP or MLD membership reports. Setting a
+ *   limit of 0 disables the limit. The default value is 0.
+ *
+ * @IFLA_BRPORT_NEIGH_VLAN_SUPPRESS
+ *   Controls whether neighbor discovery (arp and nd) proxy and suppression is
+ *   enabled for a given port. By default this flag is off.
+ *
+ *   Note that this option only takes effect when *IFLA_BRPORT_NEIGH_SUPPRESS*
+ *   is enabled for a given port.
+ *
+ * @IFLA_BRPORT_BACKUP_NHID
+ *   The FDB nexthop object ID to attach to packets being redirected to a
+ *   backup port that has VLAN tunnel mapping enabled (via the
+ *   *IFLA_BRPORT_VLAN_TUNNEL* option). Setting a value of 0 (default) has
+ *   the effect of not attaching any ID.
+ */
 enum {
 	IFLA_BRPORT_UNSPEC,
 	IFLA_BRPORT_STATE,	/* Spanning tree state     */
@@ -769,6 +1292,19 @@ enum netkit_mode {
 	NETKIT_L3,
 };
 
+/* NETKIT_SCRUB_NONE leaves clearing skb->{mark,priority} up to
+ * the BPF program if attached. This also means the latter can
+ * consume the two fields if they were populated earlier.
+ *
+ * NETKIT_SCRUB_DEFAULT zeroes skb->{mark,priority} fields before
+ * invoking the attached BPF program when the peer device resides
+ * in a different network namespace. This is the default behavior.
+ */
+enum netkit_scrub {
+	NETKIT_SCRUB_NONE,
+	NETKIT_SCRUB_DEFAULT,
+};
+
 enum {
 	IFLA_NETKIT_UNSPEC,
 	IFLA_NETKIT_PEER_INFO,
@@ -776,6 +1312,8 @@ enum {
 	IFLA_NETKIT_POLICY,
 	IFLA_NETKIT_PEER_POLICY,
 	IFLA_NETKIT_MODE,
+	IFLA_NETKIT_SCRUB,
+	IFLA_NETKIT_PEER_SCRUB,
 	__IFLA_NETKIT_MAX,
 };
 #define IFLA_NETKIT_MAX	(__IFLA_NETKIT_MAX - 1)
@@ -854,6 +1392,7 @@ enum {
 	IFLA_VXLAN_DF,
 	IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */
 	IFLA_VXLAN_LOCALBYPASS,
+	IFLA_VXLAN_LABEL_POLICY, /* IPv6 flow label policy; ifla_vxlan_label_policy */
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
@@ -871,6 +1410,13 @@ enum ifla_vxlan_df {
 	VXLAN_DF_MAX = __VXLAN_DF_END - 1,
 };
 
+enum ifla_vxlan_label_policy {
+	VXLAN_LABEL_FIXED = 0,
+	VXLAN_LABEL_INHERIT = 1,
+	__VXLAN_LABEL_END,
+	VXLAN_LABEL_MAX = __VXLAN_LABEL_END - 1,
+};
+
 /* GENEVE section */
 enum {
 	IFLA_GENEVE_UNSPEC,
@@ -935,6 +1481,8 @@ enum {
 	IFLA_GTP_ROLE,
 	IFLA_GTP_CREATE_SOCKETS,
 	IFLA_GTP_RESTART_COUNT,
+	IFLA_GTP_LOCAL,
+	IFLA_GTP_LOCAL6,
 	__IFLA_GTP_MAX,
 };
 #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1)
@@ -1240,6 +1788,7 @@ enum {
 	IFLA_HSR_PROTOCOL,		/* Indicate different protocol than
 					 * HSR. For example PRP.
 					 */
+	IFLA_HSR_INTERLINK,		/* HSR interlink network device */
 	__IFLA_HSR_MAX,
 };
 
@@ -1417,7 +1966,9 @@ enum {
 
 enum {
 	IFLA_DSA_UNSPEC,
-	IFLA_DSA_MASTER,
+	IFLA_DSA_CONDUIT,
+	/* Deprecated, use IFLA_DSA_CONDUIT instead */
+	IFLA_DSA_MASTER = IFLA_DSA_CONDUIT,
 	__IFLA_DSA_MAX,
 };
 
-- 
2.51.0


From 716fa7dadf116ec4a27f56558b2a5bdd7e8decab Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 4 Oct 2024 12:13:35 +0200
Subject: [PATCH 15/16] selftests/bpf: Extend netkit tests to validate skb meta
 data

Add a small netkit test to validate skb mark and priority under the
default scrubbing as well as with mark and priority scrubbing off.

  # ./vmtest.sh -- ./test_progs -t netkit
  [...]
  ./test_progs -t netkit
  [    1.419662] tsc: Refined TSC clocksource calibration: 3407.993 MHz
  [    1.420151] clocksource: tsc: mask: 0xffffffffffffffff max_cycles: 0x311fcd52370, max_idle_ns: 440795242006 ns
  [    1.420897] clocksource: Switched to clocksource tsc
  [    1.447996] bpf_testmod: loading out-of-tree module taints kernel.
  [    1.448447] bpf_testmod: module verification failed: signature and/or required key missing - tainting kernel
  #357     tc_netkit_basic:OK
  #358     tc_netkit_device:OK
  #359     tc_netkit_multi_links:OK
  #360     tc_netkit_multi_opts:OK
  #361     tc_netkit_neigh_links:OK
  #362     tc_netkit_pkt_type:OK
  #363     tc_netkit_scrub:OK
  Summary: 7/0 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20241004101335.117711-5-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../selftests/bpf/prog_tests/tc_netkit.c      | 94 +++++++++++++++++--
 .../selftests/bpf/progs/test_tc_link.c        | 12 +++
 2 files changed, 97 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c
index b9135720024c..151a4210028f 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c
@@ -14,7 +14,9 @@
 #include "netlink_helpers.h"
 #include "tc_helpers.h"
 
-#define ICMP_ECHO 8
+#define MARK		42
+#define PRIO		0xeb9f
+#define ICMP_ECHO	8
 
 struct icmphdr {
 	__u8		type;
@@ -33,7 +35,7 @@ struct iplink_req {
 };
 
 static int create_netkit(int mode, int policy, int peer_policy, int *ifindex,
-			 bool same_netns)
+			 bool same_netns, int scrub, int peer_scrub)
 {
 	struct rtnl_handle rth = { .fd = -1 };
 	struct iplink_req req = {};
@@ -58,6 +60,8 @@ static int create_netkit(int mode, int policy, int peer_policy, int *ifindex,
 	data = addattr_nest(&req.n, sizeof(req), IFLA_INFO_DATA);
 	addattr32(&req.n, sizeof(req), IFLA_NETKIT_POLICY, policy);
 	addattr32(&req.n, sizeof(req), IFLA_NETKIT_PEER_POLICY, peer_policy);
+	addattr32(&req.n, sizeof(req), IFLA_NETKIT_SCRUB, scrub);
+	addattr32(&req.n, sizeof(req), IFLA_NETKIT_PEER_SCRUB, peer_scrub);
 	addattr32(&req.n, sizeof(req), IFLA_NETKIT_MODE, mode);
 	addattr_nest_end(&req.n, data);
 	addattr_nest_end(&req.n, linkinfo);
@@ -118,9 +122,9 @@ static void destroy_netkit(void)
 
 static int __send_icmp(__u32 dest)
 {
+	int sock, ret, mark = MARK, prio = PRIO;
 	struct sockaddr_in addr;
 	struct icmphdr icmp;
-	int sock, ret;
 
 	ret = write_sysctl("/proc/sys/net/ipv4/ping_group_range", "0 0");
 	if (!ASSERT_OK(ret, "write_sysctl(net.ipv4.ping_group_range)"))
@@ -135,6 +139,15 @@ static int __send_icmp(__u32 dest)
 	if (!ASSERT_OK(ret, "setsockopt(SO_BINDTODEVICE)"))
 		goto out;
 
+	ret = setsockopt(sock, SOL_SOCKET, SO_MARK, &mark, sizeof(mark));
+	if (!ASSERT_OK(ret, "setsockopt(SO_MARK)"))
+		goto out;
+
+	ret = setsockopt(sock, SOL_SOCKET, SO_PRIORITY,
+			 &prio, sizeof(prio));
+	if (!ASSERT_OK(ret, "setsockopt(SO_PRIORITY)"))
+		goto out;
+
 	memset(&addr, 0, sizeof(addr));
 	addr.sin_family = AF_INET;
 	addr.sin_addr.s_addr = htonl(dest);
@@ -171,7 +184,8 @@ void serial_test_tc_netkit_basic(void)
 	int err, ifindex;
 
 	err = create_netkit(NETKIT_L2, NETKIT_PASS, NETKIT_PASS,
-			    &ifindex, false);
+			    &ifindex, false, NETKIT_SCRUB_DEFAULT,
+			    NETKIT_SCRUB_DEFAULT);
 	if (err)
 		return;
 
@@ -285,7 +299,8 @@ static void serial_test_tc_netkit_multi_links_target(int mode, int target)
 	int err, ifindex;
 
 	err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS,
-			    &ifindex, false);
+			    &ifindex, false, NETKIT_SCRUB_DEFAULT,
+			    NETKIT_SCRUB_DEFAULT);
 	if (err)
 		return;
 
@@ -413,7 +428,8 @@ static void serial_test_tc_netkit_multi_opts_target(int mode, int target)
 	int err, ifindex;
 
 	err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS,
-			    &ifindex, false);
+			    &ifindex, false, NETKIT_SCRUB_DEFAULT,
+			    NETKIT_SCRUB_DEFAULT);
 	if (err)
 		return;
 
@@ -527,7 +543,8 @@ void serial_test_tc_netkit_device(void)
 	int err, ifindex, ifindex2;
 
 	err = create_netkit(NETKIT_L3, NETKIT_PASS, NETKIT_PASS,
-			    &ifindex, true);
+			    &ifindex, true, NETKIT_SCRUB_DEFAULT,
+			    NETKIT_SCRUB_DEFAULT);
 	if (err)
 		return;
 
@@ -638,7 +655,8 @@ static void serial_test_tc_netkit_neigh_links_target(int mode, int target)
 	int err, ifindex;
 
 	err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS,
-			    &ifindex, false);
+			    &ifindex, false, NETKIT_SCRUB_DEFAULT,
+			    NETKIT_SCRUB_DEFAULT);
 	if (err)
 		return;
 
@@ -715,7 +733,8 @@ static void serial_test_tc_netkit_pkt_type_mode(int mode)
 	struct bpf_link *link;
 
 	err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS,
-			    &ifindex, true);
+			    &ifindex, true, NETKIT_SCRUB_DEFAULT,
+			    NETKIT_SCRUB_DEFAULT);
 	if (err)
 		return;
 
@@ -779,3 +798,60 @@ void serial_test_tc_netkit_pkt_type(void)
 	serial_test_tc_netkit_pkt_type_mode(NETKIT_L2);
 	serial_test_tc_netkit_pkt_type_mode(NETKIT_L3);
 }
+
+static void serial_test_tc_netkit_scrub_type(int scrub)
+{
+	LIBBPF_OPTS(bpf_netkit_opts, optl);
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err, ifindex;
+
+	err = create_netkit(NETKIT_L2, NETKIT_PASS, NETKIT_PASS,
+			    &ifindex, false, scrub, scrub);
+	if (err)
+		return;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc8,
+		  BPF_NETKIT_PRIMARY), 0, "tc8_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
+
+	ASSERT_EQ(skel->bss->seen_tc8, false, "seen_tc8");
+
+	link = bpf_program__attach_netkit(skel->progs.tc8, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc8 = link;
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
+
+	ASSERT_EQ(skel->bss->seen_tc8, true, "seen_tc8");
+	ASSERT_EQ(skel->bss->mark, scrub == NETKIT_SCRUB_NONE ? MARK : 0, "mark");
+	ASSERT_EQ(skel->bss->prio, scrub == NETKIT_SCRUB_NONE ? PRIO : 0, "prio");
+cleanup:
+	test_tc_link__destroy(skel);
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
+	destroy_netkit();
+}
+
+void serial_test_tc_netkit_scrub(void)
+{
+	serial_test_tc_netkit_scrub_type(NETKIT_SCRUB_DEFAULT);
+	serial_test_tc_netkit_scrub_type(NETKIT_SCRUB_NONE);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_tc_link.c b/tools/testing/selftests/bpf/progs/test_tc_link.c
index ab3eae3d6af8..10d825928499 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_link.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_link.c
@@ -18,6 +18,7 @@ bool seen_tc4;
 bool seen_tc5;
 bool seen_tc6;
 bool seen_tc7;
+bool seen_tc8;
 
 bool set_type;
 
@@ -25,6 +26,8 @@ bool seen_eth;
 bool seen_host;
 bool seen_mcast;
 
+int mark, prio;
+
 SEC("tc/ingress")
 int tc1(struct __sk_buff *skb)
 {
@@ -100,3 +103,12 @@ out:
 	seen_tc7 = true;
 	return TCX_PASS;
 }
+
+SEC("tc/egress")
+int tc8(struct __sk_buff *skb)
+{
+	seen_tc8 = true;
+	mark = skb->mark;
+	prio = skb->priority;
+	return TCX_PASS;
+}
-- 
2.51.0


From bc9b3fb827fceec4e05564d6e668280f4470ab5b Mon Sep 17 00:00:00 2001
From: =?utf8?q?Alexis=20Lothor=C3=A9=20=28eBPF=20Foundation=29?=
 <alexis.lothore@bootlin.com>
Date: Tue, 8 Oct 2024 16:50:57 +0200
Subject: [PATCH 16/16] selftests/bpf: add missing header include for htons
MIME-Version: 1.0
Content-Type: text/plain; charset=utf8
Content-Transfer-Encoding: 8bit

Including the network_helpers.h header in tests can lead to the following
build error:

./network_helpers.h: In function ‘csum_tcpudp_magic’:
./network_helpers.h:116:14: error: implicit declaration of function \
  ‘htons’ [-Werror=implicit-function-declaration]
  116 |         s += htons(proto + len);

The error is avoided in many cases thanks to some other headers included
earlier and bringing in arpa/inet.h (ie: test_progs.h).

Make sure that test_progs build success does not depend on header ordering
by adding the missing header include in network_helpers.h

Fixes: f6642de0c3e9 ("selftests/bpf: Add csum helpers")
Signed-off-by: Alexis Lothoré (eBPF Foundation) <alexis.lothore@bootlin.com>
Link: https://lore.kernel.org/r/20241008-network_helpers_fix-v1-1-2c2ae03df7ef@bootlin.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/network_helpers.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
index c72c16e1aff8..5764155b6d25 100644
--- a/tools/testing/selftests/bpf/network_helpers.h
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __NETWORK_HELPERS_H
 #define __NETWORK_HELPERS_H
+#include <arpa/inet.h>
 #include <sys/socket.h>
 #include <sys/types.h>
 #include <linux/types.h>
-- 
2.51.0