Add support for printing per-flow PIE statistics exposed by the kernel
via the new TCA_FQ_PIE_XSTATS_CLASS type in tc_fq_pie_xstats.

'tc -s class show' against an fq_pie qdisc now prints:

 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. Apply the same fix to tc/q_pie.c, where avg_dq_rate was
also printed as a raw integer without a unit.

Update the UAPI header to mirror tc_fq_pie_cl_stats from the kernel.
Fix the 'delay' field comment in struct tc_pie_xstats from "in ms" to
"in microseconds" to match the kernel's
PSCHED_TICKS2NS / NSEC_PER_USEC conversion.

Add a 'tc -s class show' example to tc-fq_pie(8) with dq_rate_estimator
enabled, showing all per-flow fields (prob, delay, deficit, avg_dq_rate)
across multiple flows. Update tc-pie(8) avg_dq_rate example from a raw
integer to a formatted bits/second string.

The corresponding kernel patch can bew viewed: 
https://lore.kernel.org/netdev/20260531125314.22492-1-hemendranaik@gmail.com/

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 | 29 +++++++++++++++--
 man/man8/tc-fq_pie.8           | 19 ++++++++++++
 man/man8/tc-pie.8              |  2 +-
 tc/q_fq_pie.c                  | 57 +++++++++++++++++++++++-----------
 tc/q_pie.c                     |  4 +--
 5 files changed, 87 insertions(+), 24 deletions(-)

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index fb07a889..9cc040b1 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -910,9 +910,9 @@ enum {
 
 struct tc_pie_xstats {
 	__u64 prob;			/* current probability */
-	__u32 delay;			/* current delay in ms */
+	__u32 delay;			/* current delay in microseconds */
 	__u32 avg_dq_rate;		/* current average dq_rate in
-					 * bits/pie_time
+					 * bytes/second
 					 */
 	__u32 dq_rate_estimating;	/* is avg_dq_rate being calculated? */
 	__u32 packets_in;		/* total number of packets enqueued */
@@ -943,7 +943,12 @@ enum {
 };
 #define TCA_FQ_PIE_MAX   (__TCA_FQ_PIE_MAX - 1)
 
-struct tc_fq_pie_xstats {
+enum {
+	TCA_FQ_PIE_XSTATS_QDISC,
+	TCA_FQ_PIE_XSTATS_CLASS,
+};
+
+struct tc_fq_pie_qd_stats {
 	__u32 packets_in;	/* total number of packets enqueued */
 	__u32 dropped;		/* packets dropped due to fq_pie_action */
 	__u32 overlimit;	/* dropped due to lack of space in queue */
@@ -955,6 +960,24 @@ struct tc_fq_pie_xstats {
 	__u32 memory_usage;	/* total memory across all queues */
 };
 
+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	type;
+	union {
+		struct tc_fq_pie_qd_stats qdisc_stats;
+		struct tc_fq_pie_cl_stats class_stats;
+	};
+};
+
 /* CBS */
 struct tc_cbs_qopt {
 	__u8 offload;
diff --git a/man/man8/tc-fq_pie.8 b/man/man8/tc-fq_pie.8
index 457a56bb..1c8ca1a6 100644
--- a/man/man8/tc-fq_pie.8
+++ b/man/man8/tc-fq_pie.8
@@ -153,6 +153,25 @@ 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 15ms flows 3 dq_rate_estimator
+.br
+# tc -s class show dev eth0
+.br
+class fq_pie 200:1 parent 200:
+ (dropped 0, overlimits 0 requeues 0)
+ backlog 0b 0p requeues 0
+  prob 0.000000 delay 0us  deficit 1514 avg_dq_rate 0bit
+.br
+class fq_pie 200:2 parent 200:
+ (dropped 0, overlimits 0 requeues 0)
+ backlog 0b 0p requeues 0
+  prob 0.000000 delay 0us  deficit 1514 avg_dq_rate 0bit
+.br
+class fq_pie 200:3 parent 200:
+ (dropped 0, overlimits 0 requeues 0)
+ backlog 4470b 3p requeues 0
+  prob 0.509691 delay 6.1ms  deficit -82 avg_dq_rate 3906Kbit
+
 .SH SEE ALSO
 .BR tc (8),
 .BR tc-pie (8),
diff --git a/man/man8/tc-pie.8 b/man/man8/tc-pie.8
index 5a8c7820..ec0d4af2 100644
--- a/man/man8/tc-pie.8
+++ b/man/man8/tc-pie.8
@@ -115,7 +115,7 @@ is turned off.
    qdisc pie 8036: dev eth0 root refcnt 2 limit 1000p target 15.0ms tupdate 16.0ms alpha 2 beta 20
     Sent 63947420 bytes 42414 pkt (dropped 41, overlimits 0 requeues 0)
     backlog 271006b 179p requeues 0
-     prob 0.000092 delay 22200us avg_dq_rate 12145996
+     prob 0.000092 delay 22200us avg_dq_rate 10742Kbit
      pkts_in 41 overlimit 343 dropped 0 maxq 50 ecn_mark 0
 
  # tc qdisc add dev eth0 root pie limit 100 target 20ms tupdate 30ms ecn
diff --git a/tc/q_fq_pie.c b/tc/q_fq_pie.c
index dc2710cd..80b956e8 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);
+	if (st->type == TCA_FQ_PIE_XSTATS_QDISC) {
+		print_uint(PRINT_ANY, "pkts_in", "  pkts_in %u",
+			   st->qdisc_stats.packets_in);
+		print_uint(PRINT_ANY, "overlimit", " overlimit %u",
+			   st->qdisc_stats.overlimit);
+		print_uint(PRINT_ANY, "overmemory", " overmemory %u",
+			   st->qdisc_stats.overmemory);
+		print_uint(PRINT_ANY, "dropped", " dropped %u",
+			   st->qdisc_stats.dropped);
+		print_uint(PRINT_ANY, "ecn_mark", " ecn_mark %u",
+			   st->qdisc_stats.ecn_mark);
+		print_nl();
+		print_uint(PRINT_ANY, "new_flow_count", "  new_flow_count %u",
+			   st->qdisc_stats.new_flow_count);
+		print_uint(PRINT_ANY, "new_flows_len", " new_flows_len %u",
+			   st->qdisc_stats.new_flows_len);
+			print_uint(PRINT_ANY, "old_flows_len", " old_flows_len %u",
+				   st->qdisc_stats.old_flows_len);
+			print_uint(PRINT_ANY, "memory_used", " memory_used %u",
+				   st->qdisc_stats.memory_usage);
+	}
+
+	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();
-	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);
+	}
+
 
 	return 0;
 
diff --git a/tc/q_pie.c b/tc/q_pie.c
index 04c9aa61..97690d49 100644
--- a/tc/q_pie.c
+++ b/tc/q_pie.c
@@ -220,8 +220,8 @@ static int pie_print_xstats(const struct qdisc_util *qu, FILE *f,
 	print_string(PRINT_FP, NULL, " delay %s", sprint_time(st->delay, b1));
 
 	if (st->dq_rate_estimating)
-		print_uint(PRINT_ANY, "avg_dq_rate", " avg_dq_rate %u",
-			   st->avg_dq_rate);
+		tc_print_rate(PRINT_ANY, "avg_dq_rate", " avg_dq_rate %s",
+			      st->avg_dq_rate);
 
 	print_nl();
 	print_uint(PRINT_ANY, "pkts_in", "  pkts_in %u", st->packets_in);
-- 
2.34.1