netdev - [PATCH net-next 1/2] tcp: add tcp_ld_RTO

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20200527024850.81404-2-edumazet@google.com>
Date:   Tue, 26 May 2020 19:48:49 -0700
From:   Eric Dumazet <edumazet@...gle.com>
To:     "David S . Miller" <davem@...emloft.net>
Cc:     netdev <netdev@...r.kernel.org>,
        Eric Dumazet <edumazet@...gle.com>,
        Eric Dumazet <eric.dumazet@...il.com>
Subject: [PATCH net-next 1/2] tcp: add tcp_ld_RTO_revert() helper

RFC 6069 logic has been implemented for IPv4 only so far,
right in the middle of tcp_v4_err() and was error prone.

Move this code to one helper, to make tcp_v4_err() more
readable and to eventually expand RFC 6069 to IPv6 in
the future.

Also perform sock_owned_by_user() check a bit sooner.

Signed-off-by: Eric Dumazet <edumazet@...gle.com>
---
 net/ipv4/tcp_ipv4.c | 85 ++++++++++++++++++++++++---------------------
 1 file changed, 45 insertions(+), 40 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3ac0a7523923e0f1d959dfa65cf2b73bd6a4af15..8b257a92c98ffdb4618b8cde0937740ad5fe2e64 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -403,6 +403,45 @@ void tcp_req_err(struct sock *sk, u32 seq, bool abort)
 }
 EXPORT_SYMBOL(tcp_req_err);
 
+/* TCP-LD (RFC 6069) logic */
+static void tcp_ld_RTO_revert(struct sock *sk, u32 seq)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct sk_buff *skb;
+	s32 remaining;
+	u32 delta_us;
+
+	if (sock_owned_by_user(sk))
+		return;
+
+	if (seq != tp->snd_una  || !icsk->icsk_retransmits ||
+	    !icsk->icsk_backoff)
+		return;
+
+	skb = tcp_rtx_queue_head(sk);
+	if (WARN_ON_ONCE(!skb))
+		return;
+
+	icsk->icsk_backoff--;
+	icsk->icsk_rto = tp->srtt_us ? __tcp_set_rto(tp) : TCP_TIMEOUT_INIT;
+	icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX);
+
+	tcp_mstamp_refresh(tp);
+	delta_us = (u32)(tp->tcp_mstamp - tcp_skb_timestamp_us(skb));
+	remaining = icsk->icsk_rto - usecs_to_jiffies(delta_us);
+
+	if (remaining > 0) {
+		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+					  remaining, TCP_RTO_MAX);
+	} else {
+		/* RTO revert clocked out retransmission.
+		 * Will retransmit now.
+		 */
+		tcp_retransmit_timer(sk);
+	}
+}
+
 /*
  * This routine is called by the ICMP module when it gets some
  * sort of error condition.  If err < 0 then the socket should
@@ -423,17 +462,13 @@ int tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 {
 	const struct iphdr *iph = (const struct iphdr *)icmp_skb->data;
 	struct tcphdr *th = (struct tcphdr *)(icmp_skb->data + (iph->ihl << 2));
-	struct inet_connection_sock *icsk;
 	struct tcp_sock *tp;
 	struct inet_sock *inet;
 	const int type = icmp_hdr(icmp_skb)->type;
 	const int code = icmp_hdr(icmp_skb)->code;
 	struct sock *sk;
-	struct sk_buff *skb;
 	struct request_sock *fastopen;
 	u32 seq, snd_una;
-	s32 remaining;
-	u32 delta_us;
 	int err;
 	struct net *net = dev_net(icmp_skb->dev);
 
@@ -476,7 +511,6 @@ int tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 		goto out;
 	}
 
-	icsk = inet_csk(sk);
 	tp = tcp_sk(sk);
 	/* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */
 	fastopen = rcu_dereference(tp->fastopen_rsk);
@@ -521,41 +555,12 @@ int tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 		}
 
 		err = icmp_err_convert[code].errno;
-		/* check if icmp_skb allows revert of backoff
-		 * (see draft-zimmermann-tcp-lcd) */
-		if (code != ICMP_NET_UNREACH && code != ICMP_HOST_UNREACH)
-			break;
-		if (seq != tp->snd_una  || !icsk->icsk_retransmits ||
-		    !icsk->icsk_backoff || fastopen)
-			break;
-
-		if (sock_owned_by_user(sk))
-			break;
-
-		skb = tcp_rtx_queue_head(sk);
-		if (WARN_ON_ONCE(!skb))
-			break;
-
-		icsk->icsk_backoff--;
-		icsk->icsk_rto = tp->srtt_us ? __tcp_set_rto(tp) :
-					       TCP_TIMEOUT_INIT;
-		icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX);
-
-
-		tcp_mstamp_refresh(tp);
-		delta_us = (u32)(tp->tcp_mstamp - tcp_skb_timestamp_us(skb));
-		remaining = icsk->icsk_rto -
-			    usecs_to_jiffies(delta_us);
-
-		if (remaining > 0) {
-			inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-						  remaining, TCP_RTO_MAX);
-		} else {
-			/* RTO revert clocked out retransmission.
-			 * Will retransmit now */
-			tcp_retransmit_timer(sk);
-		}
-
+		/* check if this ICMP message allows revert of backoff.
+		 * (see RFC 6069)
+		 */
+		if (!fastopen &&
+		    (code == ICMP_NET_UNREACH || code == ICMP_HOST_UNREACH))
+			tcp_ld_RTO_revert(sk, seq);
 		break;
 	case ICMP_TIME_EXCEEDED:
 		err = EHOSTUNREACH;
-- 
2.27.0.rc0.183.gde8f92d652-goog