bpf: cpumap add tracepoints

This adds two tracepoint to the cpumap.  One for the enqueue side
trace_xdp_cpumap_enqueue() and one for the kthread dequeue side
trace_xdp_cpumap_kthread().

To mitigate the tracepoint overhead, these are invoked during the
enqueue/dequeue bulking phases, thus amortizing the cost.

The obvious use-cases are for debugging and monitoring.  The
non-intuitive use-case is using these as a feedback loop to know the
system load.  One can imagine auto-scaling by reducing, adding or
activating more worker CPUs on demand.

V4: tracepoint remove time_limit info, instead add sched info

V8: intro struct bpf_cpu_map_entry members cpu+map_id in this patch

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

2 files changed, 89 insertions, 5 deletions

diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index eb2ece96c1a2..0c8dec61987e 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -150,6 +150,76 @@ DEFINE_EVENT_PRINT(xdp_redirect_template, xdp_redirect_map_err,
 	 trace_xdp_redirect_map_err(dev, xdp, devmap_ifindex(fwd, map),	\
 				    err, map, idx)
 
+TRACE_EVENT(xdp_cpumap_kthread,
+
+	TP_PROTO(int map_id, unsigned int processed,  unsigned int drops,
+		 int sched),
+
+	TP_ARGS(map_id, processed, drops, sched),
+
+	TP_STRUCT__entry(
+		__field(int, map_id)
+		__field(u32, act)
+		__field(int, cpu)
+		__field(unsigned int, drops)
+		__field(unsigned int, processed)
+		__field(int, sched)
+	),
+
+	TP_fast_assign(
+		__entry->map_id		= map_id;
+		__entry->act		= XDP_REDIRECT;
+		__entry->cpu		= smp_processor_id();
+		__entry->drops		= drops;
+		__entry->processed	= processed;
+		__entry->sched	= sched;
+	),
+
+	TP_printk("kthread"
+		  " cpu=%d map_id=%d action=%s"
+		  " processed=%u drops=%u"
+		  " sched=%d",
+		  __entry->cpu, __entry->map_id,
+		  __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
+		  __entry->processed, __entry->drops,
+		  __entry->sched)
+);
+
+TRACE_EVENT(xdp_cpumap_enqueue,
+
+	TP_PROTO(int map_id, unsigned int processed,  unsigned int drops,
+		 int to_cpu),
+
+	TP_ARGS(map_id, processed, drops, to_cpu),
+
+	TP_STRUCT__entry(
+		__field(int, map_id)
+		__field(u32, act)
+		__field(int, cpu)
+		__field(unsigned int, drops)
+		__field(unsigned int, processed)
+		__field(int, to_cpu)
+	),
+
+	TP_fast_assign(
+		__entry->map_id		= map_id;
+		__entry->act		= XDP_REDIRECT;
+		__entry->cpu		= smp_processor_id();
+		__entry->drops		= drops;
+		__entry->processed	= processed;
+		__entry->to_cpu		= to_cpu;
+	),
+
+	TP_printk("enqueue"
+		  " cpu=%d map_id=%d action=%s"
+		  " processed=%u drops=%u"
+		  " to_cpu=%d",
+		  __entry->cpu, __entry->map_id,
+		  __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
+		  __entry->processed, __entry->drops,
+		  __entry->to_cpu)
+);
+
 #endif /* _TRACE_XDP_H */
 
 #include <trace/define_trace.h>
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index ee7adf4352dd..b4358d84ddf1 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -24,6 +24,7 @@
 #include <linux/workqueue.h>
 #include <linux/kthread.h>
 #include <linux/capability.h>
+#include <trace/events/xdp.h>
 
 #include <linux/netdevice.h>   /* netif_receive_skb_core */
 #include <linux/etherdevice.h> /* eth_type_trans */
@@ -43,6 +44,8 @@ struct xdp_bulk_queue {
 
 /* Struct for every remote "destination" CPU in map */
 struct bpf_cpu_map_entry {
+	u32 cpu;    /* kthread CPU and map index */
+	int map_id; /* Back reference to map */
 	u32 qsize;  /* Queue size placeholder for map lookup */
 
 	/* XDP can run multiple RX-ring queues, need __percpu enqueue store */
@@ -280,15 +283,16 @@ static int cpu_map_kthread_run(void *data)
 	 * kthread_stop signal until queue is empty.
 	 */
 	while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) {
-		unsigned int processed = 0, drops = 0;
+		unsigned int processed = 0, drops = 0, sched = 0;
 		struct xdp_pkt *xdp_pkt;
 
 		/* Release CPU reschedule checks */
 		if (__ptr_ring_empty(rcpu->queue)) {
 			__set_current_state(TASK_INTERRUPTIBLE);
 			schedule();
+			sched = 1;
 		} else {
-			cond_resched();
+			sched = cond_resched();
 		}
 		__set_current_state(TASK_RUNNING);
 
@@ -318,6 +322,9 @@ static int cpu_map_kthread_run(void *data)
 			if (++processed == 8)
 				break;
 		}
+		/* Feedback loop via tracepoint */
+		trace_xdp_cpumap_kthread(rcpu->map_id, processed, drops, sched);
+
 		local_bh_enable(); /* resched point, may call do_softirq() */
 	}
 	__set_current_state(TASK_RUNNING);
@@ -354,7 +361,9 @@ struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu, int map_id)
 	if (err)
 		goto free_queue;
 
-	rcpu->qsize = qsize;
+	rcpu->cpu    = cpu;
+	rcpu->map_id = map_id;
+	rcpu->qsize  = qsize;
 
 	/* Setup kthread */
 	rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa,
@@ -584,6 +593,8 @@ const struct bpf_map_ops cpu_map_ops = {
 static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
 			     struct xdp_bulk_queue *bq)
 {
+	unsigned int processed = 0, drops = 0;
+	const int to_cpu = rcpu->cpu;
 	struct ptr_ring *q;
 	int i;
 
@@ -599,13 +610,16 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
 
 		err = __ptr_ring_produce(q, xdp_pkt);
 		if (err) {
-			/* Free xdp_pkt */
-			page_frag_free(xdp_pkt);
+			drops++;
+			page_frag_free(xdp_pkt); /* Free xdp_pkt */
 		}
+		processed++;
 	}
 	bq->count = 0;
 	spin_unlock(&q->producer_lock);
 
+	/* Feedback loop via tracepoints */
+	trace_xdp_cpumap_enqueue(rcpu->map_id, processed, drops, to_cpu);
 	return 0;
 }