1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
|
/*
* Codel - The Controlled-Delay Active Queue Management algorithm
*
* Copyright (C) 2011-2012 Kathleen Nichols <nichols@pollere.com>
* Copyright (C) 2011-2012 Van Jacobson <van@pollere.net>
*
* Implemented on linux by :
* Copyright (C) 2012 Michael D. Taht <dave.taht@bufferbloat.net>
* Copyright (C) 2012,2015 Eric Dumazet <edumazet@google.com>
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions, and the following disclaimer,
* without modification.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. The names of the authors may not be used to endorse or promote products
* derived from this software without specific prior written permission.
*
* Alternatively, provided that this notice is retained in full, this
* software may be distributed under the terms of the GNU General
* Public License ("GPL") version 2, in which case the provisions of the
* GPL apply INSTEAD OF those given above.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
* DAMAGE.
*
*/
#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 <linux/prefetch.h>
#include <net/pkt_sched.h>
#include <net/codel.h>
#include <net/codel_impl.h>
#include <net/codel_qdisc.h>
#define DEFAULT_CODEL_LIMIT 1000
struct codel_sched_data {
struct codel_params params;
struct codel_vars vars;
struct codel_stats stats;
u32 drop_overlimit;
};
/* This is the specific function called from codel_dequeue()
* to dequeue a packet from queue. Note: backlog is handled in
* codel, we dont need to reduce it here.
*/
static struct sk_buff *dequeue_func(struct codel_vars *vars, void *ctx)
{
struct Qdisc *sch = ctx;
struct sk_buff *skb = __skb_dequeue(&sch->q);
if (skb)
sch->qstats.backlog -= qdisc_pkt_len(skb);
prefetch(&skb->end); /* we'll need skb_shinfo() */
return skb;
}
static void drop_func(struct sk_buff *skb, void *ctx)
{
struct Qdisc *sch = ctx;
kfree_skb(skb);
qdisc_qstats_drop(sch);
}
static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch)
{
struct codel_sched_data *q = qdisc_priv(sch);
struct sk_buff *skb;
skb = codel_dequeue(sch, &sch->qstats.backlog, &q->params, &q->vars,
&q->stats, qdisc_pkt_len, codel_get_enqueue_time,
drop_func, dequeue_func);
/* We cant call qdisc_tree_reduce_backlog() if our qlen is 0,
* or HTB crashes. Defer it for next round.
*/
if (q->stats.drop_count && sch->q.qlen) {
qdisc_tree_reduce_backlog(sch, q->stats.drop_count, q->stats.drop_len);
q->stats.drop_count = 0;
q->stats.drop_len = 0;
}
if (skb)
qdisc_bstats_update(sch, skb);
return skb;
}
static int codel_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct sk_buff **to_free)
{
struct codel_sched_data *q;
if (likely(qdisc_qlen(sch) < sch->limit)) {
codel_set_enqueue_time(skb);
return qdisc_enqueue_tail(skb, sch);
}
q = qdisc_priv(sch);
q->drop_overlimit++;
return qdisc_drop(skb, sch, to_free);
}
static const struct nla_policy codel_policy[TCA_CODEL_MAX + 1] = {
[TCA_CODEL_TARGET] = { .type = NLA_U32 },
[TCA_CODEL_LIMIT] = { .type = NLA_U32 },
[TCA_CODEL_INTERVAL] = { .type = NLA_U32 },
[TCA_CODEL_ECN] = { .type = NLA_U32 },
[TCA_CODEL_CE_THRESHOLD]= { .type = NLA_U32 },
};
static int codel_change(struct Qdisc *sch, struct nlattr *opt)
{
struct codel_sched_data *q = qdisc_priv(sch);
struct nlattr *tb[TCA_CODEL_MAX + 1];
unsigned int qlen, dropped = 0;
int err;
if (!opt)
return -EINVAL;
err = nla_parse_nested(tb, TCA_CODEL_MAX, opt, codel_policy);
if (err < 0)
return err;
sch_tree_lock(sch);
if (tb[TCA_CODEL_TARGET]) {
u32 target = nla_get_u32(tb[TCA_CODEL_TARGET]);
q->params.target = ((u64)target * NSEC_PER_USEC) >> CODEL_SHIFT;
}
if (tb[TCA_CODEL_CE_THRESHOLD]) {
u64 val = nla_get_u32(tb[TCA_CODEL_CE_THRESHOLD]);
q->params.ce_threshold = (val * NSEC_PER_USEC) >> CODEL_SHIFT;
}
if (tb[TCA_CODEL_INTERVAL]) {
u32 interval = nla_get_u32(tb[TCA_CODEL_INTERVAL]);
q->params.interval = ((u64)interval * NSEC_PER_USEC) >> CODEL_SHIFT;
}
if (tb[TCA_CODEL_LIMIT])
sch->limit = nla_get_u32(tb[TCA_CODEL_LIMIT]);
if (tb[TCA_CODEL_ECN])
q->params.ecn = !!nla_get_u32(tb[TCA_CODEL_ECN]);
qlen = sch->q.qlen;
while (sch->q.qlen > sch->limit) {
struct sk_buff *skb = __skb_dequeue(&sch->q);
dropped += qdisc_pkt_len(skb);
qdisc_qstats_backlog_dec(sch, skb);
rtnl_qdisc_drop(skb, sch);
}
qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
sch_tree_unlock(sch);
return 0;
}
static int codel_init(struct Qdisc *sch, struct nlattr *opt)
{
struct codel_sched_data *q = qdisc_priv(sch);
sch->limit = DEFAULT_CODEL_LIMIT;
codel_params_init(&q->params);
codel_vars_init(&q->vars);
codel_stats_init(&q->stats);
q->params.mtu = psched_mtu(qdisc_dev(sch));
if (opt) {
int err = codel_change(sch, opt);
if (err)
return err;
}
if (sch->limit >= 1)
sch->flags |= TCQ_F_CAN_BYPASS;
else
sch->flags &= ~TCQ_F_CAN_BYPASS;
return 0;
}
static int codel_dump(struct Qdisc *sch, struct sk_buff *skb)
{
struct codel_sched_data *q = qdisc_priv(sch);
struct nlattr *opts;
opts = nla_nest_start(skb, TCA_OPTIONS);
if (opts == NULL)
goto nla_put_failure;
if (nla_put_u32(skb, TCA_CODEL_TARGET,
codel_time_to_us(q->params.target)) ||
nla_put_u32(skb, TCA_CODEL_LIMIT,
sch->limit) ||
nla_put_u32(skb, TCA_CODEL_INTERVAL,
codel_time_to_us(q->params.interval)) ||
nla_put_u32(skb, TCA_CODEL_ECN,
q->params.ecn))
goto nla_put_failure;
if (q->params.ce_threshold != CODEL_DISABLED_THRESHOLD &&
nla_put_u32(skb, TCA_CODEL_CE_THRESHOLD,
codel_time_to_us(q->params.ce_threshold)))
goto nla_put_failure;
return nla_nest_end(skb, opts);
nla_put_failure:
nla_nest_cancel(skb, opts);
return -1;
}
static int codel_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
{
const struct codel_sched_data *q = qdisc_priv(sch);
struct tc_codel_xstats st = {
.maxpacket = q->stats.maxpacket,
.count = q->vars.count,
.lastcount = q->vars.lastcount,
.drop_overlimit = q->drop_overlimit,
.ldelay = codel_time_to_us(q->vars.ldelay),
.dropping = q->vars.dropping,
.ecn_mark = q->stats.ecn_mark,
.ce_mark = q->stats.ce_mark,
};
if (q->vars.dropping) {
codel_tdiff_t delta = q->vars.drop_next - codel_get_time();
if (delta >= 0)
st.drop_next = codel_time_to_us(delta);
else
st.drop_next = -codel_time_to_us(-delta);
}
return gnet_stats_copy_app(d, &st, sizeof(st));
}
static void codel_reset(struct Qdisc *sch)
{
struct codel_sched_data *q = qdisc_priv(sch);
qdisc_reset_queue(sch);
codel_vars_init(&q
|