[mirror_zfs.git] / include / sys / dbuf.h

/*
 * 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 (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
 * Copyright (c) 2013 by Delphix. All rights reserved.
 * Copyright (c) 2013 by Saso Kiselkov. All rights reserved.
 */

#ifndef	_SYS_DBUF_H
#define	_SYS_DBUF_H

#include <sys/dmu.h>
#include <sys/spa.h>
#include <sys/txg.h>
#include <sys/zio.h>
#include <sys/arc.h>
#include <sys/zfs_context.h>
#include <sys/refcount.h>
#include <sys/zrlock.h>

#ifdef	__cplusplus
extern "C" {
#endif

#define	IN_DMU_SYNC 2

/*
 * define flags for dbuf_read
 */

#define	DB_RF_MUST_SUCCEED	(1 << 0)
#define	DB_RF_CANFAIL		(1 << 1)
#define	DB_RF_HAVESTRUCT	(1 << 2)
#define	DB_RF_NOPREFETCH	(1 << 3)
#define	DB_RF_NEVERWAIT		(1 << 4)
#define	DB_RF_CACHED		(1 << 5)

/*
 * The simplified state transition diagram for dbufs looks like:
 *
 *		+----> READ ----+
 *		|		|
 *		|		V
 *  (alloc)-->UNCACHED	     CACHED-->EVICTING-->(free)
 *		|		^	 ^
 *		|		|	 |
 *		+----> FILL ----+	 |
 *		|			 |
 *		|			 |
 *		+--------> NOFILL -------+
 */
typedef enum dbuf_states {
	DB_UNCACHED,
	DB_FILL,
	DB_NOFILL,
	DB_READ,
	DB_CACHED,
	DB_EVICTING
} dbuf_states_t;

struct dnode;
struct dmu_tx;

/*
 * level = 0 means the user data
 * level = 1 means the single indirect block
 * etc.
 */

struct dmu_buf_impl;

typedef enum override_states {
	DR_NOT_OVERRIDDEN,
	DR_IN_DMU_SYNC,
	DR_OVERRIDDEN
} override_states_t;

typedef struct dbuf_dirty_record {
	/* link on our parents dirty list */
	list_node_t dr_dirty_node;

	/* transaction group this data will sync in */
	uint64_t dr_txg;

	/* zio of outstanding write IO */
	zio_t *dr_zio;

	/* pointer back to our dbuf */
	struct dmu_buf_impl *dr_dbuf;

	/* pointer to next dirty record */
	struct dbuf_dirty_record *dr_next;

	/* pointer to parent dirty record */
	struct dbuf_dirty_record *dr_parent;

	/* How much space was changed to dsl_pool_dirty_space() for this? */
	unsigned int dr_accounted;

	union dirty_types {
		struct dirty_indirect {

			/* protect access to list */
			kmutex_t dr_mtx;

			/* Our list of dirty children */
			list_t dr_children;
		} di;
		struct dirty_leaf {

			/*
			 * dr_data is set when we dirty the buffer
			 * so that we can retain the pointer even if it
			 * gets COW'd in a subsequent transaction group.
			 */
			arc_buf_t *dr_data;
			blkptr_t dr_overridden_by;
			override_states_t dr_override_state;
			uint8_t dr_copies;
			boolean_t dr_nopwrite;
		} dl;
	} dt;
} dbuf_dirty_record_t;

typedef struct dmu_buf_impl {
	/*
	 * The following members are immutable, with the exception of
	 * db.db_data, which is protected by db_mtx.
	 */

	/* the publicly visible structure */
	dmu_buf_t db;

	/* the objset we belong to */
	struct objset *db_objset;

	/*
	 * handle to safely access the dnode we belong to (NULL when evicted)
	 */
	struct dnode_handle *db_dnode_handle;

	/*
	 * our parent buffer; if the dnode points to us directly,
	 * db_parent == db_dnode_handle->dnh_dnode->dn_dbuf
	 * only accessed by sync thread ???
	 * (NULL when evicted)
	 * May change from NULL to non-NULL under the protection of db_mtx
	 * (see dbuf_check_blkptr())
	 */
	struct dmu_buf_impl *db_parent;

	/*
	 * link for hash table of all dmu_buf_impl_t's
	 */
	struct dmu_buf_impl *db_hash_next;

	/* our block number */
	uint64_t db_blkid;

	/*
	 * Pointer to the blkptr_t which points to us. May be NULL if we
	 * don't have one yet. (NULL when evicted)
	 */
	blkptr_t *db_blkptr;

	/*
	 * Our indirection level.  Data buffers have db_level==0.
	 * Indirect buffers which point to data buffers have
	 * db_level==1. etc.  Buffers which contain dnodes have
	 * db_level==0, since the dnodes are stored in a file.
	 */
	uint8_t db_level;

	/* db_mtx protects the members below */
	kmutex_t db_mtx;

	/*
	 * Current state of the buffer
	 */
	dbuf_states_t db_state;

	/*
	 * Refcount accessed by dmu_buf_{hold,rele}.
	 * If nonzero, the buffer can't be destroyed.
	 * Protected by db_mtx.
	 */
	refcount_t db_holds;

	/* buffer holding our data */
	arc_buf_t *db_buf;

	kcondvar_t db_changed;
	dbuf_dirty_record_t *db_data_pending;

	/* pointer to most recent dirty record for this buffer */
	dbuf_dirty_record_t *db_last_dirty;

	/*
	 * Our link on the owner dnodes's dn_dbufs list.
	 * Protected by its dn_dbufs_mtx.
	 */
	list_node_t db_link;

	/* Data which is unique to data (leaf) blocks: */

	/* stuff we store for the user (see dmu_buf_set_user) */
	void *db_user_ptr;
	void **db_user_data_ptr_ptr;
	dmu_buf_evict_func_t *db_evict_func;

	uint8_t db_immediate_evict;
	uint8_t db_freed_in_flight;

	uint8_t db_dirtycnt;
} dmu_buf_impl_t;

/* Note: the dbuf hash table is exposed only for the mdb module */
#define	DBUF_MUTEXES 256
#define	DBUF_HASH_MUTEX(h, idx) (&(h)->hash_mutexes[(idx) & (DBUF_MUTEXES-1)])
typedef struct dbuf_hash_table {
	uint64_t hash_table_mask;
	dmu_buf_impl_t **hash_table;
	kmutex_t hash_mutexes[DBUF_MUTEXES];
} dbuf_hash_table_t;


uint64_t dbuf_whichblock(struct dnode *di, uint64_t offset);

void dbuf_create_bonus(struct dnode *dn);
int dbuf_spill_set_blksz(dmu_buf_t *db, uint64_t blksz, dmu_tx_t *tx);

void dbuf_rm_spill(struct dnode *dn, dmu_tx_t *tx);

dmu_buf_impl_t *dbuf_hold(struct dnode *dn, uint64_t blkid, void *tag);
dmu_buf_impl_t *dbuf_hold_level(struct dnode *dn, int level, uint64_t blkid,
    void *tag);
int dbuf_hold_impl(struct dnode *dn, uint8_t level, uint64_t blkid, int create,
    void *tag, dmu_buf_impl_t **dbp);

void dbuf_prefetch(struct dnode *dn, uint64_t blkid, zio_priority_t prio);

void dbuf_add_ref(dmu_buf_impl_t *db, void *tag);
uint64_t dbuf_refcount(dmu_buf_impl_t *db);

void dbuf_rele(dmu_buf_impl_t *db, void *tag);
void dbuf_rele_and_unlock(dmu_buf_impl_t *db, void *tag);

dmu_buf_impl_t *dbuf_find(struct dnode *dn, uint8_t level, uint64_t blkid);

int dbuf_read(dmu_buf_impl_t *db, zio_t *zio, uint32_t flags);
void dmu_buf_will_not_fill(dmu_buf_t *db, dmu_tx_t *tx);
void dmu_buf_will_fill(dmu_buf_t *db, dmu_tx_t *tx);
void dmu_buf_fill_done(dmu_buf_t *db, dmu_tx_t *tx);
void dbuf_assign_arcbuf(dmu_buf_impl_t *db, arc_buf_t *buf, dmu_tx_t *tx);
dbuf_dirty_record_t *dbuf_dirty(dmu_buf_impl_t *db, dmu_tx_t *tx);
arc_buf_t *dbuf_loan_arcbuf(dmu_buf_impl_t *db);
void dmu_buf_write_embedded(dmu_buf_t *dbuf, void *data,
    bp_embedded_type_t etype, enum zio_compress comp,
    int uncompressed_size, int compressed_size, int byteorder, dmu_tx_t *tx);

void dbuf_clear(dmu_buf_impl_t *db);
void dbuf_evict(dmu_buf_impl_t *db);

void dbuf_unoverride(dbuf_dirty_record_t *dr);
void dbuf_sync_list(list_t *list, dmu_tx_t *tx);
void dbuf_release_bp(dmu_buf_impl_t *db);

void dbuf_free_range(struct dnode *dn, uint64_t start, uint64_t end,
    struct dmu_tx *);

void dbuf_new_size(dmu_buf_impl_t *db, int size, dmu_tx_t *tx);

void dbuf_stats_init(dbuf_hash_table_t *hash);
void dbuf_stats_destroy(void);

#define	DB_DNODE(_db)		((_db)->db_dnode_handle->dnh_dnode)
#define	DB_DNODE_LOCK(_db)	((_db)->db_dnode_handle->dnh_zrlock)
#define	DB_DNODE_ENTER(_db)	(zrl_add(&DB_DNODE_LOCK(_db)))
#define	DB_DNODE_EXIT(_db)	(zrl_remove(&DB_DNODE_LOCK(_db)))
#define	DB_DNODE_HELD(_db)	(!zrl_is_zero(&DB_DNODE_LOCK(_db)))

void dbuf_init(void);
void dbuf_fini(void);

boolean_t dbuf_is_metadata(dmu_buf_impl_t *db);

#define	DBUF_GET_BUFC_TYPE(_db)	\
	(dbuf_is_metadata(_db) ? ARC_BUFC_METADATA : ARC_BUFC_DATA)

#define	DBUF_IS_CACHEABLE(_db)						\
	((_db)->db_objset->os_primary_cache == ZFS_CACHE_ALL ||		\
	(dbuf_is_metadata(_db) &&					\
	((_db)->db_objset->os_primary_cache == ZFS_CACHE_METADATA)))

#define	DBUF_IS_L2CACHEABLE(_db)					\
	((_db)->db_objset->os_secondary_cache == ZFS_CACHE_ALL ||	\
	(dbuf_is_metadata(_db) &&					\
	((_db)->db_objset->os_secondary_cache == ZFS_CACHE_METADATA)))

#define	DBUF_IS_L2COMPRESSIBLE(_db)					\
	((_db)->db_objset->os_compress != ZIO_COMPRESS_OFF ||		\
	(dbuf_is_metadata(_db) && zfs_mdcomp_disable == B_FALSE))

#ifdef ZFS_DEBUG

/*
 * There should be a ## between the string literal and fmt, to make it
 * clear that we're joining two strings together, but gcc does not
 * support that preprocessor token.
 */
#define	dprintf_dbuf(dbuf, fmt, ...) do { \
	if (zfs_flags & ZFS_DEBUG_DPRINTF) { \
	char __db_buf[32]; \
	uint64_t __db_obj = (dbuf)->db.db_object; \
	if (__db_obj == DMU_META_DNODE_OBJECT) \
		(void) strcpy(__db_buf, "mdn"); \
	else \
		(void) snprintf(__db_buf, sizeof (__db_buf), "%lld", \
		    (u_longlong_t)__db_obj); \
	dprintf_ds((dbuf)->db_objset->os_dsl_dataset, \
	    "obj=%s lvl=%u blkid=%lld " fmt, \
	    __db_buf, (dbuf)->db_level, \
	    (u_longlong_t)(dbuf)->db_blkid, __VA_ARGS__); \
	} \
_NOTE(CONSTCOND) } while (0)

#define	dprintf_dbuf_bp(db, bp, fmt, ...) do {				\
	if (zfs_flags & ZFS_DEBUG_DPRINTF) {				\
	char *__blkbuf = kmem_alloc(BP_SPRINTF_LEN, KM_PUSHPAGE);	\
	snprintf_blkptr(__blkbuf, BP_SPRINTF_LEN, bp);		\
	dprintf_dbuf(db, fmt " %s\n", __VA_ARGS__, __blkbuf);		\
	kmem_free(__blkbuf, BP_SPRINTF_LEN);				\
	}								\
_NOTE(CONSTCOND) } while (0)

#define	DBUF_VERIFY(db)	dbuf_verify(db)

#else

#define	dprintf_dbuf(db, fmt, ...)
#define	dprintf_dbuf_bp(db, bp, fmt, ...)
#define	DBUF_VERIFY(db)

#endif


#ifdef	__cplusplus
}
#endif

#endif /* _SYS_DBUF_H */
Commit	Line	Data
34dc7c2f BB	1	/*
	2	* CDDL HEADER START
	3	*
	4	* The contents of this file are subject to the terms of the
	5	* Common Development and Distribution License (the "License").
	6	* You may not use this file except in compliance with the License.
	7	*
	8	* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
	9	* or http://www.opensolaris.org/os/licensing.
	10	* See the License for the specific language governing permissions
	11	* and limitations under the License.
	12	*
	13	* When distributing Covered Code, include this CDDL HEADER in each
	14	* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
	15	* If applicable, add the following below this CDDL HEADER, with the
	16	* fields enclosed by brackets "[]" replaced with your own identifying
	17	* information: Portions Copyright [yyyy] [name of copyright owner]
	18	*
	19	* CDDL HEADER END
	20	*/
	21	/*
428870ff	22	* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
03c6040b	23	* Copyright (c) 2013 by Delphix. All rights reserved.
3a17a7a9	24	* Copyright (c) 2013 by Saso Kiselkov. All rights reserved.
34dc7c2f BB	25	*/
	26
	27	#ifndef _SYS_DBUF_H
	28	#define _SYS_DBUF_H
	29
34dc7c2f BB	30	#include <sys/dmu.h>
	31	#include <sys/spa.h>
	32	#include <sys/txg.h>
	33	#include <sys/zio.h>
	34	#include <sys/arc.h>
	35	#include <sys/zfs_context.h>
	36	#include <sys/refcount.h>
572e2857	37	#include <sys/zrlock.h>
34dc7c2f BB	38
	39	#ifdef __cplusplus
	40	extern "C" {
	41	#endif
	42
34dc7c2f BB	43	#define IN_DMU_SYNC 2
	44
	45	/*
	46	* define flags for dbuf_read
	47	*/
	48
	49	#define DB_RF_MUST_SUCCEED (1 << 0)
	50	#define DB_RF_CANFAIL (1 << 1)
	51	#define DB_RF_HAVESTRUCT (1 << 2)
	52	#define DB_RF_NOPREFETCH (1 << 3)
	53	#define DB_RF_NEVERWAIT (1 << 4)
	54	#define DB_RF_CACHED (1 << 5)
	55
	56	/*
b128c09f	57	* The simplified state transition diagram for dbufs looks like:
34dc7c2f BB	58	*
	59	* +----> READ ----+
	60	* \| \|
	61	* \| V
	62	* (alloc)-->UNCACHED CACHED-->EVICTING-->(free)
b128c09f BB	63	* \| ^ ^
	64	* \| \| \|
	65	* +----> FILL ----+ \|
	66	* \| \|
	67	* \| \|
	68	* +--------> NOFILL -------+
34dc7c2f BB	69	*/
	70	typedef enum dbuf_states {
	71	DB_UNCACHED,
	72	DB_FILL,
b128c09f	73	DB_NOFILL,
34dc7c2f BB	74	DB_READ,
	75	DB_CACHED,
	76	DB_EVICTING
	77	} dbuf_states_t;
	78
34dc7c2f BB	79	struct dnode;
	80	struct dmu_tx;
	81
	82	/*
	83	* level = 0 means the user data
	84	* level = 1 means the single indirect block
	85	* etc.
	86	*/
	87
34dc7c2f BB	88	struct dmu_buf_impl;
	89
	90	typedef enum override_states {
	91	DR_NOT_OVERRIDDEN,
	92	DR_IN_DMU_SYNC,
	93	DR_OVERRIDDEN
	94	} override_states_t;
	95
	96	typedef struct dbuf_dirty_record {
	97	/* link on our parents dirty list */
	98	list_node_t dr_dirty_node;
	99
	100	/* transaction group this data will sync in */
	101	uint64_t dr_txg;
	102
	103	/* zio of outstanding write IO */
	104	zio_t *dr_zio;
	105
	106	/* pointer back to our dbuf */
	107	struct dmu_buf_impl *dr_dbuf;
	108
	109	/* pointer to next dirty record */
	110	struct dbuf_dirty_record *dr_next;
	111
	112	/* pointer to parent dirty record */
	113	struct dbuf_dirty_record *dr_parent;
	114
e8b96c60 MA	115	/* How much space was changed to dsl_pool_dirty_space() for this? */
	116	unsigned int dr_accounted;
	117
34dc7c2f BB	118	union dirty_types {
	119	struct dirty_indirect {
	120
	121	/* protect access to list */
	122	kmutex_t dr_mtx;
	123
	124	/* Our list of dirty children */
	125	list_t dr_children;
	126	} di;
	127	struct dirty_leaf {
	128
	129	/*
	130	* dr_data is set when we dirty the buffer
	131	* so that we can retain the pointer even if it
	132	* gets COW'd in a subsequent transaction group.
	133	*/
	134	arc_buf_t *dr_data;
	135	blkptr_t dr_overridden_by;
	136	override_states_t dr_override_state;
428870ff	137	uint8_t dr_copies;
03c6040b	138	boolean_t dr_nopwrite;
34dc7c2f BB	139	} dl;
	140	} dt;
	141	} dbuf_dirty_record_t;
	142
	143	typedef struct dmu_buf_impl {
	144	/*
	145	* The following members are immutable, with the exception of
	146	* db.db_data, which is protected by db_mtx.
	147	*/
	148
	149	/* the publicly visible structure */
	150	dmu_buf_t db;
	151
	152	/* the objset we belong to */
428870ff	153	struct objset *db_objset;
34dc7c2f BB	154
34dc7c2f BB	155	/*
572e2857	156	* handle to safely access the dnode we belong to (NULL when evicted)
34dc7c2f	157	*/
572e2857	158	struct dnode_handle *db_dnode_handle;
34dc7c2f BB	159
	160	/*
	161	* our parent buffer; if the dnode points to us directly,
572e2857	162	* db_parent == db_dnode_handle->dnh_dnode->dn_dbuf
34dc7c2f BB	163	* only accessed by sync thread ???
34dc7c2f BB	164	* (NULL when evicted)
572e2857 BB	165	* May change from NULL to non-NULL under the protection of db_mtx
572e2857 BB	166	* (see dbuf_check_blkptr())
34dc7c2f BB	167	*/
	168	struct dmu_buf_impl *db_parent;
	169
	170	/*
	171	* link for hash table of all dmu_buf_impl_t's
	172	*/
	173	struct dmu_buf_impl *db_hash_next;
	174
	175	/* our block number */
	176	uint64_t db_blkid;
	177
	178	/*
	179	* Pointer to the blkptr_t which points to us. May be NULL if we
	180	* don't have one yet. (NULL when evicted)
	181	*/
	182	blkptr_t *db_blkptr;
	183
	184	/*
	185	* Our indirection level. Data buffers have db_level==0.
	186	* Indirect buffers which point to data buffers have
	187	* db_level==1. etc. Buffers which contain dnodes have
	188	* db_level==0, since the dnodes are stored in a file.
	189	*/
	190	uint8_t db_level;
	191
	192	/* db_mtx protects the members below */
	193	kmutex_t db_mtx;
	194
	195	/*
	196	* Current state of the buffer
	197	*/
	198	dbuf_states_t db_state;
	199
	200	/*
	201	* Refcount accessed by dmu_buf_{hold,rele}.
	202	* If nonzero, the buffer can't be destroyed.
	203	* Protected by db_mtx.
	204	*/
	205	refcount_t db_holds;
	206
	207	/* buffer holding our data */
	208	arc_buf_t *db_buf;
	209
	210	kcondvar_t db_changed;
	211	dbuf_dirty_record_t *db_data_pending;
	212
	213	/* pointer to most recent dirty record for this buffer */
	214	dbuf_dirty_record_t *db_last_dirty;
	215
	216	/*
	217	* Our link on the owner dnodes's dn_dbufs list.
	218	* Protected by its dn_dbufs_mtx.
	219	*/
	220	list_node_t db_link;
	221
	222	/* Data which is unique to data (leaf) blocks: */
	223
	224	/* stuff we store for the user (see dmu_buf_set_user) */
	225	void *db_user_ptr;
	226	void **db_user_data_ptr_ptr;
	227	dmu_buf_evict_func_t *db_evict_func;
	228
	229	uint8_t db_immediate_evict;
	230	uint8_t db_freed_in_flight;
231
232	uint8_t db_dirtycnt;
233	} dmu_buf_impl_t;
234
235	/* Note: the dbuf hash table is exposed only for the mdb module */
236	#define DBUF_MUTEXES 256
237	#define DBUF_HASH_MUTEX(h, idx) (&(h)->hash_mutexes[(idx) & (DBUF_MUTEXES-1)])
238	typedef struct dbuf_hash_table {
239	uint64_t hash_table_mask;
240	dmu_buf_impl_t **hash_table;
241	kmutex_t hash_mutexes[DBUF_MUTEXES];
242	} dbuf_hash_table_t;
243
244
245	uint64_t dbuf_whichblock(struct dnode *di, uint64_t offset);
246
34dc7c2f	247	void dbuf_create_bonus(struct dnode *dn);
428870ff	248	int dbuf_spill_set_blksz(dmu_buf_t db, uint64_t blksz, dmu_tx_t tx);
428870ff BB	249
428870ff BB	250	void dbuf_rm_spill(struct dnode dn, dmu_tx_t tx);
34dc7c2f BB	251
	252	dmu_buf_impl_t dbuf_hold(struct dnode dn, uint64_t blkid, void *tag);
	253	dmu_buf_impl_t dbuf_hold_level(struct dnode dn, int level, uint64_t blkid,
	254	void *tag);
	255	int dbuf_hold_impl(struct dnode *dn, uint8_t level, uint64_t blkid, int create,
	256	void tag, dmu_buf_impl_t *dbp);
	257
e8b96c60	258	void dbuf_prefetch(struct dnode *dn, uint64_t blkid, zio_priority_t prio);
34dc7c2f BB	259
	260	void dbuf_add_ref(dmu_buf_impl_t db, void tag);
	261	uint64_t dbuf_refcount(dmu_buf_impl_t *db);
	262
	263	void dbuf_rele(dmu_buf_impl_t db, void tag);
428870ff	264	void dbuf_rele_and_unlock(dmu_buf_impl_t db, void tag);
34dc7c2f BB	265
	266	dmu_buf_impl_t dbuf_find(struct dnode dn, uint8_t level, uint64_t blkid);
	267
	268	int dbuf_read(dmu_buf_impl_t db, zio_t zio, uint32_t flags);
b128c09f	269	void dmu_buf_will_not_fill(dmu_buf_t db, dmu_tx_t tx);
34dc7c2f BB	270	void dmu_buf_will_fill(dmu_buf_t db, dmu_tx_t tx);
34dc7c2f BB	271	void dmu_buf_fill_done(dmu_buf_t db, dmu_tx_t tx);
9babb374	272	void dbuf_assign_arcbuf(dmu_buf_impl_t db, arc_buf_t buf, dmu_tx_t *tx);
34dc7c2f	273	dbuf_dirty_record_t dbuf_dirty(dmu_buf_impl_t db, dmu_tx_t *tx);
428870ff	274	arc_buf_t dbuf_loan_arcbuf(dmu_buf_impl_t db);
9b67f605 MA	275	void dmu_buf_write_embedded(dmu_buf_t dbuf, void data,
	276	bp_embedded_type_t etype, enum zio_compress comp,
	277	int uncompressed_size, int compressed_size, int byteorder, dmu_tx_t *tx);
34dc7c2f BB	278
	279	void dbuf_clear(dmu_buf_impl_t *db);
	280	void dbuf_evict(dmu_buf_impl_t *db);
	281
34dc7c2f BB	282	void dbuf_unoverride(dbuf_dirty_record_t *dr);
34dc7c2f BB	283	void dbuf_sync_list(list_t list, dmu_tx_t tx);
428870ff	284	void dbuf_release_bp(dmu_buf_impl_t *db);
34dc7c2f	285
b128c09f	286	void dbuf_free_range(struct dnode *dn, uint64_t start, uint64_t end,
34dc7c2f BB	287	struct dmu_tx *);
	288
	289	void dbuf_new_size(dmu_buf_impl_t db, int size, dmu_tx_t tx);
	290
e0b0ca98 BB	291	void dbuf_stats_init(dbuf_hash_table_t *hash);
	292	void dbuf_stats_destroy(void);
	293
572e2857 BB	294	#define DB_DNODE(_db) ((_db)->db_dnode_handle->dnh_dnode)
	295	#define DB_DNODE_LOCK(_db) ((_db)->db_dnode_handle->dnh_zrlock)
	296	#define DB_DNODE_ENTER(_db) (zrl_add(&DB_DNODE_LOCK(_db)))
	297	#define DB_DNODE_EXIT(_db) (zrl_remove(&DB_DNODE_LOCK(_db)))
	298	#define DB_DNODE_HELD(_db) (!zrl_is_zero(&DB_DNODE_LOCK(_db)))
572e2857	299
34dc7c2f BB	300	void dbuf_init(void);
	301	void dbuf_fini(void);
	302
572e2857 BB	303	boolean_t dbuf_is_metadata(dmu_buf_impl_t *db);
572e2857 BB	304
572e2857	305	#define DBUF_GET_BUFC_TYPE(_db) \
13fe0198	306	(dbuf_is_metadata(_db) ? ARC_BUFC_METADATA : ARC_BUFC_DATA)
b128c09f	307
572e2857 BB	308	#define DBUF_IS_CACHEABLE(_db) \
572e2857 BB	309	((_db)->db_objset->os_primary_cache == ZFS_CACHE_ALL \|\| \
13fe0198	310	(dbuf_is_metadata(_db) && \
572e2857	311	((_db)->db_objset->os_primary_cache == ZFS_CACHE_METADATA)))
b128c09f	312
572e2857 BB	313	#define DBUF_IS_L2CACHEABLE(_db) \
572e2857 BB	314	((_db)->db_objset->os_secondary_cache == ZFS_CACHE_ALL \|\| \
13fe0198	315	(dbuf_is_metadata(_db) && \
572e2857	316	((_db)->db_objset->os_secondary_cache == ZFS_CACHE_METADATA)))
34dc7c2f	317
3a17a7a9	318	#define DBUF_IS_L2COMPRESSIBLE(_db) \
4e59f475 SK	319	((_db)->db_objset->os_compress != ZIO_COMPRESS_OFF \|\| \
4e59f475 SK	320	(dbuf_is_metadata(_db) && zfs_mdcomp_disable == B_FALSE))
3a17a7a9	321
34dc7c2f BB	322	#ifdef ZFS_DEBUG
	323
	324	/*
	325	* There should be a ## between the string literal and fmt, to make it
	326	* clear that we're joining two strings together, but gcc does not
	327	* support that preprocessor token.
	328	*/
	329	#define dprintf_dbuf(dbuf, fmt, ...) do { \
	330	if (zfs_flags & ZFS_DEBUG_DPRINTF) { \
	331	char __db_buf[32]; \
	332	uint64_t __db_obj = (dbuf)->db.db_object; \
	333	if (__db_obj == DMU_META_DNODE_OBJECT) \
	334	(void) strcpy(__db_buf, "mdn"); \
	335	else \
	336	(void) snprintf(__db_buf, sizeof (__db_buf), "%lld", \
	337	(u_longlong_t)__db_obj); \
	338	dprintf_ds((dbuf)->db_objset->os_dsl_dataset, \
	339	"obj=%s lvl=%u blkid=%lld " fmt, \
	340	__db_buf, (dbuf)->db_level, \
	341	(u_longlong_t)(dbuf)->db_blkid, __VA_ARGS__); \
	342	} \
	343	_NOTE(CONSTCOND) } while (0)
	344
b8d06fca RY	345	#define dprintf_dbuf_bp(db, bp, fmt, ...) do { \
	346	if (zfs_flags & ZFS_DEBUG_DPRINTF) { \
	347	char *__blkbuf = kmem_alloc(BP_SPRINTF_LEN, KM_PUSHPAGE); \
b0bc7a84	348	snprintf_blkptr(__blkbuf, BP_SPRINTF_LEN, bp); \
b8d06fca RY	349	dprintf_dbuf(db, fmt " %s\n", __VA_ARGS__, __blkbuf); \
	350	kmem_free(__blkbuf, BP_SPRINTF_LEN); \
	351	} \
34dc7c2f BB	352	_NOTE(CONSTCOND) } while (0)
	353
	354	#define DBUF_VERIFY(db) dbuf_verify(db)
	355
	356	#else
	357
	358	#define dprintf_dbuf(db, fmt, ...)
	359	#define dprintf_dbuf_bp(db, bp, fmt, ...)
	360	#define DBUF_VERIFY(db)
	361
	362	#endif
	363
	364
	365	#ifdef __cplusplus
	366	}
	367	#endif
	368
	369	#endif /* _SYS_DBUF_H */