Blame view

drivers/md/dm-log-userspace-base.c 19.1 KB
f5db4af46   Jonthan Brassow   dm raid1: add use...
1
2
3
4
5
6
7
  /*
   * Copyright (C) 2006-2009 Red Hat, Inc.
   *
   * This file is released under the LGPL.
   */
  
  #include <linux/bio.h>
5a0e3ad6a   Tejun Heo   include cleanup: ...
8
  #include <linux/slab.h>
f5db4af46   Jonthan Brassow   dm raid1: add use...
9
10
11
  #include <linux/dm-dirty-log.h>
  #include <linux/device-mapper.h>
  #include <linux/dm-log-userspace.h>
056075c76   Paul Gortmaker   md: Add module.h ...
12
  #include <linux/module.h>
f5db4af46   Jonthan Brassow   dm raid1: add use...
13
14
  
  #include "dm-log-userspace-transfer.h"
86a54a480   Jonathan Brassow   dm log userspace:...
15
  #define DM_LOG_USERSPACE_VSN "1.1.0"
f5db4af46   Jonthan Brassow   dm raid1: add use...
16
17
18
19
20
  struct flush_entry {
  	int type;
  	region_t region;
  	struct list_head list;
  };
085ae0651   Jonathan Brassow   dm log userspace:...
21
22
23
24
25
26
27
  /*
   * This limit on the number of mark and clear request is, to a degree,
   * arbitrary.  However, there is some basis for the choice in the limits
   * imposed on the size of data payload by dm-log-userspace-transfer.c:
   * dm_consult_userspace().
   */
  #define MAX_FLUSH_GROUP_COUNT 32
f5db4af46   Jonthan Brassow   dm raid1: add use...
28
29
  struct log_c {
  	struct dm_target *ti;
5a25f0eb7   Jonathan E Brassow   dm log userspace:...
30
  	struct dm_dev *log_dev;
f5db4af46   Jonthan Brassow   dm raid1: add use...
31
32
  	uint32_t region_size;
  	region_t region_count;
7ec23d509   Jonathan Brassow   dm log: userspace...
33
  	uint64_t luid;
f5db4af46   Jonthan Brassow   dm raid1: add use...
34
35
36
37
38
39
40
41
42
43
44
45
46
  	char uuid[DM_UUID_LEN];
  
  	char *usr_argv_str;
  	uint32_t usr_argc;
  
  	/*
  	 * in_sync_hint gets set when doing is_remote_recovering.  It
  	 * represents the first region that needs recovery.  IOW, the
  	 * first zero bit of sync_bits.  This can be useful for to limit
  	 * traffic for calls like is_remote_recovering and get_resync_work,
  	 * but be take care in its use for anything else.
  	 */
  	uint64_t in_sync_hint;
909cc4fb4   Jonathan Brassow   dm log userspace:...
47
48
49
50
51
52
  	/*
  	 * Mark and clear requests are held until a flush is issued
  	 * so that we can group, and thereby limit, the amount of
  	 * network traffic between kernel and userspace.  The 'flush_lock'
  	 * is used to protect these lists.
  	 */
f5db4af46   Jonthan Brassow   dm raid1: add use...
53
  	spinlock_t flush_lock;
909cc4fb4   Jonathan Brassow   dm log userspace:...
54
55
  	struct list_head mark_list;
  	struct list_head clear_list;
f5db4af46   Jonthan Brassow   dm raid1: add use...
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
  };
  
  static mempool_t *flush_entry_pool;
  
  static void *flush_entry_alloc(gfp_t gfp_mask, void *pool_data)
  {
  	return kmalloc(sizeof(struct flush_entry), gfp_mask);
  }
  
  static void flush_entry_free(void *element, void *pool_data)
  {
  	kfree(element);
  }
  
  static int userspace_do_request(struct log_c *lc, const char *uuid,
  				int request_type, char *data, size_t data_size,
  				char *rdata, size_t *rdata_size)
  {
  	int r;
  
  	/*
  	 * If the server isn't there, -ESRCH is returned,
  	 * and we must keep trying until the server is
  	 * restored.
  	 */
  retry:
7ec23d509   Jonathan Brassow   dm log: userspace...
82
  	r = dm_consult_userspace(uuid, lc->luid, request_type, data,
f5db4af46   Jonthan Brassow   dm raid1: add use...
83
84
85
86
87
88
89
90
91
92
  				 data_size, rdata, rdata_size);
  
  	if (r != -ESRCH)
  		return r;
  
  	DMERR(" Userspace log server not found.");
  	while (1) {
  		set_current_state(TASK_INTERRUPTIBLE);
  		schedule_timeout(2*HZ);
  		DMWARN("Attempting to contact userspace log server...");
7ec23d509   Jonathan Brassow   dm log: userspace...
93
94
  		r = dm_consult_userspace(uuid, lc->luid, DM_ULOG_CTR,
  					 lc->usr_argv_str,
f5db4af46   Jonthan Brassow   dm raid1: add use...
95
96
97
98
99
100
  					 strlen(lc->usr_argv_str) + 1,
  					 NULL, NULL);
  		if (!r)
  			break;
  	}
  	DMINFO("Reconnected to userspace log server... DM_ULOG_CTR complete");
7ec23d509   Jonathan Brassow   dm log: userspace...
101
  	r = dm_consult_userspace(uuid, lc->luid, DM_ULOG_RESUME, NULL,
f5db4af46   Jonthan Brassow   dm raid1: add use...
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
  				 0, NULL, NULL);
  	if (!r)
  		goto retry;
  
  	DMERR("Error trying to resume userspace log: %d", r);
  
  	return -ESRCH;
  }
  
  static int build_constructor_string(struct dm_target *ti,
  				    unsigned argc, char **argv,
  				    char **ctr_str)
  {
  	int i, str_size;
  	char *str = NULL;
  
  	*ctr_str = NULL;
  
  	for (i = 0, str_size = 0; i < argc; i++)
  		str_size += strlen(argv[i]) + 1; /* +1 for space between args */
  
  	str_size += 20; /* Max number of chars in a printed u64 number */
  
  	str = kzalloc(str_size, GFP_KERNEL);
  	if (!str) {
  		DMWARN("Unable to allocate memory for constructor string");
  		return -ENOMEM;
  	}
b8313b6da   Jonathan Brassow   dm log: remove in...
130
131
132
  	str_size = sprintf(str, "%llu", (unsigned long long)ti->len);
  	for (i = 0; i < argc; i++)
  		str_size += sprintf(str + str_size, " %s", argv[i]);
f5db4af46   Jonthan Brassow   dm raid1: add use...
133
134
135
136
137
138
139
140
141
142
143
144
  
  	*ctr_str = str;
  	return str_size;
  }
  
  /*
   * userspace_ctr
   *
   * argv contains:
   *	<UUID> <other args>
   * Where 'other args' is the userspace implementation specific log
   * arguments.  An example might be:
b89544575   Jonathan Brassow   dm log userspace:...
145
   *	<UUID> clustered-disk <arg count> <log dev> <region_size> [[no]sync]
f5db4af46   Jonthan Brassow   dm raid1: add use...
146
147
148
149
150
151
152
153
154
155
156
157
158
159
   *
   * So, this module will strip off the <UUID> for identification purposes
   * when communicating with userspace about a log; but will pass on everything
   * else.
   */
  static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
  			 unsigned argc, char **argv)
  {
  	int r = 0;
  	int str_size;
  	char *ctr_str = NULL;
  	struct log_c *lc = NULL;
  	uint64_t rdata;
  	size_t rdata_size = sizeof(rdata);
5a25f0eb7   Jonathan E Brassow   dm log userspace:...
160
161
  	char *devices_rdata = NULL;
  	size_t devices_rdata_size = DM_NAME_LEN;
f5db4af46   Jonthan Brassow   dm raid1: add use...
162
163
164
165
166
  
  	if (argc < 3) {
  		DMWARN("Too few arguments to userspace dirty log");
  		return -EINVAL;
  	}
5a25f0eb7   Jonathan E Brassow   dm log userspace:...
167
  	lc = kzalloc(sizeof(*lc), GFP_KERNEL);
f5db4af46   Jonthan Brassow   dm raid1: add use...
168
169
170
171
  	if (!lc) {
  		DMWARN("Unable to allocate userspace log context.");
  		return -ENOMEM;
  	}
7ec23d509   Jonathan Brassow   dm log: userspace...
172
  	/* The ptr value is sufficient for local unique id */
bca915aae   Andrew Morton   dm log: userspace...
173
  	lc->luid = (unsigned long)lc;
7ec23d509   Jonathan Brassow   dm log: userspace...
174

f5db4af46   Jonthan Brassow   dm raid1: add use...
175
176
177
178
179
180
181
182
183
184
  	lc->ti = ti;
  
  	if (strlen(argv[0]) > (DM_UUID_LEN - 1)) {
  		DMWARN("UUID argument too long.");
  		kfree(lc);
  		return -EINVAL;
  	}
  
  	strncpy(lc->uuid, argv[0], DM_UUID_LEN);
  	spin_lock_init(&lc->flush_lock);
909cc4fb4   Jonathan Brassow   dm log userspace:...
185
186
  	INIT_LIST_HEAD(&lc->mark_list);
  	INIT_LIST_HEAD(&lc->clear_list);
f5db4af46   Jonthan Brassow   dm raid1: add use...
187
188
189
190
191
192
  
  	str_size = build_constructor_string(ti, argc - 1, argv + 1, &ctr_str);
  	if (str_size < 0) {
  		kfree(lc);
  		return str_size;
  	}
5a25f0eb7   Jonathan E Brassow   dm log userspace:...
193
194
195
196
197
198
199
200
201
202
  	devices_rdata = kzalloc(devices_rdata_size, GFP_KERNEL);
  	if (!devices_rdata) {
  		DMERR("Failed to allocate memory for device information");
  		r = -ENOMEM;
  		goto out;
  	}
  
  	/*
  	 * Send table string and get back any opened device.
  	 */
7ec23d509   Jonathan Brassow   dm log: userspace...
203
  	r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_CTR,
5a25f0eb7   Jonathan E Brassow   dm log userspace:...
204
205
  				 ctr_str, str_size,
  				 devices_rdata, &devices_rdata_size);
f5db4af46   Jonthan Brassow   dm raid1: add use...
206

4a038677d   Jonathan Brassow   dm log userspace:...
207
208
209
210
211
  	if (r < 0) {
  		if (r == -ESRCH)
  			DMERR("Userspace log server not found");
  		else
  			DMERR("Userspace log server failed to create log");
f5db4af46   Jonthan Brassow   dm raid1: add use...
212
213
214
215
216
  		goto out;
  	}
  
  	/* Since the region size does not change, get it now */
  	rdata_size = sizeof(rdata);
7ec23d509   Jonathan Brassow   dm log: userspace...
217
  	r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_GET_REGION_SIZE,
f5db4af46   Jonthan Brassow   dm raid1: add use...
218
219
220
221
222
223
224
225
226
  				 NULL, 0, (char *)&rdata, &rdata_size);
  
  	if (r) {
  		DMERR("Failed to get region size of dirty log");
  		goto out;
  	}
  
  	lc->region_size = (uint32_t)rdata;
  	lc->region_count = dm_sector_div_up(ti->len, lc->region_size);
5a25f0eb7   Jonathan E Brassow   dm log userspace:...
227
228
229
230
231
232
233
234
235
236
237
238
  	if (devices_rdata_size) {
  		if (devices_rdata[devices_rdata_size - 1] != '\0') {
  			DMERR("DM_ULOG_CTR device return string not properly terminated");
  			r = -EINVAL;
  			goto out;
  		}
  		r = dm_get_device(ti, devices_rdata,
  				  dm_table_get_mode(ti->table), &lc->log_dev);
  		if (r)
  			DMERR("Failed to register %s with device-mapper",
  			      devices_rdata);
  	}
f5db4af46   Jonthan Brassow   dm raid1: add use...
239
  out:
5a25f0eb7   Jonathan E Brassow   dm log userspace:...
240
  	kfree(devices_rdata);
f5db4af46   Jonthan Brassow   dm raid1: add use...
241
242
243
244
245
246
247
248
249
250
251
252
253
254
  	if (r) {
  		kfree(lc);
  		kfree(ctr_str);
  	} else {
  		lc->usr_argv_str = ctr_str;
  		lc->usr_argc = argc;
  		log->context = lc;
  	}
  
  	return r;
  }
  
  static void userspace_dtr(struct dm_dirty_log *log)
  {
f5db4af46   Jonthan Brassow   dm raid1: add use...
255
  	struct log_c *lc = log->context;
4a038677d   Jonathan Brassow   dm log userspace:...
256
  	(void) dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_DTR,
f5db4af46   Jonthan Brassow   dm raid1: add use...
257
258
  				 NULL, 0,
  				 NULL, NULL);
5a25f0eb7   Jonathan E Brassow   dm log userspace:...
259
260
  	if (lc->log_dev)
  		dm_put_device(lc->ti, lc->log_dev);
f5db4af46   Jonthan Brassow   dm raid1: add use...
261
262
263
264
265
266
267
268
269
270
  	kfree(lc->usr_argv_str);
  	kfree(lc);
  
  	return;
  }
  
  static int userspace_presuspend(struct dm_dirty_log *log)
  {
  	int r;
  	struct log_c *lc = log->context;
7ec23d509   Jonathan Brassow   dm log: userspace...
271
  	r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_PRESUSPEND,
f5db4af46   Jonthan Brassow   dm raid1: add use...
272
273
274
275
276
277
278
279
280
281
  				 NULL, 0,
  				 NULL, NULL);
  
  	return r;
  }
  
  static int userspace_postsuspend(struct dm_dirty_log *log)
  {
  	int r;
  	struct log_c *lc = log->context;
7ec23d509   Jonathan Brassow   dm log: userspace...
282
  	r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_POSTSUSPEND,
f5db4af46   Jonthan Brassow   dm raid1: add use...
283
284
285
286
287
288
289
290
291
292
293
294
  				 NULL, 0,
  				 NULL, NULL);
  
  	return r;
  }
  
  static int userspace_resume(struct dm_dirty_log *log)
  {
  	int r;
  	struct log_c *lc = log->context;
  
  	lc->in_sync_hint = 0;
7ec23d509   Jonathan Brassow   dm log: userspace...
295
  	r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_RESUME,
f5db4af46   Jonthan Brassow   dm raid1: add use...
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
  				 NULL, 0,
  				 NULL, NULL);
  
  	return r;
  }
  
  static uint32_t userspace_get_region_size(struct dm_dirty_log *log)
  {
  	struct log_c *lc = log->context;
  
  	return lc->region_size;
  }
  
  /*
   * userspace_is_clean
   *
   * Check whether a region is clean.  If there is any sort of
   * failure when consulting the server, we return not clean.
   *
   * Returns: 1 if clean, 0 otherwise
   */
  static int userspace_is_clean(struct dm_dirty_log *log, region_t region)
  {
  	int r;
  	uint64_t region64 = (uint64_t)region;
  	int64_t is_clean;
  	size_t rdata_size;
  	struct log_c *lc = log->context;
  
  	rdata_size = sizeof(is_clean);
  	r = userspace_do_request(lc, lc->uuid, DM_ULOG_IS_CLEAN,
  				 (char *)&region64, sizeof(region64),
  				 (char *)&is_clean, &rdata_size);
  
  	return (r) ? 0 : (int)is_clean;
  }
  
  /*
   * userspace_in_sync
   *
   * Check if the region is in-sync.  If there is any sort
   * of failure when consulting the server, we assume that
   * the region is not in sync.
   *
   * If 'can_block' is set, return immediately
   *
   * Returns: 1 if in-sync, 0 if not-in-sync, -EWOULDBLOCK
   */
  static int userspace_in_sync(struct dm_dirty_log *log, region_t region,
  			     int can_block)
  {
  	int r;
  	uint64_t region64 = region;
  	int64_t in_sync;
  	size_t rdata_size;
  	struct log_c *lc = log->context;
  
  	/*
  	 * We can never respond directly - even if in_sync_hint is
  	 * set.  This is because another machine could see a device
  	 * failure and mark the region out-of-sync.  If we don't go
  	 * to userspace to ask, we might think the region is in-sync
  	 * and allow a read to pick up data that is stale.  (This is
  	 * very unlikely if a device actually fails; but it is very
  	 * likely if a connection to one device from one machine fails.)
  	 *
  	 * There still might be a problem if the mirror caches the region
  	 * state as in-sync... but then this call would not be made.  So,
  	 * that is a mirror problem.
  	 */
  	if (!can_block)
  		return -EWOULDBLOCK;
  
  	rdata_size = sizeof(in_sync);
  	r = userspace_do_request(lc, lc->uuid, DM_ULOG_IN_SYNC,
  				 (char *)&region64, sizeof(region64),
  				 (char *)&in_sync, &rdata_size);
  	return (r) ? 0 : (int)in_sync;
  }
085ae0651   Jonathan Brassow   dm log userspace:...
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
  static int flush_one_by_one(struct log_c *lc, struct list_head *flush_list)
  {
  	int r = 0;
  	struct flush_entry *fe;
  
  	list_for_each_entry(fe, flush_list, list) {
  		r = userspace_do_request(lc, lc->uuid, fe->type,
  					 (char *)&fe->region,
  					 sizeof(fe->region),
  					 NULL, NULL);
  		if (r)
  			break;
  	}
  
  	return r;
  }
  
  static int flush_by_group(struct log_c *lc, struct list_head *flush_list)
  {
  	int r = 0;
  	int count;
  	uint32_t type = 0;
  	struct flush_entry *fe, *tmp_fe;
  	LIST_HEAD(tmp_list);
  	uint64_t group[MAX_FLUSH_GROUP_COUNT];
  
  	/*
  	 * Group process the requests
  	 */
  	while (!list_empty(flush_list)) {
  		count = 0;
  
  		list_for_each_entry_safe(fe, tmp_fe, flush_list, list) {
  			group[count] = fe->region;
  			count++;
6c9b27ab0   Kirill A. Shutemov   dm log: userspace...
410
  			list_move(&fe->list, &tmp_list);
085ae0651   Jonathan Brassow   dm log userspace:...
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
  
  			type = fe->type;
  			if (count >= MAX_FLUSH_GROUP_COUNT)
  				break;
  		}
  
  		r = userspace_do_request(lc, lc->uuid, type,
  					 (char *)(group),
  					 count * sizeof(uint64_t),
  					 NULL, NULL);
  		if (r) {
  			/* Group send failed.  Attempt one-by-one. */
  			list_splice_init(&tmp_list, flush_list);
  			r = flush_one_by_one(lc, flush_list);
  			break;
  		}
  	}
  
  	/*
  	 * Must collect flush_entrys that were successfully processed
  	 * as a group so that they will be free'd by the caller.
  	 */
  	list_splice_init(&tmp_list, flush_list);
  
  	return r;
  }
f5db4af46   Jonthan Brassow   dm raid1: add use...
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
  /*
   * userspace_flush
   *
   * This function is ok to block.
   * The flush happens in two stages.  First, it sends all
   * clear/mark requests that are on the list.  Then it
   * tells the server to commit them.  This gives the
   * server a chance to optimise the commit, instead of
   * doing it for every request.
   *
   * Additionally, we could implement another thread that
   * sends the requests up to the server - reducing the
   * load on flush.  Then the flush would have less in
   * the list and be responsible for the finishing commit.
   *
   * Returns: 0 on success, < 0 on failure
   */
  static int userspace_flush(struct dm_dirty_log *log)
  {
  	int r = 0;
  	unsigned long flags;
  	struct log_c *lc = log->context;
909cc4fb4   Jonathan Brassow   dm log userspace:...
459
460
  	LIST_HEAD(mark_list);
  	LIST_HEAD(clear_list);
f5db4af46   Jonthan Brassow   dm raid1: add use...
461
462
463
  	struct flush_entry *fe, *tmp_fe;
  
  	spin_lock_irqsave(&lc->flush_lock, flags);
909cc4fb4   Jonathan Brassow   dm log userspace:...
464
465
  	list_splice_init(&lc->mark_list, &mark_list);
  	list_splice_init(&lc->clear_list, &clear_list);
f5db4af46   Jonthan Brassow   dm raid1: add use...
466
  	spin_unlock_irqrestore(&lc->flush_lock, flags);
909cc4fb4   Jonathan Brassow   dm log userspace:...
467
  	if (list_empty(&mark_list) && list_empty(&clear_list))
f5db4af46   Jonthan Brassow   dm raid1: add use...
468
  		return 0;
085ae0651   Jonathan Brassow   dm log userspace:...
469
470
471
  	r = flush_by_group(lc, &mark_list);
  	if (r)
  		goto fail;
909cc4fb4   Jonathan Brassow   dm log userspace:...
472

085ae0651   Jonathan Brassow   dm log userspace:...
473
474
475
  	r = flush_by_group(lc, &clear_list);
  	if (r)
  		goto fail;
f5db4af46   Jonthan Brassow   dm raid1: add use...
476
477
478
479
480
481
482
483
484
485
  
  	r = userspace_do_request(lc, lc->uuid, DM_ULOG_FLUSH,
  				 NULL, 0, NULL, NULL);
  
  fail:
  	/*
  	 * We can safely remove these entries, even if failure.
  	 * Calling code will receive an error and will know that
  	 * the log facility has failed.
  	 */
909cc4fb4   Jonathan Brassow   dm log userspace:...
486
487
488
489
490
  	list_for_each_entry_safe(fe, tmp_fe, &mark_list, list) {
  		list_del(&fe->list);
  		mempool_free(fe, flush_entry_pool);
  	}
  	list_for_each_entry_safe(fe, tmp_fe, &clear_list, list) {
f5db4af46   Jonthan Brassow   dm raid1: add use...
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
  		list_del(&fe->list);
  		mempool_free(fe, flush_entry_pool);
  	}
  
  	if (r)
  		dm_table_event(lc->ti->table);
  
  	return r;
  }
  
  /*
   * userspace_mark_region
   *
   * This function should avoid blocking unless absolutely required.
   * (Memory allocation is valid for blocking.)
   */
  static void userspace_mark_region(struct dm_dirty_log *log, region_t region)
  {
  	unsigned long flags;
  	struct log_c *lc = log->context;
  	struct flush_entry *fe;
  
  	/* Wait for an allocation, but _never_ fail */
  	fe = mempool_alloc(flush_entry_pool, GFP_NOIO);
  	BUG_ON(!fe);
  
  	spin_lock_irqsave(&lc->flush_lock, flags);
  	fe->type = DM_ULOG_MARK_REGION;
  	fe->region = region;
909cc4fb4   Jonathan Brassow   dm log userspace:...
520
  	list_add(&fe->list, &lc->mark_list);
f5db4af46   Jonthan Brassow   dm raid1: add use...
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
  	spin_unlock_irqrestore(&lc->flush_lock, flags);
  
  	return;
  }
  
  /*
   * userspace_clear_region
   *
   * This function must not block.
   * So, the alloc can't block.  In the worst case, it is ok to
   * fail.  It would simply mean we can't clear the region.
   * Does nothing to current sync context, but does mean
   * the region will be re-sync'ed on a reload of the mirror
   * even though it is in-sync.
   */
  static void userspace_clear_region(struct dm_dirty_log *log, region_t region)
  {
  	unsigned long flags;
  	struct log_c *lc = log->context;
  	struct flush_entry *fe;
  
  	/*
  	 * If we fail to allocate, we skip the clearing of
  	 * the region.  This doesn't hurt us in any way, except
  	 * to cause the region to be resync'ed when the
  	 * device is activated next time.
  	 */
  	fe = mempool_alloc(flush_entry_pool, GFP_ATOMIC);
  	if (!fe) {
  		DMERR("Failed to allocate memory to clear region.");
  		return;
  	}
  
  	spin_lock_irqsave(&lc->flush_lock, flags);
  	fe->type = DM_ULOG_CLEAR_REGION;
  	fe->region = region;
909cc4fb4   Jonathan Brassow   dm log userspace:...
557
  	list_add(&fe->list, &lc->clear_list);
f5db4af46   Jonthan Brassow   dm raid1: add use...
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
  	spin_unlock_irqrestore(&lc->flush_lock, flags);
  
  	return;
  }
  
  /*
   * userspace_get_resync_work
   *
   * Get a region that needs recovery.  It is valid to return
   * an error for this function.
   *
   * Returns: 1 if region filled, 0 if no work, <0 on error
   */
  static int userspace_get_resync_work(struct dm_dirty_log *log, region_t *region)
  {
  	int r;
  	size_t rdata_size;
  	struct log_c *lc = log->context;
  	struct {
  		int64_t i; /* 64-bit for mix arch compatibility */
  		region_t r;
  	} pkg;
  
  	if (lc->in_sync_hint >= lc->region_count)
  		return 0;
  
  	rdata_size = sizeof(pkg);
  	r = userspace_do_request(lc, lc->uuid, DM_ULOG_GET_RESYNC_WORK,
  				 NULL, 0,
  				 (char *)&pkg, &rdata_size);
  
  	*region = pkg.r;
  	return (r) ? r : (int)pkg.i;
  }
  
  /*
   * userspace_set_region_sync
   *
   * Set the sync status of a given region.  This function
   * must not fail.
   */
  static void userspace_set_region_sync(struct dm_dirty_log *log,
  				      region_t region, int in_sync)
  {
  	int r;
  	struct log_c *lc = log->context;
  	struct {
  		region_t r;
  		int64_t i;
  	} pkg;
  
  	pkg.r = region;
  	pkg.i = (int64_t)in_sync;
  
  	r = userspace_do_request(lc, lc->uuid, DM_ULOG_SET_REGION_SYNC,
  				 (char *)&pkg, sizeof(pkg),
  				 NULL, NULL);
  
  	/*
  	 * It would be nice to be able to report failures.
  	 * However, it is easy emough to detect and resolve.
  	 */
  	return;
  }
  
  /*
   * userspace_get_sync_count
   *
   * If there is any sort of failure when consulting the server,
   * we assume that the sync count is zero.
   *
   * Returns: sync count on success, 0 on failure
   */
  static region_t userspace_get_sync_count(struct dm_dirty_log *log)
  {
  	int r;
  	size_t rdata_size;
  	uint64_t sync_count;
  	struct log_c *lc = log->context;
  
  	rdata_size = sizeof(sync_count);
  	r = userspace_do_request(lc, lc->uuid, DM_ULOG_GET_SYNC_COUNT,
  				 NULL, 0,
  				 (char *)&sync_count, &rdata_size);
  
  	if (r)
  		return 0;
  
  	if (sync_count >= lc->region_count)
  		lc->in_sync_hint = lc->region_count;
  
  	return (region_t)sync_count;
  }
  
  /*
   * userspace_status
   *
   * Returns: amount of space consumed
   */
  static int userspace_status(struct dm_dirty_log *log, status_type_t status_type,
  			    char *result, unsigned maxlen)
  {
  	int r = 0;
b8313b6da   Jonathan Brassow   dm log: remove in...
661
  	char *table_args;
f5db4af46   Jonthan Brassow   dm raid1: add use...
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
  	size_t sz = (size_t)maxlen;
  	struct log_c *lc = log->context;
  
  	switch (status_type) {
  	case STATUSTYPE_INFO:
  		r = userspace_do_request(lc, lc->uuid, DM_ULOG_STATUS_INFO,
  					 NULL, 0,
  					 result, &sz);
  
  		if (r) {
  			sz = 0;
  			DMEMIT("%s 1 COM_FAILURE", log->type->name);
  		}
  		break;
  	case STATUSTYPE_TABLE:
  		sz = 0;
0d03d59d9   Geert Uytterhoeven   md: Fix "strchr" ...
678
  		table_args = strchr(lc->usr_argv_str, ' ');
b8313b6da   Jonathan Brassow   dm log: remove in...
679
680
681
682
683
  		BUG_ON(!table_args); /* There will always be a ' ' */
  		table_args++;
  
  		DMEMIT("%s %u %s %s ", log->type->name, lc->usr_argc,
  		       lc->uuid, table_args);
f5db4af46   Jonthan Brassow   dm raid1: add use...
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
  		break;
  	}
  	return (r) ? 0 : (int)sz;
  }
  
  /*
   * userspace_is_remote_recovering
   *
   * Returns: 1 if region recovering, 0 otherwise
   */
  static int userspace_is_remote_recovering(struct dm_dirty_log *log,
  					  region_t region)
  {
  	int r;
  	uint64_t region64 = region;
  	struct log_c *lc = log->context;
  	static unsigned long long limit;
  	struct {
  		int64_t is_recovering;
  		uint64_t in_sync_hint;
  	} pkg;
  	size_t rdata_size = sizeof(pkg);
  
  	/*
  	 * Once the mirror has been reported to be in-sync,
  	 * it will never again ask for recovery work.  So,
  	 * we can safely say there is not a remote machine
  	 * recovering if the device is in-sync.  (in_sync_hint
  	 * must be reset at resume time.)
  	 */
  	if (region < lc->in_sync_hint)
  		return 0;
  	else if (jiffies < limit)
  		return 1;
  
  	limit = jiffies + (HZ / 4);
  	r = userspace_do_request(lc, lc->uuid, DM_ULOG_IS_REMOTE_RECOVERING,
  				 (char *)&region64, sizeof(region64),
  				 (char *)&pkg, &rdata_size);
  	if (r)
  		return 1;
  
  	lc->in_sync_hint = pkg.in_sync_hint;
  
  	return (int)pkg.is_recovering;
  }
  
  static struct dm_dirty_log_type _userspace_type = {
  	.name = "userspace",
  	.module = THIS_MODULE,
  	.ctr = userspace_ctr,
  	.dtr = userspace_dtr,
  	.presuspend = userspace_presuspend,
  	.postsuspend = userspace_postsuspend,
  	.resume = userspace_resume,
  	.get_region_size = userspace_get_region_size,
  	.is_clean = userspace_is_clean,
  	.in_sync = userspace_in_sync,
  	.flush = userspace_flush,
  	.mark_region = userspace_mark_region,
  	.clear_region = userspace_clear_region,
  	.get_resync_work = userspace_get_resync_work,
  	.set_region_sync = userspace_set_region_sync,
  	.get_sync_count = userspace_get_sync_count,
  	.status = userspace_status,
  	.is_remote_recovering = userspace_is_remote_recovering,
  };
  
  static int __init userspace_dirty_log_init(void)
  {
  	int r = 0;
  
  	flush_entry_pool = mempool_create(100, flush_entry_alloc,
  					  flush_entry_free, NULL);
  
  	if (!flush_entry_pool) {
  		DMWARN("Unable to create flush_entry_pool:  No memory.");
  		return -ENOMEM;
  	}
  
  	r = dm_ulog_tfr_init();
  	if (r) {
  		DMWARN("Unable to initialize userspace log communications");
  		mempool_destroy(flush_entry_pool);
  		return r;
  	}
  
  	r = dm_dirty_log_type_register(&_userspace_type);
  	if (r) {
  		DMWARN("Couldn't register userspace dirty log type");
  		dm_ulog_tfr_exit();
  		mempool_destroy(flush_entry_pool);
  		return r;
  	}
86a54a480   Jonathan Brassow   dm log userspace:...
778
  	DMINFO("version " DM_LOG_USERSPACE_VSN " loaded");
f5db4af46   Jonthan Brassow   dm raid1: add use...
779
780
781
782
783
784
785
786
  	return 0;
  }
  
  static void __exit userspace_dirty_log_exit(void)
  {
  	dm_dirty_log_type_unregister(&_userspace_type);
  	dm_ulog_tfr_exit();
  	mempool_destroy(flush_entry_pool);
86a54a480   Jonathan Brassow   dm log userspace:...
787
  	DMINFO("version " DM_LOG_USERSPACE_VSN " unloaded");
f5db4af46   Jonthan Brassow   dm raid1: add use...
788
789
790
791
792
793
794
795
796
  	return;
  }
  
  module_init(userspace_dirty_log_init);
  module_exit(userspace_dirty_log_exit);
  
  MODULE_DESCRIPTION(DM_NAME " userspace dirty log link");
  MODULE_AUTHOR("Jonathan Brassow <dm-devel@redhat.com>");
  MODULE_LICENSE("GPL");