[PATCH iproute2-next v4 1/3] tc: fq_pie: add support for printing per-flow PIE statistics

["Hemendra M. Naik" <hemendranaik@gmail.com>]

`tc -s class show` for an fq_pie qdisc now prints the following
per-flow PIE statistics:

 prob           drop probability for the flow
 delay          per-flow queue sojourn time (microseconds)
 deficit        remaining DRR byte credits (signed integer)
 avg_dq_rate    dequeue rate estimate in bytes/second
                (dq_rate_estimator mode only)

avg_dq_rate is formatted using tc_print_rate(), which converts the
kernel's bytes/second value to a human-readable bits/second string
(e.g. 3906Kbit), consistent with how other tc schedulers display
rate fields.

Update the UAPI header to mirror tc_fq_pie_cl_stats from the kernel.

Add `tc -s class show` examples to tc-fq_pie(8) demonstrating the new
per-flow statistics with and without dq_rate_estimator enabled.

Signed-off-by: Hemendra M. Naik <hemendranaik@gmail.com>
Signed-off-by: Vishal Kamath <vishy0777@gmail.com>
Signed-off-by: Mohit P. Tahiliani <tahiliani@nitk.edu.in>
---
 include/uapi/linux/pkt_sched.h | 25 ++++++++++++++
 man/man8/tc-fq_pie.8           | 18 +++++++++++
 tc/q_fq_pie.c                  | 59 +++++++++++++++++++++++-----------
 3 files changed, 83 insertions(+), 19 deletions(-)

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index d1f67ef8..b99312d2 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -953,6 +953,25 @@ 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_xqd_stats {
+	/* placeholder for new qdisc-level stats */
+};
+
 struct tc_fq_pie_xstats {
 	__u32 packets_in;	/* total number of packets enqueued */
 	__u32 dropped;		/* packets dropped due to fq_pie_action */
@@ -963,6 +982,12 @@ 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;
+	union {
+		struct tc_fq_pie_cl_stats class_stats;
+		struct tc_fq_pie_xqd_stats xqdisc_stats;
+	};
+
 };
 
 /* CBS */
diff --git a/man/man8/tc-fq_pie.8 b/man/man8/tc-fq_pie.8
index 457a56bb..8027783c 100644
--- a/man/man8/tc-fq_pie.8
+++ b/man/man8/tc-fq_pie.8
@@ -153,6 +153,24 @@ dq_rate_estimator
   pkts_in 6082 overlimit 0 overmemory 0 dropped 4 ecn_mark 0
   new_flow_count 94 new_flows_len 0 old_flows_len 8 memory_used 1157632
 
+# tc qdisc add dev eth0 parent 100:1 handle 200: fq_pie target 2ms flows 3
+.br
+# tc -s class show dev eth0
+.br
+class fq_pie 200:2 parent 200:
+ Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
+ backlog 22800b 2p requeues 0
+  prob 0.57679 delay 2.38ms deficit -52
+
+# tc qdisc add dev eth0 parent 100:1 handle 200: fq_pie target 2ms flows 3 dq_rate_estimator
+.br
+# tc -s class show dev eth0
+.br
+class fq_pie 200:2 parent 200:
+ Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
+ backlog 22800b 2p requeues 0
+  prob 0.57679 delay 2.38ms deficit -52 avg_dq_rate 10742Kbit
+
 .SH SEE ALSO
 .BR tc (8),
 .BR tc-pie (8),
diff --git a/tc/q_fq_pie.c b/tc/q_fq_pie.c
index dc2710cd..1b89ee3a 100644
--- a/tc/q_fq_pie.c
+++ b/tc/q_fq_pie.c
@@ -274,6 +274,8 @@ static int fq_pie_print_xstats(const struct qdisc_util *qu, FILE *f,
 {
 	struct tc_fq_pie_xstats _st = {}, *st;
 
+	SPRINT_BUF(b1);
+
 	if (xstats == NULL)
 		return 0;
 
@@ -283,25 +285,44 @@ static int fq_pie_print_xstats(const struct qdisc_util *qu, FILE *f,
 		st = &_st;
 	}
 
-	print_uint(PRINT_ANY, "pkts_in", "  pkts_in %u",
-		   st->packets_in);
-	print_uint(PRINT_ANY, "overlimit", " overlimit %u",
-		   st->overlimit);
-	print_uint(PRINT_ANY, "overmemory", " overmemory %u",
-		   st->overmemory);
-	print_uint(PRINT_ANY, "dropped", " dropped %u",
-		   st->dropped);
-	print_uint(PRINT_ANY, "ecn_mark", " ecn_mark %u",
-		   st->ecn_mark);
-	print_nl();
-	print_uint(PRINT_ANY, "new_flow_count", "  new_flow_count %u",
-		   st->new_flow_count);
-	print_uint(PRINT_ANY, "new_flows_len", " new_flows_len %u",
-		   st->new_flows_len);
-	print_uint(PRINT_ANY, "old_flows_len", " old_flows_len %u",
-		   st->old_flows_len);
-	print_uint(PRINT_ANY, "memory_used", " memory_used %u",
-		   st->memory_usage);
+	if (!st->type || st->type == TCA_FQ_PIE_XSTATS_QDISC) {
+		print_uint(PRINT_ANY, "pkts_in", "  pkts_in %u",
+			   st->packets_in);
+		print_uint(PRINT_ANY, "overlimit", " overlimit %u",
+			   st->overlimit);
+		print_uint(PRINT_ANY, "overmemory", " overmemory %u",
+			   st->overmemory);
+		print_uint(PRINT_ANY, "dropped", " dropped %u",
+			   st->dropped);
+		print_uint(PRINT_ANY, "ecn_mark", " ecn_mark %u",
+			   st->ecn_mark);
+		print_nl();
+		print_uint(PRINT_ANY, "new_flow_count", "  new_flow_count %u",
+			   st->new_flow_count);
+		print_uint(PRINT_ANY, "new_flows_len", " new_flows_len %u",
+			   st->new_flows_len);
+		print_uint(PRINT_ANY, "old_flows_len", " old_flows_len %u",
+			   st->old_flows_len);
+		print_uint(PRINT_ANY, "memory_used", " memory_used %u",
+			   st->memory_usage);
+		print_nl();
+	}
+
+	if (st->type == TCA_FQ_PIE_XSTATS_CLASS) {
+		print_float(PRINT_ANY, "prob", " prob %lg",
+			    (double)st->class_stats.prob / (double)UINT64_MAX);
+		print_uint(PRINT_JSON, "delay", NULL, st->class_stats.delay);
+		print_string(PRINT_FP, NULL, " delay %s",
+			     sprint_time(st->class_stats.delay, b1));
+		print_int(PRINT_ANY, "deficit", " deficit %d",
+			  st->class_stats.deficit);
+
+		if (st->class_stats.dq_rate_estimating) {
+			tc_print_rate(PRINT_ANY, "avg_dq_rate", " avg_dq_rate %s",
+				      st->class_stats.avg_dq_rate);
+		}
+		print_nl();
+	}
 
 	return 0;
 
-- 
2.34.1