tcp: add tcpi_bytes_received to tcp_info

This patch tracks total number of payload bytes received on a TCP socket.
This is the sum of all changes done to tp->rcv_nxt

RFC4898 named this : tcpEStatsAppHCThruOctetsReceived

This is a 64bit field, and can be fetched both from TCP_INFO
getsockopt() if one has a handle on a TCP socket, or from inet_diag
netlink facility (iproute2/ss patch will follow)

Note that tp->bytes_received was placed near tp->rcv_nxt for
best data locality and minimal performance impact.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Matt Mathis <mattmathis@google.com>
Cc: Eric Salo <salo@google.com>
Cc: Martin Lau <kafai@fb.com>
Cc: Chris Rapier <rapier@psc.edu>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 0f73b43..3b29115 100644 (file)
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -145,6 +145,10 @@ struct tcp_sock {
  *     read the code and the spec side by side (and laugh ...)
  *     See RFC793 and RFC1122. The RFC writes these in capitals.
  */
+       u64     bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived
+                                * sum(delta(rcv_nxt)), or how many bytes
+                                * were acked.
+                                */
        u32     rcv_nxt;        /* What we want to receive next         */
        u32     copied_seq;     /* Head of yet unread data              */
        u32     rcv_wup;        /* rcv_nxt on last window update sent   */

diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 6666e98..a48f93f 100644 (file)
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -190,6 +190,7 @@ struct tcp_info {
        __u64   tcpi_pacing_rate;
        __u64   tcpi_max_pacing_rate;
        __u64   tcpi_bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked */
+       __u64   tcpi_bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived */
 };
 
 /* for TCP_MD5SIG socket option */

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 4bf0e8c..99fcc0b 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2666,6 +2666,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 
        spin_lock_bh(&sk->sk_lock.slock);
        info->tcpi_bytes_acked = tp->bytes_acked;
+       info->tcpi_bytes_received = tp->bytes_received;
        spin_unlock_bh(&sk->sk_lock.slock);
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);

diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index e3d87ac..3c673d5 100644 (file)
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -206,6 +206,7 @@ static bool tcp_fastopen_create_child(struct sock *sk,
                        skb_set_owner_r(skb2, child);
                        __skb_queue_tail(&child->sk_receive_queue, skb2);
                        tp->syn_data_acked = 1;
+                       tp->bytes_received = end_seq - TCP_SKB_CB(skb)->seq - 1;
                } else {
                        end_seq = TCP_SKB_CB(skb)->seq + 1;
                }

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 378d3f4..7e6962b 100644 (file)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3289,6 +3289,15 @@ static void tcp_snd_una_update(struct tcp_sock *tp, u32 ack)
        tp->snd_una = ack;
 }
 
+/* If we update tp->rcv_nxt, also update tp->bytes_received */
+static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq)
+{
+       u32 delta = seq - tp->rcv_nxt;
+
+       tp->bytes_received += delta;
+       tp->rcv_nxt = seq;
+}
+
 /* Update our send window.
  *
  * Window update algorithm, described in RFC793/RFC1122 (used in linux-2.2
@@ -4245,7 +4254,7 @@ static void tcp_ofo_queue(struct sock *sk)
 
                tail = skb_peek_tail(&sk->sk_receive_queue);
                eaten = tail && tcp_try_coalesce(sk, tail, skb, &fragstolen);
-               tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+               tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
                if (!eaten)
                        __skb_queue_tail(&sk->sk_receive_queue, skb);
                if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
@@ -4413,7 +4422,7 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int
        __skb_pull(skb, hdrlen);
        eaten = (tail &&
                 tcp_try_coalesce(sk, tail, skb, fragstolen)) ? 1 : 0;
-       tcp_sk(sk)->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+       tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq);
        if (!eaten) {
                __skb_queue_tail(&sk->sk_receive_queue, skb);
                skb_set_owner_r(skb, sk);
@@ -4506,7 +4515,7 @@ queue_and_out:
 
                        eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen);
                }
-               tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+               tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
                if (skb->len)
                        tcp_event_data_recv(sk, skb);
                if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
@@ -5254,7 +5263,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
                                        tcp_rcv_rtt_measure_ts(sk, skb);
 
                                        __skb_pull(skb, tcp_header_len);
-                                       tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+                                       tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
                                        NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPHITSTOUSER);
                                        eaten = 1;
                                }