forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
blktrace.c
1911 lines (1612 loc) · 45.9 KB
/
blktrace.c
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
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2006 Jens Axboe <[email protected]>
*
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/blkdev.h>
#include <linux/blktrace_api.h>
#include <linux/percpu.h>
#include <linux/init.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/debugfs.h>
#include <linux/export.h>
#include <linux/time.h>
#include <linux/uaccess.h>
#include <linux/list.h>
#include <linux/blk-cgroup.h>
#include "../../block/blk.h"
#include <trace/events/block.h>
#include "trace_output.h"
#ifdef CONFIG_BLK_DEV_IO_TRACE
static unsigned int blktrace_seq __read_mostly = 1;
static struct trace_array *blk_tr;
static bool blk_tracer_enabled __read_mostly;
static LIST_HEAD(running_trace_list);
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(running_trace_lock);
/* Select an alternative, minimalistic output than the original one */
#define TRACE_BLK_OPT_CLASSIC 0x1
#define TRACE_BLK_OPT_CGROUP 0x2
#define TRACE_BLK_OPT_CGNAME 0x4
static struct tracer_opt blk_tracer_opts[] = {
/* Default disable the minimalistic output */
{ TRACER_OPT(blk_classic, TRACE_BLK_OPT_CLASSIC) },
#ifdef CONFIG_BLK_CGROUP
{ TRACER_OPT(blk_cgroup, TRACE_BLK_OPT_CGROUP) },
{ TRACER_OPT(blk_cgname, TRACE_BLK_OPT_CGNAME) },
#endif
{ }
};
static struct tracer_flags blk_tracer_flags = {
.val = 0,
.opts = blk_tracer_opts,
};
/* Global reference count of probes */
static DEFINE_MUTEX(blk_probe_mutex);
static int blk_probes_ref;
static void blk_register_tracepoints(void);
static void blk_unregister_tracepoints(void);
/*
* Send out a notify message.
*/
static void trace_note(struct blk_trace *bt, pid_t pid, int action,
const void *data, size_t len, u64 cgid)
{
struct blk_io_trace *t;
struct ring_buffer_event *event = NULL;
struct trace_buffer *buffer = NULL;
int pc = 0;
int cpu = smp_processor_id();
bool blk_tracer = blk_tracer_enabled;
ssize_t cgid_len = cgid ? sizeof(cgid) : 0;
if (blk_tracer) {
buffer = blk_tr->array_buffer.buffer;
pc = preempt_count();
event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
sizeof(*t) + len + cgid_len,
0, pc);
if (!event)
return;
t = ring_buffer_event_data(event);
goto record_it;
}
if (!bt->rchan)
return;
t = relay_reserve(bt->rchan, sizeof(*t) + len + cgid_len);
if (t) {
t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION;
t->time = ktime_to_ns(ktime_get());
record_it:
t->device = bt->dev;
t->action = action | (cgid ? __BLK_TN_CGROUP : 0);
t->pid = pid;
t->cpu = cpu;
t->pdu_len = len + cgid_len;
if (cgid_len)
memcpy((void *)t + sizeof(*t), &cgid, cgid_len);
memcpy((void *) t + sizeof(*t) + cgid_len, data, len);
if (blk_tracer)
trace_buffer_unlock_commit(blk_tr, buffer, event, 0, pc);
}
}
/*
* Send out a notify for this process, if we haven't done so since a trace
* started
*/
static void trace_note_tsk(struct task_struct *tsk)
{
unsigned long flags;
struct blk_trace *bt;
tsk->btrace_seq = blktrace_seq;
spin_lock_irqsave(&running_trace_lock, flags);
list_for_each_entry(bt, &running_trace_list, running_list) {
trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm,
sizeof(tsk->comm), 0);
}
spin_unlock_irqrestore(&running_trace_lock, flags);
}
static void trace_note_time(struct blk_trace *bt)
{
struct timespec64 now;
unsigned long flags;
u32 words[2];
/* need to check user space to see if this breaks in y2038 or y2106 */
ktime_get_real_ts64(&now);
words[0] = (u32)now.tv_sec;
words[1] = now.tv_nsec;
local_irq_save(flags);
trace_note(bt, 0, BLK_TN_TIMESTAMP, words, sizeof(words), 0);
local_irq_restore(flags);
}
void __trace_note_message(struct blk_trace *bt, struct blkcg *blkcg,
const char *fmt, ...)
{
int n;
va_list args;
unsigned long flags;
char *buf;
if (unlikely(bt->trace_state != Blktrace_running &&
!blk_tracer_enabled))
return;
/*
* If the BLK_TC_NOTIFY action mask isn't set, don't send any note
* message to the trace.
*/
if (!(bt->act_mask & BLK_TC_NOTIFY))
return;
local_irq_save(flags);
buf = this_cpu_ptr(bt->msg_data);
va_start(args, fmt);
n = vscnprintf(buf, BLK_TN_MAX_MSG, fmt, args);
va_end(args);
if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP))
blkcg = NULL;
#ifdef CONFIG_BLK_CGROUP
trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n,
blkcg ? cgroup_id(blkcg->css.cgroup) : 1);
#else
trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n, 0);
#endif
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(__trace_note_message);
static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector,
pid_t pid)
{
if (((bt->act_mask << BLK_TC_SHIFT) & what) == 0)
return 1;
if (sector && (sector < bt->start_lba || sector > bt->end_lba))
return 1;
if (bt->pid && pid != bt->pid)
return 1;
return 0;
}
/*
* Data direction bit lookup
*/
static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
BLK_TC_ACT(BLK_TC_WRITE) };
#define BLK_TC_RAHEAD BLK_TC_AHEAD
#define BLK_TC_PREFLUSH BLK_TC_FLUSH
/* The ilog2() calls fall out because they're constant */
#define MASK_TC_BIT(rw, __name) ((rw & REQ_ ## __name) << \
(ilog2(BLK_TC_ ## __name) + BLK_TC_SHIFT - __REQ_ ## __name))
/*
* The worker for the various blk_add_trace*() types. Fills out a
* blk_io_trace structure and places it in a per-cpu subbuffer.
*/
static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
int op, int op_flags, u32 what, int error, int pdu_len,
void *pdu_data, u64 cgid)
{
struct task_struct *tsk = current;
struct ring_buffer_event *event = NULL;
struct trace_buffer *buffer = NULL;
struct blk_io_trace *t;
unsigned long flags = 0;
unsigned long *sequence;
pid_t pid;
int cpu, pc = 0;
bool blk_tracer = blk_tracer_enabled;
ssize_t cgid_len = cgid ? sizeof(cgid) : 0;
if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer))
return;
what |= ddir_act[op_is_write(op) ? WRITE : READ];
what |= MASK_TC_BIT(op_flags, SYNC);
what |= MASK_TC_BIT(op_flags, RAHEAD);
what |= MASK_TC_BIT(op_flags, META);
what |= MASK_TC_BIT(op_flags, PREFLUSH);
what |= MASK_TC_BIT(op_flags, FUA);
if (op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)
what |= BLK_TC_ACT(BLK_TC_DISCARD);
if (op == REQ_OP_FLUSH)
what |= BLK_TC_ACT(BLK_TC_FLUSH);
if (cgid)
what |= __BLK_TA_CGROUP;
pid = tsk->pid;
if (act_log_check(bt, what, sector, pid))
return;
cpu = raw_smp_processor_id();
if (blk_tracer) {
tracing_record_cmdline(current);
buffer = blk_tr->array_buffer.buffer;
pc = preempt_count();
event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
sizeof(*t) + pdu_len + cgid_len,
0, pc);
if (!event)
return;
t = ring_buffer_event_data(event);
goto record_it;
}
if (unlikely(tsk->btrace_seq != blktrace_seq))
trace_note_tsk(tsk);
/*
* A word about the locking here - we disable interrupts to reserve
* some space in the relay per-cpu buffer, to prevent an irq
* from coming in and stepping on our toes.
*/
local_irq_save(flags);
t = relay_reserve(bt->rchan, sizeof(*t) + pdu_len + cgid_len);
if (t) {
sequence = per_cpu_ptr(bt->sequence, cpu);
t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION;
t->sequence = ++(*sequence);
t->time = ktime_to_ns(ktime_get());
record_it:
/*
* These two are not needed in ftrace as they are in the
* generic trace_entry, filled by tracing_generic_entry_update,
* but for the trace_event->bin() synthesizer benefit we do it
* here too.
*/
t->cpu = cpu;
t->pid = pid;
t->sector = sector;
t->bytes = bytes;
t->action = what;
t->device = bt->dev;
t->error = error;
t->pdu_len = pdu_len + cgid_len;
if (cgid_len)
memcpy((void *)t + sizeof(*t), &cgid, cgid_len);
if (pdu_len)
memcpy((void *)t + sizeof(*t) + cgid_len, pdu_data, pdu_len);
if (blk_tracer) {
trace_buffer_unlock_commit(blk_tr, buffer, event, 0, pc);
return;
}
}
local_irq_restore(flags);
}
static void blk_trace_free(struct blk_trace *bt)
{
debugfs_remove(bt->msg_file);
debugfs_remove(bt->dropped_file);
relay_close(bt->rchan);
debugfs_remove(bt->dir);
free_percpu(bt->sequence);
free_percpu(bt->msg_data);
kfree(bt);
}
static void get_probe_ref(void)
{
mutex_lock(&blk_probe_mutex);
if (++blk_probes_ref == 1)
blk_register_tracepoints();
mutex_unlock(&blk_probe_mutex);
}
static void put_probe_ref(void)
{
mutex_lock(&blk_probe_mutex);
if (!--blk_probes_ref)
blk_unregister_tracepoints();
mutex_unlock(&blk_probe_mutex);
}
static void blk_trace_cleanup(struct blk_trace *bt)
{
synchronize_rcu();
blk_trace_free(bt);
put_probe_ref();
}
static int __blk_trace_remove(struct request_queue *q)
{
struct blk_trace *bt;
bt = rcu_replace_pointer(q->blk_trace, NULL,
lockdep_is_held(&q->debugfs_mutex));
if (!bt)
return -EINVAL;
if (bt->trace_state != Blktrace_running)
blk_trace_cleanup(bt);
return 0;
}
int blk_trace_remove(struct request_queue *q)
{
int ret;
mutex_lock(&q->debugfs_mutex);
ret = __blk_trace_remove(q);
mutex_unlock(&q->debugfs_mutex);
return ret;
}
EXPORT_SYMBOL_GPL(blk_trace_remove);
static ssize_t blk_dropped_read(struct file *filp, char __user *buffer,
size_t count, loff_t *ppos)
{
struct blk_trace *bt = filp->private_data;
char buf[16];
snprintf(buf, sizeof(buf), "%u\n", atomic_read(&bt->dropped));
return simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf));
}
static const struct file_operations blk_dropped_fops = {
.owner = THIS_MODULE,
.open = simple_open,
.read = blk_dropped_read,
.llseek = default_llseek,
};
static ssize_t blk_msg_write(struct file *filp, const char __user *buffer,
size_t count, loff_t *ppos)
{
char *msg;
struct blk_trace *bt;
if (count >= BLK_TN_MAX_MSG)
return -EINVAL;
msg = memdup_user_nul(buffer, count);
if (IS_ERR(msg))
return PTR_ERR(msg);
bt = filp->private_data;
__trace_note_message(bt, NULL, "%s", msg);
kfree(msg);
return count;
}
static const struct file_operations blk_msg_fops = {
.owner = THIS_MODULE,
.open = simple_open,
.write = blk_msg_write,
.llseek = noop_llseek,
};
/*
* Keep track of how many times we encountered a full subbuffer, to aid
* the user space app in telling how many lost events there were.
*/
static int blk_subbuf_start_callback(struct rchan_buf *buf, void *subbuf,
void *prev_subbuf, size_t prev_padding)
{
struct blk_trace *bt;
if (!relay_buf_full(buf))
return 1;
bt = buf->chan->private_data;
atomic_inc(&bt->dropped);
return 0;
}
static int blk_remove_buf_file_callback(struct dentry *dentry)
{
debugfs_remove(dentry);
return 0;
}
static struct dentry *blk_create_buf_file_callback(const char *filename,
struct dentry *parent,
umode_t mode,
struct rchan_buf *buf,
int *is_global)
{
return debugfs_create_file(filename, mode, parent, buf,
&relay_file_operations);
}
static const struct rchan_callbacks blk_relay_callbacks = {
.subbuf_start = blk_subbuf_start_callback,
.create_buf_file = blk_create_buf_file_callback,
.remove_buf_file = blk_remove_buf_file_callback,
};
static void blk_trace_setup_lba(struct blk_trace *bt,
struct block_device *bdev)
{
if (bdev) {
bt->start_lba = bdev->bd_start_sect;
bt->end_lba = bdev->bd_start_sect + bdev_nr_sectors(bdev);
} else {
bt->start_lba = 0;
bt->end_lba = -1ULL;
}
}
/*
* Setup everything required to start tracing
*/
static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
struct block_device *bdev,
struct blk_user_trace_setup *buts)
{
struct blk_trace *bt = NULL;
struct dentry *dir = NULL;
int ret;
lockdep_assert_held(&q->debugfs_mutex);
if (!buts->buf_size || !buts->buf_nr)
return -EINVAL;
strncpy(buts->name, name, BLKTRACE_BDEV_SIZE);
buts->name[BLKTRACE_BDEV_SIZE - 1] = '\0';
/*
* some device names have larger paths - convert the slashes
* to underscores for this to work as expected
*/
strreplace(buts->name, '/', '_');
/*
* bdev can be NULL, as with scsi-generic, this is a helpful as
* we can be.
*/
if (rcu_dereference_protected(q->blk_trace,
lockdep_is_held(&q->debugfs_mutex))) {
pr_warn("Concurrent blktraces are not allowed on %s\n",
buts->name);
return -EBUSY;
}
bt = kzalloc(sizeof(*bt), GFP_KERNEL);
if (!bt)
return -ENOMEM;
ret = -ENOMEM;
bt->sequence = alloc_percpu(unsigned long);
if (!bt->sequence)
goto err;
bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG, __alignof__(char));
if (!bt->msg_data)
goto err;
/*
* When tracing the whole disk reuse the existing debugfs directory
* created by the block layer on init. For partitions block devices,
* and scsi-generic block devices we create a temporary new debugfs
* directory that will be removed once the trace ends.
*/
if (bdev && !bdev_is_partition(bdev))
dir = q->debugfs_dir;
else
bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root);
/*
* As blktrace relies on debugfs for its interface the debugfs directory
* is required, contrary to the usual mantra of not checking for debugfs
* files or directories.
*/
if (IS_ERR_OR_NULL(dir)) {
pr_warn("debugfs_dir not present for %s so skipping\n",
buts->name);
ret = -ENOENT;
goto err;
}
bt->dev = dev;
atomic_set(&bt->dropped, 0);
INIT_LIST_HEAD(&bt->running_list);
ret = -EIO;
bt->dropped_file = debugfs_create_file("dropped", 0444, dir, bt,
&blk_dropped_fops);
bt->msg_file = debugfs_create_file("msg", 0222, dir, bt, &blk_msg_fops);
bt->rchan = relay_open("trace", dir, buts->buf_size,
buts->buf_nr, &blk_relay_callbacks, bt);
if (!bt->rchan)
goto err;
bt->act_mask = buts->act_mask;
if (!bt->act_mask)
bt->act_mask = (u16) -1;
blk_trace_setup_lba(bt, bdev);
/* overwrite with user settings */
if (buts->start_lba)
bt->start_lba = buts->start_lba;
if (buts->end_lba)
bt->end_lba = buts->end_lba;
bt->pid = buts->pid;
bt->trace_state = Blktrace_setup;
rcu_assign_pointer(q->blk_trace, bt);
get_probe_ref();
ret = 0;
err:
if (ret)
blk_trace_free(bt);
return ret;
}
static int __blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
struct block_device *bdev, char __user *arg)
{
struct blk_user_trace_setup buts;
int ret;
ret = copy_from_user(&buts, arg, sizeof(buts));
if (ret)
return -EFAULT;
ret = do_blk_trace_setup(q, name, dev, bdev, &buts);
if (ret)
return ret;
if (copy_to_user(arg, &buts, sizeof(buts))) {
__blk_trace_remove(q);
return -EFAULT;
}
return 0;
}
int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
struct block_device *bdev,
char __user *arg)
{
int ret;
mutex_lock(&q->debugfs_mutex);
ret = __blk_trace_setup(q, name, dev, bdev, arg);
mutex_unlock(&q->debugfs_mutex);
return ret;
}
EXPORT_SYMBOL_GPL(blk_trace_setup);
#if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64)
static int compat_blk_trace_setup(struct request_queue *q, char *name,
dev_t dev, struct block_device *bdev,
char __user *arg)
{
struct blk_user_trace_setup buts;
struct compat_blk_user_trace_setup cbuts;
int ret;
if (copy_from_user(&cbuts, arg, sizeof(cbuts)))
return -EFAULT;
buts = (struct blk_user_trace_setup) {
.act_mask = cbuts.act_mask,
.buf_size = cbuts.buf_size,
.buf_nr = cbuts.buf_nr,
.start_lba = cbuts.start_lba,
.end_lba = cbuts.end_lba,
.pid = cbuts.pid,
};
ret = do_blk_trace_setup(q, name, dev, bdev, &buts);
if (ret)
return ret;
if (copy_to_user(arg, &buts.name, ARRAY_SIZE(buts.name))) {
__blk_trace_remove(q);
return -EFAULT;
}
return 0;
}
#endif
static int __blk_trace_startstop(struct request_queue *q, int start)
{
int ret;
struct blk_trace *bt;
bt = rcu_dereference_protected(q->blk_trace,
lockdep_is_held(&q->debugfs_mutex));
if (bt == NULL)
return -EINVAL;
/*
* For starting a trace, we can transition from a setup or stopped
* trace. For stopping a trace, the state must be running
*/
ret = -EINVAL;
if (start) {
if (bt->trace_state == Blktrace_setup ||
bt->trace_state == Blktrace_stopped) {
blktrace_seq++;
smp_mb();
bt->trace_state = Blktrace_running;
spin_lock_irq(&running_trace_lock);
list_add(&bt->running_list, &running_trace_list);
spin_unlock_irq(&running_trace_lock);
trace_note_time(bt);
ret = 0;
}
} else {
if (bt->trace_state == Blktrace_running) {
bt->trace_state = Blktrace_stopped;
spin_lock_irq(&running_trace_lock);
list_del_init(&bt->running_list);
spin_unlock_irq(&running_trace_lock);
relay_flush(bt->rchan);
ret = 0;
}
}
return ret;
}
int blk_trace_startstop(struct request_queue *q, int start)
{
int ret;
mutex_lock(&q->debugfs_mutex);
ret = __blk_trace_startstop(q, start);
mutex_unlock(&q->debugfs_mutex);
return ret;
}
EXPORT_SYMBOL_GPL(blk_trace_startstop);
/*
* When reading or writing the blktrace sysfs files, the references to the
* opened sysfs or device files should prevent the underlying block device
* from being removed. So no further delete protection is really needed.
*/
/**
* blk_trace_ioctl: - handle the ioctls associated with tracing
* @bdev: the block device
* @cmd: the ioctl cmd
* @arg: the argument data, if any
*
**/
int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
{
struct request_queue *q;
int ret, start = 0;
char b[BDEVNAME_SIZE];
q = bdev_get_queue(bdev);
if (!q)
return -ENXIO;
mutex_lock(&q->debugfs_mutex);
switch (cmd) {
case BLKTRACESETUP:
bdevname(bdev, b);
ret = __blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
break;
#if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64)
case BLKTRACESETUP32:
bdevname(bdev, b);
ret = compat_blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
break;
#endif
case BLKTRACESTART:
start = 1;
fallthrough;
case BLKTRACESTOP:
ret = __blk_trace_startstop(q, start);
break;
case BLKTRACETEARDOWN:
ret = __blk_trace_remove(q);
break;
default:
ret = -ENOTTY;
break;
}
mutex_unlock(&q->debugfs_mutex);
return ret;
}
/**
* blk_trace_shutdown: - stop and cleanup trace structures
* @q: the request queue associated with the device
*
**/
void blk_trace_shutdown(struct request_queue *q)
{
mutex_lock(&q->debugfs_mutex);
if (rcu_dereference_protected(q->blk_trace,
lockdep_is_held(&q->debugfs_mutex))) {
__blk_trace_startstop(q, 0);
__blk_trace_remove(q);
}
mutex_unlock(&q->debugfs_mutex);
}
#ifdef CONFIG_BLK_CGROUP
static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio)
{
struct blk_trace *bt;
/* We don't use the 'bt' value here except as an optimization... */
bt = rcu_dereference_protected(q->blk_trace, 1);
if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP))
return 0;
if (!bio->bi_blkg)
return 0;
return cgroup_id(bio_blkcg(bio)->css.cgroup);
}
#else
static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio)
{
return 0;
}
#endif
static u64
blk_trace_request_get_cgid(struct request *rq)
{
if (!rq->bio)
return 0;
/* Use the first bio */
return blk_trace_bio_get_cgid(rq->q, rq->bio);
}
/*
* blktrace probes
*/
/**
* blk_add_trace_rq - Add a trace for a request oriented action
* @rq: the source request
* @error: return status to log
* @nr_bytes: number of completed bytes
* @what: the action
* @cgid: the cgroup info
*
* Description:
* Records an action against a request. Will log the bio offset + size.
*
**/
static void blk_add_trace_rq(struct request *rq, int error,
unsigned int nr_bytes, u32 what, u64 cgid)
{
struct blk_trace *bt;
rcu_read_lock();
bt = rcu_dereference(rq->q->blk_trace);
if (likely(!bt)) {
rcu_read_unlock();
return;
}
if (blk_rq_is_passthrough(rq))
what |= BLK_TC_ACT(BLK_TC_PC);
else
what |= BLK_TC_ACT(BLK_TC_FS);
__blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq),
rq->cmd_flags, what, error, 0, NULL, cgid);
rcu_read_unlock();
}
static void blk_add_trace_rq_insert(void *ignore, struct request *rq)
{
blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_INSERT,
blk_trace_request_get_cgid(rq));
}
static void blk_add_trace_rq_issue(void *ignore, struct request *rq)
{
blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_ISSUE,
blk_trace_request_get_cgid(rq));
}
static void blk_add_trace_rq_merge(void *ignore, struct request *rq)
{
blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_BACKMERGE,
blk_trace_request_get_cgid(rq));
}
static void blk_add_trace_rq_requeue(void *ignore, struct request *rq)
{
blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_REQUEUE,
blk_trace_request_get_cgid(rq));
}
static void blk_add_trace_rq_complete(void *ignore, struct request *rq,
int error, unsigned int nr_bytes)
{
blk_add_trace_rq(rq, error, nr_bytes, BLK_TA_COMPLETE,
blk_trace_request_get_cgid(rq));
}
/**
* blk_add_trace_bio - Add a trace for a bio oriented action
* @q: queue the io is for
* @bio: the source bio
* @what: the action
* @error: error, if any
*
* Description:
* Records an action against a bio. Will log the bio offset + size.
*
**/
static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
u32 what, int error)
{
struct blk_trace *bt;
rcu_read_lock();
bt = rcu_dereference(q->blk_trace);
if (likely(!bt)) {
rcu_read_unlock();
return;
}
__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
bio_op(bio), bio->bi_opf, what, error, 0, NULL,
blk_trace_bio_get_cgid(q, bio));
rcu_read_unlock();
}
static void blk_add_trace_bio_bounce(void *ignore, struct bio *bio)
{
blk_add_trace_bio(bio->bi_disk->queue, bio, BLK_TA_BOUNCE, 0);
}
static void blk_add_trace_bio_complete(void *ignore,
struct request_queue *q, struct bio *bio)
{
blk_add_trace_bio(q, bio, BLK_TA_COMPLETE,
blk_status_to_errno(bio->bi_status));
}
static void blk_add_trace_bio_backmerge(void *ignore, struct bio *bio)
{
blk_add_trace_bio(bio->bi_disk->queue, bio, BLK_TA_BACKMERGE, 0);
}
static void blk_add_trace_bio_frontmerge(void *ignore, struct bio *bio)
{
blk_add_trace_bio(bio->bi_disk->queue, bio, BLK_TA_FRONTMERGE, 0);
}
static void blk_add_trace_bio_queue(void *ignore, struct bio *bio)
{
blk_add_trace_bio(bio->bi_disk->queue, bio, BLK_TA_QUEUE, 0);
}
static void blk_add_trace_getrq(void *ignore, struct bio *bio)
{
blk_add_trace_bio(bio->bi_disk->queue, bio, BLK_TA_GETRQ, 0);
}
static void blk_add_trace_plug(void *ignore, struct request_queue *q)
{
struct blk_trace *bt;
rcu_read_lock();
bt = rcu_dereference(q->blk_trace);
if (bt)
__blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, 0);
rcu_read_unlock();
}
static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
unsigned int depth, bool explicit)
{
struct blk_trace *bt;
rcu_read_lock();
bt = rcu_dereference(q->blk_trace);
if (bt) {
__be64 rpdu = cpu_to_be64(depth);
u32 what;
if (explicit)
what = BLK_TA_UNPLUG_IO;
else
what = BLK_TA_UNPLUG_TIMER;
__blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, 0);
}
rcu_read_unlock();
}
static void blk_add_trace_split(void *ignore, struct bio *bio, unsigned int pdu)
{
struct request_queue *q = bio->bi_disk->queue;
struct blk_trace *bt;
rcu_read_lock();
bt = rcu_dereference(q->blk_trace);
if (bt) {
__be64 rpdu = cpu_to_be64(pdu);
__blk_add_trace(bt, bio->bi_iter.bi_sector,
bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf,
BLK_TA_SPLIT,
blk_status_to_errno(bio->bi_status),
sizeof(rpdu), &rpdu,
blk_trace_bio_get_cgid(q, bio));
}
rcu_read_unlock();
}
/**
* blk_add_trace_bio_remap - Add a trace for a bio-remap operation
* @ignore: trace callback data parameter (not used)
* @bio: the source bio
* @dev: source device
* @from: source sector
*
* Called after a bio is remapped to a different device and/or sector.
**/
static void blk_add_trace_bio_remap(void *ignore, struct bio *bio, dev_t dev,
sector_t from)
{
struct request_queue *q = bio->bi_disk->queue;