From 72c3cb9ad2d7cbbf22bd1c844e681a5753070157 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 28 Apr 2015 15:28:18 -0700 Subject: [PATCH] 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 Cc: Yuchung Cheng Cc: Matt Mathis Cc: Eric Salo Cc: Martin Lau Cc: Chris Rapier Acked-by: Yuchung Cheng Signed-off-by: David S. Miller Change-Id: Ie1fec6455c8c6cf9ae3e2df09bf55abb56b57286 --- include/linux/tcp.h | 5 +++++ net/ipv4/tcp.c | 1 + net/ipv4/tcp_input.c | 17 +++++++++++++---- 3 files changed, 19 insertions(+), 4 deletions(-) diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 996f87f492f..ac8e7a733a1 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -172,6 +172,7 @@ 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 */ @@ -318,6 +319,10 @@ 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/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7fad28ae4f4..842c42cf4f1 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2574,6 +2574,7 @@ 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); if (sk->sk_socket) { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 4ea3a983a01..19c2d8bb85f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3560,6 +3560,15 @@ 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 @@ -4513,7 +4522,7 @@ static void tcp_ofo_queue(struct sock *sk) __skb_unlink(skb, &tp->out_of_order_queue); __skb_queue_tail(&sk->sk_receive_queue, skb); - tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); if (tcp_hdr(skb)->fin) tcp_fin(sk); } @@ -4724,7 +4733,7 @@ queue_and_out: skb_set_owner_r(skb, sk); __skb_queue_tail(&sk->sk_receive_queue, skb); } - 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 (th->fin) @@ -5567,7 +5576,7 @@ int 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); } if (copied_early) @@ -5597,7 +5606,7 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, __skb_pull(skb, tcp_header_len); __skb_queue_tail(&sk->sk_receive_queue, skb); skb_set_owner_r(skb, sk); - tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); } tcp_event_data_recv(sk, skb);