From ea08eeccae9297f7aabd2ef7f0c2517ac4549acc Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:18:26 +0000
Subject: [PATCH] write in 30M
---
kernel/net/sched/sch_pie.c | 404 +++++++++++++++++++++++++++++----------------------------
1 files changed, 204 insertions(+), 200 deletions(-)
diff --git a/kernel/net/sched/sch_pie.c b/kernel/net/sched/sch_pie.c
index 18d30bb..c65077f 100644
--- a/kernel/net/sched/sch_pie.c
+++ b/kernel/net/sched/sch_pie.c
@@ -1,14 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
/* 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@cisco.com>
* Author: Mythili Prabhu <mysuryan@cisco.com>
@@ -17,9 +8,7 @@
* University of Oslo, Norway.
*
* References:
- * IETF draft submission: http://tools.ietf.org/html/draft-pan-aqm-pie-00
- * IEEE Conference on High Performance Switching and Routing 2013 :
- * "PIE: A * Lightweight Control Scheme to Address the Bufferbloat Problem"
+ * RFC 8033: https://tools.ietf.org/html/rfc8033
*/
#include <linux/module.h>
@@ -30,110 +19,68 @@
#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; /* timer frequency (in jiffies) */
- u32 limit; /* number of packets that can be enqueued */
- u32 alpha; /* alpha and beta are between 0 and 32 */
- 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 */
-};
+#include <net/pie.h>
/* private data for the Qdisc */
struct pie_sched_data {
- struct pie_params params;
struct pie_vars vars;
+ struct pie_params params;
struct pie_stats stats;
struct timer_list adapt_timer;
struct Qdisc *sch;
};
-static void pie_params_init(struct pie_params *params)
+bool pie_drop_early(struct Qdisc *sch, struct pie_params *params,
+ struct pie_vars *vars, u32 backlog, u32 packet_size)
{
- params->alpha = 2;
- params->beta = 20;
- params->tupdate = usecs_to_jiffies(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;
+ u64 rnd;
+ u64 local_prob = 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)
+ if (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))
+ if ((vars->qdelay < params->target / 2) &&
+ (vars->prob < MAX_PROB / 5))
return false;
- /* If we have fewer than 2 mtu-sized packets, disable drop_early,
+ /* If we have fewer than 2 mtu-sized packets, disable pie_drop_early,
* similar to min_th in RED
*/
- if (sch->qstats.backlog < 2 * mtu)
+ if (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;
+ if (params->bytemode && packet_size <= mtu)
+ local_prob = (u64)packet_size * div_u64(local_prob, mtu);
else
- local_prob = q->vars.prob;
+ local_prob = vars->prob;
- rnd = prandom_u32();
- if (rnd < local_prob)
+ if (local_prob == 0)
+ vars->accu_prob = 0;
+ else
+ vars->accu_prob += local_prob;
+
+ if (vars->accu_prob < (MAX_PROB / 100) * 85)
+ return false;
+ if (vars->accu_prob >= (MAX_PROB / 2) * 17)
return true;
+
+ prandom_bytes(&rnd, 8);
+ if ((rnd >> BITS_PER_BYTE) < local_prob) {
+ vars->accu_prob = 0;
+ return true;
+ }
return false;
}
+EXPORT_SYMBOL_GPL(pie_drop_early);
static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct sk_buff **to_free)
@@ -146,7 +93,8 @@
goto out;
}
- if (!drop_early(sch, skb->len)) {
+ if (!pie_drop_early(sch, &q->params, &q->vars, sch->qstats.backlog,
+ skb->len)) {
enqueue = true;
} else if (q->params.ecn && (q->vars.prob <= MAX_PROB / 10) &&
INET_ECN_set_ce(skb)) {
@@ -159,6 +107,10 @@
/* we can enqueue the packet */
if (enqueue) {
+ /* Set enqueue time only when dq_rate_estimator is disabled. */
+ if (!q->params.dq_rate_estimator)
+ pie_set_enqueue_time(skb);
+
q->stats.packets_in++;
if (qdisc_qlen(sch) > q->stats.maxq)
q->stats.maxq = qdisc_qlen(sch);
@@ -168,17 +120,19 @@
out:
q->stats.dropped++;
+ q->vars.accu_prob = 0;
return qdisc_drop(skb, sch, to_free);
}
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},
+ [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},
+ [TCA_PIE_DQ_RATE_ESTIMATOR] = {.type = NLA_U32},
};
static int pie_change(struct Qdisc *sch, struct nlattr *opt,
@@ -192,7 +146,8 @@
if (!opt)
return -EINVAL;
- err = nla_parse_nested(tb, TCA_PIE_MAX, opt, pie_policy, NULL);
+ err = nla_parse_nested_deprecated(tb, TCA_PIE_MAX, opt, pie_policy,
+ NULL);
if (err < 0)
return err;
@@ -209,7 +164,8 @@
/* tupdate is in jiffies */
if (tb[TCA_PIE_TUPDATE])
- q->params.tupdate = usecs_to_jiffies(nla_get_u32(tb[TCA_PIE_TUPDATE]));
+ q->params.tupdate =
+ usecs_to_jiffies(nla_get_u32(tb[TCA_PIE_TUPDATE]));
if (tb[TCA_PIE_LIMIT]) {
u32 limit = nla_get_u32(tb[TCA_PIE_LIMIT]);
@@ -230,6 +186,10 @@
if (tb[TCA_PIE_BYTEMODE])
q->params.bytemode = nla_get_u32(tb[TCA_PIE_BYTEMODE]);
+ if (tb[TCA_PIE_DQ_RATE_ESTIMATOR])
+ q->params.dq_rate_estimator =
+ nla_get_u32(tb[TCA_PIE_DQ_RATE_ESTIMATOR]);
+
/* Drop excess packets if new limit is lower */
qlen = sch->q.qlen;
while (sch->q.qlen > sch->limit) {
@@ -245,133 +205,163 @@
return 0;
}
-static void pie_process_dequeue(struct Qdisc *sch, struct sk_buff *skb)
+void pie_process_dequeue(struct sk_buff *skb, struct pie_params *params,
+ struct pie_vars *vars, u32 backlog)
{
+ psched_time_t now = psched_get_time();
+ u32 dtime = 0;
- struct pie_sched_data *q = qdisc_priv(sch);
- int qlen = sch->qstats.backlog; /* current queue size in bytes */
+ /* If dq_rate_estimator is disabled, calculate qdelay using the
+ * packet timestamp.
+ */
+ if (!params->dq_rate_estimator) {
+ vars->qdelay = now - pie_get_enqueue_time(skb);
+
+ if (vars->dq_tstamp != DTIME_INVALID)
+ dtime = now - vars->dq_tstamp;
+
+ vars->dq_tstamp = now;
+
+ if (backlog == 0)
+ vars->qdelay = 0;
+
+ if (dtime == 0)
+ return;
+
+ goto burst_allowance_reduction;
+ }
/* 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;
+ if (backlog >= QUEUE_THRESHOLD && vars->dq_count == DQCOUNT_INVALID) {
+ vars->dq_tstamp = psched_get_time();
+ 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
+ /* 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
+ * 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 (vars->dq_count != DQCOUNT_INVALID) {
+ 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 (vars->dq_count >= QUEUE_THRESHOLD) {
+ u32 count = vars->dq_count << PIE_SCALE;
+
+ dtime = now - vars->dq_tstamp;
if (dtime == 0)
return;
count = count / dtime;
- if (q->vars.avg_dq_rate == 0)
- q->vars.avg_dq_rate = count;
+ if (vars->avg_dq_rate == 0)
+ vars->avg_dq_rate = count;
else
- q->vars.avg_dq_rate =
- (q->vars.avg_dq_rate -
- (q->vars.avg_dq_rate >> 3)) + (count >> 3);
+ vars->avg_dq_rate =
+ (vars->avg_dq_rate -
+ (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 (backlog < QUEUE_THRESHOLD) {
+ vars->dq_count = DQCOUNT_INVALID;
+ } else {
+ vars->dq_count = 0;
+ 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;
- }
+ goto burst_allowance_reduction;
}
}
-}
-static void calculate_probability(struct Qdisc *sch)
+ return;
+
+burst_allowance_reduction:
+ if (vars->burst_time > 0) {
+ if (vars->burst_time > dtime)
+ vars->burst_time -= dtime;
+ else
+ vars->burst_time = 0;
+ }
+}
+EXPORT_SYMBOL_GPL(pie_process_dequeue);
+
+void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars,
+ u32 backlog)
{
- 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;
+ psched_time_t qdelay_old = 0; /* in pschedtime */
+ s64 delta = 0; /* determines the change in probability */
+ u64 oldprob;
+ u64 alpha, beta;
+ u32 power;
bool update_prob = true;
- q->vars.qdelay_old = q->vars.qdelay;
+ if (params->dq_rate_estimator) {
+ qdelay_old = vars->qdelay;
+ vars->qdelay_old = vars->qdelay;
- if (q->vars.avg_dq_rate > 0)
- qdelay = (qlen << PIE_SCALE) / q->vars.avg_dq_rate;
- else
- qdelay = 0;
+ if (vars->avg_dq_rate > 0)
+ qdelay = (backlog << PIE_SCALE) / vars->avg_dq_rate;
+ else
+ qdelay = 0;
+ } else {
+ qdelay = vars->qdelay;
+ qdelay_old = vars->qdelay_old;
+ }
- /* 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 is zero and backlog is not, it means backlog is very small,
+ * so we do not update probabilty in this round.
*/
- if (qdelay == 0 && qlen != 0)
+ if (qdelay == 0 && backlog != 0)
update_prob = false;
/* In the algorithm, alpha and beta are between 0 and 2 with typical
* value for alpha as 0.125. In this implementation, we use values 0-32
* passed from user space to represent this. Also, alpha and beta have
* unit of HZ and need to be scaled before they can used to update
- * probability. alpha/beta are updated locally below by 1) scaling them
- * appropriately 2) scaling down by 16 to come to 0-2 range.
- * Please see paper for details.
- *
- * We scale alpha and beta differently depending on whether we are in
- * light, medium or high dropping mode.
+ * probability. alpha/beta are updated locally below by scaling down
+ * by 16 to come to 0-2 range.
*/
- 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 = ((u64)params->alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4;
+ beta = ((u64)params->beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4;
+
+ /* We scale alpha and beta differently depending on how heavy the
+ * congestion is. Please see RFC 8033 for details.
+ */
+ if (vars->prob < MAX_PROB / 10) {
+ alpha >>= 1;
+ beta >>= 1;
+
+ power = 100;
+ while (vars->prob < div_u64(MAX_PROB, power) &&
+ power <= 1000000) {
+ alpha >>= 2;
+ beta >>= 2;
+ power *= 10;
+ }
}
/* 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));
+ delta += alpha * (qdelay - params->target);
+ delta += beta * (qdelay - qdelay_old);
- oldprob = q->vars.prob;
+ oldprob = vars->prob;
/* 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)
+ if (delta > (s64)(MAX_PROB / (100 / 2)) &&
+ vars->prob >= MAX_PROB / 10)
delta = (MAX_PROB / 100) * 2;
/* Non-linear drop:
@@ -382,12 +372,12 @@
if (qdelay > (PSCHED_NS2TICKS(250 * NSEC_PER_MSEC)))
delta += MAX_PROB / (100 / 2);
- q->vars.prob += delta;
+ vars->prob += delta;
if (delta > 0) {
/* prevent overflow */
- if (q->vars.prob < oldprob) {
- q->vars.prob = MAX_PROB;
+ if (vars->prob < oldprob) {
+ vars->prob = MAX_PROB;
/* Prevent normalization error. If probability is at
* maximum value already, we normalize it here, and
* skip the check to do a non-linear drop in the next
@@ -397,32 +387,38 @@
}
} else {
/* prevent underflow */
- if (q->vars.prob > oldprob)
- q->vars.prob = 0;
+ if (vars->prob > oldprob)
+ 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;
+ if (qdelay == 0 && qdelay_old == 0 && update_prob)
+ /* Reduce drop probability to 98.4% */
+ vars->prob -= vars->prob / 64;
- q->vars.qdelay = qdelay;
- q->vars.qlen_old = qlen;
+ vars->qdelay = qdelay;
+ vars->backlog_old = backlog;
/* 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
+ * 3. If average dq_rate_estimator is enabled, 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);
+ if ((vars->qdelay < params->target / 2) &&
+ (vars->qdelay_old < params->target / 2) &&
+ vars->prob == 0 &&
+ (!params->dq_rate_estimator || vars->avg_dq_rate > 0)) {
+ pie_vars_init(vars);
+ }
+
+ if (!params->dq_rate_estimator)
+ vars->qdelay_old = qdelay;
}
+EXPORT_SYMBOL_GPL(pie_calculate_probability);
static void pie_timer(struct timer_list *t)
{
@@ -431,13 +427,12 @@
spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch));
spin_lock(root_lock);
- calculate_probability(sch);
+ pie_calculate_probability(&q->params, &q->vars, sch->qstats.backlog);
/* reset the timer to fire after 'tupdate'. tupdate is in jiffies. */
if (q->params.tupdate)
mod_timer(&q->adapt_timer, jiffies + q->params.tupdate);
spin_unlock(root_lock);
-
}
static int pie_init(struct Qdisc *sch, struct nlattr *opt,
@@ -468,20 +463,23 @@
struct pie_sched_data *q = qdisc_priv(sch);
struct nlattr *opts;
- opts = nla_nest_start(skb, TCA_OPTIONS);
- if (opts == NULL)
+ opts = nla_nest_start_noflag(skb, TCA_OPTIONS);
+ if (!opts)
goto nla_put_failure;
/* convert target from pschedtime to us */
if (nla_put_u32(skb, TCA_PIE_TARGET,
- ((u32) PSCHED_TICKS2NS(q->params.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, jiffies_to_usecs(q->params.tupdate)) ||
+ nla_put_u32(skb, TCA_PIE_TUPDATE,
+ jiffies_to_usecs(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))
+ nla_put_u32(skb, TCA_PIE_BYTEMODE, q->params.bytemode) ||
+ nla_put_u32(skb, TCA_PIE_DQ_RATE_ESTIMATOR,
+ q->params.dq_rate_estimator))
goto nla_put_failure;
return nla_nest_end(skb, opts);
@@ -489,19 +487,15 @@
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)) /
+ .prob = q->vars.prob << BITS_PER_BYTE,
+ .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,
@@ -509,24 +503,33 @@
.ecn_mark = q->stats.ecn_mark,
};
+ /* avg_dq_rate is only valid if dq_rate_estimator is enabled */
+ st.dq_rate_estimating = q->params.dq_rate_estimator;
+
+ /* unscale and return dq_rate in bytes per sec */
+ if (q->params.dq_rate_estimator)
+ st.avg_dq_rate = q->vars.avg_dq_rate *
+ (PSCHED_TICKS_PER_SEC) >> PIE_SCALE;
+
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);
+ struct pie_sched_data *q = qdisc_priv(sch);
+ struct sk_buff *skb = qdisc_dequeue_head(sch);
if (!skb)
return NULL;
- pie_process_dequeue(sch, skb);
+ pie_process_dequeue(skb, &q->params, &q->vars, sch->qstats.backlog);
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);
}
@@ -534,12 +537,13 @@
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",
+ .id = "pie",
.priv_size = sizeof(struct pie_sched_data),
.enqueue = pie_qdisc_enqueue,
.dequeue = pie_qdisc_dequeue,
--
Gitblit v1.6.2