Netdev List
 help / color / mirror / Atom feed
From: "Hemendra M. Naik" <hemendranaik@gmail.com>
To: netdev@vger.kernel.org
Cc: davem@davemloft.net, edumazet@google.com, kuba@kernel.org,
	pabeni@redhat.com, horms@kernel.org, jiri@resnulli.us,
	jhs@mojatatu.com, shuah@kernel.org, linux-kernel@vger.kernel.org,
	linux-kselftest@vger.kernel.org, vishy0777@gmail.com,
	tahiliani@nitk.edu.in,
	"Hemendra M. Naik" <hemendranaik@gmail.com>
Subject: [PATCH net-next v2 1/2]     net/sched: sch_fq_pie: add per-flow statistics via class ops
Date: Sun, 14 Jun 2026 18:19:59 +0530	[thread overview]
Message-ID: <20260614125000.6058-2-hemendranaik@gmail.com> (raw)
In-Reply-To: <20260614125000.6058-1-hemendranaik@gmail.com>

  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 active delay estimation mode

  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.

  Also correct the avg_dq_rate comment in tc_pie_xstats from
  "bits/pie_time" to "bytes/second" to match the actual kernel
  conversion (avg_dq_rate * PSCHED_TICKS_PER_SEC >> PIE_SCALE).

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>
---
 Changelog:
  v2: Addressed ABI backward compatibility issue for tc_fq_pie_xstats.
  
  v1: https://lore.kernel.org/netdev/20260531125314.22492-2-hemendranaik@gmail.com

---
 include/uapi/linux/pkt_sched.h       |  29 ++++++-
 net/sched/sch_fq_pie.c               | 118 +++++++++++++++++++++++++--
 tools/include/uapi/linux/pkt_sched.h |   4 +-
 3 files changed, 141 insertions(+), 10 deletions(-)

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 66e8072f44df..fd4daad98abc 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 */
@@ -943,6 +943,25 @@ 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 */
@@ -953,6 +972,12 @@ 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 7becbf5362b3..2778d3cda956 100644
--- a/net/sched/sch_fq_pie.c
+++ b/net/sched/sch_fq_pie.c
@@ -330,7 +330,7 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt,
 	/* tupdate is in jiffies */
 	if (tb[TCA_FQ_PIE_TUPDATE])
 		WRITE_ONCE(q->p_params.tupdate,
-			usecs_to_jiffies(nla_get_u32(tb[TCA_FQ_PIE_TUPDATE])));
+			   usecs_to_jiffies(nla_get_u32(tb[TCA_FQ_PIE_TUPDATE])));
 
 	if (tb[TCA_FQ_PIE_ALPHA])
 		WRITE_ONCE(q->p_params.alpha,
@@ -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);
@@ -517,10 +519,10 @@ static int fq_pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
 	st.packets_in	= q->stats.packets_in;
 	st.overlimit	= q->stats.overlimit;
 	st.overmemory	= q->overmemory;
-	st.dropped	= q->stats.dropped;
-	st.ecn_mark	= q->stats.ecn_mark;
-	st.new_flow_count = q->new_flow_count;
-	st.memory_usage   = q->memory_usage;
+	st.dropped		= q->stats.dropped;
+	st.ecn_mark		= q->stats.ecn_mark;
+	st.new_flow_count	= q->new_flow_count;
+	st.memory_usage	= q->memory_usage;
 
 	list_for_each(pos, &q->new_flows)
 		st.new_flows_len++;
@@ -561,7 +563,111 @@ 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,
diff --git a/tools/include/uapi/linux/pkt_sched.h b/tools/include/uapi/linux/pkt_sched.h
index 587481a19433..45ea10026742 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 micoseconds */
+	__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


  reply	other threads:[~2026-06-14 12:50 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-06-14 12:49 [PATCH net-next v2 0/2] net/sched: sch_fq_pie: add per-flow class statistics Hemendra M. Naik
2026-06-14 12:49 ` Hemendra M. Naik [this message]
2026-06-14 12:50 ` [PATCH net-next v2 2/2] selftests: tc-testing: add fq_pie per-flow class stats test Hemendra M. Naik

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260614125000.6058-2-hemendranaik@gmail.com \
    --to=hemendranaik@gmail.com \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=horms@kernel.org \
    --cc=jhs@mojatatu.com \
    --cc=jiri@resnulli.us \
    --cc=kuba@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=shuah@kernel.org \
    --cc=tahiliani@nitk.edu.in \
    --cc=vishy0777@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox