Training courses

Kernel and Embedded Linux

Bootlin training courses

Embedded Linux, kernel,
Yocto Project, Buildroot, real-time,
graphics, boot time, debugging...

Bootlin logo

Elixir Cross Referencer

  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
/*
 * CDDL HEADER START
 *
 * The contents of this file are subject to the terms of the
 * Common Development and Distribution License (the "License").
 * You may not use this file except in compliance with the License.
 *
 * You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
 * or http://www.opensolaris.org/os/licensing.
 * See the License for the specific language governing permissions
 * and limitations under the License.
 *
 * When distributing Covered Code, include this CDDL HEADER in each
 * file and include the License file at usr/src/OPENSOLARIS.LICENSE.
 * If applicable, add the following below this CDDL HEADER, with the
 * fields enclosed by brackets "[]" replaced with your own identifying
 * information: Portions Copyright [yyyy] [name of copyright owner]
 *
 * CDDL HEADER END
 */
/*
 * Copyright 2015 Nexenta Systems, Inc. All rights reserved.
 * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
 * Copyright (c) 2012, 2018 by Delphix. All rights reserved.
 * Copyright 2015 RackTop Systems.
 * Copyright (c) 2016, Intel Corporation.
 */

#include <errno.h>
#include <libintl.h>
#include <libgen.h>
#include <stddef.h>
#include <stdlib.h>
#include <string.h>
#include <sys/stat.h>
#include <unistd.h>
#include <sys/vdev_impl.h>
#include <libzfs.h>
#include <libzfs_impl.h>
#include <libzutil.h>
#include <sys/arc_impl.h>

/*
 * Returns true if the named pool matches the given GUID.
 */
static int
pool_active(libzfs_handle_t *hdl, const char *name, uint64_t guid,
    boolean_t *isactive)
{
	zpool_handle_t *zhp;
	uint64_t theguid;

	if (zpool_open_silent(hdl, name, &zhp) != 0)
		return (-1);

	if (zhp == NULL) {
		*isactive = B_FALSE;
		return (0);
	}

	verify(nvlist_lookup_uint64(zhp->zpool_config, ZPOOL_CONFIG_POOL_GUID,
	    &theguid) == 0);

	zpool_close(zhp);

	*isactive = (theguid == guid);
	return (0);
}

static nvlist_t *
refresh_config(libzfs_handle_t *hdl, nvlist_t *config)
{
	nvlist_t *nvl;
	zfs_cmd_t zc = {"\0"};
	int err, dstbuf_size;

	if (zcmd_write_conf_nvlist(hdl, &zc, config) != 0)
		return (NULL);

	dstbuf_size = MAX(CONFIG_BUF_MINSIZE, zc.zc_nvlist_conf_size * 4);

	if (zcmd_alloc_dst_nvlist(hdl, &zc, dstbuf_size) != 0) {
		zcmd_free_nvlists(&zc);
		return (NULL);
	}

	while ((err = zfs_ioctl(hdl, ZFS_IOC_POOL_TRYIMPORT,
	    &zc)) != 0 && errno == ENOMEM) {
		if (zcmd_expand_dst_nvlist(hdl, &zc) != 0) {
			zcmd_free_nvlists(&zc);
			return (NULL);
		}
	}

	if (err) {
		zcmd_free_nvlists(&zc);
		return (NULL);
	}

	if (zcmd_read_dst_nvlist(hdl, &zc, &nvl) != 0) {
		zcmd_free_nvlists(&zc);
		return (NULL);
	}

	zcmd_free_nvlists(&zc);
	return (nvl);
}

static nvlist_t *
refresh_config_libzfs(void *handle, nvlist_t *tryconfig)
{
	return (refresh_config((libzfs_handle_t *)handle, tryconfig));
}


static int
pool_active_libzfs(void *handle, const char *name, uint64_t guid,
    boolean_t *isactive)
{
	return (pool_active((libzfs_handle_t *)handle, name, guid, isactive));
}

const pool_config_ops_t libzfs_config_ops = {
	.pco_refresh_config = refresh_config_libzfs,
	.pco_pool_active = pool_active_libzfs,
};

/*
 * Return the offset of the given label.
 */
static uint64_t
label_offset(uint64_t size, int l)
{
	ASSERT(P2PHASE_TYPED(size, sizeof (vdev_label_t), uint64_t) == 0);
	return (l * sizeof (vdev_label_t) + (l < VDEV_LABELS / 2 ?
	    0 : size - VDEV_LABELS * sizeof (vdev_label_t)));
}

/*
 * Given a file descriptor, clear (zero) the label information.  This function
 * is used in the appliance stack as part of the ZFS sysevent module and
 * to implement the "zpool labelclear" command.
 */
int
zpool_clear_label(int fd)
{
	struct stat64 statbuf;
	int l;
	vdev_label_t *label;
	l2arc_dev_hdr_phys_t *l2dhdr;
	uint64_t size;
	int labels_cleared = 0, header_cleared = 0;
	boolean_t clear_l2arc_header = B_FALSE;

	if (fstat64_blk(fd, &statbuf) == -1)
		return (0);

	size = P2ALIGN_TYPED(statbuf.st_size, sizeof (vdev_label_t), uint64_t);

	if ((label = calloc(1, sizeof (vdev_label_t))) == NULL)
		return (-1);

	if ((l2dhdr = calloc(1, sizeof (l2arc_dev_hdr_phys_t))) == NULL) {
		free(label);
		return (-1);
	}

	for (l = 0; l < VDEV_LABELS; l++) {
		uint64_t state, guid, l2cache;
		nvlist_t *config;

		if (pread64(fd, label, sizeof (vdev_label_t),
		    label_offset(size, l)) != sizeof (vdev_label_t)) {
			continue;
		}

		if (nvlist_unpack(label->vl_vdev_phys.vp_nvlist,
		    sizeof (label->vl_vdev_phys.vp_nvlist), &config, 0) != 0) {
			continue;
		}

		/* Skip labels which do not have a valid guid. */
		if (nvlist_lookup_uint64(config, ZPOOL_CONFIG_GUID,
		    &guid) != 0 || guid == 0) {
			nvlist_free(config);
			continue;
		}

		/* Skip labels which are not in a known valid state. */
		if (nvlist_lookup_uint64(config, ZPOOL_CONFIG_POOL_STATE,
		    &state) != 0 || state > POOL_STATE_L2CACHE) {
			nvlist_free(config);
			continue;
		}

		/* If the device is a cache device clear the header. */
		if (!clear_l2arc_header) {
			if (nvlist_lookup_uint64(config,
			    ZPOOL_CONFIG_POOL_STATE, &l2cache) == 0 &&
			    l2cache == POOL_STATE_L2CACHE) {
				clear_l2arc_header = B_TRUE;
			}
		}

		nvlist_free(config);

		/*
		 * A valid label was found, overwrite this label's nvlist
		 * and uberblocks with zeros on disk.  This is done to prevent
		 * system utilities, like blkid, from incorrectly detecting a
		 * partial label.  The leading pad space is left untouched.
		 */
		memset(label, 0, sizeof (vdev_label_t));
		size_t label_size = sizeof (vdev_label_t) - (2 * VDEV_PAD_SIZE);

		if (pwrite64(fd, label, label_size, label_offset(size, l) +
		    (2 * VDEV_PAD_SIZE)) == label_size) {
			labels_cleared++;
		}
	}

	/* Clear the L2ARC header. */
	if (clear_l2arc_header) {
		memset(l2dhdr, 0, sizeof (l2arc_dev_hdr_phys_t));
		if (pwrite64(fd, l2dhdr, sizeof (l2arc_dev_hdr_phys_t),
		    VDEV_LABEL_START_SIZE) == sizeof (l2arc_dev_hdr_phys_t)) {
			header_cleared++;
		}
	}

	free(label);
	free(l2dhdr);

	if (labels_cleared == 0)
		return (-1);

	return (0);
}

static boolean_t
find_guid(nvlist_t *nv, uint64_t guid)
{
	uint64_t tmp;
	nvlist_t **child;
	uint_t c, children;

	verify(nvlist_lookup_uint64(nv, ZPOOL_CONFIG_GUID, &tmp) == 0);
	if (tmp == guid)
		return (B_TRUE);

	if (nvlist_lookup_nvlist_array(nv, ZPOOL_CONFIG_CHILDREN,
	    &child, &children) == 0) {
		for (c = 0; c < children; c++)
			if (find_guid(child[c], guid))
				return (B_TRUE);
	}

	return (B_FALSE);
}

typedef struct aux_cbdata {
	const char	*cb_type;
	uint64_t	cb_guid;
	zpool_handle_t	*cb_zhp;
} aux_cbdata_t;

static int
find_aux(zpool_handle_t *zhp, void *data)
{
	aux_cbdata_t *cbp = data;
	nvlist_t **list;
	uint_t i, count;
	uint64_t guid;
	nvlist_t *nvroot;

	verify(nvlist_lookup_nvlist(zhp->zpool_config, ZPOOL_CONFIG_VDEV_TREE,
	    &nvroot) == 0);

	if (nvlist_lookup_nvlist_array(nvroot, cbp->cb_type,
	    &list, &count) == 0) {
		for (i = 0; i < count; i++) {
			verify(nvlist_lookup_uint64(list[i],
			    ZPOOL_CONFIG_GUID, &guid) == 0);
			if (guid == cbp->cb_guid) {
				cbp->cb_zhp = zhp;
				return (1);
			}
		}
	}

	zpool_close(zhp);
	return (0);
}

/*
 * Determines if the pool is in use.  If so, it returns true and the state of
 * the pool as well as the name of the pool.  Name string is allocated and
 * must be freed by the caller.
 */
int
zpool_in_use(libzfs_handle_t *hdl, int fd, pool_state_t *state, char **namestr,
    boolean_t *inuse)
{
	nvlist_t *config;
	char *name;
	boolean_t ret;
	uint64_t guid, vdev_guid;
	zpool_handle_t *zhp;
	nvlist_t *pool_config;
	uint64_t stateval, isspare;
	aux_cbdata_t cb = { 0 };
	boolean_t isactive;

	*inuse = B_FALSE;

	if (zpool_read_label(fd, &config, NULL) != 0) {
		(void) no_memory(hdl);
		return (-1);
	}

	if (config == NULL)
		return (0);

	verify(nvlist_lookup_uint64(config, ZPOOL_CONFIG_POOL_STATE,
	    &stateval) == 0);
	verify(nvlist_lookup_uint64(config, ZPOOL_CONFIG_GUID,
	    &vdev_guid) == 0);

	if (stateval != POOL_STATE_SPARE && stateval != POOL_STATE_L2CACHE) {
		verify(nvlist_lookup_string(config, ZPOOL_CONFIG_POOL_NAME,
		    &name) == 0);
		verify(nvlist_lookup_uint64(config, ZPOOL_CONFIG_POOL_GUID,
		    &guid) == 0);
	}

	switch (stateval) {
	case POOL_STATE_EXPORTED:
		/*
		 * A pool with an exported state may in fact be imported
		 * read-only, so check the in-core state to see if it's
		 * active and imported read-only.  If it is, set
		 * its state to active.
		 */
		if (pool_active(hdl, name, guid, &isactive) == 0 && isactive &&
		    (zhp = zpool_open_canfail(hdl, name)) != NULL) {
			if (zpool_get_prop_int(zhp, ZPOOL_PROP_READONLY, NULL))
				stateval = POOL_STATE_ACTIVE;

			/*
			 * All we needed the zpool handle for is the
			 * readonly prop check.
			 */
			zpool_close(zhp);
		}

		ret = B_TRUE;
		break;

	case POOL_STATE_ACTIVE:
		/*
		 * For an active pool, we have to determine if it's really part
		 * of a currently active pool (in which case the pool will exist
		 * and the guid will be the same), or whether it's part of an
		 * active pool that was disconnected without being explicitly
		 * exported.
		 */
		if (pool_active(hdl, name, guid, &isactive) != 0) {
			nvlist_free(config);
			return (-1);
		}

		if (isactive) {
			/*
			 * Because the device may have been removed while
			 * offlined, we only report it as active if the vdev is
			 * still present in the config.  Otherwise, pretend like
			 * it's not in use.
			 */
			if ((zhp = zpool_open_canfail(hdl, name)) != NULL &&
			    (pool_config = zpool_get_config(zhp, NULL))
			    != NULL) {
				nvlist_t *nvroot;

				verify(nvlist_lookup_nvlist(pool_config,
				    ZPOOL_CONFIG_VDEV_TREE, &nvroot) == 0);
				ret = find_guid(nvroot, vdev_guid);
			} else {
				ret = B_FALSE;
			}

			/*
			 * If this is an active spare within another pool, we
			 * treat it like an unused hot spare.  This allows the
			 * user to create a pool with a hot spare that currently
			 * in use within another pool.  Since we return B_TRUE,
			 * libdiskmgt will continue to prevent generic consumers
			 * from using the device.
			 */
			if (ret && nvlist_lookup_uint64(config,
			    ZPOOL_CONFIG_IS_SPARE, &isspare) == 0 && isspare)
				stateval = POOL_STATE_SPARE;

			if (zhp != NULL)
				zpool_close(zhp);
		} else {
			stateval = POOL_STATE_POTENTIALLY_ACTIVE;
			ret = B_TRUE;
		}
		break;

	case POOL_STATE_SPARE:
		/*
		 * For a hot spare, it can be either definitively in use, or
		 * potentially active.  To determine if it's in use, we iterate
		 * over all pools in the system and search for one with a spare
		 * with a matching guid.
		 *
		 * Due to the shared nature of spares, we don't actually report
		 * the potentially active case as in use.  This means the user
		 * can freely create pools on the hot spares of exported pools,
		 * but to do otherwise makes the resulting code complicated, and
		 * we end up having to deal with this case anyway.
		 */
		cb.cb_zhp = NULL;
		cb.cb_guid = vdev_guid;
		cb.cb_type = ZPOOL_CONFIG_SPARES;
		if (zpool_iter(hdl, find_aux, &cb) == 1) {
			name = (char *)zpool_get_name(cb.cb_zhp);
			ret = B_TRUE;
		} else {
			ret = B_FALSE;
		}
		break;

	case POOL_STATE_L2CACHE:

		/*
		 * Check if any pool is currently using this l2cache device.
		 */
		cb.cb_zhp = NULL;
		cb.cb_guid = vdev_guid;
		cb.cb_type = ZPOOL_CONFIG_L2CACHE;
		if (zpool_iter(hdl, find_aux, &cb) == 1) {
			name = (char *)zpool_get_name(cb.cb_zhp);
			ret = B_TRUE;
		} else {
			ret = B_FALSE;
		}
		break;

	default:
		ret = B_FALSE;
	}


	if (ret) {
		if ((*namestr = zfs_strdup(hdl, name)) == NULL) {
			if (cb.cb_zhp)
				zpool_close(cb.cb_zhp);
			nvlist_free(config);
			return (-1);
		}
		*state = (pool_state_t)stateval;
	}

	if (cb.cb_zhp)
		zpool_close(cb.cb_zhp);

	nvlist_free(config);
	*inuse = ret;
	return (0);
}