Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf

Pablo Neira Ayuso says:

====================
Netfilter fixes for net

1) Remove leftovers from flowtable modules, from Geert Uytterhoeven.

2) Missing refcount increment of conntrack template in nft_ct,
   from Florian Westphal.

3) Reduce nft_zone selftest time, also from Florian.

4) Add selftest to cover stateless NAT on fragments, from Florian Westphal.

5) Do not set net_device when for reject packets from the bridge path,
   from Phil Sutter.

6) Cancel register tracking info on nft_byteorder operations.

7) Extend nft_concat_range selftest to cover set reload with no elements,
   from Florian Westphal.

8) Remove useless update of pointer in chain blob builder, reported
   by kbuild test robot.

* git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf:
  netfilter: nf_tables: remove assignment with no effect in chain blob builder
  selftests: nft_concat_range: add test for reload with no element add/del
  netfilter: nft_byteorder: track register operations
  netfilter: nft_reject_bridge: Fix for missing reply from prerouting
  selftests: netfilter: check stateless nat udp checksum fixup
  selftests: netfilter: reduce zone stress test running time
  netfilter: nft_ct: fix use after free when attaching zone template
  netfilter: Remove flowtable relics
====================

Link: https://lore.kernel.org/r/20220127235235.656931-1-pablo@netfilter.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

11 files changed, 249 insertions, 24 deletions

diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index eba0efe64d05..fbf858ddec35 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -49,7 +49,7 @@ static void nft_reject_br_send_v4_tcp_reset(struct net *net,
 {
 	struct sk_buff *nskb;
 
-	nskb = nf_reject_skb_v4_tcp_reset(net, oldskb, dev, hook);
+	nskb = nf_reject_skb_v4_tcp_reset(net, oldskb, NULL, hook);
 	if (!nskb)
 		return;
 
@@ -65,7 +65,7 @@ static void nft_reject_br_send_v4_unreach(struct net *net,
 {
 	struct sk_buff *nskb;
 
-	nskb = nf_reject_skb_v4_unreach(net, oldskb, dev, hook, code);
+	nskb = nf_reject_skb_v4_unreach(net, oldskb, NULL, hook, code);
 	if (!nskb)
 		return;
 
@@ -81,7 +81,7 @@ static void nft_reject_br_send_v6_tcp_reset(struct net *net,
 {
 	struct sk_buff *nskb;
 
-	nskb = nf_reject_skb_v6_tcp_reset(net, oldskb, dev, hook);
+	nskb = nf_reject_skb_v6_tcp_reset(net, oldskb, NULL, hook);
 	if (!nskb)
 		return;
 
@@ -98,7 +98,7 @@ static void nft_reject_br_send_v6_unreach(struct net *net,
 {
 	struct sk_buff *nskb;
 
-	nskb = nf_reject_skb_v6_unreach(net, oldskb, dev, hook, code);
+	nskb = nf_reject_skb_v6_unreach(net, oldskb, NULL, hook, code);
 	if (!nskb)
 		return;
 
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 67087f95579f..aab384126f61 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -58,10 +58,6 @@ config NF_TABLES_ARP
 
 endif # NF_TABLES
 
-config NF_FLOW_TABLE_IPV4
-	tristate
-	select NF_FLOW_TABLE_INET
-
 config NF_DUP_IPV4
 	tristate "Netfilter IPv4 packet duplication to alternate destination"
 	depends on !NF_CONNTRACK || NF_CONNTRACK
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 97d3d1b36dbc..0ba62f4868f9 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -47,10 +47,6 @@ config NFT_FIB_IPV6
 endif # NF_TABLES_IPV6
 endif # NF_TABLES
 
-config NF_FLOW_TABLE_IPV6
-	tristate
-	select NF_FLOW_TABLE_INET
-
 config NF_DUP_IPV6
 	tristate "Netfilter IPv6 packet duplication to alternate destination"
 	depends on !NF_CONNTRACK || NF_CONNTRACK
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index b85383606df7..b8d6dc9aeeb6 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -28,9 +28,6 @@ obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o
 obj-$(CONFIG_NFT_DUP_IPV6) += nft_dup_ipv6.o
 obj-$(CONFIG_NFT_FIB_IPV6) += nft_fib_ipv6.o
 
-# flow table support
-obj-$(CONFIG_NF_FLOW_TABLE_IPV6) += nf_flow_table_ipv6.o
-
 # matches
 obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o
 obj-$(CONFIG_IP6_NF_MATCH_EUI64) += ip6t_eui64.o
diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c
deleted file mode 100644
index e69de29bb2d1..000000000000
--- a/net/ipv6/netfilter/nf_flow_table_ipv6.c
+++ /dev/null
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index cf454f8ca2b0..5fa16990da95 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2011,7 +2011,6 @@ static void nft_last_rule(struct nft_rule_blob *blob, const void *ptr)
 
 	prule = (struct nft_rule_dp *)ptr;
 	prule->is_last = 1;
-	ptr += offsetof(struct nft_rule_dp, data);
 	/* blob size does not include the trailer rule */
 }
 
diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c
index 9d5947ab8d4e..e646e9ee4a98 100644
--- a/net/netfilter/nft_byteorder.c
+++ b/net/netfilter/nft_byteorder.c
@@ -167,12 +167,24 @@ nla_put_failure:
 	return -1;
 }
 
+static bool nft_byteorder_reduce(struct nft_regs_track *track,
+				 const struct nft_expr *expr)
+{
+	struct nft_byteorder *priv = nft_expr_priv(expr);
+
+	track->regs[priv->dreg].selector = NULL;
+	track->regs[priv->dreg].bitwise = NULL;
+
+	return false;
+}
+
 static const struct nft_expr_ops nft_byteorder_ops = {
 	.type		= &nft_byteorder_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_byteorder)),
 	.eval		= nft_byteorder_eval,
 	.init		= nft_byteorder_init,
 	.dump		= nft_byteorder_dump,
+	.reduce		= nft_byteorder_reduce,
 };
 
 struct nft_expr_type nft_byteorder_type __read_mostly = {
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 518d96c8c247..5adf8bb628a8 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -260,9 +260,12 @@ static void nft_ct_set_zone_eval(const struct nft_expr *expr,
 	ct = this_cpu_read(nft_ct_pcpu_template);
 
 	if (likely(refcount_read(&ct->ct_general.use) == 1)) {
+		refcount_inc(&ct->ct_general.use);
 		nf_ct_zone_add(ct, &zone);
 	} else {
-		/* previous skb got queued to userspace */
+		/* previous skb got queued to userspace, allocate temporary
+		 * one until percpu template can be reused.
+		 */
 		ct = nf_ct_tmpl_alloc(nft_net(pkt), &zone, GFP_ATOMIC);
 		if (!ct) {
 			regs->verdict.code = NF_DROP;
diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh
index ed61f6cab60f..df322e47a54f 100755
--- a/tools/testing/selftests/netfilter/nft_concat_range.sh
+++ b/tools/testing/selftests/netfilter/nft_concat_range.sh
@@ -27,7 +27,7 @@ TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto
        net6_port_net6_port net_port_mac_proto_net"
 
 # Reported bugs, also described by TYPE_ variables below
-BUGS="flush_remove_add"
+BUGS="flush_remove_add reload"
 
 # List of possible paths to pktgen script from kernel tree for performance tests
 PKTGEN_SCRIPT_PATHS="
@@ -354,6 +354,23 @@ TYPE_flush_remove_add="
 display		Add two elements, flush, re-add
 "
 
+TYPE_reload="
+display		net,mac with reload
+type_spec	ipv4_addr . ether_addr
+chain_spec	ip daddr . ether saddr
+dst		addr4
+src		mac
+start		1
+count		1
+src_delta	2000
+tools		sendip nc bash
+proto		udp
+
+race_repeat	0
+
+perf_duration	0
+"
+
 # Set template for all tests, types and rules are filled in depending on test
 set_template='
 flush ruleset
@@ -1473,6 +1490,59 @@ test_bug_flush_remove_add() {
 	nft flush ruleset
 }
 
+# - add ranged element, check that packets match it
+# - reload the set, check packets still match
+test_bug_reload() {
+	setup veth send_"${proto}" set || return ${KSELFTEST_SKIP}
+	rstart=${start}
+
+	range_size=1
+	for i in $(seq "${start}" $((start + count))); do
+		end=$((start + range_size))
+
+		# Avoid negative or zero-sized port ranges
+		if [ $((end / 65534)) -gt $((start / 65534)) ]; then
+			start=${end}
+			end=$((end + 1))
+		fi
+		srcstart=$((start + src_delta))
+		srcend=$((end + src_delta))
+
+		add "$(format)" || return 1
+		range_size=$((range_size + 1))
+		start=$((end + range_size))
+	done
+
+	# check kernel does allocate pcpu sctrach map
+	# for reload with no elemet add/delete
+	( echo flush set inet filter test ;
+	  nft list set inet filter test ) | nft -f -
+
+	start=${rstart}
+	range_size=1
+
+	for i in $(seq "${start}" $((start + count))); do
+		end=$((start + range_size))
+
+		# Avoid negative or zero-sized port ranges
+		if [ $((end / 65534)) -gt $((start / 65534)) ]; then
+			start=${end}
+			end=$((end + 1))
+		fi
+		srcstart=$((start + src_delta))
+		srcend=$((end + src_delta))
+
+		for j in $(seq ${start} $((range_size / 2 + 1)) ${end}); do
+			send_match "${j}" $((j + src_delta)) || return 1
+		done
+
+		range_size=$((range_size + 1))
+		start=$((end + range_size))
+	done
+
+	nft flush ruleset
+}
+
 test_reported_issues() {
 	eval test_bug_"${subtest}"
 }
diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh
index 349a319a9e51..79fe627b9e81 100755
--- a/tools/testing/selftests/netfilter/nft_nat.sh
+++ b/tools/testing/selftests/netfilter/nft_nat.sh
@@ -899,6 +899,144 @@ EOF
 	ip netns exec "$ns0" nft delete table $family nat
 }
 
+test_stateless_nat_ip()
+{
+	local lret=0
+
+	ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
+	ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+
+	ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+	if [ $? -ne 0 ] ; then
+		echo "ERROR: cannot ping $ns1 from $ns2 before loading stateless rules"
+		return 1
+	fi
+
+ip netns exec "$ns0" nft -f /dev/stdin <<EOF
+table ip stateless {
+	map xlate_in {
+		typeof meta iifname . ip saddr . ip daddr : ip daddr
+		elements = {
+			"veth1" . 10.0.2.99 . 10.0.1.99 : 10.0.2.2,
+		}
+	}
+	map xlate_out {
+		typeof meta iifname . ip saddr . ip daddr : ip daddr
+		elements = {
+			"veth0" . 10.0.1.99 . 10.0.2.2 : 10.0.2.99
+		}
+	}
+
+	chain prerouting {
+		type filter hook prerouting priority -400; policy accept;
+		ip saddr set meta iifname . ip saddr . ip daddr map @xlate_in
+		ip daddr set meta iifname . ip saddr . ip daddr map @xlate_out
+	}
+}
+EOF
+	if [ $? -ne 0 ]; then
+		echo "SKIP: Could not add ip statless rules"
+		return $ksft_skip
+	fi
+
+	reset_counters
+
+	ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+	if [ $? -ne 0 ] ; then
+		echo "ERROR: cannot ping $ns1 from $ns2 with stateless rules"
+		lret=1
+	fi
+
+	# ns1 should have seen packets from .2.2, due to stateless rewrite.
+	expect="packets 1 bytes 84"
+	cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0insl | grep -q "$expect")
+	if [ $? -ne 0 ]; then
+		bad_counter "$ns1" ns0insl "$expect" "test_stateless 1"
+		lret=1
+	fi
+
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter "$ns2" ns1$dir "$expect" "test_stateless 2"
+			lret=1
+		fi
+	done
+
+	# ns1 should not have seen packets from ns2, due to masquerade
+	expect="packets 0 bytes 0"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter "$ns1" ns0$dir "$expect" "test_stateless 3"
+			lret=1
+		fi
+
+		cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter "$ns0" ns1$dir "$expect" "test_stateless 4"
+			lret=1
+		fi
+	done
+
+	reset_counters
+
+	socat -h > /dev/null 2>&1
+	if [ $? -ne 0 ];then
+		echo "SKIP: Could not run stateless nat frag test without socat tool"
+		if [ $lret -eq 0 ]; then
+			return $ksft_skip
+		fi
+
+		ip netns exec "$ns0" nft delete table ip stateless
+		return $lret
+	fi
+
+	local tmpfile=$(mktemp)
+	dd if=/dev/urandom of=$tmpfile bs=4096 count=1 2>/dev/null
+
+	local outfile=$(mktemp)
+	ip netns exec "$ns1" timeout 3 socat -u UDP4-RECV:4233 OPEN:$outfile < /dev/null &
+	sc_r=$!
+
+	sleep 1
+	# re-do with large ping -> ip fragmentation
+	ip netns exec "$ns2" timeout 3 socat - UDP4-SENDTO:"10.0.1.99:4233" < "$tmpfile" > /dev/null
+	if [ $? -ne 0 ] ; then
+		echo "ERROR: failed to test udp $ns1 to $ns2 with stateless ip nat" 1>&2
+		lret=1
+	fi
+
+	wait
+
+	cmp "$tmpfile" "$outfile"
+	if [ $? -ne 0 ]; then
+		ls -l "$tmpfile" "$outfile"
+		echo "ERROR: in and output file mismatch when checking udp with stateless nat" 1>&2
+		lret=1
+	fi
+
+	rm -f "$tmpfile" "$outfile"
+
+	# ns1 should have seen packets from 2.2, due to stateless rewrite.
+	expect="packets 3 bytes 4164"
+	cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0insl | grep -q "$expect")
+	if [ $? -ne 0 ]; then
+		bad_counter "$ns1" ns0insl "$expect" "test_stateless 5"
+		lret=1
+	fi
+
+	ip netns exec "$ns0" nft delete table ip stateless
+	if [ $? -ne 0 ]; then
+		echo "ERROR: Could not delete table ip stateless" 1>&2
+		lret=1
+	fi
+
+	test $lret -eq 0 && echo "PASS: IP statless for $ns2"
+
+	return $lret
+}
+
 # ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99
 for i in 0 1 2; do
 ip netns exec ns$i-$sfx nft -f /dev/stdin <<EOF
@@ -965,6 +1103,19 @@ table inet filter {
 EOF
 done
 
+# special case for stateless nat check, counter needs to
+# be done before (input) ip defragmentation
+ip netns exec ns1-$sfx nft -f /dev/stdin <<EOF
+table inet filter {
+	counter ns0insl {}
+
+	chain pre {
+		type filter hook prerouting priority -400; policy accept;
+		ip saddr 10.0.2.2 counter name "ns0insl"
+	}
+}
+EOF
+
 sleep 3
 # test basic connectivity
 for i in 1 2; do
@@ -1019,6 +1170,7 @@ $test_inet_nat && test_redirect inet
 $test_inet_nat && test_redirect6 inet
 
 test_port_shadowing
+test_stateless_nat_ip
 
 if [ $ret -ne 0 ];then
 	echo -n "FAIL: "
diff --git a/tools/testing/selftests/netfilter/nft_zones_many.sh b/tools/testing/selftests/netfilter/nft_zones_many.sh
index 04633119b29a..5a8db0b48928 100755
--- a/tools/testing/selftests/netfilter/nft_zones_many.sh
+++ b/tools/testing/selftests/netfilter/nft_zones_many.sh
@@ -9,7 +9,7 @@ ns="ns-$sfx"
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
 
-zones=20000
+zones=2000
 have_ct_tool=0
 ret=0
 
@@ -75,10 +75,10 @@ EOF
 
 	while [ $i -lt $max_zones ]; do
 		local start=$(date +%s%3N)
-		i=$((i + 10000))
+		i=$((i + 1000))
 		j=$((j + 1))
 		# nft rule in output places each packet in a different zone.
-		dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" socat STDIN UDP:127.0.0.1:12345,sourceport=12345
+		dd if=/dev/zero of=/dev/stdout bs=8k count=1000 2>/dev/null | ip netns exec "$ns" socat STDIN UDP:127.0.0.1:12345,sourceport=12345
 		if [ $? -ne 0 ] ;then
 			ret=1
 			break
@@ -86,7 +86,7 @@ EOF
 
 		stop=$(date +%s%3N)
 		local duration=$((stop-start))
-		echo "PASS: added 10000 entries in $duration ms (now $i total, loop $j)"
+		echo "PASS: added 1000 entries in $duration ms (now $i total, loop $j)"
 	done
 
 	if [ $have_ct_tool -eq 1 ]; then
@@ -128,11 +128,11 @@ test_conntrack_tool() {
 			break
 		fi
 
-		if [ $((i%10000)) -eq 0 ];then
+		if [ $((i%1000)) -eq 0 ];then
 			stop=$(date +%s%3N)
 
 			local duration=$((stop-start))
-			echo "PASS: added 10000 entries in $duration ms (now $i total)"
+			echo "PASS: added 1000 entries in $duration ms (now $i total)"
 			start=$stop
 		fi
 	done