diff options
Diffstat (limited to 'include/linux/ceph')
| -rw-r--r-- | include/linux/ceph/auth.h | 8 | ||||
| -rw-r--r-- | include/linux/ceph/ceph_features.h | 15 | ||||
| -rw-r--r-- | include/linux/ceph/ceph_fs.h | 1 | ||||
| -rw-r--r-- | include/linux/ceph/decode.h | 18 | ||||
| -rw-r--r-- | include/linux/ceph/libceph.h | 8 | ||||
| -rw-r--r-- | include/linux/ceph/messenger.h | 32 | ||||
| -rw-r--r-- | include/linux/ceph/msgpool.h | 11 | ||||
| -rw-r--r-- | include/linux/ceph/msgr.h | 2 | ||||
| -rw-r--r-- | include/linux/ceph/osd_client.h | 38 | ||||
| -rw-r--r-- | include/linux/ceph/osdmap.h | 8 | ||||
| -rw-r--r-- | include/linux/ceph/pagelist.h | 13 | ||||
| -rw-r--r-- | include/linux/ceph/rados.h | 28 |
12 files changed, 113 insertions, 69 deletions
diff --git a/include/linux/ceph/auth.h b/include/linux/ceph/auth.h index e931da8424a4..6728c2ee0205 100644 --- a/include/linux/ceph/auth.h +++ b/include/linux/ceph/auth.h @@ -64,6 +64,10 @@ struct ceph_auth_client_ops { /* ensure that an existing authorizer is up to date */ int (*update_authorizer)(struct ceph_auth_client *ac, int peer_type, struct ceph_auth_handshake *auth); + int (*add_authorizer_challenge)(struct ceph_auth_client *ac, + struct ceph_authorizer *a, + void *challenge_buf, + int challenge_buf_len); int (*verify_authorizer_reply)(struct ceph_auth_client *ac, struct ceph_authorizer *a); void (*invalidate_authorizer)(struct ceph_auth_client *ac, @@ -118,6 +122,10 @@ void ceph_auth_destroy_authorizer(struct ceph_authorizer *a); extern int ceph_auth_update_authorizer(struct ceph_auth_client *ac, int peer_type, struct ceph_auth_handshake *a); +int ceph_auth_add_authorizer_challenge(struct ceph_auth_client *ac, + struct ceph_authorizer *a, + void *challenge_buf, + int challenge_buf_len); extern int ceph_auth_verify_authorizer_reply(struct ceph_auth_client *ac, struct ceph_authorizer *a); extern void ceph_auth_invalidate_authorizer(struct ceph_auth_client *ac, diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 3901927cf6a0..65a38c4a02a1 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -165,9 +165,9 @@ DEFINE_CEPH_FEATURE(58, 1, FS_FILE_LAYOUT_V2) // overlap DEFINE_CEPH_FEATURE(59, 1, FS_BTIME) DEFINE_CEPH_FEATURE(59, 1, FS_CHANGE_ATTR) // overlap DEFINE_CEPH_FEATURE(59, 1, MSG_ADDR2) // overlap -DEFINE_CEPH_FEATURE(60, 1, BLKIN_TRACING) // *do not share this bit* +DEFINE_CEPH_FEATURE(60, 1, OSD_RECOVERY_DELETES) // *do not share this bit* +DEFINE_CEPH_FEATURE(61, 1, CEPHX_V2) // *do not share this bit* -DEFINE_CEPH_FEATURE(61, 1, RESERVED2) // unused, but slow down! DEFINE_CEPH_FEATURE(62, 1, RESERVED) // do not use; used as a sentinal DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facing @@ -210,14 +210,9 @@ DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facin CEPH_FEATURE_SERVER_JEWEL | \ CEPH_FEATURE_MON_STATEFUL_SUB | \ CEPH_FEATURE_CRUSH_TUNABLES5 | \ - CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING) + CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING | \ + CEPH_FEATURE_CEPHX_V2) -#define CEPH_FEATURES_REQUIRED_DEFAULT \ - (CEPH_FEATURE_NOSRCADDR | \ - CEPH_FEATURE_SUBSCRIBE2 | \ - CEPH_FEATURE_RECONNECT_SEQ | \ - CEPH_FEATURE_PGID64 | \ - CEPH_FEATURE_PGPOOL3 | \ - CEPH_FEATURE_OSDENC) +#define CEPH_FEATURES_REQUIRED_DEFAULT 0 #endif diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 7ecfc88314d8..4903deb0777a 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -628,6 +628,7 @@ int ceph_flags_to_mode(int flags); CEPH_CAP_XATTR_SHARED) #define CEPH_STAT_CAP_INLINE_DATA (CEPH_CAP_FILE_SHARED | \ CEPH_CAP_FILE_RD) +#define CEPH_STAT_RSTAT CEPH_CAP_FILE_WREXTEND #define CEPH_CAP_ANY_SHARED (CEPH_CAP_AUTH_SHARED | \ CEPH_CAP_LINK_SHARED | \ diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index d143ac8879c6..a6c2a48d42e0 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -194,16 +194,22 @@ ceph_decode_skip_n(p, end, sizeof(u8), bad) } while (0) /* - * struct ceph_timespec <-> struct timespec + * struct ceph_timespec <-> struct timespec64 */ -static inline void ceph_decode_timespec(struct timespec *ts, - const struct ceph_timespec *tv) +static inline void ceph_decode_timespec64(struct timespec64 *ts, + const struct ceph_timespec *tv) { - ts->tv_sec = (__kernel_time_t)le32_to_cpu(tv->tv_sec); + /* + * This will still overflow in year 2106. We could extend + * the protocol to steal two more bits from tv_nsec to + * add three more 136 year epochs after that the way ext4 + * does if necessary. + */ + ts->tv_sec = (time64_t)le32_to_cpu(tv->tv_sec); ts->tv_nsec = (long)le32_to_cpu(tv->tv_nsec); } -static inline void ceph_encode_timespec(struct ceph_timespec *tv, - const struct timespec *ts) +static inline void ceph_encode_timespec64(struct ceph_timespec *tv, + const struct timespec64 *ts) { tv->tv_sec = cpu_to_le32((u32)ts->tv_sec); tv->tv_nsec = cpu_to_le32((u32)ts->tv_nsec); diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 49c93b9308d7..68bb09c29ce8 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -81,7 +81,13 @@ struct ceph_options { #define CEPH_MSG_MAX_FRONT_LEN (16*1024*1024) #define CEPH_MSG_MAX_MIDDLE_LEN (16*1024*1024) -#define CEPH_MSG_MAX_DATA_LEN (16*1024*1024) + +/* + * Handle the largest possible rbd object in one message. + * There is no limit on the size of cephfs objects, but it has to obey + * rsize and wsize mount options anyway. + */ +#define CEPH_MSG_MAX_DATA_LEN (32*1024*1024) #define CEPH_AUTH_NAME_DEFAULT "guest" diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index c7dfcb8a1fb2..800a2128d411 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -31,6 +31,9 @@ struct ceph_connection_operations { struct ceph_auth_handshake *(*get_authorizer) ( struct ceph_connection *con, int *proto, int force_new); + int (*add_authorizer_challenge)(struct ceph_connection *con, + void *challenge_buf, + int challenge_buf_len); int (*verify_authorizer_reply) (struct ceph_connection *con); int (*invalidate_authorizer)(struct ceph_connection *con); @@ -79,22 +82,6 @@ enum ceph_msg_data_type { CEPH_MSG_DATA_BVECS, /* data source/destination is a bio_vec array */ }; -static __inline__ bool ceph_msg_data_type_valid(enum ceph_msg_data_type type) -{ - switch (type) { - case CEPH_MSG_DATA_NONE: - case CEPH_MSG_DATA_PAGES: - case CEPH_MSG_DATA_PAGELIST: -#ifdef CONFIG_BLOCK - case CEPH_MSG_DATA_BIO: -#endif /* CONFIG_BLOCK */ - case CEPH_MSG_DATA_BVECS: - return true; - default: - return false; - } -} - #ifdef CONFIG_BLOCK struct ceph_bio_iter { @@ -178,7 +165,6 @@ struct ceph_bvec_iter { } while (0) struct ceph_msg_data { - struct list_head links; /* ceph_msg->data */ enum ceph_msg_data_type type; union { #ifdef CONFIG_BLOCK @@ -199,7 +185,6 @@ struct ceph_msg_data { struct ceph_msg_data_cursor { size_t total_resid; /* across all data items */ - struct list_head *data_head; /* = &ceph_msg->data */ struct ceph_msg_data *data; /* current data item */ size_t resid; /* bytes not yet consumed */ @@ -237,7 +222,9 @@ struct ceph_msg { struct ceph_buffer *middle; size_t data_length; - struct list_head data; + struct ceph_msg_data *data; + int num_data_items; + int max_data_items; struct ceph_msg_data_cursor cursor; struct ceph_connection *con; @@ -286,9 +273,8 @@ struct ceph_connection { attempt for this connection, client */ u32 peer_global_seq; /* peer's global seq for this connection */ + struct ceph_auth_handshake *auth; 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; @@ -330,7 +316,7 @@ struct ceph_connection { int in_base_pos; /* bytes read */ __le64 in_temp_ack; /* for reading an ack */ - struct timespec last_keepalive_ack; /* keepalive2 ack stamp */ + struct timespec64 last_keepalive_ack; /* keepalive2 ack stamp */ struct delayed_work work; /* send|recv work */ unsigned long delay; /* current delay interval */ @@ -379,6 +365,8 @@ void ceph_msg_data_add_bio(struct ceph_msg *msg, struct ceph_bio_iter *bio_pos, void ceph_msg_data_add_bvecs(struct ceph_msg *msg, struct ceph_bvec_iter *bvec_pos); +struct ceph_msg *ceph_msg_new2(int type, int front_len, int max_data_items, + gfp_t flags, bool can_fail); extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, bool can_fail); diff --git a/include/linux/ceph/msgpool.h b/include/linux/ceph/msgpool.h index 76c98a512758..729cdf700eae 100644 --- a/include/linux/ceph/msgpool.h +++ b/include/linux/ceph/msgpool.h @@ -13,14 +13,15 @@ struct ceph_msgpool { mempool_t *pool; int type; /* preallocated message type */ int front_len; /* preallocated payload size */ + int max_data_items; }; -extern int ceph_msgpool_init(struct ceph_msgpool *pool, int type, - int front_len, int size, bool blocking, - const char *name); +int ceph_msgpool_init(struct ceph_msgpool *pool, int type, + int front_len, int max_data_items, int size, + 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); +struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool, int front_len, + int max_data_items); 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 index 73ae2a926548..9e50aede46c8 100644 --- a/include/linux/ceph/msgr.h +++ b/include/linux/ceph/msgr.h @@ -91,7 +91,7 @@ struct ceph_entity_inst { #define CEPH_MSGR_TAG_SEQ 13 /* 64-bit int follows with seen seq number */ #define CEPH_MSGR_TAG_KEEPALIVE2 14 /* keepalive2 byte + ceph_timespec */ #define CEPH_MSGR_TAG_KEEPALIVE2_ACK 15 /* keepalive2 reply */ - +#define CEPH_MSGR_TAG_CHALLENGE_AUTHORIZER 16 /* cephx v2 doing server challenge */ /* * connection negotiation diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 96bb32285989..7a2af5034278 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -136,6 +136,13 @@ struct ceph_osd_req_op { u64 expected_object_size; u64 expected_write_size; } alloc_hint; + struct { + u64 snapid; + u64 src_version; + u8 flags; + u32 src_fadvise_flags; + struct ceph_osd_data osd_data; + } copy_from; }; }; @@ -170,6 +177,7 @@ struct ceph_osd_request { u64 r_tid; /* unique for this client */ struct rb_node r_node; struct rb_node r_mc_node; /* map check */ + struct work_struct r_complete_work; struct ceph_osd *r_osd; struct ceph_osd_request_target r_t; @@ -198,10 +206,9 @@ struct ceph_osd_request { /* set by submitter */ u64 r_snapid; /* for reads, CEPH_NOSNAP o/w */ struct ceph_snap_context *r_snapc; /* for writes */ - struct timespec r_mtime; /* ditto */ + struct timespec64 r_mtime; /* ditto */ u64 r_data_offset; /* ditto */ bool r_linger; /* don't resend on failure */ - bool r_abort_on_full; /* return ENOSPC when full */ /* internal */ unsigned long r_stamp; /* jiffies, send or check time */ @@ -253,7 +260,7 @@ struct ceph_osd_linger_request { struct ceph_osd_request_target t; u32 map_dne_bound; - struct timespec mtime; + struct timespec64 mtime; struct kref kref; struct mutex lock; @@ -347,6 +354,8 @@ struct ceph_osd_client { struct rb_root linger_map_checks; atomic_t num_requests; atomic_t num_homeless; + bool abort_on_full; /* abort w/ ENOSPC when full */ + int abort_err; struct delayed_work timeout_work; struct delayed_work osds_timeout_work; #ifdef CONFIG_DEBUG_FS @@ -359,6 +368,7 @@ struct ceph_osd_client { struct ceph_msgpool msgpool_op_reply; struct workqueue_struct *notify_wq; + struct workqueue_struct *completion_wq; }; static inline bool ceph_osdmap_flag(struct ceph_osd_client *osdc, int flag) @@ -378,6 +388,7 @@ 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); void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb); +void ceph_osdc_abort_requests(struct ceph_osd_client *osdc, int err); extern void osd_req_op_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, u32 flags); @@ -440,9 +451,8 @@ extern void osd_req_op_cls_response_data_pages(struct ceph_osd_request *, struct page **pages, u64 length, u32 alignment, bool pages_from_pool, bool own_pages); -extern void osd_req_op_cls_init(struct ceph_osd_request *osd_req, - unsigned int which, u16 opcode, - const char *class, const char *method); +int osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which, + const char *class, const char *method); extern int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, const char *name, const void *value, size_t size, u8 cmp_op, u8 cmp_mode); @@ -504,9 +514,19 @@ extern int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_snap_context *sc, u64 off, u64 len, u32 truncate_seq, u64 truncate_size, - struct timespec *mtime, + struct timespec64 *mtime, struct page **pages, int nr_pages); +int ceph_osdc_copy_from(struct ceph_osd_client *osdc, + u64 src_snapid, u64 src_version, + struct ceph_object_id *src_oid, + struct ceph_object_locator *src_oloc, + u32 src_fadvise_flags, + struct ceph_object_id *dst_oid, + struct ceph_object_locator *dst_oloc, + u32 dst_fadvise_flags, + u8 copy_from_flags); + /* watch/notify */ struct ceph_osd_linger_request * ceph_osdc_watch(struct ceph_osd_client *osdc, @@ -524,12 +544,12 @@ int ceph_osdc_notify_ack(struct ceph_osd_client *osdc, u64 notify_id, u64 cookie, void *payload, - size_t payload_len); + u32 payload_len); int ceph_osdc_notify(struct ceph_osd_client *osdc, struct ceph_object_id *oid, struct ceph_object_locator *oloc, void *payload, - size_t payload_len, + u32 payload_len, u32 timeout, struct page ***preply_pages, size_t *preply_len); diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index e71fb222c7c3..5675b1f09bc5 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -279,10 +279,10 @@ bool ceph_osds_changed(const struct ceph_osds *old_acting, const struct ceph_osds *new_acting, bool any_change); -int __ceph_object_locator_to_pg(struct ceph_pg_pool_info *pi, - const struct ceph_object_id *oid, - const struct ceph_object_locator *oloc, - struct ceph_pg *raw_pgid); +void __ceph_object_locator_to_pg(struct ceph_pg_pool_info *pi, + const struct ceph_object_id *oid, + const struct ceph_object_locator *oloc, + struct ceph_pg *raw_pgid); int ceph_object_locator_to_pg(struct ceph_osdmap *osdmap, const struct ceph_object_id *oid, const struct ceph_object_locator *oloc, diff --git a/include/linux/ceph/pagelist.h b/include/linux/ceph/pagelist.h index 7edcded07641..5dead8486fd8 100644 --- a/include/linux/ceph/pagelist.h +++ b/include/linux/ceph/pagelist.h @@ -23,16 +23,7 @@ struct ceph_pagelist_cursor { size_t room; /* room remaining to reset to */ }; -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; - INIT_LIST_HEAD(&pl->free_list); - pl->num_pages_free = 0; - refcount_set(&pl->refcnt, 1); -} +struct ceph_pagelist *ceph_pagelist_alloc(gfp_t gfp_flags); extern void ceph_pagelist_release(struct ceph_pagelist *pl); @@ -68,7 +59,7 @@ 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) + char *s, u32 len) { int ret = ceph_pagelist_encode_32(pl, len); if (ret) diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h index f1988387c5ad..3eb0e55665b4 100644 --- a/include/linux/ceph/rados.h +++ b/include/linux/ceph/rados.h @@ -410,6 +410,14 @@ enum { enum { CEPH_OSD_OP_FLAG_EXCL = 1, /* EXCL object create */ CEPH_OSD_OP_FLAG_FAILOK = 2, /* continue despite failure */ + CEPH_OSD_OP_FLAG_FADVISE_RANDOM = 0x4, /* the op is random */ + CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL = 0x8, /* the op is sequential */ + CEPH_OSD_OP_FLAG_FADVISE_WILLNEED = 0x10,/* data will be accessed in + the near future */ + CEPH_OSD_OP_FLAG_FADVISE_DONTNEED = 0x20,/* data will not be accessed + in the near future */ + CEPH_OSD_OP_FLAG_FADVISE_NOCACHE = 0x40,/* data will be accessed only + once by this client */ }; #define EOLDSNAPC ERESTART /* ORDERSNAP flag set; writer has old snapc*/ @@ -432,6 +440,15 @@ enum { }; enum { + CEPH_OSD_COPY_FROM_FLAG_FLUSH = 1, /* part of a flush operation */ + CEPH_OSD_COPY_FROM_FLAG_IGNORE_OVERLAY = 2, /* ignore pool overlay */ + CEPH_OSD_COPY_FROM_FLAG_IGNORE_CACHE = 4, /* ignore osd cache logic */ + CEPH_OSD_COPY_FROM_FLAG_MAP_SNAP_CLONE = 8, /* map snap direct to + * cloneid */ + CEPH_OSD_COPY_FROM_FLAG_RWORDERED = 16, /* order with write */ +}; + +enum { CEPH_OSD_WATCH_OP_UNWATCH = 0, CEPH_OSD_WATCH_OP_LEGACY_WATCH = 1, /* note: use only ODD ids to prevent pre-giant code from @@ -497,6 +514,17 @@ struct ceph_osd_op { __le64 expected_object_size; __le64 expected_write_size; } __attribute__ ((packed)) alloc_hint; + struct { + __le64 snapid; + __le64 src_version; + __u8 flags; /* CEPH_OSD_COPY_FROM_FLAG_* */ + /* + * CEPH_OSD_OP_FLAG_FADVISE_*: fadvise flags + * for src object, flags for dest object are in + * ceph_osd_op::flags. + */ + __le32 src_fadvise_flags; + } __attribute__ ((packed)) copy_from; }; __le32 payload_len; } __attribute__ ((packed)); |
