blob: bf7bd6a7fa9f1b42af0445b202e5519279320202 [file] [log] [blame]
/*
* 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 2010 Sun Microsystems, Inc. All rights reserved.
* Use is subject to license terms.
*/
#include <ctype.h>
#include <errno.h>
#include <devid.h>
#include <fcntl.h>
#include <libintl.h>
#include <stdio.h>
#include <stdlib.h>
#include <strings.h>
#include <dlfcn.h>
#include <unistd.h>
#include <sys/efi_partition.h>
#include <sys/vtoc.h>
#include <sys/stat.h>
#include <sys/zfs_ioctl.h>
#include "zfs_namecheck.h"
#include "zfs_prop.h"
#include "libzfs_impl.h"
#include "zfs_comutil.h"
#include "format.h"
#include <syslog.h>
const char *hist_event_table[LOG_END] = {
"invalid event",
"pool create",
"vdev add",
"pool remove",
"pool destroy",
"pool export",
"pool import",
"vdev attach",
"vdev replace",
"vdev detach",
"vdev online",
"vdev offline",
"vdev upgrade",
"pool clear",
"pool scrub",
"pool property set",
"create",
"clone",
"destroy",
"destroy_begin_sync",
"inherit",
"property set",
"quota set",
"permission update",
"permission remove",
"permission who remove",
"promote",
"receive",
"rename",
"reservation set",
"replay_inc_sync",
"replay_full_sync",
"rollback",
"snapshot",
"filesystem version upgrade",
"refquota set",
"refreservation set",
"pool scrub done",
"user hold",
"user release",
"pool split",
};
/*static int read_efi_label(nvlist_t *config, diskaddr_t *sb);*/
#if defined(__i386) || defined(__amd64)
#define BOOTCMD "installgrub(1M)"
#else
#define BOOTCMD "installboot(1M)"
#endif
#define DISK_ROOT "/dev"
#define RDISK_ROOT "/dev"
#define BACKUP_SLICE "s2"
/*
* ====================================================================
* zpool property functions
* ====================================================================
*/
static int
zpool_get_all_props(zpool_handle_t *zhp)
{
spa_t *p_spa;
int i_error;
if((i_error = spa_open(zhp->zpool_name, &p_spa, FTAG)))
{
//TODO !!
// fprintf(stderr, "FIXME !!!\n");
return -1;
}
else
{
i_error = spa_prop_get(p_spa, &zhp->zpool_props);
spa_close(p_spa, FTAG);
return 0;
}
#if 0 //libzfswrap
zfs_cmd_t zc = { 0 };
libzfs_handle_t *hdl = zhp->zpool_hdl;
(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
if (zcmd_alloc_dst_nvlist(hdl, &zc, 0) != 0)
return (-1);
while (ioctl(hdl->libzfs_fd, ZFS_IOC_POOL_GET_PROPS, &zc) != 0) {
if (errno == ENOMEM) {
if (zcmd_expand_dst_nvlist(hdl, &zc) != 0) {
zcmd_free_nvlists(&zc);
return (-1);
}
} else {
zcmd_free_nvlists(&zc);
return (-1);
}
}
if (zcmd_read_dst_nvlist(hdl, &zc, &zhp->zpool_props) != 0) {
zcmd_free_nvlists(&zc);
return (-1);
}
zcmd_free_nvlists(&zc);
return (0);
#endif
}
static int
zpool_props_refresh(zpool_handle_t *zhp)
{
nvlist_t *old_props;
old_props = zhp->zpool_props;
if (zpool_get_all_props(zhp) != 0)
return (-1);
nvlist_free(old_props);
return (0);
}
static char *
zpool_get_prop_string(zpool_handle_t *zhp, zpool_prop_t prop,
zprop_source_t *src)
{
nvlist_t *nv, *nvl;
uint64_t ival;
char *value;
zprop_source_t source;
nvl = zhp->zpool_props;
if (nvlist_lookup_nvlist(nvl, zpool_prop_to_name(prop), &nv) == 0) {
verify(nvlist_lookup_uint64(nv, ZPROP_SOURCE, &ival) == 0);
source = ival;
verify(nvlist_lookup_string(nv, ZPROP_VALUE, &value) == 0);
} else {
source = ZPROP_SRC_DEFAULT;
if ((value = (char *)zpool_prop_default_string(prop)) == NULL)
value = "-";
}
if (src)
*src = source;
return (value);
}
uint64_t
zpool_get_prop_int(zpool_handle_t *zhp, zpool_prop_t prop, zprop_source_t *src)
{
nvlist_t *nv, *nvl;
uint64_t value;
zprop_source_t source;
if (zhp->zpool_props == NULL && zpool_get_all_props(zhp)) {
/*
* zpool_get_all_props() has most likely failed because
* the pool is faulted, but if all we need is the top level
* vdev's guid then get it from the zhp config nvlist.
*/
if ((prop == ZPOOL_PROP_GUID) &&
(nvlist_lookup_nvlist(zhp->zpool_config,
ZPOOL_CONFIG_VDEV_TREE, &nv) == 0) &&
(nvlist_lookup_uint64(nv, ZPOOL_CONFIG_GUID, &value)
== 0)) {
return (value);
}
return (zpool_prop_default_numeric(prop));
}
nvl = zhp->zpool_props;
if (nvlist_lookup_nvlist(nvl, zpool_prop_to_name(prop), &nv) == 0) {
verify(nvlist_lookup_uint64(nv, ZPROP_SOURCE, &value) == 0);
source = value;
verify(nvlist_lookup_uint64(nv, ZPROP_VALUE, &value) == 0);
} else {
source = ZPROP_SRC_DEFAULT;
value = zpool_prop_default_numeric(prop);
}
if (src)
*src = source;
return (value);
}
/*
* Map VDEV STATE to printed strings.
*/
char *
zpool_state_to_name(vdev_state_t state, vdev_aux_t aux)
{
switch (state) {
case VDEV_STATE_CLOSED:
case VDEV_STATE_OFFLINE:
return (gettext("OFFLINE"));
case VDEV_STATE_REMOVED:
return (gettext("REMOVED"));
case VDEV_STATE_CANT_OPEN:
if (aux == VDEV_AUX_CORRUPT_DATA || aux == VDEV_AUX_BAD_LOG)
return (gettext("FAULTED"));
else if (aux == VDEV_AUX_SPLIT_POOL)
return (gettext("SPLIT"));
else
return (gettext("UNAVAIL"));
case VDEV_STATE_FAULTED:
return (gettext("FAULTED"));
case VDEV_STATE_DEGRADED:
return (gettext("DEGRADED"));
case VDEV_STATE_HEALTHY:
return (gettext("ONLINE"));
}
return (gettext("UNKNOWN"));
}
/*
* Get a zpool property value for 'prop' and return the value in
* a pre-allocated buffer.
*/
int
zpool_get_prop(zpool_handle_t *zhp, zpool_prop_t prop, char *buf, size_t len,
zprop_source_t *srctype)
{
uint64_t intval;
const char *strval;
zprop_source_t src = ZPROP_SRC_NONE;
nvlist_t *nvroot;
vdev_stat_t *vs;
uint_t vsc;
if (zpool_get_state(zhp) == POOL_STATE_UNAVAIL) {
switch (prop) {
case ZPOOL_PROP_NAME:
(void) strlcpy(buf, zpool_get_name(zhp), len);
break;
case ZPOOL_PROP_HEALTH:
(void) strlcpy(buf, "FAULTED", len);
break;
case ZPOOL_PROP_GUID:
intval = zpool_get_prop_int(zhp, prop, &src);
(void) snprintf(buf, len, "%llu", (long long unsigned int)intval);
break;
case ZPOOL_PROP_ALTROOT:
case ZPOOL_PROP_CACHEFILE:
if (zhp->zpool_props != NULL ||
zpool_get_all_props(zhp) == 0) {
(void) strlcpy(buf,
zpool_get_prop_string(zhp, prop, &src),
len);
if (srctype != NULL)
*srctype = src;
return (0);
}
/* FALLTHROUGH */
default:
(void) strlcpy(buf, "-", len);
break;
}
if (srctype != NULL)
*srctype = src;
return (0);
}
if (zhp->zpool_props == NULL && zpool_get_all_props(zhp) &&
prop != ZPOOL_PROP_NAME)
return (-1);
switch (zpool_prop_get_type(prop)) {
case PROP_TYPE_STRING:
(void) strlcpy(buf, zpool_get_prop_string(zhp, prop, &src),
len);
break;
case PROP_TYPE_NUMBER:
intval = zpool_get_prop_int(zhp, prop, &src);
switch (prop) {
case ZPOOL_PROP_SIZE:
case ZPOOL_PROP_ALLOCATED:
case ZPOOL_PROP_FREE:
(void) zfs_nicenum(intval, buf, len);
break;
case ZPOOL_PROP_CAPACITY:
(void) snprintf(buf, len, "%llu%%",
(u_longlong_t)intval);
break;
case ZPOOL_PROP_DEDUPRATIO:
(void) snprintf(buf, len, "%llu.%02llux",
(u_longlong_t)(intval / 100),
(u_longlong_t)(intval % 100));
break;
case ZPOOL_PROP_HEALTH:
verify(nvlist_lookup_nvlist(zpool_get_config(zhp, NULL),
ZPOOL_CONFIG_VDEV_TREE, &nvroot) == 0);
verify(nvlist_lookup_uint64_array(nvroot,
ZPOOL_CONFIG_STATS, (uint64_t **)&vs, &vsc) == 0);
(void) strlcpy(buf, zpool_state_to_name(intval,
vs->vs_aux), len);
break;
default:
(void) snprintf(buf, len, "%llu", (u_longlong_t) intval);
}
break;
case PROP_TYPE_INDEX:
intval = zpool_get_prop_int(zhp, prop, &src);
if (zpool_prop_index_to_string(prop, intval, &strval)
!= 0)
return (-1);
(void) strlcpy(buf, strval, len);
break;
default:
abort();
}
if (srctype)
*srctype = src;
return (0);
}
/*
* Check if the bootfs name has the same pool name as it is set to.
* Assuming bootfs is a valid dataset name.
*/
static boolean_t
bootfs_name_valid(const char *pool, char *bootfs)
{
int len = strlen(pool);
if (!zfs_name_valid(bootfs, ZFS_TYPE_FILESYSTEM|ZFS_TYPE_SNAPSHOT))
return (B_FALSE);
if (strncmp(pool, bootfs, len) == 0 &&
(bootfs[len] == '/' || bootfs[len] == '\0'))
return (B_TRUE);
return (B_FALSE);
}
/*
* Inspect the configuration to determine if any of the devices contain
* an EFI label.
*/
/* ZFSFUSE: disabled */
#if 0
static boolean_t
pool_uses_efi(nvlist_t *config)
{
nvlist_t **child;
uint_t c, children;
if (nvlist_lookup_nvlist_array(config, ZPOOL_CONFIG_CHILDREN,
&child, &children) != 0)
return (read_efi_label(config, NULL) >= 0);
for (c = 0; c < children; c++) {
if (pool_uses_efi(child[c]))
return (B_TRUE);
}
return (B_FALSE);
}
#endif
static boolean_t
pool_is_bootable(zpool_handle_t *zhp)
{
char bootfs[ZPOOL_MAXNAMELEN];
return (zpool_get_prop(zhp, ZPOOL_PROP_BOOTFS, bootfs,
sizeof (bootfs), NULL) == 0 && strncmp(bootfs, "-",
sizeof (bootfs)) != 0);
}
/*
* Given an nvlist of zpool properties to be set, validate that they are
* correct, and parse any numeric properties (index, boolean, etc) if they are
* specified as strings.
*/
static nvlist_t *
zpool_valid_proplist(libzfs_handle_t *hdl, const char *poolname,
nvlist_t *props, uint64_t version, boolean_t create_or_import, char *errbuf)
{
nvpair_t *elem;
nvlist_t *retprops;
zpool_prop_t prop;
char *strval;
uint64_t intval;
char *slash;
struct stat64 statbuf;
zpool_handle_t *zhp;
nvlist_t *nvroot;
if (nvlist_alloc(&retprops, NV_UNIQUE_NAME, 0) != 0) {
(void) no_memory(hdl);
return (NULL);
}
elem = NULL;
while ((elem = nvlist_next_nvpair(props, elem)) != NULL) {
const char *propname = nvpair_name(elem);
/*
* Make sure this property is valid and applies to this type.
*/
if ((prop = zpool_name_to_prop(propname)) == ZPROP_INVAL) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"invalid property '%s'"), propname);
(void) zfs_error(hdl, EZFS_BADPROP, errbuf);
goto error;
}
if (zpool_prop_readonly(prop)) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "'%s' "
"is readonly"), propname);
(void) zfs_error(hdl, EZFS_PROPREADONLY, errbuf);
goto error;
}
if (zprop_parse_value(hdl, elem, prop, ZFS_TYPE_POOL, retprops,
&strval, &intval, errbuf) != 0)
goto error;
/*
* Perform additional checking for specific properties.
*/
switch (prop) {
case ZPOOL_PROP_VERSION:
if (intval < version || intval > SPA_VERSION) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"property '%s' number %d is invalid."),
propname, intval);
(void) zfs_error(hdl, EZFS_BADVERSION, errbuf);
goto error;
}
break;
case ZPOOL_PROP_BOOTFS:
if (create_or_import) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"property '%s' cannot be set at creation "
"or import time"), propname);
(void) zfs_error(hdl, EZFS_BADPROP, errbuf);
goto error;
}
if (version < SPA_VERSION_BOOTFS) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"pool must be upgraded to support "
"'%s' property"), propname);
(void) zfs_error(hdl, EZFS_BADVERSION, errbuf);
goto error;
}
/*
* bootfs property value has to be a dataset name and
* the dataset has to be in the same pool as it sets to.
*/
if (strval[0] != '\0' && !bootfs_name_valid(poolname,
strval)) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "'%s' "
"is an invalid name"), strval);
(void) zfs_error(hdl, EZFS_INVALIDNAME, errbuf);
goto error;
}
if ((zhp = zpool_open_canfail(hdl, poolname)) == NULL) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"could not open pool '%s'"), poolname);
(void) zfs_error(hdl, EZFS_OPENFAILED, errbuf);
goto error;
}
verify(nvlist_lookup_nvlist(zpool_get_config(zhp, NULL),
ZPOOL_CONFIG_VDEV_TREE, &nvroot) == 0);
/*
* bootfs property cannot be set on a disk which has
* been EFI labeled.
*/
/* ZFSFUSE: disabled */
/*if (pool_uses_efi(nvroot)) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"property '%s' not supported on "
"EFI labeled devices"), propname);
(void) zfs_error(hdl, EZFS_POOL_NOTSUP, errbuf);
zpool_close(zhp);
goto error;
}*/
zpool_close(zhp);
break;
case ZPOOL_PROP_ALTROOT:
if (!create_or_import) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"property '%s' can only be set during pool "
"creation or import"), propname);
(void) zfs_error(hdl, EZFS_BADPROP, errbuf);
goto error;
}
if (strval[0] != '/') {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"bad alternate root '%s'"), strval);
(void) zfs_error(hdl, EZFS_BADPATH, errbuf);
goto error;
}
break;
case ZPOOL_PROP_CACHEFILE:
if (strval[0] == '\0')
break;
if (strcmp(strval, "none") == 0)
break;
if (strval[0] != '/') {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"property '%s' must be empty, an "
"absolute path, or 'none'"), propname);
(void) zfs_error(hdl, EZFS_BADPATH, errbuf);
goto error;
}
slash = strrchr(strval, '/');
if (slash[1] == '\0' || strcmp(slash, "/.") == 0 ||
strcmp(slash, "/..") == 0) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"'%s' is not a valid file"), strval);
(void) zfs_error(hdl, EZFS_BADPATH, errbuf);
goto error;
}
*slash = '\0';
if (strval[0] != '\0' &&
(stat64(strval, &statbuf) != 0 ||
!S_ISDIR(statbuf.st_mode))) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"'%s' is not a valid directory"),
strval);
(void) zfs_error(hdl, EZFS_BADPATH, errbuf);
goto error;
}
*slash = '/';
break;
}
}
return (retprops);
error:
nvlist_free(retprops);
return (NULL);
}
/*
* Set zpool property : propname=propval.
*/
int
zpool_set_prop(zpool_handle_t *zhp, const char *propname, const char *propval)
{
zfs_cmd_t zc = { 0 };
int ret = -1;
char errbuf[1024];
nvlist_t *nvl = NULL;
nvlist_t *realprops;
uint64_t version;
(void) snprintf(errbuf, sizeof (errbuf),
dgettext(TEXT_DOMAIN, "cannot set property for '%s'"),
zhp->zpool_name);
if (nvlist_alloc(&nvl, NV_UNIQUE_NAME, 0) != 0)
return (no_memory(zhp->zpool_hdl));
if (nvlist_add_string(nvl, propname, propval) != 0) {
nvlist_free(nvl);
return (no_memory(zhp->zpool_hdl));
}
version = zpool_get_prop_int(zhp, ZPOOL_PROP_VERSION, NULL);
if ((realprops = zpool_valid_proplist(zhp->zpool_hdl,
zhp->zpool_name, nvl, version, B_FALSE, errbuf)) == NULL) {
nvlist_free(nvl);
return (-1);
}
nvlist_free(nvl);
nvl = realprops;
/*
* Execute the corresponding ioctl() to set this property.
*/
(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
if (zcmd_write_src_nvlist(zhp->zpool_hdl, &zc, nvl) != 0) {
nvlist_free(nvl);
return (-1);
}
ret = zfs_ioctl(zhp->zpool_hdl, ZFS_IOC_POOL_SET_PROPS, &zc);
zcmd_free_nvlists(&zc);
nvlist_free(nvl);
if (ret)
(void) zpool_standard_error(zhp->zpool_hdl, errno, errbuf);
else
(void) zpool_props_refresh(zhp);
return (ret);
}
int
zpool_expand_proplist(zpool_handle_t *zhp, zprop_list_t **plp)
{
libzfs_handle_t *hdl = zhp->zpool_hdl;
zprop_list_t *entry;
char buf[ZFS_MAXPROPLEN];
if (zprop_expand_list(hdl, plp, ZFS_TYPE_POOL) != 0)
return (-1);
for (entry = *plp; entry != NULL; entry = entry->pl_next) {
if (entry->pl_fixed)
continue;
if (entry->pl_prop != ZPROP_INVAL &&
zpool_get_prop(zhp, entry->pl_prop, buf, sizeof (buf),
NULL) == 0) {
if (strlen(buf) > entry->pl_width)
entry->pl_width = strlen(buf);
}
}
return (0);
}
/*
* Don't start the slice at the default block of 34; many storage
* devices will use a stripe width of 128k, so start there instead.
*/
#define NEW_START_BLOCK 256
/*
* Validate the given pool name, optionally putting an extended error message in
* 'buf'.
*/
boolean_t
zpool_name_valid(libzfs_handle_t *hdl, boolean_t isopen, const char *pool)
{
namecheck_err_t why;
char what;
int ret;
ret = pool_namecheck(pool, &why, &what);
/*
* The rules for reserved pool names were extended at a later point.
* But we need to support users with existing pools that may now be
* invalid. So we only check for this expanded set of names during a
* create (or import), and only in userland.
*/
if (ret == 0 && !isopen &&
(strncmp(pool, "mirror", 6) == 0 ||
strncmp(pool, "raidz", 5) == 0 ||
strncmp(pool, "spare", 5) == 0 ||
strcmp(pool, "log") == 0)) {
if (hdl != NULL)
zfs_error_aux(hdl,
dgettext(TEXT_DOMAIN, "name is reserved"));
return (B_FALSE);
}
if (ret != 0) {
if (hdl != NULL) {
switch (why) {
case NAME_ERR_TOOLONG:
zfs_error_aux(hdl,
dgettext(TEXT_DOMAIN, "name is too long"));
break;
case NAME_ERR_INVALCHAR:
zfs_error_aux(hdl,
dgettext(TEXT_DOMAIN, "invalid character "
"'%c' in pool name"), what);
break;
case NAME_ERR_NOLETTER:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"name must begin with a letter"));
break;
case NAME_ERR_RESERVED:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"name is reserved"));
break;
case NAME_ERR_DISKLIKE:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"pool name is reserved"));
break;
case NAME_ERR_LEADING_SLASH:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"leading slash in name"));
break;
case NAME_ERR_EMPTY_COMPONENT:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"empty component in name"));
break;
case NAME_ERR_TRAILING_SLASH:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"trailing slash in name"));
break;
case NAME_ERR_MULTIPLE_AT:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"multiple '@' delimiters in name"));
break;
}
}
return (B_FALSE);
}
return (B_TRUE);
}
/*
* Open a handle to the given pool, even if the pool is currently in the FAULTED
* state.
*/
zpool_handle_t *
zpool_open_canfail(libzfs_handle_t *hdl, const char *pool)
{
zpool_handle_t *zhp;
boolean_t missing;
/*
* Make sure the pool name is valid.
*/
if (!zpool_name_valid(hdl, B_TRUE, pool)) {
(void) zfs_error_fmt(hdl, EZFS_INVALIDNAME,
dgettext(TEXT_DOMAIN, "cannot open '%s'"),
pool);
return (NULL);
}
if ((zhp = zfs_alloc(hdl, sizeof (zpool_handle_t))) == NULL)
return (NULL);
zhp->zpool_hdl = hdl;
(void) strlcpy(zhp->zpool_name, pool, sizeof (zhp->zpool_name));
if (zpool_refresh_stats(zhp, &missing) != 0) {
zpool_close(zhp);
return (NULL);
}
if (missing) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "no such pool"));
(void) zfs_error_fmt(hdl, EZFS_NOENT,
dgettext(TEXT_DOMAIN, "cannot open '%s'"), pool);
zpool_close(zhp);
return (NULL);
}
return (zhp);
}
/*
* Like the above, but silent on error. Used when iterating over pools (because
* the configuration cache may be out of date).
*/
int
zpool_open_silent(libzfs_handle_t *hdl, const char *pool, zpool_handle_t **ret)
{
zpool_handle_t *zhp;
boolean_t missing;
if ((zhp = zfs_alloc(hdl, sizeof (zpool_handle_t))) == NULL)
return (-1);
zhp->zpool_hdl = hdl;
(void) strlcpy(zhp->zpool_name, pool, sizeof (zhp->zpool_name));
if (zpool_refresh_stats(zhp, &missing) != 0) {
zpool_close(zhp);
return (-1);
}
if (missing) {
zpool_close(zhp);
*ret = NULL;
return (0);
}
*ret = zhp;
return (0);
}
/*
* Similar to zpool_open_canfail(), but refuses to open pools in the faulted
* state.
*/
zpool_handle_t *
zpool_open(libzfs_handle_t *hdl, const char *pool)
{
zpool_handle_t *zhp;
if ((zhp = zpool_open_canfail(hdl, pool)) == NULL)
return (NULL);
if (zhp->zpool_state == POOL_STATE_UNAVAIL) {
(void) zfs_error_fmt(hdl, EZFS_POOLUNAVAIL,
dgettext(TEXT_DOMAIN, "cannot open '%s'"), zhp->zpool_name);
zpool_close(zhp);
return (NULL);
}
return (zhp);
}
/*
* Close the handle. Simply frees the memory associated with the handle.
*/
void
zpool_close(zpool_handle_t *zhp)
{
if (zhp->zpool_config)
nvlist_free(zhp->zpool_config);
if (zhp->zpool_old_config)
nvlist_free(zhp->zpool_old_config);
if (zhp->zpool_props)
nvlist_free(zhp->zpool_props);
free(zhp);
}
/*
* Return the name of the pool.
*/
const char *
zpool_get_name(zpool_handle_t *zhp)
{
return (zhp->zpool_name);
}
/*
* Return the state of the pool (ACTIVE or UNAVAILABLE)
*/
int
zpool_get_state(zpool_handle_t *zhp)
{
return (zhp->zpool_state);
}
/*
* Create the named pool, using the provided vdev list. It is assumed
* that the consumer has already validated the contents of the nvlist, so we
* don't have to worry about error semantics.
*/
int
zpool_create(libzfs_handle_t *hdl, const char *pool, nvlist_t *nvroot,
nvlist_t *props, nvlist_t *fsprops)
{
// zfs_cmd_t zc = { 0 };
nvlist_t *zc_fsprops = NULL;
nvlist_t *zc_props = NULL;
char msg[1024];
char *altroot;
int ret = -1;
(void) snprintf(msg, sizeof (msg), dgettext(TEXT_DOMAIN,
"cannot create '%s'"), pool);
if (!zpool_name_valid(hdl, B_FALSE, pool))
return (zfs_error(hdl, EZFS_INVALIDNAME, msg));
#if 0
if (zcmd_write_conf_nvlist(hdl, &zc, nvroot) != 0)
return (-1);
#endif
if (props) {
if ((zc_props = zpool_valid_proplist(hdl, pool, props,
SPA_VERSION_1, B_TRUE, msg)) == NULL) {
goto create_failed;
}
}
if (fsprops) {
uint64_t zoned;
char *zonestr;
zoned = ((nvlist_lookup_string(fsprops,
zfs_prop_to_name(ZFS_PROP_ZONED), &zonestr) == 0) &&
strcmp(zonestr, "on") == 0);
if ((zc_fsprops = zfs_valid_proplist(hdl,
ZFS_TYPE_FILESYSTEM, fsprops, zoned, NULL, msg)) == NULL) {
goto create_failed;
}
if (!zc_props &&
(nvlist_alloc(&zc_props, NV_UNIQUE_NAME, 0) != 0)) {
goto create_failed;
}
if (nvlist_add_nvlist(zc_props,
ZPOOL_ROOTFS_PROPS, zc_fsprops) != 0) {
goto create_failed;
}
}
#if 0 //libzfswrap
if (zc_props && zcmd_write_src_nvlist(hdl, &zc, zc_props) != 0)
goto create_failed;
(void) strlcpy(zc.zc_name, pool, sizeof (zc.zc_name));
if ((ret = zfs_ioctl(hdl, ZFS_IOC_POOL_CREATE, &zc)) != 0) {
#endif
if((ret = spa_create(pool, nvroot, props, "libzfswrap_zpool_create", fsprops)) != 0)
{
// zcmd_free_nvlists(&zc);
nvlist_free(zc_props);
nvlist_free(zc_fsprops);
switch (errno) {
case EBUSY:
/*
* This can happen if the user has specified the same
* device multiple times. We can't reliably detect this
* until we try to add it and see we already have a
* label.
*/
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"one or more vdevs refer to the same device"));
return (zfs_error(hdl, EZFS_BADDEV, msg));
case EOVERFLOW:
/*
* This occurs when one of the devices is below
* SPA_MINDEVSIZE. Unfortunately, we can't detect which
* device was the problem device since there's no
* reliable way to determine device size from userland.
*/
{
char buf[64];
zfs_nicenum(SPA_MINDEVSIZE, buf, sizeof (buf));
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"one or more devices is less than the "
"minimum size (%s)"), buf);
}
return (zfs_error(hdl, EZFS_BADDEV, msg));
case ENOSPC:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"one or more devices is out of space"));
return (zfs_error(hdl, EZFS_BADDEV, msg));
case ENOTBLK:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"cache device must be a disk or disk slice"));
return (zfs_error(hdl, EZFS_BADDEV, msg));
default:
return (zpool_standard_error(hdl, errno, msg));
}
}
/*
* If this is an alternate root pool, then we automatically set the
* mountpoint of the root dataset to be '/'.
*/
if (nvlist_lookup_string(props, zpool_prop_to_name(ZPOOL_PROP_ALTROOT),
&altroot) == 0) {
zfs_handle_t *zhp;
verify((zhp = zfs_open(hdl, pool, ZFS_TYPE_DATASET)) != NULL);
verify(zfs_prop_set(zhp, zfs_prop_to_name(ZFS_PROP_MOUNTPOINT),
"/") == 0);
zfs_close(zhp);
}
create_failed:
// zcmd_free_nvlists(&zc);
nvlist_free(zc_props);
nvlist_free(zc_fsprops);
return (ret);
}
/*
* Destroy the given pool. It is up to the caller to ensure that there are no
* datasets left in the pool.
*/
int
zpool_destroy(zpool_handle_t *zhp)
{
zfs_cmd_t zc = { 0 };
zfs_handle_t *zfp = NULL;
libzfs_handle_t *hdl = zhp->zpool_hdl;
char msg[1024];
if (zhp->zpool_state == POOL_STATE_ACTIVE &&
(zfp = zfs_open(zhp->zpool_hdl, zhp->zpool_name,
ZFS_TYPE_FILESYSTEM)) == NULL)
return (-1);
(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
if (zfs_ioctl(zhp->zpool_hdl, ZFS_IOC_POOL_DESTROY, &zc) != 0) {
(void) snprintf(msg, sizeof (msg), dgettext(TEXT_DOMAIN,
"cannot destroy '%s'"), zhp->zpool_name);
if (errno == EROFS) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"one or more devices is read only"));
(void) zfs_error(hdl, EZFS_BADDEV, msg);
} else {
(void) zpool_standard_error(hdl, errno, msg);
}
if (zfp)
zfs_close(zfp);
return (-1);
}
if (zfp) {
remove_mountpoint(zfp);
zfs_close(zfp);
}
return (0);
}
/*
* Add the given vdevs to the pool. The caller must have already performed the
* necessary verification to ensure that the vdev specification is well-formed.
*/
int
zpool_add(zpool_handle_t *zhp, nvlist_t *nvroot)
{
zfs_cmd_t zc = { 0 };
int ret;
libzfs_handle_t *hdl = zhp->zpool_hdl;
char msg[1024];
nvlist_t **spares, **l2cache;
uint_t nspares, nl2cache;
(void) snprintf(msg, sizeof (msg), dgettext(TEXT_DOMAIN,
"cannot add to '%s'"), zhp->zpool_name);
if (zpool_get_prop_int(zhp, ZPOOL_PROP_VERSION, NULL) <
SPA_VERSION_SPARES &&
nvlist_lookup_nvlist_array(nvroot, ZPOOL_CONFIG_SPARES,
&spares, &nspares) == 0) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "pool must be "
"upgraded to add hot spares"));
return (zfs_error(hdl, EZFS_BADVERSION, msg));
}
#if 0
if (pool_is_bootable(zhp) && nvlist_lookup_nvlist_array(nvroot,
ZPOOL_CONFIG_SPARES, &spares, &nspares) == 0) {
uint64_t s;
for (s = 0; s < nspares; s++) {
char *path;
if (nvlist_lookup_string(spares[s], ZPOOL_CONFIG_PATH,
&path) == 0 && pool_uses_efi(spares[s])) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"device '%s' contains an EFI label and "
"cannot be used on root pools."),
zpool_vdev_name(hdl, NULL, spares[s],
B_FALSE));
return (zfs_error(hdl, EZFS_POOL_NOTSUP, msg));
}
}
}
#endif
if (zpool_get_prop_int(zhp, ZPOOL_PROP_VERSION, NULL) <
SPA_VERSION_L2CACHE &&
nvlist_lookup_nvlist_array(nvroot, ZPOOL_CONFIG_L2CACHE,
&l2cache, &nl2cache) == 0) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "pool must be "
"upgraded to add cache devices"));
return (zfs_error(hdl, EZFS_BADVERSION, msg));
}
if (zcmd_write_conf_nvlist(hdl, &zc, nvroot) != 0)
return (-1);
(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
if (zfs_ioctl(zhp->zpool_hdl, ZFS_IOC_VDEV_ADD, &zc) != 0) {
switch (errno) {
case EBUSY:
/*
* This can happen if the user has specified the same
* device multiple times. We can't reliably detect this
* until we try to add it and see we already have a
* label.
*/
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"one or more vdevs refer to the same device"));
(void) zfs_error(hdl, EZFS_BADDEV, msg);
break;
case EOVERFLOW:
/*
* This occurrs when one of the devices is below
* SPA_MINDEVSIZE. Unfortunately, we can't detect which
* device was the problem device since there's no
* reliable way to determine device size from userland.
*/
{
char buf[64];
zfs_nicenum(SPA_MINDEVSIZE, buf, sizeof (buf));
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"device is less than the minimum "
"size (%s)"), buf);
}
(void) zfs_error(hdl, EZFS_BADDEV, msg);
break;
case ENOTSUP:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"pool must be upgraded to add these vdevs"));
(void) zfs_error(hdl, EZFS_BADVERSION, msg);
break;
case EDOM:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"root pool can not have multiple vdevs"
" or separate logs"));
(void) zfs_error(hdl, EZFS_POOL_NOTSUP, msg);
break;
case ENOTBLK:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"cache device must be a disk or disk slice"));
(void) zfs_error(hdl, EZFS_BADDEV, msg);
break;
default:
(void) zpool_standard_error(hdl, errno, msg);
}
ret = -1;
} else {
ret = 0;
}
zcmd_free_nvlists(&zc);
return (ret);
}
/*
* Exports the pool from the system. The caller must ensure that there are no
* mounted datasets in the pool.
*/
int
zpool_export_common(zpool_handle_t *zhp, boolean_t force, boolean_t hardforce)
{
zfs_cmd_t zc = { 0 };
char msg[1024];
(void) snprintf(msg, sizeof (msg), dgettext(TEXT_DOMAIN,
"cannot export '%s'"), zhp->zpool_name);
(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
zc.zc_cookie = force;
zc.zc_guid = hardforce;
#define ZFSFUSE_BUSY_SLEEP_FACTOR 50000 // .5 seconds was chosen ater some tuning
int retry = 0;
int ret;
while ((ret = zfs_ioctl(zhp->zpool_hdl, ZFS_IOC_POOL_EXPORT, &zc)) == EBUSY
&& retry++ < 6) {
struct timeval timeout;
/* Something in the way zfs-fuse works keeps the datasets busy for
* longer than expected.
* If we try to export/destroy a pool containing a few fs like
* pool/fs1/fs2, then it will try to export it much before the umounts
* are really finished.
* The sleep is a temporary workaround here.
* The zfsfuse_destroy function is called after umount has already
* returned, so the only solution is to allow a pause here in case the
* export fails with EBUSY */
timeout.tv_sec=0;
timeout.tv_usec=ZFSFUSE_BUSY_SLEEP_FACTOR;
VERIFY(select(0,NULL,NULL,NULL,&timeout)==0);
}
if (retry>0)
syslog(LOG_WARNING, "Pool '%s' was busy, export was tried for %0.1fs (%i attempts) resulting in %s",
zhp->zpool_name, (retry*ZFSFUSE_BUSY_SLEEP_FACTOR)/100000.0, retry, strerror(errno));
if (ret != 0) {
switch (errno) {
case EXDEV:
zfs_error_aux(zhp->zpool_hdl, dgettext(TEXT_DOMAIN,
"use '-f' to override the following errors:\n"
"'%s' has an active shared spare which could be"
" used by other pools once '%s' is exported."),
zhp->zpool_name, zhp->zpool_name);
return (zfs_error(zhp->zpool_hdl, EZFS_ACTIVE_SPARE,
msg));
default:
return (zpool_standard_error_fmt(zhp->zpool_hdl, errno,
msg));
}
}
return (0);
}
int
zpool_export(zpool_handle_t *zhp, boolean_t force)
{
return (zpool_export_common(zhp, force, B_FALSE));
}
int
zpool_export_force(zpool_handle_t *zhp)
{
return (zpool_export_common(zhp, B_TRUE, B_TRUE));
}
static void
zpool_rewind_exclaim(libzfs_handle_t *hdl, const char *name, boolean_t dryrun,
nvlist_t *rbi)
{
uint64_t rewindto;
int64_t loss = -1;
struct tm t;
char timestr[128];
if (!hdl->libzfs_printerr || rbi == NULL)
return;
if (nvlist_lookup_uint64(rbi, ZPOOL_CONFIG_LOAD_TIME, &rewindto) != 0)
return;
(void) nvlist_lookup_int64(rbi, ZPOOL_CONFIG_REWIND_TIME, &loss);
if (localtime_r((time_t *)&rewindto, &t) != NULL &&
strftime(timestr, 128, "%F", &t) != 0) {
if (dryrun) {
(void) printf(dgettext(TEXT_DOMAIN,
"Would be able to return %s "
"to its state as of %s.\n"),
name, timestr);
} else {
(void) printf(dgettext(TEXT_DOMAIN,
"Pool %s returned to its state as of %s.\n"),
name, timestr);
}
if (loss > 120) {
(void) printf(dgettext(TEXT_DOMAIN,
"%s approximately " FI64 " "),
dryrun ? "Would discard" : "Discarded",
(loss + 30) / 60);
(void) printf(dgettext(TEXT_DOMAIN,
"minutes of transactions.\n"));
} else if (loss > 0) {
(void) printf(dgettext(TEXT_DOMAIN,
"%s approximately " FI64 " "),
dryrun ? "Would discard" : "Discarded", loss);
(void) printf(dgettext(TEXT_DOMAIN,
"seconds of transactions.\n"));
}
}
}
void
zpool_explain_recover(libzfs_handle_t *hdl, const char *name, int reason,
nvlist_t *config)
{
int64_t loss = -1;
uint64_t edata = UINT64_MAX;
uint64_t rewindto;
struct tm t;
char timestr[128];
if (!hdl->libzfs_printerr)
return;
if (reason >= 0)
(void) printf(dgettext(TEXT_DOMAIN, "action: "));
else
(void) printf(dgettext(TEXT_DOMAIN, "\t"));
/* All attempted rewinds failed if ZPOOL_CONFIG_LOAD_TIME missing */
if (nvlist_lookup_uint64(config,
ZPOOL_CONFIG_LOAD_TIME, &rewindto) != 0)
goto no_info;
(void) nvlist_lookup_int64(config, ZPOOL_CONFIG_REWIND_TIME, &loss);
(void) nvlist_lookup_uint64(config, ZPOOL_CONFIG_LOAD_DATA_ERRORS,
&edata);
(void) printf(dgettext(TEXT_DOMAIN,
"Recovery is possible, but will result in some data loss.\n"));
if (localtime_r((time_t *)&rewindto, &t) != NULL &&
strftime(timestr, 128, "%F", &t) != 0) {
(void) printf(dgettext(TEXT_DOMAIN,
"\tReturning the pool to its state as of %s\n"
"\tshould correct the problem. "),
timestr);
} else {
(void) printf(dgettext(TEXT_DOMAIN,
"\tReverting the pool to an earlier state "
"should correct the problem.\n\t"));
}
if (loss > 120) {
(void) printf(dgettext(TEXT_DOMAIN,
"Approximately " FI64 " minutes of data\n"
"\tmust be discarded, irreversibly. "), (loss + 30) / 60);
} else if (loss > 0) {
(void) printf(dgettext(TEXT_DOMAIN,
"Approximately " FI64 " seconds of data\n"
"\tmust be discarded, irreversibly. "), loss);
}
if (edata != 0 && edata != UINT64_MAX) {
if (edata == 1) {
(void) printf(dgettext(TEXT_DOMAIN,
"After rewind, at least\n"
"\tone persistent user-data error will remain. "));
} else {
(void) printf(dgettext(TEXT_DOMAIN,
"After rewind, several\n"
"\tpersistent user-data errors will remain. "));
}
}
(void) printf(dgettext(TEXT_DOMAIN,
"Recovery can be attempted\n\tby executing 'zpool %s -F %s'. "),
reason >= 0 ? "clear" : "import", name);
(void) printf(dgettext(TEXT_DOMAIN,
"A scrub of the pool\n"
"\tis strongly recommended after recovery.\n"));
return;
no_info:
(void) printf(dgettext(TEXT_DOMAIN,
"Destroy and re-create the pool from\n\ta backup source.\n"));
}
/*
* zpool_import() is a contracted interface. Should be kept the same
* if possible.
*
* Applications should use zpool_import_props() to import a pool with
* new properties value to be set.
*/
int
zpool_import(libzfs_handle_t *hdl, nvlist_t *config, const char *newname,
char *altroot)
{
nvlist_t *props = NULL;
int ret;
if (altroot != NULL) {
if (nvlist_alloc(&props, NV_UNIQUE_NAME, 0) != 0) {
return (zfs_error_fmt(hdl, EZFS_NOMEM,
dgettext(TEXT_DOMAIN, "cannot import '%s'"),
newname));
}
if (nvlist_add_string(props,
zpool_prop_to_name(ZPOOL_PROP_ALTROOT), altroot) != 0 ||
nvlist_add_string(props,
zpool_prop_to_name(ZPOOL_PROP_CACHEFILE), "none") != 0) {
nvlist_free(props);
return (zfs_error_fmt(hdl, EZFS_NOMEM,
dgettext(TEXT_DOMAIN, "cannot import '%s'"),
newname));
}
}
ret = zpool_import_props(hdl, config, newname, props, B_FALSE);
if (props)
nvlist_free(props);
return (ret);
}
/*
* Import the given pool using the known configuration and a list of
* properties to be set. The configuration should have come from
* zpool_find_import(). The 'newname' parameters control whether the pool
* is imported with a different name.
*/
int
zpool_import_props(libzfs_handle_t *hdl, nvlist_t *config, const char *newname,
nvlist_t *props, boolean_t importfaulted)
{
zfs_cmd_t zc = { 0 };
zpool_rewind_policy_t policy;
nvlist_t *nvi = NULL;
char *thename;
char *origname;
uint64_t returned_size;
int ret;
char errbuf[1024];
verify(nvlist_lookup_string(config, ZPOOL_CONFIG_POOL_NAME,
&origname) == 0);
(void) snprintf(errbuf, sizeof (errbuf), dgettext(TEXT_DOMAIN,
"cannot import pool '%s'"), origname);
if (newname != NULL) {
if (!zpool_name_valid(hdl, B_FALSE, newname))
return (zfs_error_fmt(hdl, EZFS_INVALIDNAME,
dgettext(TEXT_DOMAIN, "cannot import '%s'"),
newname));
thename = (char *)newname;
} else {
thename = origname;
}
if (props) {
uint64_t version;
verify(nvlist_lookup_uint64(config, ZPOOL_CONFIG_VERSION,
&version) == 0);
if ((props = zpool_valid_proplist(hdl, origname,
props, version, B_TRUE, errbuf)) == NULL) {
return (-1);
} else if (zcmd_write_src_nvlist(hdl, &zc, props) != 0) {
nvlist_free(props);
return (-1);
}
}
(void) strlcpy(zc.zc_name, thename, sizeof (zc.zc_name));
verify(nvlist_lookup_uint64(config, ZPOOL_CONFIG_POOL_GUID,
&zc.zc_guid) == 0);
if (zcmd_write_conf_nvlist(hdl, &zc, config) != 0) {
nvlist_free(props);
return (-1);
}
returned_size = zc.zc_nvlist_conf_size + 512;
if (zcmd_alloc_dst_nvlist(hdl, &zc, returned_size) != 0) {
nvlist_free(props);
return (-1);
}
zc.zc_cookie = (uint64_t)importfaulted;
ret = 0;
if (zfs_ioctl(hdl, ZFS_IOC_POOL_IMPORT, &zc) != 0) {
char desc[1024];
(void) zcmd_read_dst_nvlist(hdl, &zc, &nvi);
zpool_get_rewind_policy(config, &policy);
/*
* Dry-run failed, but we print out what success
* looks like if we found a best txg
*/
if ((policy.zrp_request & ZPOOL_TRY_REWIND) && nvi) {
zpool_rewind_exclaim(hdl, newname ? origname : thename,
B_TRUE, nvi);
nvlist_free(nvi);
return (-1);
}
if (newname == NULL)
(void) snprintf(desc, sizeof (desc),
dgettext(TEXT_DOMAIN, "cannot import '%s'"),
thename);
else
(void) snprintf(desc, sizeof (desc),
dgettext(TEXT_DOMAIN, "cannot import '%s' as '%s'"),
origname, thename);
switch (errno) {
case ENOTSUP:
/*
* Unsupported version.
*/
(void) zfs_error(hdl, EZFS_BADVERSION, desc);
break;
case EINVAL:
(void) zfs_error(hdl, EZFS_INVALCONFIG, desc);
break;
case EROFS:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"one or more devices is read only"));
(void) zfs_error(hdl, EZFS_BADDEV, desc);
break;
default:
(void) zcmd_read_dst_nvlist(hdl, &zc, &nvi);
(void) zpool_standard_error(hdl, errno, desc);
zpool_explain_recover(hdl,
newname ? origname : thename, -errno, nvi);
nvlist_free(nvi);
break;
}
ret = -1;
} else {
zpool_handle_t *zhp;
/*
* This should never fail, but play it safe anyway.
*/
if (zpool_open_silent(hdl, thename, &zhp) != 0)
ret = -1;
else if (zhp != NULL)
zpool_close(zhp);
(void) zcmd_read_dst_nvlist(hdl, &zc, &nvi);
zpool_get_rewind_policy(config, &policy);
if (policy.zrp_request &
(ZPOOL_DO_REWIND | ZPOOL_TRY_REWIND)) {
zpool_rewind_exclaim(hdl, newname ? origname : thename,
((policy.zrp_request & ZPOOL_TRY_REWIND) != 0),
nvi);
}
nvlist_free(nvi);
return (0);
}
zcmd_free_nvlists(&zc);
nvlist_free(props);
return (ret);
}
/*
* Scrub the pool.
*/
int
zpool_scrub(zpool_handle_t *zhp, pool_scrub_type_t type)
{
zfs_cmd_t zc = { 0 };
char msg[1024];
libzfs_handle_t *hdl = zhp->zpool_hdl;
(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
zc.zc_cookie = type;
if (zfs_ioctl(zhp->zpool_hdl, ZFS_IOC_POOL_SCRUB, &zc) == 0)
return (0);
(void) snprintf(msg, sizeof (msg),
dgettext(TEXT_DOMAIN, "cannot scrub %s"), zc.zc_name);
if (errno == EBUSY)
return (zfs_error(hdl, EZFS_RESILVERING, msg));
else
return (zpool_standard_error(hdl, errno, msg));
}
/*
* Find a vdev that matches the search criteria specified. We use the
* the nvpair name to determine how we should look for the device.
* 'avail_spare' is set to TRUE if the provided guid refers to an AVAIL
* spare; but FALSE if its an INUSE spare.
*/
static nvlist_t *
vdev_to_nvlist_iter(nvlist_t *nv, nvlist_t *search, boolean_t *avail_spare,
boolean_t *l2cache, boolean_t *log)
{
uint_t c, children;
nvlist_t **child;
nvlist_t *ret;
uint64_t is_log;
char *srchkey;
nvpair_t *pair = nvlist_next_nvpair(search, NULL);
/* Nothing to look for */
if (search == NULL || pair == NULL)
return (NULL);
/* Obtain the key we will use to search */
srchkey = nvpair_name(pair);
switch (nvpair_type(pair)) {
case DATA_TYPE_UINT64: {
uint64_t srchval, theguid, present;
verify(nvpair_value_uint64(pair, &srchval) == 0);
if (strcmp(srchkey, ZPOOL_CONFIG_GUID) == 0) {
if (nvlist_lookup_uint64(nv, ZPOOL_CONFIG_NOT_PRESENT,
&present) == 0) {
/*
* If the device has never been present since
* import, the only reliable way to match the
* vdev is by GUID.
*/
verify(nvlist_lookup_uint64(nv,
ZPOOL_CONFIG_GUID, &theguid) == 0);
if (theguid == srchval)
return (nv);
}
}
break;
}
case DATA_TYPE_STRING: {
char *srchval, *val;
verify(nvpair_value_string(pair, &srchval) == 0);
if (nvlist_lookup_string(nv, srchkey, &val) != 0)
break;
/*
* Search for the requested value. We special case the search
* for ZPOOL_CONFIG_PATH when it's a wholedisk and when
* Looking for a top-level vdev name (i.e. ZPOOL_CONFIG_TYPE).
* Otherwise, all other searches are simple string compares.
*/
if (strcmp(srchkey, ZPOOL_CONFIG_PATH) == 0 && val) {
uint64_t wholedisk = 0;
(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_WHOLE_DISK,
&wholedisk);
if (wholedisk) {
/*
* For whole disks, the internal path has 's0',
* but the path passed in by the user doesn't.
*/
if (strlen(srchval) == strlen(val) - 2 &&
strncmp(srchval, val, strlen(srchval)) == 0)
return (nv);
break;
}
} else if (strcmp(srchkey, ZPOOL_CONFIG_TYPE) == 0 && val) {
char *type, *idx, *end, *p;
uint64_t id, vdev_id;
/*
* Determine our vdev type, keeping in mind
* that the srchval is composed of a type and
* vdev id pair (i.e. mirror-4).
*/
if ((type = strdup(srchval)) == NULL)
return (NULL);
if ((p = strrchr(type, '-')) == NULL) {
free(type);
break;
}
idx = p + 1;
*p = '\0';
/*
* If the types don't match then keep looking.
*/
if (strncmp(val, type, strlen(val)) != 0) {
free(type);
break;
}
verify(strncmp(type, VDEV_TYPE_RAIDZ,
strlen(VDEV_TYPE_RAIDZ)) == 0 ||
strncmp(type, VDEV_TYPE_MIRROR,
strlen(VDEV_TYPE_MIRROR)) == 0);
verify(nvlist_lookup_uint64(nv, ZPOOL_CONFIG_ID,
&id) == 0);
errno = 0;
vdev_id = strtoull(idx, &end, 10);
free(type);
if (errno != 0)
return (NULL);
/*
* Now verify that we have the correct vdev id.
*/
if (vdev_id == id)
return (nv);
}
/*
* Common case
*/
if (strcmp(srchval, val) == 0)
return (nv);
break;
}
default:
break;
}
if (nvlist_lookup_nvlist_array(nv, ZPOOL_CONFIG_CHILDREN,
&child, &children) != 0)
return (NULL);
for (c = 0; c < children; c++) {
if ((ret = vdev_to_nvlist_iter(child[c], search,
avail_spare, l2cache, NULL)) != NULL) {
/*
* The 'is_log' value is only set for the toplevel
* vdev, not the leaf vdevs. So we always lookup the
* log device from the root of the vdev tree (where
* 'log' is non-NULL).
*/
if (log != NULL &&
nvlist_lookup_uint64(child[c],
ZPOOL_CONFIG_IS_LOG, &is_log) == 0 &&
is_log) {
*log = B_TRUE;
}
return (ret);
}
}
if (nvlist_lookup_nvlist_array(nv, ZPOOL_CONFIG_SPARES,
&child, &children) == 0) {
for (c = 0; c < children; c++) {
if ((ret = vdev_to_nvlist_iter(child[c], search,
avail_spare, l2cache, NULL)) != NULL) {
*avail_spare = B_TRUE;
return (ret);
}
}
}
if (nvlist_lookup_nvlist_array(nv, ZPOOL_CONFIG_L2CACHE,
&child, &children) == 0) {
for (c = 0; c < children; c++) {
if ((ret = vdev_to_nvlist_iter(child[c], search,
avail_spare, l2cache, NULL)) != NULL) {
*l2cache = B_TRUE;
return (ret);
}
}
}
return (NULL);
}
/*
* Given a physical path (minus the "/devices" prefix), find the
* associated vdev.
*/
nvlist_t *
zpool_find_vdev_by_physpath(zpool_handle_t *zhp, const char *ppath,
boolean_t *avail_spare, boolean_t *l2cache, boolean_t *log)
{
nvlist_t *search, *nvroot, *ret;
verify(nvlist_alloc(&search, NV_UNIQUE_NAME, KM_SLEEP) == 0);
verify(nvlist_add_string(search, ZPOOL_CONFIG_PHYS_PATH, ppath) == 0);
verify(nvlist_lookup_nvlist(zhp->zpool_config, ZPOOL_CONFIG_VDEV_TREE,
&nvroot) == 0);
*avail_spare = B_FALSE;
ret = vdev_to_nvlist_iter(nvroot, search, avail_spare, l2cache, log);
nvlist_free(search);
return (ret);
}
/*
* Determine if we have an "interior" top-level vdev (i.e mirror/raidz).
*/
boolean_t
zpool_vdev_is_interior(const char *name)
{
if (strncmp(name, VDEV_TYPE_RAIDZ, strlen(VDEV_TYPE_RAIDZ)) == 0 ||
strncmp(name, VDEV_TYPE_MIRROR, strlen(VDEV_TYPE_MIRROR)) == 0)
return (B_TRUE);
return (B_FALSE);
}
nvlist_t *
zpool_find_vdev(zpool_handle_t *zhp, const char *path, boolean_t *avail_spare,
boolean_t *l2cache, boolean_t *log)
{
char buf[MAXPATHLEN];
char *end;
nvlist_t *nvroot, *search, *ret;
uint64_t guid;
verify(nvlist_alloc(&search, NV_UNIQUE_NAME, KM_SLEEP) == 0);
guid = strtoull(path, &end, 10);
if (guid != 0 && *end == '\0') {
verify(nvlist_add_uint64(search, ZPOOL_CONFIG_GUID, guid) == 0);
} else if (zpool_vdev_is_interior(path)) {
verify(nvlist_add_string(search, ZPOOL_CONFIG_TYPE, path) == 0);
} else if (path[0] != '/') {
(void) snprintf(buf, sizeof (buf), "%s%s", "/dev/dsk/", path);
verify(nvlist_add_string(search, ZPOOL_CONFIG_PATH, buf) == 0);
} else {
verify(nvlist_add_string(search, ZPOOL_CONFIG_PATH, path) == 0);
}
verify(nvlist_lookup_nvlist(zhp->zpool_config, ZPOOL_CONFIG_VDEV_TREE,
&nvroot) == 0);
*avail_spare = B_FALSE;
*l2cache = B_FALSE;
if (log != NULL)
*log = B_FALSE;
ret = vdev_to_nvlist_iter(nvroot, search, avail_spare, l2cache, log);
nvlist_free(search);
return (ret);
}
static int
vdev_online(nvlist_t *nv)
{
uint64_t ival;
if (nvlist_lookup_uint64(nv, ZPOOL_CONFIG_OFFLINE, &ival) == 0 ||
nvlist_lookup_uint64(nv, ZPOOL_CONFIG_FAULTED, &ival) == 0 ||
nvlist_lookup_uint64(nv, ZPOOL_CONFIG_REMOVED, &ival) == 0)
return (0);
return (1);
}
/*
* Helper function for zpool_get_physpaths().
*/
static int
vdev_get_one_physpath(nvlist_t *config, char *physpath, size_t physpath_size,
size_t *bytes_written)
{
size_t bytes_left, pos, rsz;
char *tmppath;
const char *format;
if (nvlist_lookup_string(config, ZPOOL_CONFIG_PHYS_PATH,
&tmppath) != 0)
return (EZFS_NODEVICE);
pos = *bytes_written;
bytes_left = physpath_size - pos;
format = (pos == 0) ? "%s" : " %s";
rsz = snprintf(physpath + pos, bytes_left, format, tmppath);
*bytes_written += rsz;
if (rsz >= bytes_left) {
/* if physpath was not copied properly, clear it */
if (bytes_left != 0) {
physpath[pos] = 0;
}
return (EZFS_NOSPC);
}
return (0);
}
static int
vdev_get_physpaths(nvlist_t *nv, char *physpath, size_t phypath_size,
size_t *rsz, boolean_t is_spare)
{
char *type;
int ret;
if (nvlist_lookup_string(nv, ZPOOL_CONFIG_TYPE, &type) != 0)
return (EZFS_INVALCONFIG);
if (strcmp(type, VDEV_TYPE_DISK) == 0) {
/*
* An active spare device has ZPOOL_CONFIG_IS_SPARE set.
* For a spare vdev, we only want to boot from the active
* spare device.
*/
if (is_spare) {
uint64_t spare = 0;
(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_IS_SPARE,
&spare);
if (!spare)
return (EZFS_INVALCONFIG);
}
if (vdev_online(nv)) {
if ((ret = vdev_get_one_physpath(nv, physpath,
phypath_size, rsz)) != 0)
return (ret);
}
} else if (strcmp(type, VDEV_TYPE_MIRROR) == 0 ||
strcmp(type, VDEV_TYPE_REPLACING) == 0 ||
(is_spare = (strcmp(type, VDEV_TYPE_SPARE) == 0))) {
nvlist_t **child;
uint_t count;
int i, ret;
if (nvlist_lookup_nvlist_array(nv,
ZPOOL_CONFIG_CHILDREN, &child, &count) != 0)
return (EZFS_INVALCONFIG);
for (i = 0; i < count; i++) {
ret = vdev_get_physpaths(child[i], physpath,
phypath_size, rsz, is_spare);
if (ret == EZFS_NOSPC)
return (ret);
}
}
return (EZFS_POOL_INVALARG);
}
/*
* Get phys_path for a root pool config.
* Return 0 on success; non-zero on failure.
*/
static int
zpool_get_config_physpath(nvlist_t *config, char *physpath, size_t phypath_size)
{
size_t rsz;
nvlist_t *vdev_root;
nvlist_t **child;
uint_t count;
char *type;
rsz = 0;
if (nvlist_lookup_nvlist(config, ZPOOL_CONFIG_VDEV_TREE,
&vdev_root) != 0)
return (EZFS_INVALCONFIG);
if (nvlist_lookup_string(vdev_root, ZPOOL_CONFIG_TYPE, &type) != 0 ||
nvlist_lookup_nvlist_array(vdev_root, ZPOOL_CONFIG_CHILDREN,
&child, &count) != 0)
return (EZFS_INVALCONFIG);
/*
* root pool can not have EFI labeled disks and can only have
* a single top-level vdev.
*/
#if 0
if (strcmp(type, VDEV_TYPE_ROOT) != 0 || count != 1 ||
pool_uses_efi(vdev_root))
return (EZFS_POOL_INVALARG);
#endif
(void) vdev_get_physpaths(child[0], physpath, phypath_size, &rsz,
B_FALSE);
/* No online devices */
if (rsz == 0)
return (EZFS_NODEVICE);
return (0);
}
/*
* Get phys_path for a root pool
* Return 0 on success; non-zero on failure.
*/
int
zpool_get_physpath(zpool_handle_t *zhp, char *physpath, size_t phypath_size)
{
return (zpool_get_config_physpath(zhp->zpool_config, physpath,
phypath_size));
}
/*
* If the device has being dynamically expanded then we need to relabel
* the disk to use the new unallocated space.
*/
static int
zpool_relabel_disk(libzfs_handle_t *hdl, const char *name)
{
char path[MAXPATHLEN];
char errbuf[1024];
int fd, error;
int (*_efi_use_whole_disk)(int);
if ((_efi_use_whole_disk = (int (*)(int))dlsym(RTLD_DEFAULT,
"efi_use_whole_disk")) == NULL)
return (-1);
(void) snprintf(path, sizeof (path), "%s/%s", RDISK_ROOT, name);
if ((fd = open(path, O_RDWR | O_NDELAY)) < 0) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "cannot "
"relabel '%s': unable to open device"), name);
return (zfs_error(hdl, EZFS_OPENFAILED, errbuf));
}
/*
* It's possible that we might encounter an error if the device
* does not have any unallocated space left. If so, we simply
* ignore that error and continue on.
*/
/* zfs-fuse : no efi function here, this should be fixed later if
* possible...
* error = _efi_use_whole_disk(fd); */
(void) close(fd);
/* if (error && error != VT_ENOSPC) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "cannot "
"relabel '%s': unable to read disk capacity"), name);
return (zfs_error(hdl, EZFS_NOCAP, errbuf));
} */
return (0);
}
/*
* Bring the specified vdev online. The 'flags' parameter is a set of the
* ZFS_ONLINE_* flags.
*/
int
zpool_vdev_online(zpool_handle_t *zhp, const char *path, int flags,
vdev_state_t *newstate)
{
zfs_cmd_t zc = { 0 };
char msg[1024];
nvlist_t *tgt;
boolean_t avail_spare, l2cache, islog;
libzfs_handle_t *hdl = zhp->zpool_hdl;
if (flags & ZFS_ONLINE_EXPAND) {
(void) snprintf(msg, sizeof (msg),
dgettext(TEXT_DOMAIN, "cannot expand %s"), path);
} else {
(void) snprintf(msg, sizeof (msg),
dgettext(TEXT_DOMAIN, "cannot online %s"), path);
}
(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
if ((tgt = zpool_find_vdev(zhp, path, &avail_spare, &l2cache,
&islog)) == NULL)
return (zfs_error(hdl, EZFS_NODEVICE, msg));
verify(nvlist_lookup_uint64(tgt, ZPOOL_CONFIG_GUID, &zc.zc_guid) == 0);
if (avail_spare)
return (zfs_error(hdl, EZFS_ISSPARE, msg));
if (flags & ZFS_ONLINE_EXPAND ||
zpool_get_prop_int(zhp, ZPOOL_PROP_AUTOEXPAND, NULL)) {
char *pathname = NULL;
uint64_t wholedisk = 0;
(void) nvlist_lookup_uint64(tgt, ZPOOL_CONFIG_WHOLE_DISK,
&wholedisk);
verify(nvlist_lookup_string(tgt, ZPOOL_CONFIG_PATH,
&pathname) == 0);
/*
* XXX - L2ARC 1.0 devices can't support expansion.
*/
if (l2cache) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"cannot expand cache devices"));
return (zfs_error(hdl, EZFS_VDEVNOTSUP, msg));
}
if (wholedisk) {
pathname += strlen(DISK_ROOT) + 1;
(void) zpool_relabel_disk(zhp->zpool_hdl, pathname);
}
}
zc.zc_cookie = VDEV_STATE_ONLINE;
zc.zc_obj = flags;
if (zfs_ioctl(zhp->zpool_hdl, ZFS_IOC_VDEV_SET_STATE, &zc) != 0) {
if (errno == EINVAL) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "was split "
"from this pool into a new one. Use '%s' "
"instead"), "zpool detach");
return (zfs_error(hdl, EZFS_POSTSPLIT_ONLINE, msg));
}
return (zpool_standard_error(hdl, errno, msg));
}
*newstate = zc.zc_cookie;
return (0);
}
/*
* Take the specified vdev offline
*/
int
zpool_vdev_offline(zpool_handle_t *zhp, const char *path, boolean_t istmp)
{
zfs_cmd_t zc = { 0 };
char msg[1024];
nvlist_t *tgt;
boolean_t avail_spare, l2cache;
libzfs_handle_t *hdl = zhp->zpool_hdl;
(void) snprintf(msg, sizeof (msg),
dgettext(TEXT_DOMAIN, "cannot offline %s"), path);
(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
if ((tgt = zpool_find_vdev(zhp, path, &avail_spare, &l2cache,
NULL)) == NULL)
return (zfs_error(hdl, EZFS_NODEVICE, msg));
verify(nvlist_lookup_uint64(tgt, ZPOOL_CONFIG_GUID, &zc.zc_guid) == 0);
if (avail_spare)
return (zfs_error(hdl, EZFS_ISSPARE, msg));
zc.zc_cookie = VDEV_STATE_OFFLINE;
zc.zc_obj = istmp ? ZFS_OFFLINE_TEMPORARY : 0;
if (zfs_ioctl(zhp->zpool_hdl, ZFS_IOC_VDEV_SET_STATE, &zc) == 0)
return (0);
switch (errno) {
case EBUSY:
/*
* There are no other replicas of this device.
*/
return (zfs_error(hdl, EZFS_NOREPLICAS, msg));
case EEXIST:
/*
* The log device has unplayed logs
*/
return (zfs_error(hdl, EZFS_UNPLAYED_LOGS, msg));
default:
return (zpool_standard_error(hdl, errno, msg));
}
}
/*
* Mark the given vdev faulted.
*/
int
zpool_vdev_fault(zpool_handle_t *zhp, uint64_t guid, vdev_aux_t aux)
{
zfs_cmd_t zc = { 0 };
char msg[1024];
libzfs_handle_t *hdl = zhp->zpool_hdl;
(void) snprintf(msg, sizeof (msg),
dgettext(TEXT_DOMAIN, "cannot fault %llu"), (u_longlong_t) guid);
(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
zc.zc_guid = guid;
zc.zc_cookie = VDEV_STATE_FAULTED;
zc.zc_obj = aux;
if (ioctl(zhp->zpool_hdl->libzfs_fd, ZFS_IOC_VDEV_SET_STATE, &zc) == 0)
return (0);
switch (errno) {
case EBUSY:
/*
* There are no other replicas of this device.
*/
return (zfs_error(hdl, EZFS_NOREPLICAS, msg));
default:
return (zpool_standard_error(hdl, errno, msg));
}
}
/*
* Mark the given vdev degraded.
*/
int
zpool_vdev_degrade(zpool_handle_t *zhp, uint64_t guid, vdev_aux_t aux)
{
zfs_cmd_t zc = { 0 };
char msg[1024];
libzfs_handle_t *hdl = zhp->zpool_hdl;
(void) snprintf(msg, sizeof (msg),
dgettext(TEXT_DOMAIN, "cannot degrade %llu"), (u_longlong_t) guid);
(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
zc.zc_guid = guid;
zc.zc_cookie = VDEV_STATE_DEGRADED;
zc.zc_obj = aux;
if (ioctl(zhp->zpool_hdl->libzfs_fd, ZFS_IOC_VDEV_SET_STATE, &zc) == 0)
return (0);
return (zpool_standard_error(hdl, errno, msg));
}
/*
* Returns TRUE if the given nvlist is a vdev that was originally swapped in as
* a hot spare.
*/
static boolean_t
is_replacing_spare(nvlist_t *search, nvlist_t *tgt, int which)
{
nvlist_t **child;
uint_t c, children;
char *type;
if (nvlist_lookup_nvlist_array(search, ZPOOL_CONFIG_CHILDREN, &child,
&children) == 0) {
verify(nvlist_lookup_string(search, ZPOOL_CONFIG_TYPE,
&type) == 0);
if (strcmp(type, VDEV_TYPE_SPARE) == 0 &&
children == 2 && child[which] == tgt)
return (B_TRUE);
for (c = 0; c < children; c++)
if (is_replacing_spare(child[c], tgt, which))
return (B_TRUE);
}
return (B_FALSE);
}
/*
* Attach new_disk (fully described by nvroot) to old_disk.
* If 'replacing' is specified, the new disk will replace the old one.
*/
int
zpool_vdev_attach(zpool_handle_t *zhp,
const char *old_disk, const char *new_disk, nvlist_t *nvroot, int replacing)
{
zfs_cmd_t zc = { 0 };
char msg[1024];
int ret;
nvlist_t *tgt;
boolean_t avail_spare, l2cache, islog;
uint64_t val;
char *path, *newname;
nvlist_t **child;
uint_t children;
nvlist_t *config_root;
libzfs_handle_t *hdl = zhp->zpool_hdl;
boolean_t rootpool = pool_is_bootable(zhp);
if (replacing)
(void) snprintf(msg, sizeof (msg), dgettext(TEXT_DOMAIN,
"cannot replace %s with %s"), old_disk, new_disk);
else
(void) snprintf(msg, sizeof (msg), dgettext(TEXT_DOMAIN,
"cannot attach %s to %s"), new_disk, old_disk);
/*
* If this is a root pool, make sure that we're not attaching an
* EFI labeled device.
*/
#if 0
if (rootpool && pool_uses_efi(nvroot)) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"EFI labeled devices are not supported on root pools."));
return (zfs_error(hdl, EZFS_POOL_NOTSUP, msg));
}
#endif
(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
if ((tgt = zpool_find_vdev(zhp, old_disk, &avail_spare, &l2cache,
&islog)) == 0)
return (zfs_error(hdl, EZFS_NODEVICE, msg));
if (avail_spare)
return (zfs_error(hdl, EZFS_ISSPARE, msg));
if (l2cache)
return (zfs_error(hdl, EZFS_ISL2CACHE, msg));
verify(nvlist_lookup_uint64(tgt, ZPOOL_CONFIG_GUID, &zc.zc_guid) == 0);
zc.zc_cookie = replacing;
if (nvlist_lookup_nvlist_array(nvroot, ZPOOL_CONFIG_CHILDREN,
&child, &children) != 0 || children != 1) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"new device must be a single disk"));
return (zfs_error(hdl, EZFS_INVALCONFIG, msg));
}
verify(nvlist_lookup_nvlist(zpool_get_config(zhp, NULL),
ZPOOL_CONFIG_VDEV_TREE, &config_root) == 0);
if ((newname = zpool_vdev_name(NULL, NULL, child[0], B_FALSE)) == NULL)
return (-1);
/*
* If the target is a hot spare that has been swapped in, we can only
* replace it with another hot spare.
*/
if (replacing &&
nvlist_lookup_uint64(tgt, ZPOOL_CONFIG_IS_SPARE, &val) == 0 &&
(zpool_find_vdev(zhp, newname, &avail_spare, &l2cache,
NULL) == NULL || !avail_spare) &&
is_replacing_spare(config_root, tgt, 1)) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"can only be replaced by another hot spare"));
free(newname);
return (zfs_error(hdl, EZFS_BADTARGET, msg));
}
/*
* If we are attempting to replace a spare, it canot be applied to an
* already spared device.
*/
if (replacing &&
nvlist_lookup_string(child[0], ZPOOL_CONFIG_PATH, &path) == 0 &&
zpool_find_vdev(zhp, newname, &avail_spare,
&l2cache, NULL) != NULL && avail_spare &&
is_replacing_spare(config_root, tgt, 0)) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"device has already been replaced with a spare"));
free(newname);
return (zfs_error(hdl, EZFS_BADTARGET, msg));
}
free(newname);
if (zcmd_write_conf_nvlist(hdl, &zc, nvroot) != 0)
return (-1);
ret = zfs_ioctl(zhp->zpool_hdl, ZFS_IOC_VDEV_ATTACH, &zc);
zcmd_free_nvlists(&zc);
if (ret == 0) {
if (rootpool) {
/*
* XXX - This should be removed once we can
* automatically install the bootblocks on the
* newly attached disk.
*/
(void) fprintf(stderr, dgettext(TEXT_DOMAIN, "Please "
"be sure to invoke %s to make '%s' bootable.\n"),
BOOTCMD, new_disk);
/*
* XXX need a better way to prevent user from
* booting up a half-baked vdev.
*/
(void) fprintf(stderr, dgettext(TEXT_DOMAIN, "Make "
"sure to wait until resilver is done "
"before rebooting.\n"));
}
return (0);
}
switch (errno) {
case ENOTSUP:
/*
* Can't attach to or replace this type of vdev.
*/
if (replacing) {
if (islog)
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"cannot replace a log with a spare"));
else
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"cannot replace a replacing device"));
} else {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"can only attach to mirrors and top-level "
"disks"));
}
(void) zfs_error(hdl, EZFS_BADTARGET, msg);
break;
case EINVAL:
/*
* The new device must be a single disk.
*/
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"new device must be a single disk"));
(void) zfs_error(hdl, EZFS_INVALCONFIG, msg);
break;
case EBUSY:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "%s is busy"),
new_disk);
(void) zfs_error(hdl, EZFS_BADDEV, msg);
break;
case EOVERFLOW:
/*
* The new device is too small.
*/
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"device is too small"));
(void) zfs_error(hdl, EZFS_BADDEV, msg);
break;
case EDOM:
/*
* The new device has a different alignment requirement.
*/
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"devices have different sector alignment"));
(void) zfs_error(hdl, EZFS_BADDEV, msg);
break;
case ENAMETOOLONG:
/*
* The resulting top-level vdev spec won't fit in the label.
*/
(void) zfs_error(hdl, EZFS_DEVOVERFLOW, msg);
break;
default:
(void) zpool_standard_error(hdl, errno, msg);
}
return (-1);
}
/*
* Detach the specified device.
*/
int
zpool_vdev_detach(zpool_handle_t *zhp, const char *path)
{
zfs_cmd_t zc = { 0 };
char msg[1024];
nvlist_t *tgt;
boolean_t avail_spare, l2cache;
libzfs_handle_t *hdl = zhp->zpool_hdl;
(void) snprintf(msg, sizeof (msg),
dgettext(TEXT_DOMAIN, "cannot detach %s"), path);
(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
if ((tgt = zpool_find_vdev(zhp, path, &avail_spare, &l2cache,
NULL)) == 0)
return (zfs_error(hdl, EZFS_NODEVICE, msg));
if (avail_spare)
return (zfs_error(hdl, EZFS_ISSPARE, msg));
if (l2cache)
return (zfs_error(hdl, EZFS_ISL2CACHE, msg));
verify(nvlist_lookup_uint64(tgt, ZPOOL_CONFIG_GUID, &zc.zc_guid) == 0);
if (zfs_ioctl(hdl, ZFS_IOC_VDEV_DETACH, &zc) == 0)
return (0);
switch (errno) {
case ENOTSUP:
/*
* Can't detach from this type of vdev.
*/
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "only "
"applicable to mirror and replacing vdevs"));
(void) zfs_error(zhp->zpool_hdl, EZFS_BADTARGET, msg);
break;
case EBUSY:
/*
* There are no other replicas of this device.
*/
(void) zfs_error(hdl, EZFS_NOREPLICAS, msg);
break;
default:
(void) zpool_standard_error(hdl, errno, msg);
}
return (-1);
}
/*
* Find a mirror vdev in the source nvlist.
*
* The mchild array contains a list of disks in one of the top-level mirrors
* of the source pool. The schild array contains a list of disks that the
* user specified on the command line. We loop over the mchild array to
* see if any entry in the schild array matches.
*
* If a disk in the mchild array is found in the schild array, we return
* the index of that entry. Otherwise we return -1.
*/
static int
find_vdev_entry(zpool_handle_t *zhp, nvlist_t **mchild, uint_t mchildren,
nvlist_t **schild, uint_t schildren)
{
uint_t mc;
for (mc = 0; mc < mchildren; mc++) {
uint_t sc;
char *mpath = zpool_vdev_name(zhp->zpool_hdl, zhp,
mchild[mc], B_FALSE);
for (sc = 0; sc < schildren; sc++) {
char *spath = zpool_vdev_name(zhp->zpool_hdl, zhp,
schild[sc], B_FALSE);
boolean_t result = (strcmp(mpath, spath) == 0);
free(spath);
if (result) {
free(mpath);
return (mc);
}
}
free(mpath);
}
return (-1);
}
/*
* Split a mirror pool. If newroot points to null, then a new nvlist
* is generated and it is the responsibility of the caller to free it.
*/
int
zpool_vdev_split(zpool_handle_t *zhp, char *newname, nvlist_t **newroot,
nvlist_t *props, splitflags_t flags)
{
zfs_cmd_t zc = { 0 };
char msg[1024];
nvlist_t *tree, *config, **child, **newchild, *newconfig = NULL;
nvlist_t **varray = NULL, *zc_props = NULL;
uint_t c, children, newchildren, lastlog = 0, vcount, found = 0;
libzfs_handle_t *hdl = zhp->zpool_hdl;
uint64_t vers;
boolean_t freelist = B_FALSE, memory_err = B_TRUE;
int retval = 0;
(void) snprintf(msg, sizeof (msg),
dgettext(TEXT_DOMAIN, "Unable to split %s"), zhp->zpool_name);
if (!zpool_name_valid(hdl, B_FALSE, newname))
return (zfs_error(hdl, EZFS_INVALIDNAME, msg));
if ((config = zpool_get_config(zhp, NULL)) == NULL) {
(void) fprintf(stderr, gettext("Internal error: unable to "
"retrieve pool configuration\n"));
return (-1);
}
verify(nvlist_lookup_nvlist(config, ZPOOL_CONFIG_VDEV_TREE, &tree)
== 0);
verify(nvlist_lookup_uint64(config, ZPOOL_CONFIG_VERSION, &vers) == 0);
if (props) {
if ((zc_props = zpool_valid_proplist(hdl, zhp->zpool_name,
props, vers, B_TRUE, msg)) == NULL)
return (-1);
}
if (nvlist_lookup_nvlist_array(tree, ZPOOL_CONFIG_CHILDREN, &child,
&children) != 0) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"Source pool is missing vdev tree"));
if (zc_props)
nvlist_free(zc_props);
return (-1);
}
varray = zfs_alloc(hdl, children * sizeof (nvlist_t *));
vcount = 0;
if (*newroot == NULL ||
nvlist_lookup_nvlist_array(*newroot, ZPOOL_CONFIG_CHILDREN,
&newchild, &newchildren) != 0)
newchildren = 0;
for (c = 0; c < children; c++) {
uint64_t is_log = B_FALSE, is_hole = B_FALSE;
char *type;
nvlist_t **mchild, *vdev;
uint_t mchildren;
int entry;
/*
* Unlike cache & spares, slogs are stored in the
* ZPOOL_CONFIG_CHILDREN array. We filter them out here.
*/
(void) nvlist_lookup_uint64(child[c], ZPOOL_CONFIG_IS_LOG,
&is_log);
(void) nvlist_lookup_uint64(child[c], ZPOOL_CONFIG_IS_HOLE,
&is_hole);
if (is_log || is_hole) {
/*
* Create a hole vdev and put it in the config.
*/
if (nvlist_alloc(&vdev, NV_UNIQUE_NAME, 0) != 0)
goto out;
if (nvlist_add_string(vdev, ZPOOL_CONFIG_TYPE,
VDEV_TYPE_HOLE) != 0)
goto out;
if (nvlist_add_uint64(vdev, ZPOOL_CONFIG_IS_HOLE,
1) != 0)
goto out;
if (lastlog == 0)
lastlog = vcount;
varray[vcount++] = vdev;
continue;
}
lastlog = 0;
verify(nvlist_lookup_string(child[c], ZPOOL_CONFIG_TYPE, &type)
== 0);
if (strcmp(type, VDEV_TYPE_MIRROR) != 0) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"Source pool must be composed only of mirrors\n"));
retval = zfs_error(hdl, EZFS_INVALCONFIG, msg);
goto out;
}
verify(nvlist_lookup_nvlist_array(child[c],
ZPOOL_CONFIG_CHILDREN, &mchild, &mchildren) == 0);
/* find or add an entry for this top-level vdev */
if (newchildren > 0 &&
(entry = find_vdev_entry(zhp, mchild, mchildren,
newchild, newchildren)) >= 0) {
/* We found a disk that the user specified. */
vdev = mchild[entry];
++found;
} else {
/* User didn't specify a disk for this vdev. */
vdev = mchild[mchildren - 1];
}
if (nvlist_dup(vdev, &varray[vcount++], 0) != 0)
goto out;
}
/* did we find every disk the user specified? */
if (found != newchildren) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "Device list must "
"include at most one disk from each mirror"));
retval = zfs_error(hdl, EZFS_INVALCONFIG, msg);
goto out;
}
/* Prepare the nvlist for populating. */
if (*newroot == NULL) {
if (nvlist_alloc(newroot, NV_UNIQUE_NAME, 0) != 0)
goto out;
freelist = B_TRUE;
if (nvlist_add_string(*newroot, ZPOOL_CONFIG_TYPE,
VDEV_TYPE_ROOT) != 0)
goto out;
} else {
verify(nvlist_remove_all(*newroot, ZPOOL_CONFIG_CHILDREN) == 0);
}
/* Add all the children we found */
if (nvlist_add_nvlist_array(*newroot, ZPOOL_CONFIG_CHILDREN, varray,
lastlog == 0 ? vcount : lastlog) != 0)
goto out;
/*
* If we're just doing a dry run, exit now with success.
*/
if (flags.dryrun) {
memory_err = B_FALSE;
freelist = B_FALSE;
goto out;
}
/* now build up the config list & call the ioctl */
if (nvlist_alloc(&newconfig, NV_UNIQUE_NAME, 0) != 0)
goto out;
if (nvlist_add_nvlist(newconfig,
ZPOOL_CONFIG_VDEV_TREE, *newroot) != 0 ||
nvlist_add_string(newconfig,
ZPOOL_CONFIG_POOL_NAME, newname) != 0 ||
nvlist_add_uint64(newconfig, ZPOOL_CONFIG_VERSION, vers) != 0)
goto out;
/*
* The new pool is automatically part of the namespace unless we
* explicitly export it.
*/
if (!flags.import)
zc.zc_cookie = ZPOOL_EXPORT_AFTER_SPLIT;
(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
(void) strlcpy(zc.zc_string, newname, sizeof (zc.zc_string));
if (zcmd_write_conf_nvlist(hdl, &zc, newconfig) != 0)
goto out;
if (zc_props != NULL && zcmd_write_src_nvlist(hdl, &zc, zc_props) != 0)
goto out;
if (zfs_ioctl(hdl, ZFS_IOC_VDEV_SPLIT, &zc) != 0) {
retval = zpool_standard_error(hdl, errno, msg);
goto out;
}
freelist = B_FALSE;
memory_err = B_FALSE;
out:
if (varray != NULL) {
int v;
for (v = 0; v < vcount; v++)
nvlist_free(varray[v]);
free(varray);
}
zcmd_free_nvlists(&zc);
if (zc_props)
nvlist_free(zc_props);
if (newconfig)
nvlist_free(newconfig);
if (freelist) {
nvlist_free(*newroot);
*newroot = NULL;
}
if (retval != 0)
return (retval);
if (memory_err)
return (no_memory(hdl));
return (0);
}
/*
* Remove the given device. Currently, this is supported only for hot spares
* and level 2 cache devices.
*/
int
zpool_vdev_remove(zpool_handle_t *zhp, const char *path)
{
zfs_cmd_t zc = { 0 };
char msg[1024];
nvlist_t *tgt;
boolean_t avail_spare, l2cache, islog;
libzfs_handle_t *hdl = zhp->zpool_hdl;
uint64_t version;
(void) snprintf(msg, sizeof (msg),
dgettext(TEXT_DOMAIN, "cannot remove %s"), path);
(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
if ((tgt = zpool_find_vdev(zhp, path, &avail_spare, &l2cache,
&islog)) == 0)
return (zfs_error(hdl, EZFS_NODEVICE, msg));
/*
* XXX - this should just go away.
*/
if (!avail_spare && !l2cache && !islog) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"only inactive hot spares, cache, top-level, "
"or log devices can be removed"));
return (zfs_error(hdl, EZFS_NODEVICE, msg));
}
version = zpool_get_prop_int(zhp, ZPOOL_PROP_VERSION, NULL);
if (islog && version < SPA_VERSION_HOLES) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"pool must be upgrade to support log removal"));
return (zfs_error(hdl, EZFS_BADVERSION, msg));
}
verify(nvlist_lookup_uint64(tgt, ZPOOL_CONFIG_GUID, &zc.zc_guid) == 0);
if (zfs_ioctl(hdl, ZFS_IOC_VDEV_REMOVE, &zc) == 0)
return (0);
return (zpool_standard_error(hdl, errno, msg));
}
/*
* Clear the errors for the pool, or the particular device if specified.
*/
int
zpool_clear(zpool_handle_t *zhp, const char *path, nvlist_t *rewindnvl)
{
zfs_cmd_t zc = { 0 };
char msg[1024];
nvlist_t *tgt;
zpool_rewind_policy_t policy;
boolean_t avail_spare, l2cache;
libzfs_handle_t *hdl = zhp->zpool_hdl;
nvlist_t *nvi = NULL;
if (path)
(void) snprintf(msg, sizeof (msg),
dgettext(TEXT_DOMAIN, "cannot clear errors for %s"),
path);
else
(void) snprintf(msg, sizeof (msg),
dgettext(TEXT_DOMAIN, "cannot clear errors for %s"),
zhp->zpool_name);
(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
if (path) {
if ((tgt = zpool_find_vdev(zhp, path, &avail_spare,
&l2cache, NULL)) == 0)
return (zfs_error(hdl, EZFS_NODEVICE, msg));
/*
* Don't allow error clearing for hot spares. Do allow
* error clearing for l2cache devices.
*/
if (avail_spare)
return (zfs_error(hdl, EZFS_ISSPARE, msg));
verify(nvlist_lookup_uint64(tgt, ZPOOL_CONFIG_GUID,
&zc.zc_guid) == 0);
}
zpool_get_rewind_policy(rewindnvl, &policy);
zc.zc_cookie = policy.zrp_request;
if (zcmd_alloc_dst_nvlist(hdl, &zc, 8192) != 0)
return (-1);
if (zcmd_write_src_nvlist(zhp->zpool_hdl, &zc, rewindnvl) != 0)
return (-1);
if (zfs_ioctl(hdl, ZFS_IOC_CLEAR, &zc) == 0 ||
((policy.zrp_request & ZPOOL_TRY_REWIND) &&
errno != EPERM && errno != EACCES)) {
if (policy.zrp_request &
(ZPOOL_DO_REWIND | ZPOOL_TRY_REWIND)) {
(void) zcmd_read_dst_nvlist(hdl, &zc, &nvi);
zpool_rewind_exclaim(hdl, zc.zc_name,
((policy.zrp_request & ZPOOL_TRY_REWIND) != 0),
nvi);
nvlist_free(nvi);
}
zcmd_free_nvlists(&zc);
return (0);
}
zcmd_free_nvlists(&zc);
return (zpool_standard_error(hdl, errno, msg));
}
/*
* Similar to zpool_clear(), but takes a GUID (used by fmd).
*/
int
zpool_vdev_clear(zpool_handle_t *zhp, uint64_t guid)
{
zfs_cmd_t zc = { 0 };
char msg[1024];
libzfs_handle_t *hdl = zhp->zpool_hdl;
(void) snprintf(msg, sizeof (msg),
dgettext(TEXT_DOMAIN, "cannot clear errors for %llx"),
(longlong_t) guid);
(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
zc.zc_guid = guid;
if (ioctl(hdl->libzfs_fd, ZFS_IOC_CLEAR, &zc) == 0)
return (0);
return (zpool_standard_error(hdl, errno, msg));
}
/*
* Convert from a devid string to a path.
*/
static char *
devid_to_path(char *devid_str)
{
ddi_devid_t devid;
char *minor;
char *path;
devid_nmlist_t *list = NULL;
int ret;
if (devid_str_decode(devid_str, &devid, &minor) != 0)
return (NULL);
ret = devid_deviceid_to_nmlist("/dev", devid, minor, &list);
devid_str_free(minor);
devid_free(devid);
if (ret != 0)
return (NULL);
if ((path = strdup(list[0].devname)) == NULL)
return (NULL);
devid_free_nmlist(list);
return (path);
}
/*
* Convert from a path to a devid string.
*/
static char *
path_to_devid(const char *path)
{
int fd;
ddi_devid_t devid;
char *minor, *ret;
if ((fd = open(path, O_RDONLY)) < 0)
return (NULL);
minor = NULL;
ret = NULL;
if (devid_get(fd, &devid) == 0) {
if (devid_get_minor_name(fd, &minor) == 0)
ret = devid_str_encode(devid, minor);
if (minor != NULL)
devid_str_free(minor);
devid_free(devid);
}