ceph: factor out libceph from Ceph file system

This factors out protocol and low-level storage parts of ceph into a
separate libceph module living in net/ceph and include/linux/ceph.  This
is mostly a matter of moving files around.  However, a few key pieces
of the interface change as well:

 - ceph_client becomes ceph_fs_client and ceph_client, where the latter
   captures the mon and osd clients, and the fs_client gets the mds client
   and file system specific pieces.
 - Mount option parsing and debugfs setup is correspondingly broken into
   two pieces.
 - The mon client gets a generic handler callback for otherwise unknown
   messages (mds map, in this case).
 - The basic supported/required feature bits can be expanded (and are by
   ceph_fs_client).

No functional change, aside from some subtle error handling cases that got
cleaned up in the refactoring process.

Signed-off-by: Sage Weil <sage@newdream.net>

22 files changed, 3216 insertions, 0 deletions

diff --git a/include/linux/ceph/auth.h b/include/linux/ceph/auth.h
new file mode 100644
index 00000000000..7fff521d7eb
--- /dev/null
+++ b/include/linux/ceph/auth.h
@@ -0,0 +1,92 @@
+#ifndef _FS_CEPH_AUTH_H
+#define _FS_CEPH_AUTH_H
+
+#include <linux/ceph/types.h>
+#include <linux/ceph/buffer.h>
+
+/*
+ * Abstract interface for communicating with the authenticate module.
+ * There is some handshake that takes place between us and the monitor
+ * to acquire the necessary keys.  These are used to generate an
+ * 'authorizer' that we use when connecting to a service (mds, osd).
+ */
+
+struct ceph_auth_client;
+struct ceph_authorizer;
+
+struct ceph_auth_client_ops {
+	const char *name;
+
+	/*
+	 * true if we are authenticated and can connect to
+	 * services.
+	 */
+	int (*is_authenticated)(struct ceph_auth_client *ac);
+
+	/*
+	 * true if we should (re)authenticate, e.g., when our tickets
+	 * are getting old and crusty.
+	 */
+	int (*should_authenticate)(struct ceph_auth_client *ac);
+
+	/*
+	 * build requests and process replies during monitor
+	 * handshake.  if handle_reply returns -EAGAIN, we build
+	 * another request.
+	 */
+	int (*build_request)(struct ceph_auth_client *ac, void *buf, void *end);
+	int (*handle_reply)(struct ceph_auth_client *ac, int result,
+			    void *buf, void *end);
+
+	/*
+	 * Create authorizer for connecting to a service, and verify
+	 * the response to authenticate the service.
+	 */
+	int (*create_authorizer)(struct ceph_auth_client *ac, int peer_type,
+				 struct ceph_authorizer **a,
+				 void **buf, size_t *len,
+				 void **reply_buf, size_t *reply_len);
+	int (*verify_authorizer_reply)(struct ceph_auth_client *ac,
+				       struct ceph_authorizer *a, size_t len);
+	void (*destroy_authorizer)(struct ceph_auth_client *ac,
+				   struct ceph_authorizer *a);
+	void (*invalidate_authorizer)(struct ceph_auth_client *ac,
+				      int peer_type);
+
+	/* reset when we (re)connect to a monitor */
+	void (*reset)(struct ceph_auth_client *ac);
+
+	void (*destroy)(struct ceph_auth_client *ac);
+};
+
+struct ceph_auth_client {
+	u32 protocol;           /* CEPH_AUTH_* */
+	void *private;          /* for use by protocol implementation */
+	const struct ceph_auth_client_ops *ops;  /* null iff protocol==0 */
+
+	bool negotiating;       /* true if negotiating protocol */
+	const char *name;       /* entity name */
+	u64 global_id;          /* our unique id in system */
+	const char *secret;     /* our secret key */
+	unsigned want_keys;     /* which services we want */
+};
+
+extern struct ceph_auth_client *ceph_auth_init(const char *name,
+					       const char *secret);
+extern void ceph_auth_destroy(struct ceph_auth_client *ac);
+
+extern void ceph_auth_reset(struct ceph_auth_client *ac);
+
+extern int ceph_auth_build_hello(struct ceph_auth_client *ac,
+				 void *buf, size_t len);
+extern int ceph_handle_auth_reply(struct ceph_auth_client *ac,
+				  void *buf, size_t len,
+				  void *reply_buf, size_t reply_len);
+extern int ceph_entity_name_encode(const char *name, void **p, void *end);
+
+extern int ceph_build_auth(struct ceph_auth_client *ac,
+		    void *msg_buf, size_t msg_len);
+
+extern int ceph_auth_is_authenticated(struct ceph_auth_client *ac);
+
+#endif
diff --git a/include/linux/ceph/buffer.h b/include/linux/ceph/buffer.h
new file mode 100644
index 00000000000..58d19014068
--- /dev/null
+++ b/include/linux/ceph/buffer.h
@@ -0,0 +1,39 @@
+#ifndef __FS_CEPH_BUFFER_H
+#define __FS_CEPH_BUFFER_H
+
+#include <linux/kref.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+#include <linux/types.h>
+#include <linux/uio.h>
+
+/*
+ * a simple reference counted buffer.
+ *
+ * use kmalloc for small sizes (<= one page), vmalloc for larger
+ * sizes.
+ */
+struct ceph_buffer {
+	struct kref kref;
+	struct kvec vec;
+	size_t alloc_len;
+	bool is_vmalloc;
+};
+
+extern struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp);
+extern void ceph_buffer_release(struct kref *kref);
+
+static inline struct ceph_buffer *ceph_buffer_get(struct ceph_buffer *b)
+{
+	kref_get(&b->kref);
+	return b;
+}
+
+static inline void ceph_buffer_put(struct ceph_buffer *b)
+{
+	kref_put(&b->kref, ceph_buffer_release);
+}
+
+extern int ceph_decode_buffer(struct ceph_buffer **b, void **p, void *end);
+
+#endif
diff --git a/include/linux/ceph/ceph_debug.h b/include/linux/ceph/ceph_debug.h
new file mode 100644
index 00000000000..aa2e19182d9
--- /dev/null
+++ b/include/linux/ceph/ceph_debug.h
@@ -0,0 +1,38 @@
+#ifndef _FS_CEPH_DEBUG_H
+#define _FS_CEPH_DEBUG_H
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#ifdef CONFIG_CEPH_LIB_PRETTYDEBUG
+
+/*
+ * wrap pr_debug to include a filename:lineno prefix on each line.
+ * this incurs some overhead (kernel size and execution time) due to
+ * the extra function call at each call site.
+ */
+
+# if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG)
+extern const char *ceph_file_part(const char *s, int len);
+#  define dout(fmt, ...)						\
+	pr_debug("%.*s %12.12s:%-4d : " fmt,				\
+		 8 - (int)sizeof(KBUILD_MODNAME), "    ",		\
+		 ceph_file_part(__FILE__, sizeof(__FILE__)),		\
+		 __LINE__, ##__VA_ARGS__)
+# else
+/* faux printk call just to see any compiler warnings. */
+#  define dout(fmt, ...)	do {				\
+		if (0)						\
+			printk(KERN_DEBUG fmt, ##__VA_ARGS__);	\
+	} while (0)
+# endif
+
+#else
+
+/*
+ * or, just wrap pr_debug
+ */
+# define dout(fmt, ...)	pr_debug(" " fmt, ##__VA_ARGS__)
+
+#endif
+
+#endif
diff --git a/include/linux/ceph/ceph_frag.h b/include/linux/ceph/ceph_frag.h
new file mode 100644
index 00000000000..5babb8e9535
--- /dev/null
+++ b/include/linux/ceph/ceph_frag.h
@@ -0,0 +1,109 @@
+#ifndef FS_CEPH_FRAG_H
+#define FS_CEPH_FRAG_H
+
+/*
+ * "Frags" are a way to describe a subset of a 32-bit number space,
+ * using a mask and a value to match against that mask.  Any given frag
+ * (subset of the number space) can be partitioned into 2^n sub-frags.
+ *
+ * Frags are encoded into a 32-bit word:
+ *   8 upper bits = "bits"
+ *  24 lower bits = "value"
+ * (We could go to 5+27 bits, but who cares.)
+ *
+ * We use the _most_ significant bits of the 24 bit value.  This makes
+ * values logically sort.
+ *
+ * Unfortunately, because the "bits" field is still in the high bits, we
+ * can't sort encoded frags numerically.  However, it does allow you
+ * to feed encoded frags as values into frag_contains_value.
+ */
+static inline __u32 ceph_frag_make(__u32 b, __u32 v)
+{
+	return (b << 24) |
+		(v & (0xffffffu << (24-b)) & 0xffffffu);
+}
+static inline __u32 ceph_frag_bits(__u32 f)
+{
+	return f >> 24;
+}
+static inline __u32 ceph_frag_value(__u32 f)
+{
+	return f & 0xffffffu;
+}
+static inline __u32 ceph_frag_mask(__u32 f)
+{
+	return (0xffffffu << (24-ceph_frag_bits(f))) & 0xffffffu;
+}
+static inline __u32 ceph_frag_mask_shift(__u32 f)
+{
+	return 24 - ceph_frag_bits(f);
+}
+
+static inline int ceph_frag_contains_value(__u32 f, __u32 v)
+{
+	return (v & ceph_frag_mask(f)) == ceph_frag_value(f);
+}
+static inline int ceph_frag_contains_frag(__u32 f, __u32 sub)
+{
+	/* is sub as specific as us, and contained by us? */
+	return ceph_frag_bits(sub) >= ceph_frag_bits(f) &&
+	       (ceph_frag_value(sub) & ceph_frag_mask(f)) == ceph_frag_value(f);
+}
+
+static inline __u32 ceph_frag_parent(__u32 f)
+{
+	return ceph_frag_make(ceph_frag_bits(f) - 1,
+			 ceph_frag_value(f) & (ceph_frag_mask(f) << 1));
+}
+static inline int ceph_frag_is_left_child(__u32 f)
+{
+	return ceph_frag_bits(f) > 0 &&
+		(ceph_frag_value(f) & (0x1000000 >> ceph_frag_bits(f))) == 0;
+}
+static inline int ceph_frag_is_right_child(__u32 f)
+{
+	return ceph_frag_bits(f) > 0 &&
+		(ceph_frag_value(f) & (0x1000000 >> ceph_frag_bits(f))) == 1;
+}
+static inline __u32 ceph_frag_sibling(__u32 f)
+{
+	return ceph_frag_make(ceph_frag_bits(f),
+		      ceph_frag_value(f) ^ (0x1000000 >> ceph_frag_bits(f)));
+}
+static inline __u32 ceph_frag_left_child(__u32 f)
+{
+	return ceph_frag_make(ceph_frag_bits(f)+1, ceph_frag_value(f));
+}
+static inline __u32 ceph_frag_right_child(__u32 f)
+{
+	return ceph_frag_make(ceph_frag_bits(f)+1,
+	      ceph_frag_value(f) | (0x1000000 >> (1+ceph_frag_bits(f))));
+}
+static inline __u32 ceph_frag_make_child(__u32 f, int by, int i)
+{
+	int newbits = ceph_frag_bits(f) + by;
+	return ceph_frag_make(newbits,
+			 ceph_frag_value(f) | (i << (24 - newbits)));
+}
+static inline int ceph_frag_is_leftmost(__u32 f)
+{
+	return ceph_frag_value(f) == 0;
+}
+static inline int ceph_frag_is_rightmost(__u32 f)
+{
+	return ceph_frag_value(f) == ceph_frag_mask(f);
+}
+static inline __u32 ceph_frag_next(__u32 f)
+{
+	return ceph_frag_make(ceph_frag_bits(f),
+			 ceph_frag_value(f) + (0x1000000 >> ceph_frag_bits(f)));
+}
+
+/*
+ * comparator to sort frags logically, as when traversing the
+ * number space in ascending order...
+ */
+int ceph_frag_compare(__u32 a, __u32 b);
+
+#endif
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
new file mode 100644
index 00000000000..d5619ac8671
--- /dev/null
+++ b/include/linux/ceph/ceph_fs.h
@@ -0,0 +1,728 @@
+/*
+ * 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 CEPH_FS_H
+#define CEPH_FS_H
+
+#include "msgr.h"
+#include "rados.h"
+
+/*
+ * 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     8 /* cluster internal */
+#define CEPH_MDS_PROTOCOL    12 /* cluster internal */
+#define CEPH_MON_PROTOCOL     5 /* cluster internal */
+#define CEPH_OSDC_PROTOCOL   24 /* server/client */
+#define CEPH_MDSC_PROTOCOL   32 /* server/client */
+#define CEPH_MONC_PROTOCOL   15 /* server/client */
+
+
+#define CEPH_INO_ROOT  1
+#define CEPH_INO_CEPH  2        /* hidden .ceph dir */
+
+/* arbitrary limit on max # of monitors (cluster of 3 is typical) */
+#define CEPH_MAX_MON   31
+
+
+/*
+ * feature bits
+ */
+#define CEPH_FEATURE_UID            (1<<0)
+#define CEPH_FEATURE_NOSRCADDR      (1<<1)
+#define CEPH_FEATURE_MONCLOCKCHECK  (1<<2)
+#define CEPH_FEATURE_FLOCK          (1<<3)
+
+
+/*
+ * 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
+
+#define CEPH_AES_IV "cephsageyudagreg"
+
+/* security/authentication protocols */
+#define CEPH_AUTH_UNKNOWN	0x0
+#define CEPH_AUTH_NONE	 	0x1
+#define CEPH_AUTH_CEPHX	 	0x2
+
+#define CEPH_AUTH_UID_DEFAULT ((__u64) -1)
+
+
+/*********************************************
+ * 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
+
+/* pool ops */
+#define CEPH_MSG_POOLOP_REPLY           48
+#define CEPH_MSG_POOLOP                 49
+
+
+/* osd */
+#define CEPH_MSG_OSD_MAP          41
+#define CEPH_MSG_OSD_OP           42
+#define CEPH_MSG_OSD_OPREPLY      43
+
+/* pool operations */
+enum {
+  POOL_OP_CREATE			= 0x01,
+  POOL_OP_DELETE			= 0x02,
+  POOL_OP_AUID_CHANGE			= 0x03,
+  POOL_OP_CREATE_SNAP			= 0x11,
+  POOL_OP_DELETE_SNAP			= 0x12,
+  POOL_OP_CREATE_UNMANAGED_SNAP		= 0x21,
+  POOL_OP_DELETE_UNMANAGED_SNAP		= 0x22,
+};
+
+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;
+} __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 version;
+	struct ceph_statfs st;
+} __attribute__ ((packed));
+
+const char *ceph_pool_op_name(int op);
+
+struct ceph_mon_poolop {
+	struct ceph_mon_request_header monhdr;
+	struct ceph_fsid fsid;
+	__le32 pool;
+	__le32 op;
+	__le64 auid;
+	__le64 snapid;
+	__le32 name_len;
+} __attribute__ ((packed));
+
+struct ceph_mon_poolop_reply {
+	struct ceph_mon_request_header monhdr;
+	struct ceph_fsid fsid;
+	__le32 reply_code;
+	__le32 epoch;
+	char has_data;
+	char data[0];
+} __attribute__ ((packed));
+
+struct ceph_mon_unmanaged_snap {
+	__le64 snapid;
+} __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_DVERSION    1
+#define CEPH_LOCK_DN          2
+#define CEPH_LOCK_ISNAP       16
+#define CEPH_LOCK_IVERSION    32    /* mds internal */
+#define CEPH_LOCK_IFILE       64
+#define CEPH_LOCK_IAUTH       128
+#define CEPH_LOCK_ILINK       256
+#define CEPH_LOCK_IDFT        512   /* dir frag tree */
+#define CEPH_LOCK_INEST       1024  /* mds internal */
+#define CEPH_LOCK_IXATTR      2048
+#define CEPH_LOCK_IFLOCK      4096  /* advisory file locks */
+#define CEPH_LOCK_INO         8192  /* 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_SETFILELOCK= 0x01109,
+	CEPH_MDS_OP_GETFILELOCK= 0x00110,
+
+	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     = 0x01301,
+	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 */
+		__le32 max_bytes;
+	} __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;
+	struct {
+		__u8 rule; /* currently fcntl or flock */
+		__u8 type; /* shared, exclusive, remove*/
+		__le64 pid; /* process id requesting the lock */
+		__le64 pid_namespace;
+		__le64 start; /* initial location to lock */
+		__le64 length; /* num bytes to lock from start */
+		__u8 wait; /* will caller wait for lock to become available? */
+	} __attribute__ ((packed)) filelock_change;
+} __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 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;
+	__le64 ino;                    /* use this ino for openc, mkdir, mknod,
+					  etc. (if replaying) */
+	union ceph_mds_request_args args;
+} __attribute__ ((packed));
+
+/* cap/lease release record */
+struct ceph_mds_request_release {
+	__le64 ino, cap_id;            /* ino and unique cap id */
+	__le32 caps, wanted;           /* new issued, wanted */
+	__le32 seq, issue_seq, mseq;
+	__le32 dname_seq;              /* if releasing a dentry lease, a */
+	__le32 dname_len;              /* string follows. */
+} __attribute__ ((packed));
+
+/* client reply */
+struct ceph_mds_reply_head {
+	__le32 op;
+	__le32 result;
+	__le32 mdsmap_epoch;
+	__u8 safe;                     /* true if committed to disk */
+	__u8 is_dentry, is_target;     /* true if dentry, target inode records
+					  are included with reply */
+} __attribute__ ((packed));
+
+/* one for each node split */
+struct ceph_frag_tree_split {
+	__le32 frag;                   /* this frag splits... */
+	__le32 by;                     /* ...by this many bits */
+} __attribute__ ((packed));
+
+struct ceph_frag_tree_head {
+	__le32 nsplits;                /* num ceph_frag_tree_split records */
+	struct ceph_frag_tree_split splits[];
+} __attribute__ ((packed));
+
+/* capability issue, for bundling with mds reply */
+struct ceph_mds_reply_cap {
+	__le32 caps, wanted;           /* caps issued, wanted */
+	__le64 cap_id;
+	__le32 seq, mseq;
+	__le64 realm;                  /* snap realm */
+	__u8 flags;                    /* CEPH_CAP_FLAG_* */
+} __attribute__ ((packed));
+
+#define CEPH_CAP_FLAG_AUTH  1          /* cap is issued by auth mds */
+
+/* inode record, for bundling with mds reply */
+struct ceph_mds_reply_inode {
+	__le64 ino;
+	__le64 snapid;
+	__le32 rdev;
+	__le64 version;                /* inode version */
+	__le64 xattr_version;          /* version for xattr blob */
+	struct ceph_mds_reply_cap cap; /* caps issued for this inode */
+	struct ceph_file_layout layout;
+	struct ceph_timespec ctime, mtime, atime;
+	__le32 time_warp_seq;
+	__le64 size, max_size, truncate_size;
+	__le32 truncate_seq;
+	__le32 mode, uid, gid;
+	__le32 nlink;
+	__le64 files, subdirs, rbytes, rfiles, rsubdirs;  /* dir stats */
+	struct ceph_timespec rctime;
+	struct ceph_frag_tree_head fragtree;  /* (must be at end of struct) */
+} __attribute__ ((packed));
+/* followed by frag array, then symlink string, then xattr blob */
+
+/* reply_lease follows dname, and reply_inode */
+struct ceph_mds_reply_lease {
+	__le16 mask;            /* lease type(s) */
+	__le32 duration_ms;     /* lease duration */
+	__le32 seq;
+} __attribute__ ((packed));
+
+struct ceph_mds_reply_dirfrag {
+	__le32 frag;            /* fragment */
+	__le32 auth;            /* auth mds, if this is a delegation point */
+	__le32 ndist;           /* number of mds' this is replicated on */
+	__le32 dist[];
+} __attribute__ ((packed));
+
+#define CEPH_LOCK_FCNTL    1
+#define CEPH_LOCK_FLOCK    2
+
+#define CEPH_LOCK_SHARED   1
+#define CEPH_LOCK_EXCL     2
+#define CEPH_LOCK_UNLOCK   4
+
+struct ceph_filelock {
+	__le64 start;/* file offset to start lock at */
+	__le64 length; /* num bytes to lock; 0 for all following start */
+	__le64 client; /* which client holds the lock */
+	__le64 pid; /* process id holding the lock on the client */
+	__le64 pid_namespace;
+	__u8 type; /* shared lock, exclusive lock, or unlock */
+} __attribute__ ((packed));
+
+
+/* file access modes */
+#define CEPH_FILE_MODE_PIN        0
+#define CEPH_FILE_MODE_RD         1
+#define CEPH_FILE_MODE_WR         2
+#define CEPH_FILE_MODE_RDWR       3  /* RD | WR */
+#define CEPH_FILE_MODE_LAZY       4  /* lazy io */
+#define CEPH_FILE_MODE_NUM        8  /* bc these are bit fields.. mostly */
+
+int ceph_flags_to_mode(int flags);
+
+
+/* capability bits */
+#define CEPH_CAP_PIN         1  /* no specific capabilities beyond the pin */
+
+/* generic cap bits */
+#define CEPH_CAP_GSHARED     1  /* client can reads */
+#define CEPH_CAP_GEXCL       2  /* client can read and update */
+#define CEPH_CAP_GCACHE      4  /* (file) client can cache reads */
+#define CEPH_CAP_GRD         8  /* (file) client can read */
+#define CEPH_CAP_GWR        16  /* (file) client can write */
+#define CEPH_CAP_GBUFFER    32  /* (file) client can buffer writes */
+#define CEPH_CAP_GWREXTEND  64  /* (file) client can extend EOF */
+#define CEPH_CAP_GLAZYIO   128  /* (file) client can perform lazy io */
+
+/* per-lock shift */
+#define CEPH_CAP_SAUTH      2
+#define CEPH_CAP_SLINK      4
+#define CEPH_CAP_SXATTR     6
+#define CEPH_CAP_SFILE      8
+#define CEPH_CAP_SFLOCK    20 
+
+#define CEPH_CAP_BITS       22
+
+/* composed values */
+#define CEPH_CAP_AUTH_SHARED  (CEPH_CAP_GSHARED  << CEPH_CAP_SAUTH)
+#define CEPH_CAP_AUTH_EXCL     (CEPH_CAP_GEXCL     << CEPH_CAP_SAUTH)
+#define CEPH_CAP_LINK_SHARED  (CEPH_CAP_GSHARED  << CEPH_CAP_SLINK)
+#define CEPH_CAP_LINK_EXCL     (CEPH_CAP_GEXCL     << CEPH_CAP_SLINK)
+#define CEPH_CAP_XATTR_SHARED (CEPH_CAP_GSHARED  << CEPH_CAP_SXATTR)
+#define CEPH_CAP_XATTR_EXCL    (CEPH_CAP_GEXCL     << CEPH_CAP_SXATTR)
+#define CEPH_CAP_FILE(x)    (x << CEPH_CAP_SFILE)
+#define CEPH_CAP_FILE_SHARED   (CEPH_CAP_GSHARED   << CEPH_CAP_SFILE)
+#define CEPH_CAP_FILE_EXCL     (CEPH_CAP_GEXCL     << CEPH_CAP_SFILE)
+#define CEPH_CAP_FILE_CACHE    (CEPH_CAP_GCACHE    << CEPH_CAP_SFILE)
+#define CEPH_CAP_FILE_RD       (CEPH_CAP_GRD       << CEPH_CAP_SFILE)
+#define CEPH_CAP_FILE_WR       (CEPH_CAP_GWR       << CEPH_CAP_SFILE)
+#define CEPH_CAP_FILE_BUFFER   (CEPH_CAP_GBUFFER   << CEPH_CAP_SFILE)
+#define CEPH_CAP_FILE_WREXTEND (CEPH_CAP_GWREXTEND << CEPH_CAP_SFILE)
+#define CEPH_CAP_FILE_LAZYIO   (CEPH_CAP_GLAZYIO   << CEPH_CAP_SFILE)
+#define CEPH_CAP_FLOCK_SHARED  (CEPH_CAP_GSHARED   << CEPH_CAP_SFLOCK)
+#define CEPH_CAP_FLOCK_EXCL    (CEPH_CAP_GEXCL     << CEPH_CAP_SFLOCK)
+
+
+/* cap masks (for getattr) */
+#define CEPH_STAT_CAP_INODE    CEPH_CAP_PIN
+#define CEPH_STAT_CAP_TYPE     CEPH_CAP_PIN  /* mode >> 12 */
+#define CEPH_STAT_CAP_SYMLINK  CEPH_CAP_PIN
+#define CEPH_STAT_CAP_UID      CEPH_CAP_AUTH_SHARED
+#define CEPH_STAT_CAP_GID      CEPH_CAP_AUTH_SHARED
+#define CEPH_STAT_CAP_MODE     CEPH_CAP_AUTH_SHARED
+#define CEPH_STAT_CAP_NLINK    CEPH_CAP_LINK_SHARED
+#define CEPH_STAT_CAP_LAYOUT   CEPH_CAP_FILE_SHARED
+#define CEPH_STAT_CAP_MTIME    CEPH_CAP_FILE_SHARED
+#define CEPH_STAT_CAP_SIZE     CEPH_CAP_FILE_SHARED
+#define CEPH_STAT_CAP_ATIME    CEPH_CAP_FILE_SHARED  /* fixme */
+#define CEPH_STAT_CAP_XATTR    CEPH_CAP_XATTR_SHARED
+#define CEPH_STAT_CAP_INODE_ALL (CEPH_CAP_PIN |			\
+				 CEPH_CAP_AUTH_SHARED |	\
+				 CEPH_CAP_LINK_SHARED |	\
+				 CEPH_CAP_FILE_SHARED |	\
+				 CEPH_CAP_XATTR_SHARED)
+
+#define CEPH_CAP_ANY_SHARED (CEPH_CAP_AUTH_SHARED |			\
+			      CEPH_CAP_LINK_SHARED |			\
+			      CEPH_CAP_XATTR_SHARED |			\
+			      CEPH_CAP_FILE_SHARED)
+#define CEPH_CAP_ANY_RD   (CEPH_CAP_ANY_SHARED | CEPH_CAP_FILE_RD |	\
+			   CEPH_CAP_FILE_CACHE)
+
+#define CEPH_CAP_ANY_EXCL (CEPH_CAP_AUTH_EXCL |		\
+			   CEPH_CAP_LINK_EXCL |		\
+			   CEPH_CAP_XATTR_EXCL |	\
+			   CEPH_CAP_FILE_EXCL)
+#define CEPH_CAP_ANY_FILE_WR (CEPH_CAP_FILE_WR | CEPH_CAP_FILE_BUFFER |	\
+			      CEPH_CAP_FILE_EXCL)
+#define CEPH_CAP_ANY_WR   (CEPH_CAP_ANY_EXCL | CEPH_CAP_ANY_FILE_WR)
+#define CEPH_CAP_ANY      (CEPH_CAP_ANY_RD | CEPH_CAP_ANY_EXCL | \
+			   CEPH_CAP_ANY_FILE_WR | CEPH_CAP_FILE_LAZYIO | \
+			   CEPH_CAP_PIN)
+
+#define CEPH_CAP_LOCKS (CEPH_LOCK_IFILE | CEPH_LOCK_IAUTH | CEPH_LOCK_ILINK | \
+			CEPH_LOCK_IXATTR)
+
+int ceph_caps_for_mode(int mode);
+
+enum {
+	CEPH_CAP_OP_GRANT,         /* mds->client grant */
+	CEPH_CAP_OP_REVOKE,        /* mds->client revoke */
+	CEPH_CAP_OP_TRUNC,         /* mds->client trunc notify */
+	CEPH_CAP_OP_EXPORT,        /* mds has exported the cap */
+	CEPH_CAP_OP_IMPORT,        /* mds has imported the cap */
+	CEPH_CAP_OP_UPDATE,        /* client->mds update */
+	CEPH_CAP_OP_DROP,          /* client->mds drop cap bits */
+	CEPH_CAP_OP_FLUSH,         /* client->mds cap writeback */
+	CEPH_CAP_OP_FLUSH_ACK,     /* mds->client flushed */
+	CEPH_CAP_OP_FLUSHSNAP,     /* client->mds flush snapped metadata */
+	CEPH_CAP_OP_FLUSHSNAP_ACK, /* mds->client flushed s