qdisc: add tracepoint qdisc:qdisc_dequeue for dequeued SKBs

The main purpose of this tracepoint is to monitor bulk dequeue
in the network qdisc layer, as it cannot be deducted from the
existing qdisc stats.

The txq_state can be used for determining the reason for zero packet
dequeues, see enum netdev_queue_state_t.

Notice all packets doesn't necessary activate this tracepoint. As
qdiscs with flag TCQ_F_CAN_BYPASS, can directly invoke
sch_direct_xmit() when qdisc_qlen is zero.

Remember that perf record supports filters like:

 perf record -e qdisc:qdisc_dequeue \
  --filter 'ifindex == 4 && (packets > 1 || txq_state > 0)'

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 57 insertions, 2 deletions

diff --git a/include/trace/events/qdisc.h b/include/trace/events/qdisc.h
new file mode 100644
index 000000000000..60d0d8bd336d
--- /dev/null
+++ b/include/trace/events/qdisc.h
@@ -0,0 +1,50 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM qdisc
+
+#if !defined(_TRACE_QDISC_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_QDISC_H_
+
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/tracepoint.h>
+#include <linux/ftrace.h>
+
+TRACE_EVENT(qdisc_dequeue,
+
+	TP_PROTO(struct Qdisc *qdisc, const struct netdev_queue *txq,
+		 int packets, struct sk_buff *skb),
+
+	TP_ARGS(qdisc, txq, packets, skb),
+
+	TP_STRUCT__entry(
+		__field(	struct Qdisc *,		qdisc	)
+		__field(const	struct netdev_queue *,	txq	)
+		__field(	int,			packets	)
+		__field(	void *,			skbaddr	)
+		__field(	int,			ifindex	)
+		__field(	u32,			handle	)
+		__field(	u32,			parent	)
+		__field(	unsigned long,		txq_state)
+	),
+
+	/* skb==NULL indicate packets dequeued was 0, even when packets==1 */
+	TP_fast_assign(
+		__entry->qdisc		= qdisc;
+		__entry->txq		= txq;
+		__entry->packets	= skb ? packets : 0;
+		__entry->skbaddr	= skb;
+		__entry->ifindex	= txq->dev ? txq->dev->ifindex : 0;
+		__entry->handle		= qdisc->handle;
+		__entry->parent		= qdisc->parent;
+		__entry->txq_state	= txq->state;
+	),
+
+	TP_printk("dequeue ifindex=%d qdisc handle=0x%X parent=0x%X txq_state=0x%lX packets=%d skbaddr=%p",
+		  __entry->ifindex, __entry->handle, __entry->parent,
+		  __entry->txq_state, __entry->packets, __entry->skbaddr )
+);
+
+#endif /* _TRACE_QDISC_H_ */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/net/core/net-traces.c b/net/core/net-traces.c
index 92da5e4ceb4f..4f1468ccd056 100644
--- a/net/core/net-traces.c
+++ b/net/core/net-traces.c
@@ -32,6 +32,7 @@
 #include <trace/events/sock.h>
 #include <trace/events/udp.h>
 #include <trace/events/fib.h>
+#include <trace/events/qdisc.h>
 #if IS_ENABLED(CONFIG_IPV6)
 #include <trace/events/fib6.h>
 EXPORT_TRACEPOINT_SYMBOL_GPL(fib6_table_lookup);
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 57ba406f1437..c6b89a34e8d2 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -29,6 +29,7 @@
 #include <net/sch_generic.h>
 #include <net/pkt_sched.h>
 #include <net/dst.h>
+#include <trace/events/qdisc.h>
 
 /* Qdisc to use by default */
 const struct Qdisc_ops *default_qdisc_ops = &pfifo_fast_ops;
@@ -126,7 +127,7 @@ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate,
 			q->q.qlen--;
 		} else
 			skb = NULL;
-		return skb;
+		goto trace;
 	}
 	*validate = true;
 	skb = q->skb_bad_txq;
@@ -139,7 +140,8 @@ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate,
 			q->q.qlen--;
 			goto bulk;
 		}
-		return NULL;
+		skb = NULL;
+		goto trace;
 	}
 	if (!(q->flags & TCQ_F_ONETXQUEUE) ||
 	    !netif_xmit_frozen_or_stopped(txq))
@@ -151,6 +153,8 @@ bulk:
 		else
 			try_bulk_dequeue_skb_slow(q, skb, packets);
 	}
+trace:
+	trace_qdisc_dequeue(q, txq, *packets, skb);
 	return skb;
 }