Merge branch 'tcp-ao-md5-racepoits'

Dmitry Safonov says:

====================
net/tcp: TCP-AO and TCP-MD5 tracepoints

Changes in v2:
- Fix the build with CONFIG_IPV6=m (Eric Dumazet)
- Move unused keyid/rnext/maclen later in the series to the patch
  that uses them (Simon Horman)
- Reworked tcp_ao selftest lib to allow async tracing non-tcp events
  (was working on a stress-test that needs trace_kfree_skb() event,
   not in this series).
- Separated selftest changes from kernel, as they now have a couple
  of unrelated to tracepoints changes
- Wrote a few lines of Documentation/
- Link to v1: https://lore.kernel.org/r/20240224-tcp-ao-tracepoints-v1-0-15f31b7f30a7@arista.com
====================

Signed-off-by: Dmitry Safonov <0x7f454c46@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 104 insertions, 36 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 6553221694ec..e03a342c9162 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -282,6 +282,7 @@
 #include <asm/ioctls.h>
 #include <net/busy_poll.h>
 #include <net/hotdata.h>
+#include <trace/events/tcp.h>
 #include <net/rps.h>
 
 /* Track pending CMSGs. */
@@ -4463,7 +4464,7 @@ int tcp_md5_hash_key(struct tcp_sigpool *hp,
 EXPORT_SYMBOL(tcp_md5_hash_key);
 
 /* Called with rcu_read_lock() */
-enum skb_drop_reason
+static enum skb_drop_reason
 tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
 		     const void *saddr, const void *daddr,
 		     int family, int l3index, const __u8 *hash_location)
@@ -4483,7 +4484,7 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
 
 	if (!key && hash_location) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED);
-		tcp_hash_fail("Unexpected MD5 Hash found", family, skb, "");
+		trace_tcp_hash_md5_unexpected(sk, skb);
 		return SKB_DROP_REASON_TCP_MD5UNEXPECTED;
 	}
 
@@ -4498,29 +4499,90 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
 							 NULL, skb);
 	if (genhash || memcmp(hash_location, newhash, 16) != 0) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE);
-		if (family == AF_INET) {
-			tcp_hash_fail("MD5 Hash failed", AF_INET, skb, "%s L3 index %d",
-				      genhash ? "tcp_v4_calc_md5_hash failed"
-				      : "", l3index);
-		} else {
-			if (genhash) {
-				tcp_hash_fail("MD5 Hash failed",
-					      AF_INET6, skb, "L3 index %d",
-					      l3index);
-			} else {
-				tcp_hash_fail("MD5 Hash mismatch",
-					      AF_INET6, skb, "L3 index %d",
-					      l3index);
-			}
-		}
+		trace_tcp_hash_md5_mismatch(sk, skb);
 		return SKB_DROP_REASON_TCP_MD5FAILURE;
 	}
 	return SKB_NOT_DROPPED_YET;
 }
-EXPORT_SYMBOL(tcp_inbound_md5_hash);
+#else
+static inline enum skb_drop_reason
+tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
+		     const void *saddr, const void *daddr,
+		     int family, int l3index, const __u8 *hash_location)
+{
+	return SKB_NOT_DROPPED_YET;
+}
 
 #endif
 
+/* Called with rcu_read_lock() */
+enum skb_drop_reason
+tcp_inbound_hash(struct sock *sk, const struct request_sock *req,
+		 const struct sk_buff *skb,
+		 const void *saddr, const void *daddr,
+		 int family, int dif, int sdif)
+{
+	const struct tcphdr *th = tcp_hdr(skb);
+	const struct tcp_ao_hdr *aoh;
+	const __u8 *md5_location;
+	int l3index;
+
+	/* Invalid option or two times meet any of auth options */
+	if (tcp_parse_auth_options(th, &md5_location, &aoh)) {
+		trace_tcp_hash_bad_header(sk, skb);
+		return SKB_DROP_REASON_TCP_AUTH_HDR;
+	}
+
+	if (req) {
+		if (tcp_rsk_used_ao(req) != !!aoh) {
+			u8 keyid, rnext, maclen;
+
+			if (aoh) {
+				keyid = aoh->keyid;
+				rnext = aoh->rnext_keyid;
+				maclen = tcp_ao_hdr_maclen(aoh);
+			} else {
+				keyid = rnext = maclen = 0;
+			}
+
+			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD);
+			trace_tcp_ao_handshake_failure(sk, skb, keyid, rnext, maclen);
+			return SKB_DROP_REASON_TCP_AOFAILURE;
+		}
+	}
+
+	/* sdif set, means packet ingressed via a device
+	 * in an L3 domain and dif is set to the l3mdev
+	 */
+	l3index = sdif ? dif : 0;
+
+	/* Fast path: unsigned segments */
+	if (likely(!md5_location && !aoh)) {
+		/* Drop if there's TCP-MD5 or TCP-AO key with any rcvid/sndid
+		 * for the remote peer. On TCP-AO established connection
+		 * the last key is impossible to remove, so there's
+		 * always at least one current_key.
+		 */
+		if (tcp_ao_required(sk, saddr, family, l3index, true)) {
+			trace_tcp_hash_ao_required(sk, skb);
+			return SKB_DROP_REASON_TCP_AONOTFOUND;
+		}
+		if (unlikely(tcp_md5_do_lookup(sk, l3index, saddr, family))) {
+			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND);
+			trace_tcp_hash_md5_required(sk, skb);
+			return SKB_DROP_REASON_TCP_MD5NOTFOUND;
+		}
+		return SKB_NOT_DROPPED_YET;
+	}
+
+	if (aoh)
+		return tcp_inbound_ao_hash(sk, skb, family, req, l3index, aoh);
+
+	return tcp_inbound_md5_hash(sk, skb, saddr, daddr, family,
+				    l3index, md5_location);
+}
+EXPORT_SYMBOL_GPL(tcp_inbound_hash);
+
 void tcp_done(struct sock *sk)
 {
 	struct request_sock *req;
diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c
index 37c42b63ff99..0de863aa5f66 100644
--- a/net/ipv4/tcp_ao.c
+++ b/net/ipv4/tcp_ao.c
@@ -16,6 +16,7 @@
 #include <net/tcp.h>
 #include <net/ipv6.h>
 #include <net/icmp.h>
+#include <trace/events/tcp.h>
 
 DEFINE_STATIC_KEY_DEFERRED_FALSE(tcp_ao_needed, HZ);
 
@@ -884,17 +885,16 @@ tcp_ao_verify_hash(const struct sock *sk, const struct sk_buff *skb,
 		   const struct tcp_ao_hdr *aoh, struct tcp_ao_key *key,
 		   u8 *traffic_key, u8 *phash, u32 sne, int l3index)
 {
-	u8 maclen = aoh->length - sizeof(struct tcp_ao_hdr);
 	const struct tcphdr *th = tcp_hdr(skb);
+	u8 maclen = tcp_ao_hdr_maclen(aoh);
 	void *hash_buf = NULL;
 
 	if (maclen != tcp_ao_maclen(key)) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD);
 		atomic64_inc(&info->counters.pkt_bad);
 		atomic64_inc(&key->pkt_bad);
-		tcp_hash_fail("AO hash wrong length", family, skb,
-			      "%u != %d L3index: %d", maclen,
-			      tcp_ao_maclen(key), l3index);
+		trace_tcp_ao_wrong_maclen(sk, skb, aoh->keyid,
+					  aoh->rnext_keyid, maclen);
 		return SKB_DROP_REASON_TCP_AOFAILURE;
 	}
 
@@ -909,8 +909,8 @@ tcp_ao_verify_hash(const struct sock *sk, const struct sk_buff *skb,
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD);
 		atomic64_inc(&info->counters.pkt_bad);
 		atomic64_inc(&key->pkt_bad);
-		tcp_hash_fail("AO hash mismatch", family, skb,
-			      "L3index: %d", l3index);
+		trace_tcp_ao_mismatch(sk, skb, aoh->keyid,
+				      aoh->rnext_keyid, maclen);
 		kfree(hash_buf);
 		return SKB_DROP_REASON_TCP_AOFAILURE;
 	}
@@ -927,6 +927,7 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb,
 		    int l3index, const struct tcp_ao_hdr *aoh)
 {
 	const struct tcphdr *th = tcp_hdr(skb);
+	u8 maclen = tcp_ao_hdr_maclen(aoh);
 	u8 *phash = (u8 *)(aoh + 1); /* hash goes just after the header */
 	struct tcp_ao_info *info;
 	enum skb_drop_reason ret;
@@ -939,8 +940,8 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb,
 	info = rcu_dereference(tcp_sk(sk)->ao_info);
 	if (!info) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOKEYNOTFOUND);
-		tcp_hash_fail("AO key not found", family, skb,
-			      "keyid: %u L3index: %d", aoh->keyid, l3index);
+		trace_tcp_ao_key_not_found(sk, skb, aoh->keyid,
+					   aoh->rnext_keyid, maclen);
 		return SKB_DROP_REASON_TCP_AOUNEXPECTED;
 	}
 
@@ -981,6 +982,9 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb,
 		current_key = READ_ONCE(info->current_key);
 		/* Key rotation: the peer asks us to use new key (RNext) */
 		if (unlikely(aoh->rnext_keyid != current_key->sndid)) {
+			trace_tcp_ao_rnext_request(sk, skb, current_key->sndid,
+						   aoh->rnext_keyid,
+						   tcp_ao_hdr_maclen(aoh));
 			/* If the key is not found we do nothing. */
 			key = tcp_ao_established_key(info, aoh->rnext_keyid, -1);
 			if (key)
@@ -1046,8 +1050,8 @@ verify_hash:
 key_not_found:
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOKEYNOTFOUND);
 	atomic64_inc(&info->counters.key_not_found);
-	tcp_hash_fail("Requested by the peer AO key id not found",
-		      family, skb, "L3index: %d", l3index);
+	trace_tcp_ao_key_not_found(sk, skb, aoh->keyid,
+				   aoh->rnext_keyid, maclen);
 	return SKB_DROP_REASON_TCP_AOKEYNOTFOUND;
 }
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index eb187450e4d7..d0a1e34d69f6 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3578,8 +3578,10 @@ static void tcp_snd_sne_update(struct tcp_sock *tp, u32 ack)
 
 	ao = rcu_dereference_protected(tp->ao_info,
 				       lockdep_sock_is_held((struct sock *)tp));
-	if (ao && ack < tp->snd_una)
+	if (ao && ack < tp->snd_una) {
 		ao->snd_sne++;
+		trace_tcp_ao_snd_sne_update((struct sock *)tp, ao->snd_sne);
+	}
 #endif
 }
 
@@ -3604,8 +3606,10 @@ static void tcp_rcv_sne_update(struct tcp_sock *tp, u32 seq)
 
 	ao = rcu_dereference_protected(tp->ao_info,
 				       lockdep_sock_is_held((struct sock *)tp));
-	if (ao && seq < tp->rcv_nxt)
+	if (ao && seq < tp->rcv_nxt) {
 		ao->rcv_sne++;
+		trace_tcp_ao_rcv_sne_update((struct sock *)tp, ao->rcv_sne);
+	}
 #endif
 }
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index e61c7c974745..de0c8f43448a 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1054,12 +1054,10 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
 #else
 	if (0) {
 #endif
-#ifdef CONFIG_TCP_MD5SIG
-	} else if (static_branch_unlikely(&tcp_md5_needed.key)) {
+	} else if (static_branch_tcp_md5()) {
 		key.md5_key = tcp_twsk_md5_key(tcptw);
 		if (key.md5_key)
 			key.type = TCP_KEY_MD5;
-#endif
 	}
 
 	tcp_v4_send_ack(sk, skb,
@@ -1128,8 +1126,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 #else
 	if (0) {
 #endif
-#ifdef CONFIG_TCP_MD5SIG
-	} else if (static_branch_unlikely(&tcp_md5_needed.key)) {
+	} else if (static_branch_tcp_md5()) {
 		const union tcp_md5_addr *addr;
 		int l3index;
 
@@ -1138,7 +1135,6 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 		key.md5_key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET);
 		if (key.md5_key)
 			key.type = TCP_KEY_MD5;
-#endif
 	}
 
 	tcp_v4_send_ack(sk, skb, seq,
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 090fb0c24599..16c48df8df4c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3768,6 +3768,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 #ifdef CONFIG_TCP_AO
 		struct tcp_ao_key *ao_key = NULL;
 		u8 keyid = tcp_rsk(req)->ao_keyid;
+		u8 rnext = tcp_rsk(req)->ao_rcv_next;
 
 		ao_key = tcp_sk(sk)->af_specific->ao_lookup(sk, req_to_sk(req),
 							    keyid, -1);
@@ -3777,6 +3778,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 		 * ao_keyid (RFC5925 RNextKeyID), so let's keep it simple here.
 		 */
 		if (unlikely(!ao_key)) {
+			trace_tcp_ao_synack_no_key(sk, keyid, rnext);
 			rcu_read_unlock();
 			kfree_skb(skb);
 			net_warn_ratelimited("TCP-AO: the keyid %u from SYN packet is not present - not sending SYNACK\n",