[PATCH net-next v4 0/3] net/sched: sch_fq_pie: add per-flow class statistics

[PATCH net-next v4 0/3] net/sched: sch_fq_pie: add per-flow class statistics

[Hemendra M. Naik]

FQ-PIE runs an independent PIE controller per flow but exposes no
per-flow statistics. This series wires up fq_pie_class_ops to expose
per-flow AQM state (prob, delay, deficit, avg_dq_rate)
via 'tc -s class show', following a similar pattern as FQ-CoDel.
---
Changelog:

v4:
- Fixed unaligned commit message; moved typo fixes to another patch.

v3: https://lore.kernel.org/netdev/20260630183702.170798-1-hemendranaik@gmail.com/
- No changes since v2.
- Resent after the previous submission was deferred due to the
  net-next tree closing during review.
- Updated corresponding iproute2 patch in response to review comments;
  kernel patches unchanged.

v2: https://lore.kernel.org/netdev/20260614125000.6058-1-hemendranaik@gmail.com/
- Addressed ABI backward compatibility issue for tc_fq_pie_xstats.

v1: https://lore.kernel.org/netdev/20260531125314.22492-1-hemendranaik@gmail.com/
- Initial submission

Hemendra M. Naik (3):
  net/sched: sch_fq_pie: add per-flow statistics via class ops
  selftests: tc-testing: add fq_pie per-flow class stats test
  net/sched: pie: correct tc_pie_xstats field documentation

 include/uapi/linux/pkt_sched.h                |  29 ++++-
 net/sched/sch_fq_pie.c                        | 109 +++++++++++++++++-
 tools/include/uapi/linux/pkt_sched.h          |   4 +-
 .../tc-testing/tc-tests/qdiscs/fq_pie.json    |  22 ++++
 4 files changed, 159 insertions(+), 5 deletions(-)

--
2.34.1

[PATCH net-next v4 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 to support both qdisc and class-level
extended statistics.

- Add enum with QDISC and CLASS type discriminators.
- Add struct tc_fq_pie_cl_stats for per-flow metrics (prob,
  delay, deficit, avg_dq_rate, dq_rate_estimating).
- Add empty struct tc_fq_pie_xqd_stats placeholder.

Wire up fq_pie_class_ops (.walk, .dump, .dump_stats) so that
'tc -s class show' against an fq_pie qdisc reports per-flow state:

  prob               per-flow PIE drop probability
  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)
  dq_rate_estimating flag indicating whether avg_dq_rate
		     is being calculated

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 ++++++++
 net/sched/sch_fq_pie.c         | 109 ++++++++++++++++++++++++++++++++-
 2 files changed, 133 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 490efd288526..9a86fa4d6846 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/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c
index 72f48fa4010b..664fef18568b 100644
--- a/net/sched/sch_fq_pie.c
+++ b/net/sched/sch_fq_pie.c
@@ -509,7 +509,9 @@ 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);
@@ -561,7 +563,112 @@ 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 unsigned long fq_pie_bind(struct Qdisc *sch, unsigned long parent,
+				 u32 classid)
+{
+	return 0;
+}
+
+static void fq_pie_unbind(struct Qdisc *q, unsigned long cl)
+{
+}
+
+static struct tcf_block *fq_pie_tcf_block(struct Qdisc *sch, unsigned long cl,
+					  struct netlink_ext_ack *extack)
+{
+	struct fq_pie_sched_data *q = qdisc_priv(sch);
+
+	if (cl)
+		return NULL;
+	return q->block;
+}
+
+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 =
+			((u32)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 =
+				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,
+	.tcf_block	=	fq_pie_tcf_block,
+	.bind_tcf	=	fq_pie_bind,
+	.unbind_tcf	=	fq_pie_unbind,
+	.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

Re: [PATCH net-next v4 1/3] net/sched: sch_fq_pie: add per-flow statistics via class ops

[Simon Horman]

On Mon, Jul 27, 2026 at 10:10:54PM +0530, Hemendra M. Naik wrote:

...

> +static struct tcf_block *fq_pie_tcf_block(struct Qdisc *sch, unsigned long cl,
> +					  struct netlink_ext_ack *extack)
> +{
> +	struct fq_pie_sched_data *q = qdisc_priv(sch);
> +
> +	if (cl)
> +		return NULL;
> +	return q->block;
> +}

Hi,

The AI-generated review of this patch on netdev-ai [1] reports several
findings. And while I'd appreciate it if you could look over each of them
the one below seems to warrant highlighting here.

[1] https://netdev-ai.bots.linux.dev/sashiko/#/patchset/20260727164056.106203-1-hemendranaik%40gmail.com?part=1

   Is the side effect of making fq_pie filter-capable intended, and should
   it be described in the commit message?

   Before this patch fq_pie_qdisc_ops had no .cl_ops, so filter attachment
   was rejected in net/sched/cls_api.c:__tcf_qdisc_find():

	cops = (*q)->ops->cl_ops;
	if (!cops) {
		NL_SET_ERR_MSG(extack, "Qdisc not classful");
		err = -EINVAL;

   q->filter_list was therefore always NULL and the filter branch of
   fq_pie_classify() was unreachable since fq_pie was added.  With .cl_ops
   present and fq_pie_tcf_block() returning q->block, 'tc filter add ...
   parent <fq_pie handle>' now succeeds and classifier verdicts plus
   classid-driven flow selection become live in the enqueue fast path.

   That newly reachable code does not handle TC_ACT_CONSUMED:

   net/sched/sch_fq_pie.c:fq_pie_classify() {
	result = tcf_classify_qdisc(skb, filter, &res, false);
	if (result >= 0) {
		switch (result) {
		case TC_ACT_STOLEN:
		case TC_ACT_QUEUED:
		case TC_ACT_TRAP:
			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
			fallthrough;
		case TC_ACT_SHOT:
			return 0;
		}
		if (TC_H_MIN(res.classid) <= q->flows_cnt)
			return TC_H_MIN(res.classid);
	}

   TC_ACT_CONSUMED is TC_ACT_VALUE_MAX + 1, so it is >= 0 and matches no
   case arm, and control reaches the classid path.  act_ct produces it
   after the skb ownership has already been handed away:

   net/sched/act_ct.c:tcf_ct_act() {
   out_frag:
	if (err != -EINPROGRESS)
		tcf_action_inc_drop_qstats(&c->common);
	return TC_ACT_CONSUMED;

   tcf_action_exec() propagates any value != TC_ACT_PIPE and
   __tcf_classify() returns it verbatim.  For a filter such as
	tc filter add dev eth0 parent 1: matchall action ct

   with no flowid, res.classid is 0, TC_H_MIN(0) <= flows_cnt holds and 0
   is returned, so fq_pie_qdisc_enqueue() frees the consumed skb a second
   time:

	idx = fq_pie_classify(skb, sch, &ret);
	if (idx == 0) {
		if (ret & __NET_XMIT_BYPASS)
			qdisc_qstats_drop(sch);
		__qdisc_drop(skb, to_free);

   and with 'flowid 1:N' a valid flow index is returned instead, so
   flow_queue_add() links the already freed skb into q->flows[idx].  Can
   fragmented traffic hitting that qdisc then cause a double free or
   use-after-free?

   That TC_ACT_CONSUMED is expected from qdisc-attached filter chains is
   also visible in net/sched/cls_api.c:tcf_qevent_handle(), which has an
   explicit case TC_ACT_CONSUMED: arm that must not free the skb.

   fq_codel, sfq and cake have the same missing arm, but for fq_pie the
   path only becomes reachable with this patch.

...

[PATCH net-next v4 2/3] selftests: tc-testing: add fq_pie per-flow class stats test

[Hemendra M. Naik]

Add a tc-testing entry (id: 83c0) to verify the fq_pie class ops
wired up in the previous patch do not crash and integrate cleanly
with the tc class show path.

The test creates an fq_pie root qdisc on a dummy interface and runs
'tc -s class show'.

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>
---
 .../tc-testing/tc-tests/qdiscs/fq_pie.json    | 22 +++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json
index 229fe1bf4a90..88139f429430 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json
@@ -40,5 +40,27 @@
         "matchPattern": "qdisc fq_pie 1: root refcnt [0-9]+ limit 1p",
         "matchCount": "1",
         "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"]
+    },
+    {
+        "id": "83c0",
+        "name": "FQ-PIE class stats accessible via tc class show",
+        "category": [
+            "qdisc",
+            "fq_pie"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$TC qdisc add dev $DUMMY handle 1: root fq_pie"
+        ],
+        "cmdUnderTest": "$TC -s class show dev $DUMMY",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s class show dev $DUMMY",
+        "matchPattern": "class fq_pie",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
     }
 ]
--
2.34.1

[PATCH net-next v4 3/3] net/sched: pie: correct tc_pie_xstats field documentation

[Hemendra M. Naik]

The comments describing `struct tc_pie_xstats` do not match the values
exported by the kernel.

Update the `delay` field comment to indicate that the value is reported
in microseconds, matching the `PSCHED_TICKS2NS() / NSEC_PER_USEC`
conversion.

Similarly, update the `avg_dq_rate` field comment to indicate that the
value is reported in bytes/second, matching the conversion performed by
`avg_dq_rate * PSCHED_TICKS_PER_SEC >> PIE_SCALE`.

These are documentation-only changes and do not modify the UAPI layout
or runtime behavior.

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       | 4 ++--
 tools/include/uapi/linux/pkt_sched.h | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 9a86fa4d6846..26b7e6964adb 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -920,9 +920,9 @@ 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 */
diff --git a/tools/include/uapi/linux/pkt_sched.h b/tools/include/uapi/linux/pkt_sched.h
index 587481a19433..9bc190f0b3cf 100644
--- a/tools/include/uapi/linux/pkt_sched.h
+++ b/tools/include/uapi/linux/pkt_sched.h
@@ -847,8 +847,8 @@ enum {
 
 struct tc_pie_xstats {
 	__u32 prob;             /* current probability */
-	__u32 delay;            /* current delay in ms */
-	__u32 avg_dq_rate;      /* current average dq_rate in bits/pie_time */
+	__u32 delay;            /* current delay in microseconds */
+	__u32 avg_dq_rate;      /* current average dq_rate in bytes/second */
 	__u32 packets_in;       /* total number of packets enqueued */
 	__u32 dropped;          /* packets dropped due to pie_action */
 	__u32 overlimit;        /* dropped due to lack of space in queue */
--
2.34.1