X-Git-Url: https://git.whamcloud.com/?a=blobdiff_plain;f=lustre%2Finclude%2Flustre%2Flustre_idl.h;h=0a129dcce07f2080b9d31effb46a63d6a6bade66;hb=4f53536d002c13886210b672b657795baa067144;hp=b27d33f664c6e3634bdecc4d9708821b4850eba1;hpb=a8c9796fddaeda0572a64cedb471b2eead78c506;p=fs%2Flustre-release.git diff --git a/lustre/include/lustre/lustre_idl.h b/lustre/include/lustre/lustre_idl.h index b27d33f..0a129dc 100644 --- a/lustre/include/lustre/lustre_idl.h +++ b/lustre/include/lustre/lustre_idl.h @@ -27,7 +27,7 @@ * Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved. * Use is subject to license terms. * - * Copyright (c) 2011, 2013, Intel Corporation. + * Copyright (c) 2011, 2014, Intel Corporation. */ /* * This file is part of Lustre, http://www.lustre.org/ @@ -91,14 +91,11 @@ #ifndef _LUSTRE_IDL_H_ #define _LUSTRE_IDL_H_ -#if !defined(LPU64) #include /* for LPUX64, etc */ -#endif - -/* Defn's shared with user-space. */ -#include - +#include +#include /* Defn's shared with user-space. */ #include +#include /* * GENERAL STUFF @@ -150,10 +147,7 @@ #define PTL_RPC_MSG_REPLY 4713 /* DON'T use swabbed values of MAGIC as magic! */ -#define LUSTRE_MSG_MAGIC_V1 0x0BD00BD0 #define LUSTRE_MSG_MAGIC_V2 0x0BD00BD3 - -#define LUSTRE_MSG_MAGIC_V1_SWABBED 0xD00BD00B #define LUSTRE_MSG_MAGIC_V2_SWABBED 0xD30BD00B #define LUSTRE_MSG_MAGIC LUSTRE_MSG_MAGIC_V2 @@ -167,22 +161,6 @@ #define LUSTRE_LOG_VERSION 0x00050000 #define LUSTRE_MGS_VERSION 0x00060000 -typedef __u32 mdsno_t; -typedef __u64 seqno_t; -typedef __u64 obd_id; -typedef __u64 obd_seq; -typedef __s64 obd_time; -typedef __u64 obd_size; -typedef __u64 obd_off; -typedef __u64 obd_blocks; -typedef __u64 obd_valid; -typedef __u32 obd_blksize; -typedef __u32 obd_mode; -typedef __u32 obd_uid; -typedef __u32 obd_gid; -typedef __u32 obd_flag; -typedef __u32 obd_count; - /** * Describes a range of sequence, lsr_start is included but lsr_end is * not in the range. @@ -325,7 +303,7 @@ static inline int range_compare_loc(const struct lu_seq_range *r1, */ enum lma_compat { LMAC_HSM = 0x00000001, - LMAC_SOM = 0x00000002, +/* LMAC_SOM = 0x00000002, obsolete since 2.8.0 */ LMAC_NOT_IN_OI = 0x00000004, /* the object does NOT need OI mapping */ LMAC_FID_ON_OST = 0x00000008, /* For OST-object, its OI mapping is * under /O//d. */ @@ -341,36 +319,21 @@ enum lma_incompat { LMAI_AGENT = 0x00000002, /* agent inode */ LMAI_REMOTE_PARENT = 0x00000004, /* the parent of the object is on the remote MDT */ + LMAI_STRIPED = 0x00000008, /* striped directory inode */ }; -#define LMA_INCOMPAT_SUPP (LMAI_AGENT | LMAI_REMOTE_PARENT) +#define LMA_INCOMPAT_SUPP (LMAI_AGENT | LMAI_REMOTE_PARENT | LMAI_STRIPED) extern void lustre_lma_swab(struct lustre_mdt_attrs *lma); extern void lustre_lma_init(struct lustre_mdt_attrs *lma, const struct lu_fid *fid, __u32 compat, __u32 incompat); -/** - * SOM on-disk attributes stored in a separate xattr. - */ -struct som_attrs { - /** Bitfield for supported data in this structure. For future use. */ - __u32 som_compat; - /** Incompat feature list. The supported feature mask is availabe in - * SOM_INCOMPAT_SUPP */ - __u32 som_incompat; - - /** IO Epoch SOM attributes belongs to */ - __u64 som_ioepoch; - /** total file size in objects */ - __u64 som_size; - /** total fs blocks in objects */ - __u64 som_blocks; - /** mds mount id the size is valid for */ - __u64 som_mountid; -}; -extern void lustre_som_swab(struct som_attrs *attrs); - -#define SOM_INCOMPAT_SUPP 0x0 +/* copytool uses a 32b bitmask field to encode archive-Ids during register + * with MDT thru kuc. + * archive num = 0 => all + * archive num from 1 to 32 + */ +#define LL_HSM_MAX_ARCHIVE (sizeof(__u32) * 8) /** * HSM on-disk attributes stored in a separate xattr. @@ -421,7 +384,7 @@ static inline void fid_zero(struct lu_fid *fid) memset(fid, 0, sizeof(*fid)); } -static inline obd_id fid_ver_oid(const struct lu_fid *fid) +static inline __u64 fid_ver_oid(const struct lu_fid *fid) { return ((__u64)fid_ver(fid) << 32 | fid_oid(fid)); } @@ -438,8 +401,8 @@ enum fid_seq { FID_SEQ_OST_MDT0 = 0, FID_SEQ_LLOG = 1, /* unnamed llogs */ FID_SEQ_ECHO = 2, - FID_SEQ_OST_MDT1 = 3, - FID_SEQ_OST_MAX = 9, /* Max MDT count before OST_on_FID */ + FID_SEQ_UNUSED_START = 3, + FID_SEQ_UNUSED_END = 9, FID_SEQ_LLOG_NAME = 10, /* named llogs */ FID_SEQ_RSVD = 11, FID_SEQ_IGIF = 12, @@ -463,6 +426,11 @@ enum fid_seq { FID_SEQ_QUOTA_GLB = 0x200000006ULL, FID_SEQ_ROOT = 0x200000007ULL, /* Located on MDT0 */ FID_SEQ_LAYOUT_RBTREE = 0x200000008ULL, + /* sequence is used for update logs of cross-MDT operation */ + FID_SEQ_UPDATE_LOG = 0x200000009ULL, + /* Sequence is used for the directory under which update logs + * are created. */ + FID_SEQ_UPDATE_LOG_DIR = 0x20000000aULL, FID_SEQ_NORMAL = 0x200000400ULL, FID_SEQ_LOV_DEFAULT = 0xffffffffffffffffULL }; @@ -487,7 +455,13 @@ enum dot_lustre_oid { FID_OID_DOT_LUSTRE_LPF = 3UL, }; -static inline bool fid_seq_is_mdt0(obd_seq seq) +/** OID for FID_SEQ_ROOT */ +enum root_oid { + FID_OID_ROOT = 1UL, + FID_OID_ECHO_ROOT = 2UL, +}; + +static inline bool fid_seq_is_mdt0(__u64 seq) { return seq == FID_SEQ_OST_MDT0; } @@ -497,7 +471,7 @@ static inline bool fid_seq_is_mdt(__u64 seq) return seq == FID_SEQ_OST_MDT0 || seq >= FID_SEQ_NORMAL; }; -static inline bool fid_seq_is_echo(obd_seq seq) +static inline bool fid_seq_is_echo(__u64 seq) { return seq == FID_SEQ_ECHO; } @@ -507,7 +481,7 @@ static inline bool fid_is_echo(const struct lu_fid *fid) return fid_seq_is_echo(fid_seq(fid)); } -static inline bool fid_seq_is_llog(obd_seq seq) +static inline bool fid_seq_is_llog(__u64 seq) { return seq == FID_SEQ_LLOG; } @@ -557,14 +531,35 @@ static inline bool fid_is_mdt0(const struct lu_fid *fid) static inline void lu_root_fid(struct lu_fid *fid) { fid->f_seq = FID_SEQ_ROOT; - fid->f_oid = 1; + fid->f_oid = FID_OID_ROOT; + fid->f_ver = 0; +} + +static inline void lu_echo_root_fid(struct lu_fid *fid) +{ + fid->f_seq = FID_SEQ_ROOT; + fid->f_oid = FID_OID_ECHO_ROOT; + fid->f_ver = 0; +} + +static inline void lu_update_log_fid(struct lu_fid *fid, __u32 index) +{ + fid->f_seq = FID_SEQ_UPDATE_LOG; + fid->f_oid = index; + fid->f_ver = 0; +} + +static inline void lu_update_log_dir_fid(struct lu_fid *fid, __u32 index) +{ + fid->f_seq = FID_SEQ_UPDATE_LOG_DIR; + fid->f_oid = index; fid->f_ver = 0; } /** * Check if a fid is igif or not. * \param fid the fid to be tested. - * \return true if the fid is a igif; otherwise false. + * \return true if the fid is an igif; otherwise false. */ static inline bool fid_seq_is_igif(__u64 seq) { @@ -579,7 +574,7 @@ static inline bool fid_is_igif(const struct lu_fid *fid) /** * Check if a fid is idif or not. * \param fid the fid to be tested. - * \return true if the fid is a idif; otherwise false. + * \return true if the fid is an idif; otherwise false. */ static inline bool fid_seq_is_idif(__u64 seq) { @@ -611,19 +606,39 @@ static inline int fid_is_layout_rbtree(const struct lu_fid *fid) return fid_seq(fid) == FID_SEQ_LAYOUT_RBTREE; } +static inline bool fid_seq_is_update_log(__u64 seq) +{ + return seq == FID_SEQ_UPDATE_LOG; +} + +static inline bool fid_is_update_log(const struct lu_fid *fid) +{ + return fid_seq_is_update_log(fid_seq(fid)); +} + +static inline bool fid_seq_is_update_log_dir(__u64 seq) +{ + return seq == FID_SEQ_UPDATE_LOG_DIR; +} + +static inline bool fid_is_update_log_dir(const struct lu_fid *fid) +{ + return fid_seq_is_update_log_dir(fid_seq(fid)); +} + /* convert an OST objid into an IDIF FID SEQ number */ -static inline obd_seq fid_idif_seq(obd_id id, __u32 ost_idx) +static inline __u64 fid_idif_seq(__u64 id, __u32 ost_idx) { return FID_SEQ_IDIF | (ost_idx << 16) | ((id >> 32) & 0xffff); } /* convert a packed IDIF FID into an OST objid */ -static inline obd_id fid_idif_id(obd_seq seq, __u32 oid, __u32 ver) +static inline __u64 fid_idif_id(__u64 seq, __u32 oid, __u32 ver) { return ((__u64)ver << 48) | ((seq & 0xffff) << 32) | oid; } -static inline __u32 idif_ost_idx(obd_seq seq) +static inline __u32 idif_ost_idx(__u64 seq) { return (seq >> 16) & 0xffff; } @@ -635,7 +650,7 @@ static inline __u32 fid_idif_ost_idx(const struct lu_fid *fid) } /* extract OST sequence (group) from a wire ost_id (id/seq) pair */ -static inline obd_seq ostid_seq(const struct ost_id *ostid) +static inline __u64 ostid_seq(const struct ost_id *ostid) { if (fid_seq_is_mdt0(ostid->oi.oi_seq)) return FID_SEQ_OST_MDT0; @@ -650,7 +665,7 @@ static inline obd_seq ostid_seq(const struct ost_id *ostid) } /* extract OST objid from a wire ost_id (id/seq) pair */ -static inline obd_id ostid_id(const struct ost_id *ostid) +static inline __u64 ostid_id(const struct ost_id *ostid) { if (fid_seq_is_mdt0(ostid->oi.oi_seq)) return ostid->oi.oi_id & IDIF_OID_MASK; @@ -766,7 +781,7 @@ static inline int fid_set_id(struct lu_fid *fid, __u64 oid) static inline int ostid_to_fid(struct lu_fid *fid, const struct ost_id *ostid, __u32 ost_idx) { - obd_seq seq = ostid_seq(ostid); + __u64 seq = ostid_seq(ostid); if (ost_idx > 0xffff) { CERROR("bad ost_idx, "DOSTID" ost_idx:%u\n", POSTID(ostid), @@ -775,7 +790,7 @@ static inline int ostid_to_fid(struct lu_fid *fid, const struct ost_id *ostid, } if (fid_seq_is_mdt0(seq)) { - obd_id oid = ostid_id(ostid); + __u64 oid = ostid_id(ostid); /* This is a "legacy" (old 1.x/2.early) OST object in "group 0" * that we map into the IDIF namespace. It allows up to 2^48 @@ -783,9 +798,9 @@ static inline int ostid_to_fid(struct lu_fid *fid, const struct ost_id *ostid, * been in production for years. This can handle create rates * of 1M objects/s/OST for 9 years, or combinations thereof. */ if (oid >= IDIF_MAX_OID) { - CERROR("bad MDT0 id, "DOSTID" ost_idx:%u\n", - POSTID(ostid), ost_idx); - return -EBADF; + CERROR("bad MDT0 id(1), "DOSTID" ost_idx:%u\n", + POSTID(ostid), ost_idx); + return -EBADF; } fid->f_seq = fid_idif_seq(oid, ost_idx); /* truncate to 32 bits by assignment */ @@ -799,7 +814,7 @@ static inline int ostid_to_fid(struct lu_fid *fid, const struct ost_id *ostid, * OST objects into the FID namespace. In both cases, we just * pass the FID through, no conversion needed. */ if (ostid->oi_fid.f_ver != 0) { - CERROR("bad MDT0 id, "DOSTID" ost_idx:%u\n", + CERROR("bad MDT0 id(2), "DOSTID" ost_idx:%u\n", POSTID(ostid), ost_idx); return -EBADF; } @@ -831,12 +846,13 @@ static inline int fid_to_ostid(const struct lu_fid *fid, struct ost_id *ostid) /* Check whether the fid is for LAST_ID */ static inline bool fid_is_last_id(const struct lu_fid *fid) { - return fid_oid(fid) == 0; + return fid_oid(fid) == 0 && fid_seq(fid) != FID_SEQ_UPDATE_LOG && + fid_seq(fid) != FID_SEQ_UPDATE_LOG_DIR; } /** - * Get inode number from a igif. - * \param fid a igif to get inode number from. + * Get inode number from an igif. + * \param fid an igif to get inode number from. * \return inode number for the igif. */ static inline ino_t lu_igif_ino(const struct lu_fid *fid) @@ -847,8 +863,8 @@ static inline ino_t lu_igif_ino(const struct lu_fid *fid) extern void lustre_swab_ost_id(struct ost_id *oid); /** - * Get inode generation from a igif. - * \param fid a igif to get inode generation from. + * Get inode generation from an igif. + * \param fid an igif to get inode generation from. * \return inode generation for the igif. */ static inline __u32 lu_igif_gen(const struct lu_fid *fid) @@ -906,11 +922,6 @@ static inline bool fid_is_sane(const struct lu_fid *fid) fid_seq_is_rsvd(fid_seq(fid))); } -static inline bool fid_is_zero(const struct lu_fid *fid) -{ - return fid_seq(fid) == 0 && fid_oid(fid) == 0; -} - extern void lustre_swab_lu_fid(struct lu_fid *fid); extern void lustre_swab_lu_seq_range(struct lu_seq_range *range); @@ -939,7 +950,7 @@ static inline int lu_fid_cmp(const struct lu_fid *f0, static inline void ostid_cpu_to_le(const struct ost_id *src_oi, struct ost_id *dst_oi) { - if (fid_seq_is_mdt0(ostid_seq(src_oi))) { + if (fid_seq_is_mdt0(src_oi->oi.oi_seq)) { dst_oi->oi.oi_id = cpu_to_le64(src_oi->oi.oi_id); dst_oi->oi.oi_seq = cpu_to_le64(src_oi->oi.oi_seq); } else { @@ -950,7 +961,7 @@ static inline void ostid_cpu_to_le(const struct ost_id *src_oi, static inline void ostid_le_to_cpu(const struct ost_id *src_oi, struct ost_id *dst_oi) { - if (fid_seq_is_mdt0(ostid_seq(src_oi))) { + if (fid_seq_is_mdt0(src_oi->oi.oi_seq)) { dst_oi->oi.oi_id = le64_to_cpu(src_oi->oi.oi_id); dst_oi->oi.oi_seq = le64_to_cpu(src_oi->oi.oi_seq); } else { @@ -972,6 +983,9 @@ struct lu_orphan_ent { }; void lustre_swab_orphan_ent(struct lu_orphan_ent *ent); +struct update_ops; +void lustre_swab_update_ops(struct update_ops *uops, unsigned int op_count); + /** @} lu_fid */ /** \defgroup lu_dir lu_dir @@ -988,7 +1002,7 @@ enum lu_dirent_attrs { LUDA_TYPE = 0x0002, LUDA_64BITHASH = 0x0004, - /* The following attrs are used for MDT interanl only, + /* The following attrs are used for MDT internal only, * not visible to client */ /* Verify the dirent consistency */ @@ -1095,12 +1109,12 @@ static inline struct lu_dirent *lu_dirent_next(struct lu_dirent *ent) return next; } -static inline int lu_dirent_calc_size(int namelen, __u16 attr) +static inline size_t lu_dirent_calc_size(size_t namelen, __u16 attr) { - int size; + size_t size; - if (attr & LUDA_TYPE) { - const unsigned align = sizeof(struct luda_type) - 1; + if (attr & LUDA_TYPE) { + const size_t align = sizeof(struct luda_type) - 1; size = (sizeof(struct lu_dirent) + namelen + align) & ~align; size += sizeof(struct luda_type); } else @@ -1109,15 +1123,6 @@ static inline int lu_dirent_calc_size(int namelen, __u16 attr) return (size + 7) & ~7; } -static inline int lu_dirent_size(const struct lu_dirent *ent) -{ - if (le16_to_cpu(ent->lde_reclen) == 0) { - return lu_dirent_calc_size(le16_to_cpu(ent->lde_namelen), - le32_to_cpu(ent->lde_attrs)); - } - return le16_to_cpu(ent->lde_reclen); -} - #define MDS_DIR_END_OFF 0xfffffffffffffffeULL /** @@ -1180,15 +1185,16 @@ struct lustre_msg_v2 { /* without gss, ptlrpc_body is put at the first buffer. */ #define PTLRPC_NUM_VERSIONS 4 -#define JOBSTATS_JOBID_SIZE 32 /* 32 bytes string */ struct ptlrpc_body_v3 { struct lustre_handle pb_handle; __u32 pb_type; __u32 pb_version; __u32 pb_opc; __u32 pb_status; - __u64 pb_last_xid; - __u64 pb_last_seen; + __u64 pb_last_xid; /* highest replied XID without lower unreplied XID */ + __u16 pb_tag; /* virtual slot idx for multiple modifying RPCs */ + __u16 pb_padding0; + __u32 pb_padding1; __u64 pb_last_committed; __u64 pb_transno; __u32 pb_flags; @@ -1202,7 +1208,7 @@ struct ptlrpc_body_v3 { __u64 pb_pre_versions[PTLRPC_NUM_VERSIONS]; /* padding for future needs */ __u64 pb_padding[4]; - char pb_jobid[JOBSTATS_JOBID_SIZE]; + char pb_jobid[LUSTRE_JOBID_SIZE]; }; #define ptlrpc_body ptlrpc_body_v3 @@ -1212,8 +1218,10 @@ struct ptlrpc_body_v2 { __u32 pb_version; __u32 pb_opc; __u32 pb_status; - __u64 pb_last_xid; - __u64 pb_last_seen; + __u64 pb_last_xid; /* highest replied XID without lower unreplied XID */ + __u16 pb_tag; /* virtual slot idx for multiple modifying RPCs */ + __u16 pb_padding0; + __u32 pb_padding1; __u64 pb_last_committed; __u64 pb_transno; __u32 pb_flags; @@ -1352,6 +1360,10 @@ extern void lustre_swab_ptlrpc_body(struct ptlrpc_body *pb); #define OBD_CONNECT_OPEN_BY_FID 0x20000000000000ULL /* open by fid won't pack name in request */ #define OBD_CONNECT_LFSCK 0x40000000000000ULL/* support online LFSCK */ +#define OBD_CONNECT_UNLINK_CLOSE 0x100000000000000ULL/* close file in unlink */ +#define OBD_CONNECT_MULTIMODRPCS 0x200000000000000ULL /* support multiple modify + RPCs in parallel */ +#define OBD_CONNECT_DIR_STRIPE 0x400000000000000ULL /* striped DNE dir */ /* XXX README XXX: * Please DO NOT add flag values here before first ensuring that this same @@ -1389,14 +1401,16 @@ extern void lustre_swab_ptlrpc_body(struct ptlrpc_body *pb); OBD_CONNECT_OSS_CAPA | OBD_CONNECT_MDS_MDS | \ OBD_CONNECT_FID | LRU_RESIZE_CONNECT_FLAG | \ OBD_CONNECT_VBR | OBD_CONNECT_LOV_V3 | \ - OBD_CONNECT_SOM | OBD_CONNECT_FULL20 | \ + OBD_CONNECT_FULL20 | \ OBD_CONNECT_64BITHASH | OBD_CONNECT_JOBSTATS | \ OBD_CONNECT_EINPROGRESS | \ OBD_CONNECT_LIGHTWEIGHT | OBD_CONNECT_UMASK | \ OBD_CONNECT_LVB_TYPE | OBD_CONNECT_LAYOUTLOCK |\ OBD_CONNECT_PINGLESS | OBD_CONNECT_MAX_EASIZE |\ OBD_CONNECT_FLOCK_DEAD | \ - OBD_CONNECT_DISP_STRIPE | OBD_CONNECT_LFSCK) + OBD_CONNECT_DISP_STRIPE | OBD_CONNECT_LFSCK | \ + OBD_CONNECT_OPEN_BY_FID | \ + OBD_CONNECT_DIR_STRIPE) #define OST_CONNECT_SUPPORTED (OBD_CONNECT_SRVLOCK | OBD_CONNECT_GRANT | \ OBD_CONNECT_REQPORTAL | OBD_CONNECT_VERSION | \ @@ -1424,36 +1438,10 @@ extern void lustre_swab_ptlrpc_body(struct ptlrpc_body *pb); #define CLIENT_CONNECT_MDT_REQD (OBD_CONNECT_IBITS | OBD_CONNECT_FID | \ OBD_CONNECT_FULL20) -#define OBD_OCD_VERSION(major,minor,patch,fix) (((major)<<24) + ((minor)<<16) +\ - ((patch)<<8) + (fix)) -#define OBD_OCD_VERSION_MAJOR(version) ((int)((version)>>24)&255) -#define OBD_OCD_VERSION_MINOR(version) ((int)((version)>>16)&255) -#define OBD_OCD_VERSION_PATCH(version) ((int)((version)>>8)&255) -#define OBD_OCD_VERSION_FIX(version) ((int)(version)&255) - /* This structure is used for both request and reply. * * If we eventually have separate connect data for different types, which we * almost certainly will, then perhaps we stick a union in here. */ -struct obd_connect_data_v1 { - __u64 ocd_connect_flags; /* OBD_CONNECT_* per above */ - __u32 ocd_version; /* lustre release version number */ - __u32 ocd_grant; /* initial cache grant amount (bytes) */ - __u32 ocd_index; /* LOV index to connect to */ - __u32 ocd_brw_size; /* Maximum BRW size in bytes, must be 2^n */ - __u64 ocd_ibits_known; /* inode bits this client understands */ - __u8 ocd_blocksize; /* log2 of the backend filesystem blocksize */ - __u8 ocd_inodespace; /* log2 of the per-inode space consumption */ - __u16 ocd_grant_extent; /* per-extent grant overhead, in 1K blocks */ - __u32 ocd_unused; /* also fix lustre_swab_connect */ - __u64 ocd_transno; /* first transno from client to be replayed */ - __u32 ocd_group; /* MDS group on OST */ - __u32 ocd_cksum_types; /* supported checksum algorithms */ - __u32 ocd_max_easize; /* How big LOV EA can be on MDS */ - __u32 ocd_instance; /* also fix lustre_swab_connect */ - __u64 ocd_maxbytes; /* Maximum stripe size in bytes */ -}; - struct obd_connect_data { __u64 ocd_connect_flags; /* OBD_CONNECT_* per above */ __u32 ocd_version; /* lustre release version number */ @@ -1475,7 +1463,9 @@ struct obd_connect_data { * if the corresponding flag in ocd_connect_flags is set. Accessing * any field after ocd_maxbytes on the receiver without a valid flag * may result in out-of-bound memory access and kernel oops. */ - __u64 padding1; /* added 2.1.0. also fix lustre_swab_connect */ + __u16 ocd_maxmodrpcs; /* Maximum modify RPCs in parallel */ + __u16 padding0; /* added 2.1.0. also fix lustre_swab_connect */ + __u32 padding1; /* added 2.1.0. also fix lustre_swab_connect */ __u64 padding2; /* added 2.1.0. also fix lustre_swab_connect */ __u64 padding3; /* added 2.1.0. also fix lustre_swab_connect */ __u64 padding4; /* added 2.1.0. also fix lustre_swab_connect */ @@ -1536,7 +1526,7 @@ typedef enum { OST_STATFS = 13, OST_SYNC = 16, OST_SET_INFO = 17, - OST_QUOTACHECK = 18, + OST_QUOTACHECK = 18, /* not used since 2.4 */ OST_QUOTACTL = 19, OST_QUOTA_ADJUST_QUNIT = 20, /* not used since 2.4 */ OST_LAST_OPC @@ -1592,6 +1582,8 @@ enum obdo_flags { #define LOV_MAGIC_JOIN_V1 (0x0BD20000 | LOV_MAGIC_MAGIC) #define LOV_MAGIC_V3 (0x0BD30000 | LOV_MAGIC_MAGIC) #define LOV_MAGIC_MIGRATE (0x0BD40000 | LOV_MAGIC_MAGIC) +/* reserved for specifying OSTs */ +#define LOV_MAGIC_SPECIFIC (0x0BD50000 | LOV_MAGIC_MAGIC) #define LOV_MAGIC LOV_MAGIC_V1 /* @@ -1609,14 +1601,6 @@ enum obdo_flags { #define LOV_MAGIC_V1_DEF 0x0CD10BD0 #define LOV_MAGIC_V3_DEF 0x0CD30BD0 -#define LOV_PATTERN_RAID0 0x001 /* stripes are used round-robin */ -#define LOV_PATTERN_RAID1 0x002 /* stripes are mirrors of each other */ -#define LOV_PATTERN_FIRST 0x100 /* first stripe is not in round-robin */ -#define LOV_PATTERN_CMOBD 0x200 - -#define LOV_PATTERN_F_MASK 0xffff0000 -#define LOV_PATTERN_F_RELEASED 0x80000000 /* HSM released file */ - #define lov_pattern(pattern) (pattern & ~LOV_PATTERN_F_MASK) #define lov_pattern_flags(pattern) (pattern & LOV_PATTERN_F_MASK) @@ -1720,7 +1704,6 @@ static inline void lmm_oi_cpu_to_le(struct ost_id *dst_oi, #define XATTR_USER_PREFIX "user." #define XATTR_TRUSTED_PREFIX "trusted." #define XATTR_SECURITY_PREFIX "security." -#define XATTR_LUSTRE_PREFIX "lustre." #define XATTR_NAME_LOV "trusted.lov" #define XATTR_NAME_LMA "trusted.lma" @@ -1731,7 +1714,14 @@ static inline void lmm_oi_cpu_to_le(struct ost_id *dst_oi, #define XATTR_NAME_VERSION "trusted.version" #define XATTR_NAME_SOM "trusted.som" #define XATTR_NAME_HSM "trusted.hsm" -#define XATTR_NAME_LFSCK_NAMESPACE "trusted.lfsck_namespace" +#define XATTR_NAME_LFSCK_BITMAP "trusted.lfsck_bitmap" +#define XATTR_NAME_DUMMY "trusted.dummy" + +#if LUSTRE_VERSION_CODE < OBD_OCD_VERSION(2, 8, 53, 0) +# define XATTR_NAME_LFSCK_NAMESPACE_OLD "trusted.lfsck_namespace" +#endif + +#define XATTR_NAME_LFSCK_NAMESPACE "trusted.lfsck_ns" #define XATTR_NAME_MAX_LEN 32 /* increase this, if there is longer name. */ struct lov_mds_md_v3 { /* LOV EA mds/wire data (little-endian) */ @@ -1742,7 +1732,7 @@ struct lov_mds_md_v3 { /* LOV EA mds/wire data (little-endian) */ /* lmm_stripe_count used to be __u32 */ __u16 lmm_stripe_count; /* num stripes in use for this object */ __u16 lmm_layout_gen; /* layout generation number */ - char lmm_pool_name[LOV_MAXPOOLNAME]; /* must be 32bit aligned */ + char lmm_pool_name[LOV_MAXPOOLNAME + 1]; /* must be 32bit aligned */ struct lov_ost_data_v1 lmm_objects[0]; /* per-stripe data */ }; @@ -1803,7 +1793,7 @@ lov_mds_md_max_stripe_count(size_t buf_size, __u32 lmm_magic) #define OBD_MD_FLCKSUM (0x00100000ULL) /* bulk data checksum */ #define OBD_MD_FLQOS (0x00200000ULL) /* quality of service stats */ /*#define OBD_MD_FLOSCOPQ (0x00400000ULL) osc opaque data, never used */ -#define OBD_MD_FLCOOKIE (0x00800000ULL) /* log cancellation cookie */ +/* OBD_MD_FLCOOKIE (0x00800000ULL) obsolete in 2.8 */ #define OBD_MD_FLGROUP (0x01000000ULL) /* group */ #define OBD_MD_FLFID (0x02000000ULL) /* ->ost write inline fid */ #define OBD_MD_FLEPOCH (0x04000000ULL) /* ->ost write with ioepoch */ @@ -1840,7 +1830,8 @@ lov_mds_md_max_stripe_count(size_t buf_size, __u32 lmm_magic) #define OBD_MD_FLRMTRGETFACL (0x0008000000000000ULL) /* lfs rgetfacl case */ #define OBD_MD_FLDATAVERSION (0x0010000000000000ULL) /* iversion sum */ -#define OBD_MD_FLRELEASED (0x0020000000000000ULL) /* file released */ +#define OBD_MD_CLOSE_INTENT_EXECED (0x0020000000000000ULL) /* close intent + executed */ #define OBD_MD_DEFAULT_MEA (0x0040000000000000ULL) /* default MEA */ @@ -1896,7 +1887,7 @@ extern void lustre_swab_obd_statfs (struct obd_statfs *os); * space for unstable pages; asking * it to sync quickly */ -#define OBD_OBJECT_EOF 0xffffffffffffffffULL +#define OBD_OBJECT_EOF LUSTRE_EOF #define OST_MIN_PRECREATE 32 #define OST_MAX_PRECREATE 20000 @@ -1919,12 +1910,12 @@ extern void lustre_swab_obd_ioobj (struct obd_ioobj *ioo); /* multiple of 8 bytes => can array */ struct niobuf_remote { - __u64 offset; - __u32 len; - __u32 flags; + __u64 rnb_offset; + __u32 rnb_len; + __u32 rnb_flags; }; -extern void lustre_swab_niobuf_remote (struct niobuf_remote *nbr); +void lustre_swab_niobuf_remote(struct niobuf_remote *nbr); /* lock value block communicated between the filter and llite */ @@ -1939,25 +1930,25 @@ extern void lustre_swab_niobuf_remote (struct niobuf_remote *nbr); #define OST_LVB_GET_ERR(blocks) (int)(blocks - OST_LVB_ERR_INIT) struct ost_lvb_v1 { - __u64 lvb_size; - obd_time lvb_mtime; - obd_time lvb_atime; - obd_time lvb_ctime; - __u64 lvb_blocks; + __u64 lvb_size; + __s64 lvb_mtime; + __s64 lvb_atime; + __s64 lvb_ctime; + __u64 lvb_blocks; }; extern void lustre_swab_ost_lvb_v1(struct ost_lvb_v1 *lvb); struct ost_lvb { - __u64 lvb_size; - obd_time lvb_mtime; - obd_time lvb_atime; - obd_time lvb_ctime; - __u64 lvb_blocks; - __u32 lvb_mtime_ns; - __u32 lvb_atime_ns; - __u32 lvb_ctime_ns; - __u32 lvb_padding; + __u64 lvb_size; + __s64 lvb_mtime; + __s64 lvb_atime; + __s64 lvb_ctime; + __u64 lvb_blocks; + __u32 lvb_mtime_ns; + __u32 lvb_atime_ns; + __u32 lvb_ctime_ns; + __u32 lvb_padding; }; extern void lustre_swab_ost_lvb(struct ost_lvb *lvb); @@ -1967,15 +1958,15 @@ extern void lustre_swab_ost_lvb(struct ost_lvb *lvb); */ #ifndef QUOTABLOCK_BITS -#define QUOTABLOCK_BITS 10 +# define QUOTABLOCK_BITS LUSTRE_QUOTABLOCK_BITS #endif #ifndef QUOTABLOCK_SIZE -#define QUOTABLOCK_SIZE (1 << QUOTABLOCK_BITS) +# define QUOTABLOCK_SIZE LUSTRE_QUOTABLOCK_SIZE #endif #ifndef toqb -#define toqb(x) (((x) + QUOTABLOCK_SIZE - 1) >> QUOTABLOCK_BITS) +# define toqb lustre_stoqb #endif /* The lquota_id structure is an union of all the possible identifier types that @@ -2001,12 +1992,6 @@ struct obd_quotactl { extern void lustre_swab_obd_quotactl(struct obd_quotactl *q); -#define Q_QUOTACHECK 0x800100 /* deprecated as of 2.4 */ -#define Q_INITQUOTA 0x800101 /* deprecated as of 2.4 */ -#define Q_GETOINFO 0x800102 /* get obd quota info */ -#define Q_GETOQUOTA 0x800103 /* get obd quotas */ -#define Q_FINVALIDATE 0x800104 /* deprecated as of 2.4 */ - #define Q_COPY(out, in, member) (out)->member = (in)->member #define QCTL_COPY(out, in) \ @@ -2156,17 +2141,17 @@ typedef enum { MDS_DISCONNECT = 39, MDS_GETSTATUS = 40, MDS_STATFS = 41, - MDS_PIN = 42, - MDS_UNPIN = 43, + MDS_PIN = 42, /* obsolete, never used in a release */ + MDS_UNPIN = 43, /* obsolete, never used in a release */ MDS_SYNC = 44, - MDS_DONE_WRITING = 45, + MDS_DONE_WRITING = 45, /* obsolete since 2.8.0 */ MDS_SET_INFO = 46, - MDS_QUOTACHECK = 47, + MDS_QUOTACHECK = 47, /* not used since 2.4 */ MDS_QUOTACTL = 48, MDS_GETXATTR = 49, MDS_SETXATTR = 50, /* obsolete, now it's MDS_REINT op */ MDS_WRITEPAGE = 51, - MDS_IS_SUBDIR = 52, + MDS_IS_SUBDIR = 52, /* obsolete, never used in a release */ MDS_GET_INFO = 53, MDS_HSM_STATE_GET = 54, MDS_HSM_STATE_SET = 55, @@ -2222,6 +2207,7 @@ extern void lustre_swab_generic_32s (__u32 *val); #define DISP_OPEN_LOCK 0x02000000 #define DISP_OPEN_LEASE 0x04000000 #define DISP_OPEN_STRIPE 0x08000000 +#define DISP_OPEN_DENY 0x10000000 /* INODE LOCK PARTS */ #define MDS_INODELOCK_LOOKUP 0x000001 /* For namespace, dentry etc, and also @@ -2264,26 +2250,6 @@ enum { #define MDS_STATUS_CONN 1 #define MDS_STATUS_LOV 2 -/* mdt_thread_info.mti_flags. */ -enum md_op_flags { - /* The flag indicates Size-on-MDS attributes are changed. */ - MF_SOM_CHANGE = (1 << 0), - /* Flags indicates an epoch opens or closes. */ - MF_EPOCH_OPEN = (1 << 1), - MF_EPOCH_CLOSE = (1 << 2), - MF_MDC_CANCEL_FID1 = (1 << 3), - MF_MDC_CANCEL_FID2 = (1 << 4), - MF_MDC_CANCEL_FID3 = (1 << 5), - MF_MDC_CANCEL_FID4 = (1 << 6), - /* There is a pending attribute update. */ - MF_SOM_AU = (1 << 7), - /* Cancel OST locks while getattr OST attributes. */ - MF_GETATTR_LOCK = (1 << 8), - MF_GET_MDT_IDX = (1 << 9), -}; - -#define MF_SOM_LOCAL_FLAGS (MF_SOM_CHANGE | MF_EPOCH_OPEN | MF_EPOCH_CLOSE) - #define LUSTRE_BFLAG_UNCOMMITTED_WRITES 0x1 /* these should be identical to their EXT4_*_FL counterparts, they are @@ -2330,51 +2296,51 @@ enum md_transient_state { }; struct mdt_body { - struct lu_fid fid1; - struct lu_fid fid2; - struct lustre_handle handle; - __u64 valid; - __u64 size; /* Offset, in the case of MDS_READPAGE */ - obd_time mtime; - obd_time atime; - obd_time ctime; - __u64 blocks; /* XID, in the case of MDS_READPAGE */ - __u64 ioepoch; - __u64 t_state; /* transient file state defined in - * enum md_transient_state - * was "ino" until 2.4.0 */ - __u32 fsuid; - __u32 fsgid; - __u32 capability; - __u32 mode; - __u32 uid; - __u32 gid; - __u32 flags; /* from vfs for pin/unpin, LUSTRE_BFLAG close */ - __u32 rdev; - __u32 nlink; /* #bytes to read in the case of MDS_READPAGE */ - __u32 unused2; /* was "generation" until 2.4.0 */ - __u32 suppgid; - __u32 eadatasize; - __u32 aclsize; - __u32 max_mdsize; - __u32 max_cookiesize; - __u32 uid_h; /* high 32-bits of uid, for FUID */ - __u32 gid_h; /* high 32-bits of gid, for FUID */ - __u32 padding_5; /* also fix lustre_swab_mdt_body */ - __u64 padding_6; - __u64 padding_7; - __u64 padding_8; - __u64 padding_9; - __u64 padding_10; + struct lu_fid mbo_fid1; + struct lu_fid mbo_fid2; + struct lustre_handle mbo_handle; + __u64 mbo_valid; + __u64 mbo_size; /* Offset, in the case of MDS_READPAGE */ + __s64 mbo_mtime; + __s64 mbo_atime; + __s64 mbo_ctime; + __u64 mbo_blocks; /* XID, in the case of MDS_READPAGE */ + __u64 mbo_ioepoch; + __u64 mbo_t_state; /* transient file state defined in + * enum md_transient_state + * was "ino" until 2.4.0 */ + __u32 mbo_fsuid; + __u32 mbo_fsgid; + __u32 mbo_capability; + __u32 mbo_mode; + __u32 mbo_uid; + __u32 mbo_gid; + __u32 mbo_flags; + __u32 mbo_rdev; + __u32 mbo_nlink; /* #bytes to read in the case of MDS_READPAGE */ + __u32 mbo_unused2; /* was "generation" until 2.4.0 */ + __u32 mbo_suppgid; + __u32 mbo_eadatasize; + __u32 mbo_aclsize; + __u32 mbo_max_mdsize; + __u32 mbo_unused3; /* was max_cookiesize until 2.8 */ + __u32 mbo_uid_h; /* high 32-bits of uid, for FUID */ + __u32 mbo_gid_h; /* high 32-bits of gid, for FUID */ + __u32 mbo_padding_5; /* also fix lustre_swab_mdt_body */ + __u64 mbo_padding_6; + __u64 mbo_padding_7; + __u64 mbo_padding_8; + __u64 mbo_padding_9; + __u64 mbo_padding_10; }; /* 216 */ extern void lustre_swab_mdt_body (struct mdt_body *b); struct mdt_ioepoch { - struct lustre_handle handle; - __u64 ioepoch; - __u32 flags; - __u32 padding; + struct lustre_handle mio_handle; + __u64 mio_unused1; /* was ioepoch */ + __u32 mio_unused2; /* was flags */ + __u32 mio_padding; }; extern void lustre_swab_mdt_ioepoch (struct mdt_ioepoch *b); @@ -2420,9 +2386,9 @@ struct mdt_rec_setattr { __u32 sa_gid; __u64 sa_size; __u64 sa_blocks; - obd_time sa_mtime; - obd_time sa_atime; - obd_time sa_ctime; + __s64 sa_mtime; + __s64 sa_atime; + __s64 sa_ctime; __u32 sa_attr_flags; __u32 sa_mode; __u32 sa_bias; /* some operation flags */ @@ -2463,12 +2429,9 @@ extern void lustre_swab_mdt_rec_setattr (struct mdt_rec_setattr *sa); #define MDS_FMODE_CLOSED 00000000 #define MDS_FMODE_EXEC 00000004 -/* IO Epoch is opened on a closed file. */ -#define MDS_FMODE_EPOCH 01000000 -/* IO Epoch is opened on a file truncate. */ -#define MDS_FMODE_TRUNC 02000000 -/* Size-on-MDS Attribute Update is pending. */ -#define MDS_FMODE_SOM 04000000 +/* MDS_FMODE_EPOCH 01000000 obsolete since 2.8.0 */ +/* MDS_FMODE_TRUNC 02000000 obsolete since 2.8.0 */ +/* MDS_FMODE_SOM 04000000 obsolete since 2.8.0 */ #define MDS_OPEN_CREATED 00000010 #define MDS_OPEN_CROSS 00000020 @@ -2503,6 +2466,12 @@ extern void lustre_swab_mdt_rec_setattr (struct mdt_rec_setattr *sa); */ #define MDS_OPEN_RELEASE 02000000000000ULL /* Open the file for HSM release */ +/* lustre internal open flags, which should not be set from user space */ +#define MDS_OPEN_FL_INTERNAL (MDS_OPEN_HAS_EA | MDS_OPEN_HAS_OBJS | \ + MDS_OPEN_OWNEROVERRIDE | MDS_OPEN_LOCK | \ + MDS_OPEN_BY_FID | MDS_OPEN_LEASE | \ + MDS_OPEN_RELEASE) + /* permission for create non-directory file */ #define MAY_CREATE (1 << 7) /* permission for create directory file */ @@ -2525,7 +2494,7 @@ enum mds_op_bias { MDS_CROSS_REF = 1 << 1, MDS_VTX_BYPASS = 1 << 2, MDS_PERM_BYPASS = 1 << 3, - MDS_SOM = 1 << 4, +/* MDS_SOM = 1 << 4, obsolete since 2.8.0 */ MDS_QUOTA_IGNORE = 1 << 5, /* Was MDS_CLOSE_CLEANUP (1 << 6), No more used */ MDS_KEEP_ORPHAN = 1 << 7, @@ -2535,6 +2504,7 @@ enum mds_op_bias { MDS_OWNEROVERRIDE = 1 << 11, MDS_HSM_RELEASE = 1 << 12, MDS_RENAME_MIGRATE = 1 << 13, + MDS_CLOSE_LAYOUT_SWAP = 1 << 14, }; /* instance of mdt_reint_rec */ @@ -2552,7 +2522,7 @@ struct mdt_rec_create { struct lu_fid cr_fid1; struct lu_fid cr_fid2; struct lustre_handle cr_old_handle; /* handle in case of open replay */ - obd_time cr_time; + __s64 cr_time; __u64 cr_rdev; __u64 cr_ioepoch; __u64 cr_padding_1; /* rr_blocks */ @@ -2592,7 +2562,7 @@ struct mdt_rec_link { __u32 lk_suppgid2_h; struct lu_fid lk_fid1; struct lu_fid lk_fid2; - obd_time lk_time; + __s64 lk_time; __u64 lk_padding_1; /* rr_atime */ __u64 lk_padding_2; /* rr_ctime */ __u64 lk_padding_3; /* rr_size */ @@ -2619,7 +2589,7 @@ struct mdt_rec_unlink { __u32 ul_suppgid2_h; struct lu_fid ul_fid1; struct lu_fid ul_fid2; - obd_time ul_time; + __s64 ul_time; __u64 ul_padding_2; /* rr_atime */ __u64 ul_padding_3; /* rr_ctime */ __u64 ul_padding_4; /* rr_size */ @@ -2646,7 +2616,7 @@ struct mdt_rec_rename { __u32 rn_suppgid2_h; struct lu_fid rn_fid1; struct lu_fid rn_fid2; - obd_time rn_time; + __s64 rn_time; __u64 rn_padding_1; /* rr_atime */ __u64 rn_padding_2; /* rr_ctime */ __u64 rn_padding_3; /* rr_size */ @@ -2676,7 +2646,7 @@ struct mdt_rec_setxattr { __u32 sx_padding_2; __u32 sx_padding_3; __u64 sx_valid; - obd_time sx_time; + __s64 sx_time; __u64 sx_padding_5; /* rr_ctime */ __u64 sx_padding_6; /* rr_size */ __u64 sx_padding_7; /* rr_blocks */ @@ -2709,9 +2679,9 @@ struct mdt_rec_reint { __u32 rr_suppgid2_h; struct lu_fid rr_fid1; struct lu_fid rr_fid2; - obd_time rr_mtime; - obd_time rr_atime; - obd_time rr_ctime; + __s64 rr_mtime; + __s64 rr_atime; + __s64 rr_ctime; __u64 rr_size; __u64 rr_blocks; __u32 rr_bias; @@ -2741,20 +2711,47 @@ struct lmv_desc { extern void lustre_swab_lmv_desc (struct lmv_desc *ld); -/* lmv structures */ -#define LMV_MAGIC_V1 0x0CD10CD0 /* normal stripe lmv magic */ -#define LMV_USER_MAGIC 0x0CD20CD0 /* default lmv magic*/ -#define LMV_MAGIC_MIGRATE 0x0CD30CD0 /* migrate stripe lmv magic */ +/* LMV layout EA, and it will be stored both in master and slave object */ +struct lmv_mds_md_v1 { + __u32 lmv_magic; + __u32 lmv_stripe_count; + __u32 lmv_master_mdt_index; /* On master object, it is master + * MDT index, on slave object, it + * is stripe index of the slave obj */ + __u32 lmv_hash_type; /* dir stripe policy, i.e. indicate + * which hash function to be used, + * Note: only lower 16 bits is being + * used for now. Higher 16 bits will + * be used to mark the object status, + * for example migrating or dead. */ + __u32 lmv_layout_version; /* Used for directory restriping */ + __u32 lmv_padding1; + __u64 lmv_padding2; + __u64 lmv_padding3; + char lmv_pool_name[LOV_MAXPOOLNAME + 1]; /* pool name */ + struct lu_fid lmv_stripe_fids[0]; /* FIDs for each stripe */ +}; + +#define LMV_MAGIC_V1 0x0CD20CD0 /* normal stripe lmv magic */ #define LMV_MAGIC LMV_MAGIC_V1 -enum lmv_hash_type { - LMV_HASH_TYPE_ALL_CHARS = 1, - LMV_HASH_TYPE_FNV_1A_64 = 2, - LMV_HASH_TYPE_MIGRATION = 3, -}; +/* #define LMV_USER_MAGIC 0x0CD30CD0 */ +#define LMV_MAGIC_STRIPE 0x0CD40CD0 /* magic for dir sub_stripe */ + +/* Right now only the lower part(0-16bits) of lmv_hash_type is being used, + * and the higher part will be the flag to indicate the status of object, + * for example the object is being migrated. And the hash function + * might be interpreted differently with different flags. */ +#define LMV_HASH_TYPE_MASK 0x0000ffff + +#define LMV_HASH_FLAG_MIGRATION 0x80000000 +#define LMV_HASH_FLAG_DEAD 0x40000000 +#define LMV_HASH_FLAG_BAD_TYPE 0x20000000 -#define LMV_HASH_NAME_ALL_CHARS "all_char" -#define LMV_HASH_NAME_FNV_1A_64 "fnv_1a_64" +/* The striped directory has ever lost its master LMV EA, then LFSCK + * re-generated it. This flag is used to indicate such case. It is an + * on-disk flag. */ +#define LMV_HASH_FLAG_LOST_LMV 0x10000000 /** * The FNV-1a hash algorithm is as follows: @@ -2784,18 +2781,6 @@ static inline __u64 lustre_hash_fnv_1a_64(const void *buf, size_t size) return hash; } -struct lmv_mds_md_v1 { - __u32 lmv_magic; - __u32 lmv_stripe_count; /* stripe count */ - __u32 lmv_master_mdt_index; /* master MDT index */ - __u32 lmv_hash_type; /* dir stripe policy, i.e. indicate - * which hash function to be used */ - __u32 lmv_layout_version; /* Used for directory restriping */ - __u32 lmv_padding; - char lmv_pool_name[LOV_MAXPOOLNAME]; /* pool name */ - struct lu_fid lmv_stripe_fids[0]; /* FIDs for each stripe */ -}; - union lmv_mds_md { __u32 lmv_magic; struct lmv_mds_md_v1 lmv_md_v1; @@ -2807,8 +2792,7 @@ extern void lustre_swab_lmv_mds_md(union lmv_mds_md *lmm); static inline int lmv_mds_md_size(int stripe_count, unsigned int lmm_magic) { switch (lmm_magic) { - case LMV_MAGIC_V1: - case LMV_MAGIC_MIGRATE: { + case LMV_MAGIC_V1:{ struct lmv_mds_md_v1 *lmm1; return sizeof(*lmm1) + stripe_count * @@ -2823,7 +2807,6 @@ static inline int lmv_mds_md_stripe_count_get(const union lmv_mds_md *lmm) { switch (le32_to_cpu(lmm->lmv_magic)) { case LMV_MAGIC_V1: - case LMV_MAGIC_MIGRATE: return le32_to_cpu(lmm->lmv_md_v1.lmv_stripe_count); case LMV_USER_MAGIC: return le32_to_cpu(lmm->lmv_user_md.lum_stripe_count); @@ -2837,7 +2820,6 @@ static inline int lmv_mds_md_stripe_count_set(union lmv_mds_md *lmm, { switch (le32_to_cpu(lmm->lmv_magic)) { case LMV_MAGIC_V1: - case LMV_MAGIC_MIGRATE: lmm->lmv_md_v1.lmv_stripe_count = cpu_to_le32(stripe_count); break; case LMV_USER_MAGIC: @@ -3164,14 +3146,14 @@ extern void lustre_swab_mgs_config_res(struct mgs_config_res *body); #define CM_START_SKIP (CM_START | CM_SKIP) struct cfg_marker { - __u32 cm_step; /* aka config version */ - __u32 cm_flags; - __u32 cm_vers; /* lustre release version number */ - __u32 cm_padding; /* 64 bit align */ - obd_time cm_createtime; /*when this record was first created */ - obd_time cm_canceltime; /*when this record is no longer valid*/ - char cm_tgtname[MTI_NAME_MAXLEN]; - char cm_comment[MTI_NAME_MAXLEN]; + __u32 cm_step; /* aka config version */ + __u32 cm_flags; + __u32 cm_vers; /* lustre release version number */ + __u32 cm_padding; /* 64 bit align */ + __s64 cm_createtime; /*when this record was first created */ + __s64 cm_canceltime; /*when this record is no longer valid*/ + char cm_tgtname[MTI_NAME_MAXLEN]; + char cm_comment[MTI_NAME_MAXLEN]; }; extern void lustre_swab_cfg_marker(struct cfg_marker *marker, @@ -3184,13 +3166,37 @@ extern void lustre_swab_cfg_marker(struct cfg_marker *marker, typedef enum { OBD_PING = 400, OBD_LOG_CANCEL, - OBD_QC_CALLBACK, + OBD_QC_CALLBACK, /* not used since 2.4 */ OBD_IDX_READ, OBD_LAST_OPC } obd_cmd_t; #define OBD_FIRST_OPC OBD_PING -/* catalog of log objects */ +/** + * llog contexts indices. + * + * There is compatibility problem with indexes below, they are not + * continuous and must keep their numbers for compatibility needs. + * See LU-5218 for details. + */ +enum llog_ctxt_id { + LLOG_CONFIG_ORIG_CTXT = 0, + LLOG_CONFIG_REPL_CTXT = 1, + LLOG_MDS_OST_ORIG_CTXT = 2, + LLOG_MDS_OST_REPL_CTXT = 3, /* kept just to avoid re-assignment */ + LLOG_SIZE_ORIG_CTXT = 4, + LLOG_SIZE_REPL_CTXT = 5, + LLOG_TEST_ORIG_CTXT = 8, + LLOG_TEST_REPL_CTXT = 9, /* kept just to avoid re-assignment */ + LLOG_CHANGELOG_ORIG_CTXT = 12, /**< changelog generation on mdd */ + LLOG_CHANGELOG_REPL_CTXT = 13, /**< changelog access on clients */ + /* for multiple changelog consumers */ + LLOG_CHANGELOG_USER_ORIG_CTXT = 14, + LLOG_AGENT_ORIG_CTXT = 15, /**< agent requests generation on cdt */ + LLOG_UPDATELOG_ORIG_CTXT = 16, /* update log */ + LLOG_UPDATELOG_REPL_CTXT = 17, /* update log */ + LLOG_MAX_CTXTS +}; /** Identifier for a single log object */ struct llog_logid { @@ -3231,6 +3237,7 @@ typedef enum { CHANGELOG_REC = LLOG_OP_MAGIC | 0x60000, CHANGELOG_USER_REC = LLOG_OP_MAGIC | 0x70000, HSM_AGENT_REC = LLOG_OP_MAGIC | 0x80000, + UPDATE_REC = LLOG_OP_MAGIC | 0xa0000, LLOG_HDR_MAGIC = LLOG_OP_MAGIC | 0x45539, LLOG_LOGID_MAGIC = LLOG_OP_MAGIC | 0x4553b, } llog_op_type; @@ -3262,6 +3269,12 @@ struct llog_rec_tail { (rec->lrh_len - sizeof(struct llog_rec_hdr) - \ sizeof(struct llog_rec_tail)) +static inline void *rec_tail(struct llog_rec_hdr *rec) +{ + return (void *)((char *)rec + rec->lrh_len - + sizeof(struct llog_rec_tail)); +} + struct llog_logid_rec { struct llog_rec_hdr lid_hdr; struct llog_logid lid_id; @@ -3273,16 +3286,16 @@ struct llog_logid_rec { struct llog_unlink_rec { struct llog_rec_hdr lur_hdr; - obd_id lur_oid; - obd_count lur_oseq; - obd_count lur_count; + __u64 lur_oid; + __u32 lur_oseq; + __u32 lur_count; struct llog_rec_tail lur_tail; } __attribute__((packed)); struct llog_unlink64_rec { struct llog_rec_hdr lur_hdr; struct lu_fid lur_fid; - obd_count lur_count; /* to destroy the lost precreated */ + __u32 lur_count; /* to destroy the lost precreated */ __u32 lur_padding1; __u64 lur_padding2; __u64 lur_padding3; @@ -3296,7 +3309,7 @@ struct llog_setattr64_rec { __u32 lsr_uid_h; __u32 lsr_gid; __u32 lsr_gid_h; - __u64 lsr_padding; + __u64 lsr_valid; struct llog_rec_tail lsr_tail; } __attribute__((packed)); @@ -3316,8 +3329,10 @@ struct llog_size_change_rec { #define CHANGELOG_MINMASK (1 << CL_MARK) /** bits covering all \a changelog_rec_type's */ #define CHANGELOG_ALLMASK 0XFFFFFFFF -/** default \a changelog_rec_type mask */ -#define CHANGELOG_DEFMASK CHANGELOG_ALLMASK & ~(1 << CL_ATIME | 1 << CL_CLOSE) +/** default \a changelog_rec_type mask. Allow all of them, except + * CL_ATIME since it can really be time consuming, and not necessary + * under normal use. */ +#define CHANGELOG_DEFMASK (CHANGELOG_ALLMASK & ~(1 << CL_ATIME)) /* changelog llog name, needed by client replicators */ #define CHANGELOG_CATALOG "changelog_catalog" @@ -3329,15 +3344,9 @@ struct changelog_setinfo { /** changelog record */ struct llog_changelog_rec { - struct llog_rec_hdr cr_hdr; - struct changelog_rec cr; - struct llog_rec_tail cr_tail; /**< for_sizezof_only */ -} __attribute__((packed)); - -struct llog_changelog_ext_rec { - struct llog_rec_hdr cr_hdr; - struct changelog_ext_rec cr; - struct llog_rec_tail cr_tail; /**< for_sizezof_only */ + struct llog_rec_hdr cr_hdr; + struct changelog_rec cr; /**< Variable length field */ + struct llog_rec_tail cr_do_not_use; /**< for_sizeof_only */ } __attribute__((packed)); #define CHANGELOG_USER_PREFIX "cl" @@ -3423,11 +3432,14 @@ enum llog_flag { LLOG_F_ZAP_WHEN_EMPTY = 0x1, LLOG_F_IS_CAT = 0x2, LLOG_F_IS_PLAIN = 0x4, + LLOG_F_EXT_JOBID = 0x8, + + LLOG_F_EXT_MASK = LLOG_F_EXT_JOBID, }; struct llog_log_hdr { - struct llog_rec_hdr llh_hdr; - obd_time llh_timestamp; + struct llog_rec_hdr llh_hdr; + __s64 llh_timestamp; __u32 llh_count; __u32 llh_bitmap_offset; __u32 llh_size; @@ -3485,37 +3497,38 @@ struct llogd_conn_body { /* Note: 64-bit types are 64-bit aligned in structure */ struct obdo { - obd_valid o_valid; /* hot fields in this obdo */ - struct ost_id o_oi; - obd_id o_parent_seq; - obd_size o_size; /* o_size-o_blocks == ost_lvb */ - obd_time o_mtime; - obd_time o_atime; - obd_time o_ctime; - obd_blocks o_blocks; /* brw: cli sent cached bytes */ - obd_size o_grant; - - /* 32-bit fields start here: keep an even number of them via padding */ - obd_blksize o_blksize; /* optimal IO blocksize */ - obd_mode o_mode; /* brw: cli sent cache remain */ - obd_uid o_uid; - obd_gid o_gid; - obd_flag o_flags; - obd_count o_nlink; /* brw: checksum */ - obd_count o_parent_oid; - obd_count o_misc; /* brw: o_dropped */ - - __u64 o_ioepoch; /* epoch in ost writes */ - __u32 o_stripe_idx; /* holds stripe idx */ - __u32 o_parent_ver; - struct lustre_handle o_handle; /* brw: lock handle to prolong - * locks */ - struct llog_cookie o_lcookie; /* destroy: unlink cookie from - * MDS */ + __u64 o_valid; /* hot fields in this obdo */ + struct ost_id o_oi; + __u64 o_parent_seq; + __u64 o_size; /* o_size-o_blocks == ost_lvb */ + __s64 o_mtime; + __s64 o_atime; + __s64 o_ctime; + __u64 o_blocks; /* brw: cli sent cached bytes */ + __u64 o_grant; + + /* 32-bit fields start here: keep an even number of them via padding */ + __u32 o_blksize; /* optimal IO blocksize */ + __u32 o_mode; /* brw: cli sent cache remain */ + __u32 o_uid; + __u32 o_gid; + __u32 o_flags; + __u32 o_nlink; /* brw: checksum */ + __u32 o_parent_oid; + __u32 o_misc; /* brw: o_dropped */ + + __u64 o_ioepoch; /* epoch in ost writes */ + __u32 o_stripe_idx; /* holds stripe idx */ + __u32 o_parent_ver; + struct lustre_handle o_handle; /* brw: lock handle to prolong + * locks */ + struct llog_cookie o_lcookie; /* destroy: unlink cookie from + * MDS, obsolete in 2.8, reused + * in OSP */ __u32 o_uid_h; __u32 o_gid_h; - __u64 o_data_version; /* getattr: sum of iversion for + __u64 o_data_version; /* getattr: sum of iversion for * each stripe. * brw: grant space consumed on * the client for the write */ @@ -3538,17 +3551,18 @@ struct lfsck_request { union { __u32 lr_speed; __u32 lr_status; + __u32 lr_type; }; __u16 lr_version; __u16 lr_active; __u16 lr_param; __u16 lr_async_windows; - __u32 lr_padding_1; + __u32 lr_flags2; struct lu_fid lr_fid; struct lu_fid lr_fid2; struct lu_fid lr_fid3; + __u64 lr_padding_1; __u64 lr_padding_2; - __u64 lr_padding_3; }; void lustre_swab_lfsck_request(struct lfsck_request *lr); @@ -3573,11 +3587,18 @@ enum lfsck_events { LE_PEER_EXIT = 9, LE_CONDITIONAL_DESTROY = 10, LE_PAIRS_VERIFY = 11, + LE_SKIP_NLINK_DECLARE = 13, + LE_SKIP_NLINK = 14, + LE_SET_LMV_MASTER = 15, + LE_SET_LMV_SLAVE = 16, }; enum lfsck_event_flags { LEF_TO_OST = 0x00000001, LEF_FROM_OST = 0x00000002, + LEF_SET_LMV_HASH = 0x00000004, + LEF_SET_LMV_ALL = 0x00000008, + LEF_RECHECK_NAME_HASH = 0x00000010, }; static inline void lustre_set_wire_obdo(const struct obd_connect_data *ocd, @@ -3602,7 +3623,7 @@ static inline void lustre_get_wire_obdo(const struct obd_connect_data *ocd, struct obdo *lobdo, const struct obdo *wobdo) { - obd_flag local_flags = 0; + __u32 local_flags = 0; if (lobdo->o_valid & OBD_MD_FLFLAGS) local_flags = lobdo->o_flags & OBD_FL_LOCAL_MASK; @@ -3634,20 +3655,22 @@ struct ost_body { /* Key for FIEMAP to be used in get_info calls */ struct ll_fiemap_info_key { - char name[8]; - struct obdo oa; - struct ll_user_fiemap fiemap; + char lfik_name[8]; + struct obdo lfik_oa; + struct fiemap lfik_fiemap; }; extern void lustre_swab_ost_body (struct ost_body *b); -extern void lustre_swab_ost_last_id(obd_id *id); -extern void lustre_swab_fiemap(struct ll_user_fiemap *fiemap); +extern void lustre_swab_ost_last_id(__u64 *id); +extern void lustre_swab_fiemap(struct fiemap *fiemap); extern void lustre_swab_lov_user_md_v1(struct lov_user_md_v1 *lum); extern void lustre_swab_lov_user_md_v3(struct lov_user_md_v3 *lum); extern void lustre_swab_lov_user_md_objects(struct lov_user_ost_data *lod, int stripe_count); extern void lustre_swab_lov_mds_md(struct lov_mds_md *lmm); +void lustre_print_user_md(unsigned int level, struct lov_user_md *lum, + const char *msg); /* llog_swab.c */ extern void lustre_swab_llogd_body (struct llogd_body *d); @@ -3719,6 +3742,7 @@ enum idx_info_flags { II_FL_VARKEY = 1 << 1, /* keys can be of variable size */ II_FL_VARREC = 1 << 2, /* records can be of variable size */ II_FL_NONUNQ = 1 << 3, /* index supports non-unique keys */ + II_FL_NOKEY = 1 << 4, /* client doesn't care about key */ }; #define LIP_MAGIC 0x8A6D6B6C @@ -3823,6 +3847,16 @@ static inline int capa_for_oss(struct lustre_capa *c) return (c->lc_opc & CAPA_OPC_INDEX_LOOKUP) == 0; } +static inline bool lovea_slot_is_dummy(const struct lov_ost_data_v1 *obj) +{ + /* zero area does not care about the bytes-order. */ + if (obj->l_ost_oi.oi.oi_id == 0 && obj->l_ost_oi.oi.oi_seq == 0 && + obj->l_ost_idx == 0 && obj->l_ost_gen == 0) + return true; + + return false; +} + /* lustre_capa::lc_hmac_alg */ enum { CAPA_HMAC_ALG_SHA1 = 1, /**< sha1 algorithm */ @@ -3873,6 +3907,14 @@ struct getinfo_fid2path { void lustre_swab_fid2path (struct getinfo_fid2path *gf); +/** path2parent request/reply structures */ +struct getparent { + struct lu_fid gp_fid; /**< parent FID */ + __u32 gp_linkno; /**< hardlink number */ + __u32 gp_name_size; /**< size of the name field */ + char gp_name[0]; /**< zero-terminated link name */ +} __attribute__((packed)); + enum { LAYOUT_INTENT_ACCESS = 0, LAYOUT_INTENT_READ = 1, @@ -3951,9 +3993,11 @@ extern void lustre_swab_hsm_request(struct hsm_request *hr); */ /** - * Type of each update + * Type of each update, if adding/deleting update, please also update + * update_opcode in lustre/target/out_lib.c. */ enum update_type { + OUT_START = 0, OUT_CREATE = 1, OUT_DESTROY = 2, OUT_REF_ADD = 3, @@ -3966,6 +4010,9 @@ enum update_type { OUT_INDEX_INSERT = 10, OUT_INDEX_DELETE = 11, OUT_WRITE = 12, + OUT_XATTR_DEL = 13, + OUT_PUNCH = 14, + OUT_READ = 15, OUT_LAST }; @@ -3983,6 +4030,12 @@ struct object_update_param { char oup_buf[0]; }; +static inline size_t +object_update_param_size(const struct object_update_param *param) +{ + return cfs_size_round(sizeof(*param) + param->oup_len); +} + /* object update */ struct object_update { __u16 ou_type; /* enum update_type */ @@ -4009,6 +4062,52 @@ struct object_update_request { void lustre_swab_object_update(struct object_update *ou); void lustre_swab_object_update_request(struct object_update_request *our); +static inline size_t +object_update_params_size(const struct object_update *update) +{ + const struct object_update_param *param; + size_t total_size = 0; + unsigned int i; + + param = &update->ou_params[0]; + for (i = 0; i < update->ou_params_count; i++) { + size_t size = object_update_param_size(param); + + param = (struct object_update_param *)((char *)param + size); + total_size += size; + } + + return total_size; +} + +static inline size_t +object_update_size(const struct object_update *update) +{ + return offsetof(struct object_update, ou_params[0]) + + object_update_params_size(update); +} + +static inline struct object_update * +object_update_request_get(const struct object_update_request *our, + unsigned int index, size_t *size) +{ + void *ptr; + unsigned int i; + + if (index >= our->ourq_count) + return NULL; + + ptr = (void *)&our->ourq_updates[0]; + for (i = 0; i < index; i++) + ptr += object_update_size(ptr); + + if (size != NULL) + *size = object_update_size(ptr); + + return ptr; +} + + /* the result of object update */ struct object_update_result { __u32 our_rc; @@ -4031,6 +4130,57 @@ struct object_update_reply { void lustre_swab_object_update_result(struct object_update_result *our); void lustre_swab_object_update_reply(struct object_update_reply *our); +static inline struct object_update_result * +object_update_result_get(const struct object_update_reply *reply, + unsigned int index, size_t *size) +{ + __u16 count = reply->ourp_count; + unsigned int i; + void *ptr; + + if (index >= count) + return NULL; + + ptr = (char *)reply + + cfs_size_round(offsetof(struct object_update_reply, + ourp_lens[count])); + for (i = 0; i < index; i++) { + if (reply->ourp_lens[i] == 0) + return NULL; + + ptr += cfs_size_round(reply->ourp_lens[i]); + } + + if (size != NULL) + *size = reply->ourp_lens[index]; + + return ptr; +} + +/* read update result */ +struct out_read_reply { + __u32 orr_size; + __u32 orr_padding; + __u64 orr_offset; + char orr_data[0]; +}; + +static inline void orr_cpu_to_le(struct out_read_reply *orr_dst, + const struct out_read_reply *orr_src) +{ + orr_dst->orr_size = cpu_to_le32(orr_src->orr_size); + orr_dst->orr_padding = cpu_to_le32(orr_src->orr_padding); + orr_dst->orr_offset = cpu_to_le64(orr_dst->orr_offset); +} + +static inline void orr_le_to_cpu(struct out_read_reply *orr_dst, + const struct out_read_reply *orr_src) +{ + orr_dst->orr_size = le32_to_cpu(orr_src->orr_size); + orr_dst->orr_padding = le32_to_cpu(orr_src->orr_padding); + orr_dst->orr_offset = le64_to_cpu(orr_dst->orr_offset); +} + /** layout swap request structure * fid1 and fid2 are in mdt_body */