netdev - [Patch net-next v2] net_sched: introduce tracepoint trace_qdisc

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-Id: <20210711190308.8476-1-xiyou.wangcong@gmail.com>
Date:   Sun, 11 Jul 2021 12:03:08 -0700
From:   Cong Wang <xiyou.wangcong@...il.com>
To:     netdev@...r.kernel.org
Cc:     xiangxia.m.yue@...il.com, Qitao Xu <qitao.xu@...edance.com>,
        Cong Wang <cong.wang@...edance.com>,
        Jamal Hadi Salim <jhs@...atatu.com>,
        Jiri Pirko <jiri@...nulli.us>
Subject: [Patch net-next v2] net_sched: introduce tracepoint trace_qdisc_enqueue()

From: Qitao Xu <qitao.xu@...edance.com>

Tracepoint trace_qdisc_enqueue() is introduced to trace skb at
the entrance of TC layer on TX side. This is kinda symmetric to
trace_qdisc_dequeue(), and together they can be used to calculate
the packet queueing latency. It is more accurate than
trace_net_dev_queue(), because we already successfully enqueue
the packet at that point.

Note, trace ring buffer is only accessible to privileged users,
it is safe to use %px to print a real kernel address here.

Reviewed-by: Cong Wang <cong.wang@...edance.com>
Cc: Jamal Hadi Salim <jhs@...atatu.com>
Cc: Jiri Pirko <jiri@...nulli.us>
Signed-off-by: Qitao Xu <qitao.xu@...edance.com>
---
 include/trace/events/qdisc.h | 26 ++++++++++++++++++++++++++
 net/core/dev.c               |  9 +++++++++
 2 files changed, 35 insertions(+)

diff --git a/include/trace/events/qdisc.h b/include/trace/events/qdisc.h
index 58209557cb3a..c3006c6b4a87 100644
--- a/include/trace/events/qdisc.h
+++ b/include/trace/events/qdisc.h
@@ -46,6 +46,32 @@ TRACE_EVENT(qdisc_dequeue,
 		  __entry->txq_state, __entry->packets, __entry->skbaddr )
 );
 
+TRACE_EVENT(qdisc_enqueue,
+
+	TP_PROTO(struct Qdisc *qdisc, const struct netdev_queue *txq, struct sk_buff *skb),
+
+	TP_ARGS(qdisc, txq, skb),
+
+	TP_STRUCT__entry(
+		__field(struct Qdisc *, qdisc)
+		__field(void *,	skbaddr)
+		__field(int, ifindex)
+		__field(u32, handle)
+		__field(u32, parent)
+	),
+
+	TP_fast_assign(
+		__entry->qdisc = qdisc;
+		__entry->skbaddr = skb;
+		__entry->ifindex = txq->dev ? txq->dev->ifindex : 0;
+		__entry->handle	 = qdisc->handle;
+		__entry->parent	 = qdisc->parent;
+	),
+
+	TP_printk("enqueue ifindex=%d qdisc handle=0x%X parent=0x%X skbaddr=%px",
+		  __entry->ifindex, __entry->handle, __entry->parent, __entry->skbaddr)
+);
+
 TRACE_EVENT(qdisc_reset,
 
 	TP_PROTO(struct Qdisc *q),
diff --git a/net/core/dev.c b/net/core/dev.c
index c253c2aafe97..20b9376de301 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -131,6 +131,7 @@
 #include <trace/events/napi.h>
 #include <trace/events/net.h>
 #include <trace/events/skb.h>
+#include <trace/events/qdisc.h>
 #include <linux/inetdevice.h>
 #include <linux/cpu_rmap.h>
 #include <linux/static_key.h>
@@ -3864,6 +3865,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 			if (unlikely(!nolock_qdisc_is_empty(q))) {
 				rc = q->enqueue(skb, q, &to_free) &
 					NET_XMIT_MASK;
+				if (rc == NET_XMIT_SUCCESS)
+					trace_qdisc_enqueue(q, txq, skb);
 				__qdisc_run(q);
 				qdisc_run_end(q);
 
@@ -3880,6 +3883,9 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 		}
 
 		rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
+		if (rc == NET_XMIT_SUCCESS)
+			trace_qdisc_enqueue(q, txq, skb);
+
 		qdisc_run(q);
 
 no_lock_out:
@@ -3924,6 +3930,9 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 		rc = NET_XMIT_SUCCESS;
 	} else {
 		rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
+		if (rc == NET_XMIT_SUCCESS)
+			trace_qdisc_enqueue(q, txq, skb);
+
 		if (qdisc_run_begin(q)) {
 			if (unlikely(contended)) {
 				spin_unlock(&q->busylock);
-- 
2.27.0