[mirror_zfs.git] / include / sys / sa_impl.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) 2010, Oracle and/or its affiliates. All rights reserved.
 * Copyright (c) 2013 by Delphix. All rights reserved.
 * Copyright (c) 2014 Spectra Logic Corporation, All rights reserved.
 */

#ifndef	_SYS_SA_IMPL_H
#define	_SYS_SA_IMPL_H

#include <sys/dmu.h>
#include <sys/refcount.h>
#include <sys/list.h>

/*
 * Array of known attributes and their
 * various characteristics.
 */
typedef struct sa_attr_table {
	sa_attr_type_t	sa_attr;
	uint8_t sa_registered;
	uint16_t sa_length;
	sa_bswap_type_t sa_byteswap;
	char *sa_name;
} sa_attr_table_t;

/*
 * Zap attribute format for attribute registration
 *
 * 64      56      48      40      32      24      16      8       0
 * +-------+-------+-------+-------+-------+-------+-------+-------+
 * |        unused         |      len      | bswap |   attr num    |
 * +-------+-------+-------+-------+-------+-------+-------+-------+
 *
 * Zap attribute format for layout information.
 *
 * layout information is stored as an array of attribute numbers
 * The name of the attribute is the layout number (0, 1, 2, ...)
 *
 * 16       0
 * +---- ---+
 * | attr # |
 * +--------+
 * | attr # |
 * +--- ----+
 *  ......
 *
 */

#define	ATTR_BSWAP(x)	BF32_GET(x, 16, 8)
#define	ATTR_LENGTH(x)	BF32_GET(x, 24, 16)
#define	ATTR_NUM(x)	BF32_GET(x, 0, 16)
#define	ATTR_ENCODE(x, attr, length, bswap) \
{ \
	BF64_SET(x, 24, 16, length); \
	BF64_SET(x, 16, 8, bswap); \
	BF64_SET(x, 0, 16, attr); \
}

#define	TOC_OFF(x)		BF32_GET(x, 0, 23)
#define	TOC_ATTR_PRESENT(x)	BF32_GET(x, 31, 1)
#define	TOC_LEN_IDX(x)		BF32_GET(x, 24, 4)
#define	TOC_ATTR_ENCODE(x, len_idx, offset) \
{ \
	BF32_SET(x, 31, 1, 1); \
	BF32_SET(x, 24, 7, len_idx); \
	BF32_SET(x, 0, 24, offset); \
}

#define	SA_LAYOUTS	"LAYOUTS"
#define	SA_REGISTRY	"REGISTRY"

/*
 * Each unique layout will have their own table
 * sa_lot (layout_table)
 */
typedef struct sa_lot {
	avl_node_t lot_num_node;
	avl_node_t lot_hash_node;
	uint64_t lot_num;
	uint64_t lot_hash;
	sa_attr_type_t *lot_attrs;	/* array of attr #'s */
	uint32_t lot_var_sizes;	/* how many aren't fixed size */
	uint32_t lot_attr_count;	/* total attr count */
	list_t 	lot_idx_tab;	/* should be only a couple of entries */
	int	lot_instance;	/* used with lot_hash to identify entry */
} sa_lot_t;

/* index table of offsets */
typedef struct sa_idx_tab {
	list_node_t	sa_next;
	sa_lot_t	*sa_layout;
	uint16_t	*sa_variable_lengths;
	zfs_refcount_t	sa_refcount;
	uint32_t	*sa_idx_tab;	/* array of offsets */
} sa_idx_tab_t;

/*
 * Since the offset/index information into the actual data
 * will usually be identical we can share that information with
 * all handles that have the exact same offsets.
 *
 * You would typically only have a large number of different table of
 * contents if you had a several variable sized attributes.
 *
 * Two AVL trees are used to track the attribute layout numbers.
 * one is keyed by number and will be consulted when a DMU_OT_SA
 * object is first read.  The second tree is keyed by the hash signature
 * of the attributes and will be consulted when an attribute is added
 * to determine if we already have an instance of that layout.  Both
 * of these tree's are interconnected.  The only difference is that
 * when an entry is found in the "hash" tree the list of attributes will
 * need to be compared against the list of attributes you have in hand.
 * The assumption is that typically attributes will just be updated and
 * adding a completely new attribute is a very rare operation.
 */
struct sa_os {
	kmutex_t 	sa_lock;
	boolean_t	sa_need_attr_registration;
	boolean_t	sa_force_spill;
	uint64_t	sa_master_obj;
	uint64_t	sa_reg_attr_obj;
	uint64_t	sa_layout_attr_obj;
	int		sa_num_attrs;
	sa_attr_table_t *sa_attr_table;	 /* private attr table */
	sa_update_cb_t	*sa_update_cb;
	avl_tree_t	sa_layout_num_tree;  /* keyed by layout number */
	avl_tree_t	sa_layout_hash_tree; /* keyed by layout hash value */
	int		sa_user_table_sz;
	sa_attr_type_t	*sa_user_table; /* user name->attr mapping table */
};

/*
 * header for all bonus and spill buffers.
 *
 * The header has a fixed portion with a variable number
 * of "lengths" depending on the number of variable sized
 * attributes which are determined by the "layout number"
 */

#define	SA_MAGIC	0x2F505A  /* ZFS SA */
typedef struct sa_hdr_phys {
	uint32_t sa_magic;
	/*
	 * Encoded with hdrsize and layout number as follows:
	 * 16      10       0
	 * +--------+-------+
	 * | hdrsz  |layout |
	 * +--------+-------+
	 *
	 * Bits 0-10 are the layout number
	 * Bits 11-16 are the size of the header.
	 * The hdrsize is the number * 8
	 *
	 * For example.
	 * hdrsz of 1 ==> 8 byte header
	 *          2 ==> 16 byte header
	 *
	 */
	uint16_t sa_layout_info;
	uint16_t sa_lengths[1];	/* optional sizes for variable length attrs */
	/* ... Data follows the lengths.  */
} sa_hdr_phys_t;

#define	SA_HDR_LAYOUT_NUM(hdr) BF32_GET(hdr->sa_layout_info, 0, 10)
#define	SA_HDR_SIZE(hdr) BF32_GET_SB(hdr->sa_layout_info, 10, 6, 3, 0)
#define	SA_HDR_LAYOUT_INFO_ENCODE(x, num, size) \
{ \
	BF32_SET_SB(x, 10, 6, 3, 0, size); \
	BF32_SET(x, 0, 10, num); \
}

typedef enum sa_buf_type {
	SA_BONUS = 1,
	SA_SPILL = 2
} sa_buf_type_t;

typedef enum sa_data_op {
	SA_LOOKUP,
	SA_UPDATE,
	SA_ADD,
	SA_REPLACE,
	SA_REMOVE
} sa_data_op_t;

/*
 * Opaque handle used for most sa functions
 *
 * This needs to be kept as small as possible.
 */

struct sa_handle {
	dmu_buf_user_t	sa_dbu;
	kmutex_t	sa_lock;
	dmu_buf_t	*sa_bonus;
	dmu_buf_t	*sa_spill;
	objset_t	*sa_os;
	void		*sa_userp;
	sa_idx_tab_t	*sa_bonus_tab;	 /* idx of bonus */
	sa_idx_tab_t	*sa_spill_tab; /* only present if spill activated */
};

#define	SA_GET_DB(hdl, type)	\
	(dmu_buf_impl_t *)((type == SA_BONUS) ? hdl->sa_bonus : hdl->sa_spill)

#define	SA_GET_HDR(hdl, type) \
	((sa_hdr_phys_t *)((dmu_buf_impl_t *)(SA_GET_DB(hdl, \
	type))->db.db_data))

#define	SA_IDX_TAB_GET(hdl, type) \
	(type == SA_BONUS ? hdl->sa_bonus_tab : hdl->sa_spill_tab)

#define	IS_SA_BONUSTYPE(a)	\
	((a == DMU_OT_SA) ? B_TRUE : B_FALSE)

#define	SA_BONUSTYPE_FROM_DB(db) \
	(dmu_get_bonustype((dmu_buf_t *)db))

#define	SA_BLKPTR_SPACE	(DN_OLD_MAX_BONUSLEN - sizeof (blkptr_t))

#define	SA_LAYOUT_NUM(x, type) \
	((!IS_SA_BONUSTYPE(type) ? 0 : (((IS_SA_BONUSTYPE(type)) && \
	((SA_HDR_LAYOUT_NUM(x)) == 0)) ? 1 : SA_HDR_LAYOUT_NUM(x))))


#define	SA_REGISTERED_LEN(sa, attr) sa->sa_attr_table[attr].sa_length

#define	SA_ATTR_LEN(sa, idx, attr, hdr) ((SA_REGISTERED_LEN(sa, attr) == 0) ?\
	hdr->sa_lengths[TOC_LEN_IDX(idx->sa_idx_tab[attr])] : \
	SA_REGISTERED_LEN(sa, attr))

#define	SA_SET_HDR(hdr, num, size) \
	{ \
		hdr->sa_magic = SA_MAGIC; \
		SA_HDR_LAYOUT_INFO_ENCODE(hdr->sa_layout_info, num, size); \
	}

#define	SA_ATTR_INFO(sa, idx, hdr, attr, bulk, type, hdl) \
	{ \
		bulk.sa_size = SA_ATTR_LEN(sa, idx, attr, hdr); \
		bulk.sa_buftype = type; \
		bulk.sa_addr = \
		    (void *)((uintptr_t)TOC_OFF(idx->sa_idx_tab[attr]) + \
		    (uintptr_t)hdr); \
}

#define	SA_HDR_SIZE_MATCH_LAYOUT(hdr, tb) \
	(SA_HDR_SIZE(hdr) == (sizeof (sa_hdr_phys_t) + \
	(tb->lot_var_sizes > 1 ? P2ROUNDUP((tb->lot_var_sizes - 1) * \
	sizeof (uint16_t), 8) : 0)))

int sa_add_impl(sa_handle_t *, sa_attr_type_t,
    uint32_t, sa_data_locator_t, void *, dmu_tx_t *);

void sa_register_update_callback_locked(objset_t *, sa_update_cb_t *);
int sa_size_locked(sa_handle_t *, sa_attr_type_t, int *);

void sa_default_locator(void **, uint32_t *, uint32_t, boolean_t, void *);
int sa_attr_size(sa_os_t *, sa_idx_tab_t *, sa_attr_type_t,
    uint16_t *, sa_hdr_phys_t *);

#ifdef	__cplusplus
extern "C" {
#endif

#ifdef	__cplusplus
}
#endif

#endif	/* _SYS_SA_IMPL_H */
Commit	Line	Data
428870ff 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	/*
572e2857	22	* Copyright (c) 2010, Oracle and/or its affiliates. All rights reserved.
e8b96c60	23	* Copyright (c) 2013 by Delphix. All rights reserved.
0c66c32d	24	* Copyright (c) 2014 Spectra Logic Corporation, All rights reserved.
428870ff BB	25	*/
	26
	27	#ifndef _SYS_SA_IMPL_H
	28	#define _SYS_SA_IMPL_H
	29
	30	#include <sys/dmu.h>
	31	#include <sys/refcount.h>
	32	#include <sys/list.h>
	33
	34	/*
	35	* Array of known attributes and their
	36	* various characteristics.
	37	*/
	38	typedef struct sa_attr_table {
	39	sa_attr_type_t sa_attr;
	40	uint8_t sa_registered;
	41	uint16_t sa_length;
	42	sa_bswap_type_t sa_byteswap;
	43	char *sa_name;
	44	} sa_attr_table_t;
	45
	46	/*
	47	* Zap attribute format for attribute registration
	48	*
	49	* 64 56 48 40 32 24 16 8 0
	50	* +-------+-------+-------+-------+-------+-------+-------+-------+
	51	* \| unused \| len \| bswap \| attr num \|
	52	* +-------+-------+-------+-------+-------+-------+-------+-------+
	53	*
	54	* Zap attribute format for layout information.
	55	*
	56	* layout information is stored as an array of attribute numbers
	57	* The name of the attribute is the layout number (0, 1, 2, ...)
	58	*
	59	* 16 0
	60	* +---- ---+
	61	* \| attr # \|
	62	* +--------+
	63	* \| attr # \|
	64	* +--- ----+
	65	* ......
	66	*
	67	*/
	68
	69	#define ATTR_BSWAP(x) BF32_GET(x, 16, 8)
	70	#define ATTR_LENGTH(x) BF32_GET(x, 24, 16)
	71	#define ATTR_NUM(x) BF32_GET(x, 0, 16)
	72	#define ATTR_ENCODE(x, attr, length, bswap) \
	73	{ \
	74	BF64_SET(x, 24, 16, length); \
	75	BF64_SET(x, 16, 8, bswap); \
	76	BF64_SET(x, 0, 16, attr); \
	77	}
	78
	79	#define TOC_OFF(x) BF32_GET(x, 0, 23)
	80	#define TOC_ATTR_PRESENT(x) BF32_GET(x, 31, 1)
	81	#define TOC_LEN_IDX(x) BF32_GET(x, 24, 4)
	82	#define TOC_ATTR_ENCODE(x, len_idx, offset) \
	83	{ \
	84	BF32_SET(x, 31, 1, 1); \
	85	BF32_SET(x, 24, 7, len_idx); \
	86	BF32_SET(x, 0, 24, offset); \
	87	}
	88
89	#define SA_LAYOUTS "LAYOUTS"
90	#define SA_REGISTRY "REGISTRY"
91
92	/*
93	* Each unique layout will have their own table
94	* sa_lot (layout_table)
95	*/
96	typedef struct sa_lot {
97	avl_node_t lot_num_node;
98	avl_node_t lot_hash_node;
99	uint64_t lot_num;
100	uint64_t lot_hash;
101	sa_attr_type_t lot_attrs; / array of attr #'s */
102	uint32_t lot_var_sizes; /* how many aren't fixed size */
103	uint32_t lot_attr_count; /* total attr count */
104	list_t lot_idx_tab; /* should be only a couple of entries */
105	int lot_instance; /* used with lot_hash to identify entry */
106	} sa_lot_t;
107
108	/* index table of offsets */
109	typedef struct sa_idx_tab {
110	list_node_t sa_next;
111	sa_lot_t *sa_layout;
112	uint16_t *sa_variable_lengths;
c13060e4	113	zfs_refcount_t sa_refcount;
428870ff BB	114	uint32_t sa_idx_tab; / array of offsets */
	115	} sa_idx_tab_t;
	116
	117	/*
	118	* Since the offset/index information into the actual data
	119	* will usually be identical we can share that information with
	120	* all handles that have the exact same offsets.
	121	*
	122	* You would typically only have a large number of different table of
	123	* contents if you had a several variable sized attributes.
	124	*
	125	* Two AVL trees are used to track the attribute layout numbers.
	126	* one is keyed by number and will be consulted when a DMU_OT_SA
	127	* object is first read. The second tree is keyed by the hash signature
	128	* of the attributes and will be consulted when an attribute is added
	129	* to determine if we already have an instance of that layout. Both
	130	* of these tree's are interconnected. The only difference is that
	131	* when an entry is found in the "hash" tree the list of attributes will
	132	* need to be compared against the list of attributes you have in hand.
	133	* The assumption is that typically attributes will just be updated and
	134	* adding a completely new attribute is a very rare operation.
	135	*/
	136	struct sa_os {
	137	kmutex_t sa_lock;
	138	boolean_t sa_need_attr_registration;
	139	boolean_t sa_force_spill;
	140	uint64_t sa_master_obj;
	141	uint64_t sa_reg_attr_obj;
	142	uint64_t sa_layout_attr_obj;
	143	int sa_num_attrs;
	144	sa_attr_table_t sa_attr_table; / private attr table */
	145	sa_update_cb_t *sa_update_cb;
	146	avl_tree_t sa_layout_num_tree; /* keyed by layout number */
	147	avl_tree_t sa_layout_hash_tree; /* keyed by layout hash value */
	148	int sa_user_table_sz;
	149	sa_attr_type_t sa_user_table; / user name->attr mapping table */
	150	};
	151
	152	/*
	153	* header for all bonus and spill buffers.
d3cc8b15	154	*
428870ff BB	155	* The header has a fixed portion with a variable number
428870ff BB	156	* of "lengths" depending on the number of variable sized
e8b96c60	157	* attributes which are determined by the "layout number"
428870ff BB	158	*/
	159
	160	#define SA_MAGIC 0x2F505A /* ZFS SA */
	161	typedef struct sa_hdr_phys {
	162	uint32_t sa_magic;
d3cc8b15 WA	163	/*
	164	* Encoded with hdrsize and layout number as follows:
	165	* 16 10 0
	166	* +--------+-------+
	167	* \| hdrsz \|layout \|
	168	* +--------+-------+
	169	*
	170	* Bits 0-10 are the layout number
	171	* Bits 11-16 are the size of the header.
	172	* The hdrsize is the number * 8
	173	*
	174	* For example.
	175	* hdrsz of 1 ==> 8 byte header
	176	* 2 ==> 16 byte header
	177	*
	178	*/
	179	uint16_t sa_layout_info;
428870ff BB	180	uint16_t sa_lengths[1]; /* optional sizes for variable length attrs */
	181	/* ... Data follows the lengths. */
	182	} sa_hdr_phys_t;
	183
428870ff	184	#define SA_HDR_LAYOUT_NUM(hdr) BF32_GET(hdr->sa_layout_info, 0, 10)
a94addd9	185	#define SA_HDR_SIZE(hdr) BF32_GET_SB(hdr->sa_layout_info, 10, 6, 3, 0)
428870ff BB	186	#define SA_HDR_LAYOUT_INFO_ENCODE(x, num, size) \
	187	{ \
	188	BF32_SET_SB(x, 10, 6, 3, 0, size); \
	189	BF32_SET(x, 0, 10, num); \
	190	}
	191
	192	typedef enum sa_buf_type {
	193	SA_BONUS = 1,
	194	SA_SPILL = 2
	195	} sa_buf_type_t;
	196
	197	typedef enum sa_data_op {
	198	SA_LOOKUP,
	199	SA_UPDATE,
	200	SA_ADD,
	201	SA_REPLACE,
	202	SA_REMOVE
	203	} sa_data_op_t;
	204
	205	/*
	206	* Opaque handle used for most sa functions
	207	*
	208	* This needs to be kept as small as possible.
	209	*/
	210
	211	struct sa_handle {
0c66c32d	212	dmu_buf_user_t sa_dbu;
428870ff BB	213	kmutex_t sa_lock;
	214	dmu_buf_t *sa_bonus;
	215	dmu_buf_t *sa_spill;
	216	objset_t *sa_os;
0c66c32d	217	void *sa_userp;
428870ff BB	218	sa_idx_tab_t sa_bonus_tab; / idx of bonus */
	219	sa_idx_tab_t sa_spill_tab; / only present if spill activated */
	220	};
	221
	222	#define SA_GET_DB(hdl, type) \
	223	(dmu_buf_impl_t *)((type == SA_BONUS) ? hdl->sa_bonus : hdl->sa_spill)
	224
	225	#define SA_GET_HDR(hdl, type) \
	226	((sa_hdr_phys_t )((dmu_buf_impl_t )(SA_GET_DB(hdl, \
	227	type))->db.db_data))
	228
	229	#define SA_IDX_TAB_GET(hdl, type) \
	230	(type == SA_BONUS ? hdl->sa_bonus_tab : hdl->sa_spill_tab)
	231
	232	#define IS_SA_BONUSTYPE(a) \
	233	((a == DMU_OT_SA) ? B_TRUE : B_FALSE)
	234
	235	#define SA_BONUSTYPE_FROM_DB(db) \
572e2857	236	(dmu_get_bonustype((dmu_buf_t *)db))
428870ff	237
50c957f7	238	#define SA_BLKPTR_SPACE (DN_OLD_MAX_BONUSLEN - sizeof (blkptr_t))
428870ff BB	239
	240	#define SA_LAYOUT_NUM(x, type) \
	241	((!IS_SA_BONUSTYPE(type) ? 0 : (((IS_SA_BONUSTYPE(type)) && \
	242	((SA_HDR_LAYOUT_NUM(x)) == 0)) ? 1 : SA_HDR_LAYOUT_NUM(x))))
	243
	244
	245	#define SA_REGISTERED_LEN(sa, attr) sa->sa_attr_table[attr].sa_length
	246
	247	#define SA_ATTR_LEN(sa, idx, attr, hdr) ((SA_REGISTERED_LEN(sa, attr) == 0) ?\
	248	hdr->sa_lengths[TOC_LEN_IDX(idx->sa_idx_tab[attr])] : \
	249	SA_REGISTERED_LEN(sa, attr))
	250
	251	#define SA_SET_HDR(hdr, num, size) \
	252	{ \
	253	hdr->sa_magic = SA_MAGIC; \
	254	SA_HDR_LAYOUT_INFO_ENCODE(hdr->sa_layout_info, num, size); \
	255	}
	256
	257	#define SA_ATTR_INFO(sa, idx, hdr, attr, bulk, type, hdl) \
	258	{ \
	259	bulk.sa_size = SA_ATTR_LEN(sa, idx, attr, hdr); \
	260	bulk.sa_buftype = type; \
	261	bulk.sa_addr = \
	262	(void *)((uintptr_t)TOC_OFF(idx->sa_idx_tab[attr]) + \
	263	(uintptr_t)hdr); \
	264	}
	265
	266	#define SA_HDR_SIZE_MATCH_LAYOUT(hdr, tb) \
	267	(SA_HDR_SIZE(hdr) == (sizeof (sa_hdr_phys_t) + \
	268	(tb->lot_var_sizes > 1 ? P2ROUNDUP((tb->lot_var_sizes - 1) * \
	269	sizeof (uint16_t), 8) : 0)))
	270
	271	int sa_add_impl(sa_handle_t *, sa_attr_type_t,
	272	uint32_t, sa_data_locator_t, void , dmu_tx_t );
	273
	274	void sa_register_update_callback_locked(objset_t , sa_update_cb_t );
	275	int sa_size_locked(sa_handle_t , sa_attr_type_t, int );
	276
	277	void sa_default_locator(void *, uint32_t , uint32_t, boolean_t, void *);
	278	int sa_attr_size(sa_os_t , sa_idx_tab_t , sa_attr_type_t,
	279	uint16_t , sa_hdr_phys_t );
	280
	281	#ifdef __cplusplus
	282	extern "C" {
	283	#endif
	284
	285	#ifdef __cplusplus
	286	}
	287	#endif
	288
	289	#endif /* _SYS_SA_IMPL_H */