*/
/*
- * Copyright 2009 Sun Microsystems, Inc. All rights reserved.
- * Use is subject to license terms.
+ * Copyright (c) 2005, 2010, Oracle and/or its affiliates. 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 <zone.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"
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;
+
/*
* ====================================================================
* zpool property functions
static int
zpool_get_all_props(zpool_handle_t *zhp)
{
- zfs_cmd_t zc = { 0 };
+ zfs_cmd_t zc = { "\0", "\0", "\0", "\0", 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:
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:
switch (prop) {
case ZPOOL_PROP_SIZE:
- case ZPOOL_PROP_USED:
- case ZPOOL_PROP_AVAILABLE:
+ case ZPOOL_PROP_ALLOCATED:
+ case ZPOOL_PROP_FREE:
(void) zfs_nicenum(intval, buf, len);
break;
(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);
+ ZPOOL_CONFIG_VDEV_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", intval);
+ (void) snprintf(buf, len, "%llu", (u_longlong_t)intval);
}
break;
*/
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;
* Perform additional checking for specific properties.
*/
switch (prop) {
+ default:
+ break;
case ZPOOL_PROP_VERSION:
if (intval < version || intval > SPA_VERSION) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
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);
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_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;
}
}
int
zpool_set_prop(zpool_handle_t *zhp, const char *propname, const char *propval)
{
- zfs_cmd_t zc = { 0 };
+ zfs_cmd_t zc = { "\0", "\0", "\0", "\0", 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);
}
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);
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", "\0", "\0", "\0", 0 };
nvlist_t *zc_fsprops = NULL;
nvlist_t *zc_props = NULL;
char msg[1024];
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;
}
}
int
zpool_destroy(zpool_handle_t *zhp)
{
- zfs_cmd_t zc = { 0 };
+ zfs_cmd_t zc = { "\0", "\0", "\0", "\0", 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));
- 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", "\0", "\0", "\0", 0 };
int ret;
libzfs_handle_t *hdl = zhp->zpool_hdl;
char msg[1024];
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],
+ B_FALSE));
return (zfs_error(hdl, EZFS_POOL_NOTSUP, msg));
}
}
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:
/*
int
zpool_export_common(zpool_handle_t *zhp, boolean_t force, boolean_t hardforce)
{
- zfs_cmd_t zc = { 0 };
+ zfs_cmd_t zc = { "\0", "\0", "\0", "\0", 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);
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 *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)
+ 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)
+{
+ 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_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"));
+}
+
/*
* zpool_import() is a contracted interface. Should be kept the same
* if possible.
}
}
- ret = zpool_import_props(hdl, config, newname, props, B_FALSE);
+ ret = zpool_import_props(hdl, config, newname, props,
+ ZFS_IMPORT_NORMAL);
if (props)
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], B_TRUE);
+ print_vdev_tree(hdl, vname, child[c], indent + 2);
+ free(vname);
+ }
+}
+
/*
* 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", "\0", "\0", "\0", 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,
if (props) {
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) {
nvlist_free(props);
nvlist_free(props);
return (-1);
}
+ if (zcmd_alloc_dst_nvlist(hdl, &zc, zc.zc_nvlist_conf_size * 2) != 0) {
+ nvlist_free(props);
+ 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);
+ 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:
/*
* Unsupported version.
(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;
+
+ 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;
+
default:
- (void) zpool_standard_error(hdl, errno, desc);
+ (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);
}
/*
- * 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", "\0", "\0", "\0", 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));
+ }
+}
+
+/*
+ * This provides a very minimal check whether a given string is likely a
+ * c#t#d# style string. Users of this are expected to do their own
+ * verification of the s# part.
+ */
+#define CTD_CHECK(str) (str && str[0] == 'c' && isdigit(str[1]))
+
+/*
+ * More elaborate version for ones which may start with "/dev/dsk/"
+ * and the like.
+ */
+static int
+ctd_check_path(char *str) {
+ /*
+ * If it starts with a slash, check the last component.
+ */
+ if (str && str[0] == '/') {
+ char *tmp = strrchr(str, '/');
+
+ /*
+ * If it ends in "/old", check the second-to-last
+ * component of the string instead.
+ */
+ if (tmp != str && strcmp(tmp, "/old") == 0) {
+ for (tmp--; *tmp != '/'; tmp--)
+ ;
+ }
+ str = tmp + 1;
+ }
+ return (CTD_CHECK(str));
}
/*
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
+ * "s0" or "s0/old". The "s0" part is hidden from the user,
+ * but included in the string, so this matches around it.
+ * - 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 &&
+ ctd_check_path(val)) {
uint64_t wholedisk = 0;
(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_WHOLE_DISK,
&wholedisk);
if (wholedisk) {
+ int slen = strlen(srchval);
+ int vlen = strlen(val);
+
+ if (slen != vlen - 2)
+ break;
+
/*
- * For whole disks, the internal path has 's0',
- * but the path passed in by the user doesn't.
+ * make_leaf_vdev() should only set
+ * wholedisk for ZPOOL_CONFIG_PATHs which
+ * will include "/dev/dsk/", giving plenty of
+ * room for the indices used next.
*/
- if (strlen(srchval) == strlen(val) - 2 &&
- strncmp(srchval, val, strlen(srchval)) == 0)
+ ASSERT(vlen >= 6);
+
+ /*
+ * strings identical except trailing "s0"
+ */
+ if (strcmp(&val[vlen - 2], "s0") == 0 &&
+ strncmp(srchval, val, slen) == 0)
return (nv);
+
+ /*
+ * strings identical except trailing "s0/old"
+ */
+ if (strcmp(&val[vlen - 6], "s0/old") == 0 &&
+ strcmp(&srchval[slen - 4], "/old") == 0 &&
+ strncmp(srchval, val, slen - 4) == 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);
}
/*
&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)
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);
}
/*
- * 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.
*/
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", "\0", "\0", "\0", 0 };
char msg[1024];
nvlist_t *tgt;
boolean_t avail_spare, l2cache, islog;
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 ||
if (wholedisk) {
pathname += strlen(DISK_ROOT) + 1;
- (void) zpool_relabel_disk(zhp->zpool_hdl, pathname);
+ (void) zpool_relabel_disk(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 (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", "\0", "\0", "\0", 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", "\0", "\0", "\0", 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", "\0", "\0", "\0", 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", "\0", "\0", "\0", 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;
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], B_FALSE)) == 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"));
int
zpool_vdev_detach(zpool_handle_t *zhp, const char *path)
{
- zfs_cmd_t zc = { 0 };
+ zfs_cmd_t zc = { "\0", "\0", "\0", "\0", 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:
}
/*
+ * 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", "\0", "\0", "\0", 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"));
+ 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 };
+ zfs_cmd_t zc = { "\0", "\0", "\0", "\0", 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", "\0", "\0", "\0", 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", "\0", "\0", "\0", 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.
- */
-int
-zpool_iter_zvol(zpool_handle_t *zhp, int (*cb)(const char *, void *),
- void *data)
-{
- 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);
-
- if (fstatat(base, zhp->zpool_name, &st, 0) != 0) {
- int err = errno;
- (void) close(base);
- return (err == ENOENT ? 0 : -1);
- }
-
- /*
- * 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);
- 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);
-}
-
-/*
- * Iterate over all zvols in the pool and make any necessary minor nodes.
- */
-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_handle_t *zhp = data;
-
- return (zvol_remove_link(zhp->zpool_hdl, dataset));
-}
-
-/*
- * 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));
-}
-
-/*
* Convert from a devid string to a path.
*/
static char *
static void
set_path(zpool_handle_t *zhp, nvlist_t *nv, const char *path)
{
- zfs_cmd_t zc = { 0 };
+ zfs_cmd_t zc = { "\0", "\0", "\0", "\0", 0 };
(void) strncpy(zc.zc_name, zhp->zpool_name, sizeof (zc.zc_name));
(void) strncpy(zc.zc_value, path, sizeof (zc.zc_value));
* 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,
+ boolean_t verbose)
{
char *path, *devid;
uint64_t value;
* 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 (nvlist_lookup_uint64(nv, ZPOOL_CONFIG_WHOLE_DISK,
&value) == 0 && value) {
+ int pathlen = strlen(path);
char *tmp = zfs_strdup(hdl, path);
- if (tmp == NULL)
- return (NULL);
- tmp[strlen(path) - 2] = '\0';
+
+ /*
+ * If it starts with c#, and ends with "s0", chop
+ * the "s0" off, or if it ends with "s0/old", remove
+ * the "s0" from the middle.
+ */
+ if (CTD_CHECK(tmp)) {
+ if (strcmp(&tmp[pathlen - 2], "s0") == 0) {
+ tmp[pathlen - 2] = '\0';
+ } else if (pathlen > 6 &&
+ strcmp(&tmp[pathlen - 6], "s0/old") == 0) {
+ (void) strcpy(&tmp[pathlen - 6],
+ "/old");
+ }
+ }
return (tmp);
}
} else {
(u_longlong_t)value);
path = buf;
}
+
+ /*
+ * We identify each top-level vdev by using a <type-id>
+ * naming convention.
+ */
+ if (verbose) {
+ uint64_t id;
+
+ verify(nvlist_lookup_uint64(nv, ZPOOL_CONFIG_ID,
+ &id) == 0);
+ (void) snprintf(buf, sizeof (buf), "%s-%llu", path,
+ (u_longlong_t)id);
+ path = buf;
+ }
}
return (zfs_strdup(hdl, path));
int
zpool_get_errlog(zpool_handle_t *zhp, nvlist_t **nverrlistp)
{
- zfs_cmd_t zc = { 0 };
+ zfs_cmd_t zc = { "\0", "\0", "\0", "\0", 0 };
uint64_t count;
zbookmark_t *zb = NULL;
int i;
int
zpool_upgrade(zpool_handle_t *zhp, uint64_t new_version)
{
- zfs_cmd_t zc = { 0 };
+ zfs_cmd_t zc = { "\0", "\0", "\0", "\0", 0 };
libzfs_handle_t *hdl = zhp->zpool_hdl;
(void) strcpy(zc.zc_name, zhp->zpool_name);
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", "\0", "\0", "\0", 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)
{
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", "\0", "\0", "\0", 0 };
boolean_t mounted = B_FALSE;
char *mntpnt = NULL;
char dsname[MAXNAMELEN];
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 (strcmp(type, VDEV_TYPE_RAIDZ) == 0 ||
strcmp(type, VDEV_TYPE_FILE) == 0 ||
strcmp(type, VDEV_TYPE_LOG) == 0 ||
+ strcmp(type, VDEV_TYPE_HOLE) == 0 ||
strcmp(type, VDEV_TYPE_MISSING) == 0) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"vdev type '%s' is not supported"), type);