| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1259883691-1042-3-git-send-email-sage@newdream.net>
Date: Thu, 3 Dec 2009 15:41:09 -0800
From: Sage Weil <sage@...dream.net>
To: linux-kernel@...r.kernel.org, linux-fsdevel@...r.kernel.org
Cc: Sage Weil <sage@...dream.net>
Subject: [PATCH 02/24] ceph: on-wire types
These headers describe the types used to exchange messages between the
Ceph client and various servers. All types are little-endian and
packed. These headers are shared between the kernel and userspace, so
all types are in terms of e.g. __u32.
Additionally, we define a few magic values to identify the current
version of the protocol(s) in use, so that discrepancies to be
detected on mount.
Signed-off-by: Sage Weil <sage@...dream.net>
---
fs/ceph/ceph_fs.c | 74 ++++++
fs/ceph/ceph_fs.h | 648 ++++++++++++++++++++++++++++++++++++++++++++++++
fs/ceph/ceph_strings.c | 176 +++++++++++++
fs/ceph/msgr.h | 167 +++++++++++++
fs/ceph/rados.h | 370 +++++++++++++++++++++++++++
5 files changed, 1435 insertions(+), 0 deletions(-)
create mode 100644 fs/ceph/ceph_fs.c
create mode 100644 fs/ceph/ceph_fs.h
create mode 100644 fs/ceph/ceph_strings.c
create mode 100644 fs/ceph/msgr.h
create mode 100644 fs/ceph/rados.h
diff --git a/fs/ceph/ceph_fs.c b/fs/ceph/ceph_fs.c
new file mode 100644
index 0000000..79d76bc
--- /dev/null
+++ b/fs/ceph/ceph_fs.c
@@ -0,0 +1,74 @@
+/*
+ * Some non-inline ceph helpers
+ */
+#include "types.h"
+
+/*
+ * return true if @layout appears to be valid
+ */
+int ceph_file_layout_is_valid(const struct ceph_file_layout *layout)
+{
+ __u32 su = le32_to_cpu(layout->fl_stripe_unit);
+ __u32 sc = le32_to_cpu(layout->fl_stripe_count);
+ __u32 os = le32_to_cpu(layout->fl_object_size);
+
+ /* stripe unit, object size must be non-zero, 64k increment */
+ if (!su || (su & (CEPH_MIN_STRIPE_UNIT-1)))
+ return 0;
+ if (!os || (os & (CEPH_MIN_STRIPE_UNIT-1)))
+ return 0;
+ /* object size must be a multiple of stripe unit */
+ if (os < su || os % su)
+ return 0;
+ /* stripe count must be non-zero */
+ if (!sc)
+ return 0;
+ return 1;
+}
+
+
+int ceph_flags_to_mode(int flags)
+{
+#ifdef O_DIRECTORY /* fixme */
+ if ((flags & O_DIRECTORY) == O_DIRECTORY)
+ return CEPH_FILE_MODE_PIN;
+#endif
+#ifdef O_LAZY
+ if (flags & O_LAZY)
+ return CEPH_FILE_MODE_LAZY;
+#endif
+ if ((flags & O_APPEND) == O_APPEND)
+ flags |= O_WRONLY;
+
+ flags &= O_ACCMODE;
+ if ((flags & O_RDWR) == O_RDWR)
+ return CEPH_FILE_MODE_RDWR;
+ if ((flags & O_WRONLY) == O_WRONLY)
+ return CEPH_FILE_MODE_WR;
+ return CEPH_FILE_MODE_RD;
+}
+
+int ceph_caps_for_mode(int mode)
+{
+ switch (mode) {
+ case CEPH_FILE_MODE_PIN:
+ return CEPH_CAP_PIN;
+ case CEPH_FILE_MODE_RD:
+ return CEPH_CAP_PIN | CEPH_CAP_FILE_SHARED |
+ CEPH_CAP_FILE_RD | CEPH_CAP_FILE_CACHE;
+ case CEPH_FILE_MODE_RDWR:
+ return CEPH_CAP_PIN | CEPH_CAP_FILE_SHARED |
+ CEPH_CAP_FILE_EXCL |
+ CEPH_CAP_FILE_RD | CEPH_CAP_FILE_CACHE |
+ CEPH_CAP_FILE_WR | CEPH_CAP_FILE_BUFFER |
+ CEPH_CAP_AUTH_SHARED | CEPH_CAP_AUTH_EXCL |
+ CEPH_CAP_XATTR_SHARED | CEPH_CAP_XATTR_EXCL;
+ case CEPH_FILE_MODE_WR:
+ return CEPH_CAP_PIN | CEPH_CAP_FILE_SHARED |
+ CEPH_CAP_FILE_EXCL |
+ CEPH_CAP_FILE_WR | CEPH_CAP_FILE_BUFFER |
+ CEPH_CAP_AUTH_SHARED | CEPH_CAP_AUTH_EXCL |
+ CEPH_CAP_XATTR_SHARED | CEPH_CAP_XATTR_EXCL;
+ }
+ return 0;
+}
diff --git a/fs/ceph/ceph_fs.h b/fs/ceph/ceph_fs.h
new file mode 100644
index 0000000..699196a
--- /dev/null
+++ b/fs/ceph/ceph_fs.h
@@ -0,0 +1,648 @@
+/*
+ * ceph_fs.h - Ceph constants and data types to share between kernel and
+ * user space.
+ *
+ * Most types in this file are defined as little-endian, and are
+ * primarily intended to describe data structures that pass over the
+ * wire or that are stored on disk.
+ *
+ * LGPL2
+ */
+
+#ifndef _FS_CEPH_CEPH_FS_H
+#define _FS_CEPH_CEPH_FS_H
+
+#include "msgr.h"
+#include "rados.h"
+
+/*
+ * Ceph release version
+ */
+#define CEPH_VERSION_MAJOR 0
+#define CEPH_VERSION_MINOR 17
+#define CEPH_VERSION_PATCH 0
+
+#define _CEPH_STRINGIFY(x) #x
+#define CEPH_STRINGIFY(x) _CEPH_STRINGIFY(x)
+#define CEPH_MAKE_VERSION(x, y, z) CEPH_STRINGIFY(x) "." CEPH_STRINGIFY(y) \
+ "." CEPH_STRINGIFY(z)
+#define CEPH_VERSION CEPH_MAKE_VERSION(CEPH_VERSION_MAJOR, \
+ CEPH_VERSION_MINOR, CEPH_VERSION_PATCH)
+
+/*
+ * subprotocol versions. when specific messages types or high-level
+ * protocols change, bump the affected components. we keep rev
+ * internal cluster protocols separately from the public,
+ * client-facing protocol.
+ */
+#define CEPH_OSD_PROTOCOL 7 /* cluster internal */
+#define CEPH_MDS_PROTOCOL 9 /* cluster internal */
+#define CEPH_MON_PROTOCOL 5 /* cluster internal */
+#define CEPH_OSDC_PROTOCOL 22 /* server/client */
+#define CEPH_MDSC_PROTOCOL 30 /* server/client */
+#define CEPH_MONC_PROTOCOL 15 /* server/client */
+
+
+#define CEPH_INO_ROOT 1
+#define CEPH_INO_CEPH 2 /* hidden .ceph dir */
+
+/* arbitrary limit on max # of monitors (cluster of 3 is typical) */
+#define CEPH_MAX_MON 31
+
+
+
+/*
+ * ceph_file_layout - describe data layout for a file/inode
+ */
+struct ceph_file_layout {
+ /* file -> object mapping */
+ __le32 fl_stripe_unit; /* stripe unit, in bytes. must be multiple
+ of page size. */
+ __le32 fl_stripe_count; /* over this many objects */
+ __le32 fl_object_size; /* until objects are this big, then move to
+ new objects */
+ __le32 fl_cas_hash; /* 0 = none; 1 = sha256 */
+
+ /* pg -> disk layout */
+ __le32 fl_object_stripe_unit; /* for per-object parity, if any */
+
+ /* object -> pg layout */
+ __le32 fl_pg_preferred; /* preferred primary for pg (-1 for none) */
+ __le32 fl_pg_pool; /* namespace, crush ruleset, rep level */
+} __attribute__ ((packed));
+
+#define CEPH_MIN_STRIPE_UNIT 65536
+
+int ceph_file_layout_is_valid(const struct ceph_file_layout *layout);
+
+
+/* crypto algorithms */
+#define CEPH_CRYPTO_NONE 0x0
+#define CEPH_CRYPTO_AES 0x1
+
+/* security/authentication protocols */
+#define CEPH_AUTH_UNKNOWN 0x0
+#define CEPH_AUTH_NONE 0x1
+#define CEPH_AUTH_CEPHX 0x2
+
+
+/*********************************************
+ * message layer
+ */
+
+/*
+ * message types
+ */
+
+/* misc */
+#define CEPH_MSG_SHUTDOWN 1
+#define CEPH_MSG_PING 2
+
+/* client <-> monitor */
+#define CEPH_MSG_MON_MAP 4
+#define CEPH_MSG_MON_GET_MAP 5
+#define CEPH_MSG_STATFS 13
+#define CEPH_MSG_STATFS_REPLY 14
+#define CEPH_MSG_MON_SUBSCRIBE 15
+#define CEPH_MSG_MON_SUBSCRIBE_ACK 16
+#define CEPH_MSG_AUTH 17
+#define CEPH_MSG_AUTH_REPLY 18
+
+/* client <-> mds */
+#define CEPH_MSG_MDS_MAP 21
+
+#define CEPH_MSG_CLIENT_SESSION 22
+#define CEPH_MSG_CLIENT_RECONNECT 23
+
+#define CEPH_MSG_CLIENT_REQUEST 24
+#define CEPH_MSG_CLIENT_REQUEST_FORWARD 25
+#define CEPH_MSG_CLIENT_REPLY 26
+#define CEPH_MSG_CLIENT_CAPS 0x310
+#define CEPH_MSG_CLIENT_LEASE 0x311
+#define CEPH_MSG_CLIENT_SNAP 0x312
+#define CEPH_MSG_CLIENT_CAPRELEASE 0x313
+
+/* osd */
+#define CEPH_MSG_OSD_MAP 41
+#define CEPH_MSG_OSD_OP 42
+#define CEPH_MSG_OSD_OPREPLY 43
+
+struct ceph_mon_request_header {
+ __le64 have_version;
+ __le16 session_mon;
+ __le64 session_mon_tid;
+} __attribute__ ((packed));
+
+struct ceph_mon_statfs {
+ struct ceph_mon_request_header monhdr;
+ struct ceph_fsid fsid;
+ __le64 tid;
+} __attribute__ ((packed));
+
+struct ceph_statfs {
+ __le64 kb, kb_used, kb_avail;
+ __le64 num_objects;
+} __attribute__ ((packed));
+
+struct ceph_mon_statfs_reply {
+ struct ceph_fsid fsid;
+ __le64 tid;
+ __le64 version;
+ struct ceph_statfs st;
+} __attribute__ ((packed));
+
+struct ceph_osd_getmap {
+ struct ceph_mon_request_header monhdr;
+ struct ceph_fsid fsid;
+ __le32 start;
+} __attribute__ ((packed));
+
+struct ceph_mds_getmap {
+ struct ceph_mon_request_header monhdr;
+ struct ceph_fsid fsid;
+} __attribute__ ((packed));
+
+struct ceph_client_mount {
+ struct ceph_mon_request_header monhdr;
+} __attribute__ ((packed));
+
+struct ceph_mon_subscribe_item {
+ __le64 have_version; __le64 have;
+ __u8 onetime;
+} __attribute__ ((packed));
+
+struct ceph_mon_subscribe_ack {
+ __le32 duration; /* seconds */
+ struct ceph_fsid fsid;
+} __attribute__ ((packed));
+
+/*
+ * mds states
+ * > 0 -> in
+ * <= 0 -> out
+ */
+#define CEPH_MDS_STATE_DNE 0 /* down, does not exist. */
+#define CEPH_MDS_STATE_STOPPED -1 /* down, once existed, but no subtrees.
+ empty log. */
+#define CEPH_MDS_STATE_BOOT -4 /* up, boot announcement. */
+#define CEPH_MDS_STATE_STANDBY -5 /* up, idle. waiting for assignment. */
+#define CEPH_MDS_STATE_CREATING -6 /* up, creating MDS instance. */
+#define CEPH_MDS_STATE_STARTING -7 /* up, starting previously stopped mds */
+#define CEPH_MDS_STATE_STANDBY_REPLAY -8 /* up, tailing active node's journal */
+
+#define CEPH_MDS_STATE_REPLAY 8 /* up, replaying journal. */
+#define CEPH_MDS_STATE_RESOLVE 9 /* up, disambiguating distributed
+ operations (import, rename, etc.) */
+#define CEPH_MDS_STATE_RECONNECT 10 /* up, reconnect to clients */
+#define CEPH_MDS_STATE_REJOIN 11 /* up, rejoining distributed cache */
+#define CEPH_MDS_STATE_CLIENTREPLAY 12 /* up, replaying client operations */
+#define CEPH_MDS_STATE_ACTIVE 13 /* up, active */
+#define CEPH_MDS_STATE_STOPPING 14 /* up, but exporting metadata */
+
+extern const char *ceph_mds_state_name(int s);
+
+
+/*
+ * metadata lock types.
+ * - these are bitmasks.. we can compose them
+ * - they also define the lock ordering by the MDS
+ * - a few of these are internal to the mds
+ */
+#define CEPH_LOCK_DN 1
+#define CEPH_LOCK_ISNAP 2
+#define CEPH_LOCK_IVERSION 4 /* mds internal */
+#define CEPH_LOCK_IFILE 8 /* mds internal */
+#define CEPH_LOCK_IAUTH 32
+#define CEPH_LOCK_ILINK 64
+#define CEPH_LOCK_IDFT 128 /* dir frag tree */
+#define CEPH_LOCK_INEST 256 /* mds internal */
+#define CEPH_LOCK_IXATTR 512
+#define CEPH_LOCK_INO 2048 /* immutable inode bits; not a lock */
+
+/* client_session ops */
+enum {
+ CEPH_SESSION_REQUEST_OPEN,
+ CEPH_SESSION_OPEN,
+ CEPH_SESSION_REQUEST_CLOSE,
+ CEPH_SESSION_CLOSE,
+ CEPH_SESSION_REQUEST_RENEWCAPS,
+ CEPH_SESSION_RENEWCAPS,
+ CEPH_SESSION_STALE,
+ CEPH_SESSION_RECALL_STATE,
+};
+
+extern const char *ceph_session_op_name(int op);
+
+struct ceph_mds_session_head {
+ __le32 op;
+ __le64 seq;
+ struct ceph_timespec stamp;
+ __le32 max_caps, max_leases;
+} __attribute__ ((packed));
+
+/* client_request */
+/*
+ * metadata ops.
+ * & 0x001000 -> write op
+ * & 0x010000 -> follow symlink (e.g. stat(), not lstat()).
+ & & 0x100000 -> use weird ino/path trace
+ */
+#define CEPH_MDS_OP_WRITE 0x001000
+enum {
+ CEPH_MDS_OP_LOOKUP = 0x00100,
+ CEPH_MDS_OP_GETATTR = 0x00101,
+ CEPH_MDS_OP_LOOKUPHASH = 0x00102,
+ CEPH_MDS_OP_LOOKUPPARENT = 0x00103,
+
+ CEPH_MDS_OP_SETXATTR = 0x01105,
+ CEPH_MDS_OP_RMXATTR = 0x01106,
+ CEPH_MDS_OP_SETLAYOUT = 0x01107,
+ CEPH_MDS_OP_SETATTR = 0x01108,
+
+ CEPH_MDS_OP_MKNOD = 0x01201,
+ CEPH_MDS_OP_LINK = 0x01202,
+ CEPH_MDS_OP_UNLINK = 0x01203,
+ CEPH_MDS_OP_RENAME = 0x01204,
+ CEPH_MDS_OP_MKDIR = 0x01220,
+ CEPH_MDS_OP_RMDIR = 0x01221,
+ CEPH_MDS_OP_SYMLINK = 0x01222,
+
+ CEPH_MDS_OP_CREATE = 0x00301,
+ CEPH_MDS_OP_OPEN = 0x00302,
+ CEPH_MDS_OP_READDIR = 0x00305,
+
+ CEPH_MDS_OP_LOOKUPSNAP = 0x00400,
+ CEPH_MDS_OP_MKSNAP = 0x01400,
+ CEPH_MDS_OP_RMSNAP = 0x01401,
+ CEPH_MDS_OP_LSSNAP = 0x00402,
+};
+
+extern const char *ceph_mds_op_name(int op);
+
+
+#define CEPH_SETATTR_MODE 1
+#define CEPH_SETATTR_UID 2
+#define CEPH_SETATTR_GID 4
+#define CEPH_SETATTR_MTIME 8
+#define CEPH_SETATTR_ATIME 16
+#define CEPH_SETATTR_SIZE 32
+#define CEPH_SETATTR_CTIME 64
+
+union ceph_mds_request_args {
+ struct {
+ __le32 mask; /* CEPH_CAP_* */
+ } __attribute__ ((packed)) getattr;
+ struct {
+ __le32 mode;
+ __le32 uid;
+ __le32 gid;
+ struct ceph_timespec mtime;
+ struct ceph_timespec atime;
+ __le64 size, old_size; /* old_size needed by truncate */
+ __le32 mask; /* CEPH_SETATTR_* */
+ } __attribute__ ((packed)) setattr;
+ struct {
+ __le32 frag; /* which dir fragment */
+ __le32 max_entries; /* how many dentries to grab */
+ } __attribute__ ((packed)) readdir;
+ struct {
+ __le32 mode;
+ __le32 rdev;
+ } __attribute__ ((packed)) mknod;
+ struct {
+ __le32 mode;
+ } __attribute__ ((packed)) mkdir;
+ struct {
+ __le32 flags;
+ __le32 mode;
+ __le32 stripe_unit; /* layout for newly created file */
+ __le32 stripe_count; /* ... */
+ __le32 object_size;
+ __le32 file_replication;
+ __le32 preferred;
+ } __attribute__ ((packed)) open;
+ struct {
+ __le32 flags;
+ } __attribute__ ((packed)) setxattr;
+ struct {
+ struct ceph_file_layout layout;
+ } __attribute__ ((packed)) setlayout;
+} __attribute__ ((packed));
+
+#define CEPH_MDS_FLAG_REPLAY 1 /* this is a replayed op */
+#define CEPH_MDS_FLAG_WANT_DENTRY 2 /* want dentry in reply */
+
+struct ceph_mds_request_head {
+ __le64 tid, oldest_client_tid;
+ __le32 mdsmap_epoch; /* on client */
+ __le32 flags; /* CEPH_MDS_FLAG_* */
+ __u8 num_retry, num_fwd; /* count retry, fwd attempts */
+ __le16 num_releases; /* # include cap/lease release records */
+ __le32 op; /* mds op code */
+ __le32 caller_uid, caller_gid;
+ __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 {
+ __le64 tid;
+ __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));
+
+/* 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 /* goes at the end (uses >2 cap bits) */
+
+#define CEPH_CAP_BITS 16
+
+/* 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)
+
+/* 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_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;
+ __le64 client_tid; /* for FLUSH(SNAP) -> FLUSH(SNAP)_ACK */
+
+ /* 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 size;
+ struct ceph_timespec mtime, atime;
+ __le64 snaprealm;
+ __le64 pathbase; /* base ino for our path to this ino */
+} __attribute__ ((packed));
+/* followed by encoded string */
+
+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/fs/ceph/ceph_strings.c b/fs/ceph/ceph_strings.c
new file mode 100644
index 0000000..8e4be6a
--- /dev/null
+++ b/fs/ceph/ceph_strings.c
@@ -0,0 +1,176 @@
+/*
+ * Ceph string constants
+ */
+#include "types.h"
+
+const char *ceph_entity_type_name(int type)
+{
+ switch (type) {
+ case CEPH_ENTITY_TYPE_MDS: return "mds";
+ case CEPH_ENTITY_TYPE_OSD: return "osd";
+ case CEPH_ENTITY_TYPE_MON: return "mon";
+ case CEPH_ENTITY_TYPE_CLIENT: return "client";
+ case CEPH_ENTITY_TYPE_ADMIN: return "admin";
+ case CEPH_ENTITY_TYPE_AUTH: return "auth";
+ default: return "unknown";
+ }
+}
+
+const char *ceph_osd_op_name(int op)
+{
+ switch (op) {
+ case CEPH_OSD_OP_READ: return "read";
+ case CEPH_OSD_OP_STAT: return "stat";
+
+ case CEPH_OSD_OP_MASKTRUNC: return "masktrunc";
+
+ case CEPH_OSD_OP_WRITE: return "write";
+ case CEPH_OSD_OP_DELETE: return "delete";
+ case CEPH_OSD_OP_TRUNCATE: return "truncate";
+ case CEPH_OSD_OP_ZERO: return "zero";
+ case CEPH_OSD_OP_WRITEFULL: return "writefull";
+
+ case CEPH_OSD_OP_APPEND: return "append";
+ case CEPH_OSD_OP_STARTSYNC: return "startsync";
+ case CEPH_OSD_OP_SETTRUNC: return "settrunc";
+ case CEPH_OSD_OP_TRIMTRUNC: return "trimtrunc";
+
+ case CEPH_OSD_OP_TMAPUP: return "tmapup";
+ case CEPH_OSD_OP_TMAPGET: return "tmapget";
+ case CEPH_OSD_OP_TMAPPUT: return "tmapput";
+
+ case CEPH_OSD_OP_GETXATTR: return "getxattr";
+ case CEPH_OSD_OP_GETXATTRS: return "getxattrs";
+ case CEPH_OSD_OP_SETXATTR: return "setxattr";
+ case CEPH_OSD_OP_SETXATTRS: return "setxattrs";
+ case CEPH_OSD_OP_RESETXATTRS: return "resetxattrs";
+ case CEPH_OSD_OP_RMXATTR: return "rmxattr";
+
+ case CEPH_OSD_OP_PULL: return "pull";
+ case CEPH_OSD_OP_PUSH: return "push";
+ case CEPH_OSD_OP_BALANCEREADS: return "balance-reads";
+ case CEPH_OSD_OP_UNBALANCEREADS: return "unbalance-reads";
+ case CEPH_OSD_OP_SCRUB: return "scrub";
+
+ case CEPH_OSD_OP_WRLOCK: return "wrlock";
+ case CEPH_OSD_OP_WRUNLOCK: return "wrunlock";
+ case CEPH_OSD_OP_RDLOCK: return "rdlock";
+ case CEPH_OSD_OP_RDUNLOCK: return "rdunlock";
+ case CEPH_OSD_OP_UPLOCK: return "uplock";
+ case CEPH_OSD_OP_DNLOCK: return "dnlock";
+
+ case CEPH_OSD_OP_CALL: return "call";
+
+ case CEPH_OSD_OP_PGLS: return "pgls";
+ }
+ return "???";
+}
+
+const char *ceph_mds_state_name(int s)
+{
+ switch (s) {
+ /* down and out */
+ case CEPH_MDS_STATE_DNE: return "down:dne";
+ case CEPH_MDS_STATE_STOPPED: return "down:stopped";
+ /* up and out */
+ case CEPH_MDS_STATE_BOOT: return "up:boot";
+ case CEPH_MDS_STATE_STANDBY: return "up:standby";
+ case CEPH_MDS_STATE_STANDBY_REPLAY: return "up:standby-replay";
+ case CEPH_MDS_STATE_CREATING: return "up:creating";
+ case CEPH_MDS_STATE_STARTING: return "up:starting";
+ /* up and in */
+ case CEPH_MDS_STATE_REPLAY: return "up:replay";
+ case CEPH_MDS_STATE_RESOLVE: return "up:resolve";
+ case CEPH_MDS_STATE_RECONNECT: return "up:reconnect";
+ case CEPH_MDS_STATE_REJOIN: return "up:rejoin";
+ case CEPH_MDS_STATE_CLIENTREPLAY: return "up:clientreplay";
+ case CEPH_MDS_STATE_ACTIVE: return "up:active";
+ case CEPH_MDS_STATE_STOPPING: return "up:stopping";
+ }
+ return "???";
+}
+
+const char *ceph_session_op_name(int op)
+{
+ switch (op) {
+ case CEPH_SESSION_REQUEST_OPEN: return "request_open";
+ case CEPH_SESSION_OPEN: return "open";
+ case CEPH_SESSION_REQUEST_CLOSE: return "request_close";
+ case CEPH_SESSION_CLOSE: return "close";
+ case CEPH_SESSION_REQUEST_RENEWCAPS: return "request_renewcaps";
+ case CEPH_SESSION_RENEWCAPS: return "renewcaps";
+ case CEPH_SESSION_STALE: return "stale";
+ case CEPH_SESSION_RECALL_STATE: return "recall_state";
+ }
+ return "???";
+}
+
+const char *ceph_mds_op_name(int op)
+{
+ switch (op) {
+ case CEPH_MDS_OP_LOOKUP: return "lookup";
+ case CEPH_MDS_OP_LOOKUPHASH: return "lookuphash";
+ case CEPH_MDS_OP_LOOKUPPARENT: return "lookupparent";
+ case CEPH_MDS_OP_GETATTR: return "getattr";
+ case CEPH_MDS_OP_SETXATTR: return "setxattr";
+ case CEPH_MDS_OP_SETATTR: return "setattr";
+ case CEPH_MDS_OP_RMXATTR: return "rmxattr";
+ case CEPH_MDS_OP_READDIR: return "readdir";
+ case CEPH_MDS_OP_MKNOD: return "mknod";
+ case CEPH_MDS_OP_LINK: return "link";
+ case CEPH_MDS_OP_UNLINK: return "unlink";
+ case CEPH_MDS_OP_RENAME: return "rename";
+ case CEPH_MDS_OP_MKDIR: return "mkdir";
+ case CEPH_MDS_OP_RMDIR: return "rmdir";
+ case CEPH_MDS_OP_SYMLINK: return "symlink";
+ case CEPH_MDS_OP_CREATE: return "create";
+ case CEPH_MDS_OP_OPEN: return "open";
+ case CEPH_MDS_OP_LOOKUPSNAP: return "lookupsnap";
+ case CEPH_MDS_OP_LSSNAP: return "lssnap";
+ case CEPH_MDS_OP_MKSNAP: return "mksnap";
+ case CEPH_MDS_OP_RMSNAP: return "rmsnap";
+ }
+ return "???";
+}
+
+const char *ceph_cap_op_name(int op)
+{
+ switch (op) {
+ case CEPH_CAP_OP_GRANT: return "grant";
+ case CEPH_CAP_OP_REVOKE: return "revoke";
+ case CEPH_CAP_OP_TRUNC: return "trunc";
+ case CEPH_CAP_OP_EXPORT: return "export";
+ case CEPH_CAP_OP_IMPORT: return "import";
+ case CEPH_CAP_OP_UPDATE: return "update";
+ case CEPH_CAP_OP_DROP: return "drop";
+ case CEPH_CAP_OP_FLUSH: return "flush";
+ case CEPH_CAP_OP_FLUSH_ACK: return "flush_ack";
+ case CEPH_CAP_OP_FLUSHSNAP: return "flushsnap";
+ case CEPH_CAP_OP_FLUSHSNAP_ACK: return "flushsnap_ack";
+ case CEPH_CAP_OP_RELEASE: return "release";
+ case CEPH_CAP_OP_RENEW: return "renew";
+ }
+ return "???";
+}
+
+const char *ceph_lease_op_name(int o)
+{
+ switch (o) {
+ case CEPH_MDS_LEASE_REVOKE: return "revoke";
+ case CEPH_MDS_LEASE_RELEASE: return "release";
+ case CEPH_MDS_LEASE_RENEW: return "renew";
+ case CEPH_MDS_LEASE_REVOKE_ACK: return "revoke_ack";
+ }
+ return "???";
+}
+
+const char *ceph_snap_op_name(int o)
+{
+ switch (o) {
+ case CEPH_SNAP_OP_UPDATE: return "update";
+ case CEPH_SNAP_OP_CREATE: return "create";
+ case CEPH_SNAP_OP_DESTROY: return "destroy";
+ case CEPH_SNAP_OP_SPLIT: return "split";
+ }
+ return "???";
+}
diff --git a/fs/ceph/msgr.h b/fs/ceph/msgr.h
new file mode 100644
index 0000000..c758e8f
--- /dev/null
+++ b/fs/ceph/msgr.h
@@ -0,0 +1,167 @@
+#ifndef __MSGR_H
+#define __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 v024"
+#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_ADMIN 0x10
+#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 erank; /* entity's rank in process */
+ __le32 nonce; /* unique id for process (e.g. pid) */
+ struct sockaddr_storage in_addr;
+} __attribute__ ((packed));
+
+static inline bool ceph_entity_addr_is_local(const struct ceph_entity_addr *a,
+ const struct ceph_entity_addr *b)
+{
+ return a->nonce == b->nonce &&
+ memcmp(&a->in_addr, &b->in_addr, sizeof(a->in_addr)) == 0;
+}
+
+static inline bool ceph_entity_addr_equal(const struct ceph_entity_addr *a,
+ const struct ceph_entity_addr *b)
+{
+ return memcmp(a, b, sizeof(*a)) == 0;
+}
+
+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 */
+
+
+/*
+ * connection negotiation
+ */
+struct ceph_msg_connect {
+ __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;
+ __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 {
+ __le64 seq; /* message seq# for this session */
+ __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 dst_erank;
+ __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/fs/ceph/rados.h b/fs/ceph/rados.h
new file mode 100644
index 0000000..12bfb2f
--- /dev/null
+++ b/fs/ceph/rados.h
@@ -0,0 +1,370 @@
+#ifndef __RADOS_H
+#define __RADOS_H
+
+/*
+ * Data types for the Ceph distributed object storage layer RADOS
+ * (Reliable Autonomic Distributed Object Store).
+ */
+
+#include "msgr.h"
+
+/*
+ * fs id
+ */
+struct ceph_fsid {
+ unsigned char fsid[16];
+};
+
+static inline int ceph_fsid_compare(const struct ceph_fsid *a,
+ const struct ceph_fsid *b)
+{
+ return memcmp(a, b, sizeof(*a));
+}
+
+/*
+ * ino, object, etc.
+ */
+typedef __le64 ceph_snapid_t;
+#define CEPH_SNAPDIR ((__u64)(-1)) /* reserved for hidden .snap dir */
+#define CEPH_NOSNAP ((__u64)(-2)) /* "head", "live" revision */
+#define CEPH_MAXSNAP ((__u64)(-3)) /* largest valid snapid */
+
+struct ceph_timespec {
+ __le32 tv_sec;
+ __le32 tv_nsec;
+} __attribute__ ((packed));
+
+
+/*
+ * object layout - how objects are mapped into PGs
+ */
+#define CEPH_OBJECT_LAYOUT_HASH 1
+#define CEPH_OBJECT_LAYOUT_LINEAR 2
+#define CEPH_OBJECT_LAYOUT_HASHINO 3
+
+/*
+ * pg layout -- how PGs are mapped onto (sets of) OSDs
+ */
+#define CEPH_PG_LAYOUT_CRUSH 0
+#define CEPH_PG_LAYOUT_HASH 1
+#define CEPH_PG_LAYOUT_LINEAR 2
+#define CEPH_PG_LAYOUT_HYBRID 3
+
+
+/*
+ * placement group.
+ * we encode this into one __le64.
+ */
+struct ceph_pg {
+ __le16 preferred; /* preferred primary osd */
+ __le16 ps; /* placement seed */
+ __le32 pool; /* object pool */
+} __attribute__ ((packed));
+
+/*
+ * pg_pool is a set of pgs storing a pool of objects
+ *
+ * pg_num -- base number of pseudorandomly placed pgs
+ *
+ * pgp_num -- effective number when calculating pg placement. this
+ * is used for pg_num increases. new pgs result in data being "split"
+ * into new pgs. for this to proceed smoothly, new pgs are intiially
+ * colocated with their parents; that is, pgp_num doesn't increase
+ * until the new pgs have successfully split. only _then_ are the new
+ * pgs placed independently.
+ *
+ * lpg_num -- localized pg count (per device). replicas are randomly
+ * selected.
+ *
+ * lpgp_num -- as above.
+ */
+#define CEPH_PG_TYPE_REP 1
+#define CEPH_PG_TYPE_RAID4 2
+struct ceph_pg_pool {
+ __u8 type; /* CEPH_PG_TYPE_* */
+ __u8 size; /* number of osds in each pg */
+ __u8 crush_ruleset; /* crush placement rule */
+ __u8 object_hash; /* hash mapping object name to ps */
+ __le32 pg_num, pgp_num; /* number of pg's */
+ __le32 lpg_num, lpgp_num; /* number of localized pg's */
+ __le32 last_change; /* most recent epoch changed */
+ __le64 snap_seq; /* seq for per-pool snapshot */
+ __le32 snap_epoch; /* epoch of last snap */
+ __le32 num_snaps;
+ __le32 num_removed_snap_intervals;
+} __attribute__ ((packed));
+
+/*
+ * stable_mod func is used to control number of placement groups.
+ * similar to straight-up modulo, but produces a stable mapping as b
+ * increases over time. b is the number of bins, and bmask is the
+ * containing power of 2 minus 1.
+ *
+ * b <= bmask and bmask=(2**n)-1
+ * e.g., b=12 -> bmask=15, b=123 -> bmask=127
+ */
+static inline int ceph_stable_mod(int x, int b, int bmask)
+{
+ if ((x & bmask) < b)
+ return x & bmask;
+ else
+ return x & (bmask >> 1);
+}
+
+/*
+ * object layout - how a given object should be stored.
+ */
+struct ceph_object_layout {
+ struct ceph_pg ol_pgid; /* raw pg, with _full_ ps precision. */
+ __le32 ol_stripe_unit; /* for per-object parity, if any */
+} __attribute__ ((packed));
+
+/*
+ * compound epoch+version, used by storage layer to serialize mutations
+ */
+struct ceph_eversion {
+ __le32 epoch;
+ __le64 version;
+} __attribute__ ((packed));
+
+/*
+ * osd map bits
+ */
+
+/* status bits */
+#define CEPH_OSD_EXISTS 1
+#define CEPH_OSD_UP 2
+
+/* osd weights. fixed point value: 0x10000 == 1.0 ("in"), 0 == "out" */
+#define CEPH_OSD_IN 0x10000
+#define CEPH_OSD_OUT 0
+
+
+/*
+ * osd map flag bits
+ */
+#define CEPH_OSDMAP_NEARFULL (1<<0) /* sync writes (near ENOSPC) */
+#define CEPH_OSDMAP_FULL (1<<1) /* no data writes (ENOSPC) */
+#define CEPH_OSDMAP_PAUSERD (1<<2) /* pause all reads */
+#define CEPH_OSDMAP_PAUSEWR (1<<3) /* pause all writes */
+#define CEPH_OSDMAP_PAUSEREC (1<<4) /* pause recovery */
+
+/*
+ * osd ops
+ */
+#define CEPH_OSD_OP_MODE 0xf000
+#define CEPH_OSD_OP_MODE_RD 0x1000
+#define CEPH_OSD_OP_MODE_WR 0x2000
+#define CEPH_OSD_OP_MODE_RMW 0x3000
+#define CEPH_OSD_OP_MODE_SUB 0x4000
+
+#define CEPH_OSD_OP_TYPE 0x0f00
+#define CEPH_OSD_OP_TYPE_LOCK 0x0100
+#define CEPH_OSD_OP_TYPE_DATA 0x0200
+#define CEPH_OSD_OP_TYPE_ATTR 0x0300
+#define CEPH_OSD_OP_TYPE_EXEC 0x0400
+#define CEPH_OSD_OP_TYPE_PG 0x0500
+
+enum {
+ /** data **/
+ /* read */
+ CEPH_OSD_OP_READ = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 1,
+ CEPH_OSD_OP_STAT = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 2,
+
+ /* fancy read */
+ CEPH_OSD_OP_MASKTRUNC = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 4,
+
+ /* write */
+ CEPH_OSD_OP_WRITE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 1,
+ CEPH_OSD_OP_WRITEFULL = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 2,
+ CEPH_OSD_OP_TRUNCATE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 3,
+ CEPH_OSD_OP_ZERO = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 4,
+ CEPH_OSD_OP_DELETE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 5,
+
+ /* fancy write */
+ CEPH_OSD_OP_APPEND = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 6,
+ CEPH_OSD_OP_STARTSYNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 7,
+ CEPH_OSD_OP_SETTRUNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 8,
+ CEPH_OSD_OP_TRIMTRUNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 9,
+
+ CEPH_OSD_OP_TMAPUP = CEPH_OSD_OP_MODE_RMW | CEPH_OSD_OP_TYPE_DATA | 10,
+ CEPH_OSD_OP_TMAPPUT = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 11,
+ CEPH_OSD_OP_TMAPGET = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 12,
+
+ CEPH_OSD_OP_CREATE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 13,
+
+ /** attrs **/
+ /* read */
+ CEPH_OSD_OP_GETXATTR = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 1,
+ CEPH_OSD_OP_GETXATTRS = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 2,
+
+ /* write */
+ CEPH_OSD_OP_SETXATTR = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 1,
+ CEPH_OSD_OP_SETXATTRS = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 2,
+ CEPH_OSD_OP_RESETXATTRS = CEPH_OSD_OP_MODE_WR|CEPH_OSD_OP_TYPE_ATTR | 3,
+ CEPH_OSD_OP_RMXATTR = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 4,
+
+ /** subop **/
+ CEPH_OSD_OP_PULL = CEPH_OSD_OP_MODE_SUB | 1,
+ CEPH_OSD_OP_PUSH = CEPH_OSD_OP_MODE_SUB | 2,
+ CEPH_OSD_OP_BALANCEREADS = CEPH_OSD_OP_MODE_SUB | 3,
+ CEPH_OSD_OP_UNBALANCEREADS = CEPH_OSD_OP_MODE_SUB | 4,
+ CEPH_OSD_OP_SCRUB = CEPH_OSD_OP_MODE_SUB | 5,
+
+ /** lock **/
+ CEPH_OSD_OP_WRLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 1,
+ CEPH_OSD_OP_WRUNLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 2,
+ CEPH_OSD_OP_RDLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 3,
+ CEPH_OSD_OP_RDUNLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 4,
+ CEPH_OSD_OP_UPLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 5,
+ CEPH_OSD_OP_DNLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 6,
+
+ /** exec **/
+ CEPH_OSD_OP_CALL = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_EXEC | 1,
+
+ /** pg **/
+ CEPH_OSD_OP_PGLS = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_PG | 1,
+};
+
+static inline int ceph_osd_op_type_lock(int op)
+{
+ return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_LOCK;
+}
+static inline int ceph_osd_op_type_data(int op)
+{
+ return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_DATA;
+}
+static inline int ceph_osd_op_type_attr(int op)
+{
+ return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_ATTR;
+}
+static inline int ceph_osd_op_type_exec(int op)
+{
+ return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_EXEC;
+}
+static inline int ceph_osd_op_type_pg(int op)
+{
+ return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_PG;
+}
+
+static inline int ceph_osd_op_mode_subop(int op)
+{
+ return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_SUB;
+}
+static inline int ceph_osd_op_mode_read(int op)
+{
+ return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_RD;
+}
+static inline int ceph_osd_op_mode_modify(int op)
+{
+ return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_WR;
+}
+
+#define CEPH_OSD_TMAP_HDR 'h'
+#define CEPH_OSD_TMAP_SET 's'
+#define CEPH_OSD_TMAP_RM 'r'
+
+extern const char *ceph_osd_op_name(int op);
+
+
+/*
+ * osd op flags
+ *
+ * An op may be READ, WRITE, or READ|WRITE.
+ */
+enum {
+ CEPH_OSD_FLAG_ACK = 1, /* want (or is) "ack" ack */
+ CEPH_OSD_FLAG_ONNVRAM = 2, /* want (or is) "onnvram" ack */
+ CEPH_OSD_FLAG_ONDISK = 4, /* want (or is) "ondisk" ack */
+ CEPH_OSD_FLAG_RETRY = 8, /* resend attempt */
+ CEPH_OSD_FLAG_READ = 16, /* op may read */
+ CEPH_OSD_FLAG_WRITE = 32, /* op may write */
+ CEPH_OSD_FLAG_ORDERSNAP = 64, /* EOLDSNAP if snapc is out of order */
+ CEPH_OSD_FLAG_PEERSTAT = 128, /* msg includes osd_peer_stat */
+ CEPH_OSD_FLAG_BALANCE_READS = 256,
+ CEPH_OSD_FLAG_PARALLELEXEC = 512, /* execute op in parallel */
+ CEPH_OSD_FLAG_PGOP = 1024, /* pg op, no object */
+ CEPH_OSD_FLAG_EXEC = 2048, /* op may exec */
+};
+
+enum {
+ CEPH_OSD_OP_FLAG_EXCL = 1, /* EXCL object create */
+};
+
+#define EOLDSNAPC ERESTART /* ORDERSNAP flag set; writer has old snapc*/
+#define EBLACKLISTED ESHUTDOWN /* blacklisted */
+
+/*
+ * an individual object operation. each may be accompanied by some data
+ * payload
+ */
+struct ceph_osd_op {
+ __le16 op; /* CEPH_OSD_OP_* */
+ __le32 flags; /* CEPH_OSD_FLAG_* */
+ union {
+ struct {
+ __le64 offset, length;
+ } __attribute__ ((packed)) extent;
+ struct {
+ __le32 name_len;
+ __le32 value_len;
+ } __attribute__ ((packed)) xattr;
+ struct {
+ __le64 truncate_size;
+ __le32 truncate_seq;
+ } __attribute__ ((packed)) trunc;
+ struct {
+ __u8 class_len;
+ __u8 method_len;
+ __u8 argc;
+ __le32 indata_len;
+ } __attribute__ ((packed)) cls;
+ struct {
+ __le64 cookie, count;
+ } __attribute__ ((packed)) pgls;
+ };
+ __le32 payload_len;
+} __attribute__ ((packed));
+
+/*
+ * osd request message header. each request may include multiple
+ * ceph_osd_op object operations.
+ */
+struct ceph_osd_request_head {
+ __le64 tid; /* transaction id */
+ __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 {
+ __le64 tid; /* transaction id */
+ __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
--
1.6.5
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists