summaryrefslogtreecommitdiffstats
path: root/include
diff options
context:
space:
mode:
authorYehuda Sadeh <yehuda@hq.newdream.net>2010-04-06 15:14:15 -0700
committerSage Weil <sage@newdream.net>2010-10-20 15:37:28 -0700
commit3d14c5d2b6e15c21d8e5467dc62d33127c23a644 (patch)
tree7d123c47847df9d1e865b6b78dc7da3fe739b704 /include
parentae1533b62b3369e6ae32338f4a77d64d0e88f676 (diff)
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>
Diffstat (limited to 'include')
-rw-r--r--include/linux/ceph/auth.h92
-rw-r--r--include/linux/ceph/buffer.h39
-rw-r--r--include/linux/ceph/ceph_debug.h38
-rw-r--r--include/linux/ceph/ceph_frag.h109
-rw-r--r--include/linux/ceph/ceph_fs.h728
-rw-r--r--include/linux/ceph/ceph_hash.h13
-rw-r--r--include/linux/ceph/debugfs.h33
-rw-r--r--include/linux/ceph/decode.h201
-rw-r--r--include/linux/ceph/libceph.h249
-rw-r--r--include/linux/ceph/mdsmap.h62
-rw-r--r--include/linux/ceph/messenger.h261
-rw-r--r--include/linux/ceph/mon_client.h122
-rw-r--r--include/linux/ceph/msgpool.h25
-rw-r--r--include/linux/ceph/msgr.h175
-rw-r--r--include/linux/ceph/osd_client.h234
-rw-r--r--include/linux/ceph/osdmap.h130
-rw-r--r--include/linux/ceph/pagelist.h54
-rw-r--r--include/linux/ceph/rados.h405
-rw-r--r--include/linux/ceph/types.h29
-rw-r--r--include/linux/crush/crush.h180
-rw-r--r--include/linux/crush/hash.h17
-rw-r--r--include/linux/crush/mapper.h20
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 snapped metadata */
+ CEPH_CAP_OP_RELEASE, /* client->mds release (clean) cap */
+ CEPH_CAP_OP_RENEW, /* client->mds renewal request */
+};
+
+extern const char *ceph_cap_op_name(int op);
+
+/*
+ * caps message, used for capability callbacks, acks, requests, etc.
+ */
+struct ceph_mds_caps {
+ __le32 op; /* CEPH_CAP_OP_* */
+ __le64 ino, realm;
+ __le64 cap_id;
+ __le32 seq, issue_seq;
+ __le32 caps, wanted, dirty; /* latest issued/wanted/dirty */
+ __le32 migrate_seq;
+ __le64 snap_follows;
+ __le32 snap_trace_len;
+
+ /* authlock */
+ __le32 uid, gid, mode;
+
+ /* linklock */
+ __le32 nlink;
+
+ /* xattrlock */
+ __le32 xattr_len;
+ __le64 xattr_version;
+
+ /* filelock */
+ __le64 size, max_size, truncate_size;
+ __le32 truncate_seq;
+ struct ceph_timespec mtime, atime, ctime;
+ struct ceph_file_layout layout;
+ __le32 time_warp_seq;
+} __attribute__ ((packed));
+
+/* cap release msg head */
+struct ceph_mds_cap_release {
+ __le32 num; /* number of cap_items that follow */
+} __attribute__ ((packed));
+
+struct ceph_mds_cap_item {
+ __le64 ino;
+ __le64 cap_id;
+ __le32 migrate_seq, seq;
+} __attribute__ ((packed));
+
+#define CEPH_MDS_LEASE_REVOKE 1 /* mds -> client */
+#define CEPH_MDS_LEASE_RELEASE 2 /* client -> mds */
+#define CEPH_MDS_LEASE_RENEW 3 /* client <-> mds */
+#define CEPH_MDS_LEASE_REVOKE_ACK 4 /* client -> mds */
+
+extern const char *ceph_lease_op_name(int o);
+
+/* lease msg header */
+struct ceph_mds_lease {
+ __u8 action; /* CEPH_MDS_LEASE_* */
+ __le16 mask; /* which lease */
+ __le64 ino;
+ __le64 first, last; /* snap range */
+ __le32 seq;
+ __le32 duration_ms; /* duration of renewal */
+} __attribute__ ((packed));
+/* followed by a __le32+string for dname */
+
+/* client reconnect */
+struct ceph_mds_cap_reconnect {
+ __le64 cap_id;
+ __le32 wanted;
+ __le32 issued;
+ __le64 snaprealm;
+ __le64 pathbase; /* base ino for our path to this ino */
+ __le32 flock_len; /* size of flock state blob, if any */
+} __attribute__ ((packed));
+/* followed by flock blob */
+
+struct ceph_mds_cap_reconnect_v1 {
+ __le64 cap_id;
+ __le32 wanted;
+ __le32 issued;
+ __le64 size;
+ struct ceph_timespec mtime, atime;
+ __le64 snaprealm;
+ __le64 pathbase; /* base ino for our path to this ino */
+} __attribute__ ((packed));
+
+struct ceph_mds_snaprealm_reconnect {
+ __le64 ino; /* snap realm base */
+ __le64 seq; /* snap seq for this snap realm */
+ __le64 parent; /* parent realm */
+} __attribute__ ((packed));
+
+/*
+ * snaps
+ */
+enum {
+ CEPH_SNAP_OP_UPDATE, /* CREATE or DESTROY */
+ CEPH_SNAP_OP_CREATE,
+ CEPH_SNAP_OP_DESTROY,
+ CEPH_SNAP_OP_SPLIT,
+};
+
+extern const char *ceph_snap_op_name(int o);
+
+/* snap msg header */
+struct ceph_mds_snap_head {
+ __le32 op; /* CEPH_SNAP_OP_* */
+ __le64 split; /* ino to split off, if any */
+ __le32 num_split_inos; /* # inos belonging to new child realm */
+ __le32 num_split_realms; /* # child realms udner new child realm */
+ __le32 trace_len; /* size of snap trace blob */
+} __attribute__ ((packed));
+/* followed by split ino list, then split realms, then the trace blob */
+
+/*
+ * encode info about a snaprealm, as viewed by a client
+ */
+struct ceph_mds_snap_realm {
+ __le64 ino; /* ino */
+ __le64 created; /* snap: when created */
+ __le64 parent; /* ino: parent realm */
+ __le64 parent_since; /* snap: same parent since */
+ __le64 seq; /* snap: version */
+ __le32 num_snaps;
+ __le32 num_prior_parent_snaps;
+} __attribute__ ((packed));
+/* followed by my snap list, then prior parent snap list */
+
+#endif
diff --git a/include/linux/ceph/ceph_hash.h b/include/linux/ceph/ceph_hash.h
new file mode 100644
index 00000000000..d099c3f9023
--- /dev/null
+++ b/include/linux/ceph/ceph_hash.h
@@ -0,0 +1,13 @@
+#ifndef FS_CEPH_HASH_H
+#define FS_CEPH_HASH_H
+
+#define CEPH_STR_HASH_LINUX 0x1 /* linux dcache hash */
+#define CEPH_STR_HASH_RJENKINS 0x2 /* robert jenkins' */
+
+extern unsigned ceph_str_hash_linux(const char *s, unsigned len);
+extern unsigned ceph_str_hash_rjenkins(const char *s, unsigned len);
+
+extern unsigned ceph_str_hash(int type, const char *s, unsigned len);
+extern const char *ceph_str_hash_name(int type);
+
+#endif
diff --git a/include/linux/ceph/debugfs.h b/include/linux/ceph/debugfs.h
new file mode 100644
index 00000000000..2a79702e092
--- /dev/null
+++ b/include/linux/ceph/debugfs.h
@@ -0,0 +1,33 @@
+#ifndef _FS_CEPH_DEBUGFS_H
+#define _FS_CEPH_DEBUGFS_H
+
+#include "ceph_debug.h"
+#include "types.h"
+
+#define CEPH_DEFINE_SHOW_FUNC(name) \
+static int name##_open(struct inode *inode, struct file *file) \
+{ \
+ struct seq_file *sf; \
+ int ret; \
+ \
+ ret = single_open(file, name, NULL); \
+ sf = file->private_data; \
+ sf->private = inode->i_private; \
+ return ret; \
+} \
+ \
+static const struct file_operations name##_fops = { \
+ .open = name##_open, \
+ .read = seq_read, \
+ .llseek = seq_lseek, \
+ .release = single_release, \
+};
+
+/* debugfs.c */
+extern int ceph_debugfs_init(void);
+extern void ceph_debugfs_cleanup(void);
+extern int ceph_debugfs_client_init(struct ceph_client *client);
+extern void ceph_debugfs_client_cleanup(struct ceph_client *client);
+
+#endif
+
diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h
new file mode 100644
index 00000000000..c5b6939fb32
--- /dev/null
+++ b/include/linux/ceph/decode.h
@@ -0,0 +1,201 @@
+#ifndef __CEPH_DECODE_H
+#define __CEPH_DECODE_H
+
+#include <asm/unaligned.h>
+#include <linux/time.h>
+
+#include "types.h"
+
+/*
+ * in all cases,
+ * void **p pointer to position pointer
+ * void *end pointer to end of buffer (last byte + 1)
+ */
+
+static inline u64 ceph_decode_64(void **p)
+{
+ u64 v = get_unaligned_le64(*p);
+ *p += sizeof(u64);
+ return v;
+}
+static inline u32 ceph_decode_32(void **p)
+{
+ u32 v = get_unaligned_le32(*p);
+ *p += sizeof(u32);
+ return v;
+}
+static inline u16 ceph_decode_16(void **p)
+{
+ u16 v = get_unaligned_le16(*p);
+ *p += sizeof(u16);
+ return v;
+}
+static inline u8 ceph_decode_8(void **p)
+{
+ u8 v = *(u8 *)*p;
+ (*p)++;
+ return v;
+}
+static inline void ceph_decode_copy(void **p, void *pv, size_t n)
+{
+ memcpy(pv, *p, n);
+ *p += n;
+}
+
+/*
+ * bounds check input.
+ */
+#define ceph_decode_need(p, end, n, bad) \
+ do { \
+ if (unlikely(*(p) + (n) > (end))) \
+ goto bad; \
+ } while (0)
+
+#define ceph_decode_64_safe(p, end, v, bad) \
+ do { \
+ ceph_decode_need(p, end, sizeof(u64), bad); \
+ v = ceph_decode_64(p); \
+ } while (0)
+#define ceph_decode_32_safe(p, end, v, bad) \
+ do { \
+ ceph_decode_need(p, end, sizeof(u32), bad); \
+ v = ceph_decode_32(p); \
+ } while (0)
+#define ceph_decode_16_safe(p, end, v, bad) \
+ do { \
+ ceph_decode_need(p, end, sizeof(u16), bad); \
+ v = ceph_decode_16(p); \
+ } while (0)
+#define ceph_decode_8_safe(p, end, v, bad) \
+ do { \
+ ceph_decode_need(p, end, sizeof(u8), bad); \
+ v = ceph_decode_8(p); \
+ } while (0)
+
+#define ceph_decode_copy_safe(p, end, pv, n, bad) \
+ do { \
+ ceph_decode_need(p, end, n, bad); \
+ ceph_decode_copy(p, pv, n); \
+ } while (0)
+
+/*
+ * struct ceph_timespec <-> struct timespec
+ */
+static inline void ceph_decode_timespec(struct timespec *ts,
+ const struct ceph_timespec *tv)
+{
+ ts->tv_sec = le32_to_cpu(tv->tv_sec);
+ ts->tv_nsec = le32_to_cpu(tv->tv_nsec);
+}
+static inline void ceph_encode_timespec(struct ceph_timespec *tv,
+ const struct timespec *ts)
+{
+ tv->tv_sec = cpu_to_le32(ts->tv_sec);
+ tv->tv_nsec = cpu_to_le32(ts->tv_nsec);
+}
+
+/*
+ * sockaddr_storage <-> ceph_sockaddr
+ */
+static inline void ceph_encode_addr(struct ceph_entity_addr *a)
+{
+ __be16 ss_family = htons(a->in_addr.ss_family);
+ a->in_addr.ss_family = *(__u16 *)&ss_family;
+}
+static inline void ceph_decode_addr(struct ceph_entity_addr *a)
+{
+ __be16 ss_family = *(__be16 *)&a->in_addr.ss_family;
+ a->in_addr.ss_family = ntohs(ss_family);
+ WARN_ON(a->in_addr.ss_family == 512);
+}
+
+/*
+ * encoders
+ */
+static inline void ceph_encode_64(void **p, u64 v)
+{
+ put_unaligned_le64(v, (__le64 *)*p);
+ *p += sizeof(u64);
+}
+static inline void ceph_encode_32(void **p, u32 v)
+{
+ put_unaligned_le32(v, (__le32 *)*p);
+ *p += sizeof(u32);
+}
+static inline void ceph_encode_16(void **p, u16 v)
+{
+ put_unaligned_le16(v, (__le16 *)*p);
+ *p += sizeof(u16);
+}
+static inline void ceph_encode_8(void **p, u8 v)
+{
+ *(u8 *)*p = v;
+ (*p)++;
+}
+static inline void ceph_encode_copy(void **p, const void *s, int len)
+{
+ memcpy(*p, s, len);
+ *p += len;
+}
+
+/*
+ * filepath, string encoders
+ */
+static inline void ceph_encode_filepath(void **p, void *end,
+ u64 ino, const char *path)
+{
+ u32 len = path ? strlen(path) : 0;
+ BUG_ON(*p + sizeof(ino) + sizeof(len) + len > end);
+ ceph_encode_8(p, 1);
+ ceph_encode_64(p, ino);
+ ceph_encode_32(p, len);
+ if (len)
+ memcpy(*p, path, len);
+ *p += len;
+}
+
+static inline void ceph_encode_string(void **p, void *end,
+ const char *s, u32 len)
+{
+ BUG_ON(*p + sizeof(len) + len > end);
+ ceph_encode_32(p, len);
+ if (len)
+ memcpy(*p, s, len);
+ *p += len;
+}
+
+#define ceph_encode_need(p, end, n, bad) \
+ do { \
+ if (unlikely(*(p) + (n) > (end))) \
+ goto bad; \
+ } while (0)
+
+#define ceph_encode_64_safe(p, end, v, bad) \
+ do { \
+ ceph_encode_need(p, end, sizeof(u64), bad); \
+ ceph_encode_64(p, v); \
+ } while (0)
+#define ceph_encode_32_safe(p, end, v, bad) \
+ do { \
+ ceph_encode_need(p, end, sizeof(u32), bad); \
+ ceph_encode_32(p, v); \
+ } while (0)
+#define ceph_encode_16_safe(p, end, v, bad) \
+ do { \
+ ceph_encode_need(p, end, sizeof(u16), bad); \
+ ceph_encode_16(p, v); \
+ } while (0)
+
+#define ceph_encode_copy_safe(p, end, pv, n, bad) \
+ do { \
+ ceph_encode_need(p, end, n, bad); \
+ ceph_encode_copy(p, pv, n); \
+ } while (0)
+#define ceph_encode_string_safe(p, end, s, n, bad) \
+ do { \
+ ceph_encode_need(p, end, n, bad); \
+ ceph_encode_string(p, end, s, n); \
+ } while (0)
+
+
+#endif
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
new file mode 100644
index 00000000000..f22b2e94168
--- /dev/null
+++ b/include/linux/ceph/libceph.h
@@ -0,0 +1,249 @@
+#ifndef _FS_CEPH_LIBCEPH_H
+#define _FS_CEPH_LIBCEPH_H
+
+#include "ceph_debug.h"
+
+#include <asm/unaligned.h>
+#include <linux/backing-dev.h>
+#include <linux/completion.h>
+#include <linux/exportfs.h>
+#include <linux/fs.h>
+#include <linux/mempool.h>
+#include <linux/pagemap.h>
+#include <linux/wait.h>
+#include <linux/writeback.h>
+#include <linux/slab.h>
+
+#include "types.h"
+#include "messenger.h"
+#include "msgpool.h"
+#include "mon_client.h"
+#include "osd_client.h"
+#include "ceph_fs.h"
+
+/*
+ * Supported features
+ */
+#define CEPH_FEATURE_SUPPORTED_DEFAULT CEPH_FEATURE_NOSRCADDR
+#define CEPH_FEATURE_REQUIRED_DEFAULT CEPH_FEATURE_NOSRCADDR
+
+/*
+ * mount options
+ */
+#define CEPH_OPT_FSID (1<<0)
+#define CEPH_OPT_NOSHARE (1<<1) /* don't share client with other sbs */
+#define CEPH_OPT_MYIP (1<<2) /* specified my ip */
+#define CEPH_OPT_NOCRC (1<<3) /* no data crc on writes */
+
+#define CEPH_OPT_DEFAULT (0);
+
+#define ceph_set_opt(client, opt) \
+ (client)->options->flags |= CEPH_OPT_##opt;
+#define ceph_test_opt(client, opt) \
+ (!!((client)->options->flags & CEPH_OPT_##opt))
+
+struct ceph_options {
+ int flags;
+ struct ceph_fsid fsid;
+ struct ceph_entity_addr my_addr;
+ int mount_timeout;
+ int osd_idle_ttl;
+ int osd_timeout;
+ int osd_keepalive_timeout;
+
+ /*
+ * any type that can't be simply compared or doesn't need need
+ * to be compared should go beyond this point,
+ * ceph_compare_options() should be updated accordingly
+ */
+
+ struct ceph_entity_addr *mon_addr; /* should be the first
+ pointer type of args */
+ int num_mon;
+ char *name;
+ char *secret;
+};
+
+/*
+ * defaults
+ */
+#define CEPH_MOUNT_TIMEOUT_DEFAULT 60
+#define CEPH_OSD_TIMEOUT_DEFAULT 60 /* seconds */
+#define CEPH_OSD_KEEPALIVE_DEFAULT 5
+#define CEPH_OSD_IDLE_TTL_DEFAULT 60
+#define CEPH_MOUNT_RSIZE_DEFAULT (512*1024) /* readahead */
+
+#define CEPH_MSG_MAX_FRONT_LEN (16*1024*1024)
+#define CEPH_MSG_MAX_DATA_LEN (16*1024*1024)
+
+#define CEPH_AUTH_NAME_DEFAULT "guest"
+
+/*
+ * Delay telling the MDS we no longer want caps, in case we reopen
+ * the file. Delay a minimum amount of time, even if we send a cap
+ * message for some other reason. Otherwise, take the oppotunity to
+ * update the mds to avoid sending another message later.
+ */
+#define CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT 5 /* cap release delay */
+#define CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT 60 /* cap release delay */
+
+#define CEPH_CAP_RELEASE_SAFETY_DEFAULT (CEPH_CAPS_PER_RELEASE * 4)
+
+/* mount state */
+enum {
+ CEPH_MOUNT_MOUNTING,
+ CEPH_MOUNT_MOUNTED,
+ CEPH_MOUNT_UNMOUNTING,
+ CEPH_MOUNT_UNMOUNTED,
+ CEPH_MOUNT_SHUTDOWN,
+};
+
+/*
+ * subtract jiffies
+ */
+static inline unsigned long time_sub(unsigned long a, unsigned long b)
+{
+ BUG_ON(time_after(b, a));
+ return (long)a - (long)b;
+}
+
+struct ceph_mds_client;
+
+/*
+ * per client state
+ *
+ * possibly shared by multiple mount points, if they are
+ * mounting the same ceph filesystem/cluster.
+ */
+struct ceph_client {
+ struct ceph_fsid fsid;
+ bool have_fsid;
+
+ void *private;
+
+ struct ceph_options *options;
+
+ struct mutex mount_mutex; /* serialize mount attempts */
+ wait_queue_head_t auth_wq;
+ int auth_err;
+
+ int (*extra_mon_dispatch)(struct ceph_client *, struct ceph_msg *);
+
+ u32 supported_features;
+ u32 required_features;
+
+ struct ceph_messenger *msgr; /* messenger instance */
+ struct ceph_mon_client monc;
+ struct ceph_osd_client osdc;
+
+#ifdef CONFIG_DEBUG_FS
+ struct dentry *debugfs_dir;
+ struct dentry *debugfs_monmap;
+ struct dentry *debugfs_osdmap;
+#endif
+};
+
+
+
+/*
+ * snapshots
+ */
+
+/*
+ * A "snap context" is the set of existing snapshots when we
+ * write data. It is used by the OSD to guide its COW behavior.
+ *
+ * The ceph_snap_context is refcounted, and attached to each dirty
+ * page, indicating which context the dirty data belonged when it was
+ * dirtied.
+ */
+struct ceph_snap_context {
+ atomic_t nref;
+ u64 seq;
+ int num_snaps;
+ u64 snaps[];
+};
+
+static inline struct ceph_snap_context *
+ceph_get_snap_context(struct ceph_snap_context *sc)
+{
+ /*
+ printk("get_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref),
+ atomic_read(&sc->nref)+1);
+ */
+ if (sc)
+ atomic_inc(&sc->nref);
+ return sc;
+}
+
+static inline void ceph_put_snap_context(struct ceph_snap_context *sc)
+{
+ if (!sc)
+ return;
+ /*
+ printk("put_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref),
+ atomic_read(&sc->nref)-1);
+ */
+ if (atomic_dec_and_test(&sc->nref)) {
+ /*printk(" deleting snap_context %p\n", sc);*/
+ kfree(sc);
+ }
+}
+
+/*
+ * calculate the number of pages a given length and offset map onto,
+ * if we align the data.
+ */
+static inline int calc_pages_for(u64 off, u64 len)
+{
+ return ((off+len+PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT) -
+ (off >> PAGE_CACHE_SHIFT);
+}
+
+/* ceph_common.c */
+extern const char *ceph_msg_type_name(int type);
+extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid);
+extern struct kmem_cache *ceph_inode_cachep;
+extern struct kmem_cache *ceph_cap_cachep;
+extern struct kmem_cache *ceph_dentry_cachep;
+extern struct kmem_cache *ceph_file_cachep;
+
+extern int ceph_parse_options(struct ceph_options **popt, char *options,
+ const char *dev_name, const char *dev_name_end,
+ int (*parse_extra_token)(char *c, void *private),
+ void *private);
+extern void ceph_destroy_options(struct ceph_options *opt);
+extern int ceph_compare_options(struct ceph_options *new_opt,
+ struct ceph_client *client);
+extern struct ceph_client *ceph_create_client(struct ceph_options *opt,
+ void *private);
+extern u64 ceph_client_id(struct ceph_client *client);
+extern void ceph_destroy_client(struct ceph_client *client);
+extern int __ceph_open_session(struct ceph_client *client,
+ unsigned long started);
+extern int ceph_open_session(struct ceph_client *client);
+
+/* pagevec.c */
+extern void ceph_release_page_vector(struct page **pages, int num_pages);
+
+extern struct page **ceph_get_direct_page_vector(const char __user *data,
+ int num_pages,
+ loff_t off, size_t len);
+extern void ceph_put_page_vector(struct page **pages, int num_pages);
+extern void ceph_release_page_vector(struct page **pages, int num_pages);
+extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
+extern int ceph_copy_user_to_page_vector(struct page **pages,
+ const char __user *data,
+ loff_t off, size_t len);
+extern int ceph_copy_to_page_vector(struct page **pages,
+ const char *data,
+ loff_t off, size_t len);
+extern int ceph_copy_from_page_vector(struct page **pages,
+ char *data,
+ loff_t off, size_t len);
+extern int ceph_copy_page_vector_to_user(struct page **pages, char __user *data,
+ loff_t off, size_t len);
+extern void ceph_zero_page_vector_range(int off, int len, struct page **pages);
+
+
+#endif /* _FS_CEPH_SUPER_H */
diff --git a/include/linux/ceph/mdsmap.h b/include/linux/ceph/mdsmap.h
new file mode 100644
index 00000000000..4c5cb0880bb
--- /dev/null
+++ b/include/linux/ceph/mdsmap.h
@@ -0,0 +1,62 @@
+#ifndef _FS_CEPH_MDSMAP_H
+#define _FS_CEPH_MDSMAP_H
+
+#include "types.h"
+
+/*
+ * mds map - describe servers in the mds cluster.
+ *
+ * we limit fields to those the client actually xcares about
+ */
+struct ceph_mds_info {
+ u64 global_id;
+ struct ceph_entity_addr addr;
+ s32 state;
+ int num_export_targets;
+ bool laggy;
+ u32 *export_targets;
+};
+
+struct ceph_mdsmap {
+ u32 m_epoch, m_client_epoch, m_last_failure;
+ u32 m_root;
+ u32 m_session_timeout; /* seconds */
+ u32 m_session_autoclose; /* seconds */
+ u64 m_max_file_size;
+ u32 m_max_mds; /* size of m_addr, m_state arrays */
+ struct ceph_mds_info *m_info;
+
+ /* which object pools file data can be stored in */
+ int m_num_data_pg_pools;
+ u32 *m_data_pg_pools;
+ u32 m_cas_pg_pool;
+};
+
+static inline struct ceph_entity_addr *
+ceph_mdsmap_get_addr(struct ceph_mdsmap *m, int w)
+{
+ if (w >= m->m_max_mds)
+ return NULL;
+ return &m->m_info[w].addr;
+}
+
+static inline int ceph_mdsmap_get_state(struct ceph_mdsmap *m, int w)
+{
+ BUG_ON(w < 0);
+ if (w >= m->m_max_mds)
+ return CEPH_MDS_STATE_DNE;
+ return m->m_info[w].state;
+}
+
+static inline bool ceph_mdsmap_is_laggy(struct ceph_mdsmap *m, int w)
+{
+ if (w >= 0 && w < m->m_max_mds)
+ return m->m_info[w].laggy;
+ return false;
+}
+
+extern int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m);
+extern struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end);
+extern void ceph_mdsmap_destroy(struct ceph_mdsmap *m);
+
+#endif
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
new file mode 100644
index 00000000000..5956d62c305
--- /dev/null
+++ b/include/linux/ceph/messenger.h
@@ -0,0 +1,261 @@
+#ifndef __FS_CEPH_MESSENGER_H
+#define __FS_CEPH_MESSENGER_H
+
+#include <linux/kref.h>
+#include <linux/mutex.h>
+#include <linux/net.h>
+#include <linux/radix-tree.h>
+#include <linux/uio.h>
+#include <linux/version.h>
+#include <linux/workqueue.h>
+
+#include "types.h"
+#include "buffer.h"
+
+struct ceph_msg;
+struct ceph_connection;
+
+extern struct workqueue_struct *ceph_msgr_wq; /* receive work queue */
+
+/*
+ * Ceph defines these callbacks for handling connection events.
+ */
+struct ceph_connection_operations {
+ struct ceph_connection *(*get)(struct ceph_connection *);
+ void (*put)(struct ceph_connection *);
+
+ /* handle an incoming message. */
+ void (*dispatch) (struct ceph_connection *con, struct ceph_msg *m);
+
+ /* authorize an outgoing connection */
+ int (*get_authorizer) (struct ceph_connection *con,
+ void **buf, int *len, int *proto,
+ void **reply_buf, int *reply_len, int force_new);
+ int (*verify_authorizer_reply) (struct ceph_connection *con, int len);
+ int (*invalidate_authorizer)(struct ceph_connection *con);
+
+ /* protocol version mismatch */
+ void (*bad_proto) (struct ceph_connection *con);
+
+ /* there was some error on the socket (disconnect, whatever) */
+ void (*fault) (struct ceph_connection *con);
+
+ /* a remote host as terminated a message exchange session, and messages
+ * we sent (or they tried to send us) may be lost. */
+ void (*peer_reset) (struct ceph_connection *con);
+
+ struct ceph_msg * (*alloc_msg) (struct ceph_connection *con,
+ struct ceph_msg_header *hdr,
+ int *skip);
+};
+
+/* use format string %s%d */
+#define ENTITY_NAME(n) ceph_entity_type_name((n).type), le64_to_cpu((n).num)
+
+struct ceph_messenger {
+ struct ceph_entity_inst inst; /* my name+address */
+ struct ceph_entity_addr my_enc_addr;
+ struct page *zero_page; /* used in certain error cases */
+
+ bool nocrc;
+
+ /*
+ * the global_seq counts connections i (attempt to) initiate
+ * in order to disambiguate certain connect race conditions.
+ */
+ u32 global_seq;
+ spinlock_t global_seq_lock;
+
+ u32 supported_features;
+ u32 required_features;
+};
+
+/*
+ * a single message. it contains a header (src, dest, message type, etc.),
+ * footer (crc values, mainly), a "front" message body, and possibly a
+ * data payload (stored in some number of pages).
+ */
+struct ceph_msg {
+ struct ceph_msg_header hdr; /* header */
+ struct ceph_msg_footer footer; /* footer */
+ struct kvec front; /* unaligned blobs of message */
+ struct ceph_buffer *middle;
+ struct page **pages; /* data payload. NOT OWNER. */
+ unsigned nr_pages; /* size of page array */
+ struct ceph_pagelist *pagelist; /* instead of pages */
+ struct list_head list_head;
+ struct kref kref;
+ struct bio *bio; /* instead of pages/pagelist */
+ struct bio *bio_iter; /* bio iterator */
+ int bio_seg; /* current bio segment */
+ struct ceph_pagelist *trail; /* the trailing part of the data */
+ bool front_is_vmalloc;
+ bool more_to_follow;
+ bool needs_out_seq;
+ int front_max;
+
+ struct ceph_msgpool *pool;
+};
+
+struct ceph_msg_pos {
+ int page, page_pos; /* which page; offset in page */
+ int data_pos; /* offset in data payload */
+ int did_page_crc; /* true if we've calculated crc for current page */
+};
+
+/* ceph connection fault delay defaults, for exponential backoff */
+#define BASE_DELAY_INTERVAL (HZ/2)
+#define MAX_DELAY_INTERVAL (5 * 60 * HZ)
+
+/*
+ * ceph_connection state bit flags
+ *
+ * QUEUED and BUSY are used together to ensure that only a single
+ * thread is currently opening, reading or writing data to the socket.
+ */
+#define LOSSYTX 0 /* we can close channel or drop messages on errors */
+#define CONNECTING 1
+#define NEGOTIATING 2
+#define KEEPALIVE_PENDING 3
+#define WRITE_PENDING 4 /* we have data ready to send */
+#define QUEUED 5 /* there is work queued on this connection */
+#define BUSY 6 /* work is being done */
+#define STANDBY 8 /* no outgoing messages, socket closed. we keep
+ * the ceph_connection around to maintain shared
+ * state with the peer. */
+#define CLOSED 10 /* we've closed the connection */
+#define SOCK_CLOSED 11 /* socket state changed to closed */
+#define OPENING 13 /* open connection w/ (possibly new) peer */
+#define DEAD 14 /* dead, about to kfree */
+
+/*
+ * A single connection with another host.
+ *
+ * We maintain a queue of outgoing messages, and some session state to
+ * ensure that we can preserve the lossless, ordered delivery of
+ * messages in the case of a TCP disconnect.
+ */
+struct ceph_connection {
+ void *private;
+ atomic_t nref;
+
+ const struct ceph_connection_operations *ops;
+
+ struct ceph_messenger *msgr;
+ struct socket *sock;
+ unsigned long state; /* connection state (see flags above) */
+ const char *error_msg; /* error message, if any */
+
+ struct ceph_entity_addr peer_addr; /* peer address */
+ struct ceph_entity_name peer_name; /* peer name */
+ struct ceph_entity_addr peer_addr_for_me;
+ unsigned peer_features;
+ u32 connect_seq; /* identify the most recent connection
+ attempt for this connection, client */
+ u32 peer_global_seq; /* peer's global seq for this connection */
+
+ int auth_retry; /* true if we need a newer authorizer */
+ void *auth_reply_buf; /* where to put the authorizer reply */
+ int auth_reply_buf_len;
+
+ struct mutex mutex;
+
+ /* out queue */
+ struct list_head out_queue;
+ struct list_head out_sent; /* sending or sent but unacked */
+ u64 out_seq; /* last message queued for send */
+ bool out_keepalive_pending;
+
+ u64 in_seq, in_seq_acked; /* last message received, acked */
+
+ /* connection negotiation temps */
+ char in_banner[CEPH_BANNER_MAX_LEN];
+ union {
+ struct { /* outgoing connection */
+ struct ceph_msg_connect out_connect;
+ struct ceph_msg_connect_reply in_reply;
+ };
+ struct { /* incoming */
+ struct ceph_msg_connect in_connect;
+ struct ceph_msg_connect_reply out_reply;
+ };
+ };
+ struct ceph_entity_addr actual_peer_addr;
+
+ /* message out temps */
+ struct ceph_msg *out_msg; /* sending message (== tail of
+ out_sent) */
+ bool out_msg_done;
+ struct ceph_msg_pos out_msg_pos;
+
+ struct kvec out_kvec[8], /* sending header/footer data */
+ *out_kvec_cur;
+ int out_kvec_left; /* kvec's left in out_kvec */
+ int out_skip; /* skip this many bytes */
+ int out_kvec_bytes; /* total bytes left */
+ bool out_kvec_is_msg; /* kvec refers to out_msg */
+ int out_more; /* there is more data after the kvecs */
+ __le64 out_temp_ack; /* for writing an ack */
+
+ /* message in temps */
+ struct ceph_msg_header in_hdr;
+ struct ceph_msg *in_msg;
+ struct ceph_msg_pos in_msg_pos;
+ u32 in_front_crc, in_middle_crc, in_data_crc; /* calculated crc */
+
+ char in_tag; /* protocol control byte */
+ int in_base_pos; /* bytes read */
+ __le64 in_temp_ack; /* for reading an ack */
+
+ struct delayed_work work; /* send|recv work */
+ unsigned long delay; /* current delay interval */
+};
+
+
+extern const char *ceph_pr_addr(const struct sockaddr_storage *ss);
+extern int ceph_parse_ips(const char *c, const char *end,
+ struct ceph_entity_addr *addr,
+ int max_count, int *count);
+
+
+extern int ceph_msgr_init(void);
+extern void ceph_msgr_exit(void);
+extern void ceph_msgr_flush(void);
+
+extern struct ceph_messenger *ceph_messenger_create(
+ struct ceph_entity_addr *myaddr,
+ u32 features, u32 required);
+extern void ceph_messenger_destroy(struct ceph_messenger *);
+
+extern void ceph_con_init(struct ceph_messenger *msgr,
+ struct ceph_connection *con);
+extern void ceph_con_open(struct ceph_connection *con,
+ struct ceph_entity_addr *addr);
+extern bool ceph_con_opened(struct ceph_connection *con);
+extern void ceph_con_close(struct ceph_connection *con);
+extern void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg);
+extern void ceph_con_revoke(struct ceph_connection *con, struct ceph_msg *msg);
+extern void ceph_con_revoke_message(struct ceph_connection *con,
+ struct ceph_msg *msg);
+extern void ceph_con_keepalive(struct ceph_connection *con);
+extern struct ceph_connection *ceph_con_get(struct ceph_connection *con);
+extern void ceph_con_put(struct ceph_connection *con);
+
+extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags);
+extern void ceph_msg_kfree(struct ceph_msg *m);
+
+
+static inline struct ceph_msg *ceph_msg_get(struct ceph_msg *msg)
+{
+ kref_get(&msg->kref);
+ return msg;
+}
+extern void ceph_msg_last_put(struct kref *kref);
+static inline void ceph_msg_put(struct ceph_msg *msg)
+{
+ kref_put(&msg->kref, ceph_msg_last_put);
+}
+
+extern void ceph_msg_dump(struct ceph_msg *msg);
+
+#endif
diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h
new file mode 100644
index 00000000000..545f8591778
--- /dev/null
+++ b/include/linux/ceph/mon_client.h
@@ -0,0 +1,122 @@
+#ifndef _FS_CEPH_MON_CLIENT_H
+#define _FS_CEPH_MON_CLIENT_H
+
+#include <linux/completion.h>
+#include <linux/kref.h>
+#include <linux/rbtree.h>
+
+#include "messenger.h"
+
+struct ceph_client;
+struct ceph_mount_args;
+struct ceph_auth_client;
+
+/*
+ * The monitor map enumerates the set of all monitors.
+ */
+struct ceph_monmap {
+ struct ceph_fsid fsid;
+ u32 epoch;
+ u32 num_mon;
+ struct ceph_entity_inst mon_inst[0];
+};
+
+struct ceph_mon_client;
+struct ceph_mon_generic_request;
+
+
+/*
+ * Generic mechanism for resending monitor requests.
+ */
+typedef void (*ceph_monc_request_func_t)(struct ceph_mon_client *monc,
+ int newmon);
+
+/* a pending monitor request */
+struct ceph_mon_request {
+ struct ceph_mon_client *monc;
+ struct delayed_work delayed_work;
+ unsigned long delay;
+ ceph_monc_request_func_t do_request;
+};
+
+/*
+ * ceph_mon_generic_request is being used for the statfs and poolop requests
+ * which are bening done a bit differently because we need to get data back
+ * to the caller
+ */
+struct ceph_mon_generic_request {
+ struct kref kref;
+ u64 tid;
+ struct rb_node node;
+ int result;
+ void *buf;
+ int buf_len;
+ struct completion completion;
+ struct ceph_msg *request; /* original request */
+ struct ceph_msg *reply; /* and reply */
+};
+
+struct ceph_mon_client {
+ struct ceph_client *client;
+ struct ceph_monmap *monmap;
+
+ struct mutex mutex;
+ struct delayed_work delayed_work;
+
+ struct ceph_auth_client *auth;
+ struct ceph_msg *m_auth, *m_auth_reply, *m_subscribe, *m_subscribe_ack;
+ int pending_auth;
+
+ bool hunting;
+ int cur_mon; /* last monitor i contacted */
+ unsigned long sub_sent, sub_renew_after;
+ struct ceph_connection *con;
+ bool have_fsid;
+
+ /* pending generic requests */
+ struct rb_root generic_request_tree;
+ int num_generic_requests;
+ u64 last_tid;
+
+ /* mds/osd map */
+ int want_mdsmap;
+ int want_next_osdmap; /* 1 = want, 2 = want+asked */
+ u32 have_osdmap, have_mdsmap;
+
+#ifdef CONFIG_DEBUG_FS
+ struct dentry *debugfs_file;
+#endif
+};
+
+extern struct ceph_monmap *ceph_monmap_decode(void *p, void *end);
+extern int ceph_monmap_contains(struct ceph_monmap *m,
+ struct ceph_entity_addr *addr);
+
+extern int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl);
+extern void ceph_monc_stop(struct ceph_mon_client *monc);
+
+/*
+ * The model here is to indicate that we need a new map of at least
+ * epoch @want, and also call in when we receive a map. We will
+ * periodically rerequest the map from the monitor cluster until we
+ * get what we want.
+ */
+extern int ceph_monc_got_mdsmap(struct ceph_mon_client *monc, u32 have);
+extern int ceph_monc_got_osdmap(struct ceph_mon_client *monc, u32 have);
+
+extern void ceph_monc_request_next_osdmap(struct ceph_mon_client *monc);
+
+extern int ceph_monc_do_statfs(struct ceph_mon_client *monc,
+ struct ceph_statfs *buf);
+
+extern int ceph_monc_open_session(struct ceph_mon_client *monc);
+
+extern int ceph_monc_validate_auth(struct ceph_mon_client *monc);
+
+extern int ceph_monc_create_snapid(struct ceph_mon_client *monc,
+ u32 pool, u64 *snapid);
+
+extern int ceph_monc_delete_snapid(struct ceph_mon_client *monc,
+ u32 pool, u64 snapid);
+
+#endif
diff --git a/include/linux/ceph/msgpool.h b/include/linux/ceph/msgpool.h
new file mode 100644
index 00000000000..a362605f936
--- /dev/null
+++ b/include/linux/ceph/msgpool.h
@@ -0,0 +1,25 @@
+#ifndef _FS_CEPH_MSGPOOL
+#define _FS_CEPH_MSGPOOL
+
+#include <linux/mempool.h>
+#include "messenger.h"
+
+/*
+ * we use memory pools for preallocating messages we may receive, to
+ * avoid unexpected OOM conditions.
+ */
+struct ceph_msgpool {
+ const char *name;
+ mempool_t *pool;
+ int front_len; /* preallocated payload size */
+};
+
+extern int ceph_msgpool_init(struct ceph_msgpool *pool,
+ int front_len, int size, bool blocking,
+ const char *name);
+extern void ceph_msgpool_destroy(struct ceph_msgpool *pool);
+extern struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *,
+ int front_len);
+extern void ceph_msgpool_put(struct ceph_msgpool *, struct ceph_msg *);
+
+#endif
diff --git a/include/linux/ceph/msgr.h b/include/linux/ceph/msgr.h
new file mode 100644
index 00000000000..680d3d648ca
--- /dev/null
+++ b/include/linux/ceph/msgr.h
@@ -0,0 +1,175 @@
+#ifndef CEPH_MSGR_H
+#define CEPH_MSGR_H
+
+/*
+ * Data types for message passing layer used by Ceph.
+ */
+
+#define CEPH_MON_PORT 6789 /* default monitor port */
+
+/*
+ * client-side processes will try to bind to ports in this
+ * range, simply for the benefit of tools like nmap or wireshark
+ * that would like to identify the protocol.
+ */
+#define CEPH_PORT_FIRST 6789
+#define CEPH_PORT_START 6800 /* non-monitors start here */
+#define CEPH_PORT_LAST 6900
+
+/*
+ * tcp connection banner. include a protocol version. and adjust
+ * whenever the wire protocol changes. try to keep this string length
+ * constant.
+ */
+#define CEPH_BANNER "ceph v027"
+#define CEPH_BANNER_MAX_LEN 30
+
+
+/*
+ * Rollover-safe type and comparator for 32-bit sequence numbers.
+ * Comparator returns -1, 0, or 1.
+ */
+typedef __u32 ceph_seq_t;
+
+static inline __s32 ceph_seq_cmp(__u32 a, __u32 b)
+{
+ return (__s32)a - (__s32)b;
+}
+
+
+/*
+ * entity_name -- logical name for a process participating in the
+ * network, e.g. 'mds0' or 'osd3'.
+ */
+struct ceph_entity_name {
+ __u8 type; /* CEPH_ENTITY_TYPE_* */
+ __le64 num;
+} __attribute__ ((packed));
+
+#define CEPH_ENTITY_TYPE_MON 0x01
+#define CEPH_ENTITY_TYPE_MDS 0x02
+#define CEPH_ENTITY_TYPE_OSD 0x04
+#define CEPH_ENTITY_TYPE_CLIENT 0x08
+#define CEPH_ENTITY_TYPE_AUTH 0x20
+
+#define CEPH_ENTITY_TYPE_ANY 0xFF
+
+extern const char *ceph_entity_type_name(int type);
+
+/*
+ * entity_addr -- network address
+ */
+struct ceph_entity_addr {
+ __le32 type;
+ __le32 nonce; /* unique id for process (e.g. pid) */
+ struct sockaddr_storage in_addr;
+} __attribute__ ((packed));
+
+struct ceph_entity_inst {
+ struct ceph_entity_name name;
+ struct ceph_entity_addr addr;
+} __attribute__ ((packed));
+
+
+/* used by message exchange protocol */
+#define CEPH_MSGR_TAG_READY 1 /* server->client: ready for messages */
+#define CEPH_MSGR_TAG_RESETSESSION 2 /* server->client: reset, try again */
+#define CEPH_MSGR_TAG_WAIT 3 /* server->client: wait for racing
+ incoming connection */
+#define CEPH_MSGR_TAG_RETRY_SESSION 4 /* server->client + cseq: try again
+ with higher cseq */
+#define CEPH_MSGR_TAG_RETRY_GLOBAL 5 /* server->client + gseq: try again
+ with higher gseq */
+#define CEPH_MSGR_TAG_CLOSE 6 /* closing pipe */
+#define CEPH_MSGR_TAG_MSG 7 /* message */
+#define CEPH_MSGR_TAG_ACK 8 /* message ack */
+#define CEPH_MSGR_TAG_KEEPALIVE 9 /* just a keepalive byte! */
+#define CEPH_MSGR_TAG_BADPROTOVER 10 /* bad protocol version */
+#define CEPH_MSGR_TAG_BADAUTHORIZER 11 /* bad authorizer */
+#define CEPH_MSGR_TAG_FEATURES 12 /* insufficient features */
+
+
+/*
+ * connection negotiation
+ */
+struct ceph_msg_connect {
+ __le64 features; /* supported feature bits */
+ __le32 host_type; /* CEPH_ENTITY_TYPE_* */
+ __le32 global_seq; /* count connections initiated by this host */
+ __le32 connect_seq; /* count connections initiated in this session */
+ __le32 protocol_version;
+ __le32 authorizer_protocol;
+ __le32 authorizer_len;
+ __u8 flags; /* CEPH_MSG_CONNECT_* */
+} __attribute__ ((packed));
+
+struct ceph_msg_connect_reply {
+ __u8 tag;
+ __le64 features; /* feature bits for this session */
+ __le32 global_seq;
+ __le32 connect_seq;
+ __le32 protocol_version;
+ __le32 authorizer_len;
+ __u8 flags;
+} __attribute__ ((packed));
+
+#define CEPH_MSG_CONNECT_LOSSY 1 /* messages i send may be safely dropped */
+
+
+/*
+ * message header
+ */
+struct ceph_msg_header_old {
+ __le64 seq; /* message seq# for this session */
+ __le64 tid; /* transaction id */
+ __le16 type; /* message type */
+ __le16 priority; /* priority. higher value == higher priority */
+ __le16 version; /* version of message encoding */
+
+ __le32 front_len; /* bytes in main payload */
+ __le32 middle_len;/* bytes in middle payload */
+ __le32 data_len; /* bytes of data payload */
+ __le16 data_off; /* sender: include full offset;
+ receiver: mask against ~PAGE_MASK */
+
+ struct ceph_entity_inst src, orig_src;
+ __le32 reserved;
+ __le32 crc; /* header crc32c */
+} __attribute__ ((packed));
+
+struct ceph_msg_header {
+ __le64 seq; /* message seq# for this session */
+ __le64 tid; /* transaction id */
+ __le16 type; /* message type */
+ __le16 priority; /* priority. higher value == higher priority */
+ __le16 version; /* version of message encoding */
+
+ __le32 front_len; /* bytes in main payload */
+ __le32 middle_len;/* bytes in middle payload */
+ __le32 data_len; /* bytes of data payload */
+ __le16 data_off; /* sender: include full offset;
+ receiver: mask against ~PAGE_MASK */
+
+ struct ceph_entity_name src;
+ __le32 reserved;
+ __le32 crc; /* header crc32c */
+} __attribute__ ((packed));
+
+#define CEPH_MSG_PRIO_LOW 64
+#define CEPH_MSG_PRIO_DEFAULT 127
+#define CEPH_MSG_PRIO_HIGH 196
+#define CEPH_MSG_PRIO_HIGHEST 255
+
+/*
+ * follows data payload
+ */
+struct ceph_msg_footer {
+ __le32 front_crc, middle_crc, data_crc;
+ __u8 flags;
+} __attribute__ ((packed));
+
+#define CEPH_MSG_FOOTER_COMPLETE (1<<0) /* msg wasn't aborted */
+#define CEPH_MSG_FOOTER_NOCRC (1<<1) /* no data crc */
+
+
+#endif
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
new file mode 100644
index 00000000000..6c91fb032c3
--- /dev/null
+++ b/include/linux/ceph/osd_client.h
@@ -0,0 +1,234 @@
+#ifndef _FS_CEPH_OSD_CLIENT_H
+#define _FS_CEPH_OSD_CLIENT_H
+
+#include <linux/completion.h>
+#include <linux/kref.h>
+#include <linux/mempool.h>
+#include <linux/rbtree.h>
+
+#include "types.h"
+#include "osdmap.h"
+#include "messenger.h"
+
+struct ceph_msg;
+struct ceph_snap_context;
+struct ceph_osd_request;
+struct ceph_osd_client;
+struct ceph_authorizer;
+struct ceph_pagelist;
+
+/*
+ * completion callback for async writepages
+ */
+typedef void (*ceph_osdc_callback_t)(struct ceph_osd_request *,
+ struct ceph_msg *);
+
+/* a given osd we're communicating with */
+struct ceph_osd {
+ atomic_t o_ref;
+ struct ceph_osd_client *o_osdc;
+ int o_osd;
+ int o_incarnation;
+ struct rb_node o_node;
+ struct ceph_connection o_con;
+ struct list_head o_requests;
+ struct list_head o_osd_lru;
+ struct ceph_authorizer *o_authorizer;
+ void *o_authorizer_buf, *o_authorizer_reply_buf;
+ size_t o_authorizer_buf_len, o_authorizer_reply_buf_len;
+ unsigned long lru_ttl;
+ int o_marked_for_keepalive;
+ struct list_head o_keepalive_item;
+};
+
+/* an in-flight request */
+struct ceph_osd_request {
+ u64 r_tid; /* unique for this client */
+ struct rb_node r_node;
+ struct list_head r_req_lru_item;
+ struct list_head r_osd_item;
+ struct ceph_osd *r_osd;
+ struct ceph_pg r_pgid;
+ int r_pg_osds[CEPH_PG_MAX_SIZE];
+ int r_num_pg_osds;
+
+ struct ceph_connection *r_con_filling_msg;
+
+ struct ceph_msg *r_request, *r_reply;
+ int r_result;
+ int r_flags; /* any additional flags for the osd */
+ u32 r_sent; /* >0 if r_request is sending/sent */
+ int r_got_reply;
+
+ struct ceph_osd_client *r_osdc;
+ struct kref r_kref;
+ bool r_mempool;
+ struct completion r_completion, r_safe_completion;
+ ceph_osdc_callback_t r_callback, r_safe_callback;
+ struct ceph_eversion r_reassert_version;
+ struct list_head r_unsafe_item;
+
+ struct inode *r_inode; /* for use by callbacks */
+ void *r_priv; /* ditto */
+
+ char r_oid[40]; /* object name */
+ int r_oid_len;
+ unsigned long r_stamp; /* send OR check time */
+ bool r_resend; /* msg send failed, needs retry */
+
+ struct ceph_file_layout r_file_layout;
+ struct ceph_snap_context *r_snapc; /* snap context for writes */
+ unsigned r_num_pages; /* size of page array (follows) */
+ struct page **r_pages; /* pages for data payload */
+ int r_pages_from_pool;
+ int r_own_pages; /* if true, i own page list */
+#ifdef CONFIG_BLOCK
+ struct bio *r_bio; /* instead of pages */
+#endif
+
+ struct ceph_pagelist *r_trail; /* trailing part of the data */
+};
+
+struct ceph_osd_client {
+ struct ceph_client *client;
+
+ struct ceph_osdmap *osdmap; /* current map */
+ struct rw_semaphore map_sem;
+ struct completion map_waiters;
+ u64 last_requested_map;
+
+ struct mutex request_mutex;
+ struct rb_root osds; /* osds */
+ struct list_head osd_lru; /* idle osds */
+ u64 timeout_tid; /* tid of timeout triggering rq */
+ u64 last_tid; /* tid of last request */
+ struct rb_root requests; /* pending requests */
+ struct list_head req_lru; /* pending requests lru */
+ int num_requests;
+ struct delayed_work timeout_work;
+ struct delayed_work osds_timeout_work;
+#ifdef CONFIG_DEBUG_FS
+ struct dentry *debugfs_file;
+#endif
+
+ mempool_t *req_mempool;
+
+ struct ceph_msgpool msgpool_op;
+ struct ceph_msgpool msgpool_op_reply;
+};
+
+struct ceph_osd_req_op {
+ u16 op; /* CEPH_OSD_OP_* */
+ u32 flags; /* CEPH_OSD_FLAG_* */
+ union {
+ struct {
+ u64 offset, length;
+ u64 truncate_size;
+ u32 truncate_seq;
+ } extent;
+ struct {
+ const char *name;
+ u32 name_len;
+ const char *val;
+ u32 value_len;
+ __u8 cmp_op; /* CEPH_OSD_CMPXATTR_OP_* */
+ __u8 cmp_mode; /* CEPH_OSD_CMPXATTR_MODE_* */
+ } xattr;
+ struct {
+ const char *class_name;
+ __u8 class_len;
+ const char *method_name;
+ __u8 method_len;
+ __u8 argc;
+ const char *indata;
+ u32 indata_len;
+ } cls;
+ struct {
+ u64 cookie, count;
+ } pgls;
+ struct {
+ u64 snapid;
+ } snap;
+ };
+ u32 payload_len;
+};
+
+extern int ceph_osdc_init(struct ceph_osd_client *osdc,
+ struct ceph_client *client);
+extern void ceph_osdc_stop(struct ceph_osd_client *osdc);
+
+extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc,
+ struct ceph_msg *msg);
+extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc,
+ struct ceph_msg *msg);
+
+extern void ceph_calc_raw_layout(struct ceph_osd_client *osdc,
+ struct ceph_file_layout *layout,
+ u64 snapid,
+ u64 off, u64 *plen, u64 *bno,
+ struct ceph_osd_request *req,
+ struct ceph_osd_req_op *op);
+
+extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
+ int flags,
+ struct ceph_snap_context *snapc,
+ struct ceph_osd_req_op *ops,
+ bool use_mempool,
+ gfp_t gfp_flags,
+ struct page **pages,
+ struct bio *bio);
+
+extern void ceph_osdc_build_request(struct ceph_osd_request *req,
+ u64 off, u64 *plen,
+ struct ceph_osd_req_op *src_ops,
+ struct ceph_snap_context *snapc,
+ struct timespec *mtime,
+ const char *oid,
+ int oid_len);
+
+extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *,
+ struct ceph_file_layout *layout,
+ struct ceph_vino vino,
+ u64 offset, u64 *len, int op, int flags,
+ struct ceph_snap_context *snapc,
+ int do_sync, u32 truncate_seq,
+ u64 truncate_size,
+ struct timespec *mtime,
+ bool use_mempool, int num_reply);
+
+static inline void ceph_osdc_get_request(struct ceph_osd_request *req)
+{
+ kref_get(&req->r_kref);
+}
+extern void ceph_osdc_release_request(struct kref *kref);
+static inline void ceph_osdc_put_request(struct ceph_osd_request *req)
+{
+ kref_put(&req->r_kref, ceph_osdc_release_request);
+}
+
+extern int ceph_osdc_start_request(struct ceph_osd_client *osdc,
+ struct ceph_osd_request *req,
+ bool nofail);
+extern int ceph_osdc_wait_request(struct ceph_osd_client *osdc,
+ struct ceph_osd_request *req);
+extern void ceph_osdc_sync(struct ceph_osd_client *osdc);
+
+extern int ceph_osdc_readpages(struct ceph_osd_client *osdc,
+ struct ceph_vino vino,
+ struct ceph_file_layout *layout,
+ u64 off, u64 *plen,
+ u32 truncate_seq, u64 truncate_size,
+ struct page **pages, int nr_pages);
+
+extern int ceph_osdc_writepages(struct ceph_osd_client *osdc,
+ struct ceph_vino vino,
+ struct ceph_file_layout *layout,
+ struct ceph_snap_context *sc,
+ u64 off, u64 len,
+ u32 truncate_seq, u64 truncate_size,
+ struct timespec *mtime,
+ struct page **pages, int nr_pages,
+ int flags, int do_sync, bool nofail);
+
+#endif
+
diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
new file mode 100644
index 00000000000..ba4c205cbb0
--- /dev/null
+++ b/include/linux/ceph/osdmap.h
@@ -0,0 +1,130 @@
+#ifndef _FS_CEPH_OSDMAP_H
+#define _FS_CEPH_OSDMAP_H
+
+#include <linux/rbtree.h>
+#include "types.h"
+#include "ceph_fs.h"
+#include <linux/crush/crush.h>
+
+/*
+ * The osd map describes the current membership of the osd cluster and
+ * specifies the mapping of objects to placement groups and placement
+ * groups to (sets of) osds. That is, it completely specifies the
+ * (desired) distribution of all data objects in the system at some
+ * point in time.
+ *
+ * Each map version is identified by an epoch, which increases monotonically.
+ *
+ * The map can be updated either via an incremental map (diff) describing
+ * the change between two successive epochs, or as a fully encoded map.
+ */
+struct ceph_pg_pool_info {
+ struct rb_node node;
+ int id;
+ struct ceph_pg_pool v;
+ int pg_num_mask, pgp_num_mask, lpg_num_mask, lpgp_num_mask;
+ char *name;
+};
+
+struct ceph_pg_mapping {
+ struct rb_node node;
+ struct ceph_pg pgid;
+ int len;
+ int osds[];
+};
+
+struct ceph_osdmap {
+ struct ceph_fsid fsid;
+ u32 epoch;
+ u32 mkfs_epoch;
+ struct ceph_timespec created, modified;
+
+ u32 flags; /* CEPH_OSDMAP_* */
+
+ u32 max_osd; /* size of osd_state, _offload, _addr arrays */
+ u8 *osd_state; /* CEPH_OSD_* */
+ u32 *osd_weight; /* 0 = failed, 0x10000 = 100% normal */
+ struct ceph_entity_addr *osd_addr;
+
+ struct rb_root pg_temp;
+ struct rb_root pg_pools;
+ u32 pool_max;
+
+ /* the CRUSH map specifies the mapping of placement groups to
+ * the list of osds that store+replicate them. */
+ struct crush_map *crush;
+};
+
+/*
+ * file layout helpers
+ */
+#define ceph_file_layout_su(l) ((__s32)le32_to_cpu((l).fl_stripe_unit))
+#define ceph_file_layout_stripe_count(l) \
+ ((__s32)le32_to_cpu((l).fl_stripe_count))
+#define ceph_file_layout_object_size(l) ((__s32)le32_to_cpu((l).fl_object_size))
+#define ceph_file_layout_cas_hash(l) ((__s32)le32_to_cpu((l).fl_cas_hash))
+#define ceph_file_layout_object_su(l) \
+ ((__s32)le32_to_cpu((l).fl_object_stripe_unit))
+#define ceph_file_layout_pg_preferred(l) \
+ ((__s32)le32_to_cpu((l).fl_pg_preferred))
+#define ceph_file_layout_pg_pool(l) \
+ ((__s32)le32_to_cpu((l).fl_pg_pool))
+
+static inline unsigned ceph_file_layout_stripe_width(struct ceph_file_layout *l)
+{
+ return le32_to_cpu(l->fl_stripe_unit) *
+ le32_to_cpu(l->fl_stripe_count);
+}
+
+/* "period" == bytes before i start on a new set of objects */
+static inline unsigned ceph_file_layout_period(struct ceph_file_layout *l)
+{
+ return le32_to_cpu(l->fl_object_size) *
+ le32_to_cpu(l->fl_stripe_count);
+}
+
+
+static inline int ceph_osd_is_up(struct ceph_osdmap *map, int osd)
+{
+ return (osd < map->max_osd) && (map->osd_state[osd] & CEPH_OSD_UP);
+}
+
+static inline bool ceph_osdmap_flag(struct ceph_osdmap *map, int flag)
+{
+ return map && (map->flags & flag);
+}
+
+extern char *ceph_osdmap_state_str(char *str, int len, int state);
+
+static inline struct ceph_entity_addr *ceph_osd_addr(struct ceph_osdmap *map,
+ int osd)
+{
+ if (osd >= map->max_osd)
+ return NULL;
+ return &map->osd_addr[osd];
+}
+
+extern struct ceph_osdmap *osdmap_decode(void **p, void *end);
+extern struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
+ struct ceph_osdmap *map,
+ struct ceph_messenger *msgr);
+extern void ceph_osdmap_destroy(struct ceph_osdmap *map);
+
+/* calculate mapping of a file extent to an object */
+extern void ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
+ u64 off, u64 *plen,
+ u64 *bno, u64 *oxoff, u64 *oxlen);
+
+/* calculate mapping of object to a placement group */
+extern int ceph_calc_object_layout(struct ceph_object_layout *ol,
+ const char *oid,
+ struct ceph_file_layout *fl,
+ struct ceph_osdmap *osdmap);
+extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
+ int *acting);
+extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap,
+ struct ceph_pg pgid);
+
+extern int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name);
+
+#endif
diff --git a/include/linux/ceph/pagelist.h b/include/linux/ceph/pagelist.h
new file mode 100644
index 00000000000..cc9327aa1c9
--- /dev/null
+++ b/include/linux/ceph/pagelist.h
@@ -0,0 +1,54 @@
+#ifndef __FS_CEPH_PAGELIST_H
+#define __FS_CEPH_PAGELIST_H
+
+#include <linux/list.h>
+
+struct ceph_pagelist {
+ struct list_head head;
+ void *mapped_tail;
+ size_t length;
+ size_t room;
+};
+
+static inline void ceph_pagelist_init(struct ceph_pagelist *pl)
+{
+ INIT_LIST_HEAD(&pl->head);
+ pl->mapped_tail = NULL;
+ pl->length = 0;
+ pl->room = 0;
+}
+extern int ceph_pagelist_release(struct ceph_pagelist *pl);
+
+extern int ceph_pagelist_append(struct ceph_pagelist *pl, const void *d, size_t l);
+
+static inline int ceph_pagelist_encode_64(struct ceph_pagelist *pl, u64 v)
+{
+ __le64 ev = cpu_to_le64(v);
+ return ceph_pagelist_append(pl, &ev, sizeof(ev));
+}
+static inline int ceph_pagelist_encode_32(struct ceph_pagelist *pl, u32 v)
+{
+ __le32 ev = cpu_to_le32(v);
+ return ceph_pagelist_append(pl, &ev, sizeof(ev));
+}
+static inline int ceph_pagelist_encode_16(struct ceph_pagelist *pl, u16 v)
+{
+ __le16 ev = cpu_to_le16(v);
+ return ceph_pagelist_append(pl, &ev, sizeof(ev));
+}
+static inline int ceph_pagelist_encode_8(struct ceph_pagelist *pl, u8 v)
+{
+ return ceph_pagelist_append(pl, &v, 1);
+}
+static inline int ceph_pagelist_encode_string(struct ceph_pagelist *pl,
+ char *s, size_t len)
+{
+ int ret = ceph_pagelist_encode_32(pl, len);
+ if (ret)
+ return ret;
+ if (len)
+ return ceph_pagelist_append(pl, s, len);
+ return 0;
+}
+
+#endif
diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
new file mode 100644
index 00000000000..6d5247f2e81
--- /dev/null
+++ b/include/linux/ceph/rados.h
@@ -0,0 +1,405 @@
+#ifndef CEPH_RADOS_H
+#define CEPH_RADOS_H
+
+/*
+ * Data types for the Ceph distributed object storage layer RADOS
+ * (Reliable Autonomic Distributed Object Store).
+ */
+
+#include "msgr.h"
+
+/*
+ * osdmap encoding versions
+ */
+#define CEPH_OSDMAP_INC_VERSION 5
+#define CEPH_OSDMAP_INC_VERSION_EXT 5
+#define CEPH_OSDMAP_VERSION 5
+#define CEPH_OSDMAP_VERSION_EXT 5
+
+/*
+ * 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
+
+#define CEPH_PG_MAX_SIZE 16 /* max # osds in a single pg */
+
+/*
+ * 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
+#define CEPH_PG_POOL_VERSION 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; /* if non-empty, NO per-pool snaps */
+ __le64 auid; /* who owns the pg */
+} __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,
+ CEPH_OSD_OP_ROLLBACK= CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 14,
+
+ /** 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,
+ CEPH_OSD_OP_CMPXATTR = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 3,
+
+ /* 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;
+}
+
+/*
+ * note that the following tmap stuff is also defined in the ceph librados.h
+ * any modification here needs to be updated there
+ */
+#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 */
+ CEPH_OSD_FLAG_EXEC_PUBLIC = 4096, /* op may exec (public) */
+};
+
+enum {
+ CEPH_OSD_OP_FLAG_EXCL = 1, /* EXCL object create */
+};
+
+#define EOLDSNAPC ERESTART /* ORDERSNAP flag set; writer has old snapc*/
+#define EBLACKLISTED ESHUTDOWN /* blacklisted */
+
+/* xattr comparison */
+enum {
+ CEPH_OSD_CMPXATTR_OP_NOP = 0,
+ CEPH_OSD_CMPXATTR_OP_EQ = 1,
+ CEPH_OSD_CMPXATTR_OP_NE = 2,
+ CEPH_OSD_CMPXATTR_OP_GT = 3,
+ CEPH_OSD_CMPXATTR_OP_GTE = 4,
+ CEPH_OSD_CMPXATTR_OP_LT = 5,
+ CEPH_OSD_CMPXATTR_OP_LTE = 6
+};
+
+enum {
+ CEPH_OSD_CMPXATTR_MODE_STRING = 1,
+ CEPH_OSD_CMPXATTR_MODE_U64 = 2
+};
+
+/*
+ * 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;
+ __u8 cmp_op; /* CEPH_OSD_CMPXATTR_OP_* */
+ __u8 cmp_mode; /* CEPH_OSD_CMPXATTR_MODE_* */
+ } __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;
+ struct {
+ __le64 snapid;
+ } __attribute__ ((packed)) snap;
+ };
+ __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
diff --git a/include/linux/ceph/types.h b/include/linux/ceph/types.h
new file mode 100644
index 00000000000..28b35a005ec
--- /dev/null
+++ b/include/linux/ceph/types.h
@@ -0,0 +1,29 @@
+#ifndef _FS_CEPH_TYPES_H
+#define _FS_CEPH_TYPES_H
+
+/* needed before including ceph_fs.h */
+#include <linux/in.h>
+#include <linux/types.h>
+#include <linux/fcntl.h>
+#include <linux/string.h>
+
+#include "ceph_fs.h"
+#include "ceph_frag.h"
+#include "ceph_hash.h"
+
+/*
+ * Identify inodes by both their ino AND snapshot id (a u64).
+ */
+struct ceph_vino {
+ u64 ino;
+ u64 snap;
+};
+
+
+/* context for the caps reservation mechanism */
+struct ceph_cap_reservation {
+ int count;
+};
+
+
+#endif
diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h
new file mode 100644
index 00000000000..97e435b191f
--- /dev/null
+++ b/include/linux/crush/crush.h
@@ -0,0 +1,180 @@
+#ifndef CEPH_CRUSH_CRUSH_H
+#define CEPH_CRUSH_CRUSH_H
+
+#include <linux/types.h>
+
+/*
+ * CRUSH is a pseudo-random data distribution algorithm that
+ * efficiently distributes input values (typically, data objects)
+ * across a heterogeneous, structured storage cluster.
+ *
+ * The algorithm was originally described in detail in this paper
+ * (although the algorithm has evolved somewhat since then):
+ *
+ * http://www.ssrc.ucsc.edu/Papers/weil-sc06.pdf
+ *
+ * LGPL2
+ */
+
+
+#define CRUSH_MAGIC 0x00010000ul /* for detecting algorithm revisions */
+
+
+#define CRUSH_MAX_DEPTH 10 /* max crush hierarchy depth */
+#define CRUSH_MAX_SET 10 /* max size of a mapping result */
+
+
+/*
+ * CRUSH uses user-defined "rules" to describe how inputs should be
+ * mapped to devices. A rule consists of sequence of steps to perform
+ * to generate the set of output devices.
+ */
+struct crush_rule_step {
+ __u32 op;
+ __s32 arg1;
+ __s32 arg2;
+};
+
+/* step op codes */
+enum {
+ CRUSH_RULE_NOOP = 0,
+ CRUSH_RULE_TAKE = 1, /* arg1 = value to start with */
+ CRUSH_RULE_CHOOSE_FIRSTN = 2, /* arg1 = num items to pick */
+ /* arg2 = type */
+ CRUSH_RULE_CHOOSE_INDEP = 3, /* same */
+ CRUSH_RULE_EMIT = 4, /* no args */
+ CRUSH_RULE_CHOOSE_LEAF_FIRSTN = 6,
+ CRUSH_RULE_CHOOSE_LEAF_INDEP = 7,
+};
+
+/*
+ * for specifying choose num (arg1) relative to the max parameter
+ * passed to do_rule
+ */
+#define CRUSH_CHOOSE_N 0
+#define CRUSH_CHOOSE_N_MINUS(x) (-(x))
+
+/*
+ * The rule mask is used to describe what the rule is intended for.
+ * Given a ruleset and size of output set, we search through the
+ * rule list for a matching rule_mask.
+ */
+struct crush_rule_mask {
+ __u8 ruleset;
+ __u8 type;
+ __u8 min_size;
+ __u8 max_size;
+};
+
+struct crush_rule {
+ __u32 len;
+ struct crush_rule_mask mask;
+ struct crush_rule_step steps[0];
+};
+
+#define crush_rule_size(len) (sizeof(struct crush_rule) + \
+ (len)*sizeof(struct crush_rule_step))
+
+
+
+/*
+ * A bucket is a named container of other items (either devices or
+ * other buckets). Items within a bucket are chosen using one of a
+ * few different algorithms. The table summarizes how the speed of
+ * each option measures up against mapping stability when items are
+ * added or removed.
+ *
+ * Bucket Alg Speed Additions Removals
+ * ------------------------------------------------
+ * uniform O(1) poor poor
+ * list O(n) optimal poor
+ * tree O(log n) good good
+ * straw O(n) optimal optimal
+ */
+enum {
+ CRUSH_BUCKET_UNIFORM = 1,
+ CRUSH_BUCKET_LIST = 2,
+ CRUSH_BUCKET_TREE = 3,
+ CRUSH_BUCKET_STRAW = 4
+};
+extern const char *crush_bucket_alg_name(int alg);
+
+struct crush_bucket {
+ __s32 id; /* this'll be negative */
+ __u16 type; /* non-zero; type=0 is reserved for devices */
+ __u8 alg; /* one of CRUSH_BUCKET_* */
+ __u8 hash; /* which hash function to use, CRUSH_HASH_* */
+ __u32 weight; /* 16-bit fixed point */
+ __u32 size; /* num items */
+ __s32 *items;
+
+ /*
+ * cached random permutation: used for uniform bucket and for
+ * the linear search fallback for the other bucket types.
+ */
+ __u32 perm_x; /* @x for which *perm is defined */
+ __u32 perm_n; /* num elements of *perm that are permuted/defined */
+ __u32 *perm;
+};
+
+struct crush_bucket_uniform {
+ struct crush_bucket h;
+ __u32 item_weight; /* 16-bit fixed point; all items equally weighted */
+};
+
+struct crush_bucket_list {
+ struct crush_bucket h;
+ __u32 *item_weights; /* 16-bit fixed point */
+ __u32 *sum_weights; /* 16-bit fixed point. element i is sum
+ of weights 0..i, inclusive */
+};
+
+struct crush_bucket_tree {
+ struct crush_bucket h; /* note: h.size is _tree_ size, not number of
+ actual items */
+ __u8 num_nodes;
+ __u32 *node_weights;
+};
+
+struct crush_bucket_straw {
+ struct crush_bucket h;
+ __u32 *item_weights; /* 16-bit fixed point */
+ __u32 *straws; /* 16-bit fixed point */
+};
+
+
+
+/*
+ * CRUSH map includes all buckets, rules, etc.
+ */
+struct crush_map {
+ struct crush_bucket **buckets;
+ struct crush_rule **rules;
+
+ /*
+ * Parent pointers to identify the parent bucket a device or
+ * bucket in the hierarchy. If an item appears more than
+ * once, this is the _last_ time it appeared (where buckets
+ * are processed in bucket id order, from -1 on down to
+ * -max_buckets.
+ */
+ __u32 *bucket_parents;
+ __u32 *device_parents;
+
+ __s32 max_buckets;
+ __u32 max_rules;
+ __s32 max_devices;
+};
+
+
+/* crush.c */
+extern int crush_get_bucket_item_weight(struct crush_bucket *b, int pos);
+extern void crush_calc_parents(struct crush_map *map);
+extern void crush_destroy_bucket_uniform(struct crush_bucket_uniform *b);
+extern void crush_destroy_bucket_list(struct crush_bucket_list *b);
+extern void crush_destroy_bucket_tree(struct crush_bucket_tree *b);
+extern void crush_destroy_bucket_straw(struct crush_bucket_straw *b);
+extern void crush_destroy_bucket(struct crush_bucket *b);
+extern void crush_destroy(struct crush_map *map);
+
+#endif
diff --git a/include/linux/crush/hash.h b/include/linux/crush/hash.h
new file mode 100644
index 00000000000..91e884230d5
--- /dev/null
+++ b/include/linux/crush/hash.h
@@ -0,0 +1,17 @@
+#ifndef CEPH_CRUSH_HASH_H
+#define CEPH_CRUSH_HASH_H
+
+#define CRUSH_HASH_RJENKINS1 0
+
+#define CRUSH_HASH_DEFAULT CRUSH_HASH_RJENKINS1
+
+extern const char *crush_hash_name(int type);
+
+extern __u32 crush_hash32(int type, __u32 a);
+extern __u32 crush_hash32_2(int type, __u32 a, __u32 b);
+extern __u32 crush_hash32_3(int type, __u32 a, __u32 b, __u32 c);
+extern __u32 crush_hash32_4(int type, __u32 a, __u32 b, __u32 c, __u32 d);
+extern __u32 crush_hash32_5(int type, __u32 a, __u32 b, __u32 c, __u32 d,
+ __u32 e);
+
+#endif
diff --git a/include/linux/crush/mapper.h b/include/linux/crush/mapper.h
new file mode 100644
index 00000000000..c46b99c18bb
--- /dev/null
+++ b/include/linux/crush/mapper.h
@@ -0,0 +1,20 @@
+#ifndef CEPH_CRUSH_MAPPER_H
+#define CEPH_CRUSH_MAPPER_H
+
+/*
+ * CRUSH functions for find rules and then mapping an input to an
+ * output set.
+ *
+ * LGPL2
+ */
+
+#include "crush.h"
+
+extern int crush_find_rule(struct crush_map *map, int pool, int type, int size);
+extern int crush_do_rule(struct crush_map *map,
+ int ruleno,
+ int x, int *result, int result_max,
+ int forcefeed, /* -1 for none */
+ __u32 *weights);
+
+#endif