Message-Id: <1386386283-16728-1-git-send-email-subramanian.vijay@gmail.com>
Date:	Fri,  6 Dec 2013 19:18:03 -0800
From:	Vijay Subramanian <subramanian.vijay@...il.com>
To:	netdev@...r.kernel.org
Cc:	davem@...emloft.net, shemminger@...tta.com, eric.dumazet@...il.com,
	Vijay Subramanian <subramanian.vijay@...il.com>,
	Mythili Prabhu <mysuryan@...co.com>,
	Dave Taht <dave.taht@...ferbloat.net>
Subject: [PATCH v4 net-next] net: pkt_sched: PIE AQM scheme

From: Vijay Subramanian <vijaynsu@...co.com>

Proportional Integral controller Enhanced (PIE) is a scheduler to address the
bufferbloat problem.

>From the IETF draft below:
" Bufferbloat is a phenomenon where excess buffers in the network cause high
latency and jitter. As more and more interactive applications (e.g. voice over
IP, real time video streaming and financial transactions) run in the Internet,
high latency and jitter degrade application performance. There is a pressing
need to design intelligent queue management schemes that can control latency
and jitter; and hence provide desirable quality of service to users.

We present here a lightweight design, PIE(Proportional Integral controller
Enhanced) that can effectively control the average queueing latency to a target
value. Simulation results, theoretical analysis and Linux testbed results have
shown that PIE can ensure low latency and achieve high link utilization under
various congestion situations. The design does not require per-packet
timestamp, so it incurs very small overhead and is simple enough to implement
in both hardware and software.  "

Many thanks to Dave Taht for extensive feedback, reviews, testing and
suggestions. Thanks also to Stephen Hemminger and Eric Dumazet for reviews and
suggestions.  Naeem Khademi and Dave Taht independently
contributed to ECN support.

For more information, please see technical paper about PIE in the IEEE
Conference on High Performance Switching and Routing 2013. A copy of the paper
can be found at ftp://ftpeng.cisco.com/pie/.

Please also refer to the IETF draft submission at
http://tools.ietf.org/html/draft-pan-tsvwg-pie-00

All relevant code, documents and test scripts and results can be found at
ftp://ftpeng.cisco.com/pie/.

For problems with the iproute2/tc or Linux kernel code, please contact Vijay
Subramanian (vijaynsu@...co.com or subramanian.vijay@...il.com) Mythili Prabhu
(mysuryan@...co.com)

Signed-off-by: Vijay Subramanian <subramanian.vijay@...il.com>
Signed-off-by: Mythili Prabhu <mysuryan@...co.com>
CC: Dave Taht <dave.taht@...ferbloat.net>
---
Changes from V3: Change default value of limit to 1000 packets and increase
QUEUE_THRESHOLD to 10000 bytes. Refactor pie_qdisc_enqueue() to update stats
correctly.

Changes from V2: Prevent timer deadlock on qdisc destroy. Also maintain timer
period 'tupdate' in us throughout instead of in psched units.

Changes from V1: Addressed review comments regarding coding style and various
implementation issues. In particular 1) add locking for the timer and 2) use
psched timer directly instead of a custom timer based on psched.


 include/uapi/linux/pkt_sched.h |   26 ++
 net/sched/Kconfig              |   13 +
 net/sched/Makefile             |    1 +
 net/sched/sch_pie.c            |  560 ++++++++++++++++++++++++++++++++++++++++
 4 files changed, 600 insertions(+)
 create mode 100644 net/sched/sch_pie.c

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index f2624b5..2fb6e6d 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -787,4 +787,30 @@ struct tc_fq_qd_stats {
 	__u32	throttled_flows;
 	__u32	pad;
 };
+
+/*PIE*/
+enum {
+	TCA_PIE_UNSPEC,
+	TCA_PIE_TARGET,
+	TCA_PIE_LIMIT,
+	TCA_PIE_TUPDATE,
+	TCA_PIE_ALPHA,
+	TCA_PIE_BETA,
+	TCA_PIE_ECN,
+	TCA_PIE_BYTEMODE,
+	__TCA_PIE_MAX
+};
+#define TCA_PIE_MAX   (__TCA_PIE_MAX - 1)
+
+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 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 */
+	__u32 maxq;             /* maximum queue size */
+	__u32 ecn_mark;         /* packets marked with ecn*/
+};
+
 #endif
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index c03a32a..57c5403 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -286,6 +286,19 @@ config NET_SCH_FQ
 
 	  If unsure, say N.
 
+config NET_SCH_PIE
+        tristate "Proportional Integral controller Enhanced (PIE) scheduler"
+        help
+	  Say Y here if you want to use the Proportional Integral controller
+	  Enhanced scheduler packet scheduling algorithm.
+	  For more information, please see
+	  http://tools.ietf.org/html/draft-pan-tsvwg-pie-00
+
+          To compile this driver as a module, choose M here: the module
+          will be called sch_pie.
+
+          If unsure, say N.
+
 config NET_SCH_INGRESS
 	tristate "Ingress Qdisc"
 	depends on NET_CLS_ACT
diff --git a/net/sched/Makefile b/net/sched/Makefile
index e5f9abe..5b4ece9 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -40,6 +40,7 @@ obj-$(CONFIG_NET_SCH_QFQ)	+= sch_qfq.o
 obj-$(CONFIG_NET_SCH_CODEL)	+= sch_codel.o
 obj-$(CONFIG_NET_SCH_FQ_CODEL)	+= sch_fq_codel.o
 obj-$(CONFIG_NET_SCH_FQ)	+= sch_fq.o
+obj-$(CONFIG_NET_SCH_PIE)	+= sch_pie.o
 
 obj-$(CONFIG_NET_CLS_U32)	+= cls_u32.o
 obj-$(CONFIG_NET_CLS_ROUTE4)	+= cls_route.o
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
new file mode 100644
index 0000000..1658b65
--- /dev/null
+++ b/net/sched/sch_pie.c
@@ -0,0 +1,560 @@
+/* Copyright (C) 2013 Cisco Systems, Inc, 2013.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Author: Vijay Subramanian <vijaynsu@...co.com>
+ * Author: Mythili Prabhu <mysuryan@...co.com>
+ *
+ * ECN support is added by Naeem Khademi <naeemk@....uio.no>
+ * University of Oslo, Norway.
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <net/pkt_sched.h>
+#include <net/inet_ecn.h>
+
+#define QUEUE_THRESHOLD 10000
+#define DQCOUNT_INVALID -1
+#define MAX_PROB  0xffffffff
+#define PIE_SCALE 8
+
+/* parameters used */
+struct pie_params {
+	psched_time_t target;	/* user specified target delay in pschedtime */
+	u32 tupdate;		/* frequency with which the timer fires (us) */
+	u32 limit;		/* number of packets that can be enqueued */
+	u32 alpha;		/* alpha and beta are between -4 and 4 */
+	u32 beta;		/* and are used for shift relative to 1 */
+	bool ecn;		/* true if ecn is enabled */
+	bool bytemode;		/* to scale drop early prob based on pkt size */
+};
+
+/* variables used */
+struct pie_vars {
+	u32 prob;		/* probability but scaled by u32 limit. */
+	psched_time_t burst_time;
+	psched_time_t qdelay;
+	psched_time_t qdelay_old;
+	u64 dq_count;		/* measured in bytes */
+	psched_time_t dq_tstamp;	/* drain rate */
+	u32 avg_dq_rate;	/* bytes per pschedtime tick,scaled */
+	u32 qlen_old;		/* in bytes */
+};
+
+/* statistics gathering*/
+struct pie_stats {
+	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 */
+	u32 maxq;		/* maximum queue size */
+	u32 ecn_mark;		/* packets marked with ECN */
+};
+
+/* private data for the Qdisc */
+struct pie_sched_data {
+	struct pie_params params;
+	struct pie_vars vars;
+	struct pie_stats stats;
+	struct timer_list adapt_timer;
+};
+
+static void pie_params_init(struct pie_params *params)
+{
+	params->alpha = 2;
+	params->beta = 20;
+	params->tupdate = 30 * USEC_PER_MSEC;	/* 30 ms */
+	params->limit = 1000;	/* default of 1000 packets */
+	params->target = PSCHED_NS2TICKS(20 * NSEC_PER_MSEC);	/* 20 ms */
+	params->ecn = false;
+	params->bytemode = false;
+}
+
+static void pie_vars_init(struct pie_vars *vars)
+{
+	vars->dq_count = DQCOUNT_INVALID;
+	vars->avg_dq_rate = 0;
+	/* default of 100 ms in pschedtime  */
+	vars->burst_time = PSCHED_NS2TICKS(100 * NSEC_PER_MSEC);
+}
+
+static bool drop_early(struct Qdisc *sch, u32 packet_size)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+	u32 rnd;
+	u32 local_prob = q->vars.prob;
+	u32 mtu = psched_mtu(qdisc_dev(sch));
+
+	/* If there is still burst allowance left skip random early drop */
+	if (q->vars.burst_time > 0)
+		return false;
+
+	/* If current delay is less than half of target, and
+	 * if drop prob is low already, disable early_drop
+	 */
+	if ((q->vars.qdelay < q->params.target / 2)
+	    && (q->vars.prob < MAX_PROB / 5))
+		return false;
+
+	/* If we have fewer than 2 mtu-sized packets, disable drop_early,
+	 * similar to min_th in RED
+	 */
+	if (sch->qstats.backlog < 2 * mtu)
+		return false;
+
+	/* If bytemode is turned on, use packet size to compute new
+	 * probablity. Smaller packets will have lower drop prob in this case
+	 */
+	if (q->params.bytemode && packet_size <= mtu)
+		local_prob = (local_prob / mtu) * packet_size;
+	else
+		local_prob = q->vars.prob;
+
+	rnd = net_random();
+	if (rnd < local_prob)
+		return true;
+
+	return false;
+}
+
+static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+	bool enqueue = false;
+
+	if (unlikely(qdisc_qlen(sch) >= sch->limit)) {
+		q->stats.overlimit++;
+		goto out;
+	}
+
+	if (!drop_early(sch, skb->len)) {
+		enqueue = true;
+	} else if (q->params.ecn && (q->vars.prob <= MAX_PROB / 10) &&
+		   INET_ECN_set_ce(skb)) {
+		/* If packet is ecn capable, mark it if drop probability
+		 * is lower than 10%, else drop it.
+		 */
+		q->stats.ecn_mark++;
+		enqueue = true;
+	}
+
+	/* we can enqueue the packet */
+	if (enqueue) {
+		q->stats.packets_in++;
+		if (qdisc_qlen(sch) > q->stats.maxq)
+			q->stats.maxq = qdisc_qlen(sch);
+
+		return qdisc_enqueue_tail(skb, sch);
+	}
+
+out:
+	q->stats.dropped++;
+	return qdisc_drop(skb, sch);
+}
+
+static const struct nla_policy pie_policy[TCA_PIE_MAX + 1] = {
+	[TCA_PIE_TARGET] = {.type = NLA_U32},
+	[TCA_PIE_LIMIT] = {.type = NLA_U32},
+	[TCA_PIE_TUPDATE] = {.type = NLA_U32},
+	[TCA_PIE_ALPHA] = {.type = NLA_U32},
+	[TCA_PIE_BETA] = {.type = NLA_U32},
+	[TCA_PIE_ECN] = {.type = NLA_U32},
+	[TCA_PIE_BYTEMODE] = {.type = NLA_U32},
+};
+
+static int pie_change(struct Qdisc *sch, struct nlattr *opt)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+	struct nlattr *tb[TCA_PIE_MAX + 1];
+	unsigned int qlen;
+	int err;
+
+	if (!opt)
+		return -EINVAL;
+
+	err = nla_parse_nested(tb, TCA_PIE_MAX, opt, pie_policy);
+	if (err < 0)
+		return err;
+
+	sch_tree_lock(sch);
+
+	/* convert from microseconds to pschedtime */
+	if (tb[TCA_PIE_TARGET]) {
+		/* target is in us */
+		u32 target = nla_get_u32(tb[TCA_PIE_TARGET]);
+		/* convert to pschedtime */
+		q->params.target = PSCHED_NS2TICKS((u64)target * NSEC_PER_USEC);
+	}
+
+	/* tupdate is in us */
+	if (tb[TCA_PIE_TUPDATE])
+		q->params.tupdate = nla_get_u32(tb[TCA_PIE_TUPDATE]);
+
+	if (tb[TCA_PIE_LIMIT]) {
+		u32 limit = nla_get_u32(tb[TCA_PIE_LIMIT]);
+		q->params.limit = limit;
+		sch->limit = limit;
+	}
+
+	if (tb[TCA_PIE_ALPHA])
+		q->params.alpha = nla_get_u32(tb[TCA_PIE_ALPHA]);
+
+	if (tb[TCA_PIE_BETA])
+		q->params.beta = nla_get_u32(tb[TCA_PIE_BETA]);
+
+	if (tb[TCA_PIE_ECN])
+		q->params.ecn = nla_get_u32(tb[TCA_PIE_ECN]);
+
+	if (tb[TCA_PIE_BYTEMODE])
+		q->params.bytemode = nla_get_u32(tb[TCA_PIE_BYTEMODE]);
+
+	/* Drop excess packets if new limit is lower */
+	qlen = sch->q.qlen;
+	while (sch->q.qlen > sch->limit) {
+		struct sk_buff *skb = __skb_dequeue(&sch->q);
+
+		sch->qstats.backlog -= qdisc_pkt_len(skb);
+		qdisc_drop(skb, sch);
+	}
+	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+
+	sch_tree_unlock(sch);
+	return 0;
+}
+
+static void pie_process_dequeue(struct Qdisc *sch, struct sk_buff *skb)
+{
+
+	struct pie_sched_data *q = qdisc_priv(sch);
+	int qlen = sch->qstats.backlog;	/* current queue size in bytes */
+
+	/* If current queue is about 10 packets or more and dq_count is unset
+	 *  we have enough packets to calculate the drain rate. Save
+	 *  current time as dq_tstamp and start measurement cycle.
+	 */
+	if (qlen >= QUEUE_THRESHOLD && q->vars.dq_count == DQCOUNT_INVALID) {
+		q->vars.dq_tstamp = psched_get_time();
+		q->vars.dq_count = 0;
+	}
+
+	/*  Calculate the average drain rate from this value.  If queue length
+	 *  has receded to a small value viz., <= QUEUE_THRESHOLD bytes,reset
+	 *  the dq_count to -1 as we don't have enough packets to calculate the
+	 *  drain rate anymore The following if block is entered only when we
+	 *  have a substantial queue built up (QUEUE_THRESHOLD bytes or more)
+	 *  and we calculate the drain rate for the threshold here.  dq_count is
+	 *  in bytes, time difference in psched_time, hence rate is in
+	 *  bytes/psched_time.
+	 */
+	if (q->vars.dq_count != DQCOUNT_INVALID) {
+
+		q->vars.dq_count += skb->len;
+
+		if (q->vars.dq_count >= QUEUE_THRESHOLD) {
+			psched_time_t now = psched_get_time();
+			u32 dtime = now - q->vars.dq_tstamp;
+			u32 count = q->vars.dq_count << PIE_SCALE;
+
+			if (dtime == 0)
+				return;
+
+			count = count / dtime;
+
+			if (q->vars.avg_dq_rate == 0)
+				q->vars.avg_dq_rate = count;
+			else
+				q->vars.avg_dq_rate =
+				    (q->vars.avg_dq_rate -
+				     (q->vars.avg_dq_rate >> 3)) + (count >> 3);
+
+			/* If the queue has receded below the threshold, we hold
+			 * on to the last drain rate calculated, else we reset
+			 * dq_count to 0 to re-enter the if block when the next
+			 * packet is dequeued
+			 */
+			if (qlen < QUEUE_THRESHOLD)
+				q->vars.dq_count = DQCOUNT_INVALID;
+			else {
+				q->vars.dq_count = 0;
+				q->vars.dq_tstamp = psched_get_time();
+			}
+
+			if (q->vars.burst_time > 0) {
+				if (q->vars.burst_time > dtime)
+					q->vars.burst_time -= dtime;
+				else
+					q->vars.burst_time = 0;
+			}
+		}
+	}
+}
+
+static void calculate_probability(struct Qdisc *sch)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+	u32 qlen = sch->qstats.backlog;	/* queue size in bytes */
+	psched_time_t qdelay = 0;	/* in pschedtime */
+	psched_time_t qdelay_old = q->vars.qdelay;	/* in pschedtime */
+	s32 delta = 0;		/* determines the change in probability  */
+	u32 oldprob;
+	u32 alpha, beta;
+	bool update_prob = true;
+
+	q->vars.qdelay_old = q->vars.qdelay;
+
+	if (q->vars.avg_dq_rate > 0)
+		qdelay = (qlen << PIE_SCALE) / q->vars.avg_dq_rate;
+	else
+		qdelay = 0;
+
+	/* If qdelay is zero and qlen is not, it means qlen is very small, less
+	 * than dequeue_rate, so we do not update probabilty in this round
+	 */
+	if (qdelay == 0 && qlen != 0)
+		update_prob = false;
+
+	/* Add ranges for alpha and beta, more aggressive for high dropping
+	 * mode and gentle steps for light dropping mode
+	 * In light dropping mode, take gentle steps; in medium dropping mode,
+	 * take medium steps; in high dropping mode, take big steps.
+	 */
+	if (q->vars.prob < MAX_PROB / 100) {
+		alpha =
+		    (q->params.alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 7;
+		beta =
+		    (q->params.beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 7;
+	} else if (q->vars.prob < MAX_PROB / 10) {
+		alpha =
+		    (q->params.alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 5;
+		beta =
+		    (q->params.beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 5;
+	} else {
+		alpha =
+		    (q->params.alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4;
+		beta =
+		    (q->params.beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4;
+	}
+
+	/* alpha and beta should be between 0 and 32, in multiples of 1/16
+	 */
+	delta += alpha * ((qdelay - q->params.target));
+	delta += beta * ((qdelay - qdelay_old));
+
+	oldprob = q->vars.prob;
+
+	/* addition to ensure we increase probability in steps of no
+	 *  more than 2%
+	 */
+	if (delta > (s32) (MAX_PROB / (100 / 2))
+	    && q->vars.prob >= MAX_PROB / 10)
+		delta = (MAX_PROB / 100) * 2;
+
+	/*  Non-linear drop
+	 *  Tune drop probability to increase quickly for high delays
+	 *  (250ms and above)
+	 *  250ms is derived through experiments and provides error protection
+	 */
+
+	if (qdelay > (PSCHED_NS2TICKS(250 * NSEC_PER_MSEC)))
+		delta += MAX_PROB / (100 / 2);
+
+	q->vars.prob += delta;
+
+	if (delta > 0) {
+		/* prevent overflow */
+		if (q->vars.prob < oldprob) {
+			q->vars.prob = MAX_PROB;
+			/* Prevent normalization error
+			 * If probability is the maximum value already,
+			 * we normalize it here, and skip the
+			 * check to do a non-linear drop in the next section
+			 */
+			update_prob = false;
+		}
+	} else {
+		/* prevent underflow */
+		if (q->vars.prob > oldprob)
+			q->vars.prob = 0;
+	}
+
+	/* Non-linear drop in probability */
+	/* Reduce drop probability quickly if delay is 0 for 2 consecutive
+	 * Tupdate periods
+	 */
+	if ((qdelay == 0) && (qdelay_old == 0) && update_prob)
+		q->vars.prob = (q->vars.prob * 98) / 100;
+
+	q->vars.qdelay = qdelay;
+	q->vars.qlen_old = qlen;
+
+	/* we restart the measurement cycle if the following conditions are met
+	 *  1. If the delay has been low for 2 consecutive Tupdate periods
+	 *  2. Calculated drop probability is zero
+	 *  3. We have atleast one estimate for the avg_dq_rate ie.,
+	 *     is a non-zero value
+	 */
+	if ((q->vars.qdelay < q->params.target / 2)
+	    && (q->vars.qdelay_old < q->params.target / 2)
+	    && (q->vars.prob == 0)
+	    && q->vars.avg_dq_rate > 0)
+		pie_vars_init(&q->vars);
+}
+
+static void pie_timer(unsigned long arg)
+{
+	struct Qdisc *sch = (struct Qdisc *)arg;
+	struct pie_sched_data *q = qdisc_priv(sch);
+	spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch));
+
+	spin_lock(root_lock);
+	calculate_probability(sch);
+
+	/* reset the timer to fire after 'tupdate'. Convert from us to jiffies.
+	 */
+	if (q->params.tupdate)
+		mod_timer(&q->adapt_timer, jiffies +
+			  usecs_to_jiffies(q->params.tupdate));
+	spin_unlock(root_lock);
+
+}
+
+static int pie_init(struct Qdisc *sch, struct nlattr *opt)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+
+	pie_params_init(&q->params);
+	pie_vars_init(&q->vars);
+	sch->limit = q->params.limit;
+
+	setup_timer(&q->adapt_timer, pie_timer, (unsigned long)sch);
+	mod_timer(&q->adapt_timer, jiffies + HZ / 2);
+
+	if (opt) {
+		int err = pie_change(sch, opt);
+
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int pie_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+	struct nlattr *opts;
+
+	opts = nla_nest_start(skb, TCA_OPTIONS);
+	if (opts == NULL)
+		goto nla_put_failure;
+
+	/* convert target from pschedtime to us */
+	if (nla_put_u32(skb, TCA_PIE_TARGET,
+			((u32) PSCHED_TICKS2NS(q->params.target)) /
+			NSEC_PER_USEC) ||
+	    nla_put_u32(skb, TCA_PIE_LIMIT, sch->limit) ||
+	    nla_put_u32(skb, TCA_PIE_TUPDATE, q->params.tupdate) ||
+	    nla_put_u32(skb, TCA_PIE_ALPHA, q->params.alpha) ||
+	    nla_put_u32(skb, TCA_PIE_BETA, q->params.beta) ||
+	    nla_put_u32(skb, TCA_PIE_ECN, q->params.ecn) ||
+	    nla_put_u32(skb, TCA_PIE_BYTEMODE, q->params.bytemode))
+		goto nla_put_failure;
+
+	return nla_nest_end(skb, opts);
+
+nla_put_failure:
+	nla_nest_cancel(skb, opts);
+	return -1;
+
+}
+
+static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+	struct tc_pie_xstats st = {
+		.prob		= q->vars.prob,
+		.delay		= ((u32) PSCHED_TICKS2NS(q->vars.qdelay)) /
+				   NSEC_PER_USEC,
+		/* unscale and return dq_rate in bytes per sec */
+		.avg_dq_rate	= q->vars.avg_dq_rate *
+				  (PSCHED_TICKS_PER_SEC) >> PIE_SCALE,
+		.packets_in	= q->stats.packets_in,
+		.overlimit	= q->stats.overlimit,
+		.maxq		= q->stats.maxq,
+		.dropped	= q->stats.dropped,
+		.ecn_mark	= q->stats.ecn_mark,
+	};
+
+	return gnet_stats_copy_app(d, &st, sizeof(st));
+}
+
+static struct sk_buff *pie_qdisc_dequeue(struct Qdisc *sch)
+{
+	struct sk_buff *skb;
+	skb = __qdisc_dequeue_head(sch, &sch->q);
+
+	if (!skb)
+		return NULL;
+
+	pie_process_dequeue(sch, skb);
+	return skb;
+}
+
+static void pie_reset(struct Qdisc *sch)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+	qdisc_reset_queue(sch);
+	pie_vars_init(&q->vars);
+}
+
+static void pie_destroy(struct Qdisc *sch)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+	q->params.tupdate = 0;
+	del_timer_sync(&q->adapt_timer);
+}
+
+static struct Qdisc_ops pie_qdisc_ops __read_mostly = {
+	.id = "pie",
+	.priv_size	= sizeof(struct pie_sched_data),
+	.enqueue	= pie_qdisc_enqueue,
+	.dequeue	= pie_qdisc_dequeue,
+	.peek		= qdisc_peek_dequeued,
+	.init		= pie_init,
+	.destroy	= pie_destroy,
+	.reset		= pie_reset,
+	.change		= pie_change,
+	.dump		= pie_dump,
+	.dump_stats	= pie_dump_stats,
+	.owner		= THIS_MODULE,
+};
+
+static int __init pie_module_init(void)
+{
+	return register_qdisc(&pie_qdisc_ops);
+}
+
+static void __exit pie_module_exit(void)
+{
+	unregister_qdisc(&pie_qdisc_ops);
+}
+
+module_init(pie_module_init);
+module_exit(pie_module_exit);
+
+MODULE_DESCRIPTION("Proportional Integral controller Enhanced (PIE) scheduler");
+MODULE_AUTHOR("Vijay Subramanian");
+MODULE_AUTHOR("Mythili Prabhu");
+MODULE_LICENSE("GPL");
-- 
1.7.9.5

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Powered by blists - more mailing lists