/*

 * CDDL HEADER START

 *

 * The contents of this file are subject to the terms of the

 * Common Development and Distribution License (the "License").

 * You may not use this file except in compliance with the License.

 *

 * You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE

 * or http://www.opensolaris.org/os/licensing.

 * See the License for the specific language governing permissions

 * and limitations under the License.

 *

 * When distributing Covered Code, include this CDDL HEADER in each

 * file and include the License file at usr/src/OPENSOLARIS.LICENSE.

 * If applicable, add the following below this CDDL HEADER, with the

 * fields enclosed by brackets "[]" replaced with your own identifying

 * information: Portions Copyright [yyyy] [name of copyright owner]

 *

 * CDDL HEADER END

 */

/*

 * Copyright 2007 Sun Microsystems, Inc.  All rights reserved.

 * Use is subject to license terms.

 */

#pragma ident	"%Z%%M%	%I%	%E% SMI"

#include <sys/zfs_context.h>

#include <sys/spa_impl.h>

#include <sys/zio.h>

#include <sys/zio_checksum.h>

#include <sys/zio_compress.h>

#include <sys/dmu.h>

#include <sys/dmu_tx.h>

#include <sys/zap.h>

#include <sys/zil.h>

#include <sys/vdev_impl.h>

#include <sys/metaslab.h>

#include <sys/uberblock_impl.h>

#include <sys/txg.h>

#include <sys/avl.h>

#include <sys/unique.h>

#include <sys/dsl_pool.h>

#include <sys/dsl_dir.h>

#include <sys/dsl_prop.h>

#include <sys/fs/zfs.h>

#include <sys/metaslab_impl.h>

#include "zfs_prop.h"

/*

 * SPA locking

 *

 * There are four basic locks for managing spa_t structures:

 *

 * spa_namespace_lock (global mutex)

 *

 *	This lock must be acquired to do any of the following:

 *

 *		- Lookup a spa_t by name

 *		- Add or remove a spa_t from the namespace

 *		- Increase spa_refcount from non-zero

 *		- Check if spa_refcount is zero

 *		- Rename a spa_t

 *		- add/remove/attach/detach devices

 *		- Held for the duration of create/destroy/import/export

 *

 *	It does not need to handle recursion.  A create or destroy may

 *	reference objects (files or zvols) in other pools, but by

 *	definition they must have an existing reference, and will never need

 *	to lookup a spa_t by name.

 *

 * spa_refcount (per-spa refcount_t protected by mutex)

 *

 *	This reference count keep track of any active users of the spa_t.  The

 *	spa_t cannot be destroyed or freed while this is non-zero.  Internally,

 *	the refcount is never really 'zero' - opening a pool implicitly keeps

 *	some references in the DMU.  Internally we check against SPA_MINREF, but

 *	present the image of a zero/non-zero value to consumers.

 *

 * spa_config_lock (per-spa read-priority rwlock)

 *

 *	This protects the spa_t from config changes, and must be held in

 *	the following circumstances:

 *

 *		- RW_READER to perform I/O to the spa

 *		- RW_WRITER to change the vdev config

 *

 * spa_config_cache_lock (per-spa mutex)

 *

 *	This mutex prevents the spa_config nvlist from being updated.  No

 *      other locks are required to obtain this lock, although implicitly you

 *      must have the namespace lock or non-zero refcount to have any kind

 *      of spa_t pointer at all.

 *

 * The locking order is fairly straightforward:

 *

 *		spa_namespace_lock	->	spa_refcount

 *

 *	The namespace lock must be acquired to increase the refcount from 0

 *	or to check if it is zero.

 *

 *		spa_refcount		->	spa_config_lock

 *

 *	There must be at least one valid reference on the spa_t to acquire

 *	the config lock.

 *

 *		spa_namespace_lock	->	spa_config_lock

 *

 *	The namespace lock must always be taken before the config lock.

 *

 *

 * The spa_namespace_lock and spa_config_cache_lock can be acquired directly and

 * are globally visible.

 *

 * The namespace is manipulated using the following functions, all which require

 * the spa_namespace_lock to be held.

 *

 *	spa_lookup()		Lookup a spa_t by name.

 *

 *	spa_add()		Create a new spa_t in the namespace.

 *

 *	spa_remove()		Remove a spa_t from the namespace.  This also

 *				frees up any memory associated with the spa_t.

 *

 *	spa_next()		Returns the next spa_t in the system, or the

 *				first if NULL is passed.

 *

 *	spa_evict_all()		Shutdown and remove all spa_t structures in

 *				the system.

 *

 *	spa_guid_exists()	Determine whether a pool/device guid exists.

 *

 * The spa_refcount is manipulated using the following functions:

 *

 *	spa_open_ref()		Adds a reference to the given spa_t.  Must be

 *				called with spa_namespace_lock held if the

 *				refcount is currently zero.

 *

 *	spa_close()		Remove a reference from the spa_t.  This will

 *				not free the spa_t or remove it from the

 *				namespace.  No locking is required.

 *

 *	spa_refcount_zero()	Returns true if the refcount is currently

 *				zero.  Must be called with spa_namespace_lock

 *				held.

 *

 * The spa_config_lock is manipulated using the following functions:

 *

 *	spa_config_enter()	Acquire the config lock as RW_READER or

 *				RW_WRITER.  At least one reference on the spa_t

 *				must exist.

 *

 *	spa_config_exit()	Release the config lock.

 *

 *	spa_config_held()	Returns true if the config lock is currently

 *				held in the given state.

 *

 * The vdev configuration is protected by spa_vdev_enter() / spa_vdev_exit().

 *

 *	spa_vdev_enter()	Acquire the namespace lock and the config lock

 *				for writing.

 *

 *	spa_vdev_exit()		Release the config lock, wait for all I/O

 *				to complete, sync the updated configs to the

 *				cache, and release the namespace lock.

 *

 * The spa_name() function also requires either the spa_namespace_lock

 * or the spa_config_lock, as both are needed to do a rename.  spa_rename() is

 * also implemented within this file since is requires manipulation of the

 * namespace.

 */

static avl_tree_t spa_namespace_avl;

kmutex_t spa_namespace_lock;

static kcondvar_t spa_namespace_cv;

static int spa_active_count;

int spa_max_replication_override = SPA_DVAS_PER_BP;

static kmutex_t spa_spare_lock;

static avl_tree_t spa_spare_avl;

kmem_cache_t *spa_buffer_pool;

int spa_mode;

#ifdef ZFS_DEBUG

/* Everything except dprintf is on by default in debug builds */

int zfs_flags = ~ZFS_DEBUG_DPRINTF;

#else

int zfs_flags = 0;

#endif

/*

 * zfs_recover can be set to nonzero to attempt to recover from

 * otherwise-fatal errors, typically caused by on-disk corruption.  When

 * set, calls to zfs_panic_recover() will turn into warning messages.

 */

int zfs_recover = 0;

#define	SPA_MINREF	5	/* spa_refcnt for an open-but-idle pool */

/*

 * ==========================================================================

 * SPA namespace functions

 * ==========================================================================

 */

/*

 * Lookup the named spa_t in the AVL tree.  The spa_namespace_lock must be held.

 * Returns NULL if no matching spa_t is found.

 */

spa_t *

spa_lookup(const char *name)

{

	spa_t search, *spa;

	avl_index_t where;

	char c;

	char *cp;

	ASSERT(MUTEX_HELD(&spa_namespace_lock));

	/*

	 * If it's a full dataset name, figure out the pool name and

	 * just use that.

	 */

	cp = strpbrk(name, "/@");

	if (cp) {

		c = *cp;

		*cp = '\0';

	}

	search.spa_name = (char *)name;

	spa = avl_find(&spa_namespace_avl, &search, &where);

	if (cp)

		*cp = c;

	return (spa);

}

/*

 * Create an uninitialized spa_t with the given name.  Requires

 * spa_namespace_lock.  The caller must ensure that the spa_t doesn't already

 * exist by calling spa_lookup() first.

 */

spa_t *

spa_add(const char *name, const char *altroot)

{

	spa_t *spa;

	ASSERT(MUTEX_HELD(&spa_namespace_lock));

	spa = kmem_zalloc(sizeof (spa_t), KM_SLEEP);

	rw_init(&spa->spa_traverse_lock, NULL, RW_DEFAULT, NULL);

	mutex_init(&spa->spa_uberblock_lock, NULL, MUTEX_DEFAULT, NULL);

	mutex_init(&spa->spa_async_lock, NULL, MUTEX_DEFAULT, NULL);

	mutex_init(&spa->spa_config_cache_lock, NULL, MUTEX_DEFAULT, NULL);

	mutex_init(&spa->spa_scrub_lock, NULL, MUTEX_DEFAULT, NULL);

	mutex_init(&spa->spa_errlog_lock, NULL, MUTEX_DEFAULT, NULL);

	mutex_init(&spa->spa_errlist_lock, NULL, MUTEX_DEFAULT, NULL);

	mutex_init(&spa->spa_sync_bplist.bpl_lock, NULL, MUTEX_DEFAULT, NULL);

	mutex_init(&spa->spa_history_lock, NULL, MUTEX_DEFAULT, NULL);

	mutex_init(&spa->spa_props_lock, NULL, MUTEX_DEFAULT, NULL);

	cv_init(&spa->spa_async_cv, NULL, CV_DEFAULT, NULL);

	cv_init(&spa->spa_scrub_cv, NULL, CV_DEFAULT, NULL);

	cv_init(&spa->spa_scrub_io_cv, NULL, CV_DEFAULT, NULL);

	spa->spa_name = spa_strdup(name);

	spa->spa_state = POOL_STATE_UNINITIALIZED;

	spa->spa_freeze_txg = UINT64_MAX;

	spa->spa_final_txg = UINT64_MAX;

	refcount_create(&spa->spa_refcount);

	rprw_init(&spa->spa_config_lock);

	avl_add(&spa_namespace_avl, spa);

	/*

	 * Set the alternate root, if there is one.

	 */

	if (altroot) {

		spa->spa_root = spa_strdup(altroot);

		spa_active_count++;

	}

	return (spa);

}

/*

 * Removes a spa_t from the namespace, freeing up any memory used.  Requires

 * spa_namespace_lock.  This is called only after the spa_t has been closed and

 * deactivated.

 */

void

spa_remove(spa_t *spa)

{

	ASSERT(MUTEX_HELD(&spa_namespace_lock));

	ASSERT(spa->spa_state == POOL_STATE_UNINITIALIZED);

	ASSERT(spa->spa_scrub_thread == NULL);

	avl_remove(&spa_namespace_avl, spa);

	cv_broadcast(&spa_namespace_cv);

	if (spa->spa_root) {

		spa_strfree(spa->spa_root);

		spa_active_count--;

	}

	if (spa->spa_name)

		spa_strfree(spa->spa_name);

	spa_config_set(spa, NULL);

	refcount_destroy(&spa->spa_refcount);

	rprw_destroy(&spa->spa_config_lock);

	rw_destroy(&spa->spa_traverse_lock);

	cv_destroy(&spa->spa_async_cv);

	cv_destroy(&spa->spa_scrub_cv);

	cv_destroy(&spa->spa_scrub_io_cv);

	mutex_destroy(&spa->spa_uberblock_lock);

	mutex_destroy(&spa->spa_async_lock);

	mutex_destroy(&spa->spa_config_cache_lock);

	mutex_destroy(&spa->spa_scrub_lock);

	mutex_destroy(&spa->spa_errlog_lock);

	mutex_destroy(&spa->spa_errlist_lock);

	mutex_destroy(&spa->spa_sync_bplist.bpl_lock);

	mutex_destroy(&spa->spa_history_lock);

	mutex_destroy(&spa->spa_props_lock);

	kmem_free(spa, sizeof (spa_t));

}

/*

 * Given a pool, return the next pool in the namespace, or NULL if there is

 * none.  If 'prev' is NULL, return the first pool.

 */

spa_t *

spa_next(spa_t *prev)

{

	ASSERT(MUTEX_HELD(&spa_namespace_lock));

	if (prev)

		return (AVL_NEXT(&spa_namespace_avl, prev));

	else

		return (avl_first(&spa_namespace_avl));

}

/*

 * ==========================================================================

 * SPA refcount functions

 * ==========================================================================

 */

/*

 * Add a reference to the given spa_t.  Must have at least one reference, or

 * have the namespace lock held.

 */

void

spa_open_ref(spa_t *spa, void *tag)

{

	ASSERT(refcount_count(&spa->spa_refcount) > SPA_MINREF ||

	    MUTEX_HELD(&spa_namespace_lock));

	(void) refcount_add(&spa->spa_refcount, tag);

}

/*

 * Remove a reference to the given spa_t.  Must have at least one reference, or

 * have the namespace lock held.

 */

void

spa_close(spa_t *spa, void *tag)

{

	ASSERT(refcount_count(&spa->spa_refcount) > SPA_MINREF ||

	    MUTEX_HELD(&spa_namespace_lock));

	(void) refcount_remove(&spa->spa_refcount, tag);

}

/*

 * Check to see if the spa refcount is zero.  Must be called with

 * spa_namespace_lock held.  We really compare against SPA_MINREF, which is the

 * number of references acquired when opening a pool

 */

boolean_t

spa_refcount_zero(spa_t *spa)

{

	ASSERT(MUTEX_HELD(&spa_namespace_lock));

	return (refcount_count(&spa->spa_refcount) == SPA_MINREF);

}

/*

 * ==========================================================================

 * SPA spare tracking

 * ==========================================================================

 */

/*

 * Spares are tracked globally due to the following constraints:

 *

 * 	- A spare may be part of multiple pools.

 * 	- A spare may be added to a pool even if it's actively in use within

 *	  another pool.

 * 	- A spare in use in any pool can only be the source of a replacement if

 *	  the target is a spare in the same pool.

 *

 * We keep track of all spares on the system through the use of a reference

 * counted AVL tree.  When a vdev is added as a spare, or used as a replacement

 * spare, then we bump the reference count in the AVL tree.  In addition, we set

 * the 'vdev_isspare' member to indicate that the device is a spare (active or

 * inactive).  When a spare is made active (used to replace a device in the

 * pool), we also keep track of which pool its been made a part of.

 *

 * The 'spa_spare_lock' protects the AVL tree.  These functions are normally

 * called under the spa_namespace lock as part of vdev reconfiguration.  The

 * separate spare lock exists for the status query path, which does not need to

 * be completely consistent with respect to other vdev configuration changes.

 */

typedef struct spa_spare {

	uint64_t	spare_guid;

	uint64_t	spare_pool;

	avl_node_t	spare_avl;

	int		spare_count;

} spa_spare_t;

static int

spa_spare_compare(const void *a, const void *b)

{

	const spa_spare_t *sa = a;

	const spa_spare_t *sb = b;

	if (sa->spare_guid < sb->spare_guid)

		return (-1);

	else if (sa->spare_guid > sb->spare_guid)

		return (1);

	else

		return (0);

}

void

spa_spare_add(vdev_t *vd)

{

	avl_index_t where;

	spa_spare_t search;

	spa_spare_t *spare;

	mutex_enter(&spa_spare_lock);

	ASSERT(!vd->vdev_isspare);

	search.spare_guid = vd->vdev_guid;

	if ((spare = avl_find(&spa_spare_avl, &search, &where)) != NULL) {

		spare->spare_count++;

	} else {

		spare = kmem_zalloc(sizeof (spa_spare_t), KM_SLEEP);

		spare->spare_guid = vd->vdev_guid;

		spare->spare_count = 1;

		avl_insert(&spa_spare_avl, spare, where);

	}

	vd->vdev_isspare = B_TRUE;

	mutex_exit(&spa_spare_lock);

}

void

spa_spare_remove(vdev_t *vd)

{

	spa_spare_t search;

	spa_spare_t *spare;

	avl_index_t where;

	mutex_enter(&spa_spare_lock);

	search.spare_guid = vd->vdev_guid;

	spare = avl_find(&spa_spare_avl, &search, &where);

	ASSERT(vd->vdev_isspare);

	ASSERT(spare != NULL);

	if (--spare->spare_count == 0) {

		avl_remove(&spa_spare_avl, spare);

		kmem_free(spare, sizeof (spa_spare_t));

	} else if (spare->spare_pool == spa_guid(vd->vdev_spa)) {

		spare->spare_pool = 0ULL;

	}

	vd->vdev_isspare = B_FALSE;

	mutex_exit(&spa_spare_lock);

}

boolean_t

spa_spare_exists(uint64_t guid, uint64_t *pool)

{

	spa_spare_t search, *found;

	avl_index_t where;