Message-Id: <20181127175239.32265-1-gbastien@versatic.net>
Date:   Tue, 27 Nov 2018 12:52:39 -0500
From:   Geneviève Bastien <gbastien@...satic.net>
To:     gbastien@...satic.net
Cc:     netdev@...r.kernel.org,
        Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
        Steven Rostedt <rostedt@...dmis.org>,
        Ingo Molnar <mingo@...hat.com>,
        "David S . Miller" <davem@...emloft.net>
Subject: [PATCH v4] net: Add trace events for all receive exit points

Trace events are already present for the receive entry points, to indicate
how the reception entered the stack.

This patch adds the corresponding exit trace events that will bound the
reception such that all events occurring between the entry and the exit
can be considered as part of the reception context. This greatly helps
for dependency and root cause analyses.

Without this, it is not possible with tracepoint instrumentation to
determine whether a sched_wakeup event following a netif_receive_skb
event is the result of the packet reception or a simple coincidence after
further processing by the thread. It is possible using other mechanisms
like kretprobes, but considering the "entry" points are already present,
it would be good to add the matching exit events.

In addition to linking packets with wakeups, the entry/exit event pair
can also be used to perform network stack latency analyses.

Signed-off-by: Geneviève Bastien <gbastien@...satic.net>
CC: Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
CC: Steven Rostedt <rostedt@...dmis.org>
CC: Ingo Molnar <mingo@...hat.com>
CC: David S. Miller <davem@...emloft.net>
Reviewed-by: Steven Rostedt (VMware) <rostedt@...dmis.org> (tracing
side)
---
Changes in v4:
  - Remove the skb parameter from the tracepoints and keep only the
return value
  - Have the list exit point use the same template as others
---
Changes in v3:
  - Update commit message
  - Rename exit template to match the entry one
  - Move the similar tracepoints together in the code
---
Changes in v2:
  - Add the return value to tracepoints where applicable
  - Verify if tracepoint is enabled before walking list in
    netif_receive_skb_list
---
 include/trace/events/net.h | 59 ++++++++++++++++++++++++++++++++++++++
 net/core/dev.c             | 35 ++++++++++++++++++----
 2 files changed, 88 insertions(+), 6 deletions(-)

diff --git a/include/trace/events/net.h b/include/trace/events/net.h
index 00aa72ce0e7c..1efd7d9b25fe 100644
--- a/include/trace/events/net.h
+++ b/include/trace/events/net.h
@@ -244,6 +244,65 @@ DEFINE_EVENT(net_dev_rx_verbose_template, netif_rx_ni_entry,
 	TP_ARGS(skb)
 );
 
+DECLARE_EVENT_CLASS(net_dev_rx_exit_template,
+
+	TP_PROTO(int ret),
+
+	TP_ARGS(ret),
+
+	TP_STRUCT__entry(
+		__field(int,	ret)
+	),
+
+	TP_fast_assign(
+		__entry->ret = ret;
+	),
+
+	TP_printk("ret=%d", __entry->ret)
+);
+
+DEFINE_EVENT(net_dev_rx_exit_template, napi_gro_frags_exit,
+
+	TP_PROTO(int ret),
+
+	TP_ARGS(ret)
+);
+
+DEFINE_EVENT(net_dev_rx_exit_template, napi_gro_receive_exit,
+
+	TP_PROTO(int ret),
+
+	TP_ARGS(ret)
+);
+
+DEFINE_EVENT(net_dev_rx_exit_template, netif_receive_skb_exit,
+
+	TP_PROTO(int ret),
+
+	TP_ARGS(ret)
+);
+
+DEFINE_EVENT(net_dev_rx_exit_template, netif_rx_exit,
+
+	TP_PROTO(int ret),
+
+	TP_ARGS(ret)
+);
+
+DEFINE_EVENT(net_dev_rx_exit_template, netif_rx_ni_exit,
+
+	TP_PROTO(int ret),
+
+	TP_ARGS(ret)
+);
+
+DEFINE_EVENT(net_dev_rx_exit_template, netif_receive_skb_list_exit,
+
+	TP_PROTO(int ret),
+
+	TP_ARGS(ret)
+);
+
 #endif /* _TRACE_NET_H */
 
 /* This part must be outside protection */
diff --git a/net/core/dev.c b/net/core/dev.c
index ddc551f24ba2..de998a07cbb6 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4520,9 +4520,14 @@ static int netif_rx_internal(struct sk_buff *skb)
 
 int netif_rx(struct sk_buff *skb)
 {
+	int ret;
+
 	trace_netif_rx_entry(skb);
 
-	return netif_rx_internal(skb);
+	ret = netif_rx_internal(skb);
+	trace_netif_rx_exit(ret);
+
+	return ret;
 }
 EXPORT_SYMBOL(netif_rx);
 
@@ -4537,6 +4542,7 @@ int netif_rx_ni(struct sk_buff *skb)
 	if (local_softirq_pending())
 		do_softirq();
 	preempt_enable();
+	trace_netif_rx_ni_exit(err);
 
 	return err;
 }
@@ -5222,9 +5228,14 @@ static void netif_receive_skb_list_internal(struct list_head *head)
  */
 int netif_receive_skb(struct sk_buff *skb)
 {
+	int ret;
+
 	trace_netif_receive_skb_entry(skb);
 
-	return netif_receive_skb_internal(skb);
+	ret = netif_receive_skb_internal(skb);
+	trace_netif_receive_skb_exit(ret);
+
+	return ret;
 }
 EXPORT_SYMBOL(netif_receive_skb);
 
@@ -5244,9 +5255,12 @@ void netif_receive_skb_list(struct list_head *head)
 
 	if (list_empty(head))
 		return;
-	list_for_each_entry(skb, head, list)
-		trace_netif_receive_skb_list_entry(skb);
+	if (trace_netif_receive_skb_list_entry_enabled()) {
+		list_for_each_entry(skb, head, list)
+			trace_netif_receive_skb_list_entry(skb);
+	}
 	netif_receive_skb_list_internal(head);
+	trace_netif_receive_skb_list_exit(0);
 }
 EXPORT_SYMBOL(netif_receive_skb_list);
 
@@ -5634,12 +5648,17 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
 
 gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
+	gro_result_t ret;
+
 	skb_mark_napi_id(skb, napi);
 	trace_napi_gro_receive_entry(skb);
 
 	skb_gro_reset_offset(skb);
 
-	return napi_skb_finish(dev_gro_receive(napi, skb), skb);
+	ret = napi_skb_finish(dev_gro_receive(napi, skb), skb);
+	trace_napi_gro_receive_exit(ret);
+
+	return ret;
 }
 EXPORT_SYMBOL(napi_gro_receive);
 
@@ -5757,6 +5776,7 @@ static struct sk_buff *napi_frags_skb(struct napi_struct *napi)
 
 gro_result_t napi_gro_frags(struct napi_struct *napi)
 {
+	gro_result_t ret;
 	struct sk_buff *skb = napi_frags_skb(napi);
 
 	if (!skb)
@@ -5764,7 +5784,10 @@ gro_result_t napi_gro_frags(struct napi_struct *napi)
 
 	trace_napi_gro_frags_entry(skb);
 
-	return napi_frags_finish(napi, skb, dev_gro_receive(napi, skb));
+	ret = napi_frags_finish(napi, skb, dev_gro_receive(napi, skb));
+	trace_napi_gro_frags_exit(ret);
+
+	return ret;
 }
 EXPORT_SYMBOL(napi_gro_frags);
 
-- 
2.19.1

Powered by blists - more mailing lists