net_sched: introduce tracepoint trace_qdisc_enqueue()

Tracepoint trace_qdisc_enqueue() is introduced to trace skb at
the entrance of TC layer on TX side. This is similar to
trace_qdisc_dequeue():

1. For both we only trace successful cases. The failure cases
   can be traced via trace_kfree_skb().

2. They are called at entrance or exit of TC layer, not for each
   ->enqueue() or ->dequeue(). This is intentional, because
   we want to make trace_qdisc_enqueue() symmetric to
   trace_qdisc_dequeue(), which is easier to use.

The return value of qdisc_enqueue() is not interesting here,
we have Qdisc's drop packets in ->dequeue(), it is impossible to
trace them even if we have the return value, the only way to trace
them is tracing kfree_skb().

We only add information we need to trace ring buffer. If any other
information is needed, it is easy to extend it without breaking ABI,
see commit ee439014ee63 ("net: tracepoint: exposing sk_family in all
tcp:tracepoints").

Reviewed-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Qitao Xu <qitao.xu@bytedance.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/trace/events/qdisc.h b/include/trace/events/qdisc.h
index 58209557cb3a5261b45ff7f8ce3f1c7242478286..c3006c6b4a875badc20aa924a40e0be7d6a1433f 100644 (file)
--- 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 64b21f0a20483b290cc51ff26a8f67f8f8f27a05..7aeefc467ddc575c65934c0bddabce86fec6defd 100644 (file)
--- 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>
@@ -3844,6 +3845,18 @@ static void qdisc_pkt_len_init(struct sk_buff *skb)
        }
 }
 
+static int dev_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *q,
+                            struct sk_buff **to_free,
+                            struct netdev_queue *txq)
+{
+       int rc;
+
+       rc = q->enqueue(skb, q, to_free) & NET_XMIT_MASK;
+       if (rc == NET_XMIT_SUCCESS)
+               trace_qdisc_enqueue(q, txq, skb);
+       return rc;
+}
+
 static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
                                 struct net_device *dev,
                                 struct netdev_queue *txq)
@@ -3862,8 +3875,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
                         * of q->seqlock to protect from racing with requeuing.
                         */
                        if (unlikely(!nolock_qdisc_is_empty(q))) {
-                               rc = q->enqueue(skb, q, &to_free) &
-                                       NET_XMIT_MASK;
+                               rc = dev_qdisc_enqueue(skb, q, &to_free, txq);
                                __qdisc_run(q);
                                qdisc_run_end(q);
 
@@ -3879,7 +3891,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
                        return NET_XMIT_SUCCESS;
                }
 
-               rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
+               rc = dev_qdisc_enqueue(skb, q, &to_free, txq);
                qdisc_run(q);
 
 no_lock_out:
@@ -3923,7 +3935,7 @@ no_lock_out:
                qdisc_run_end(q);
                rc = NET_XMIT_SUCCESS;
        } else {
-               rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
+               rc = dev_qdisc_enqueue(skb, q, &to_free, txq);
                if (qdisc_run_begin(q)) {
                        if (unlikely(contended)) {
                                spin_unlock(&q->busylock);