From patchwork Wed Nov 8 10:00:33 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Masami Hiramatsu (Google)" X-Patchwork-Id: 835749 X-Patchwork-Delegate: davem@davemloft.net Return-Path: X-Original-To: patchwork-incoming@ozlabs.org Delivered-To: patchwork-incoming@ozlabs.org Authentication-Results: ozlabs.org; spf=none (mailfrom) smtp.mailfrom=vger.kernel.org (client-ip=209.132.180.67; helo=vger.kernel.org; envelope-from=netdev-owner@vger.kernel.org; receiver=) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 3yX1zM20TXz9sNc for ; Wed, 8 Nov 2017 21:01:35 +1100 (AEDT) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751951AbdKHKBA (ORCPT ); Wed, 8 Nov 2017 05:01:00 -0500 Received: from mail.kernel.org ([198.145.29.99]:45024 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751566AbdKHKA6 (ORCPT ); Wed, 8 Nov 2017 05:00:58 -0500 Received: from localhost.localdomain (NE2965lan1.rev.em-net.ne.jp [210.141.244.193]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPSA id 69707218DB; Wed, 8 Nov 2017 10:00:55 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 69707218DB Authentication-Results: mail.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.org Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=mhiramat@kernel.org From: Masami Hiramatsu To: Ingo Molnar , Ian McDonald , Vlad Yasevich , Stephen Hemminger , Steven Rostedt Cc: Peter Zijlstra , Thomas Gleixner , LKML , "H . Peter Anvin" , Gerrit Renker , "David S . Miller" , Neil Horman , dccp@vger.kernel.org, netdev@vger.kernel.org, linux-sctp@vger.kernel.org, Stephen Rothwell Subject: [RFC PATCH -tip 1/6] net: tcp: Add trace events for TCP congestion window tracing Date: Wed, 8 Nov 2017 19:00:33 +0900 Message-Id: <151013523339.7294.16732700508720389690.stgit@devbox> X-Mailer: git-send-email 2.13.6 In-Reply-To: <151013520119.7294.3518752184394738314.stgit@devbox> References: <151013520119.7294.3518752184394738314.stgit@devbox> User-Agent: StGit/0.17.1-dirty MIME-Version: 1.0 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org This adds an event to trace TCP stat variables with slightly intrusive trace-event. This uses ftrace/perf event log buffer to trace those state, no needs to prepare own ring-buffer, nor custom user apps. User can use ftrace to trace this event as below; # cd /sys/kernel/debug/tracing # echo 1 > events/tcp/tcp_probe/enable (run workloads) # cat trace Signed-off-by: Masami Hiramatsu --- include/trace/events/tcp.h | 96 ++++++++++++++++++++++++++++++++++++++++++++ net/core/net-traces.c | 1 net/ipv4/tcp_input.c | 4 ++ 3 files changed, 101 insertions(+) create mode 100644 include/trace/events/tcp.h diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h new file mode 100644 index 000000000000..b8969bbceb38 --- /dev/null +++ b/include/trace/events/tcp.h @@ -0,0 +1,96 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM tcp + +#if !defined(_TRACE_TCP_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_TCP_H + +#include +#include +#include +#include +#include +#include + +TRACE_EVENT(tcp_probe, + + TP_PROTO(struct sock *sk, struct sk_buff *skb), + + TP_ARGS(sk, skb), + + TP_STRUCT__entry( + /* sockaddr_in6 is always bigger than sockaddr_in */ + __array(__u8, saddr, sizeof(struct sockaddr_in6)) + __array(__u8, daddr, sizeof(struct sockaddr_in6)) + __field(__u16, sport) + __field(__u16, dport) + __field(__u32, mark) + __field(__u16, length) + __field(__u32, snd_nxt) + __field(__u32, snd_una) + __field(__u32, snd_cwnd) + __field(__u32, ssthresh) + __field(__u32, snd_wnd) + __field(__u32, srtt) + __field(__u32, rcv_wnd) + ), + + TP_fast_assign( + const struct tcp_sock *tp = tcp_sk(sk); + const struct inet_sock *inet = inet_sk(sk); + + memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); + memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); + + if (sk->sk_family == AF_INET) { + struct sockaddr_in *v4 = (void *)__entry->saddr; + + v4->sin_family = AF_INET; + v4->sin_port = inet->inet_sport; + v4->sin_addr.s_addr = inet->inet_saddr; + v4 = (void *)__entry->daddr; + v4->sin_family = AF_INET; + v4->sin_port = inet->inet_dport; + v4->sin_addr.s_addr = inet->inet_daddr; +#if IS_ENABLED(CONFIG_IPV6) + } else if (sk->sk_family == AF_INET6) { + struct sockaddr_in6 *v6 = (void *)__entry->saddr; + + v6->sin6_family = AF_INET6; + v6->sin6_port = inet->inet_sport; + v6->sin6_addr = inet6_sk(sk)->saddr; + v6 = (void *)__entry->daddr; + v6->sin6_family = AF_INET6; + v6->sin6_port = inet->inet_dport; + v6->sin6_addr = sk->sk_v6_daddr; +#endif + } + + /* For filtering use */ + __entry->sport = ntohs(inet->inet_sport); + __entry->dport = ntohs(inet->inet_dport); + __entry->mark = skb->mark; + + __entry->length = skb->len; + __entry->snd_nxt = tp->snd_nxt; + __entry->snd_una = tp->snd_una; + __entry->snd_cwnd = tp->snd_cwnd; + __entry->snd_wnd = tp->snd_wnd; + __entry->rcv_wnd = tp->rcv_wnd; + __entry->ssthresh = tcp_current_ssthresh(sk); + __entry->srtt = tp->srtt_us >> 3; + ), + + TP_printk("src=%pISpc dest=%pISpc mark=%#x length=%d snd_nxt=%#x " + "snd_una=%#x snd_cwnd=%u ssthresh=%u snd_wnd=%u srtt=%u " + "rcv_wnd=%u", + __entry->saddr, __entry->daddr, __entry->mark, + __entry->length, __entry->snd_nxt, __entry->snd_una, + __entry->snd_cwnd, __entry->ssthresh, __entry->snd_wnd, + __entry->srtt, __entry->rcv_wnd) +); + +#endif /* _TRACE_TCP_H */ + +/* This part must be outside protection */ +#include diff --git a/net/core/net-traces.c b/net/core/net-traces.c index 71f209542364..2e84d642c03f 100644 --- a/net/core/net-traces.c +++ b/net/core/net-traces.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #include diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 9a0b3c5ffa46..da8b342b95ce 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -76,6 +76,7 @@ #include #include #include +#include int sysctl_tcp_fack __read_mostly; int sysctl_tcp_max_reordering __read_mostly = 300; @@ -5356,6 +5357,9 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, unsigned int len = skb->len; struct tcp_sock *tp = tcp_sk(sk); + /* TCP congestion window tracking */ + trace_tcp_probe(sk, skb); + tcp_mstamp_refresh(tp); if (unlikely(!sk->sk_rx_dst)) inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb);