[net-next-2.6.git] / fs / ceph / rados.h

#ifndef __RADOS_H
#define __RADOS_H

/*
 * Data types for the Ceph distributed object storage layer RADOS
 * (Reliable Autonomic Distributed Object Store).
 */

#include "msgr.h"

/*
 * fs id
 */
struct ceph_fsid {
	unsigned char fsid[16];
};

static inline int ceph_fsid_compare(const struct ceph_fsid *a,
				    const struct ceph_fsid *b)
{
	return memcmp(a, b, sizeof(*a));
}

/*
 * ino, object, etc.
 */
typedef __le64 ceph_snapid_t;
#define CEPH_SNAPDIR ((__u64)(-1))  /* reserved for hidden .snap dir */
#define CEPH_NOSNAP  ((__u64)(-2))  /* "head", "live" revision */
#define CEPH_MAXSNAP ((__u64)(-3))  /* largest valid snapid */

struct ceph_timespec {
	__le32 tv_sec;
	__le32 tv_nsec;
} __attribute__ ((packed));


/*
 * object layout - how objects are mapped into PGs
 */
#define CEPH_OBJECT_LAYOUT_HASH     1
#define CEPH_OBJECT_LAYOUT_LINEAR   2
#define CEPH_OBJECT_LAYOUT_HASHINO  3

/*
 * pg layout -- how PGs are mapped onto (sets of) OSDs
 */
#define CEPH_PG_LAYOUT_CRUSH  0
#define CEPH_PG_LAYOUT_HASH   1
#define CEPH_PG_LAYOUT_LINEAR 2
#define CEPH_PG_LAYOUT_HYBRID 3


/*
 * placement group.
 * we encode this into one __le64.
 */
struct ceph_pg {
	__le16 preferred; /* preferred primary osd */
	__le16 ps;        /* placement seed */
	__le32 pool;      /* object pool */
} __attribute__ ((packed));

/*
 * pg_pool is a set of pgs storing a pool of objects
 *
 *  pg_num -- base number of pseudorandomly placed pgs
 *
 *  pgp_num -- effective number when calculating pg placement.  this
 * is used for pg_num increases.  new pgs result in data being "split"
 * into new pgs.  for this to proceed smoothly, new pgs are intiially
 * colocated with their parents; that is, pgp_num doesn't increase
 * until the new pgs have successfully split.  only _then_ are the new
 * pgs placed independently.
 *
 *  lpg_num -- localized pg count (per device).  replicas are randomly
 * selected.
 *
 *  lpgp_num -- as above.
 */
#define CEPH_PG_TYPE_REP     1
#define CEPH_PG_TYPE_RAID4   2
struct ceph_pg_pool {
	__u8 type;                /* CEPH_PG_TYPE_* */
	__u8 size;                /* number of osds in each pg */
	__u8 crush_ruleset;       /* crush placement rule */
	__u8 object_hash;         /* hash mapping object name to ps */
	__le32 pg_num, pgp_num;   /* number of pg's */
	__le32 lpg_num, lpgp_num; /* number of localized pg's */
	__le32 last_change;       /* most recent epoch changed */
	__le64 snap_seq;          /* seq for per-pool snapshot */
	__le32 snap_epoch;        /* epoch of last snap */
	__le32 num_snaps;
	__le32 num_removed_snap_intervals;
} __attribute__ ((packed));

/*
 * stable_mod func is used to control number of placement groups.
 * similar to straight-up modulo, but produces a stable mapping as b
 * increases over time.  b is the number of bins, and bmask is the
 * containing power of 2 minus 1.
 *
 * b <= bmask and bmask=(2**n)-1
 * e.g., b=12 -> bmask=15, b=123 -> bmask=127
 */
static inline int ceph_stable_mod(int x, int b, int bmask)
{
	if ((x & bmask) < b)
		return x & bmask;
	else
		return x & (bmask >> 1);
}

/*
 * object layout - how a given object should be stored.
 */
struct ceph_object_layout {
	struct ceph_pg ol_pgid;   /* raw pg, with _full_ ps precision. */
	__le32 ol_stripe_unit;    /* for per-object parity, if any */
} __attribute__ ((packed));

/*
 * compound epoch+version, used by storage layer to serialize mutations
 */
struct ceph_eversion {
	__le32 epoch;
	__le64 version;
} __attribute__ ((packed));

/*
 * osd map bits
 */

/* status bits */
#define CEPH_OSD_EXISTS 1
#define CEPH_OSD_UP     2

/* osd weights.  fixed point value: 0x10000 == 1.0 ("in"), 0 == "out" */
#define CEPH_OSD_IN  0x10000
#define CEPH_OSD_OUT 0


/*
 * osd map flag bits
 */
#define CEPH_OSDMAP_NEARFULL (1<<0)  /* sync writes (near ENOSPC) */
#define CEPH_OSDMAP_FULL     (1<<1)  /* no data writes (ENOSPC) */
#define CEPH_OSDMAP_PAUSERD  (1<<2)  /* pause all reads */
#define CEPH_OSDMAP_PAUSEWR  (1<<3)  /* pause all writes */
#define CEPH_OSDMAP_PAUSEREC (1<<4)  /* pause recovery */

/*
 * osd ops
 */
#define CEPH_OSD_OP_MODE       0xf000
#define CEPH_OSD_OP_MODE_RD    0x1000
#define CEPH_OSD_OP_MODE_WR    0x2000
#define CEPH_OSD_OP_MODE_RMW   0x3000
#define CEPH_OSD_OP_MODE_SUB   0x4000

#define CEPH_OSD_OP_TYPE       0x0f00
#define CEPH_OSD_OP_TYPE_LOCK  0x0100
#define CEPH_OSD_OP_TYPE_DATA  0x0200
#define CEPH_OSD_OP_TYPE_ATTR  0x0300
#define CEPH_OSD_OP_TYPE_EXEC  0x0400
#define CEPH_OSD_OP_TYPE_PG    0x0500

enum {
	/** data **/
	/* read */
	CEPH_OSD_OP_READ      = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 1,
	CEPH_OSD_OP_STAT      = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 2,

	/* fancy read */
	CEPH_OSD_OP_MASKTRUNC = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 4,

	/* write */
	CEPH_OSD_OP_WRITE     = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 1,
	CEPH_OSD_OP_WRITEFULL = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 2,
	CEPH_OSD_OP_TRUNCATE  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 3,
	CEPH_OSD_OP_ZERO      = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 4,
	CEPH_OSD_OP_DELETE    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 5,

	/* fancy write */
	CEPH_OSD_OP_APPEND    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 6,
	CEPH_OSD_OP_STARTSYNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 7,
	CEPH_OSD_OP_SETTRUNC  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 8,
	CEPH_OSD_OP_TRIMTRUNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 9,

	CEPH_OSD_OP_TMAPUP  = CEPH_OSD_OP_MODE_RMW | CEPH_OSD_OP_TYPE_DATA | 10,
	CEPH_OSD_OP_TMAPPUT = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 11,
	CEPH_OSD_OP_TMAPGET = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 12,

	CEPH_OSD_OP_CREATE  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 13,

	/** attrs **/
	/* read */
	CEPH_OSD_OP_GETXATTR  = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 1,
	CEPH_OSD_OP_GETXATTRS = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 2,

	/* write */
	CEPH_OSD_OP_SETXATTR  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 1,
	CEPH_OSD_OP_SETXATTRS = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 2,
	CEPH_OSD_OP_RESETXATTRS = CEPH_OSD_OP_MODE_WR|CEPH_OSD_OP_TYPE_ATTR | 3,
	CEPH_OSD_OP_RMXATTR   = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 4,

	/** subop **/
	CEPH_OSD_OP_PULL           = CEPH_OSD_OP_MODE_SUB | 1,
	CEPH_OSD_OP_PUSH           = CEPH_OSD_OP_MODE_SUB | 2,
	CEPH_OSD_OP_BALANCEREADS   = CEPH_OSD_OP_MODE_SUB | 3,
	CEPH_OSD_OP_UNBALANCEREADS = CEPH_OSD_OP_MODE_SUB | 4,
	CEPH_OSD_OP_SCRUB          = CEPH_OSD_OP_MODE_SUB | 5,

	/** lock **/
	CEPH_OSD_OP_WRLOCK    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 1,
	CEPH_OSD_OP_WRUNLOCK  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 2,
	CEPH_OSD_OP_RDLOCK    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 3,
	CEPH_OSD_OP_RDUNLOCK  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 4,
	CEPH_OSD_OP_UPLOCK    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 5,
	CEPH_OSD_OP_DNLOCK    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 6,

	/** exec **/
	CEPH_OSD_OP_CALL    = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_EXEC | 1,

	/** pg **/
	CEPH_OSD_OP_PGLS      = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_PG | 1,
};

static inline int ceph_osd_op_type_lock(int op)
{
	return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_LOCK;
}
static inline int ceph_osd_op_type_data(int op)
{
	return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_DATA;
}
static inline int ceph_osd_op_type_attr(int op)
{
	return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_ATTR;
}
static inline int ceph_osd_op_type_exec(int op)
{
	return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_EXEC;
}
static inline int ceph_osd_op_type_pg(int op)
{
	return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_PG;
}

static inline int ceph_osd_op_mode_subop(int op)
{
	return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_SUB;
}
static inline int ceph_osd_op_mode_read(int op)
{
	return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_RD;
}
static inline int ceph_osd_op_mode_modify(int op)
{
	return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_WR;
}

#define CEPH_OSD_TMAP_HDR 'h'
#define CEPH_OSD_TMAP_SET 's'
#define CEPH_OSD_TMAP_RM  'r'

extern const char *ceph_osd_op_name(int op);


/*
 * osd op flags
 *
 * An op may be READ, WRITE, or READ|WRITE.
 */
enum {
	CEPH_OSD_FLAG_ACK = 1,          /* want (or is) "ack" ack */
	CEPH_OSD_FLAG_ONNVRAM = 2,      /* want (or is) "onnvram" ack */
	CEPH_OSD_FLAG_ONDISK = 4,       /* want (or is) "ondisk" ack */
	CEPH_OSD_FLAG_RETRY = 8,        /* resend attempt */
	CEPH_OSD_FLAG_READ = 16,        /* op may read */
	CEPH_OSD_FLAG_WRITE = 32,       /* op may write */
	CEPH_OSD_FLAG_ORDERSNAP = 64,   /* EOLDSNAP if snapc is out of order */
	CEPH_OSD_FLAG_PEERSTAT = 128,   /* msg includes osd_peer_stat */
	CEPH_OSD_FLAG_BALANCE_READS = 256,
	CEPH_OSD_FLAG_PARALLELEXEC = 512, /* execute op in parallel */
	CEPH_OSD_FLAG_PGOP = 1024,      /* pg op, no object */
	CEPH_OSD_FLAG_EXEC = 2048,      /* op may exec */
};

enum {
	CEPH_OSD_OP_FLAG_EXCL = 1,      /* EXCL object create */
};

#define EOLDSNAPC    ERESTART  /* ORDERSNAP flag set; writer has old snapc*/
#define EBLACKLISTED ESHUTDOWN /* blacklisted */

/*
 * an individual object operation.  each may be accompanied by some data
 * payload
 */
struct ceph_osd_op {
	__le16 op;           /* CEPH_OSD_OP_* */
	__le32 flags;        /* CEPH_OSD_FLAG_* */
	union {
		struct {
			__le64 offset, length;
			__le64 truncate_size;
			__le32 truncate_seq;
		} __attribute__ ((packed)) extent;
		struct {
			__le32 name_len;
			__le32 value_len;
		} __attribute__ ((packed)) xattr;
		struct {
			__u8 class_len;
			__u8 method_len;
			__u8 argc;
			__le32 indata_len;
		} __attribute__ ((packed)) cls;
		struct {
			__le64 cookie, count;
		} __attribute__ ((packed)) pgls;
	};
	__le32 payload_len;
} __attribute__ ((packed));

/*
 * osd request message header.  each request may include multiple
 * ceph_osd_op object operations.
 */
struct ceph_osd_request_head {
	__le32 client_inc;                 /* client incarnation */
	struct ceph_object_layout layout;  /* pgid */
	__le32 osdmap_epoch;               /* client's osdmap epoch */

	__le32 flags;

	struct ceph_timespec mtime;        /* for mutations only */
	struct ceph_eversion reassert_version; /* if we are replaying op */

	__le32 object_len;     /* length of object name */

	__le64 snapid;         /* snapid to read */
	__le64 snap_seq;       /* writer's snap context */
	__le32 num_snaps;

	__le16 num_ops;
	struct ceph_osd_op ops[];  /* followed by ops[], obj, ticket, snaps */
} __attribute__ ((packed));

struct ceph_osd_reply_head {
	__le32 client_inc;                /* client incarnation */
	__le32 flags;
	struct ceph_object_layout layout;
	__le32 osdmap_epoch;
	struct ceph_eversion reassert_version; /* for replaying uncommitted */

	__le32 result;                    /* result code */

	__le32 object_len;                /* length of object name */
	__le32 num_ops;
	struct ceph_osd_op ops[0];  /* ops[], object */
} __attribute__ ((packed));


#endif
Commit	Line	Data
0dee3c28 SW	1	#ifndef __RADOS_H
	2	#define __RADOS_H
	3
	4	/*
	5	* Data types for the Ceph distributed object storage layer RADOS
	6	* (Reliable Autonomic Distributed Object Store).
	7	*/
	8
	9	#include "msgr.h"
	10
	11	/*
	12	* fs id
	13	*/
	14	struct ceph_fsid {
	15	unsigned char fsid[16];
	16	};
	17
	18	static inline int ceph_fsid_compare(const struct ceph_fsid *a,
	19	const struct ceph_fsid *b)
	20	{
	21	return memcmp(a, b, sizeof(*a));
	22	}
	23
	24	/*
	25	* ino, object, etc.
	26	*/
	27	typedef __le64 ceph_snapid_t;
	28	#define CEPH_SNAPDIR ((__u64)(-1)) /* reserved for hidden .snap dir */
	29	#define CEPH_NOSNAP ((__u64)(-2)) /* "head", "live" revision */
	30	#define CEPH_MAXSNAP ((__u64)(-3)) /* largest valid snapid */
	31
	32	struct ceph_timespec {
	33	__le32 tv_sec;
	34	__le32 tv_nsec;
	35	} __attribute__ ((packed));
	36
	37
	38	/*
	39	* object layout - how objects are mapped into PGs
	40	*/
	41	#define CEPH_OBJECT_LAYOUT_HASH 1
	42	#define CEPH_OBJECT_LAYOUT_LINEAR 2
	43	#define CEPH_OBJECT_LAYOUT_HASHINO 3
	44
	45	/*
	46	* pg layout -- how PGs are mapped onto (sets of) OSDs
	47	*/
	48	#define CEPH_PG_LAYOUT_CRUSH 0
	49	#define CEPH_PG_LAYOUT_HASH 1
	50	#define CEPH_PG_LAYOUT_LINEAR 2
	51	#define CEPH_PG_LAYOUT_HYBRID 3
	52
	53
	54	/*
	55	* placement group.
	56	* we encode this into one __le64.
	57	*/
51042122 SW	58	struct ceph_pg {
	59	__le16 preferred; /* preferred primary osd */
	60	__le16 ps; /* placement seed */
	61	__le32 pool; /* object pool */
0dee3c28 SW	62	} __attribute__ ((packed));
	63
	64	/*
	65	* pg_pool is a set of pgs storing a pool of objects
	66	*
	67	* pg_num -- base number of pseudorandomly placed pgs
	68	*
	69	* pgp_num -- effective number when calculating pg placement. this
	70	* is used for pg_num increases. new pgs result in data being "split"
	71	* into new pgs. for this to proceed smoothly, new pgs are intiially
	72	* colocated with their parents; that is, pgp_num doesn't increase
	73	* until the new pgs have successfully split. only _then_ are the new
	74	* pgs placed independently.
	75	*
	76	* lpg_num -- localized pg count (per device). replicas are randomly
	77	* selected.
	78	*
	79	* lpgp_num -- as above.
	80	*/
	81	#define CEPH_PG_TYPE_REP 1
	82	#define CEPH_PG_TYPE_RAID4 2
	83	struct ceph_pg_pool {
	84	__u8 type; /* CEPH_PG_TYPE_* */
	85	__u8 size; /* number of osds in each pg */
	86	__u8 crush_ruleset; /* crush placement rule */
1654dd0c	87	__u8 object_hash; /* hash mapping object name to ps */
0dee3c28 SW	88	__le32 pg_num, pgp_num; /* number of pg's */
	89	__le32 lpg_num, lpgp_num; /* number of localized pg's */
	90	__le32 last_change; /* most recent epoch changed */
	91	__le64 snap_seq; /* seq for per-pool snapshot */
	92	__le32 snap_epoch; /* epoch of last snap */
	93	__le32 num_snaps;
	94	__le32 num_removed_snap_intervals;
	95	} __attribute__ ((packed));
	96
	97	/*
	98	* stable_mod func is used to control number of placement groups.
	99	* similar to straight-up modulo, but produces a stable mapping as b
	100	* increases over time. b is the number of bins, and bmask is the
	101	* containing power of 2 minus 1.
	102	*
	103	* b <= bmask and bmask=(2**n)-1
	104	* e.g., b=12 -> bmask=15, b=123 -> bmask=127
	105	*/
	106	static inline int ceph_stable_mod(int x, int b, int bmask)
	107	{
	108	if ((x & bmask) < b)
	109	return x & bmask;
	110	else
	111	return x & (bmask >> 1);
	112	}
	113
	114	/*
	115	* object layout - how a given object should be stored.
	116	*/
	117	struct ceph_object_layout {
51042122	118	struct ceph_pg ol_pgid; /* raw pg, with _full_ ps precision. */
0dee3c28 SW	119	__le32 ol_stripe_unit; /* for per-object parity, if any */
	120	} __attribute__ ((packed));
	121
	122	/*
	123	* compound epoch+version, used by storage layer to serialize mutations
	124	*/
	125	struct ceph_eversion {
	126	__le32 epoch;
	127	__le64 version;
	128	} __attribute__ ((packed));
	129
	130	/*
	131	* osd map bits
	132	*/
	133
	134	/* status bits */
	135	#define CEPH_OSD_EXISTS 1
	136	#define CEPH_OSD_UP 2
	137
	138	/* osd weights. fixed point value: 0x10000 == 1.0 ("in"), 0 == "out" */
	139	#define CEPH_OSD_IN 0x10000
	140	#define CEPH_OSD_OUT 0
	141
	142
	143	/*
	144	* osd map flag bits
	145	*/
	146	#define CEPH_OSDMAP_NEARFULL (1<<0) /* sync writes (near ENOSPC) */
	147	#define CEPH_OSDMAP_FULL (1<<1) /* no data writes (ENOSPC) */
	148	#define CEPH_OSDMAP_PAUSERD (1<<2) /* pause all reads */
	149	#define CEPH_OSDMAP_PAUSEWR (1<<3) /* pause all writes */
	150	#define CEPH_OSDMAP_PAUSEREC (1<<4) /* pause recovery */
	151
	152	/*
	153	* osd ops
	154	*/
	155	#define CEPH_OSD_OP_MODE 0xf000
	156	#define CEPH_OSD_OP_MODE_RD 0x1000
	157	#define CEPH_OSD_OP_MODE_WR 0x2000
	158	#define CEPH_OSD_OP_MODE_RMW 0x3000
	159	#define CEPH_OSD_OP_MODE_SUB 0x4000
0dee3c28 SW	160
	161	#define CEPH_OSD_OP_TYPE 0x0f00
	162	#define CEPH_OSD_OP_TYPE_LOCK 0x0100
	163	#define CEPH_OSD_OP_TYPE_DATA 0x0200
	164	#define CEPH_OSD_OP_TYPE_ATTR 0x0300
	165	#define CEPH_OSD_OP_TYPE_EXEC 0x0400
	166	#define CEPH_OSD_OP_TYPE_PG 0x0500
	167
	168	enum {
	169	/ data /
	170	/* read */
	171	CEPH_OSD_OP_READ = CEPH_OSD_OP_MODE_RD \| CEPH_OSD_OP_TYPE_DATA \| 1,
	172	CEPH_OSD_OP_STAT = CEPH_OSD_OP_MODE_RD \| CEPH_OSD_OP_TYPE_DATA \| 2,
	173
	174	/* fancy read */
	175	CEPH_OSD_OP_MASKTRUNC = CEPH_OSD_OP_MODE_RD \| CEPH_OSD_OP_TYPE_DATA \| 4,
	176
	177	/* write */
	178	CEPH_OSD_OP_WRITE = CEPH_OSD_OP_MODE_WR \| CEPH_OSD_OP_TYPE_DATA \| 1,
	179	CEPH_OSD_OP_WRITEFULL = CEPH_OSD_OP_MODE_WR \| CEPH_OSD_OP_TYPE_DATA \| 2,
	180	CEPH_OSD_OP_TRUNCATE = CEPH_OSD_OP_MODE_WR \| CEPH_OSD_OP_TYPE_DATA \| 3,
	181	CEPH_OSD_OP_ZERO = CEPH_OSD_OP_MODE_WR \| CEPH_OSD_OP_TYPE_DATA \| 4,
	182	CEPH_OSD_OP_DELETE = CEPH_OSD_OP_MODE_WR \| CEPH_OSD_OP_TYPE_DATA \| 5,
	183
	184	/* fancy write */
	185	CEPH_OSD_OP_APPEND = CEPH_OSD_OP_MODE_WR \| CEPH_OSD_OP_TYPE_DATA \| 6,
	186	CEPH_OSD_OP_STARTSYNC = CEPH_OSD_OP_MODE_WR \| CEPH_OSD_OP_TYPE_DATA \| 7,
	187	CEPH_OSD_OP_SETTRUNC = CEPH_OSD_OP_MODE_WR \| CEPH_OSD_OP_TYPE_DATA \| 8,
	188	CEPH_OSD_OP_TRIMTRUNC = CEPH_OSD_OP_MODE_WR \| CEPH_OSD_OP_TYPE_DATA \| 9,
	189
	190	CEPH_OSD_OP_TMAPUP = CEPH_OSD_OP_MODE_RMW \| CEPH_OSD_OP_TYPE_DATA \| 10,
	191	CEPH_OSD_OP_TMAPPUT = CEPH_OSD_OP_MODE_WR \| CEPH_OSD_OP_TYPE_DATA \| 11,
	192	CEPH_OSD_OP_TMAPGET = CEPH_OSD_OP_MODE_RD \| CEPH_OSD_OP_TYPE_DATA \| 12,
	193
	194	CEPH_OSD_OP_CREATE = CEPH_OSD_OP_MODE_WR \| CEPH_OSD_OP_TYPE_DATA \| 13,
	195
	196	/ attrs /
	197	/* read */
	198	CEPH_OSD_OP_GETXATTR = CEPH_OSD_OP_MODE_RD \| CEPH_OSD_OP_TYPE_ATTR \| 1,
	199	CEPH_OSD_OP_GETXATTRS = CEPH_OSD_OP_MODE_RD \| CEPH_OSD_OP_TYPE_ATTR \| 2,
	200
	201	/* write */
	202	CEPH_OSD_OP_SETXATTR = CEPH_OSD_OP_MODE_WR \| CEPH_OSD_OP_TYPE_ATTR \| 1,
	203	CEPH_OSD_OP_SETXATTRS = CEPH_OSD_OP_MODE_WR \| CEPH_OSD_OP_TYPE_ATTR \| 2,
	204	CEPH_OSD_OP_RESETXATTRS = CEPH_OSD_OP_MODE_WR\|CEPH_OSD_OP_TYPE_ATTR \| 3,
	205	CEPH_OSD_OP_RMXATTR = CEPH_OSD_OP_MODE_WR \| CEPH_OSD_OP_TYPE_ATTR \| 4,
	206
	207	/ subop /
	208	CEPH_OSD_OP_PULL = CEPH_OSD_OP_MODE_SUB \| 1,
	209	CEPH_OSD_OP_PUSH = CEPH_OSD_OP_MODE_SUB \| 2,
	210	CEPH_OSD_OP_BALANCEREADS = CEPH_OSD_OP_MODE_SUB \| 3,
	211	CEPH_OSD_OP_UNBALANCEREADS = CEPH_OSD_OP_MODE_SUB \| 4,
	212	CEPH_OSD_OP_SCRUB = CEPH_OSD_OP_MODE_SUB \| 5,
	213
	214	/ lock /
	215	CEPH_OSD_OP_WRLOCK = CEPH_OSD_OP_MODE_WR \| CEPH_OSD_OP_TYPE_LOCK \| 1,
	216	CEPH_OSD_OP_WRUNLOCK = CEPH_OSD_OP_MODE_WR \| CEPH_OSD_OP_TYPE_LOCK \| 2,
	217	CEPH_OSD_OP_RDLOCK = CEPH_OSD_OP_MODE_WR \| CEPH_OSD_OP_TYPE_LOCK \| 3,
	218	CEPH_OSD_OP_RDUNLOCK = CEPH_OSD_OP_MODE_WR \| CEPH_OSD_OP_TYPE_LOCK \| 4,
	219	CEPH_OSD_OP_UPLOCK = CEPH_OSD_OP_MODE_WR \| CEPH_OSD_OP_TYPE_LOCK \| 5,
	220	CEPH_OSD_OP_DNLOCK = CEPH_OSD_OP_MODE_WR \| CEPH_OSD_OP_TYPE_LOCK \| 6,
	221
	222	/ exec /
	223	CEPH_OSD_OP_CALL = CEPH_OSD_OP_MODE_RD \| CEPH_OSD_OP_TYPE_EXEC \| 1,
224
225	/ pg /
226	CEPH_OSD_OP_PGLS = CEPH_OSD_OP_MODE_RD \| CEPH_OSD_OP_TYPE_PG \| 1,
227	};
228
229	static inline int ceph_osd_op_type_lock(int op)
230	{
231	return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_LOCK;
232	}
233	static inline int ceph_osd_op_type_data(int op)
234	{
235	return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_DATA;
236	}
237	static inline int ceph_osd_op_type_attr(int op)
238	{
239	return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_ATTR;
240	}
241	static inline int ceph_osd_op_type_exec(int op)
242	{
243	return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_EXEC;
244	}
245	static inline int ceph_osd_op_type_pg(int op)
246	{
247	return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_PG;
248	}
249
250	static inline int ceph_osd_op_mode_subop(int op)
251	{
252	return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_SUB;
253	}
254	static inline int ceph_osd_op_mode_read(int op)
255	{
256	return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_RD;
257	}
258	static inline int ceph_osd_op_mode_modify(int op)
259	{
260	return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_WR;
261	}
262
263	#define CEPH_OSD_TMAP_HDR 'h'
264	#define CEPH_OSD_TMAP_SET 's'
265	#define CEPH_OSD_TMAP_RM 'r'
266
267	extern const char *ceph_osd_op_name(int op);
268
269
270	/*
271	* osd op flags
272	*
273	* An op may be READ, WRITE, or READ\|WRITE.
274	*/
275	enum {
276	CEPH_OSD_FLAG_ACK = 1, /* want (or is) "ack" ack */
277	CEPH_OSD_FLAG_ONNVRAM = 2, /* want (or is) "onnvram" ack */
278	CEPH_OSD_FLAG_ONDISK = 4, /* want (or is) "ondisk" ack */
279	CEPH_OSD_FLAG_RETRY = 8, /* resend attempt */
280	CEPH_OSD_FLAG_READ = 16, /* op may read */
281	CEPH_OSD_FLAG_WRITE = 32, /* op may write */
282	CEPH_OSD_FLAG_ORDERSNAP = 64, /* EOLDSNAP if snapc is out of order */
283	CEPH_OSD_FLAG_PEERSTAT = 128, /* msg includes osd_peer_stat */
284	CEPH_OSD_FLAG_BALANCE_READS = 256,
285	CEPH_OSD_FLAG_PARALLELEXEC = 512, /* execute op in parallel */
286	CEPH_OSD_FLAG_PGOP = 1024, /* pg op, no object */
4e7a5dcd	287	CEPH_OSD_FLAG_EXEC = 2048, /* op may exec */
0dee3c28 SW	288	};
	289
	290	enum {
	291	CEPH_OSD_OP_FLAG_EXCL = 1, /* EXCL object create */
	292	};
	293
	294	#define EOLDSNAPC ERESTART /* ORDERSNAP flag set; writer has old snapc*/
	295	#define EBLACKLISTED ESHUTDOWN /* blacklisted */
	296
	297	/*
	298	* an individual object operation. each may be accompanied by some data
	299	* payload
	300	*/
	301	struct ceph_osd_op {
	302	__le16 op; /* CEPH_OSD_OP_* */
	303	__le32 flags; /* CEPH_OSD_FLAG_* */
	304	union {
	305	struct {
	306	__le64 offset, length;
0c948992 YS	307	__le64 truncate_size;
0c948992 YS	308	__le32 truncate_seq;
0dee3c28 SW	309	} __attribute__ ((packed)) extent;
	310	struct {
	311	__le32 name_len;
	312	__le32 value_len;
	313	} __attribute__ ((packed)) xattr;
0dee3c28 SW	314	struct {
	315	__u8 class_len;
	316	__u8 method_len;
	317	__u8 argc;
	318	__le32 indata_len;
	319	} __attribute__ ((packed)) cls;
	320	struct {
	321	__le64 cookie, count;
	322	} __attribute__ ((packed)) pgls;
	323	};
	324	__le32 payload_len;
	325	} __attribute__ ((packed));
	326
	327	/*
	328	* osd request message header. each request may include multiple
	329	* ceph_osd_op object operations.
	330	*/
	331	struct ceph_osd_request_head {
0dee3c28 SW	332	__le32 client_inc; /* client incarnation */
	333	struct ceph_object_layout layout; /* pgid */
	334	__le32 osdmap_epoch; /* client's osdmap epoch */
	335
	336	__le32 flags;
	337
	338	struct ceph_timespec mtime; /* for mutations only */
	339	struct ceph_eversion reassert_version; /* if we are replaying op */
	340
	341	__le32 object_len; /* length of object name */
	342
	343	__le64 snapid; /* snapid to read */
	344	__le64 snap_seq; /* writer's snap context */
	345	__le32 num_snaps;
	346
	347	__le16 num_ops;
	348	struct ceph_osd_op ops[]; /* followed by ops[], obj, ticket, snaps */
	349	} __attribute__ ((packed));
	350
	351	struct ceph_osd_reply_head {
0dee3c28 SW	352	__le32 client_inc; /* client incarnation */
	353	__le32 flags;
	354	struct ceph_object_layout layout;
	355	__le32 osdmap_epoch;
	356	struct ceph_eversion reassert_version; /* for replaying uncommitted */
	357
	358	__le32 result; /* result code */
	359
	360	__le32 object_len; /* length of object name */
	361	__le32 num_ops;
	362	struct ceph_osd_op ops[0]; /* ops[], object */
	363	} __attribute__ ((packed));
	364
	365
	366	#endif