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
|
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* RDMA Network Block Driver
*
* Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved.
* Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved.
* Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved.
*/
#undef pr_fmt
#define pr_fmt(fmt) KBUILD_MODNAME " L" __stringify(__LINE__) ": " fmt
#include <linux/types.h>
#include <linux/ctype.h>
#include <linux/parser.h>
#include <linux/module.h>
#include <linux/in6.h>
#include <linux/fs.h>
#include <linux/uaccess.h>
#include <linux/device.h>
#include <rdma/ib.h>
#include <rdma/rdma_cm.h>
#include "rnbd-clt.h"
static struct device *rnbd_dev;
static const struct class rnbd_dev_class = {
.name = "rnbd-client",
};
static struct kobject *rnbd_devs_kobj;
enum {
RNBD_OPT_ERR = 0,
RNBD_OPT_DEST_PORT = 1 << 0,
RNBD_OPT_PATH = 1 << 1,
RNBD_OPT_DEV_PATH = 1 << 2,
RNBD_OPT_ACCESS_MODE = 1 << 3,
RNBD_OPT_SESSNAME = 1 << 6,
RNBD_OPT_NR_POLL_QUEUES = 1 << 7,
};
static const unsigned int rnbd_opt_mandatory[] = {
RNBD_OPT_DEV_PATH,
RNBD_OPT_SESSNAME,
};
static const match_table_t rnbd_opt_tokens = {
{RNBD_OPT_PATH, "path=%s" },
{RNBD_OPT_DEV_PATH, "device_path=%s" },
{RNBD_OPT_DEST_PORT, "dest_port=%d" },
{RNBD_OPT_ACCESS_MODE, "access_mode=%s" },
{RNBD_OPT_SESSNAME, "sessname=%s" },
{RNBD_OPT_NR_POLL_QUEUES, "nr_poll_queues=%d" },
{RNBD_OPT_ERR, NULL },
};
struct rnbd_map_options {
char *sessname;
struct rtrs_addr *paths;
size_t *path_cnt;
char *pathname;
u16 *dest_port;
enum rnbd_access_mode *access_mode;
u32 *nr_poll_queues;
};
static int rnbd_clt_parse_map_options(const char *buf, size_t max_path_cnt,
struct rnbd_map_options *opt)
{
char *options, *sep_opt;
char *p;
substring_t args[MAX_OPT_ARGS];
int opt_mask = 0;
int token;
int ret = -EINVAL;
int nr_poll_queues = 0;
int dest_port = 0;
int p_cnt = 0;
int i;
options = kstrdup(buf, GFP_KERNEL);
if (!options)
return -ENOMEM;
sep_opt = strstrip(options);
while ((p = strsep(&sep_opt, " ")) != NULL) {
if (!*p)
continue;
token = match_token(p, rnbd_opt_tokens, args);
opt_mask |= token;
switch (token) {
case RNBD_OPT_SESSNAME:
p = match_strdup(args);
if (!p) {
ret = -ENOMEM;
goto out;
}
if (strlen(p) > NAME_MAX) {
pr_err("map_device: sessname too long\n");
ret = -EINVAL;
kfree(p);
goto out;
}
strscpy(opt->sessname, p, NAME_MAX);
kfree(p);
break;
case RNBD_OPT_PATH:
if (p_cnt >= max_path_cnt) {
pr_err("map_device: too many (> %zu) paths provided\n",
max_path_cnt);
ret = -ENOMEM;
goto out;
}
p = match_strdup(args);
if (!p) {
ret = -ENOMEM;
goto out;
}
ret = rtrs_addr_to_sockaddr(p, strlen(p),
*opt->dest_port,
&opt->paths[p_cnt]);
if (ret) {
pr_err("Can't parse path %s: %d\n", p, ret);
kfree(p);
goto out;
}
p_cnt++;
kfree(p);
break;
case RNBD_OPT_DEV_PATH:
p = match_strdup(args);
if (!p) {
ret = -ENOMEM;
goto out;
}
if (strlen(p) > NAME_MAX) {
pr_err("map_device: Device path too long\n");
ret = -EINVAL;
kfree(p);
goto out;
}
strscpy(opt->pathname, p, NAME_MAX);
kfree(p);
break;
case RNBD_OPT_DEST_PORT:
if (match_int(args, &dest_port) || dest_port < 0 ||
dest_port > 65535) {
pr_err("bad destination port number parameter '%d'\n",
dest_port);
ret = -EINVAL;
goto out;
}
*opt->dest_port = dest_port;
break;
case RNBD_OPT_ACCESS_MODE:
p = match_strdup(args);
if (!p) {
ret = -ENOMEM;
goto out;
}
if (!strcmp(p, "ro")) {
*opt->access_mode = RNBD_ACCESS_RO;
} else if (!strcmp(p, "rw")) {
*opt->access_mode = RNBD_ACCESS_RW;
} else if (!strcmp(p, "migration")) {
*opt->access_mode = RNBD_ACCESS_MIGRATION;
} else {
pr_err("map_device: Invalid access_mode: '%s'\n",
p);
ret = -EINVAL;
kfree(p);
goto out;
}
kfree(p);
break;
case RNBD_OPT_NR_POLL_QUEUES:
if (match_int(args, &nr_poll_queues) || nr_poll_queues < -1 ||
nr_poll_queues > (int)nr_cpu_ids) {
pr_err("bad nr_poll_queues parameter '%d'\n",
nr_poll_queues);
ret = -EINVAL;
goto out;
}
if (nr_poll_queues == -1)
nr_poll_queues = nr_cpu_ids;
*opt->nr_poll_queues = nr_poll_queues;
break;
default:
pr_err("map_device: Unknown parameter or missing value '%s'\n",
p);
ret = -EINVAL;
goto out;
}
}
for (i = 0; i < ARRAY_SIZE(rnbd_opt_mandatory); i++) {
if ((opt_mask & rnbd_opt_mandatory[i])) {
ret = 0;
} else {
pr_err("map_device: Parameters missing\n");
ret = -EINVAL;
break;
}
}
out:
*opt->path_cnt = p_cnt;
kfree(options);
return ret;
}
static ssize_t state_show(struct kobject *kobj,
struct kobj_attribute *attr, char *page)
{
struct rnbd_clt_dev *dev;
dev = container_of(kobj, struct rnbd_clt_dev, kobj);
switch (dev->dev_state) {
case DEV_STATE_INIT:
return sysfs_emit(page, "init\n");
case DEV_STATE_MAPPED:
/* TODO fix cli tool before changing to proper state */
return sysfs_emit(page, "open\n");
case DEV_STATE_MAPPED_DISCONNECTED:
/* TODO fix cli tool before changing to proper state */
return sysfs_emit(page, "closed\n");
case DEV_STATE_UNMAPPED:
return sysfs_emit(page, "unmapped\n");
default:
return sysfs_emit(page, "unknown\n");
}
}
static struct kobj_attribute rnbd_clt_state_attr = __ATTR_RO(state);
static ssize_t nr_poll_queues_show(struct kobject *kobj,
struct kobj_attribute *attr, char *page)
{
struct rnbd_clt_dev *dev;
dev = container_of(kobj, struct rnbd_clt_dev, kobj);
return sysfs_emit(page, "%d\n", dev->nr_poll_queues);
}
static struct kobj_attribute rnbd_clt_nr_poll_queues =
__ATTR_RO(nr_poll_queues);
static ssize_t mapping_path_show(struct kobject *kobj,
struct kobj_attribute *attr, char *page)
{
struct rnbd_clt_dev *dev;
dev = container_of(kobj, struct rnbd_clt_dev, kobj);
return sysfs_emit(page, "%s\n", dev->pathname);
}
static struct kobj_attribute rnbd_clt_mapping_path_attr =
__ATTR_RO(mapping_path);
static ssize_t access_mode_show(struct kobject *kobj,
struct kobj_attribute *attr, char *page)
{
struct rnbd_clt_dev *dev;
dev = container_of(kobj, struct rnbd_clt_dev, kobj);
return sysfs_emit(page, "%s\n", rnbd_access_modes[dev->access_mode].str);
}
static struct kobj_attribute rnbd_clt_access_mode =
__ATTR_RO(access_mode);
static ssize_t rnbd_clt_unmap_dev_show(struct kobject *kobj,
struct kobj_attribute *attr, char *page)
{
return sysfs_emit(page, "Usage: echo <normal|force> > %s\n",
attr->attr.name);
}
static ssize_t rnbd_clt_unmap_dev_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
struct rnbd_clt_dev *dev;
char *opt, *options;
bool force;
int err;
opt = kstrdup(buf, GFP_KERNEL);
if (!opt)
return -ENOMEM;
options = strstrip(opt);
dev = container_of(kobj, struct rnbd_clt_dev, kobj);
if (sysfs_streq(options, "normal")) {
force = false;
} else if (sysfs_streq(options, "force")) {
force = true;
} else {
rnbd_clt_err(dev,
"unmap_device: Invalid value: %s\n",
options);
err = -EINVAL;
goto out;
}
rnbd_clt_info(dev, "Unmapping device, option: %s.\n",
force ? "force" : "normal");
/*
* We take explicit module reference only for one reason: do not
* race with lockless rnbd_destroy_sessions().
*/
if (!try_module_get(THIS_MODULE)) {
err = -ENODEV;
goto out;
}
err = rnbd_clt_unmap_device(dev, force, &attr->attr);
if (err) {
if (err != -EALREADY)
rnbd_clt_err(dev, "unmap_device: %d\n", err);
goto module_put;
}
/*
* Here device can be vanished!
*/
err = count;
module_put:
module_put(THIS_MODULE);
out:
kfree(opt);
return err;
}
static struct kobj_attribute rnbd_clt_unmap_device_attr =
__ATTR(unmap_device, 0644, rnbd_clt_unmap_dev_show,
rnbd_clt_unmap_dev_store);
static ssize_t rnbd_clt_resize_dev_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *page)
{
return sysfs_emit(page, "Usage: echo <new size in sectors> > %s\n",
attr->attr.name);
}
static ssize_t rnbd_clt_resize_dev_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
int ret;
unsigned long sectors;
struct rnbd_clt_dev *dev;
dev = container_of(kobj, struct rnbd_clt_dev, kobj);
ret = kstrtoul(buf, 0, §ors);
if (ret)
return ret;
ret = rnbd_clt_resize_disk(dev, sectors);
if (ret)
return ret;
return count;
}
static struct kobj_attribute rnbd_clt_resize_dev_attr =
__ATTR(resize, 0644, rnbd_clt_resize_dev_show,
rnbd_clt_resize_dev_store);
static ssize_t rnbd_clt_remap_dev_show(struct kobject *kobj,
struct kobj_attribute *attr, char *page)
{
return sysfs_emit(page, "Usage: echo <1> > %s\n", attr->attr.name);
}
static ssize_t rnbd_clt_remap_dev_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
struct rnbd_clt_dev *dev;
char *opt, *options;
int err;
opt = kstrdup(buf, GFP_KERNEL);
if (!opt)
return -ENOMEM;
options = strstrip(opt);
dev = container_of(kobj, struct rnbd_clt_dev, kobj);
if (!sysfs_streq(options, "1")) {
rnbd_clt_err(dev,
"remap_device: Invalid value: %s\n",
options);
err = -EINVAL;
goto out;
}
err = rnbd_clt_remap_device(dev);
if (likely(!err))
err = count;
out:
kfree(opt);
return err;
}
static struct kobj_attribute rnbd_clt_remap_device_attr =
__ATTR(remap_device, 0644, rnbd_clt_remap_dev_show,
rnbd_clt_remap_dev_store);
static ssize_t session_show(struct kobject *kobj, struct kobj_attribute *attr,
char *page)
{
struct rnbd_clt_dev *dev;
dev = container_of(kobj, struct rnbd_clt_dev, kobj);
return sysfs_emit(page, "%s\n", dev->sess->sessname);
}
static struct kobj_attribute rnbd_clt_session_attr =
__ATTR_RO(session);
static struct attribute *rnbd_dev_attrs[] = {
&rnbd_clt_unmap_device_attr.attr,
&rnbd_clt_resize_dev_attr.attr,
&rnbd_clt_remap_device_attr.attr,
&rnbd_clt_mapping_path_attr.attr,
&rnbd_clt_state_attr.attr,
&rnbd_clt_session_attr.attr,
&rnbd_clt_access_mode.attr,
&rnbd_clt_nr_poll_queues.attr,
NULL,
};
ATTRIBUTE_GROUPS(rnbd_dev);
void rnbd_clt_remove_dev_symlink(struct rnbd_clt_dev *dev)
{
/*
* The module unload rnbd_client_exit path is racing with unmapping of
* the last single device from the sysfs manually
* i.e. rnbd_clt_unmap_dev_store() leading to a sysfs warning because
* of sysfs link already was removed already.
*/
if (dev->blk_symlink_name) {
if (try_module_get(THIS_MODULE)) {
sysfs_remove_link(rnbd_devs_kobj, dev->blk_symlink_name);
module_put(THIS_MODULE);
}
/* It should be freed always. */
kfree(dev->blk_symlink_name);
dev->blk_symlink_name = NULL;
}
}
static const struct kobj_type rnbd_dev_ktype = {
.sysfs_ops = &kobj_sysfs_ops,
.default_groups = rnbd_dev_groups,
};
static int rnbd_clt_add_dev_kobj(struct rnbd_clt_dev *dev)
{
int ret;
struct kobject *gd_kobj = &disk_to_dev(dev->gd)->kobj;
ret = kobject_init_and_add(&dev->kobj, &rnbd_dev_ktype, gd_kobj, "%s",
"rnbd");
if (ret) {
rnbd_clt_err(dev, "Failed to create device sysfs dir, err: %d\n",
ret);
kobject_put(&dev->kobj);
}
kobject_uevent(gd_kobj, KOBJ_ONLINE);
return ret;
}
static ssize_t rnbd_clt_map_device_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *page)
{
return sysfs_emit(page,
"Usage: echo \"[dest_port=server port number] sessname=<name of the rtrs session> path=<[srcaddr@]dstaddr> [path=<[srcaddr@]dstaddr>] device_path=<full path on remote side> [access_mode=<ro|rw|migration>] [nr_poll_queues=<number of queues>]\" > %s\n\naddr ::= [ ip:<ipv4> | ip:<ipv6> | gid:<gid> ]\n",
attr->attr.name);
}
static int rnbd_clt_get_path_name(struct rnbd_clt_dev *dev, char *buf,
size_t len)
{
int ret;
char pathname[NAME_MAX], *s;
strscpy(pathname, dev->pathname, sizeof(pathname));
while ((s = strchr(pathname, '/')))
s[0] = '!';
ret = snprintf(buf, len, "%s@%s", pathname, dev->sess->sessname);
if (ret >= len)
return -ENAMETOOLONG;
return 0;
}
static int rnbd_clt_add_dev_symlink(struct rnbd_clt_dev *dev)
{
struct kobject *gd_kobj = &disk_to_dev(dev->gd)->kobj;
int ret, len;
len = strlen(dev->pathname) + strlen(dev->sess->sessname) + 2;
dev->blk_symlink_name = kzalloc(len, GFP_KERNEL);
if (!dev->blk_symlink_name) {
rnbd_clt_err(dev, "Failed to allocate memory for blk_symlink_name\n");
return -ENOMEM;
}
ret = rnbd_clt_get_path_name(dev, dev->blk_symlink_name,
len);
if (ret) {
rnbd_clt_err(dev, "Failed to get /sys/block symlink path, err: %d\n",
ret);
goto out_err;
}
ret = sysfs_create_link(rnbd_devs_kobj, gd_kobj,
dev->blk_symlink_name);
if (ret) {
rnbd_clt_err(dev, "Creating /sys/block symlink failed, err: %d\n",
ret);
goto out_err;
}
return 0;
out_err:
kfree(dev->blk_symlink_name);
dev->blk_symlink_name = NULL ;
return ret;
}
static ssize_t rnbd_clt_map_device_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
struct rnbd_clt_dev *dev;
struct rnbd_map_options opt;
int ret;
char pathname[NAME_MAX];
char sessname[NAME_MAX];
enum rnbd_access_mode access_mode = RNBD_ACCESS_RW;
u16 port_nr = RTRS_PORT;
u32 nr_poll_queues = 0;
struct sockaddr_storage *addrs;
struct rtrs_addr paths[6];
size_t path_cnt;
opt.sessname = sessname;
opt.paths = paths;
opt.path_cnt = &path_cnt;
opt.pathname = pathname;
opt.dest_port = &port_nr;
opt.access_mode = &access_mode;
opt.nr_poll_queues = &nr_poll_queues;
addrs = kcalloc(ARRAY_SIZE(paths) * 2, sizeof(*addrs), GFP_KERNEL);
if (!addrs)
return -ENOMEM;
for (path_cnt = 0; path_cnt < ARRAY_SIZE(paths); path_cnt++) {
paths[path_cnt].src = &addrs[path_cnt * 2];
paths[path_cnt].dst = &addrs[path_cnt * 2 + 1];
}
ret = rnbd_clt_parse_map_options(buf, ARRAY_SIZE(paths), &opt);
if (ret)
goto out;
pr_info("Mapping device %s on session %s, (access_mode: %s, nr_poll_queues: %d)\n",
pathname, sessname,
rnbd_access_modes[access_mode].str,
nr_poll_queues);
dev = rnbd_clt_map_device(sessname, paths, path_cnt, port_nr, pathname,
access_mode, nr_poll_queues);
if (IS_ERR(dev)) {
ret = PTR_ERR(dev);
goto out;
}
ret = rnbd_clt_add_dev_kobj(dev);
if (ret)
goto unmap_dev;
ret = rnbd_clt_add_dev_symlink(dev);
if (ret)
goto unmap_dev;
kfree(addrs);
return count;
unmap_dev:
rnbd_clt_unmap_device(dev, true, NULL);
out:
kfree(addrs);
return ret;
}
static struct kobj_attribute rnbd_clt_map_device_attr =
__ATTR(map_device, 0644,
rnbd_clt_map_device_show, rnbd_clt_map_device_store);
static struct attribute *default_attrs[] = {
&rnbd_clt_map_device_attr.attr,
NULL,
};
static struct attribute_group default_attr_group = {
.attrs = default_attrs,
};
static const struct attribute_group *default_attr_groups[] = {
&default_attr_group,
NULL,
};
int rnbd_clt_create_sysfs_files(void)
{
int err;
err = class_register(&rnbd_dev_class);
if (err)
return err;
rnbd_dev = device_create_with_groups(&rnbd_dev_class, NULL,
MKDEV(0, 0), NULL,
default_attr_groups, "ctl");
if (IS_ERR(rnbd_dev)) {
err = PTR_ERR(rnbd_dev);
goto cls_destroy;
}
rnbd_devs_kobj = kobject_create_and_add("devices", &rnbd_dev->kobj);
if (!rnbd_devs_kobj) {
err = -ENOMEM;
goto dev_destroy;
}
return 0;
dev_destroy:
device_destroy(&rnbd_dev_class, MKDEV(0, 0));
cls_destroy:
class_unregister(&rnbd_dev_class);
return err;
}
void rnbd_clt_destroy_sysfs_files(void)
{
sysfs_remove_group(&rnbd_dev->kobj, &default_attr_group);
kobject_del(rnbd_devs_kobj);
kobject_put(rnbd_devs_kobj);
device_destroy(&rnbd_dev_class, MKDEV(0, 0));
class_unregister(&rnbd_dev_class);
}
|