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
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
|
/*
* Cell Broadband Engine OProfile Support
*
* (C) Copyright IBM Corporation 2006
*
* Author: Maynard Johnson <maynardj@us.ibm.com>
*
* 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, or (at your option) any later version.
*/
/* The purpose of this file is to handle SPU event task switching
* and to record SPU context information into the OProfile
* event buffer.
*
* Additionally, the spu_sync_buffer function is provided as a helper
* for recoding actual SPU program counter samples to the event buffer.
*/
#include <linux/dcookies.h>
#include <linux/kref.h>
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/module.h>
#include <linux/notifier.h>
#include <linux/numa.h>
#include <linux/oprofile.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include "pr_util.h"
#define RELEASE_ALL 9999
static DEFINE_SPINLOCK(buffer_lock);
static DEFINE_SPINLOCK(cache_lock);
static int num_spu_nodes;
int spu_prof_num_nodes;
struct spu_buffer spu_buff[MAX_NUMNODES * SPUS_PER_NODE];
struct delayed_work spu_work;
static unsigned max_spu_buff;
static void spu_buff_add(unsigned long int value, int spu)
{
/* spu buff is a circular buffer. Add entries to the
* head. Head is the index to store the next value.
* The buffer is full when there is one available entry
* in the queue, i.e. head and tail can't be equal.
* That way we can tell the difference between the
* buffer being full versus empty.
*
* ASSUMPTION: the buffer_lock is held when this function
* is called to lock the buffer, head and tail.
*/
int full = 1;
if (spu_buff[spu].head >= spu_buff[spu].tail) {
if ((spu_buff[spu].head - spu_buff[spu].tail)
< (max_spu_buff - 1))
full = 0;
} else if (spu_buff[spu].tail > spu_buff[spu].head) {
if ((spu_buff[spu].tail - spu_buff[spu].head)
> 1)
full = 0;
}
if (!full) {
spu_buff[spu].buff[spu_buff[spu].head] = value;
spu_buff[spu].head++;
if (spu_buff[spu].head >= max_spu_buff)
spu_buff[spu].head = 0;
} else {
/* From the user's perspective make the SPU buffer
* size management/overflow look like we are using
* per cpu buffers. The user uses the same
* per cpu parameter to adjust the SPU buffer size.
* Increment the sample_lost_overflow to inform
* the user the buffer size needs to be increased.
*/
oprofile_cpu_buffer_inc_smpl_lost();
}
}
/* This function copies the per SPU buffers to the
* OProfile kernel buffer.
*/
void sync_spu_buff(void)
{
int spu;
unsigned long flags;
int curr_head;
for (spu = 0; spu < num_spu_nodes; spu++) {
/* In case there was an issue and the buffer didn't
* get created skip it.
*/
if (spu_buff[spu].buff == NULL)
continue;
/* Hold the lock to make sure the head/tail
* doesn't change while spu_buff_add() is
* deciding if the buffer is full or not.
* Being a little paranoid.
*/
spin_lock_irqsave(&buffer_lock, flags);
curr_head = spu_buff[spu].head;
spin_unlock_irqrestore(&buffer_lock, flags);
/* Transfer the current contents to the kernel buffer.
* data can still be added to the head of the buffer.
*/
oprofile_put_buff(spu_buff[spu].buff,
spu_buff[spu].tail,
curr_head, max_spu_buff);
spin_lock_irqsave(&buffer_lock, flags);
spu_buff[spu].tail = curr_head;
spin_unlock_irqrestore(&buffer_lock, flags);
}
}
static void wq_sync_spu_buff(struct work_struct *work)
{
/* move data from spu buffers to kernel buffer */
sync_spu_buff();
/* only reschedule if profiling is not done */
if (spu_prof_running)
schedule_delayed_work(&spu_work, DEFAULT_TIMER_EXPIRE);
}
/* Container for caching information about an active SPU task. */
struct cached_info {
struct vma_to_fileoffset_map *map;
struct spu *the_spu; /* needed to access pointer to local_store */
struct kref cache_ref;
};
static struct cached_info *spu_info[MAX_NUMNODES * 8];
static void destroy_cached_info(struct kref *kref)
{
struct cached_info *info;
info = container_of(kref, struct cached_info, cache_ref);
vma_map_free(info->map);
kfree(info);
module_put(THIS_MODULE);
}
/* Return the cached_info for the passed SPU number.
* ATTENTION: Callers are responsible for obtaining the
* cache_lock if needed prior to invoking this function.
*/
static struct cached_info *get_cached_info(struct spu *the_spu, int spu_num)
{
struct kref *ref;
struct cached_info *ret_info;
if (spu_num >= num_spu_nodes) {
printk(KERN_ERR "SPU_PROF: "
"%s, line %d: Invalid index %d into spu info cache\n",
__func__, __LINE__, spu_num);
ret_info = NULL;
goto out;
}
if (!spu_info[spu_num] && the_spu) {
ref = spu_get_profile_private_kref(the_spu->ctx);
if (ref) {
spu_info[spu_num] = container_of(ref, struct cached_info, cache_ref);
kref_get(&spu_info[spu_num]->cache_ref);
}
}
ret_info = spu_info[spu_num];
out:
return ret_info;
}
/* Looks for cached info for the passed spu. If not found, the
* cached info is created for the passed spu.
* Returns 0 for success; otherwise, -1 for error.
*/
static int
prepare_cached_spu_info(struct spu *spu, unsigned long objectId)
{
unsigned long flags;
struct vma_to_fileoffset_map *new_map;
int retval = 0;
struct cached_info *info;
/* We won't bother getting cache_lock here since
* don't do anything with the cached_info that's returned.
*/
info = get_cached_info(spu, spu->number);
if (info) {
pr_debug("Found cached SPU info.\n");
goto out;
}
/* Create cached_info and set spu_info[spu->number] to point to it.
* spu->number is a system-wide value, not a per-node value.
*/
info = kzalloc(sizeof(struct cached_info), GFP_KERNEL);
if (!info) {
printk(KERN_ERR "SPU_PROF: "
"%s, line %d: create vma_map failed\n",
__func__, __LINE__);
retval = -ENOMEM;
goto err_alloc;
}
new_map = create_vma_map(spu, objectId);
if (!new_map) {
printk(KERN_ERR "SPU_PROF: "
"%s, line %d: create vma_map failed\n",
__func__, __LINE__);
retval = -ENOMEM;
goto err_alloc;
}
pr_debug("Created vma_map\n");
info->map = new_map;
info->the_spu = spu;
kref_init(&info->cache_ref);
spin_lock_irqsave(&cache_lock, flags);
spu_info[spu->number] = info;
/* Increment count before passing off ref to SPUFS. */
kref_get(&info->cache_ref);
/* We increment the module refcount here since SPUFS is
* responsible for the final destruction of the cached_info,
* and it must be able to access the destroy_cached_info()
* function defined in the OProfile module. We decrement
* the module refcount in destroy_cached_info.
*/
try_module_get(THIS_MODULE);
spu_set_profile_private_kref(spu->ctx, &info->cache_ref,
destroy_cached_info);
spin_unlock_irqrestore(&cache_lock, flags);
goto out;
err_alloc:
kfree(info);
out:
return retval;
}
/*
* NOTE: The caller is responsible for locking the
* cache_lock prior to calling this function.
*/
static int release_cached_info
|