[PATCH net-next v6 1/3] net/sched: sch_fq_pie: add per-flow statistics via class ops

[Hemendra M. Naik]

FQ-PIE schedules independent PIE controllers per flow but exposes no
per-flow AQM state. Without class-level statistics there is no way to
observe the per-flow drop probability, queue delay, deficit or dequeue
rate from userspace.

Extend tc_fq_pie_xstats with a type discriminator and tc_fq_pie_cl_stats
for per-flow metrics. The nine existing __u32 counters keep their
offsets, type is appended at offset 36 and class_stats follows it,
growing the structure from 36 to 64 bytes.

Wire up fq_pie_class_ops with walk, dump, and dump_stats only so that
'tc -s class show' reports per-flow state (prob, delay, deficit,
avg_dq_rate, dq_rate_estimating). Filter attachment callbacks
(.tcf_block, .bind_tcf, .unbind_tcf) are omitted on purpose.

Derive delay with div_u64() from the full 64-bit nanosecond value rather
than truncating to u32 before dividing, which wrapped for sojourn times
above ~4.295 s, and widen avg_dq_rate to u64 before scaling it by
PSCHED_TICKS_PER_SEC.

Signed-off-by: Hemendra M. Naik <hemendranaik@xxxxxxxxx>
Signed-off-by: Vishal Kamath <vishy0777@xxxxxxxxx>
Signed-off-by: Mohit P. Tahiliani <tahiliani@xxxxxxxxxxx>
---
 include/uapi/linux/pkt_sched.h | 16 +++++++
 net/sched/sch_fq_pie.c         | 86 +++++++++++++++++++++++++++++++++-
 2 files changed, 101 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 490efd288526..9c0c9787f0c3 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -953,6 +953,20 @@ enum {
 };
 #define TCA_FQ_PIE_MAX   (__TCA_FQ_PIE_MAX - 1)
 
+enum {
+	TCA_FQ_PIE_XSTATS_QDISC,
+	TCA_FQ_PIE_XSTATS_CLASS,
+};
+
+struct tc_fq_pie_cl_stats {
+	__u64 prob;			/* current probability */
+	__u32 delay;			/* current delay in microseconds */
+	__s32 deficit;			/* number of remaining byte credits */
+	__u32 avg_dq_rate;		/* current average dq_rate in
+					 * bytes/second
+					 */
+	__u32 dq_rate_estimating;	/* is avg_dq_rate being calculated? */
+};
 struct tc_fq_pie_xstats {
 	__u32 packets_in;	/* total number of packets enqueued */
 	__u32 dropped;		/* packets dropped due to fq_pie_action */
@@ -963,6 +977,8 @@ struct tc_fq_pie_xstats {
 	__u32 new_flows_len;	/* count of flows in new list */
 	__u32 old_flows_len;	/* count of flows in old list */
 	__u32 memory_usage;	/* total memory across all queues */
+	__u32 type;
+	struct tc_fq_pie_cl_stats class_stats;
 };
 
 /* CBS */
diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c
index 5982847df8f8..675861f578b8 100644
--- a/net/sched/sch_fq_pie.c
+++ b/net/sched/sch_fq_pie.c
@@ -511,7 +511,9 @@ static int fq_pie_dump(struct Qdisc *sch, struct sk_buff *skb)
 static int fq_pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
 {
 	struct fq_pie_sched_data *q = qdisc_priv(sch);
-	struct tc_fq_pie_xstats st = { 0 };
+	struct tc_fq_pie_xstats st = {
+		.type	= TCA_FQ_PIE_XSTATS_QDISC,
+	};
 	struct list_head *pos;
 
 	sch_tree_lock(sch);
@@ -563,7 +565,89 @@ static void fq_pie_destroy(struct Qdisc *sch)
 	kvfree(q->flows);
 }
 
+static struct Qdisc *fq_pie_leaf(struct Qdisc *sch, unsigned long arg)
+{
+	return NULL;
+}
+
+static unsigned long fq_pie_find(struct Qdisc *sch, u32 classid)
+{
+	return 0;
+}
+
+static int fq_pie_dump_class(struct Qdisc *sch, unsigned long cl,
+			     struct sk_buff *skb, struct tcmsg *tcm)
+{
+	tcm->tcm_handle |= TC_H_MIN(cl);
+	return 0;
+}
+
+static int fq_pie_dump_class_stats(struct Qdisc *sch, unsigned long cl,
+				   struct gnet_dump *d)
+{
+	struct fq_pie_sched_data *q = qdisc_priv(sch);
+	struct gnet_stats_queue qs = { 0 };
+	struct tc_fq_pie_xstats xstats;
+	u32 idx = cl - 1;
+
+	if (idx < q->flows_cnt) {
+		const struct fq_pie_flow *flow = &q->flows[idx];
+
+		memset(&xstats, 0, sizeof(xstats));
+		xstats.type = TCA_FQ_PIE_XSTATS_CLASS;
+		xstats.class_stats.prob =
+			READ_ONCE(flow->vars.prob) << BITS_PER_BYTE;
+		xstats.class_stats.delay =
+			div_u64(PSCHED_TICKS2NS(READ_ONCE(flow->vars.qdelay)),
+				NSEC_PER_USEC);
+		xstats.class_stats.deficit = READ_ONCE(flow->deficit);
+		xstats.class_stats.dq_rate_estimating =
+			READ_ONCE(q->p_params.dq_rate_estimator);
+
+		if (xstats.class_stats.dq_rate_estimating) {
+			xstats.class_stats.avg_dq_rate =
+				((u64)READ_ONCE(flow->vars.avg_dq_rate)
+				* PSCHED_TICKS_PER_SEC) >> PIE_SCALE;
+		}
+
+		qs.qlen    = READ_ONCE(flow->qlen);
+		qs.backlog = READ_ONCE(flow->backlog);
+	}
+	if (gnet_stats_copy_queue(d, NULL, &qs, qs.qlen) < 0)
+		return -1;
+	if (idx < q->flows_cnt)
+		return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
+	return 0;
+}
+
+static void fq_pie_walk(struct Qdisc *sch, struct qdisc_walker *arg)
+{
+	struct fq_pie_sched_data *q = qdisc_priv(sch);
+	unsigned int i;
+
+	if (arg->stop)
+		return;
+
+	for (i = 0; i < q->flows_cnt; i++) {
+		if (list_empty(&q->flows[i].flowchain)) {
+			arg->count++;
+			continue;
+		}
+		if (!tc_qdisc_stats_dump(sch, i + 1, arg))
+			break;
+	}
+}
+
+static const struct Qdisc_class_ops fq_pie_class_ops = {
+	.leaf		=	fq_pie_leaf,
+	.find		=	fq_pie_find,
+	.dump		=	fq_pie_dump_class,
+	.dump_stats	=	fq_pie_dump_class_stats,
+	.walk		=	fq_pie_walk,
+};
+
 static struct Qdisc_ops fq_pie_qdisc_ops __read_mostly = {
+	.cl_ops		= &fq_pie_class_ops,
 	.id		= "fq_pie",
 	.priv_size	= sizeof(struct fq_pie_sched_data),
 	.enqueue	= fq_pie_qdisc_enqueue,
-- 
2.34.1