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

Pull networking fixes from David Miller:
 "Just the usual assortment of small'ish fixes:

   1) Conntrack timeout is sometimes not initialized properly, from
      Alexander Potapenko.

   2) Add a reasonable range limit to tcp_min_rtt_wlen to avoid
      undefined behavior. From ZhangXiaoxu.

   3) des1 field of descriptor in stmmac driver is initialized with the
      wrong variable. From Yue Haibing.

   4) Increase mlxsw pci sw reset timeout a little bit more, from Ido
      Schimmel.

   5) Match IOT2000 stmmac devices more accurately, from Su Bao Cheng.

   6) Fallback refcount fix in TLS code, from Jakub Kicinski.

   7) Fix max MTU check when using XDP in mlx5, from Maxim Mikityanskiy.

   8) Fix recursive locking in team driver, from Hangbin Liu.

   9) Fix tls_set_device_offload_Rx() deadlock, from Jakub Kicinski.

  10) Don't use napi_alloc_frag() outside of softiq context of socionext
      driver, from Ilias Apalodimas.

  11) MAC address increment overflow in ncsi, from Tao Ren.

  12) Fix a regression in 8K/1M pool switching of RDS, from Zhu Yanjun.

  13) ipv4_link_failure has to validate the headers that are actually
      there because RAW sockets can pass in arbitrary garbage, from Eric
      Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (43 commits)
  ipv4: add sanity checks in ipv4_link_failure()
  net/rose: fix unbound loop in rose_loopback_timer()
  rxrpc: fix race condition in rxrpc_input_packet()
  net: rds: exchange of 8K and 1M pool
  net: vrf: Fix operation not supported when set vrf mac
  net/ncsi: handle overflow when incrementing mac address
  net: socionext: replace napi_alloc_frag with the netdev variant on init
  net: atheros: fix spelling mistake "underun" -> "underrun"
  spi: ST ST95HF NFC: declare missing of table
  spi: Micrel eth switch: declare missing of table
  net: stmmac: move stmmac_check_ether_addr() to driver probe
  netfilter: fix nf_l4proto_log_invalid to log invalid packets
  netfilter: never get/set skb->tstamp
  netfilter: ebtables: CONFIG_COMPAT: drop a bogus WARN_ON
  Documentation: decnet: remove reference to CONFIG_DECNET_ROUTE_FWMARK
  dt-bindings: add an explanation for internal phy-mode
  net/tls: don't leak IV and record seq when offload fails
  net/tls: avoid potential deadlock in tls_set_device_offload_rx()
  selftests/net: correct the return value for run_afpackettests
  team: fix possible recursive locking when add slaves
  ...

11 files changed, 172 insertions, 94 deletions

diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 43bbaa32b1d6..14457551bcb4 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1678,7 +1678,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
 	if (!cp) {
 		int v;
 
-		if (!sysctl_schedule_icmp(ipvs))
+		if (ipip || !sysctl_schedule_icmp(ipvs))
 			return NF_ACCEPT;
 
 		if (!ip_vs_try_to_schedule(ipvs, AF_INET, skb, pd, &v, &cp, &ciph))
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 82bfbeef46af..2a714527cde1 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -25,6 +25,7 @@
 #include <linux/slab.h>
 #include <linux/random.h>
 #include <linux/jhash.h>
+#include <linux/siphash.h>
 #include <linux/err.h>
 #include <linux/percpu.h>
 #include <linux/moduleparam.h>
@@ -449,6 +450,40 @@ nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
 }
 EXPORT_SYMBOL_GPL(nf_ct_invert_tuple);
 
+/* Generate a almost-unique pseudo-id for a given conntrack.
+ *
+ * intentionally doesn't re-use any of the seeds used for hash
+ * table location, we assume id gets exposed to userspace.
+ *
+ * Following nf_conn items do not change throughout lifetime
+ * of the nf_conn after it has been committed to main hash table:
+ *
+ * 1. nf_conn address
+ * 2. nf_conn->ext address
+ * 3. nf_conn->master address (normally NULL)
+ * 4. tuple
+ * 5. the associated net namespace
+ */
+u32 nf_ct_get_id(const struct nf_conn *ct)
+{
+	static __read_mostly siphash_key_t ct_id_seed;
+	unsigned long a, b, c, d;
+
+	net_get_random_once(&ct_id_seed, sizeof(ct_id_seed));
+
+	a = (unsigned long)ct;
+	b = (unsigned long)ct->master ^ net_hash_mix(nf_ct_net(ct));
+	c = (unsigned long)ct->ext;
+	d = (unsigned long)siphash(&ct->tuplehash, sizeof(ct->tuplehash),
+				   &ct_id_seed);
+#ifdef CONFIG_64BIT
+	return siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &ct_id_seed);
+#else
+	return siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &ct_id_seed);
+#endif
+}
+EXPORT_SYMBOL_GPL(nf_ct_get_id);
+
 static void
 clean_from_lists(struct nf_conn *ct)
 {
@@ -982,12 +1017,9 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 
 	/* set conntrack timestamp, if enabled. */
 	tstamp = nf_conn_tstamp_find(ct);
-	if (tstamp) {
-		if (skb->tstamp == 0)
-			__net_timestamp(skb);
+	if (tstamp)
+		tstamp->start = ktime_get_real_ns();
 
-		tstamp->start = ktime_to_ns(skb->tstamp);
-	}
 	/* Since the lookup is lockless, hash insertion must be done after
 	 * starting the timer and setting the CONFIRMED bit. The RCU barriers
 	 * guarantee that no other CPU can find the conntrack before the above
@@ -1350,6 +1382,7 @@ __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_pnet(&ct->ct_net, net);
 	memset(&ct->__nfct_init_offset[0], 0,
 	       offsetof(struct nf_conn, proto) -
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 66c596d287a5..d7f61b0547c6 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -29,6 +29,7 @@
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
 #include <linux/slab.h>
+#include <linux/siphash.h>
 
 #include <linux/netfilter.h>
 #include <net/netlink.h>
@@ -485,7 +486,9 @@ nla_put_failure:
 
 static int ctnetlink_dump_id(struct sk_buff *skb, const struct nf_conn *ct)
 {
-	if (nla_put_be32(skb, CTA_ID, htonl((unsigned long)ct)))
+	__be32 id = (__force __be32)nf_ct_get_id(ct);
+
+	if (nla_put_be32(skb, CTA_ID, id))
 		goto nla_put_failure;
 	return 0;
 
@@ -1286,8 +1289,9 @@ static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl,
 	}
 
 	if (cda[CTA_ID]) {
-		u_int32_t id = ntohl(nla_get_be32(cda[CTA_ID]));
-		if (id != (u32)(unsigned long)ct) {
+		__be32 id = nla_get_be32(cda[CTA_ID]);
+
+		if (id != (__force __be32)nf_ct_get_id(ct)) {
 			nf_ct_put(ct);
 			return -ENOENT;
 		}
@@ -2692,6 +2696,25 @@ nla_put_failure:
 
 static const union nf_inet_addr any_addr;
 
+static __be32 nf_expect_get_id(const struct nf_conntrack_expect *exp)
+{
+	static __read_mostly siphash_key_t exp_id_seed;
+	unsigned long a, b, c, d;
+
+	net_get_random_once(&exp_id_seed, sizeof(exp_id_seed));
+
+	a = (unsigned long)exp;
+	b = (unsigned long)exp->helper;
+	c = (unsigned long)exp->master;
+	d = (unsigned long)siphash(&exp->tuple, sizeof(exp->tuple), &exp_id_seed);
+
+#ifdef CONFIG_64BIT
+	return (__force __be32)siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &exp_id_seed);
+#else
+	return (__force __be32)siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &exp_id_seed);
+#endif
+}
+
 static int
 ctnetlink_exp_dump_expect(struct sk_buff *skb,
 			  const struct nf_conntrack_expect *exp)
@@ -2739,7 +2762,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb,
 	}
 #endif
 	if (nla_put_be32(skb, CTA_EXPECT_TIMEOUT, htonl(timeout)) ||
-	    nla_put_be32(skb, CTA_EXPECT_ID, htonl((unsigned long)exp)) ||
+	    nla_put_be32(skb, CTA_EXPECT_ID, nf_expect_get_id(exp)) ||
 	    nla_put_be32(skb, CTA_EXPECT_FLAGS, htonl(exp->flags)) ||
 	    nla_put_be32(skb, CTA_EXPECT_CLASS, htonl(exp->class)))
 		goto nla_put_failure;
@@ -3044,7 +3067,8 @@ static int ctnetlink_get_expect(struct net *net, struct sock *ctnl,
 
 	if (cda[CTA_EXPECT_ID]) {
 		__be32 id = nla_get_be32(cda[CTA_EXPECT_ID]);
-		if (ntohl(id) != (u32)(unsigned long)exp) {
+
+		if (id != nf_expect_get_id(exp)) {
 			nf_ct_expect_put(exp);
 			return -ENOENT;
 		}
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index b9403a266a2e..37bb530d848f 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -55,7 +55,7 @@ void nf_l4proto_log_invalid(const struct sk_buff *skb,
 	struct va_format vaf;
 	va_list args;
 
-	if (net->ct.sysctl_log_invalid != protonum ||
+	if (net->ct.sysctl_log_invalid != protonum &&
 	    net->ct.sysctl_log_invalid != IPPROTO_RAW)
 		return;
 
diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c
index 7df477996b16..9becac953587 100644
--- a/net/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/netfilter/nf_conntrack_proto_icmp.c
@@ -103,49 +103,94 @@ int nf_conntrack_icmp_packet(struct nf_conn *ct,
 	return NF_ACCEPT;
 }
 
-/* Returns conntrack if it dealt with ICMP, and filled in skb fields */
-static int
-icmp_error_message(struct nf_conn *tmpl, struct sk_buff *skb,
-		   const struct nf_hook_state *state)
+/* Check inner header is related to any of the existing connections */
+int nf_conntrack_inet_error(struct nf_conn *tmpl, struct sk_buff *skb,
+			    unsigned int dataoff,
+			    const struct nf_hook_state *state,
+			    u8 l4proto, union nf_inet_addr *outer_daddr)
 {
 	struct nf_conntrack_tuple innertuple, origtuple;
 	const struct nf_conntrack_tuple_hash *h;
 	const struct nf_conntrack_zone *zone;
 	enum ip_conntrack_info ctinfo;
 	struct nf_conntrack_zone tmp;
+	union nf_inet_addr *ct_daddr;
+	enum ip_conntrack_dir dir;
+	struct nf_conn *ct;
 
 	WARN_ON(skb_nfct(skb));
 	zone = nf_ct_zone_tmpl(tmpl, skb, &tmp);
 
 	/* Are they talking about one of our connections? */
-	if (!nf_ct_get_tuplepr(skb,
-			       skb_network_offset(skb) + ip_hdrlen(skb)
-						       + sizeof(struct icmphdr),
-			       PF_INET, state->net, &origtuple)) {
-		pr_debug("icmp_error_message: failed to get tuple\n");
+	if (!nf_ct_get_tuplepr(skb, dataoff,
+			       state->pf, state->net, &origtuple))
 		return -NF_ACCEPT;
-	}
 
 	/* Ordinarily, we'd expect the inverted tupleproto, but it's
 	   been preserved inside the ICMP. */
-	if (!nf_ct_invert_tuple(&innertuple, &origtuple)) {
-		pr_debug("icmp_error_message: no match\n");
+	if (!nf_ct_invert_tuple(&innertuple, &origtuple))
 		return -NF_ACCEPT;
-	}
-
-	ctinfo = IP_CT_RELATED;
 
 	h = nf_conntrack_find_get(state->net, zone, &innertuple);
-	if (!h) {
-		pr_debug("icmp_error_message: no match\n");
+	if (!h)
+		return -NF_ACCEPT;
+
+	/* Consider: A -> T (=This machine) -> B
+	 *   Conntrack entry will look like this:
+	 *      Original:  A->B
+	 *      Reply:     B->T (SNAT case) OR A
+	 *
+	 * When this function runs, we got packet that looks like this:
+	 * iphdr|icmphdr|inner_iphdr|l4header (tcp, udp, ..).
+	 *
+	 * Above nf_conntrack_find_get() makes lookup based on inner_hdr,
+	 * so we should expect that destination of the found connection
+	 * matches outer header destination address.
+	 *
+	 * In above example, we can consider these two cases:
+	 *  1. Error coming in reply direction from B or M (middle box) to
+	 *     T (SNAT case) or A.
+	 *     Inner saddr will be B, dst will be T or A.
+	 *     The found conntrack will be reply tuple (B->T/A).
+	 *  2. Error coming in original direction from A or M to B.
+	 *     Inner saddr will be A, inner daddr will be B.
+	 *     The found conntrack will be original tuple (A->B).
+	 *
+	 * In both cases, conntrack[dir].dst == inner.dst.
+	 *
+	 * A bogus packet could look like this:
+	 *   Inner: B->T
+	 *   Outer: B->X (other machine reachable by T).
+	 *
+	 * In this case, lookup yields connection A->B and will
+	 * set packet from B->X as *RELATED*, even though no connection
+	 * from X was ever seen.
+	 */
+	ct = nf_ct_tuplehash_to_ctrack(h);
+	dir = NF_CT_DIRECTION(h);
+	ct_daddr = &ct->tuplehash[dir].tuple.dst.u3;
+	if (!nf_inet_addr_cmp(outer_daddr, ct_daddr)) {
+		if (state->pf == AF_INET) {
+			nf_l4proto_log_invalid(skb, state->net, state->pf,
+					       l4proto,
+					       "outer daddr %pI4 != inner %pI4",
+					       &outer_daddr->ip, &ct_daddr->ip);
+		} else if (state->pf == AF_INET6) {
+			nf_l4proto_log_invalid(skb, state->net, state->pf,
+					       l4proto,
+					       "outer daddr %pI6 != inner %pI6",
+					       &outer_daddr->ip6, &ct_daddr->ip6);
+		}
+		nf_ct_put(ct);
 		return -NF_ACCEPT;
 	}
 
-	if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY)
+	ctinfo = IP_CT_RELATED;
+	if (dir == IP_CT_DIR_REPLY)
 		ctinfo += IP_CT_IS_REPLY;
 
 	/* Update skb to refer to this connection */
-	nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo);
+	nf_ct_set(skb, ct, ctinfo);
 	return NF_ACCEPT;
 }
 
@@ -162,11 +207,12 @@ int nf_conntrack_icmpv4_error(struct nf_conn *tmpl,
 			      struct sk_buff *skb, unsigned int dataoff,
 			      const struct nf_hook_state *state)
 {
+	union nf_inet_addr outer_daddr;
 	const struct icmphdr *icmph;
 	struct icmphdr _ih;
 
 	/* Not enough header? */
-	icmph = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_ih), &_ih);
+	icmph = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih);
 	if (icmph == NULL) {
 		icmp_error_log(skb, state, "short packet");
 		return -NF_ACCEPT;
@@ -199,7 +245,12 @@ int nf_conntrack_icmpv4_error(struct nf_conn *tmpl,
 	    icmph->type != ICMP_REDIRECT)
 		return NF_ACCEPT;
 
-	return icmp_error_message(tmpl, skb, state);
+	memset(&outer_daddr, 0, sizeof(outer_daddr));
+	outer_daddr.ip = ip_hdr(skb)->daddr;
+
+	dataoff += sizeof(*icmph);
+	return nf_conntrack_inet_error(tmpl, skb, dataoff, state,
+				       IPPROTO_ICMP, &outer_daddr);
 }
 
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c
index bec4a3211658..c63ee3612855 100644
--- a/net/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/netfilter/nf_conntrack_proto_icmpv6.c
@@ -123,51 +123,6 @@ int nf_conntrack_icmpv6_packet(struct nf_conn *ct,
 	return NF_ACCEPT;
 }
 
-static int
-icmpv6_error_message(struct net *net, struct nf_conn *tmpl,
-		     struct sk_buff *skb,
-		     unsigned int icmp6off)
-{
-	struct nf_conntrack_tuple intuple, origtuple;
-	const struct nf_conntrack_tuple_hash *h;
-	enum ip_conntrack_info ctinfo;
-	struct nf_conntrack_zone tmp;
-
-	WARN_ON(skb_nfct(skb));
-
-	/* Are they talking about one of our connections? */
-	if (!nf_ct_get_tuplepr(skb,
-			       skb_network_offset(skb)
-				+ sizeof(struct ipv6hdr)
-				+ sizeof(struct icmp6hdr),
-			       PF_INET6, net, &origtuple)) {
-		pr_debug("icmpv6_error: Can't get tuple\n");
-		return -NF_ACCEPT;
-	}
-
-	/* Ordinarily, we'd expect the inverted tupleproto, but it's
-	   been preserved inside the ICMP. */
-	if (!nf_ct_invert_tuple(&intuple, &origtuple)) {
-		pr_debug("icmpv6_error: Can't invert tuple\n");
-		return -NF_ACCEPT;
-	}
-
-	ctinfo = IP_CT_RELATED;
-
-	h = nf_conntrack_find_get(net, nf_ct_zone_tmpl(tmpl, skb, &tmp),
-				  &intuple);
-	if (!h) {
-		pr_debug("icmpv6_error: no match\n");
-		return -NF_ACCEPT;
-	} else {
-		if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY)
-			ctinfo += IP_CT_IS_REPLY;
-	}
-
-	/* Update skb to refer to this connection */
-	nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo);
-	return NF_ACCEPT;
-}
 
 static void icmpv6_error_log(const struct sk_buff *skb,
 			     const struct nf_hook_state *state,
@@ -182,6 +137,7 @@ int nf_conntrack_icmpv6_error(struct nf_conn *tmpl,
 			      unsigned int dataoff,
 			      const struct nf_hook_state *state)
 {
+	union nf_inet_addr outer_daddr;
 	const struct icmp6hdr *icmp6h;
 	struct icmp6hdr _ih;
 	int type;
@@ -210,7 +166,11 @@ int nf_conntrack_icmpv6_error(struct nf_conn *tmpl,
 	if (icmp6h->icmp6_type >= 128)
 		return NF_ACCEPT;
 
-	return icmpv6_error_message(state->net, tmpl, skb, dataoff);
+	memcpy(&outer_daddr.ip6, &ipv6_hdr(skb)->daddr,
+	       sizeof(outer_daddr.ip6));
+	dataoff += sizeof(*icmp6h);
+	return nf_conntrack_inet_error(tmpl, skb, dataoff, state,
+				       IPPROTO_ICMPV6, &outer_daddr);
 }
 
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index af7dc6537758..000952719adf 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -415,9 +415,14 @@ static void nf_nat_l4proto_unique_tuple(struct nf_conntrack_tuple *tuple,
 	case IPPROTO_ICMPV6:
 		/* id is same for either direction... */
 		keyptr = &tuple->src.u.icmp.id;
-		min = range->min_proto.icmp.id;
-		range_size = ntohs(range->max_proto.icmp.id) -
-			     ntohs(range->min_proto.icmp.id) + 1;
+		if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) {
+			min = 0;
+			range_size = 65536;
+		} else {
+			min = ntohs(range->min_proto.icmp.id);
+			range_size = ntohs(range->max_proto.icmp.id) -
+				     ntohs(range->min_proto.icmp.id) + 1;
+		}
 		goto find_free_id;
 #if IS_ENABLED(CONFIG_NF_CT_PROTO_GRE)
 	case IPPROTO_GRE:
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index ef7772e976cc..1606eaa5ae0d 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1545,7 +1545,7 @@ static int nft_chain_parse_hook(struct net *net,
 		if (IS_ERR(type))
 			return PTR_ERR(type);
 	}
-	if (!(type->hook_mask & (1 << hook->num)))
+	if (hook->num > NF_MAX_HOOKS || !(type->hook_mask & (1 << hook->num)))
 		return -EOPNOTSUPP;
 
 	if (type->type == NFT_CHAIN_T_NAT &&
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index b1f9c5303f02..0b3347570265 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -540,7 +540,7 @@ __build_packet_message(struct nfnl_log_net *log,
 			goto nla_put_failure;
 	}
 
-	if (skb->tstamp) {
+	if (hooknum <= NF_INET_FORWARD && skb->tstamp) {
 		struct nfulnl_msg_packet_timestamp ts;
 		struct timespec64 kts = ktime_to_timespec64(skb->tstamp);
 		ts.sec = cpu_to_be64(kts.tv_sec);
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 0dcc3592d053..e057b2961d31 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -582,7 +582,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 	if (nfqnl_put_bridge(entry, skb) < 0)
 		goto nla_put_failure;
 
-	if (entskb->tstamp) {
+	if (entry->state.hook <= NF_INET_FORWARD && entskb->tstamp) {
 		struct nfqnl_msg_packet_timestamp ts;
 		struct timespec64 kts = ktime_to_timespec64(entskb->tstamp);
 
diff --git a/net/netfilter/xt_time.c b/net/netfilter/xt_time.c
index c13bcd0ab491..8dbb4d48f2ed 100644
--- a/net/netfilter/xt_time.c
+++ b/net/netfilter/xt_time.c
@@ -163,19 +163,24 @@ time_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	s64 stamp;
 
 	/*
-	 * We cannot use get_seconds() instead of __net_timestamp() here.
+	 * We need real time here, but we can neither use skb->tstamp
+	 * nor __net_timestamp().
+	 *
+	 * skb->tstamp and skb->skb_mstamp_ns overlap, however, they
+	 * use different clock types (real vs monotonic).
+	 *
 	 * Suppose you have two rules:
-	 * 	1. match before 13:00
-	 * 	2. match after 13:00
+	 *	1. match before 13:00
+	 *	2. match after 13:00
+	 *
 	 * If you match against processing time (get_seconds) it
 	 * may happen that the same packet matches both rules if
-	 * it arrived at the right moment before 13:00.
+	 * it arrived at the right moment before 13:00, so it would be
+	 * better to check skb->tstamp and set it via __net_timestamp()
+	 * if needed.  This however breaks outgoing packets tx timestamp,
+	 * and causes them to get delayed forever by fq packet scheduler.
 	 */
-	if (skb->tstamp == 0)
-		__net_timestamp((struct sk_buff *)skb);
-
-	stamp = ktime_to_ns(skb->tstamp);
-	stamp = div_s64(stamp, NSEC_PER_SEC);
+	stamp = get_seconds();
 
 	if (info->flags & XT_TIME_LOCAL_TZ)
 		/* Adjust for local timezone */