Re: [Patch net-next v2] net_sched: introduce tracepoint trace_qdisc_enqueue()

From: Qitao Xu <redacted>

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 <redacted>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Qitao Xu <redacted>
---
 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