tcp_bbr: fix bbr pacing rate for internal pacing

This commit makes BBR use only the MSS (without any headers) to
calculate pacing rates when internal TCP-layer pacing is used.

This is necessary to achieve the correct pacing behavior in this case,
since tcp_internal_pacing() uses only the payload length to calculate
pacing delays.
Signed-off-by: Kevin Yang <yyd@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/tcp.h

@@ -1184,6 +1184,17 @@ static inline bool tcp_is_cwnd_limited(const struct sock *sk)
 	return tp->is_cwnd_limited;
 }
 
+/* BBR congestion control needs pacing.
+ * Same remark for SO_MAX_PACING_RATE.
+ * sch_fq packet scheduler is efficiently handling pacing,
+ * but is not always installed/used.
+ * Return true if TCP stack should pace packets itself.
+ */
+static inline bool tcp_needs_internal_pacing(const struct sock *sk)
+{
+	return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED;
+}
+
 /* Something is really bad, we could not queue an additional packet,
  * because qdisc is full or receiver sent a 0 window.
  * We do not want to add fuel to the fire, or abort too early,

net/ipv4/tcp_bbr.c

@@ -205,7 +205,11 @@ static u32 bbr_bw(const struct sock *sk)
  */
 static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain)
 {
-	rate *= tcp_mss_to_mtu(sk, tcp_sk(sk)->mss_cache);
+	unsigned int mss = tcp_sk(sk)->mss_cache;
+
+	if (!tcp_needs_internal_pacing(sk))
+		mss = tcp_mss_to_mtu(sk, mss);
+	rate *= mss;
 	rate *= gain;
 	rate >>= BBR_SCALE;
 	rate *= USEC_PER_SEC;

net/ipv4/tcp_output.c

@@ -973,17 +973,6 @@ enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer)
 	return HRTIMER_NORESTART;
 }
 
-/* BBR congestion control needs pacing.
- * Same remark for SO_MAX_PACING_RATE.
- * sch_fq packet scheduler is efficiently handling pacing,
- * but is not always installed/used.
- * Return true if TCP stack should pace packets itself.
- */
-static bool tcp_needs_internal_pacing(const struct sock *sk)
-{
-	return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED;
-}
-
 static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb)
 {
 	u64 len_ns;
@@ -995,9 +984,6 @@ static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb)
 	if (!rate || rate == ~0U)
 		return;
 
-	/* Should account for header sizes as sch_fq does,
-	 * but lets make things simple.
-	 */
 	len_ns = (u64)skb->len * NSEC_PER_SEC;
 	do_div(len_ns, rate);
 	hrtimer_start(&tcp_sk(sk)->pacing_timer,