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
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* Monitoring code for network dropped packet alerts
*
* Copyright (C) 2009 Neil Horman <nhorman@tuxdriver.com>
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/string.h>
#include <linux/if_arp.h>
#include <linux/inetdevice.h>
#include <linux/inet.h>
#include <linux/interrupt.h>
#include <linux/netpoll.h>
#include <linux/sched.h>
#include <linux/delay.h>
#include <linux/types.h>
#include <linux/workqueue.h>
#include <linux/netlink.h>
#include <linux/net_dropmon.h>
#include <linux/percpu.h>
#include <linux/timer.h>
#include <linux/bitops.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <net/genetlink.h>
#include <net/netevent.h>
#include <trace/events/skb.h>
#include <trace/events/napi.h>
#include <asm/unaligned.h>
#define TRACE_ON 1
#define TRACE_OFF 0
/*
* Globals, our netlink socket pointer
* and the work handle that will send up
* netlink alerts
*/
static int trace_state = TRACE_OFF;
/* net_dm_mutex
*
* An overall lock guarding every operation coming from userspace.
* It also guards the global 'hw_stats_list' list.
*/
static DEFINE_MUTEX(net_dm_mutex);
struct per_cpu_dm_data {
spinlock_t lock; /* Protects 'skb' and 'send_timer' */
struct sk_buff *skb;
struct work_struct dm_alert_work;
struct timer_list send_timer;
};
struct dm_hw_stat_delta {
struct net_device *dev;
unsigned long last_rx;
struct list_head list;
struct rcu_head rcu;
unsigned long last_drop_val;
};
static struct genl_family net_drop_monitor_family;
static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_cpu_data);
static int dm_hit_limit = 64;
static int dm_delay = 1;
static unsigned long dm_hw_check_delta = 2*HZ;
static LIST_HEAD(hw_stats_list);
static enum net_dm_alert_mode net_dm_alert_mode = NET_DM_ALERT_MODE_SUMMARY;
struct net_dm_alert_ops {
void (*kfree_skb_probe)(void *ignore, struct sk_buff *skb,
void *location);
void (*napi_poll_probe)(void *ignore, struct napi_struct *napi,
int work, int budget);
void (*work_item_func)(struct work_struct *work);
};
static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data)
{
size_t al;
struct net_dm_alert_msg *msg;
struct nlattr *nla;
struct sk_buff *skb;
unsigned long flags;
void *msg_header;
al = sizeof(struct net_dm_alert_msg);
al += dm_hit_limit * sizeof(struct net_dm_drop_point);
al += sizeof(struct nlattr);
skb = genlmsg_new(al, GFP_KERNEL);
if (!skb)
goto err;
msg_header = genlmsg_put(skb, 0, 0, &net_drop_monitor_family,
0, NET_DM_CMD_ALERT);
if (!msg_header) {
nlmsg_free(skb);
skb = NULL;
goto err;
}
nla = nla_reserve(skb, NLA_UNSPEC,
sizeof(struct net_dm_alert_msg));
if (!nla) {
nlmsg_free(skb);
skb = NULL;
goto err;
}
msg = nla_data(nla);
memset(msg, 0, al);
goto out;
err:
mod_timer(&data->send_timer, jiffies + HZ / 10);
out:
spin_lock_irqsave(&data->lock, flags);
swap(data->skb, skb);
spin_unlock_irqrestore(&data->lock, flags);
if (skb) {
struct nlmsghdr *nlh = (struct nlmsghdr *)skb->data;
struct genlmsghdr *gnlh = (struct genlmsghdr *)nlmsg_data(nlh);
genlmsg_end(skb, genlmsg_data(gnlh));
}
return skb;
}
static const struct genl_multicast_group dropmon_mcgrps[] = {
{ .name = "events", },
};
static void send_dm_alert(struct work_struct *work)
{
struct sk_buff *skb;
struct per_cpu_dm_data *data;
data = container_of(work, struct per_cpu_dm_data, dm_alert_work);
skb = reset_per_cpu_data(data);
if (skb)
genlmsg_multicast(&net_drop_monitor_family, skb, 0,
0, GFP_KERNEL);
}
/*
* This is the timer function to delay the sending of an alert
* in the event that more drops will arrive during the
* hysteresis period.
*/
static void sched_send_work(struct timer_list *t)
{
struct per_cpu_dm_data *data = from_timer(data, t, send_timer);
schedule_work(&data->dm_alert_work);
}
static void trace_drop_common(struct sk_buff *skb, void *location)
{
struct net_dm_alert_msg *msg;
struct nlmsghdr *nlh;
struct nlattr *nla;
int i;
struct sk_buff *dskb;
struct per_cpu_dm_data *data;
unsigned long flags;
local_irq_save(flags);
data = this_cpu_ptr(&dm_cpu_data);
spin_lock(&data->lock);
dskb = data->skb;
if (!dskb)
goto out;
nlh = (struct nlmsghdr *)dskb->data;
nla = genlmsg_data(nlmsg_data(nlh));
msg = nla_data(nla);
for (i = 0; i < msg->entries; i++) {
if (!memcmp(&location, msg->points[i].pc, sizeof(void *))) {
msg->points[i].count++;
goto out;
}
}
if (msg->entries == dm_hit_limit)
goto out;
/*
* We need to create a new entry
*/
__nla_reserve_nohdr(dskb, sizeof(struct net_dm_drop_point));
nla->nla_len += NLA_ALIGN(sizeof(struct net_dm_drop_point));
memcpy(msg->points[msg->entries].pc, &location, sizeof(void *));
msg->points[msg->entries].count = 1;
msg->entries++;
if (!timer_pending(&data->send_timer)) {
data->send_timer.expires = jiffies + dm_delay * HZ;
add_timer(&data->send_timer);
}
out:
spin_unlock_irqrestore(&data->lock, flags);
}
static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location)
{
trace_drop_common(skb, location);
}
static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi,
int work, int budget)
{
struct dm_hw_stat_delta *new_stat;
/*
* Don't check napi structures with no associated device
*/
if (!napi->dev)
return;
rcu_read_lock();
list_for_each_entry_rcu(new_stat, &hw_stats_list, list) {
/*
* only add a note to our monitor buffer if:
* 1) this is the dev we received on
* 2) its after the last_rx delta
* 3) our rx_dropped count has gone up
*/
if ((new_stat->dev == napi->dev) &&
(time_after(jiffies, new_stat->last_rx + dm_hw_check_delta)) &&
(napi->dev->stats.rx_dropped != new_stat->last_drop_val)) {
trace_drop_common(NULL, NULL);
new_stat->last_drop_val = napi->dev->stats.rx_dropped;
new_stat->last_rx = jiffies;
break;
}
}
rcu_read_unlock();
}
static const struct net_dm_alert_ops net_dm_alert_summary_ops = {
.kfree_skb_probe = trace_kfree_skb_hit,
.napi_poll_probe = trace_napi_poll_hit,
.work_item_func = send_dm_alert,
};
static const struct net_dm_alert_ops *net_dm_alert_ops_arr[] = {
[NET_DM_ALERT_MODE_SUMMARY] = &net_dm_alert_summary_ops,
};
static int net_dm_trace_on_set(struct netlink_ext_ack *extack)
{
const struct net_dm_alert_ops *ops;
int cpu, rc;
ops = net_dm_alert_ops_arr[net_dm_alert_mode];
if (!try_module_get(THIS_MODULE)) {
NL_SET_ERR_MSG_MOD(extack, "Failed to take reference on module");
return -ENODEV;
}
for_each_possible_cpu(cpu) {
struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu);
struct sk_buff *skb;
INIT_WORK(&data->dm_alert_work, ops->work_item_func);
timer_setup(&data->send_timer, sched_send_work, 0);
/* Allocate a new per-CPU skb for the summary alert message and
* free the old one which might contain stale data from
* previous tracing.
*/
skb = reset_per_cpu_data(data);
consume_skb(skb);
}
rc = register_trace_kfree_skb(ops->kfree_skb_probe, NULL);
if (rc) {
NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to kfree_skb() tracepoint");
goto err_module_put;
}
rc = register_trace_napi_poll(ops->napi_poll_probe, NULL);
if (rc) {
NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to napi_poll() tracepoint");
goto err_unregister_trace;
}
return 0;
err_unregister_trace:
unregister_trace_kfree_skb(ops->kfree_skb_probe, NULL);
err_module_put:
module_put(THIS_MODULE);
return rc;
}
static void net_dm_trace_off_set(void)
{
struct dm_hw_stat_delta *new_stat, *temp;
const struct net_dm_alert_ops *ops;
int cpu;
ops = net_dm_alert_ops_arr[net_dm_alert_mode];
unregister_trace_napi_poll(ops->napi_poll_probe, NULL);
unregister_trace_kfree_skb(ops->kfree_skb_probe, NULL);
tracepoint_synchronize_unregister();
/* Make sure we do not send notifications to user space after request
* to stop tracing returns.
*/
for_each_possible_cpu(cpu) {
struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu);
del_timer_sync(&data->send_timer);
cancel_work_sync(&data->dm_alert_work);
}
list_for_each_entry_safe(new_stat, temp, &hw_stats_list, list) {
if (new_stat->dev == NULL) {
list_del_rcu(&new_stat->list);
kfree_rcu(new_stat, rcu);
}
}
module_put(THIS_MODULE);
}
static int set_all_monitor_traces(int state, struct netlink_ext_ack *extack)
{
int rc = 0;
if (state == trace_state) {
NL_SET_ERR_MSG_MOD(extack, "Trace state already set to requested state");
return -EAGAIN;
}
switch (state) {
case TRACE_ON:
rc = net_dm_trace_on_set(extack);
break;
case TRACE_OFF:
net_dm_trace_off_set();
break;
default:
rc = 1;
break;
}
if (!rc)
trace_state = state;
else
rc = -EINPROGRESS;
return rc;
}
static int net_dm_cmd_config(struct sk_buff *skb,
struct genl_info *info)
{
NL_SET_ERR_MSG_MOD(info->extack, "Command not supported");
return -EOPNOTSUPP;
}
static int net_dm_cmd_trace(struct sk_buff *skb,
struct genl_info *info)
{
switch (info->genlhdr->cmd) {
case NET_DM_CMD_START:
return set_all_monitor_traces(TRACE_ON, info->extack);
case NET_DM_CMD_STOP:
return set_all_monitor_traces(TRACE_OFF, info->extack);
}
return -EOPNOTSUPP;
}
static int dropmon_net_event(struct notifier_block *ev_block,
unsigned long event, void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct dm_hw_stat_delta *new_stat = NULL;
struct dm_hw_stat_delta *tmp;
switch (event) {
case NETDEV_REGISTER:
new_stat = kzalloc(sizeof(struct dm_hw_stat_delta), GFP_KERNEL);
if (!new_stat)
goto out;
new_stat->dev = dev;
new_stat->last_rx = jiffies;
mutex_lock(&net_dm_mutex);
list_add_rcu(&new_stat->list, &hw_stats_list);
mutex_unlock(&net_dm_mutex);
break;
case NETDEV_UNREGISTER:
mutex_lock(&net_dm_mutex);
list_for_each_entry_safe(new_stat, tmp, &hw_stats_list, list) {
if (new_stat->dev == dev) {
new_stat->dev = NULL;
if (trace_state == TRACE_OFF) {
list_del_rcu(&new_stat->list);
kfree_rcu(new_stat, rcu);
break;
}
}
}
mutex_unlock(&net_dm_mutex);
break;
}
out:
return NOTIFY_DONE;
}
static const struct genl_ops dropmon_ops[] = {
{
.cmd = NET_DM_CMD_CONFIG,
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = net_dm_cmd_config,
.flags = GENL_ADMIN_PERM,
},
{
.cmd = NET_DM_CMD_START,
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = net_dm_cmd_trace,
},
{
.cmd = NET_DM_CMD_STOP,
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = net_dm_cmd_trace,
},
};
static int net_dm_nl_pre_doit(const struct genl_ops *ops,
struct sk_buff *skb, struct genl_info *info)
{
mutex_lock(&net_dm_mutex);
return 0;
}
static void net_dm_nl_post_doit(const struct genl_ops *ops,
struct sk_buff *skb, struct genl_info *info)
{
mutex_unlock(&net_dm_mutex);
}
static struct genl_family net_drop_monitor_family __ro_after_init = {
.hdrsize = 0,
.name = "NET_DM",
.version = 2,
.pre_doit = net_dm_nl_pre_doit,
.post_doit = net_dm_nl_post_doit,
.module = THIS_MODULE,
.ops = dropmon_ops,
.n_ops = ARRAY_SIZE(dropmon_ops),
.mcgrps = dropmon_mcgrps,
.n_mcgrps = ARRAY_SIZE(dropmon_mcgrps),
};
static struct notifier_block dropmon_net_notifier = {
.notifier_call = dropmon_net_event
};
static int __init init_net_drop_monitor(void)
{
struct per_cpu_dm_data *data;
int cpu, rc;
pr_info("Initializing network drop monitor service\n");
if (sizeof(void *) > 8) {
pr_err("Unable to store program counters on this arch, Drop monitor failed\n");
return -ENOSPC;
}
rc = genl_register_family(&net_drop_monitor_family);
if (rc) {
pr_err("Could not create drop monitor netlink family\n");
return rc;
}
WARN_ON(net_drop_monitor_family.mcgrp_offset != NET_DM_GRP_ALERT);
rc = register_netdevice_notifier(&dropmon_net_notifier);
if (rc < 0) {
pr_crit("Failed to register netdevice notifier\n");
goto out_unreg;
}
rc = 0;
for_each_possible_cpu(cpu) {
data = &per_cpu(dm_cpu_data, cpu);
spin_lock_init(&data->lock);
}
goto out;
out_unreg:
genl_unregister_family(&net_drop_monitor_family);
out:
return rc;
}
static void exit_net_drop_monitor(void)
{
struct per_cpu_dm_data *data;
int cpu;
BUG_ON(unregister_netdevice_notifier(&dropmon_net_notifier));
/*
* Because of the module_get/put we do in the trace state change path
* we are guarnateed not to have any current users when we get here
*/
for_each_possible_cpu(cpu) {
data = &per_cpu(dm_cpu_data, cpu);
/*
* At this point, we should have exclusive access
* to this struct and can free the skb inside it
*/
kfree_skb(data->skb);
}
BUG_ON(genl_unregister_family(&net_drop_monitor_family));
}
module_init(init_net_drop_monitor);
module_exit(exit_net_drop_monitor);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Neil Horman <nhorman@tuxdriver.com>");
MODULE_ALIAS_GENL_FAMILY("NET_DM");
|