path: root/fs/ceph/ceph_fs.h

/*
 * ceph_fs.h - Ceph constants and data types to share between kernel and
 * user space.
 *
 * Most types in this file are defined as little-endian, and are
 * primarily intended to describe data structures that pass over the
 * wire or that are stored on disk.
 *
 * LGPL2
 */

#ifndef _FS_CEPH_CEPH_FS_H
#define _FS_CEPH_CEPH_FS_H

#include "msgr.h"
#include "rados.h"

/*
 * Ceph release version
 */
#define CEPH_VERSION_MAJOR 0
#define CEPH_VERSION_MINOR 17
#define CEPH_VERSION_PATCH 0

#define _CEPH_STRINGIFY(x) #x
#define CEPH_STRINGIFY(x) _CEPH_STRINGIFY(x)
#define CEPH_MAKE_VERSION(x, y, z) CEPH_STRINGIFY(x) "." CEPH_STRINGIFY(y) \
	"." CEPH_STRINGIFY(z)
#define CEPH_VERSION CEPH_MAKE_VERSION(CEPH_VERSION_MAJOR, \
				       CEPH_VERSION_MINOR, CEPH_VERSION_PATCH)

/*
 * subprotocol versions.  when specific messages types or high-level
 * protocols change, bump the affected components.  we keep rev
 * internal cluster protocols separately from the public,
 * client-facing protocol.
 */
#define CEPH_OSD_PROTOCOL     7 /* cluster internal */
#define CEPH_MDS_PROTOCOL     9 /* cluster internal */
#define CEPH_MON_PROTOCOL     5 /* cluster internal */
#define CEPH_OSDC_PROTOCOL   22 /* server/client */
#define CEPH_MDSC_PROTOCOL   30 /* server/client */
#define CEPH_MONC_PROTOCOL   15 /* server/client */


#define CEPH_INO_ROOT  1

/* arbitrary limit on max # of monitors (cluster of 3 is typical) */
#define CEPH_MAX_MON   31



/*
 * ceph_file_layout - describe data layout for a file/inode
 */
struct ceph_file_layout {
	/* file -> object mapping */
	__le32 fl_stripe_unit;     /* stripe unit, in bytes.  must be multiple
				      of page size. */
	__le32 fl_stripe_count;    /* over this many objects */
	__le32 fl_object_size;     /* until objects are this big, then move to
				      new objects */
	__le32 fl_cas_hash;        /* 0 = none; 1 = sha256 */

	/* pg -> disk layout */
	__le32 fl_object_stripe_unit;  /* for per-object parity, if any */

	/* object -> pg layout */
	__le32 fl_pg_preferred; /* preferred primary for pg (-1 for none) */
	__le32 fl_pg_pool;      /* namespace, crush ruleset, rep level */
} __attribute__ ((packed));

#define CEPH_MIN_STRIPE_UNIT 65536

int ceph_file_layout_is_valid(const struct ceph_file_layout *layout);


/* crypto algorithms */
#define CEPH_CRYPTO_NONE 0x0
#define CEPH_CRYPTO_AES  0x1

/* security/authentication protocols */
#define CEPH_AUTH_UNKNOWN	0x0
#define CEPH_AUTH_NONE	 	0x1
#define CEPH_AUTH_CEPHX	 	0x2


/*********************************************
 * message layer
 */

/*
 * message types
 */

/* misc */
#define CEPH_MSG_SHUTDOWN               1
#define CEPH_MSG_PING                   2

/* client <-> monitor */
#define CEPH_MSG_MON_MAP                4
#define CEPH_MSG_MON_GET_MAP            5
#define CEPH_MSG_STATFS                 13
#define CEPH_MSG_STATFS_REPLY           14
#define CEPH_MSG_MON_SUBSCRIBE          15
#define CEPH_MSG_MON_SUBSCRIBE_ACK      16
#define CEPH_MSG_AUTH			17
#define CEPH_MSG_AUTH_REPLY		18

/* client <-> mds */
#define CEPH_MSG_MDS_MAP                21

#define CEPH_MSG_CLIENT_SESSION         22
#define CEPH_MSG_CLIENT_RECONNECT       23

#define CEPH_MSG_CLIENT_REQUEST         24
#define CEPH_MSG_CLIENT_REQUEST_FORWARD 25
#define CEPH_MSG_CLIENT_REPLY           26
#define CEPH_MSG_CLIENT_CAPS            0x310
#define CEPH_MSG_CLIENT_LEASE           0x311
#define CEPH_MSG_CLIENT_SNAP            0x312
#define CEPH_MSG_CLIENT_CAPRELEASE      0x313

/* osd */
#define CEPH_MSG_OSD_MAP          41
#define CEPH_MSG_OSD_OP           42
#define CEPH_MSG_OSD_OPREPLY      43

struct ceph_mon_request_header {
	__le64 have_version;
	__le16 session_mon;
	__le64 session_mon_tid;
} __attribute__ ((packed));

struct ceph_mon_statfs {
	struct ceph_mon_request_header monhdr;
	struct ceph_fsid fsid;
	__le64 tid;
} __attribute__ ((packed));

struct ceph_statfs {
	__le64 kb, kb_used, kb_avail;
	__le64 num_objects;
} __attribute__ ((packed));

struct ceph_mon_statfs_reply {
	struct ceph_fsid fsid;
	__le64 tid;
	__le64 version;
	struct ceph_statfs st;
} __attribute__ ((packed));

struct ceph_osd_getmap {
	struct ceph_mon_request_header monhdr;
	struct ceph_fsid fsid;
	__le32 start;
} __attribute__ ((packed));

struct ceph_mds_getmap {
	struct ceph_mon_request_header monhdr;
	struct ceph_fsid fsid;
} __attribute__ ((packed));

struct ceph_client_mount {
	struct ceph_mon_request_header monhdr;
} __attribute__ ((packed));

struct ceph_mon_subscribe_item {
	__le64 have_version;	__le64 have;
	__u8 onetime;
} __attribute__ ((packed));

struct ceph_mon_subscribe_ack {
	__le32 duration;         /* seconds */
	struct ceph_fsid fsid;
} __attribute__ ((packed));

/*
 * mds states
 *   > 0 -> in
 *  <= 0 -> out
 */
#define CEPH_MDS_STATE_DNE          0  /* down, does not exist. */
#define CEPH_MDS_STATE_STOPPED     -1  /* down, once existed, but no subtrees.
					  empty log. */
#define CEPH_MDS_STATE_BOOT        -4  /* up, boot announcement. */
#define CEPH_MDS_STATE_STANDBY     -5  /* up, idle.  waiting for assignment. */
#define CEPH_MDS_STATE_CREATING    -6  /* up, creating MDS instance. */
#define CEPH_MDS_STATE_STARTING    -7  /* up, starting previously stopped mds */
#define CEPH_MDS_STATE_STANDBY_REPLAY -8 /* up, tailing active node's journal */

#define CEPH_MDS_STATE_REPLAY       8  /* up, replaying journal. */
#define CEPH_MDS_STATE_RESOLVE      9  /* up, disambiguating distributed
					  operations (import, rename, etc.) */
#define CEPH_MDS_STATE_RECONNECT    10 /* up, reconnect to clients */
#define CEPH_MDS_STATE_REJOIN       11 /* up, rejoining distributed cache */
#define CEPH_MDS_STATE_CLIENTREPLAY 12 /* up, replaying client operations */
#define CEPH_MDS_STATE_ACTIVE       13 /* up, active */
#define CEPH_MDS_STATE_STOPPING     14 /* up, but exporting metadata */

extern const char *ceph_mds_state_name(int s);


/*
 * metadata lock types.
 *  - these are bitmasks.. we can compose them
 *  - they also define the lock ordering by the MDS
 *  - a few of these are internal to the mds
 */
#define CEPH_LOCK_DN          1
#define CEPH_LOCK_ISNAP       2
#define CEPH_LOCK_IVERSION    4     /* mds internal */
#define CEPH_LOCK_IFILE       8     /* mds internal */
#define CEPH_LOCK_IAUTH       32
#define CEPH_LOCK_ILINK       64
#define CEPH_LOCK_IDFT        128   /* dir frag tree */
#define CEPH_LOCK_INEST       256   /* mds internal */
#define CEPH_LOCK_IXATTR      512
#define CEPH_LOCK_INO         2048  /* immutable inode bits; not a lock */

/* client_session ops */
enum {
	CEPH_SESSION_REQUEST_OPEN,
	CEPH_SESSION_OPEN,
	CEPH_SESSION_REQUEST_CLOSE,
	CEPH_SESSION_CLOSE,
	CEPH_SESSION_REQUEST_RENEWCAPS,
	CEPH_SESSION_RENEWCAPS,
	CEPH_SESSION_STALE,
	CEPH_SESSION_RECALL_STATE,
};

extern const char *ceph_session_op_name(int op);

struct ceph_mds_session_head {
	__le32 op;
	__le64 seq;
	struct ceph_timespec stamp;
	__le32 max_caps, max_leases;
} __attribute__ ((packed));

/* client_request */
/*
 * metadata ops.
 *  & 0x001000 -> write op
 *  & 0x010000 -> follow symlink (e.g. stat(), not lstat()).
 &  & 0x100000 -> use weird ino/path trace
 */
#define CEPH_MDS_OP_WRITE        0x001000
enum {
	CEPH_MDS_OP_LOOKUP     = 0x00100,
	CEPH_MDS_OP_GETATTR    = 0x00101,
	CEPH_MDS_OP_LOOKUPHASH = 0x00102,
	CEPH_MDS_OP_LOOKUPPARENT = 0x00103,

	CEPH_MDS_OP_SETXATTR   = 0x01105,
	CEPH_MDS_OP_RMXATTR    = 0x01106,
	CEPH_MDS_OP_SETLAYOUT  = 0x01107,
	CEPH_MDS_OP_SETATTR    = 0x01108,

	CEPH_MDS_OP_MKNOD      = 0x01201,
	CEPH_MDS_OP_LINK       = 0x01202,
	CEPH_MDS_OP_UNLINK     = 0x01203,
	CEPH_MDS_OP_RENAME     = 0x01204,
	CEPH_MDS_OP_MKDIR      = 0x01220,
	CEPH_MDS_OP_RMDIR      = 0x01221,
	CEPH_MDS_OP_SYMLINK    = 0x01222,

	CEPH_MDS_OP_CREATE     = 0x00301,
	CEPH_MDS_OP_OPEN       = 0x00302,
	CEPH_MDS_OP_READDIR    = 0x00305,

	CEPH_MDS_OP_LOOKUPSNAP = 0x00400,
	CEPH_MDS_OP_MKSNAP     = 0x01400,
	CEPH_MDS_OP_RMSNAP     = 0x01401,
	CEPH_MDS_OP_LSSNAP     = 0x00402,
};

extern const char *ceph_mds_op_name(int op);


#define CEPH_SETATTR_MODE   1
#define CEPH_SETATTR_UID    2
#define CEPH_SETATTR_GID    4
#define CEPH_SETATTR_MTIME  8
#define CEPH_SETATTR_ATIME 16
#define CEPH_SETATTR_SIZE  32
#define CEPH_SETATTR_CTIME 64

union ceph_mds_request_args {
	struct {
		__le32 mask;                 /* CEPH_CAP_* */
	} __attribute__ ((packed)) getattr;
	struct {
		__le32 mode;
		__le32 uid;
		__le32 gid;
		struct ceph_timespec mtime;
		struct ceph_timespec atime;
		__le64 size, old_size;       /* old_size needed by truncate */
		__le32 mask;                 /* CEPH_SETATTR_* */
	} __attribute__ ((packed)) setattr;
	struct {
		__le32 frag;                 /* which dir fragment */
		__le32 max_entries;          /* how many dentries to grab */
	} __attribute__ ((packed)) readdir;
	struct {
		__le32 mode;
		__le32 rdev;
	} __attribute__ ((packed)) mknod;
	struct {
		__le32 mode;
	} __attribute__ ((packed)) mkdir;
	struct {
		__le32 flags;
		__le32 mode;
		__le32 stripe_unit;          /* layout for newly created file */
		__le32 stripe_count;         /* ... */
		__le32 object_size;
		__le32 file_replication;
		__le32 preferred;
	} __attribute__ ((packed)) open;
	struct {
		__le32 flags;
	} __attribute__ ((packed)) setxattr;
	struct {
		struct ceph_file_layout layout;
	} __attribute__ ((packed)) setlayout;
} __attribute__ ((packed));

#define CEPH_MDS_FLAG_REPLAY        1  /* this is a replayed op */
#define CEPH_MDS_FLAG_WANT_DENTRY   2  /* want dentry in reply */

struct ceph_mds_request_head {
	__le64 tid, oldest_client_tid;
	__le32 mdsmap_epoch;           /* on client */
	__le32 flags;                  /* CEPH_MDS_FLAG_* */
	__u8 num_retry, num_fwd;       /* count retry, fwd attempts */
	__le16 num_releases;           /* # include cap/lease release records */
	__le32 op;                     /* mds op code */
	__le32 caller_uid, caller_gid;