*/
/*
- * Copyright 2009 Sun Microsystems, Inc. All rights reserved.
- * Use is subject to license terms.
+ * Copyright 2015 Nexenta Systems, Inc. All rights reserved.
+ * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2011, 2014 by Delphix. All rights reserved.
*/
-#include <alloca.h>
-#include <assert.h>
#include <ctype.h>
#include <errno.h>
#include <devid.h>
-#include <dirent.h>
#include <fcntl.h>
#include <libintl.h>
#include <stdio.h>
#include <stdlib.h>
#include <strings.h>
#include <unistd.h>
+#include <libgen.h>
#include <zone.h>
+#include <sys/stat.h>
#include <sys/efi_partition.h>
#include <sys/vtoc.h>
#include <sys/zfs_ioctl.h>
-#include <sys/zio.h>
-#include <strings.h>
#include <dlfcn.h>
#include "zfs_namecheck.h"
#include "zfs_prop.h"
#include "libzfs_impl.h"
+#include "zfs_comutil.h"
+#include "zfeature_common.h"
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/dsk"
-#define RDISK_ROOT "/dev/rdsk"
-#define BACKUP_SLICE "s2"
+typedef struct prop_flags {
+ int create:1; /* Validate property on creation */
+ int import:1; /* Validate property on import */
+} prop_flags_t;
/*
* ====================================================================
static int
zpool_get_all_props(zpool_handle_t *zhp)
{
- zfs_cmd_t zc = { 0 };
+ zfs_cmd_t zc = {"\0"};
libzfs_handle_t *hdl = zhp->zpool_hdl;
(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
zpool_state_to_name(vdev_state_t state, vdev_aux_t aux)
{
switch (state) {
+ default:
+ break;
case VDEV_STATE_CLOSED:
case VDEV_STATE_OFFLINE:
return (gettext("OFFLINE"));
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("UNKNOWN"));
}
+/*
+ * Map POOL STATE to printed strings.
+ */
+const char *
+zpool_pool_state_to_name(pool_state_t state)
+{
+ switch (state) {
+ default:
+ break;
+ case POOL_STATE_ACTIVE:
+ return (gettext("ACTIVE"));
+ case POOL_STATE_EXPORTED:
+ return (gettext("EXPORTED"));
+ case POOL_STATE_DESTROYED:
+ return (gettext("DESTROYED"));
+ case POOL_STATE_SPARE:
+ return (gettext("SPARE"));
+ case POOL_STATE_L2CACHE:
+ return (gettext("L2CACHE"));
+ case POOL_STATE_UNINITIALIZED:
+ return (gettext("UNINITIALIZED"));
+ case POOL_STATE_UNAVAIL:
+ return (gettext("UNAVAIL"));
+ case POOL_STATE_POTENTIALLY_ACTIVE:
+ return (gettext("POTENTIALLY_ACTIVE"));
+ }
+
+ 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)
+zpool_get_prop(zpool_handle_t *zhp, zpool_prop_t prop, char *buf,
+ size_t len, zprop_source_t *srctype, boolean_t literal)
{
uint64_t intval;
const char *strval;
case ZPOOL_PROP_GUID:
intval = zpool_get_prop_int(zhp, prop, &src);
- (void) snprintf(buf, len, "%llu", intval);
+ (void) snprintf(buf, len, "%llu", (u_longlong_t)intval);
break;
case ZPOOL_PROP_ALTROOT:
case ZPOOL_PROP_CACHEFILE:
+ case ZPOOL_PROP_COMMENT:
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);
+ break;
}
/* FALLTHROUGH */
default:
switch (prop) {
case ZPOOL_PROP_SIZE:
- case ZPOOL_PROP_USED:
- case ZPOOL_PROP_AVAILABLE:
- (void) zfs_nicenum(intval, buf, len);
+ case ZPOOL_PROP_ALLOCATED:
+ case ZPOOL_PROP_FREE:
+ case ZPOOL_PROP_FREEING:
+ case ZPOOL_PROP_LEAKED:
+ case ZPOOL_PROP_ASHIFT:
+ if (literal)
+ (void) snprintf(buf, len, "%llu",
+ (u_longlong_t)intval);
+ else
+ (void) zfs_nicenum(intval, buf, len);
+ break;
+
+ case ZPOOL_PROP_EXPANDSZ:
+ if (intval == 0) {
+ (void) strlcpy(buf, "-", len);
+ } else if (literal) {
+ (void) snprintf(buf, len, "%llu",
+ (u_longlong_t)intval);
+ } else {
+ (void) zfs_nicenum(intval, buf, len);
+ }
break;
case ZPOOL_PROP_CAPACITY:
- (void) snprintf(buf, len, "%llu%%",
- (u_longlong_t)intval);
+ if (literal) {
+ (void) snprintf(buf, len, "%llu",
+ (u_longlong_t)intval);
+ } else {
+ (void) snprintf(buf, len, "%llu%%",
+ (u_longlong_t)intval);
+ }
+ break;
+
+ case ZPOOL_PROP_FRAGMENTATION:
+ if (intval == UINT64_MAX) {
+ (void) strlcpy(buf, "-", len);
+ } else if (literal) {
+ (void) snprintf(buf, len, "%llu",
+ (u_longlong_t)intval);
+ } else {
+ (void) snprintf(buf, len, "%llu%%",
+ (u_longlong_t)intval);
+ }
+ break;
+
+ case ZPOOL_PROP_DEDUPRATIO:
+ if (literal)
+ (void) snprintf(buf, len, "%llu.%02llu",
+ (u_longlong_t)(intval / 100),
+ (u_longlong_t)(intval % 100));
+ else
+ (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);
+ ZPOOL_CONFIG_VDEV_STATS, (uint64_t **)&vs, &vsc)
+ == 0);
(void) strlcpy(buf, zpool_state_to_name(intval,
vs->vs_aux), len);
break;
+ case ZPOOL_PROP_VERSION:
+ if (intval >= SPA_VERSION_FEATURES) {
+ (void) snprintf(buf, len, "-");
+ break;
+ }
+ /* FALLTHROUGH */
default:
- (void) snprintf(buf, len, "%llu", intval);
+ (void) snprintf(buf, len, "%llu", (u_longlong_t)intval);
}
break;
return (B_FALSE);
}
+#if defined(__sun__) || defined(__sun)
/*
* Inspect the configuration to determine if any of the devices contain
* an EFI label.
}
return (B_FALSE);
}
+#endif
-static boolean_t
-pool_is_bootable(zpool_handle_t *zhp)
+boolean_t
+zpool_is_bootable(zpool_handle_t *zhp)
{
- char bootfs[ZPOOL_MAXNAMELEN];
+ char bootfs[ZFS_MAX_DATASET_NAME_LEN];
return (zpool_get_prop(zhp, ZPOOL_PROP_BOOTFS, bootfs,
- sizeof (bootfs), NULL) == 0 && strncmp(bootfs, "-",
+ sizeof (bootfs), NULL, B_FALSE) == 0 && strncmp(bootfs, "-",
sizeof (bootfs)) != 0);
}
*/
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)
+ nvlist_t *props, uint64_t version, prop_flags_t flags, char *errbuf)
{
nvpair_t *elem;
nvlist_t *retprops;
zpool_prop_t prop;
char *strval;
uint64_t intval;
- char *slash;
+ char *slash, *check;
struct stat64 statbuf;
zpool_handle_t *zhp;
nvlist_t *nvroot;
while ((elem = nvlist_next_nvpair(props, elem)) != NULL) {
const char *propname = nvpair_name(elem);
+ prop = zpool_name_to_prop(propname);
+ if (prop == ZPROP_INVAL && zpool_prop_feature(propname)) {
+ int err;
+ char *fname = strchr(propname, '@') + 1;
+
+ err = zfeature_lookup_name(fname, NULL);
+ if (err != 0) {
+ ASSERT3U(err, ==, ENOENT);
+ zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
+ "invalid feature '%s'"), fname);
+ (void) zfs_error(hdl, EZFS_BADPROP, errbuf);
+ goto error;
+ }
+
+ if (nvpair_type(elem) != DATA_TYPE_STRING) {
+ zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
+ "'%s' must be a string"), propname);
+ (void) zfs_error(hdl, EZFS_BADPROP, errbuf);
+ goto error;
+ }
+
+ (void) nvpair_value_string(elem, &strval);
+ if (strcmp(strval, ZFS_FEATURE_ENABLED) != 0) {
+ zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
+ "property '%s' can only be set to "
+ "'enabled'"), propname);
+ (void) zfs_error(hdl, EZFS_BADPROP, errbuf);
+ goto error;
+ }
+
+ if (nvlist_add_uint64(retprops, propname, 0) != 0) {
+ (void) no_memory(hdl);
+ goto error;
+ }
+ continue;
+ }
+
/*
* Make sure this property is valid and applies to this type.
*/
- if ((prop = zpool_name_to_prop(propname)) == ZPROP_INVAL) {
+ if (prop == ZPROP_INVAL) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"invalid property '%s'"), propname);
(void) zfs_error(hdl, EZFS_BADPROP, errbuf);
* Perform additional checking for specific properties.
*/
switch (prop) {
+ default:
+ break;
case ZPOOL_PROP_VERSION:
- if (intval < version || intval > SPA_VERSION) {
+ if (intval < version ||
+ !SPA_VERSION_IS_SUPPORTED(intval)) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"property '%s' number %d is invalid."),
propname, intval);
}
break;
+ case ZPOOL_PROP_ASHIFT:
+ if (!flags.create) {
+ zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
+ "property '%s' can only be set at "
+ "creation time"), propname);
+ (void) zfs_error(hdl, EZFS_BADPROP, errbuf);
+ goto error;
+ }
+
+ if (intval != 0 && (intval < 9 || intval > 13)) {
+ zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
+ "property '%s' number %d is invalid."),
+ propname, intval);
+ (void) zfs_error(hdl, EZFS_BADPROP, errbuf);
+ goto error;
+ }
+ break;
+
case ZPOOL_PROP_BOOTFS:
- if (create_or_import) {
+ if (flags.create || flags.import) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"property '%s' cannot be set at creation "
"or import time"), propname);
verify(nvlist_lookup_nvlist(zpool_get_config(zhp, NULL),
ZPOOL_CONFIG_VDEV_TREE, &nvroot) == 0);
+#if defined(__sun__) || defined(__sun)
/*
* bootfs property cannot be set on a disk which has
* been EFI labeled.
zpool_close(zhp);
goto error;
}
+#endif
zpool_close(zhp);
break;
case ZPOOL_PROP_ALTROOT:
- if (!create_or_import) {
+ if (!flags.create && !flags.import) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"property '%s' can only be set during pool "
"creation or import"), propname);
*slash = '/';
break;
+
+ case ZPOOL_PROP_COMMENT:
+ for (check = strval; *check != '\0'; check++) {
+ if (!isprint(*check)) {
+ zfs_error_aux(hdl,
+ dgettext(TEXT_DOMAIN,
+ "comment may only have printable "
+ "characters"));
+ (void) zfs_error(hdl, EZFS_BADPROP,
+ errbuf);
+ goto error;
+ }
+ }
+ if (strlen(strval) > ZPROP_MAX_COMMENT) {
+ zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
+ "comment must not exceed %d characters"),
+ ZPROP_MAX_COMMENT);
+ (void) zfs_error(hdl, EZFS_BADPROP, errbuf);
+ goto error;
+ }
+ break;
+ case ZPOOL_PROP_READONLY:
+ if (!flags.import) {
+ zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
+ "property '%s' can only be set at "
+ "import time"), propname);
+ (void) zfs_error(hdl, EZFS_BADPROP, errbuf);
+ goto error;
+ }
+ break;
+ case ZPOOL_PROP_TNAME:
+ if (!flags.create) {
+ zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
+ "property '%s' can only be set at "
+ "creation time"), propname);
+ (void) zfs_error(hdl, EZFS_BADPROP, errbuf);
+ goto error;
+ }
+ break;
}
}
int
zpool_set_prop(zpool_handle_t *zhp, const char *propname, const char *propval)
{
- zfs_cmd_t zc = { 0 };
+ zfs_cmd_t zc = {"\0"};
int ret = -1;
char errbuf[1024];
nvlist_t *nvl = NULL;
nvlist_t *realprops;
uint64_t version;
+ prop_flags_t flags = { 0 };
(void) snprintf(errbuf, sizeof (errbuf),
dgettext(TEXT_DOMAIN, "cannot set property for '%s'"),
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) {
+ zhp->zpool_name, nvl, version, flags, errbuf)) == NULL) {
nvlist_free(nvl);
return (-1);
}
libzfs_handle_t *hdl = zhp->zpool_hdl;
zprop_list_t *entry;
char buf[ZFS_MAXPROPLEN];
+ nvlist_t *features = NULL;
+ nvpair_t *nvp;
+ zprop_list_t **last;
+ boolean_t firstexpand = (NULL == *plp);
+ int i;
if (zprop_expand_list(hdl, plp, ZFS_TYPE_POOL) != 0)
return (-1);
+ last = plp;
+ while (*last != NULL)
+ last = &(*last)->pl_next;
+
+ if ((*plp)->pl_all)
+ features = zpool_get_features(zhp);
+
+ if ((*plp)->pl_all && firstexpand) {
+ for (i = 0; i < SPA_FEATURES; i++) {
+ zprop_list_t *entry = zfs_alloc(hdl,
+ sizeof (zprop_list_t));
+ entry->pl_prop = ZPROP_INVAL;
+ entry->pl_user_prop = zfs_asprintf(hdl, "feature@%s",
+ spa_feature_table[i].fi_uname);
+ entry->pl_width = strlen(entry->pl_user_prop);
+ entry->pl_all = B_TRUE;
+
+ *last = entry;
+ last = &entry->pl_next;
+ }
+ }
+
+ /* add any unsupported features */
+ for (nvp = nvlist_next_nvpair(features, NULL);
+ nvp != NULL; nvp = nvlist_next_nvpair(features, nvp)) {
+ char *propname;
+ boolean_t found;
+ zprop_list_t *entry;
+
+ if (zfeature_is_supported(nvpair_name(nvp)))
+ continue;
+
+ propname = zfs_asprintf(hdl, "unsupported@%s",
+ nvpair_name(nvp));
+
+ /*
+ * Before adding the property to the list make sure that no
+ * other pool already added the same property.
+ */
+ found = B_FALSE;
+ entry = *plp;
+ while (entry != NULL) {
+ if (entry->pl_user_prop != NULL &&
+ strcmp(propname, entry->pl_user_prop) == 0) {
+ found = B_TRUE;
+ break;
+ }
+ entry = entry->pl_next;
+ }
+ if (found) {
+ free(propname);
+ continue;
+ }
+
+ entry = zfs_alloc(hdl, sizeof (zprop_list_t));
+ entry->pl_prop = ZPROP_INVAL;
+ entry->pl_user_prop = propname;
+ entry->pl_width = strlen(entry->pl_user_prop);
+ entry->pl_all = B_TRUE;
+
+ *last = entry;
+ last = &entry->pl_next;
+ }
+
for (entry = *plp; entry != NULL; entry = entry->pl_next) {
if (entry->pl_fixed)
if (entry->pl_prop != ZPROP_INVAL &&
zpool_get_prop(zhp, entry->pl_prop, buf, sizeof (buf),
- NULL) == 0) {
+ NULL, B_FALSE) == 0) {
if (strlen(buf) > entry->pl_width)
entry->pl_width = strlen(buf);
}
return (0);
}
+/*
+ * Get the state for the given feature on the given ZFS pool.
+ */
+int
+zpool_prop_get_feature(zpool_handle_t *zhp, const char *propname, char *buf,
+ size_t len)
+{
+ uint64_t refcount;
+ boolean_t found = B_FALSE;
+ nvlist_t *features = zpool_get_features(zhp);
+ boolean_t supported;
+ const char *feature = strchr(propname, '@') + 1;
+
+ supported = zpool_prop_feature(propname);
+ ASSERT(supported || zpool_prop_unsupported(propname));
+
+ /*
+ * Convert from feature name to feature guid. This conversion is
+ * unecessary for unsupported@... properties because they already
+ * use guids.
+ */
+ if (supported) {
+ int ret;
+ spa_feature_t fid;
+
+ ret = zfeature_lookup_name(feature, &fid);
+ if (ret != 0) {
+ (void) strlcpy(buf, "-", len);
+ return (ENOTSUP);
+ }
+ feature = spa_feature_table[fid].fi_guid;
+ }
+
+ if (nvlist_lookup_uint64(features, feature, &refcount) == 0)
+ found = B_TRUE;
+
+ if (supported) {
+ if (!found) {
+ (void) strlcpy(buf, ZFS_FEATURE_DISABLED, len);
+ } else {
+ if (refcount == 0)
+ (void) strlcpy(buf, ZFS_FEATURE_ENABLED, len);
+ else
+ (void) strlcpy(buf, ZFS_FEATURE_ACTIVE, len);
+ }
+ } else {
+ if (found) {
+ if (refcount == 0) {
+ (void) strcpy(buf, ZFS_UNSUPPORTED_INACTIVE);
+ } else {
+ (void) strcpy(buf, ZFS_UNSUPPORTED_READONLY);
+ }
+ } else {
+ (void) strlcpy(buf, "-", len);
+ return (ENOTSUP);
+ }
+ }
+
+ 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.
+ * devices will use a stripe width of 128k, other vendors prefer a 1m
+ * alignment. It is best to play it safe and ensure a 1m alignment
+ * given 512B blocks. When the block size is larger by a power of 2
+ * we will still be 1m aligned. Some devices are sensitive to the
+ * partition ending alignment as well.
*/
-#define NEW_START_BLOCK 256
+#define NEW_START_BLOCK 2048
+#define PARTITION_END_ALIGNMENT 2048
/*
* Validate the given pool name, optionally putting an extended error message in
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"multiple '@' delimiters in name"));
break;
-
+ case NAME_ERR_NO_AT:
+ zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
+ "permission set is missing '@'"));
+ break;
}
}
return (B_FALSE);
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);
+ nvlist_free(zhp->zpool_config);
+ nvlist_free(zhp->zpool_old_config);
+ nvlist_free(zhp->zpool_props);
free(zhp);
}
zpool_create(libzfs_handle_t *hdl, const char *pool, nvlist_t *nvroot,
nvlist_t *props, nvlist_t *fsprops)
{
- zfs_cmd_t zc = { 0 };
+ 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,
return (-1);
if (props) {
+ prop_flags_t flags = { .create = B_TRUE, .import = B_FALSE };
+
if ((zc_props = zpool_valid_proplist(hdl, pool, props,
- SPA_VERSION_1, B_TRUE, msg)) == NULL) {
+ SPA_VERSION_1, flags, msg)) == NULL) {
goto create_failed;
}
}
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) {
+ if ((zc_fsprops = zfs_valid_proplist(hdl, ZFS_TYPE_FILESYSTEM,
+ fsprops, zoned, NULL, NULL, msg)) == NULL) {
goto create_failed;
}
if (!zc_props &&
* 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.
+ * label. This can also happen under if the device is
+ * part of an active md or lvm device.
*/
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
- "one or more vdevs refer to the same device"));
+ "one or more vdevs refer to the same device, or "
+ "one of\nthe devices is part of an active md or "
+ "lvm device"));
return (zfs_error(hdl, EZFS_BADDEV, msg));
+ case ERANGE:
+ /*
+ * This happens if the record size is smaller or larger
+ * than the allowed size range, or not a power of 2.
+ *
+ * NOTE: although zfs_valid_proplist is called earlier,
+ * this case may have slipped through since the
+ * pool does not exist yet and it is therefore
+ * impossible to read properties e.g. max blocksize
+ * from the pool.
+ */
+ zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
+ "record size invalid"));
+ return (zfs_error(hdl, EZFS_BADPROP, msg));
+
case EOVERFLOW:
/*
* This occurs when one of the devices is below
}
}
- /*
- * 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);
* datasets left in the pool.
*/
int
-zpool_destroy(zpool_handle_t *zhp)
+zpool_destroy(zpool_handle_t *zhp, const char *log_str)
{
- zfs_cmd_t zc = { 0 };
+ 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);
-
- if (zpool_remove_zvol_links(zhp) != 0)
+ (zfp = zfs_open(hdl, zhp->zpool_name, ZFS_TYPE_FILESYSTEM)) == NULL)
return (-1);
(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
+ zc.zc_history = (uint64_t)(uintptr_t)log_str;
- if (zfs_ioctl(zhp->zpool_hdl, ZFS_IOC_POOL_DESTROY, &zc) != 0) {
+ if (zfs_ioctl(hdl, ZFS_IOC_POOL_DESTROY, &zc) != 0) {
(void) snprintf(msg, sizeof (msg), dgettext(TEXT_DOMAIN,
"cannot destroy '%s'"), zhp->zpool_name);
int
zpool_add(zpool_handle_t *zhp, nvlist_t *nvroot)
{
- zfs_cmd_t zc = { 0 };
+ zfs_cmd_t zc = {"\0"};
int ret;
libzfs_handle_t *hdl = zhp->zpool_hdl;
char msg[1024];
return (zfs_error(hdl, EZFS_BADVERSION, msg));
}
- if (pool_is_bootable(zhp) && nvlist_lookup_nvlist_array(nvroot,
+#if defined(__sun__) || defined(__sun)
+ if (zpool_is_bootable(zhp) && nvlist_lookup_nvlist_array(nvroot,
ZPOOL_CONFIG_SPARES, &spares, &nspares) == 0) {
uint64_t 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]));
+ zpool_vdev_name(hdl, NULL, spares[s], 0));
return (zfs_error(hdl, EZFS_POOL_NOTSUP, msg));
}
}
}
+#endif
if (zpool_get_prop_int(zhp, ZPOOL_PROP_VERSION, NULL) <
SPA_VERSION_L2CACHE &&
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) {
+ if (zfs_ioctl(hdl, ZFS_IOC_VDEV_ADD, &zc) != 0) {
switch (errno) {
case EBUSY:
/*
(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"));
* 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)
+static int
+zpool_export_common(zpool_handle_t *zhp, boolean_t force, boolean_t hardforce,
+ const char *log_str)
{
- zfs_cmd_t zc = { 0 };
+ zfs_cmd_t zc = {"\0"};
char msg[1024];
- if (zpool_remove_zvol_links(zhp) != 0)
- return (-1);
-
(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;
+ zc.zc_history = (uint64_t)(uintptr_t)log_str;
if (zfs_ioctl(zhp->zpool_hdl, ZFS_IOC_POOL_EXPORT, &zc) != 0) {
switch (errno) {
}
int
-zpool_export(zpool_handle_t *zhp, boolean_t force)
+zpool_export(zpool_handle_t *zhp, boolean_t force, const char *log_str)
{
- return (zpool_export_common(zhp, force, B_FALSE));
+ return (zpool_export_common(zhp, force, B_FALSE, log_str));
}
int
-zpool_export_force(zpool_handle_t *zhp)
+zpool_export_force(zpool_handle_t *zhp, const char *log_str)
+{
+ return (zpool_export_common(zhp, B_TRUE, B_TRUE, log_str));
+}
+
+static void
+zpool_rewind_exclaim(libzfs_handle_t *hdl, const char *name, boolean_t dryrun,
+ nvlist_t *config)
+{
+ nvlist_t *nv = NULL;
+ uint64_t rewindto;
+ int64_t loss = -1;
+ struct tm t;
+ char timestr[128];
+
+ if (!hdl->libzfs_printerr || config == NULL)
+ return;
+
+ if (nvlist_lookup_nvlist(config, ZPOOL_CONFIG_LOAD_INFO, &nv) != 0 ||
+ nvlist_lookup_nvlist(nv, ZPOOL_CONFIG_REWIND_INFO, &nv) != 0) {
+ return;
+ }
+
+ if (nvlist_lookup_uint64(nv, ZPOOL_CONFIG_LOAD_TIME, &rewindto) != 0)
+ return;
+ (void) nvlist_lookup_int64(nv, ZPOOL_CONFIG_REWIND_TIME, &loss);
+
+ if (localtime_r((time_t *)&rewindto, &t) != NULL &&
+ strftime(timestr, 128, "%c", &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 %lld "),
+ dryrun ? "Would discard" : "Discarded",
+ ((longlong_t)loss + 30) / 60);
+ (void) printf(dgettext(TEXT_DOMAIN,
+ "minutes of transactions.\n"));
+ } else if (loss > 0) {
+ (void) printf(dgettext(TEXT_DOMAIN,
+ "%s approximately %lld "),
+ dryrun ? "Would discard" : "Discarded",
+ (longlong_t)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)
{
- return (zpool_export_common(zhp, B_TRUE, B_TRUE));
+ nvlist_t *nv = NULL;
+ 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_nvlist(config, ZPOOL_CONFIG_LOAD_INFO, &nv) != 0 ||
+ nvlist_lookup_nvlist(nv, ZPOOL_CONFIG_REWIND_INFO, &nv) != 0 ||
+ nvlist_lookup_uint64(nv, ZPOOL_CONFIG_LOAD_TIME, &rewindto) != 0)
+ goto no_info;
+
+ (void) nvlist_lookup_int64(nv, ZPOOL_CONFIG_REWIND_TIME, &loss);
+ (void) nvlist_lookup_uint64(nv, 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, "%c", &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 %lld minutes of data\n"
+ "\tmust be discarded, irreversibly. "),
+ ((longlong_t)loss + 30) / 60);
+ } else if (loss > 0) {
+ (void) printf(dgettext(TEXT_DOMAIN,
+ "Approximately %lld seconds of data\n"
+ "\tmust be discarded, irreversibly. "),
+ (longlong_t)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"));
}
/*
}
}
- ret = zpool_import_props(hdl, config, newname, props, B_FALSE);
- if (props)
- nvlist_free(props);
+ ret = zpool_import_props(hdl, config, newname, props,
+ ZFS_IMPORT_NORMAL);
+ nvlist_free(props);
return (ret);
}
+static void
+print_vdev_tree(libzfs_handle_t *hdl, const char *name, nvlist_t *nv,
+ int indent)
+{
+ nvlist_t **child;
+ uint_t c, children;
+ char *vname;
+ uint64_t is_log = 0;
+
+ (void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_IS_LOG,
+ &is_log);
+
+ if (name != NULL)
+ (void) printf("\t%*s%s%s\n", indent, "", name,
+ is_log ? " [log]" : "");
+
+ if (nvlist_lookup_nvlist_array(nv, ZPOOL_CONFIG_CHILDREN,
+ &child, &children) != 0)
+ return;
+
+ for (c = 0; c < children; c++) {
+ vname = zpool_vdev_name(hdl, NULL, child[c], VDEV_NAME_TYPE_ID);
+ print_vdev_tree(hdl, vname, child[c], indent + 2);
+ free(vname);
+ }
+}
+
+void
+zpool_print_unsup_feat(nvlist_t *config)
+{
+ nvlist_t *nvinfo, *unsup_feat;
+ nvpair_t *nvp;
+
+ verify(nvlist_lookup_nvlist(config, ZPOOL_CONFIG_LOAD_INFO, &nvinfo) ==
+ 0);
+ verify(nvlist_lookup_nvlist(nvinfo, ZPOOL_CONFIG_UNSUP_FEAT,
+ &unsup_feat) == 0);
+
+ for (nvp = nvlist_next_nvpair(unsup_feat, NULL); nvp != NULL;
+ nvp = nvlist_next_nvpair(unsup_feat, nvp)) {
+ char *desc;
+
+ verify(nvpair_type(nvp) == DATA_TYPE_STRING);
+ verify(nvpair_value_string(nvp, &desc) == 0);
+
+ if (strlen(desc) > 0)
+ (void) printf("\t%s (%s)\n", nvpair_name(nvp), desc);
+ else
+ (void) printf("\t%s\n", nvpair_name(nvp));
+ }
+}
+
/*
* Import the given pool using the known configuration and a list of
* properties to be set. The configuration should have come from
*/
int
zpool_import_props(libzfs_handle_t *hdl, nvlist_t *config, const char *newname,
- nvlist_t *props, boolean_t importfaulted)
+ nvlist_t *props, int flags)
{
- zfs_cmd_t zc = { 0 };
+ zfs_cmd_t zc = {"\0"};
+ zpool_rewind_policy_t policy;
+ nvlist_t *nv = NULL;
+ nvlist_t *nvinfo = NULL;
+ nvlist_t *missing = NULL;
char *thename;
char *origname;
int ret;
+ int error = 0;
char errbuf[1024];
verify(nvlist_lookup_string(config, ZPOOL_CONFIG_POOL_NAME,
thename = origname;
}
- if (props) {
+ if (props != NULL) {
uint64_t version;
+ prop_flags_t flags = { .create = B_FALSE, .import = B_TRUE };
verify(nvlist_lookup_uint64(config, ZPOOL_CONFIG_VERSION,
&version) == 0);
if ((props = zpool_valid_proplist(hdl, origname,
- props, version, B_TRUE, errbuf)) == NULL) {
+ props, version, flags, errbuf)) == NULL)
return (-1);
- } else if (zcmd_write_src_nvlist(hdl, &zc, props) != 0) {
+ if (zcmd_write_src_nvlist(hdl, &zc, props) != 0) {
nvlist_free(props);
return (-1);
}
+ nvlist_free(props);
}
(void) strlcpy(zc.zc_name, thename, sizeof (zc.zc_name));
&zc.zc_guid) == 0);
if (zcmd_write_conf_nvlist(hdl, &zc, config) != 0) {
- nvlist_free(props);
+ zcmd_free_nvlists(&zc);
+ return (-1);
+ }
+ if (zcmd_alloc_dst_nvlist(hdl, &zc, zc.zc_nvlist_conf_size * 2) != 0) {
+ zcmd_free_nvlists(&zc);
return (-1);
}
- zc.zc_cookie = (uint64_t)importfaulted;
- ret = 0;
- if (zfs_ioctl(hdl, ZFS_IOC_POOL_IMPORT, &zc) != 0) {
+ zc.zc_cookie = flags;
+ while ((ret = zfs_ioctl(hdl, ZFS_IOC_POOL_IMPORT, &zc)) != 0 &&
+ errno == ENOMEM) {
+ if (zcmd_expand_dst_nvlist(hdl, &zc) != 0) {
+ zcmd_free_nvlists(&zc);
+ return (-1);
+ }
+ }
+ if (ret != 0)
+ error = errno;
+
+ (void) zcmd_read_dst_nvlist(hdl, &zc, &nv);
+
+ zcmd_free_nvlists(&zc);
+
+ zpool_get_rewind_policy(config, &policy);
+
+ if (error) {
char desc[1024];
+
+ /*
+ * Dry-run failed, but we print out what success
+ * looks like if we found a best txg
+ */
+ if (policy.zrp_request & ZPOOL_TRY_REWIND) {
+ zpool_rewind_exclaim(hdl, newname ? origname : thename,
+ B_TRUE, nv);
+ nvlist_free(nv);
+ return (-1);
+ }
+
if (newname == NULL)
(void) snprintf(desc, sizeof (desc),
dgettext(TEXT_DOMAIN, "cannot import '%s'"),
dgettext(TEXT_DOMAIN, "cannot import '%s' as '%s'"),
origname, thename);
- switch (errno) {
+ switch (error) {
case ENOTSUP:
+ if (nv != NULL && nvlist_lookup_nvlist(nv,
+ ZPOOL_CONFIG_LOAD_INFO, &nvinfo) == 0 &&
+ nvlist_exists(nvinfo, ZPOOL_CONFIG_UNSUP_FEAT)) {
+ (void) printf(dgettext(TEXT_DOMAIN, "This "
+ "pool uses the following feature(s) not "
+ "supported by this system:\n"));
+ zpool_print_unsup_feat(nv);
+ if (nvlist_exists(nvinfo,
+ ZPOOL_CONFIG_CAN_RDONLY)) {
+ (void) printf(dgettext(TEXT_DOMAIN,
+ "All unsupported features are only "
+ "required for writing to the pool."
+ "\nThe pool can be imported using "
+ "'-o readonly=on'.\n"));
+ }
+ }
/*
* Unsupported version.
*/
(void) zfs_error(hdl, EZFS_INVALCONFIG, desc);
break;
- default:
- (void) zpool_standard_error(hdl, errno, desc);
- }
+ case EROFS:
+ zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
+ "one or more devices is read only"));
+ (void) zfs_error(hdl, EZFS_BADDEV, desc);
+ break;
- ret = -1;
- } else {
- zpool_handle_t *zhp;
+ case ENXIO:
+ if (nv && nvlist_lookup_nvlist(nv,
+ ZPOOL_CONFIG_LOAD_INFO, &nvinfo) == 0 &&
+ nvlist_lookup_nvlist(nvinfo,
+ ZPOOL_CONFIG_MISSING_DEVICES, &missing) == 0) {
+ (void) printf(dgettext(TEXT_DOMAIN,
+ "The devices below are missing, use "
+ "'-m' to import the pool anyway:\n"));
+ print_vdev_tree(hdl, NULL, missing, 2);
+ (void) printf("\n");
+ }
+ (void) zpool_standard_error(hdl, error, desc);
+ break;
+
+ case EEXIST:
+ (void) zpool_standard_error(hdl, error, desc);
+ break;
+
+ case EBUSY:
+ zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
+ "one or more devices are already in use\n"));
+ (void) zfs_error(hdl, EZFS_BADDEV, desc);
+ break;
+ case ENAMETOOLONG:
+ zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
+ "new name of at least one dataset is longer than "
+ "the maximum allowable length"));
+ (void) zfs_error(hdl, EZFS_NAMETOOLONG, desc);
+ break;
+ default:
+ (void) zpool_standard_error(hdl, error, desc);
+ zpool_explain_recover(hdl,
+ newname ? origname : thename, -error, nv);
+ break;
+ }
+
+ nvlist_free(nv);
+ ret = -1;
+ } else {
+ zpool_handle_t *zhp;
/*
* This should never fail, but play it safe anyway.
*/
- if (zpool_open_silent(hdl, thename, &zhp) != 0) {
+ if (zpool_open_silent(hdl, thename, &zhp) != 0)
ret = -1;
- } else if (zhp != NULL) {
- ret = zpool_create_zvol_links(zhp);
+ else if (zhp != NULL)
zpool_close(zhp);
+ if (policy.zrp_request &
+ (ZPOOL_DO_REWIND | ZPOOL_TRY_REWIND)) {
+ zpool_rewind_exclaim(hdl, newname ? origname : thename,
+ ((policy.zrp_request & ZPOOL_TRY_REWIND) != 0), nv);
}
-
+ nvlist_free(nv);
+ return (0);
}
- zcmd_free_nvlists(&zc);
- nvlist_free(props);
-
return (ret);
}
/*
- * Scrub the pool.
+ * Scan the pool.
*/
int
-zpool_scrub(zpool_handle_t *zhp, pool_scrub_type_t type)
+zpool_scan(zpool_handle_t *zhp, pool_scan_func_t func)
{
- zfs_cmd_t zc = { 0 };
+ 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;
+ zc.zc_cookie = func;
- if (zfs_ioctl(zhp->zpool_hdl, ZFS_IOC_POOL_SCRUB, &zc) == 0)
+ if (zfs_ioctl(hdl, ZFS_IOC_POOL_SCAN, &zc) == 0 ||
+ (errno == ENOENT && func != POOL_SCAN_NONE))
return (0);
- (void) snprintf(msg, sizeof (msg),
- dgettext(TEXT_DOMAIN, "cannot scrub %s"), zc.zc_name);
+ if (func == POOL_SCAN_SCRUB) {
+ (void) snprintf(msg, sizeof (msg),
+ dgettext(TEXT_DOMAIN, "cannot scrub %s"), zc.zc_name);
+ } else if (func == POOL_SCAN_NONE) {
+ (void) snprintf(msg, sizeof (msg),
+ dgettext(TEXT_DOMAIN, "cannot cancel scrubbing %s"),
+ zc.zc_name);
+ } else {
+ assert(!"unexpected result");
+ }
- if (errno == EBUSY)
- return (zfs_error(hdl, EZFS_RESILVERING, msg));
- else
+ if (errno == EBUSY) {
+ nvlist_t *nvroot;
+ pool_scan_stat_t *ps = NULL;
+ uint_t psc;
+
+ verify(nvlist_lookup_nvlist(zhp->zpool_config,
+ ZPOOL_CONFIG_VDEV_TREE, &nvroot) == 0);
+ (void) nvlist_lookup_uint64_array(nvroot,
+ ZPOOL_CONFIG_SCAN_STATS, (uint64_t **)&ps, &psc);
+ if (ps && ps->pss_func == POOL_SCAN_SCRUB)
+ return (zfs_error(hdl, EZFS_SCRUBBING, msg));
+ else
+ return (zfs_error(hdl, EZFS_RESILVERING, msg));
+ } else if (errno == ENOENT) {
+ return (zfs_error(hdl, EZFS_NO_SCRUB, msg));
+ } else {
return (zpool_standard_error(hdl, errno, msg));
+ }
}
/*
srchkey = nvpair_name(pair);
switch (nvpair_type(pair)) {
- case DATA_TYPE_UINT64: {
- uint64_t srchval, theguid, present;
-
- verify(nvpair_value_uint64(pair, &srchval) == 0);
+ case DATA_TYPE_UINT64:
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);
- }
+ uint64_t srchval, theguid;
+
+ verify(nvpair_value_uint64(pair, &srchval) == 0);
+ verify(nvlist_lookup_uint64(nv, ZPOOL_CONFIG_GUID,
+ &theguid) == 0);
+ if (theguid == srchval)
+ return (nv);
}
break;
- }
case DATA_TYPE_STRING: {
char *srchval, *val;
break;
/*
- * Search for the requested value. We special case the search
- * for ZPOOL_CONFIG_PATH when it's a wholedisk. Otherwise,
- * all other searches are simple string compares.
+ * Search for the requested value. Special cases:
+ *
+ * - ZPOOL_CONFIG_PATH for whole disk entries. These end in
+ * "-part1", or "p1". The suffix is hidden from the user,
+ * but included in the string, so this matches around it.
+ * - ZPOOL_CONFIG_PATH for short names zfs_strcmp_shortname()
+ * is used to check all possible expanded paths.
+ * - 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) {
+ if (strcmp(srchkey, ZPOOL_CONFIG_PATH) == 0) {
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);
+ if (zfs_strcmp_pathname(srchval, val, wholedisk) == 0)
+ return (nv);
+
+ } 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);
}
/*
&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);
}
+/*
+ * 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);
+ guid = strtoull(path, &end, 0);
if (guid != 0 && *end == '\0') {
verify(nvlist_add_uint64(search, ZPOOL_CONFIG_GUID, guid) == 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 if (zpool_vdev_is_interior(path)) {
+ verify(nvlist_add_string(search, ZPOOL_CONFIG_TYPE, path) == 0);
} else {
verify(nvlist_add_string(search, ZPOOL_CONFIG_PATH, path) == 0);
}
&child, &count) != 0)
return (EZFS_INVALCONFIG);
+#if defined(__sun__) || defined(__sun)
/*
* root pool can not have EFI labeled disks and can only have
* a single top-level vdev.
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);
phypath_size));
}
-/*
- * Returns TRUE if the given guid corresponds to the given type.
- * This is used to check for hot spares (INUSE or not), and level 2 cache
- * devices.
- */
-static boolean_t
-is_guid_type(zpool_handle_t *zhp, uint64_t guid, const char *type)
-{
- uint64_t target_guid;
- nvlist_t *nvroot;
- nvlist_t **list;
- uint_t count;
- int i;
-
- verify(nvlist_lookup_nvlist(zhp->zpool_config, ZPOOL_CONFIG_VDEV_TREE,
- &nvroot) == 0);
- if (nvlist_lookup_nvlist_array(nvroot, type, &list, &count) == 0) {
- for (i = 0; i < count; i++) {
- verify(nvlist_lookup_uint64(list[i], ZPOOL_CONFIG_GUID,
- &target_guid) == 0);
- if (guid == target_guid)
- return (B_TRUE);
- }
- }
-
- return (B_FALSE);
-}
-
/*
* 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)
+zpool_relabel_disk(libzfs_handle_t *hdl, const char *path, const char *msg)
{
- 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) {
+ if ((fd = open(path, O_RDWR|O_DIRECT)) < 0) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "cannot "
- "relabel '%s': unable to open device"), name);
- return (zfs_error(hdl, EZFS_OPENFAILED, errbuf));
+ "relabel '%s': unable to open device: %d"), path, errno);
+ return (zfs_error(hdl, EZFS_OPENFAILED, msg));
}
/*
* 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.
+ *
+ * Also, we don't call efi_rescan() - that would just return EBUSY.
+ * The module will do it for us in vdev_disk_open().
*/
- error = _efi_use_whole_disk(fd);
+ 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));
+ "relabel '%s': unable to read disk capacity"), path);
+ return (zfs_error(hdl, EZFS_NOCAP, msg));
}
return (0);
}
zpool_vdev_online(zpool_handle_t *zhp, const char *path, int flags,
vdev_state_t *newstate)
{
- zfs_cmd_t zc = { 0 };
+ zfs_cmd_t zc = {"\0"};
char msg[1024];
nvlist_t *tgt;
boolean_t avail_spare, l2cache, islog;
libzfs_handle_t *hdl = zhp->zpool_hdl;
+ int error;
if (flags & ZFS_ONLINE_EXPAND) {
(void) snprintf(msg, sizeof (msg),
verify(nvlist_lookup_uint64(tgt, ZPOOL_CONFIG_GUID, &zc.zc_guid) == 0);
- if (avail_spare ||
- is_guid_type(zhp, zc.zc_guid, ZPOOL_CONFIG_SPARES) == B_TRUE)
+ 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 (wholedisk) {
- pathname += strlen(DISK_ROOT) + 1;
- (void) zpool_relabel_disk(zhp->zpool_hdl, pathname);
+ const char *fullpath = path;
+ char buf[MAXPATHLEN];
+
+ if (path[0] != '/') {
+ error = zfs_resolve_shortname(path, buf,
+ sizeof (buf));
+ if (error != 0)
+ return (zfs_error(hdl, EZFS_NODEVICE,
+ msg));
+
+ fullpath = buf;
+ }
+
+ error = zpool_relabel_disk(hdl, fullpath, msg);
+ if (error != 0)
+ return (error);
}
}
zc.zc_cookie = VDEV_STATE_ONLINE;
zc.zc_obj = flags;
- if (zfs_ioctl(zhp->zpool_hdl, ZFS_IOC_VDEV_SET_STATE, &zc) != 0)
+ if (zfs_ioctl(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);
int
zpool_vdev_offline(zpool_handle_t *zhp, const char *path, boolean_t istmp)
{
- zfs_cmd_t zc = { 0 };
+ zfs_cmd_t zc = {"\0"};
char msg[1024];
nvlist_t *tgt;
boolean_t avail_spare, l2cache;
verify(nvlist_lookup_uint64(tgt, ZPOOL_CONFIG_GUID, &zc.zc_guid) == 0);
- if (avail_spare ||
- is_guid_type(zhp, zc.zc_guid, ZPOOL_CONFIG_SPARES) == B_TRUE)
+ 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)
+ if (zfs_ioctl(hdl, ZFS_IOC_VDEV_SET_STATE, &zc) == 0)
return (0);
switch (errno) {
* Mark the given vdev faulted.
*/
int
-zpool_vdev_fault(zpool_handle_t *zhp, uint64_t guid)
+zpool_vdev_fault(zpool_handle_t *zhp, uint64_t guid, vdev_aux_t aux)
{
- zfs_cmd_t zc = { 0 };
+ 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"), guid);
+ 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)
+ if (ioctl(hdl->libzfs_fd, ZFS_IOC_VDEV_SET_STATE, &zc) == 0)
return (0);
switch (errno) {
* Mark the given vdev degraded.
*/
int
-zpool_vdev_degrade(zpool_handle_t *zhp, uint64_t guid)
+zpool_vdev_degrade(zpool_handle_t *zhp, uint64_t guid, vdev_aux_t aux)
{
- zfs_cmd_t zc = { 0 };
+ 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"), guid);
+ 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)
+ if (ioctl(hdl->libzfs_fd, ZFS_IOC_VDEV_SET_STATE, &zc) == 0)
return (0);
return (zpool_standard_error(hdl, errno, msg));
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 };
+ 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;
+ char *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);
+ boolean_t rootpool = zpool_is_bootable(zhp);
if (replacing)
(void) snprintf(msg, sizeof (msg), dgettext(TEXT_DOMAIN,
(void) snprintf(msg, sizeof (msg), dgettext(TEXT_DOMAIN,
"cannot attach %s to %s"), new_disk, old_disk);
+#if defined(__sun__) || defined(__sun)
/*
* If this is a root pool, make sure that we're not attaching an
* EFI labeled device.
"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,
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])) == NULL)
+ if ((newname = zpool_vdev_name(NULL, NULL, child[0], 0)) == NULL)
return (-1);
/*
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);
+ ret = zfs_ioctl(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.
* Can't attach to or replace this type of vdev.
*/
if (replacing) {
+ uint64_t version = zpool_get_prop_int(zhp,
+ ZPOOL_PROP_VERSION, NULL);
+
if (islog)
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"cannot replace a log with a spare"));
+ else if (version >= SPA_VERSION_MULTI_REPLACE)
+ zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
+ "already in replacing/spare config; wait "
+ "for completion or use 'zpool detach'"));
else
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"cannot replace a replacing device"));
case EDOM:
/*
- * The new device has a different alignment requirement.
+ * The new device has a different optimal sector size.
*/
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
- "devices have different sector alignment"));
+ "new device has a different optimal sector size; use the "
+ "option '-o ashift=N' to override the optimal size"));
(void) zfs_error(hdl, EZFS_BADDEV, msg);
break;
int
zpool_vdev_detach(zpool_handle_t *zhp, const char *path)
{
- zfs_cmd_t zc = { 0 };
+ zfs_cmd_t zc = {"\0"};
char msg[1024];
nvlist_t *tgt;
boolean_t avail_spare, l2cache;
*/
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "only "
"applicable to mirror and replacing vdevs"));
- (void) zfs_error(zhp->zpool_hdl, EZFS_BADTARGET, msg);
+ (void) zfs_error(hdl, EZFS_BADTARGET, msg);
break;
case EBUSY:
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], 0);
+
+ for (sc = 0; sc < schildren; sc++) {
+ char *spath = zpool_vdev_name(zhp->zpool_hdl, zhp,
+ schild[sc], 0);
+ 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) {
+ prop_flags_t flags = { .create = B_FALSE, .import = B_TRUE };
+ if ((zc_props = zpool_valid_proplist(hdl, zhp->zpool_name,
+ props, vers, flags, 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"));
+ 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);
+ nvlist_free(zc_props);
+ 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 };
+ zfs_cmd_t zc = {"\0"};
char msg[1024];
nvlist_t *tgt;
- boolean_t avail_spare, l2cache;
+ 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,
- NULL)) == 0)
+ &islog)) == 0)
return (zfs_error(hdl, EZFS_NODEVICE, msg));
-
- if (!avail_spare && !l2cache) {
+ /*
+ * XXX - this should just go away.
+ */
+ if (!avail_spare && !l2cache && !islog) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
- "only inactive hot spares or cache devices "
- "can be removed"));
+ "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)
* Clear the errors for the pool, or the particular device if specified.
*/
int
-zpool_clear(zpool_handle_t *zhp, const char *path)
+zpool_clear(zpool_handle_t *zhp, const char *path, nvlist_t *rewindnvl)
{
- zfs_cmd_t zc = { 0 };
+ 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;
+ int error;
if (path)
(void) snprintf(msg, sizeof (msg),
&zc.zc_guid) == 0);
}
- if (zfs_ioctl(hdl, ZFS_IOC_CLEAR, &zc) == 0)
+ zpool_get_rewind_policy(rewindnvl, &policy);
+ zc.zc_cookie = policy.zrp_request;
+
+ if (zcmd_alloc_dst_nvlist(hdl, &zc, zhp->zpool_config_size * 2) != 0)
+ return (-1);
+
+ if (zcmd_write_src_nvlist(hdl, &zc, rewindnvl) != 0)
+ return (-1);
+
+ while ((error = zfs_ioctl(hdl, ZFS_IOC_CLEAR, &zc)) != 0 &&
+ errno == ENOMEM) {
+ if (zcmd_expand_dst_nvlist(hdl, &zc) != 0) {
+ zcmd_free_nvlists(&zc);
+ return (-1);
+ }
+ }
+
+ if (!error || ((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));
}
int
zpool_vdev_clear(zpool_handle_t *zhp, uint64_t guid)
{
- zfs_cmd_t zc = { 0 };
+ 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"),
- guid);
+ (u_longlong_t)guid);
(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
zc.zc_guid = guid;
+ zc.zc_cookie = ZPOOL_NO_REWIND;
if (ioctl(hdl->libzfs_fd, ZFS_IOC_CLEAR, &zc) == 0)
return (0);
}
/*
- * Iterate over all zvols in a given pool by walking the /dev/zvol/dsk/<pool>
- * hierarchy.
+ * Change the GUID for a pool.
*/
int
-zpool_iter_zvol(zpool_handle_t *zhp, int (*cb)(const char *, void *),
- void *data)
+zpool_reguid(zpool_handle_t *zhp)
{
+ char msg[1024];
libzfs_handle_t *hdl = zhp->zpool_hdl;
- char (*paths)[MAXPATHLEN];
- size_t size = 4;
- int curr, fd, base, ret = 0;
- DIR *dirp;
- struct dirent *dp;
- struct stat st;
-
- if ((base = open("/dev/zvol/dsk", O_RDONLY)) < 0)
- return (errno == ENOENT ? 0 : -1);
+ zfs_cmd_t zc = {"\0"};
- if (fstatat(base, zhp->zpool_name, &st, 0) != 0) {
- int err = errno;
- (void) close(base);
- return (err == ENOENT ? 0 : -1);
- }
+ (void) snprintf(msg, sizeof (msg),
+ dgettext(TEXT_DOMAIN, "cannot reguid '%s'"), zhp->zpool_name);
- /*
- * Oddly this wasn't a directory -- ignore that failure since we
- * know there are no links lower in the (non-existant) hierarchy.
- */
- if (!S_ISDIR(st.st_mode)) {
- (void) close(base);
+ (void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
+ if (zfs_ioctl(hdl, ZFS_IOC_POOL_REGUID, &zc) == 0)
return (0);
- }
- if ((paths = zfs_alloc(hdl, size * sizeof (paths[0]))) == NULL) {
- (void) close(base);
- return (-1);
- }
-
- (void) strlcpy(paths[0], zhp->zpool_name, sizeof (paths[0]));
- curr = 0;
-
- while (curr >= 0) {
- if (fstatat(base, paths[curr], &st, AT_SYMLINK_NOFOLLOW) != 0)
- goto err;
-
- if (S_ISDIR(st.st_mode)) {
- if ((fd = openat(base, paths[curr], O_RDONLY)) < 0)
- goto err;
-
- if ((dirp = fdopendir(fd)) == NULL) {
- (void) close(fd);
- goto err;
- }
-
- while ((dp = readdir(dirp)) != NULL) {
- if (dp->d_name[0] == '.')
- continue;
-
- if (curr + 1 == size) {
- paths = zfs_realloc(hdl, paths,
- size * sizeof (paths[0]),
- size * 2 * sizeof (paths[0]));
- if (paths == NULL) {
- (void) closedir(dirp);
- (void) close(fd);
- goto err;
- }
-
- size *= 2;
- }
-
- (void) strlcpy(paths[curr + 1], paths[curr],
- sizeof (paths[curr + 1]));
- (void) strlcat(paths[curr], "/",
- sizeof (paths[curr]));
- (void) strlcat(paths[curr], dp->d_name,
- sizeof (paths[curr]));
- curr++;
- }
-
- (void) closedir(dirp);
-
- } else {
- if ((ret = cb(paths[curr], data)) != 0)
- break;
- }
-
- curr--;
- }
-
- free(paths);
- (void) close(base);
-
- return (ret);
-
-err:
- free(paths);
- (void) close(base);
- return (-1);
-}
-
-typedef struct zvol_cb {
- zpool_handle_t *zcb_pool;
- boolean_t zcb_create;
-} zvol_cb_t;
-
-/*ARGSUSED*/
-static int
-do_zvol_create(zfs_handle_t *zhp, void *data)
-{
- int ret = 0;
-
- if (ZFS_IS_VOLUME(zhp)) {
- (void) zvol_create_link(zhp->zfs_hdl, zhp->zfs_name);
- ret = zfs_iter_snapshots(zhp, do_zvol_create, NULL);
- }
-
- if (ret == 0)
- ret = zfs_iter_filesystems(zhp, do_zvol_create, NULL);
-
- zfs_close(zhp);
-
- return (ret);
+ return (zpool_standard_error(hdl, errno, msg));
}
/*
- * Iterate over all zvols in the pool and make any necessary minor nodes.
+ * Reopen the pool.
*/
int
-zpool_create_zvol_links(zpool_handle_t *zhp)
-{
- zfs_handle_t *zfp;
- int ret;
-
- /*
- * If the pool is unavailable, just return success.
- */
- if ((zfp = make_dataset_handle(zhp->zpool_hdl,
- zhp->zpool_name)) == NULL)
- return (0);
-
- ret = zfs_iter_filesystems(zfp, do_zvol_create, NULL);
-
- zfs_close(zfp);
- return (ret);
-}
-
-static int
-do_zvol_remove(const char *dataset, void *data)
+zpool_reopen(zpool_handle_t *zhp)
{
- zpool_handle_t *zhp = data;
+ zfs_cmd_t zc = {"\0"};
+ char msg[1024];
+ libzfs_handle_t *hdl = zhp->zpool_hdl;
- return (zvol_remove_link(zhp->zpool_hdl, dataset));
-}
+ (void) snprintf(msg, sizeof (msg),
+ dgettext(TEXT_DOMAIN, "cannot reopen '%s'"),
+ zhp->zpool_name);
-/*
- * Iterate over all zvols in the pool and remove any minor nodes. We iterate
- * by examining the /dev links so that a corrupted pool doesn't impede this
- * operation.
- */
-int
-zpool_remove_zvol_links(zpool_handle_t *zhp)
-{
- return (zpool_iter_zvol(zhp, do_zvol_remove, zhp));
+ (void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
+ if (zfs_ioctl(hdl, ZFS_IOC_POOL_REOPEN, &zc) == 0)
+ return (0);
+ return (zpool_standard_error(hdl, errno, msg));
}
+#if defined(__sun__) || defined(__sun)
/*
* Convert from a devid string to a path.
*/
if (ret != 0)
return (NULL);
- if ((path = strdup(list[0].devname)) == NULL)
- return (NULL);
+ /*
+ * In a case the strdup() fails, we will just return NULL below.
+ */
+ path = strdup(list[0].devname);
devid_free_nmlist(list);
static void
set_path(zpool_handle_t *zhp, nvlist_t *nv, const char *path)
{
- zfs_cmd_t zc = { 0 };
+ zfs_cmd_t zc = {"\0"};
(void) strncpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
(void) strncpy(zc.zc_value, path, sizeof (zc.zc_value));
(void) ioctl(zhp->zpool_hdl->libzfs_fd, ZFS_IOC_VDEV_SETPATH, &zc);
}
+#endif /* sun */
+
+/*
+ * Remove partition suffix from a vdev path. Partition suffixes may take three
+ * forms: "-partX", "pX", or "X", where X is a string of digits. The second
+ * case only occurs when the suffix is preceded by a digit, i.e. "md0p0" The
+ * third case only occurs when preceded by a string matching the regular
+ * expression "^([hsv]|xv)d[a-z]+", i.e. a scsi, ide, virtio or xen disk.
+ */
+static char *
+strip_partition(libzfs_handle_t *hdl, char *path)
+{
+ char *tmp = zfs_strdup(hdl, path);
+ char *part = NULL, *d = NULL;
+
+ if ((part = strstr(tmp, "-part")) && part != tmp) {
+ d = part + 5;
+ } else if ((part = strrchr(tmp, 'p')) &&
+ part > tmp + 1 && isdigit(*(part-1))) {
+ d = part + 1;
+ } else if ((tmp[0] == 'h' || tmp[0] == 's' || tmp[0] == 'v') &&
+ tmp[1] == 'd') {
+ for (d = &tmp[2]; isalpha(*d); part = ++d);
+ } else if (strncmp("xvd", tmp, 3) == 0) {
+ for (d = &tmp[3]; isalpha(*d); part = ++d);
+ }
+ if (part && d && *d != '\0') {
+ for (; isdigit(*d); d++);
+ if (*d == '\0')
+ *part = '\0';
+ }
+ return (tmp);
+}
+
+#define PATH_BUF_LEN 64
/*
* Given a vdev, return the name to display in iostat. If the vdev has a path,
* of these checks.
*/
char *
-zpool_vdev_name(libzfs_handle_t *hdl, zpool_handle_t *zhp, nvlist_t *nv)
+zpool_vdev_name(libzfs_handle_t *hdl, zpool_handle_t *zhp, nvlist_t *nv,
+ int name_flags)
{
- char *path, *devid;
+ char *path, *type, *env;
uint64_t value;
- char buf[64];
- vdev_stat_t *vs;
- uint_t vsc;
-
- if (nvlist_lookup_uint64(nv, ZPOOL_CONFIG_NOT_PRESENT,
- &value) == 0) {
- verify(nvlist_lookup_uint64(nv, ZPOOL_CONFIG_GUID,
- &value) == 0);
- (void) snprintf(buf, sizeof (buf), "%llu",
- (u_longlong_t)value);
+ char buf[PATH_BUF_LEN];
+ char tmpbuf[PATH_BUF_LEN];
+
+ env = getenv("ZPOOL_VDEV_NAME_PATH");
+ if (env && (strtoul(env, NULL, 0) > 0 ||
+ !strncasecmp(env, "YES", 3) || !strncasecmp(env, "ON", 2)))
+ name_flags |= VDEV_NAME_PATH;
+
+ env = getenv("ZPOOL_VDEV_NAME_GUID");
+ if (env && (strtoul(env, NULL, 0) > 0 ||
+ !strncasecmp(env, "YES", 3) || !strncasecmp(env, "ON", 2)))
+ name_flags |= VDEV_NAME_GUID;
+
+ env = getenv("ZPOOL_VDEV_NAME_FOLLOW_LINKS");
+ if (env && (strtoul(env, NULL, 0) > 0 ||
+ !strncasecmp(env, "YES", 3) || !strncasecmp(env, "ON", 2)))
+ name_flags |= VDEV_NAME_FOLLOW_LINKS;
+
+ if (nvlist_lookup_uint64(nv, ZPOOL_CONFIG_NOT_PRESENT, &value) == 0 ||
+ name_flags & VDEV_NAME_GUID) {
+ nvlist_lookup_uint64(nv, ZPOOL_CONFIG_GUID, &value);
+ (void) snprintf(buf, sizeof (buf), "%llu", (u_longlong_t)value);
path = buf;
} else if (nvlist_lookup_string(nv, ZPOOL_CONFIG_PATH, &path) == 0) {
+#if defined(__sun__) || defined(__sun)
+ /*
+ * Live VDEV path updates to a kernel VDEV during a
+ * zpool_vdev_name lookup are not supported on Linux.
+ */
+ char *devid;
+ vdev_stat_t *vs;
+ uint_t vsc;
/*
* If the device is dead (faulted, offline, etc) then don't
* open a misbehaving device, which can have undesirable
* effects.
*/
- if ((nvlist_lookup_uint64_array(nv, ZPOOL_CONFIG_STATS,
+ if ((nvlist_lookup_uint64_array(nv, ZPOOL_CONFIG_VDEV_STATS,
(uint64_t **)&vs, &vsc) != 0 ||
vs->vs_state >= VDEV_STATE_DEGRADED) &&
zhp != NULL &&
if (newdevid)
devid_str_free(newdevid);
}
+#endif /* sun */
+
+ if (name_flags & VDEV_NAME_FOLLOW_LINKS) {
+ char *rp = realpath(path, NULL);
+ if (rp) {
+ strlcpy(buf, rp, sizeof (buf));
+ path = buf;
+ free(rp);
+ }
+ }
- if (strncmp(path, "/dev/dsk/", 9) == 0)
- path += 9;
+ /*
+ * For a block device only use the name.
+ */
+ verify(nvlist_lookup_string(nv, ZPOOL_CONFIG_TYPE, &type) == 0);
+ if ((strcmp(type, VDEV_TYPE_DISK) == 0) &&
+ !(name_flags & VDEV_NAME_PATH)) {
+ path = strrchr(path, '/');
+ path++;
+ }
- if (nvlist_lookup_uint64(nv, ZPOOL_CONFIG_WHOLE_DISK,
- &value) == 0 && value) {
- char *tmp = zfs_strdup(hdl, path);
- if (tmp == NULL)
- return (NULL);
- tmp[strlen(path) - 2] = '\0';
- return (tmp);
+ /*
+ * Remove the partition from the path it this is a whole disk.
+ */
+ if (nvlist_lookup_uint64(nv, ZPOOL_CONFIG_WHOLE_DISK, &value)
+ == 0 && value && !(name_flags & VDEV_NAME_PATH)) {
+ return (strip_partition(hdl, path));
}
} else {
verify(nvlist_lookup_string(nv, ZPOOL_CONFIG_TYPE, &path) == 0);
(u_longlong_t)value);
path = buf;
}
+
+ /*
+ * We identify each top-level vdev by using a <type-id>
+ * naming convention.
+ */
+ if (name_flags & VDEV_NAME_TYPE_ID) {
+ uint64_t id;
+ verify(nvlist_lookup_uint64(nv, ZPOOL_CONFIG_ID,
+ &id) == 0);
+ (void) snprintf(tmpbuf, sizeof (tmpbuf), "%s-%llu",
+ path, (u_longlong_t)id);
+ path = tmpbuf;
+ }
}
return (zfs_strdup(hdl, path));
}
static int
-zbookmark_compare(const void *a, const void *b)
+zbookmark_mem_compare(const void *a, const void *b)
{
- return (memcmp(a, b, sizeof (zbookmark_t)));
+ return (memcmp(a, b, sizeof (zbookmark_phys_t)));
}
/*
int
zpool_get_errlog(zpool_handle_t *zhp, nvlist_t **nverrlistp)
{
- zfs_cmd_t zc = { 0 };
+ zfs_cmd_t zc = {"\0"};
uint64_t count;
- zbookmark_t *zb = NULL;
+ zbookmark_phys_t *zb = NULL;
int i;
/*
if (count == 0)
return (0);
if ((zc.zc_nvlist_dst = (uintptr_t)zfs_alloc(zhp->zpool_hdl,
- count * sizeof (zbookmark_t))) == (uintptr_t)NULL)
+ count * sizeof (zbookmark_phys_t))) == (uintptr_t)NULL)
return (-1);
zc.zc_nvlist_dst_size = count;
(void) strcpy(zc.zc_name, zhp->zpool_name);
&zc) != 0) {
free((void *)(uintptr_t)zc.zc_nvlist_dst);
if (errno == ENOMEM) {
+ void *dst;
+
count = zc.zc_nvlist_dst_size;
- if ((zc.zc_nvlist_dst = (uintptr_t)
- zfs_alloc(zhp->zpool_hdl, count *
- sizeof (zbookmark_t))) == (uintptr_t)NULL)
+ dst = zfs_alloc(zhp->zpool_hdl, count *
+ sizeof (zbookmark_phys_t));
+ if (dst == NULL)
return (-1);
+ zc.zc_nvlist_dst = (uintptr_t)dst;
} else {
return (-1);
}
* _not_ copied as part of the process. So we point the start of our
* array appropriate and decrement the total number of elements.
*/
- zb = ((zbookmark_t *)(uintptr_t)zc.zc_nvlist_dst) +
+ zb = ((zbookmark_phys_t *)(uintptr_t)zc.zc_nvlist_dst) +
zc.zc_nvlist_dst_size;
count -= zc.zc_nvlist_dst_size;
- qsort(zb, count, sizeof (zbookmark_t), zbookmark_compare);
+ qsort(zb, count, sizeof (zbookmark_phys_t), zbookmark_mem_compare);
verify(nvlist_alloc(nverrlistp, 0, KM_SLEEP) == 0);
int
zpool_upgrade(zpool_handle_t *zhp, uint64_t new_version)
{
- zfs_cmd_t zc = { 0 };
+ zfs_cmd_t zc = {"\0"};
libzfs_handle_t *hdl = zhp->zpool_hdl;
(void) strcpy(zc.zc_name, zhp->zpool_name);
}
void
-zpool_set_history_str(const char *subcommand, int argc, char **argv,
- char *history_str)
+zfs_save_arguments(int argc, char **argv, char *string, int len)
{
int i;
- (void) strlcpy(history_str, subcommand, HIS_MAX_RECORD_LEN);
+ (void) strlcpy(string, basename(argv[0]), len);
for (i = 1; i < argc; i++) {
- if (strlen(history_str) + 1 + strlen(argv[i]) >
- HIS_MAX_RECORD_LEN)
- break;
- (void) strlcat(history_str, " ", HIS_MAX_RECORD_LEN);
- (void) strlcat(history_str, argv[i], HIS_MAX_RECORD_LEN);
+ (void) strlcat(string, " ", len);
+ (void) strlcat(string, argv[i], len);
}
}
-/*
- * Stage command history for logging.
- */
int
-zpool_stage_history(libzfs_handle_t *hdl, const char *history_str)
+zpool_log_history(libzfs_handle_t *hdl, const char *message)
{
- if (history_str == NULL)
- return (EINVAL);
-
- if (strlen(history_str) > HIS_MAX_RECORD_LEN)
- return (EINVAL);
-
- if (hdl->libzfs_log_str != NULL)
- free(hdl->libzfs_log_str);
-
- if ((hdl->libzfs_log_str = strdup(history_str)) == NULL)
- return (no_memory(hdl));
-
- return (0);
+ zfs_cmd_t zc = {"\0"};
+ nvlist_t *args;
+ int err;
+
+ args = fnvlist_alloc();
+ fnvlist_add_string(args, "message", message);
+ err = zcmd_write_src_nvlist(hdl, &zc, args);
+ if (err == 0)
+ err = ioctl(hdl->libzfs_fd, ZFS_IOC_LOG_HISTORY, &zc);
+ nvlist_free(args);
+ zcmd_free_nvlists(&zc);
+ return (err);
}
/*
static int
get_history(zpool_handle_t *zhp, char *buf, uint64_t *off, uint64_t *len)
{
- zfs_cmd_t zc = { 0 };
+ zfs_cmd_t zc = {"\0"};
libzfs_handle_t *hdl = zhp->zpool_hdl;
(void) strlcpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
* into 'records'. 'leftover' is set to the number of bytes that weren't
* processed as there wasn't a complete record.
*/
-static int
+int
zpool_history_unpack(char *buf, uint64_t bytes_read, uint64_t *leftover,
nvlist_t ***records, uint_t *numrecords)
{
return (0);
}
-#define HIS_BUF_LEN (128*1024)
-
/*
* Retrieve the command history of a pool.
*/
int
zpool_get_history(zpool_handle_t *zhp, nvlist_t **nvhisp)
{
- char buf[HIS_BUF_LEN];
+ char *buf;
+ int buflen = 128 * 1024;
uint64_t off = 0;
nvlist_t **records = NULL;
uint_t numrecords = 0;
int err, i;
+ buf = malloc(buflen);
+ if (buf == NULL)
+ return (ENOMEM);
do {
- uint64_t bytes_read = sizeof (buf);
+ uint64_t bytes_read = buflen;
uint64_t leftover;
if ((err = get_history(zhp, buf, &off, &bytes_read)) != 0)
&leftover, &records, &numrecords)) != 0)
break;
off -= leftover;
+ if (leftover == bytes_read) {
+ /*
+ * no progress made, because buffer is not big enough
+ * to hold this record; resize and retry.
+ */
+ buflen *= 2;
+ free(buf);
+ buf = malloc(buflen);
+ if (buf == NULL)
+ return (ENOMEM);
+ }
/* CONSTCOND */
} while (1);
+ free(buf);
+
if (!err) {
verify(nvlist_alloc(nvhisp, NV_UNIQUE_NAME, 0) == 0);
verify(nvlist_add_nvlist_array(*nvhisp, ZPOOL_HIST_RECORD,
return (err);
}
+/*
+ * Retrieve the next event given the passed 'zevent_fd' file descriptor.
+ * If there is a new event available 'nvp' will contain a newly allocated
+ * nvlist and 'dropped' will be set to the number of missed events since
+ * the last call to this function. When 'nvp' is set to NULL it indicates
+ * no new events are available. In either case the function returns 0 and
+ * it is up to the caller to free 'nvp'. In the case of a fatal error the
+ * function will return a non-zero value. When the function is called in
+ * blocking mode (the default, unless the ZEVENT_NONBLOCK flag is passed),
+ * it will not return until a new event is available.
+ */
+int
+zpool_events_next(libzfs_handle_t *hdl, nvlist_t **nvp,
+ int *dropped, unsigned flags, int zevent_fd)
+{
+ zfs_cmd_t zc = {"\0"};
+ int error = 0;
+
+ *nvp = NULL;
+ *dropped = 0;
+ zc.zc_cleanup_fd = zevent_fd;
+
+ if (flags & ZEVENT_NONBLOCK)
+ zc.zc_guid = ZEVENT_NONBLOCK;
+
+ if (zcmd_alloc_dst_nvlist(hdl, &zc, ZEVENT_SIZE) != 0)
+ return (-1);
+
+retry:
+ if (zfs_ioctl(hdl, ZFS_IOC_EVENTS_NEXT, &zc) != 0) {
+ switch (errno) {
+ case ESHUTDOWN:
+ error = zfs_error_fmt(hdl, EZFS_POOLUNAVAIL,
+ dgettext(TEXT_DOMAIN, "zfs shutdown"));
+ goto out;
+ case ENOENT:
+ /* Blocking error case should not occur */
+ if (!(flags & ZEVENT_NONBLOCK))
+ error = zpool_standard_error_fmt(hdl, errno,
+ dgettext(TEXT_DOMAIN, "cannot get event"));
+
+ goto out;
+ case ENOMEM:
+ if (zcmd_expand_dst_nvlist(hdl, &zc) != 0) {
+ error = zfs_error_fmt(hdl, EZFS_NOMEM,
+ dgettext(TEXT_DOMAIN, "cannot get event"));
+ goto out;
+ } else {
+ goto retry;
+ }
+ default:
+ error = zpool_standard_error_fmt(hdl, errno,
+ dgettext(TEXT_DOMAIN, "cannot get event"));
+ goto out;
+ }
+ }
+
+ error = zcmd_read_dst_nvlist(hdl, &zc, nvp);
+ if (error != 0)
+ goto out;
+
+ *dropped = (int)zc.zc_cookie;
+out:
+ zcmd_free_nvlists(&zc);
+
+ return (error);
+}
+
+/*
+ * Clear all events.
+ */
+int
+zpool_events_clear(libzfs_handle_t *hdl, int *count)
+{
+ zfs_cmd_t zc = {"\0"};
+ char msg[1024];
+
+ (void) snprintf(msg, sizeof (msg), dgettext(TEXT_DOMAIN,
+ "cannot clear events"));
+
+ if (zfs_ioctl(hdl, ZFS_IOC_EVENTS_CLEAR, &zc) != 0)
+ return (zpool_standard_error_fmt(hdl, errno, msg));
+
+ if (count != NULL)
+ *count = (int)zc.zc_cookie; /* # of events cleared */
+
+ return (0);
+}
+
+/*
+ * Seek to a specific EID, ZEVENT_SEEK_START, or ZEVENT_SEEK_END for
+ * the passed zevent_fd file handle. On success zero is returned,
+ * otherwise -1 is returned and hdl->libzfs_error is set to the errno.
+ */
+int
+zpool_events_seek(libzfs_handle_t *hdl, uint64_t eid, int zevent_fd)
+{
+ zfs_cmd_t zc = {"\0"};
+ int error = 0;
+
+ zc.zc_guid = eid;
+ zc.zc_cleanup_fd = zevent_fd;
+
+ if (zfs_ioctl(hdl, ZFS_IOC_EVENTS_SEEK, &zc) != 0) {
+ switch (errno) {
+ case ENOENT:
+ error = zfs_error_fmt(hdl, EZFS_NOENT,
+ dgettext(TEXT_DOMAIN, "cannot get event"));
+ break;
+
+ case ENOMEM:
+ error = zfs_error_fmt(hdl, EZFS_NOMEM,
+ dgettext(TEXT_DOMAIN, "cannot get event"));
+ break;
+
+ default:
+ error = zpool_standard_error_fmt(hdl, errno,
+ dgettext(TEXT_DOMAIN, "cannot get event"));
+ break;
+ }
+ }
+
+ return (error);
+}
+
void
zpool_obj_to_path(zpool_handle_t *zhp, uint64_t dsobj, uint64_t obj,
char *pathname, size_t len)
{
- zfs_cmd_t zc = { 0 };
+ zfs_cmd_t zc = {"\0"};
boolean_t mounted = B_FALSE;
char *mntpnt = NULL;
- char dsname[MAXNAMELEN];
+ char dsname[ZFS_MAX_DATASET_NAME_LEN];
if (dsobj == 0) {
/* special case for the MOS */
- (void) snprintf(pathname, len, "<metadata>:<0x%llx>", obj);
+ (void) snprintf(pathname, len, "<metadata>:<0x%llx>",
+ (longlong_t)obj);
return;
}
ZFS_IOC_DSOBJ_TO_DSNAME, &zc) != 0) {
/* just write out a path of two object numbers */
(void) snprintf(pathname, len, "<0x%llx>:<0x%llx>",
- dsobj, obj);
+ (longlong_t)dsobj, (longlong_t)obj);
return;
}
(void) strlcpy(dsname, zc.zc_value, sizeof (dsname));
dsname, zc.zc_value);
}
} else {
- (void) snprintf(pathname, len, "%s:<0x%llx>", dsname, obj);
+ (void) snprintf(pathname, len, "%s:<0x%llx>", dsname,
+ (longlong_t)obj);
}
free(mntpnt);
}
if (nvlist_lookup_string(config, ZPOOL_CONFIG_PATH, &path) != 0)
return (err);
- (void) snprintf(diskname, sizeof (diskname), "%s%s", RDISK_ROOT,
+ (void) snprintf(diskname, sizeof (diskname), "%s%s", DISK_ROOT,
strrchr(path, '/'));
- if ((fd = open(diskname, O_RDONLY|O_NDELAY)) >= 0) {
+ if ((fd = open(diskname, O_RDWR|O_DIRECT)) >= 0) {
struct dk_gpt *vtoc;
if ((err = efi_alloc_and_read(fd, &vtoc)) >= 0) {
return (MAXOFFSET_T);
}
+static int
+zpool_label_disk_check(char *path)
+{
+ struct dk_gpt *vtoc;
+ int fd, err;
+
+ if ((fd = open(path, O_RDWR|O_DIRECT)) < 0)
+ return (errno);
+
+ if ((err = efi_alloc_and_read(fd, &vtoc)) != 0) {
+ (void) close(fd);
+ return (err);
+ }
+
+ if (vtoc->efi_flags & EFI_GPT_PRIMARY_CORRUPT) {
+ efi_free(vtoc);
+ (void) close(fd);
+ return (EIDRM);
+ }
+
+ efi_free(vtoc);
+ (void) close(fd);
+ return (0);
+}
+
+/*
+ * Generate a unique partition name for the ZFS member. Partitions must
+ * have unique names to ensure udev will be able to create symlinks under
+ * /dev/disk/by-partlabel/ for all pool members. The partition names are
+ * of the form <pool>-<unique-id>.
+ */
+static void
+zpool_label_name(char *label_name, int label_size)
+{
+ uint64_t id = 0;
+ int fd;
+
+ fd = open("/dev/urandom", O_RDONLY);
+ if (fd > 0) {
+ if (read(fd, &id, sizeof (id)) != sizeof (id))
+ id = 0;
+
+ close(fd);
+ }
+
+ if (id == 0)
+ id = (((uint64_t)rand()) << 32) | (uint64_t)rand();
+
+ snprintf(label_name, label_size, "zfs-%016llx", (u_longlong_t) id);
+}
+
/*
* Label an individual disk. The name provided is the short name,
* stripped of any leading /dev path.
{
char path[MAXPATHLEN];
struct dk_gpt *vtoc;
- int fd;
+ int rval, fd;
size_t resv = EFI_MIN_RESV_SIZE;
uint64_t slice_size;
diskaddr_t start_block;
if (zhp) {
nvlist_t *nvroot;
- if (pool_is_bootable(zhp)) {
+#if defined(__sun__) || defined(__sun)
+ if (zpool_is_bootable(zhp)) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"EFI labeled devices are not supported on root "
"pools."));
return (zfs_error(hdl, EZFS_POOL_NOTSUP, errbuf));
}
+#endif
verify(nvlist_lookup_nvlist(zhp->zpool_config,
ZPOOL_CONFIG_VDEV_TREE, &nvroot) == 0);
start_block = NEW_START_BLOCK;
}
- (void) snprintf(path, sizeof (path), "%s/%s%s", RDISK_ROOT, name,
- BACKUP_SLICE);
+ (void) snprintf(path, sizeof (path), "%s/%s", DISK_ROOT, name);
- if ((fd = open(path, O_RDWR | O_NDELAY)) < 0) {
+ if ((fd = open(path, O_RDWR|O_DIRECT)) < 0) {
/*
* This shouldn't happen. We've long since verified that this
* is a valid device.
*/
- zfs_error_aux(hdl,
- dgettext(TEXT_DOMAIN, "unable to open device"));
+ zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "cannot "
+ "label '%s': unable to open device: %d"), path, errno);
return (zfs_error(hdl, EZFS_OPENFAILED, errbuf));
}
(void) no_memory(hdl);
(void) close(fd);
- zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
- "unable to read disk capacity"), name);
+ zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "cannot "
+ "label '%s': unable to read disk capacity"), path);
return (zfs_error(hdl, EZFS_NOCAP, errbuf));
}
if (start_block == MAXOFFSET_T)
start_block = NEW_START_BLOCK;
slice_size -= start_block;
+ slice_size = P2ALIGN(slice_size, PARTITION_END_ALIGNMENT);
vtoc->efi_parts[0].p_start = start_block;
vtoc->efi_parts[0].p_size = slice_size;
* can get, in the absence of V_OTHER.
*/
vtoc->efi_parts[0].p_tag = V_USR;
- (void) strcpy(vtoc->efi_parts[0].p_name, "zfs");
+ zpool_label_name(vtoc->efi_parts[0].p_name, EFI_PART_NAME_LEN);
vtoc->efi_parts[8].p_start = slice_size + start_block;
vtoc->efi_parts[8].p_size = resv;
vtoc->efi_parts[8].p_tag = V_RESERVED;
- if (efi_write(fd, vtoc) != 0) {
+ if ((rval = efi_write(fd, vtoc)) != 0 || (rval = efi_rescan(fd)) != 0) {
/*
* Some block drivers (like pcata) may not support EFI
* GPT labels. Print out a helpful error message dir-
(void) close(fd);
efi_free(vtoc);
- zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
- "try using fdisk(1M) and then provide a specific slice"));
+ zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "try using "
+ "parted(8) and then provide a specific slice: %d"), rval);
return (zfs_error(hdl, EZFS_LABELFAILED, errbuf));
}
(void) close(fd);
efi_free(vtoc);
- return (0);
-}
-
-static boolean_t
-supported_dump_vdev_type(libzfs_handle_t *hdl, nvlist_t *config, char *errbuf)
-{
- char *type;
- nvlist_t **child;
- uint_t children, c;
-
- verify(nvlist_lookup_string(config, ZPOOL_CONFIG_TYPE, &type) == 0);
- if (strcmp(type, VDEV_TYPE_RAIDZ) == 0 ||
- strcmp(type, VDEV_TYPE_FILE) == 0 ||
- strcmp(type, VDEV_TYPE_LOG) == 0 ||
- strcmp(type, VDEV_TYPE_MISSING) == 0) {
- zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
- "vdev type '%s' is not supported"), type);
- (void) zfs_error(hdl, EZFS_VDEVNOTSUP, errbuf);
- return (B_FALSE);
- }
- if (nvlist_lookup_nvlist_array(config, ZPOOL_CONFIG_CHILDREN,
- &child, &children) == 0) {
- for (c = 0; c < children; c++) {
- if (!supported_dump_vdev_type(hdl, child[c], errbuf))
- return (B_FALSE);
- }
- }
- return (B_TRUE);
-}
-
-/*
- * check if this zvol is allowable for use as a dump device; zero if
- * it is, > 0 if it isn't, < 0 if it isn't a zvol
- */
-int
-zvol_check_dump_config(char *arg)
-{
- zpool_handle_t *zhp = NULL;
- nvlist_t *config, *nvroot;
- char *p, *volname;
- nvlist_t **top;
- uint_t toplevels;
- libzfs_handle_t *hdl;
- char errbuf[1024];
- char poolname[ZPOOL_MAXNAMELEN];
- int pathlen = strlen(ZVOL_FULL_DEV_DIR);
- int ret = 1;
-
- if (strncmp(arg, ZVOL_FULL_DEV_DIR, pathlen)) {
- return (-1);
- }
-
- (void) snprintf(errbuf, sizeof (errbuf), dgettext(TEXT_DOMAIN,
- "dump is not supported on device '%s'"), arg);
- if ((hdl = libzfs_init()) == NULL)
- return (1);
- libzfs_print_on_error(hdl, B_TRUE);
+ (void) snprintf(path, sizeof (path), "%s/%s", DISK_ROOT, name);
+ (void) zfs_append_partition(path, MAXPATHLEN);
- volname = arg + pathlen;
-
- /* check the configuration of the pool */
- if ((p = strchr(volname, '/')) == NULL) {
- zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
- "malformed dataset name"));
- (void) zfs_error(hdl, EZFS_INVALIDNAME, errbuf);
- return (1);
- } else if (p - volname >= ZFS_MAXNAMELEN) {
- zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
- "dataset name is too long"));
- (void) zfs_error(hdl, EZFS_NAMETOOLONG, errbuf);
- return (1);
- } else {
- (void) strncpy(poolname, volname, p - volname);
- poolname[p - volname] = '\0';
- }
-
- if ((zhp = zpool_open(hdl, poolname)) == NULL) {
- zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
- "could not open pool '%s'"), poolname);
- (void) zfs_error(hdl, EZFS_OPENFAILED, errbuf);
- goto out;
- }
- config = zpool_get_config(zhp, NULL);
- if (nvlist_lookup_nvlist(config, ZPOOL_CONFIG_VDEV_TREE,
- &nvroot) != 0) {
- zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
- "could not obtain vdev configuration for '%s'"), poolname);
- (void) zfs_error(hdl, EZFS_INVALCONFIG, errbuf);
- goto out;
- }
-
- verify(nvlist_lookup_nvlist_array(nvroot, ZPOOL_CONFIG_CHILDREN,
- &top, &toplevels) == 0);
- if (toplevels != 1) {
- zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
- "'%s' has multiple top level vdevs"), poolname);
- (void) zfs_error(hdl, EZFS_DEVOVERFLOW, errbuf);
- goto out;
+ /* Wait to udev to signal use the device has settled. */
+ rval = zpool_label_disk_wait(path, DISK_LABEL_WAIT);
+ if (rval) {
+ zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "failed to "
+ "detect device partitions on '%s': %d"), path, rval);
+ return (zfs_error(hdl, EZFS_LABELFAILED, errbuf));
}
- if (!supported_dump_vdev_type(hdl, top[0], errbuf)) {
- goto out;
+ /* We can't be to paranoid. Read the label back and verify it. */
+ (void) snprintf(path, sizeof (path), "%s/%s", DISK_ROOT, name);
+ rval = zpool_label_disk_check(path);
+ if (rval) {
+ zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "freshly written "
+ "EFI label on '%s' is damaged. Ensure\nthis device "
+ "is not in in use, and is functioning properly: %d"),
+ path, rval);
+ return (zfs_error(hdl, EZFS_LABELFAILED, errbuf));
}
- ret = 0;
-out:
- if (zhp)
- zpool_close(zhp);
- libzfs_fini(hdl);
- return (ret);
+ return (0);
}