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
|
/*
* Copyright (c) 2016, Mellanox Technologies. All rights reserved.
*
* This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU
* General Public License (GPL) Version 2, available from the file
* COPYING in the main directory of this source tree, or the
* OpenIB.org BSD license below:
*
* Redistribution and use in source and binary forms, with or
* without modification, are permitted provided that the following
* conditions are met:
*
* - Redistributions of source code must retain the above
* copyright notice, this list of conditions and the following
* disclaimer.
*
* - 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.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
#include <linux/mlx5/driver.h>
#include <linux/mlx5/fs.h>
#include <linux/rbtree.h>
#include "mlx5_core.h"
#include "fs_core.h"
#include "fs_cmd.h"
#define MLX5_FC_STATS_PERIOD msecs_to_jiffies(1000)
/* Max number of counters to query in bulk read is 32K */
#define MLX5_SW_MAX_COUNTERS_BULK BIT(15)
struct mlx5_fc_cache {
u64 packets;
u64 bytes;
u64 lastuse;
};
struct mlx5_fc {
struct list_head list;
struct llist_node addlist;
struct llist_node dellist;
/* last{packets,bytes} members are used when calculating the delta since
* last reading
*/
u64 lastpackets;
u64 lastbytes;
u32 id;
bool aging;
struct mlx5_fc_cache cache ____cacheline_aligned_in_smp;
};
/* locking scheme:
*
* It is the responsibility of the user to prevent concurrent calls or bad
* ordering to mlx5_fc_create(), mlx5_fc_destroy() and accessing a reference
* to struct mlx5_fc.
* e.g en_tc.c is protected by RTNL lock of its caller, and will never call a
* dump (access to struct mlx5_fc) after a counter is destroyed.
*
* access to counter list:
* - create (user context)
* - mlx5_fc_create() only adds to an addlist to be used by
* mlx5_fc_stats_query_work(). addlist is a lockless single linked list
* that doesn't require any additional synchronization when adding single
* node.
* - spawn thread to do the actual destroy
*
* - destroy (user context)
* - add a counter to lockless dellist
* - spawn thread to do the actual del
*
* - dump (user context)
* user should not call dump after destroy
*
* - query (single thread workqueue context)
* destroy/dump - no conflict (see destroy)
* query/dump - packets and bytes might be inconsistent (since update is not
* atomic)
* query/create - no conflict (see create)
* since every create/destroy spawn the work, only after necessary time has
* elapsed, the thread will actually query the hardware.
*/
static struct list_head *mlx5_fc_counters_lookup_next(struct mlx5_core_dev *dev,
u32 id)
{
struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
unsigned long next_id = (unsigned long)id + 1;
struct mlx5_fc *counter;
rcu_read_lock();
/* skip counters that are in idr, but not yet in counters list */
while ((counter = idr_get_next_ul(&fc_stats->counters_idr,
&next_id)) != NULL &&
list_empty(&counter->list))
next_id++;
rcu_read_unlock();
return counter ? &counter->list : &fc_stats->counters;
}
static void mlx5_fc_stats_insert(struct mlx5_core_dev *dev,
struct mlx5_fc *counter)
{
struct list_head *next = mlx5_fc_counters_lookup_next(dev, counter->id);
list_add_tail(&counter->list, next);
}
static void mlx5_fc_stats_remove(struct mlx5_core_dev *dev,
struct mlx5_fc *counter)
{
struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
list_del(&counter->list);
spin_lock(&fc_stats->counters_idr_lock);
WARN_ON(!idr_remove(&fc_stats->counters_idr, counter->id));
spin_unlock(&fc_stats->counters_idr_lock);
}
/* The function returns the last counter that was queried so the caller
* function can continue calling it till all counters are queried.
*/
static struct mlx5_fc *mlx5_fc_stats_query(struct mlx5_core_dev *dev,
struct mlx5_fc *first,
u32 last_id)
{
struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
struct mlx5_fc *counter = NULL;
struct mlx5_cmd_fc_bulk *b;
bool more = false;
u32 afirst_id;
int num;
int err;
int max_bulk = min_t(int, MLX5_SW_MAX_COUNTERS_BULK,
(1 << MLX5_CAP_GEN(dev, log_max_flow_counter_bulk)));
/* first id must be aligned to 4 when using bulk query */
afirst_id = first->id & ~0x3;
/* number of counters to query inc. the last counter */
num = ALIGN(last_id - afirst_id + 1, 4);
if (num > max_bulk) {
num = max_bulk;
last_id = afirst_id + num - 1;
}
b = mlx5_cmd_fc_bulk_alloc(dev, afirst_id, num);
if (!b) {
mlx5_core_err(dev, "Error allocating resources for bulk query\n");
return NULL;
}
err = mlx5_cmd_fc_bulk_query(dev, b);
if (err) {
mlx5_core_err(dev, "Error doing bulk query: %d\n", err);
goto out;
}
counter = first;
list_for_each_entry_from(counter, &fc_stats->counters, list) {
struct mlx5_fc_cache *c = &counter->cache;
u64 packets;
u64 bytes;
if (counter->id > last_id) {
more = true;
break;
}
mlx5_cmd_fc_bulk_get(dev, b,
counter->id, &packets, &bytes);
if (c->packets == packets)
continue;
c->packets = packets;
c->bytes = bytes;
c->lastuse = jiffies;
}
out:
mlx5_cmd_fc_bulk_free(b);
return more ? counter : NULL;
}
static void mlx5_free_fc(struct mlx5_core_dev *dev,
struct mlx5_fc *counter)
{
mlx5_cmd_fc_free(dev, counter->id);
kfree(counter);
}
static void mlx5_fc_stats_work(struct work_struct *work)
{
struct mlx5_core_dev *dev = container_of(work, struct mlx5_core_dev,
priv.fc_stats.work.work);
struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
/* Take dellist first to ensure that counters cannot be deleted before
* they are inserted.
*/
struct llist_node *dellist = llist_del_all(&fc_stats->dellist);
struct llist_node *addlist = llist_del_all(&fc_stats->addlist);
struct mlx5_fc *counter = NULL, *last = NULL, *tmp;
unsigned long now = jiffies;
if (addlist || !list_empty(&fc_stats->counters))
queue_delayed_work(fc_stats->wq, &fc_stats->work,
fc_stats->sampling_interval);
llist_for_each_entry(counter, addlist, addlist)
mlx5_fc_stats_insert(dev, counter);
llist_for_each_entry_safe(counter, tmp, dellist, dellist) {
mlx5_fc_stats_remove(dev, counter);
mlx5_free_fc(dev, counter);
}
if (time_before(now, fc_stats->next_query) ||
list_empty(&fc_stats->counters))
return;
last = list_last_entry(&fc_stats->counters, struct mlx5_fc, list);
counter = list_first_entry(&fc_stats->counters, struct mlx5_fc,
list);
while (counter)
counter = mlx5_fc_stats_query(dev, counter, last->id);
fc_stats->next_query = now + fc_stats->sampling_interval;
}
struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging)
{
struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
struct mlx5_fc *counter;
int err;
counter = kzalloc(sizeof(*counter), GFP_KERNEL);
if (!counter)
return ERR_PTR(-ENOMEM);
INIT_LIST_HEAD(&counter->list);
err = mlx5_cmd_fc_alloc(dev, &counter->id);
if (err)
goto err_out;
if (aging) {
u32 id = counter->id;
counter->cache.lastuse = jiffies;
counter->aging = true;
idr_preload(GFP_KERNEL);
spin_lock(&fc_stats->counters_idr_lock);
err = idr_alloc_u32(&fc_stats->counters_idr, counter, &id, id,
GFP_NOWAIT);
spin_unlock(&fc_stats->counters_idr_lock);
idr_preload_end();
if (err)
goto err_out_alloc;
llist_add(&counter->addlist, &fc_stats->addlist);
mod_delayed_work(fc_stats->wq, &fc_stats->work, 0);
|