Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client

Pull Ceph updates from Sage Weil:
 "A few groups of patches here.  Alex has been hard at work improving
  the RBD code, layout groundwork for understanding the new formats and
  doing layering.  Most of the infrastructure is now in place for the
  final bits that will come with the next window.

  There are a few changes to the data layout.  Jim Schutt's patch fixes
  some non-ideal CRUSH behavior, and a set of patches from me updates
  the client to speak a newer version of the protocol and implement an
  improved hashing strategy across storage nodes (when the server side
  supports it too).

  A pair of patches from Sam Lang fix the atomicity of open+create
  operations.  Several patches from Yan, Zheng fix various mds/client
  issues that turned up during multi-mds torture tests.

  A final set of patches expose file layouts via virtual xattrs, and
  allow the policies to be set on directories via xattrs as well
  (avoiding the awkward ioctl interface and providing a consistent
  interface for both kernel mount and ceph-fuse users)."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (143 commits)
  libceph: add support for HASHPSPOOL pool flag
  libceph: update osd request/reply encoding
  libceph: calculate placement based on the internal data types
  ceph: update support for PGID64, PGPOOL3, OSDENC protocol features
  ceph: update "ceph_features.h"
  libceph: decode into cpu-native ceph_pg type
  libceph: rename ceph_pg -> ceph_pg_v1
  rbd: pass length, not op for osd completions
  rbd: move rbd_osd_trivial_callback()
  libceph: use a do..while loop in con_work()
  libceph: use a flag to indicate a fault has occurred
  libceph: separate non-locked fault handling
  libceph: encapsulate connection backoff
  libceph: eliminate sparse warnings
  ceph: eliminate sparse warnings in fs code
  rbd: eliminate sparse warnings
  libceph: define connection flag helpers
  rbd: normalize dout() calls
  rbd: barriers are hard
  rbd: ignore zero-length requests
  ...

10 files changed, 227 insertions, 158 deletions

diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index dad579b0c0e6..76554cecaab2 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -12,16 +12,46 @@
 #define CEPH_FEATURE_MONNAMES       (1<<5)
 #define CEPH_FEATURE_RECONNECT_SEQ  (1<<6)
 #define CEPH_FEATURE_DIRLAYOUTHASH  (1<<7)
-/* bits 8-17 defined by user-space; not supported yet here */
+#define CEPH_FEATURE_OBJECTLOCATOR  (1<<8)
+#define CEPH_FEATURE_PGID64         (1<<9)
+#define CEPH_FEATURE_INCSUBOSDMAP   (1<<10)
+#define CEPH_FEATURE_PGPOOL3        (1<<11)
+#define CEPH_FEATURE_OSDREPLYMUX    (1<<12)
+#define CEPH_FEATURE_OSDENC         (1<<13)
+#define CEPH_FEATURE_OMAP           (1<<14)
+#define CEPH_FEATURE_MONENC         (1<<15)
+#define CEPH_FEATURE_QUERY_T        (1<<16)
+#define CEPH_FEATURE_INDEP_PG_MAP   (1<<17)
 #define CEPH_FEATURE_CRUSH_TUNABLES (1<<18)
+#define CEPH_FEATURE_CHUNKY_SCRUB   (1<<19)
+#define CEPH_FEATURE_MON_NULLROUTE  (1<<20)
+#define CEPH_FEATURE_MON_GV         (1<<21)
+#define CEPH_FEATURE_BACKFILL_RESERVATION (1<<22)
+#define CEPH_FEATURE_MSG_AUTH       (1<<23)
+#define CEPH_FEATURE_RECOVERY_RESERVATION (1<<24)
+#define CEPH_FEATURE_CRUSH_TUNABLES2 (1<<25)
+#define CEPH_FEATURE_CREATEPOOLID   (1<<26)
+#define CEPH_FEATURE_REPLY_CREATE_INODE   (1<<27)
+#define CEPH_FEATURE_OSD_HBMSGS     (1<<28)
+#define CEPH_FEATURE_MDSENC         (1<<29)
+#define CEPH_FEATURE_OSDHASHPSPOOL  (1<<30)
 
 /*
  * Features supported.
  */
 #define CEPH_FEATURES_SUPPORTED_DEFAULT  \
-        (CEPH_FEATURE_NOSRCADDR |        \
-         CEPH_FEATURE_CRUSH_TUNABLES)
+        (CEPH_FEATURE_NOSRCADDR |               \
+         CEPH_FEATURE_PGID64 |                  \
+         CEPH_FEATURE_PGPOOL3 |                 \
+         CEPH_FEATURE_OSDENC |                  \
+         CEPH_FEATURE_CRUSH_TUNABLES |          \
+         CEPH_FEATURE_CRUSH_TUNABLES2 |         \
+         CEPH_FEATURE_REPLY_CREATE_INODE |      \
+         CEPH_FEATURE_OSDHASHPSPOOL)
 
 #define CEPH_FEATURES_REQUIRED_DEFAULT   \
-        (CEPH_FEATURE_NOSRCADDR)
+        (CEPH_FEATURE_NOSRCADDR |        \
+         CEPH_FEATURE_PGID64 |           \
+         CEPH_FEATURE_PGPOOL3 |          \
+         CEPH_FEATURE_OSDENC)
 #endif
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index cf6f4d998a76..2ad7b860f062 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -21,16 +21,14 @@
  * 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 */
+#define CEPH_INO_ROOT   1
+#define CEPH_INO_CEPH   2       /* hidden .ceph dir */
+#define CEPH_INO_DOTDOT 3       /* used by ceph fuse for parent (..) */
 
 /* arbitrary limit on max # of monitors (cluster of 3 is typical) */
 #define CEPH_MAX_MON   31
@@ -51,7 +49,7 @@ struct ceph_file_layout {
         __le32 fl_object_stripe_unit;  /* UNUSED.  for per-object parity, if any */
 
         /* object -> pg layout */
-        __le32 fl_unused;       /* unused; used to be preferred primary (-1) */
+        __le32 fl_unused;       /* unused; used to be preferred primary for pg (-1 for none) */
         __le32 fl_pg_pool;      /* namespace, crush ruleset, rep level */
 } __attribute__ ((packed));
 
@@ -101,6 +99,8 @@ struct ceph_dir_layout {
 #define CEPH_MSG_MON_SUBSCRIBE_ACK      16
 #define CEPH_MSG_AUTH                   17
 #define CEPH_MSG_AUTH_REPLY             18
+#define CEPH_MSG_MON_GET_VERSION        19
+#define CEPH_MSG_MON_GET_VERSION_REPLY  20
 
 /* client <-> mds */
 #define CEPH_MSG_MDS_MAP                21
@@ -221,6 +221,11 @@ struct ceph_mon_subscribe_ack {
 } __attribute__ ((packed));
 
 /*
+ * mdsmap flags
+ */
+#define CEPH_MDSMAP_DOWN    (1<<0)  /* cluster deliberately down */
+
+/*
  * mds states
  *   > 0 -> in
  *  <= 0 -> out
@@ -233,6 +238,7 @@ struct ceph_mon_subscribe_ack {
 #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_REPLAYONCE   -9 /* up, replaying an active node's journal */
 
 #define CEPH_MDS_STATE_REPLAY       8  /* up, replaying journal. */
 #define CEPH_MDS_STATE_RESOLVE      9  /* up, disambiguating distributed
@@ -264,6 +270,7 @@ extern const char *ceph_mds_state_name(int s);
 #define CEPH_LOCK_IXATTR      2048
 #define CEPH_LOCK_IFLOCK      4096  /* advisory file locks */
 #define CEPH_LOCK_INO         8192  /* immutable inode bits; not a lock */
+#define CEPH_LOCK_IPOLICY     16384 /* policy lock on dirs. MDS internal */
 
 /* client_session ops */
 enum {
@@ -338,6 +345,12 @@ extern const char *ceph_mds_op_name(int op);
 #define CEPH_SETATTR_SIZE  32
 #define CEPH_SETATTR_CTIME 64
 
+/*
+ * Ceph setxattr request flags.
+ */
+#define CEPH_XATTR_CREATE  1
+#define CEPH_XATTR_REPLACE 2
+
 union ceph_mds_request_args {
         struct {
                 __le32 mask;                 /* CEPH_CAP_* */
@@ -522,14 +535,17 @@ int ceph_flags_to_mode(int flags);
 #define CEPH_CAP_GWREXTEND  64  /* (file) client can extend EOF */
 #define CEPH_CAP_GLAZYIO   128  /* (file) client can perform lazy io */
 
+#define CEPH_CAP_SIMPLE_BITS  2
+#define CEPH_CAP_FILE_BITS    8
+
 /* 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_SFLOCK    20
 
-#define CEPH_CAP_BITS       22
+#define CEPH_CAP_BITS      22
 
 /* composed values */
 #define CEPH_CAP_AUTH_SHARED  (CEPH_CAP_GSHARED  << CEPH_CAP_SAUTH)
diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h
index 63d092822bad..360d9d08ca9e 100644
--- a/include/linux/ceph/decode.h
+++ b/include/linux/ceph/decode.h
@@ -52,10 +52,10 @@ static inline int ceph_has_room(void **p, void *end, size_t n)
         return end >= *p && n <= end - *p;
 }
 
-#define ceph_decode_need(p, end, n, bad)                \
-        do {                                            \
-                if (!likely(ceph_has_room(p, end, n)))  \
-                        goto bad;                       \
+#define ceph_decode_need(p, end, n, bad)                        \
+        do {                                                    \
+                if (!likely(ceph_has_room(p, end, n)))          \
+                        goto bad;                               \
         } while (0)
 
 #define ceph_decode_64_safe(p, end, v, bad)                     \
@@ -99,8 +99,8 @@ static inline int ceph_has_room(void **p, void *end, size_t n)
  *
  * There are two possible failures:
  *   - converting the string would require accessing memory at or
- *     beyond the "end" pointer provided (-E
- *   - memory could not be allocated for the result
+ *     beyond the "end" pointer provided (-ERANGE)
+ *   - memory could not be allocated for the result (-ENOMEM)
  */
 static inline char *ceph_extract_encoded_string(void **p, void *end,
                                                 size_t *lenp, gfp_t gfp)
@@ -217,10 +217,10 @@ static inline void ceph_encode_string(void **p, void *end,
         *p += len;
 }
 
-#define ceph_encode_need(p, end, n, bad)                \
-        do {                                            \
-                if (!likely(ceph_has_room(p, end, n)))  \
-                        goto bad;                       \
+#define ceph_encode_need(p, end, n, bad)                        \
+        do {                                                    \
+                if (!likely(ceph_has_room(p, end, n)))          \
+                        goto bad;                               \
         } while (0)
 
 #define ceph_encode_64_safe(p, end, v, bad)                     \
@@ -231,12 +231,17 @@ static inline void ceph_encode_string(void **p, void *end,
 #define ceph_encode_32_safe(p, end, v, bad)                     \
         do {                                                    \
                 ceph_encode_need(p, end, sizeof(u32), bad);     \
-                ceph_encode_32(p, v);                   \
+                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);                   \
+                ceph_encode_16(p, v);                           \
+        } while (0)
+#define ceph_encode_8_safe(p, end, v, bad)                      \
+        do {                                                    \
+                ceph_encode_need(p, end, sizeof(u8), bad);      \
+                ceph_encode_8(p, v);                            \
         } while (0)
 
 #define ceph_encode_copy_safe(p, end, pv, n, bad)               \
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 084d3c622b12..29818fc3fa49 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -193,6 +193,8 @@ static inline int calc_pages_for(u64 off, u64 len)
 }
 
 /* ceph_common.c */
+extern bool libceph_compatible(void *data);
+
 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;
@@ -220,7 +222,7 @@ 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,
+extern struct page **ceph_get_direct_page_vector(const void __user *data,
                                                  int num_pages,
                                                  bool write_page);
 extern void ceph_put_page_vector(struct page **pages, int num_pages,
@@ -228,15 +230,15 @@ 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,
+                                         const void __user *data,
                                          loff_t off, size_t len);
-extern int ceph_copy_to_page_vector(struct page **pages,
-                                    const char *data,
+extern void ceph_copy_to_page_vector(struct page **pages,
+                                    const void *data,
                                     loff_t off, size_t len);
-extern int ceph_copy_from_page_vector(struct page **pages,
-                                    char *data,
+extern void ceph_copy_from_page_vector(struct page **pages,
+                                    void *data,
                                     loff_t off, size_t len);
-extern int ceph_copy_page_vector_to_user(struct page **pages, char __user *data,
+extern int ceph_copy_page_vector_to_user(struct page **pages, void __user *data,
                                     loff_t off, size_t len);
 extern void ceph_zero_page_vector_range(int off, int len, struct page **pages);
 
diff --git a/include/linux/ceph/mdsmap.h b/include/linux/ceph/mdsmap.h
index cb15b5d867c7..87ed09f54800 100644
--- a/include/linux/ceph/mdsmap.h
+++ b/include/linux/ceph/mdsmap.h
@@ -29,8 +29,8 @@ struct ceph_mdsmap {
 
         /* 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;
+        u64 *m_data_pg_pools;
+        u64 m_cas_pg_pool;
 };
 
 static inline struct ceph_entity_addr *
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 14ba5ee738a9..60903e0f665c 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -83,9 +83,11 @@ struct ceph_msg {
         struct list_head list_head;
 
         struct kref kref;
+#ifdef CONFIG_BLOCK
         struct bio  *bio;               /* instead of pages/pagelist */
         struct bio  *bio_iter;          /* bio iterator */
         int bio_seg;                    /* current bio segment */
+#endif /* CONFIG_BLOCK */
         struct ceph_pagelist *trail;    /* the trailing part of the data */
         bool front_is_vmalloc;
         bool more_to_follow;
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index d9b880e977e6..1dd5d466b6f9 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -10,6 +10,7 @@
 #include <linux/ceph/osdmap.h>
 #include <linux/ceph/messenger.h>
 #include <linux/ceph/auth.h>
+#include <linux/ceph/pagelist.h>
 
 /* 
  * Maximum object name size 
@@ -22,7 +23,6 @@ struct ceph_snap_context;
 struct ceph_osd_request;
 struct ceph_osd_client;
 struct ceph_authorizer;
-struct ceph_pagelist;
 
 /*
  * completion callback for async writepages
@@ -47,6 +47,9 @@ struct ceph_osd {
         struct list_head o_keepalive_item;
 };
 
+
+#define CEPH_OSD_MAX_OP 10
+
 /* an in-flight request */
 struct ceph_osd_request {
         u64             r_tid;              /* unique for this client */
@@ -63,9 +66,23 @@ struct ceph_osd_request {
         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_num_ops;
+
+        /* encoded message content */
+        struct ceph_osd_op *r_request_ops;
+        /* these are updated on each send */
+        __le32           *r_request_osdmap_epoch;
+        __le32           *r_request_flags;
+        __le64           *r_request_pool;
+        void             *r_request_pgid;
+        __le32           *r_request_attempts;
+        struct ceph_eversion *r_request_reassert_version;
+
+        int               r_result;
+        int               r_reply_op_len[CEPH_OSD_MAX_OP];
+        s32               r_reply_op_result[CEPH_OSD_MAX_OP];
         int               r_got_reply;
         int               r_linger;
 
@@ -82,6 +99,7 @@ struct ceph_osd_request {
 
         char              r_oid[MAX_OBJ_NAME_SIZE];          /* object name */
         int               r_oid_len;
+        u64               r_snapid;
         unsigned long     r_stamp;            /* send OR check time */
 
         struct ceph_file_layout r_file_layout;
@@ -95,7 +113,7 @@ struct ceph_osd_request {
         struct bio       *r_bio;              /* instead of pages */
 #endif
 
-        struct ceph_pagelist *r_trail;        /* trailing part of the data */
+        struct ceph_pagelist r_trail;         /* trailing part of the data */
 };
 
 struct ceph_osd_event {
@@ -107,7 +125,6 @@ struct ceph_osd_event {
         struct rb_node node;
         struct list_head osd_node;
         struct kref kref;
-        struct completion completion;
 };
 
 struct ceph_osd_event_work {
@@ -157,7 +174,7 @@ struct ceph_osd_client {
 
 struct ceph_osd_req_op {
         u16 op;           /* CEPH_OSD_OP_* */
-        u32 flags;        /* CEPH_OSD_FLAG_* */
+        u32 payload_len;
         union {
                 struct {
                         u64 offset, length;
@@ -166,23 +183,24 @@ struct ceph_osd_req_op {
                 } extent;
                 struct {
                         const char *name;
-                        u32 name_len;
                         const char  *val;
+                        u32 name_len;
                         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;
+                        __u8 class_len;
+                        __u8 method_len;
+                        __u8 argc;
                 } cls;
                 struct {
-                        u64 cookie, count;
+                        u64 cookie;
+                        u64 count;
                 } pgls;
                 struct {
                         u64 snapid;
@@ -190,12 +208,11 @@ struct ceph_osd_req_op {
                 struct {
                         u64 cookie;
                         u64 ver;
-                        __u8 flag;
                         u32 prot_ver;
                         u32 timeout;
+                        __u8 flag;
                 } watch;
         };
-        u32 payload_len;
 };
 
 extern int ceph_osdc_init(struct ceph_osd_client *osdc,
@@ -207,29 +224,19 @@ extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc,
 extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc,
                                  struct ceph_msg *msg);
 
-extern int 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,
+                                               unsigned int num_op,
                                                bool use_mempool,
-                                               gfp_t gfp_flags,
-                                               struct page **pages,
-                                               struct bio *bio);
+                                               gfp_t gfp_flags);
 
 extern void ceph_osdc_build_request(struct ceph_osd_request *req,
-                                    u64 off, u64 *plen,
+                                    u64 off, u64 len,
+                                    unsigned int num_op,
                                     struct ceph_osd_req_op *src_ops,
                                     struct ceph_snap_context *snapc,
-                                    struct timespec *mtime,
-                                    const char *oid,
-                                    int oid_len);
+                                    u64 snap_id,
+                                    struct timespec *mtime);
 
 extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *,
                                       struct ceph_file_layout *layout,
@@ -239,8 +246,7 @@ extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *,
                                       int do_sync, u32 truncate_seq,
                                       u64 truncate_size,
                                       struct timespec *mtime,
-                                      bool use_mempool, int num_reply,
-                                      int page_align);
+                                      bool use_mempool, int page_align);
 
 extern void ceph_osdc_set_request_linger(struct ceph_osd_client *osdc,
                                          struct ceph_osd_request *req);
@@ -279,17 +285,13 @@ extern int ceph_osdc_writepages(struct ceph_osd_client *osdc,
                                 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);
+                                struct page **pages, int nr_pages);
 
 /* watch/notify events */
 extern int ceph_osdc_create_event(struct ceph_osd_client *osdc,
                                   void (*event_cb)(u64, u64, u8, void *),
-                                  int one_shot, void *data,
-                                  struct ceph_osd_event **pevent);
+                                  void *data, struct ceph_osd_event **pevent);
 extern void ceph_osdc_cancel_event(struct ceph_osd_event *event);
-extern int ceph_osdc_wait_event(struct ceph_osd_event *event,
-                                unsigned long timeout);
 extern void ceph_osdc_put_event(struct ceph_osd_event *event);
 #endif
 
diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index 10a417f9f76f..c819190d1642 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -18,14 +18,31 @@
  * 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 {
+        uint64_t pool;
+        uint32_t seed;
+};
+
+#define CEPH_POOL_FLAG_HASHPSPOOL  1
+
 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;
+        s64 id;
+        u8 type;
+        u8 size;
+        u8 crush_ruleset;
+        u8 object_hash;
+        u32 pg_num, pgp_num;
+        int pg_num_mask, pgp_num_mask;
+        u64 flags;
         char *name;
 };
 
+struct ceph_object_locator {
+        uint64_t pool;
+        char *key;
+};
+
 struct ceph_pg_mapping {
         struct rb_node node;
         struct ceph_pg pgid;
@@ -110,15 +127,16 @@ extern void ceph_osdmap_destroy(struct ceph_osdmap *map);
 
 /* calculate mapping of a file extent to an object */
 extern int ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
-                                         u64 off, u64 *plen,
+                                         u64 off, u64 len,
                                          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,
+extern int ceph_calc_object_layout(struct ceph_pg *pg,
                                    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,
+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);
diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index 2c04afeead1c..68c96a508ac2 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -9,14 +9,6 @@
 #include <linux/ceph/msgr.h>
 
 /*
- * osdmap encoding versions
- */
-#define CEPH_OSDMAP_INC_VERSION     5
-#define CEPH_OSDMAP_INC_VERSION_EXT 6
-#define CEPH_OSDMAP_VERSION         5
-#define CEPH_OSDMAP_VERSION_EXT     6
-
-/*
  * fs id
  */
 struct ceph_fsid {
@@ -64,7 +56,7 @@ struct ceph_timespec {
  * placement group.
  * we encode this into one __le64.
  */
-struct ceph_pg {
+struct ceph_pg_v1 {
         __le16 preferred; /* preferred primary osd */
         __le16 ps;        /* placement seed */
         __le32 pool;      /* object pool */
@@ -91,21 +83,6 @@ struct ceph_pg {
 
 #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.
@@ -128,7 +105,7 @@ static inline int ceph_stable_mod(int x, int b, int bmask)
  * object layout - how a given object should be stored.
  */
 struct ceph_object_layout {
-        struct ceph_pg ol_pgid;   /* raw pg, with _full_ ps precision. */
+        struct ceph_pg_v1 ol_pgid;   /* raw pg, with _full_ ps precision. */
         __le32 ol_stripe_unit;    /* for per-object parity, if any */
 } __attribute__ ((packed));
 
@@ -145,8 +122,12 @@ struct ceph_eversion {
  */
 
 /* status bits */
-#define CEPH_OSD_EXISTS 1
-#define CEPH_OSD_UP     2
+#define CEPH_OSD_EXISTS  (1<<0)
+#define CEPH_OSD_UP      (1<<1)
+#define CEPH_OSD_AUTOOUT (1<<2)  /* osd was automatically marked out */
+#define CEPH_OSD_NEW     (1<<3)  /* osd is new, never marked in */
+
+extern const char *ceph_osd_state_name(int s);
 
 /* osd weights.  fixed point value: 0x10000 == 1.0 ("in"), 0 == "out" */
 #define CEPH_OSD_IN  0x10000
@@ -161,9 +142,25 @@ struct ceph_eversion {
 #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 */
+#define CEPH_OSDMAP_NOUP     (1<<5)  /* block osd boot */
+#define CEPH_OSDMAP_NODOWN   (1<<6)  /* block osd mark-down/failure */
+#define CEPH_OSDMAP_NOOUT    (1<<7)  /* block osd auto mark-out */
+#define CEPH_OSDMAP_NOIN     (1<<8)  /* block osd auto mark-in */
+#define CEPH_OSDMAP_NOBACKFILL (1<<9) /* block osd backfill */
+#define CEPH_OSDMAP_NORECOVER (1<<10) /* block osd recovery and backfill */
+
+/*
+ * The error code to return when an OSD can't handle a write
+ * because it is too large.
+ */
+#define OSD_WRITETOOBIG EMSGSIZE
 
 /*
  * osd ops
+ *
+ * WARNING: do not use these op codes directly.  Use the helpers
+ * defined below instead.  In certain cases, op code behavior was
+ * redefined, resulting in special-cases in the helpers.
  */
 #define CEPH_OSD_OP_MODE       0xf000
 #define CEPH_OSD_OP_MODE_RD    0x1000
@@ -177,6 +174,7 @@ struct ceph_eversion {
 #define CEPH_OSD_OP_TYPE_ATTR  0x0300
 #define CEPH_OSD_OP_TYPE_EXEC  0x0400
 #define CEPH_OSD_OP_TYPE_PG    0x0500
+#define CEPH_OSD_OP_TYPE_MULTI 0x0600 /* multiobject */
 
 enum {
         /** data **/
@@ -217,6 +215,23 @@ enum {
 
         CEPH_OSD_OP_WATCH   = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 15,
 
+        /* omap */
+        CEPH_OSD_OP_OMAPGETKEYS   = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 17,
+        CEPH_OSD_OP_OMAPGETVALS   = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 18,
+        CEPH_OSD_OP_OMAPGETHEADER = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 19,
+        CEPH_OSD_OP_OMAPGETVALSBYKEYS  =
+          CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 20,
+        CEPH_OSD_OP_OMAPSETVALS   = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 21,
+        CEPH_OSD_OP_OMAPSETHEADER = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 22,
+        CEPH_OSD_OP_OMAPCLEAR     = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 23,
+        CEPH_OSD_OP_OMAPRMKEYS    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 24,
+        CEPH_OSD_OP_OMAP_CMP      = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 25,
+
+        /** multi **/
+        CEPH_OSD_OP_CLONERANGE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_MULTI | 1,
+        CEPH_OSD_OP_ASSERT_SRC_VERSION = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_MULTI | 2,
+        CEPH_OSD_OP_SRC_CMPXATTR = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_MULTI | 3,
+
         /** attrs **/
         /* read */
         CEPH_OSD_OP_GETXATTR  = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 1,
@@ -238,6 +253,7 @@ enum {
         CEPH_OSD_OP_SCRUB_RESERVE   = CEPH_OSD_OP_MODE_SUB | 6,
         CEPH_OSD_OP_SCRUB_UNRESERVE = CEPH_OSD_OP_MODE_SUB | 7,
         CEPH_OSD_OP_SCRUB_STOP      = CEPH_OSD_OP_MODE_SUB | 8,
+        CEPH_OSD_OP_SCRUB_MAP     = CEPH_OSD_OP_MODE_SUB | 9,
 
         /** lock **/
         CEPH_OSD_OP_WRLOCK    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 1,
@@ -248,10 +264,12 @@ enum {
         CEPH_OSD_OP_DNLOCK    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 6,
 
         /** exec **/
+        /* note: the RD bit here is wrong; see special-case below in helper */
         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,
+        CEPH_OSD_OP_PGLS_FILTER = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_PG | 2,
 };
 
 static inline int ceph_osd_op_type_lock(int op)
@@ -274,6 +292,10 @@ 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_type_multi(int op)
+{
+        return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_MULTI;
+}
 
 static inline int ceph_osd_op_mode_subop(int op)
 {
@@ -281,11 +303,12 @@ static inline int ceph_osd_op_mode_subop(int op)
 }
 static inline int ceph_osd_op_mode_read(int op)
 {
-        return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_RD;
+        return (op & CEPH_OSD_OP_MODE_RD) &&
+                op != CEPH_OSD_OP_CALL;
 }
 static inline int ceph_osd_op_mode_modify(int op)
 {
-        return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_WR;
+        return op & CEPH_OSD_OP_MODE_WR;
 }
 
 /*
@@ -294,34 +317,38 @@ static inline int ceph_osd_op_mode_modify(int op)
  */
 #define CEPH_OSD_TMAP_HDR 'h'
 #define CEPH_OSD_TMAP_SET 's'
+#define CEPH_OSD_TMAP_CREATE 'c' /* create key */
 #define CEPH_OSD_TMAP_RM  'r'
+#define CEPH_OSD_TMAP_RMSLOPPY '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) */
+        CEPH_OSD_FLAG_ACK =            0x0001,  /* want (or is) "ack" ack */
+        CEPH_OSD_FLAG_ONNVRAM =        0x0002,  /* want (or is) "onnvram" ack */
+        CEPH_OSD_FLAG_ONDISK =         0x0004,  /* want (or is) "ondisk" ack */
+        CEPH_OSD_FLAG_RETRY =          0x0008,  /* resend attempt */
+        CEPH_OSD_FLAG_READ =           0x0010,  /* op may read */
+        CEPH_OSD_FLAG_WRITE =          0x0020,  /* op may write */
+        CEPH_OSD_FLAG_ORDERSNAP =      0x0040,  /* EOLDSNAP if snapc is out of order */
+        CEPH_OSD_FLAG_PEERSTAT_OLD =   0x0080,  /* DEPRECATED msg includes osd_peer_stat */
+        CEPH_OSD_FLAG_BALANCE_READS =  0x0100,
+        CEPH_OSD_FLAG_PARALLELEXEC =   0x0200,  /* execute op in parallel */
+        CEPH_OSD_FLAG_PGOP =           0x0400,  /* pg op, no object */
+        CEPH_OSD_FLAG_EXEC =           0x0800,  /* op may exec */
+        CEPH_OSD_FLAG_EXEC_PUBLIC =    0x1000,  /* DEPRECATED op may exec (public) */
+        CEPH_OSD_FLAG_LOCALIZE_READS = 0x2000,  /* read from nearby replica, if any */
+        CEPH_OSD_FLAG_RWORDERED =      0x4000,  /* order wrt concurrent reads */
 };
 
 enum {
         CEPH_OSD_OP_FLAG_EXCL = 1,      /* EXCL object create */
+        CEPH_OSD_OP_FLAG_FAILOK = 2,    /* continue despite failure */
 };
 
 #define EOLDSNAPC    ERESTART  /* ORDERSNAP flag set; writer has old snapc*/
@@ -381,48 +408,13 @@ struct ceph_osd_op {
                         __le64 ver;
                         __u8 flag;      /* 0 = unwatch, 1 = watch */
                 } __attribute__ ((packed)) watch;
-};
+                struct {
+                        __le64 offset, length;
+                        __le64 src_offset;
+                } __attribute__ ((packed)) clonerange;
+        };
         __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/crush/crush.h b/include/linux/crush/crush.h
index 25baa287cff7..6a1101f24cfb 100644
--- a/include/linux/crush/crush.h
+++ b/include/linux/crush/crush.h
@@ -162,6 +162,8 @@ struct crush_map {
         __u32 choose_local_fallback_tries;
         /* choose attempts before giving up */ 
         __u32 choose_total_tries;
+        /* attempt chooseleaf inner descent once; on failure retry outer descent */
+        __u32 chooseleaf_descend_once;
 };