/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
+ * Copyright 2011 Nexenta Systems, Inc. All rights reserved.
+ * Copyright (c) 2011, 2015 by Delphix. All rights reserved.
+ * Copyright 2017 Joyent, Inc.
*/
#include <sys/spa.h>
+#include <sys/fm/fs/zfs.h>
#include <sys/spa_impl.h>
#include <sys/nvpair.h>
#include <sys/uio.h>
#include <sys/fs/zfs.h>
#include <sys/vdev_impl.h>
#include <sys/zfs_ioctl.h>
-#include <sys/utsname.h>
#include <sys/systeminfo.h>
#include <sys/sunddi.h>
+#include <sys/zfeature.h>
#ifdef _KERNEL
#include <sys/kobj.h>
#include <sys/zone.h>
* configuration information. When the module loads, we read this information
* from /etc/zfs/zpool.cache and populate the SPA namespace. This namespace is
* maintained independently in spa.c. Whenever the namespace is modified, or
- * the configuration of a pool is changed, we call spa_config_sync(), which
+ * the configuration of a pool is changed, we call spa_write_cachefile(), which
* walks through all the active pools and writes the configuration to disk.
*/
* userland pools when doing testing.
*/
char *spa_config_path = ZPOOL_CACHE;
+int zfs_autoimport_disable = 1;
/*
* Called when the module is first loaded, this routine loads the configuration
struct _buf *file;
uint64_t fsize;
+#ifdef _KERNEL
+ if (zfs_autoimport_disable)
+ return;
+#endif
+
/*
* Open the configuration file.
*/
if (kobj_get_filesize(file, &fsize) != 0)
goto out;
- buf = kmem_alloc(fsize, KM_SLEEP | KM_NODEBUG);
+ buf = kmem_alloc(fsize, KM_SLEEP);
/*
* Read the nvlist from the file.
if (nvpair_type(nvpair) != DATA_TYPE_NVLIST)
continue;
- VERIFY(nvpair_value_nvlist(nvpair, &child) == 0);
+ child = fnvpair_value_nvlist(nvpair);
if (spa_lookup(nvpair_name(nvpair)) != NULL)
continue;
kobj_close_file(file);
}
-static void
+static int
+spa_config_remove(spa_config_dirent_t *dp)
+{
+#if defined(__linux__) && defined(_KERNEL)
+ int error, flags = FWRITE | FTRUNC;
+ uio_seg_t seg = UIO_SYSSPACE;
+ vnode_t *vp;
+
+ error = vn_open(dp->scd_path, seg, flags, 0644, &vp, 0, 0);
+ if (error == 0) {
+ (void) VOP_FSYNC(vp, FSYNC, kcred, NULL);
+ (void) VOP_CLOSE(vp, 0, 1, 0, kcred, NULL);
+ }
+
+ return (error);
+#else
+ return (vn_remove(dp->scd_path, UIO_SYSSPACE, RMFILE));
+#endif
+}
+
+static int
spa_config_write(spa_config_dirent_t *dp, nvlist_t *nvl)
{
size_t buflen;
vnode_t *vp;
int oflags = FWRITE | FTRUNC | FCREAT | FOFFMAX;
char *temp;
+ int err;
/*
* If the nvlist is empty (NULL), then remove the old cachefile.
*/
if (nvl == NULL) {
- (void) vn_remove(dp->scd_path, UIO_SYSSPACE, RMFILE);
- return;
+ err = spa_config_remove(dp);
+ if (err == ENOENT)
+ err = 0;
+
+ return (err);
}
/*
* Pack the configuration into a buffer.
*/
- VERIFY(nvlist_size(nvl, &buflen, NV_ENCODE_XDR) == 0);
-
- buf = kmem_alloc(buflen, KM_SLEEP | KM_NODEBUG);
+ buf = fnvlist_pack(nvl, &buflen);
temp = kmem_zalloc(MAXPATHLEN, KM_SLEEP);
- VERIFY(nvlist_pack(nvl, &buf, &buflen, NV_ENCODE_XDR,
- KM_SLEEP) == 0);
+#if defined(__linux__) && defined(_KERNEL)
+ /*
+ * Write the configuration to disk. Due to the complexity involved
+ * in performing a rename and remove from within the kernel the file
+ * is instead truncated and overwritten in place. This way we always
+ * have a consistent view of the data or a zero length file.
+ */
+ err = vn_open(dp->scd_path, UIO_SYSSPACE, oflags, 0644, &vp, 0, 0);
+ if (err == 0) {
+ err = vn_rdwr(UIO_WRITE, vp, buf, buflen, 0,
+ UIO_SYSSPACE, 0, RLIM64_INFINITY, kcred, NULL);
+ if (err == 0)
+ err = VOP_FSYNC(vp, FSYNC, kcred, NULL);
+ (void) VOP_CLOSE(vp, oflags, 1, 0, kcred, NULL);
+ if (err)
+ (void) spa_config_remove(dp);
+ }
+#else
/*
* Write the configuration to disk. We need to do the traditional
* 'write to temporary file, sync, move over original' to make sure we
*/
(void) snprintf(temp, MAXPATHLEN, "%s.tmp", dp->scd_path);
- if (vn_open(temp, UIO_SYSSPACE, oflags, 0644, &vp, CRCREAT, 0) == 0) {
- if (vn_rdwr(UIO_WRITE, vp, buf, buflen, 0, UIO_SYSSPACE,
- 0, RLIM64_INFINITY, kcred, NULL) == 0 &&
- VOP_FSYNC(vp, FSYNC, kcred, NULL) == 0) {
- (void) vn_rename(temp, dp->scd_path, UIO_SYSSPACE);
- }
+ err = vn_open(temp, UIO_SYSSPACE, oflags, 0644, &vp, CRCREAT, 0);
+ if (err == 0) {
+ err = vn_rdwr(UIO_WRITE, vp, buf, buflen, 0, UIO_SYSSPACE,
+ 0, RLIM64_INFINITY, kcred, NULL);
+ if (err == 0)
+ err = VOP_FSYNC(vp, FSYNC, kcred, NULL);
+ if (err == 0)
+ err = vn_rename(temp, dp->scd_path, UIO_SYSSPACE);
(void) VOP_CLOSE(vp, oflags, 1, 0, kcred, NULL);
}
(void) vn_remove(temp, UIO_SYSSPACE, RMFILE);
+#endif
- kmem_free(buf, buflen);
+ fnvlist_pack_free(buf, buflen);
kmem_free(temp, MAXPATHLEN);
+ return (err);
}
/*
* Synchronize pool configuration to disk. This must be called with the
- * namespace lock held.
+ * namespace lock held. Synchronizing the pool cache is typically done after
+ * the configuration has been synced to the MOS. This exposes a window where
+ * the MOS config will have been updated but the cache file has not. If
+ * the system were to crash at that instant then the cached config may not
+ * contain the correct information to open the pool and an explicit import
+ * would be required.
*/
void
-spa_config_sync(spa_t *target, boolean_t removing, boolean_t postsysevent)
+spa_write_cachefile(spa_t *target, boolean_t removing, boolean_t postsysevent)
{
spa_config_dirent_t *dp, *tdp;
nvlist_t *nvl;
+ char *pool_name;
+ boolean_t ccw_failure;
+ int error = 0;
ASSERT(MUTEX_HELD(&spa_namespace_lock));
* cachefile is changed, the new one is pushed onto this list, allowing
* us to update previous cachefiles that no longer contain this pool.
*/
+ ccw_failure = B_FALSE;
for (dp = list_head(&target->spa_config_list); dp != NULL;
dp = list_next(&target->spa_config_list, dp)) {
spa_t *spa = NULL;
*/
nvl = NULL;
while ((spa = spa_next(spa)) != NULL) {
- if (spa == target && removing)
+ /*
+ * Skip over our own pool if we're about to remove
+ * ourselves from the spa namespace or any pool that
+ * is readonly. Since we cannot guarantee that a
+ * readonly pool would successfully import upon reboot,
+ * we don't allow them to be written to the cache file.
+ */
+ if ((spa == target && removing) ||
+ !spa_writeable(spa))
continue;
mutex_enter(&spa->spa_props_lock);
tdp = list_head(&spa->spa_config_list);
if (spa->spa_config == NULL ||
+ tdp == NULL ||
tdp->scd_path == NULL ||
strcmp(tdp->scd_path, dp->scd_path) != 0) {
mutex_exit(&spa->spa_props_lock);
}
if (nvl == NULL)
- VERIFY(nvlist_alloc(&nvl, NV_UNIQUE_NAME,
- KM_SLEEP) == 0);
+ nvl = fnvlist_alloc();
- VERIFY(nvlist_add_nvlist(nvl, spa->spa_name,
- spa->spa_config) == 0);
+ if (spa->spa_import_flags & ZFS_IMPORT_TEMP_NAME)
+ pool_name = fnvlist_lookup_string(
+ spa->spa_config, ZPOOL_CONFIG_POOL_NAME);
+ else
+ pool_name = spa_name(spa);
+
+ fnvlist_add_nvlist(nvl, pool_name, spa->spa_config);
mutex_exit(&spa->spa_props_lock);
}
- spa_config_write(dp, nvl);
+ error = spa_config_write(dp, nvl);
+ if (error != 0)
+ ccw_failure = B_TRUE;
nvlist_free(nvl);
}
+ if (ccw_failure) {
+ /*
+ * Keep trying so that configuration data is
+ * written if/when any temporary filesystem
+ * resource issues are resolved.
+ */
+ if (target->spa_ccw_fail_time == 0) {
+ zfs_ereport_post(FM_EREPORT_ZFS_CONFIG_CACHE_WRITE,
+ target, NULL, NULL, NULL, 0, 0);
+ }
+ target->spa_ccw_fail_time = gethrtime();
+ spa_async_request(target, SPA_ASYNC_CONFIG_UPDATE);
+ } else {
+ /*
+ * Do not rate limit future attempts to update
+ * the config cache.
+ */
+ target->spa_ccw_fail_time = 0;
+ }
+
/*
* Remove any config entries older than the current one.
*/
spa_config_generation++;
if (postsysevent)
- spa_event_notify(target, NULL, FM_EREPORT_ZFS_CONFIG_SYNC);
+ spa_event_notify(target, NULL, NULL, ESC_ZFS_CONFIG_SYNC);
}
/*
if (*generation == spa_config_generation)
return (NULL);
- VERIFY(nvlist_alloc(&pools, NV_UNIQUE_NAME, KM_SLEEP) == 0);
+ pools = fnvlist_alloc();
mutex_enter(&spa_namespace_lock);
while ((spa = spa_next(spa)) != NULL) {
if (INGLOBALZONE(curproc) ||
zone_dataset_visible(spa_name(spa), NULL)) {
mutex_enter(&spa->spa_props_lock);
- VERIFY(nvlist_add_nvlist(pools, spa_name(spa),
- spa->spa_config) == 0);
+ fnvlist_add_nvlist(pools, spa_name(spa),
+ spa->spa_config);
mutex_exit(&spa->spa_props_lock);
}
}
spa_config_set(spa_t *spa, nvlist_t *config)
{
mutex_enter(&spa->spa_props_lock);
- if (spa->spa_config != NULL)
- nvlist_free(spa->spa_config);
+ nvlist_free(spa->spa_config);
spa->spa_config = config;
mutex_exit(&spa->spa_props_lock);
}
/*
* Generate the pool's configuration based on the current in-core state.
+ *
* We infer whether to generate a complete config or just one top-level config
* based on whether vd is the root vdev.
*/
unsigned long hostid = 0;
boolean_t locked = B_FALSE;
uint64_t split_guid;
+ char *pool_name;
if (vd == NULL) {
vd = rvd;
if (txg == -1ULL)
txg = spa->spa_config_txg;
- VERIFY(nvlist_alloc(&config, NV_UNIQUE_NAME, KM_SLEEP) == 0);
-
- VERIFY(nvlist_add_uint64(config, ZPOOL_CONFIG_VERSION,
- spa_version(spa)) == 0);
- VERIFY(nvlist_add_string(config, ZPOOL_CONFIG_POOL_NAME,
- spa_name(spa)) == 0);
- VERIFY(nvlist_add_uint64(config, ZPOOL_CONFIG_POOL_STATE,
- spa_state(spa)) == 0);
- VERIFY(nvlist_add_uint64(config, ZPOOL_CONFIG_POOL_TXG,
- txg) == 0);
- VERIFY(nvlist_add_uint64(config, ZPOOL_CONFIG_POOL_GUID,
- spa_guid(spa)) == 0);
-#ifdef _KERNEL
- hostid = zone_get_hostid(NULL);
-#else /* _KERNEL */
/*
- * We're emulating the system's hostid in userland, so we can't use
- * zone_get_hostid().
+ * Originally, users had to handle spa namespace collisions by either
+ * exporting the already imported pool or by specifying a new name for
+ * the pool with a conflicting name. In the case of root pools from
+ * virtual guests, neither approach to collision resolution is
+ * reasonable. This is addressed by extending the new name syntax with
+ * an option to specify that the new name is temporary. When specified,
+ * ZFS_IMPORT_TEMP_NAME will be set in spa->spa_import_flags to tell us
+ * to use the previous name, which we do below.
*/
- (void) ddi_strtoul(hw_serial, NULL, 10, &hostid);
-#endif /* _KERNEL */
- if (hostid != 0) {
- VERIFY(nvlist_add_uint64(config, ZPOOL_CONFIG_HOSTID,
- hostid) == 0);
- }
- VERIFY(nvlist_add_string(config, ZPOOL_CONFIG_HOSTNAME,
- utsname.nodename) == 0);
-
+ if (spa->spa_import_flags & ZFS_IMPORT_TEMP_NAME) {
+ VERIFY0(nvlist_lookup_string(spa->spa_config,
+ ZPOOL_CONFIG_POOL_NAME, &pool_name));
+ } else
+ pool_name = spa_name(spa);
+
+ config = fnvlist_alloc();
+
+ fnvlist_add_uint64(config, ZPOOL_CONFIG_VERSION, spa_version(spa));
+ fnvlist_add_string(config, ZPOOL_CONFIG_POOL_NAME, pool_name);
+ fnvlist_add_uint64(config, ZPOOL_CONFIG_POOL_STATE, spa_state(spa));
+ fnvlist_add_uint64(config, ZPOOL_CONFIG_POOL_TXG, txg);
+ fnvlist_add_uint64(config, ZPOOL_CONFIG_POOL_GUID, spa_guid(spa));
+ fnvlist_add_uint64(config, ZPOOL_CONFIG_ERRATA, spa->spa_errata);
+ if (spa->spa_comment != NULL)
+ fnvlist_add_string(config, ZPOOL_CONFIG_COMMENT,
+ spa->spa_comment);
+
+ hostid = spa_get_hostid();
+ if (hostid != 0)
+ fnvlist_add_uint64(config, ZPOOL_CONFIG_HOSTID, hostid);
+ fnvlist_add_string(config, ZPOOL_CONFIG_HOSTNAME, utsname()->nodename);
+
+ int config_gen_flags = 0;
if (vd != rvd) {
- VERIFY(nvlist_add_uint64(config, ZPOOL_CONFIG_TOP_GUID,
- vd->vdev_top->vdev_guid) == 0);
- VERIFY(nvlist_add_uint64(config, ZPOOL_CONFIG_GUID,
- vd->vdev_guid) == 0);
+ fnvlist_add_uint64(config, ZPOOL_CONFIG_TOP_GUID,
+ vd->vdev_top->vdev_guid);
+ fnvlist_add_uint64(config, ZPOOL_CONFIG_GUID,
+ vd->vdev_guid);
if (vd->vdev_isspare)
- VERIFY(nvlist_add_uint64(config, ZPOOL_CONFIG_IS_SPARE,
- 1ULL) == 0);
+ fnvlist_add_uint64(config,
+ ZPOOL_CONFIG_IS_SPARE, 1ULL);
if (vd->vdev_islog)
- VERIFY(nvlist_add_uint64(config, ZPOOL_CONFIG_IS_LOG,
- 1ULL) == 0);
+ fnvlist_add_uint64(config,
+ ZPOOL_CONFIG_IS_LOG, 1ULL);
vd = vd->vdev_top; /* label contains top config */
} else {
/*
* in the mos config, and not in the vdev labels
*/
if (spa->spa_config_splitting != NULL)
- VERIFY(nvlist_add_nvlist(config, ZPOOL_CONFIG_SPLIT,
- spa->spa_config_splitting) == 0);
+ fnvlist_add_nvlist(config, ZPOOL_CONFIG_SPLIT,
+ spa->spa_config_splitting);
+
+ fnvlist_add_boolean(config, ZPOOL_CONFIG_HAS_PER_VDEV_ZAPS);
+
+ config_gen_flags |= VDEV_CONFIG_MOS;
}
/*
if (spa->spa_config_splitting != NULL &&
nvlist_lookup_uint64(spa->spa_config_splitting,
ZPOOL_CONFIG_SPLIT_GUID, &split_guid) == 0) {
- VERIFY(nvlist_add_uint64(config, ZPOOL_CONFIG_SPLIT_GUID,
- split_guid) == 0);
+ fnvlist_add_uint64(config, ZPOOL_CONFIG_SPLIT_GUID, split_guid);
}
- nvroot = vdev_config_generate(spa, vd, getstats, 0);
- VERIFY(nvlist_add_nvlist(config, ZPOOL_CONFIG_VDEV_TREE, nvroot) == 0);
+ nvroot = vdev_config_generate(spa, vd, getstats, config_gen_flags);
+ fnvlist_add_nvlist(config, ZPOOL_CONFIG_VDEV_TREE, nvroot);
nvlist_free(nvroot);
+ /*
+ * Store what's necessary for reading the MOS in the label.
+ */
+ fnvlist_add_nvlist(config, ZPOOL_CONFIG_FEATURES_FOR_READ,
+ spa->spa_label_features);
+
if (getstats && spa_load_state(spa) == SPA_LOAD_NONE) {
ddt_histogram_t *ddh;
ddt_stat_t *dds;
ddh = kmem_zalloc(sizeof (ddt_histogram_t), KM_SLEEP);
ddt_get_dedup_histogram(spa, ddh);
- VERIFY(nvlist_add_uint64_array(config,
+ fnvlist_add_uint64_array(config,
ZPOOL_CONFIG_DDT_HISTOGRAM,
- (uint64_t *)ddh, sizeof (*ddh) / sizeof (uint64_t)) == 0);
+ (uint64_t *)ddh, sizeof (*ddh) / sizeof (uint64_t));
kmem_free(ddh, sizeof (ddt_histogram_t));
ddo = kmem_zalloc(sizeof (ddt_object_t), KM_SLEEP);
ddt_get_dedup_object_stats(spa, ddo);
- VERIFY(nvlist_add_uint64_array(config,
+ fnvlist_add_uint64_array(config,
ZPOOL_CONFIG_DDT_OBJ_STATS,
- (uint64_t *)ddo, sizeof (*ddo) / sizeof (uint64_t)) == 0);
+ (uint64_t *)ddo, sizeof (*ddo) / sizeof (uint64_t));
kmem_free(ddo, sizeof (ddt_object_t));
dds = kmem_zalloc(sizeof (ddt_stat_t), KM_SLEEP);
ddt_get_dedup_stats(spa, dds);
- VERIFY(nvlist_add_uint64_array(config,
+ fnvlist_add_uint64_array(config,
ZPOOL_CONFIG_DDT_STATS,
- (uint64_t *)dds, sizeof (*dds) / sizeof (uint64_t)) == 0);
+ (uint64_t *)dds, sizeof (*dds) / sizeof (uint64_t));
kmem_free(dds, sizeof (ddt_stat_t));
}
/*
* Update the global config cache to reflect the new mosconfig.
*/
- if (!spa->spa_is_root)
- spa_config_sync(spa, B_FALSE, what != SPA_CONFIG_UPDATE_POOL);
+ if (!spa->spa_is_root) {
+ spa_write_cachefile(spa, B_FALSE,
+ what != SPA_CONFIG_UPDATE_POOL);
+ }
if (what == SPA_CONFIG_UPDATE_POOL)
spa_config_update(spa, SPA_CONFIG_UPDATE_VDEVS);
}
#if defined(_KERNEL) && defined(HAVE_SPL)
-EXPORT_SYMBOL(spa_config_sync);
EXPORT_SYMBOL(spa_config_load);
EXPORT_SYMBOL(spa_all_configs);
EXPORT_SYMBOL(spa_config_set);
module_param(spa_config_path, charp, 0444);
MODULE_PARM_DESC(spa_config_path, "SPA config file (/etc/zfs/zpool.cache)");
+
+module_param(zfs_autoimport_disable, int, 0644);
+MODULE_PARM_DESC(zfs_autoimport_disable, "Disable pool import at module load");
+
#endif