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

Pablo Neira Ayuso says:

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

1) Fix bogus compilter warning in nfnetlink_queue, from Florian Westphal.

2) Don't run conntrack on vrf with !dflt qdisc, from Nicolas Dichtel.

3) Fix nft_pipapo bucket load in AVX2 lookup routine for six 8-bit
   groups, from Stefano Brivio.

4) Break rule evaluation on malformed TCP options.

5) Use socat instead of nc in selftests/netfilter/nft_zones_many.sh,
   also from Florian

6) Fix KCSAN data-race in conntrack timeout updates, from Eric Dumazet.

* git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf:
  netfilter: conntrack: annotate data-races around ct->timeout
  selftests: netfilter: switch zone stress to socat
  netfilter: nft_exthdr: break evaluation if setting TCP option fails
  selftests: netfilter: Add correctness test for mac,net set type
  nft_set_pipapo: Fix bucket load in AVX2 lookup routine for six 8-bit groups
  vrf: don't run conntrack on vrf with !dflt qdisc
  netfilter: nfnetlink_queue: silence bogus compiler warning
====================

Link: https://lore.kernel.org/r/20211209000847.102598-1-pablo@netfilter.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

11 files changed, 82 insertions, 32 deletions

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 131c745dc701..b2242a082431 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -770,8 +770,6 @@ static struct sk_buff *vrf_ip6_out_direct(struct net_device *vrf_dev,
 
 	skb->dev = vrf_dev;
 
-	vrf_nf_set_untracked(skb);
-
 	err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk,
 		      skb, NULL, vrf_dev, vrf_ip6_out_direct_finish);
 
@@ -792,6 +790,8 @@ static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev,
 	if (rt6_need_strict(&ipv6_hdr(skb)->daddr))
 		return skb;
 
+	vrf_nf_set_untracked(skb);
+
 	if (qdisc_tx_is_default(vrf_dev) ||
 	    IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED)
 		return vrf_ip6_out_direct(vrf_dev, sk, skb);
@@ -1000,8 +1000,6 @@ static struct sk_buff *vrf_ip_out_direct(struct net_device *vrf_dev,
 
 	skb->dev = vrf_dev;
 
-	vrf_nf_set_untracked(skb);
-
 	err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk,
 		      skb, NULL, vrf_dev, vrf_ip_out_direct_finish);
 
@@ -1023,6 +1021,8 @@ static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev,
 	    ipv4_is_lbcast(ip_hdr(skb)->daddr))
 		return skb;
 
+	vrf_nf_set_untracked(skb);
+
 	if (qdisc_tx_is_default(vrf_dev) ||
 	    IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED)
 		return vrf_ip_out_direct(vrf_dev, sk, skb);
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index cc663c68ddc4..d24b0a34c8f0 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -276,14 +276,14 @@ static inline bool nf_is_loopback_packet(const struct sk_buff *skb)
 /* jiffies until ct expires, 0 if already expired */
 static inline unsigned long nf_ct_expires(const struct nf_conn *ct)
 {
-	s32 timeout = ct->timeout - nfct_time_stamp;
+	s32 timeout = READ_ONCE(ct->timeout) - nfct_time_stamp;
 
 	return timeout > 0 ? timeout : 0;
 }
 
 static inline bool nf_ct_is_expired(const struct nf_conn *ct)
 {
-	return (__s32)(ct->timeout - nfct_time_stamp) <= 0;
+	return (__s32)(READ_ONCE(ct->timeout) - nfct_time_stamp) <= 0;
 }
 
 /* use after obtaining a reference count */
@@ -302,7 +302,7 @@ static inline bool nf_ct_should_gc(const struct nf_conn *ct)
 static inline void nf_ct_offload_timeout(struct nf_conn *ct)
 {
 	if (nf_ct_expires(ct) < NF_CT_DAY / 2)
-		ct->timeout = nfct_time_stamp + NF_CT_DAY;
+		WRITE_ONCE(ct->timeout, nfct_time_stamp + NF_CT_DAY);
 }
 
 struct kernel_param;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 770a63103c7a..4712a90a1820 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -684,7 +684,7 @@ bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report)
 
 	tstamp = nf_conn_tstamp_find(ct);
 	if (tstamp) {
-		s32 timeout = ct->timeout - nfct_time_stamp;
+		s32 timeout = READ_ONCE(ct->timeout) - nfct_time_stamp;
 
 		tstamp->stop = ktime_get_real_ns();
 		if (timeout < 0)
@@ -1036,7 +1036,7 @@ static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx)
 	}
 
 	/* We want the clashing entry to go away real soon: 1 second timeout. */
-	loser_ct->timeout = nfct_time_stamp + HZ;
+	WRITE_ONCE(loser_ct->timeout, nfct_time_stamp + HZ);
 
 	/* IPS_NAT_CLASH removes the entry automatically on the first
 	 * reply.  Also prevents UDP tracker from moving the entry to
@@ -1560,7 +1560,7 @@ __nf_conntrack_alloc(struct net *net,
 	/* save hash for reusing when confirming */
 	*(unsigned long *)(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev) = hash;
 	ct->status = 0;
-	ct->timeout = 0;
+	WRITE_ONCE(ct->timeout, 0);
 	write_pnet(&ct->ct_net, net);
 	memset(&ct->__nfct_init_offset, 0,
 	       offsetof(struct nf_conn, proto) -
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index c7708bde057c..81d03acf68d4 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1998,7 +1998,7 @@ static int ctnetlink_change_timeout(struct nf_conn *ct,
 
 	if (timeout > INT_MAX)
 		timeout = INT_MAX;
-	ct->timeout = nfct_time_stamp + (u32)timeout;
+	WRITE_ONCE(ct->timeout, nfct_time_stamp + (u32)timeout);
 
 	if (test_bit(IPS_DYING_BIT, &ct->status))
 		return -ETIME;
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 87a7388b6c89..ed37bb9b4e58 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -201,8 +201,8 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct)
 	if (timeout < 0)
 		timeout = 0;
 
-	if (nf_flow_timeout_delta(ct->timeout) > (__s32)timeout)
-		ct->timeout = nfct_time_stamp + timeout;
+	if (nf_flow_timeout_delta(READ_ONCE(ct->timeout)) > (__s32)timeout)
+		WRITE_ONCE(ct->timeout, nfct_time_stamp + timeout);
 }
 
 static void flow_offload_fixup_ct_state(struct nf_conn *ct)
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 4acc4b8e9fe5..5837e8efc9c2 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -387,7 +387,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 	struct net_device *indev;
 	struct net_device *outdev;
 	struct nf_conn *ct = NULL;
-	enum ip_conntrack_info ctinfo;
+	enum ip_conntrack_info ctinfo = 0;
 	struct nfnl_ct_hook *nfnl_ct;
 	bool csum_verify;
 	char *secdata = NULL;
diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index af4ee874a067..dbe1f2e7dd9e 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -236,7 +236,7 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr,
 
 	tcph = nft_tcp_header_pointer(pkt, sizeof(buff), buff, &tcphdr_len);
 	if (!tcph)
-		return;
+		goto err;
 
 	opt = (u8 *)tcph;
 	for (i = sizeof(*tcph); i < tcphdr_len - 1; i += optl) {
@@ -251,16 +251,16 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr,
 			continue;
 
 		if (i + optl > tcphdr_len || priv->len + priv->offset > optl)
-			return;
+			goto err;
 
 		if (skb_ensure_writable(pkt->skb,
 					nft_thoff(pkt) + i + priv->len))
-			return;
+			goto err;
 
 		tcph = nft_tcp_header_pointer(pkt, sizeof(buff), buff,
 					      &tcphdr_len);
 		if (!tcph)
-			return;
+			goto err;
 
 		offset = i + priv->offset;
 
@@ -303,6 +303,9 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr,
 
 		return;
 	}
+	return;
+err:
+	regs->verdict.code = NFT_BREAK;
 }
 
 static void nft_exthdr_sctp_eval(const struct nft_expr *expr,
diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index e517663e0cd1..6f4116e72958 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -886,7 +886,7 @@ static int nft_pipapo_avx2_lookup_8b_6(unsigned long *map, unsigned long *fill,
 			NFT_PIPAPO_AVX2_BUCKET_LOAD8(4,  lt, 4, pkt[4], bsize);
 
 			NFT_PIPAPO_AVX2_AND(5, 0, 1);
-			NFT_PIPAPO_AVX2_BUCKET_LOAD8(6,  lt, 6, pkt[5], bsize);
+			NFT_PIPAPO_AVX2_BUCKET_LOAD8(6,  lt, 5, pkt[5], bsize);
 			NFT_PIPAPO_AVX2_AND(7, 2, 3);
 
 			/* Stall */
diff --git a/tools/testing/selftests/netfilter/conntrack_vrf.sh b/tools/testing/selftests/netfilter/conntrack_vrf.sh
index 91f3ef0f1192..8b5ea9234588 100755
--- a/tools/testing/selftests/netfilter/conntrack_vrf.sh
+++ b/tools/testing/selftests/netfilter/conntrack_vrf.sh
@@ -150,11 +150,27 @@ EOF
 # oifname is the vrf device.
 test_masquerade_vrf()
 {
+	local qdisc=$1
+
+	if [ "$qdisc" != "default" ]; then
+		tc -net $ns0 qdisc add dev tvrf root $qdisc
+	fi
+
 	ip netns exec $ns0 conntrack -F 2>/dev/null
 
 ip netns exec $ns0 nft -f - <<EOF
 flush ruleset
 table ip nat {
+	chain rawout {
+		type filter hook output priority raw;
+
+		oif tvrf ct state untracked counter
+	}
+	chain postrouting2 {
+		type filter hook postrouting priority mangle;
+
+		oif tvrf ct state untracked counter
+	}
 	chain postrouting {
 		type nat hook postrouting priority 0;
 		# NB: masquerade should always be combined with 'oif(name) bla',
@@ -171,13 +187,18 @@ EOF
 	fi
 
 	# must also check that nat table was evaluated on second (lower device) iteration.
-	ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2'
+	ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2' &&
+	ip netns exec $ns0 nft list table ip nat |grep -q 'untracked counter packets [1-9]'
 	if [ $? -eq 0 ]; then
-		echo "PASS: iperf3 connect with masquerade + sport rewrite on vrf device"
+		echo "PASS: iperf3 connect with masquerade + sport rewrite on vrf device ($qdisc qdisc)"
 	else
-		echo "FAIL: vrf masq rule has unexpected counter value"
+		echo "FAIL: vrf rules have unexpected counter value"
 		ret=1
 	fi
+
+	if [ "$qdisc" != "default" ]; then
+		tc -net $ns0 qdisc del dev tvrf root
+	fi
 }
 
 # add masq rule that gets evaluated w. outif set to veth device.
@@ -213,7 +234,8 @@ EOF
 }
 
 test_ct_zone_in
-test_masquerade_vrf
+test_masquerade_vrf "default"
+test_masquerade_vrf "pfifo"
 test_masquerade_veth
 
 exit $ret
diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh
index 5a4938d6dcf2..ed61f6cab60f 100755
--- a/tools/testing/selftests/netfilter/nft_concat_range.sh
+++ b/tools/testing/selftests/netfilter/nft_concat_range.sh
@@ -23,8 +23,8 @@ TESTS="reported_issues correctness concurrency timeout"
 
 # Set types, defined by TYPE_ variables below
 TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto
-       net_port_net net_mac net_mac_icmp net6_mac_icmp net6_port_net6_port
-       net_port_mac_proto_net"
+       net_port_net net_mac mac_net net_mac_icmp net6_mac_icmp
+       net6_port_net6_port net_port_mac_proto_net"
 
 # Reported bugs, also described by TYPE_ variables below
 BUGS="flush_remove_add"
@@ -277,6 +277,23 @@ perf_entries	1000
 perf_proto	ipv4
 "
 
+TYPE_mac_net="
+display		mac,net
+type_spec	ether_addr . ipv4_addr
+chain_spec	ether saddr . ip saddr
+dst		 
+src		mac addr4
+start		1
+count		5
+src_delta	2000
+tools		sendip nc bash
+proto		udp
+
+race_repeat	0
+
+perf_duration	0
+"
+
 TYPE_net_mac_icmp="
 display		net,mac - ICMP
 type_spec	ipv4_addr . ether_addr
@@ -984,7 +1001,8 @@ format() {
 		fi
 	done
 	for f in ${src}; do
-		__expr="${__expr} . "
+		[ "${__expr}" != "{ " ] && __expr="${__expr} . "
+
 		__start="$(eval format_"${f}" "${srcstart}")"
 		__end="$(eval format_"${f}" "${srcend}")"
 
diff --git a/tools/testing/selftests/netfilter/nft_zones_many.sh b/tools/testing/selftests/netfilter/nft_zones_many.sh
index ac646376eb01..04633119b29a 100755
--- a/tools/testing/selftests/netfilter/nft_zones_many.sh
+++ b/tools/testing/selftests/netfilter/nft_zones_many.sh
@@ -18,11 +18,17 @@ cleanup()
 	ip netns del $ns
 }
 
-ip netns add $ns
-if [ $? -ne 0 ];then
-	echo "SKIP: Could not create net namespace $gw"
-	exit $ksft_skip
-fi
+checktool (){
+	if ! $1 > /dev/null 2>&1; then
+		echo "SKIP: Could not $2"
+		exit $ksft_skip
+	fi
+}
+
+checktool "nft --version" "run test without nft tool"
+checktool "ip -Version" "run test without ip tool"
+checktool "socat -V" "run test without socat tool"
+checktool "ip netns add $ns" "create net namespace"
 
 trap cleanup EXIT
 
@@ -71,7 +77,8 @@ EOF
 		local start=$(date +%s%3N)
 		i=$((i + 10000))
 		j=$((j + 1))
-		dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" nc -w 1 -q 1 -u -p 12345 127.0.0.1 12345 > /dev/null
+		# 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
 		if [ $? -ne 0 ] ;then
 			ret=1
 			break