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>

6 files changed, 15 insertions, 12 deletions

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 */