#define SEQ_DATA_PORTAL 31
#define SEQ_CONTROLLER_PORTAL 32
#define MGS_BULK_PORTAL 33
+#define OST_IDX_PORTAL 34
/* Portal 63 is reserved for the Cray Inc DVS - nic@cray.com, roe@cray.com, n8851@cray.com */
__u32 lsr_flags;
};
+struct lu_seq_range_array {
+ __u32 lsra_count;
+ __u32 lsra_padding;
+ struct lu_seq_range lsra_lsr[0];
+};
+
#define LU_SEQ_RANGE_MDT 0x0
#define LU_SEQ_RANGE_OST 0x1
#define LU_SEQ_RANGE_ANY 0x3
FID_SEQ_QUOTA = 0x200000005ULL,
FID_SEQ_QUOTA_GLB = 0x200000006ULL,
FID_SEQ_ROOT = 0x200000007ULL, /* Located on MDT0 */
+ FID_SEQ_LAYOUT_RBTREE = 0x200000008ULL,
FID_SEQ_NORMAL = 0x200000400ULL,
FID_SEQ_LOV_DEFAULT = 0xffffffffffffffffULL
};
/** OID for FID_SEQ_DOT_LUSTRE */
enum dot_lustre_oid {
- FID_OID_DOT_LUSTRE = 1UL,
- FID_OID_DOT_LUSTRE_OBF = 2UL,
+ FID_OID_DOT_LUSTRE = 1UL,
+ FID_OID_DOT_LUSTRE_OBF = 2UL,
+ FID_OID_DOT_LUSTRE_LPF = 3UL,
};
static inline int fid_seq_is_mdt0(obd_seq seq)
return fid_seq_is_norm(fid_seq(fid));
}
+static inline int fid_is_layout_rbtree(const struct lu_fid *fid)
+{
+ return fid_seq(fid) == FID_SEQ_LAYOUT_RBTREE;
+}
+
/* convert an OST objid into an IDIF FID SEQ number */
static inline obd_seq fid_idif_seq(obd_id id, __u32 ost_idx)
{
if (fid_seq_is_mdt0(ostid->oi.oi_seq))
return FID_SEQ_OST_MDT0;
- if (fid_seq_is_default(ostid->oi.oi_seq))
+ if (unlikely(fid_seq_is_default(ostid->oi.oi_seq)))
return FID_SEQ_LOV_DEFAULT;
if (fid_is_idif(&ostid->oi_fid))
/* extract OST objid from a wire ost_id (id/seq) pair */
static inline obd_id ostid_id(const struct ost_id *ostid)
{
- if (fid_seq_is_mdt0(ostid_seq(ostid)))
+ if (fid_seq_is_mdt0(ostid->oi.oi_seq))
return ostid->oi.oi_id & IDIF_OID_MASK;
+ if (unlikely(fid_seq_is_default(ostid->oi.oi_seq)))
+ return ostid->oi.oi_id;
+
if (fid_is_idif(&ostid->oi_fid))
return fid_idif_id(fid_seq(&ostid->oi_fid),
fid_oid(&ostid->oi_fid), 0);
*/
static inline void ostid_set_id(struct ost_id *oi, __u64 oid)
{
- if (fid_seq_is_mdt0(ostid_seq(oi))) {
+ if (fid_seq_is_mdt0(oi->oi.oi_seq)) {
if (oid >= IDIF_MAX_OID) {
CERROR("Bad "LPU64" to set "DOSTID"\n",
oid, POSTID(oi));
return;
}
oi->oi.oi_id = oid;
+ } else if (fid_is_idif(&oi->oi_fid)) {
+ if (oid >= IDIF_MAX_OID) {
+ CERROR("Bad "LPU64" to set "DOSTID"\n",
+ oid, POSTID(oi));
+ return;
+ }
+ oi->oi_fid.f_seq = fid_idif_seq(oid,
+ fid_idif_ost_idx(&oi->oi_fid));
+ oi->oi_fid.f_oid = oid;
+ oi->oi_fid.f_ver = oid >> 48;
} else {
if (oid > OBIF_MAX_OID) {
CERROR("Bad "LPU64" to set "DOSTID"\n",
}
}
-static inline void ostid_inc_id(struct ost_id *oi)
+static inline int fid_set_id(struct lu_fid *fid, __u64 oid)
{
- if (fid_seq_is_mdt0(ostid_seq(oi))) {
- if (unlikely(ostid_id(oi) + 1 > IDIF_MAX_OID)) {
- CERROR("Bad inc "DOSTID"\n", POSTID(oi));
- return;
+ if (unlikely(fid_seq_is_igif(fid->f_seq))) {
+ CERROR("bad IGIF, "DFID"\n", PFID(fid));
+ return -EBADF;
+ }
+
+ if (fid_is_idif(fid)) {
+ if (oid >= IDIF_MAX_OID) {
+ CERROR("Bad "LPU64" to set "DFID"\n",
+ oid, PFID(fid));
+ return -EBADF;
}
- oi->oi.oi_id++;
+ fid->f_seq = fid_idif_seq(oid, fid_idif_ost_idx(fid));
+ fid->f_oid = oid;
+ fid->f_ver = oid >> 48;
} else {
- oi->oi_fid.f_oid++;
+ if (oid > OBIF_MAX_OID) {
+ CERROR("Bad "LPU64" to set "DFID"\n",
+ oid, PFID(fid));
+ return -EBADF;
+ }
+ fid->f_oid = oid;
}
-}
-
-static inline void ostid_dec_id(struct ost_id *oi)
-{
- if (fid_seq_is_mdt0(ostid_seq(oi)))
- oi->oi.oi_id--;
- else
- oi->oi_fid.f_oid--;
+ return 0;
}
/**
* struct lu_fid fields without loss. For reference see:
* http://arch.lustre.org/index.php?title=Interoperability_fids_zfs
*/
-static inline int ostid_to_fid(struct lu_fid *fid, struct ost_id *ostid,
+static inline int ostid_to_fid(struct lu_fid *fid, const struct ost_id *ostid,
__u32 ost_idx)
{
+ obd_seq seq = ostid_seq(ostid);
+
if (ost_idx > 0xffff) {
CERROR("bad ost_idx, "DOSTID" ost_idx:%u\n", POSTID(ostid),
ost_idx);
return -EBADF;
}
- if (fid_seq_is_mdt0(ostid_seq(ostid))) {
+ if (fid_seq_is_mdt0(seq)) {
+ obd_id 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
* objects per OST, as this is the object namespace that has
* been in production for years. This can handle create rates
* of 1M objects/s/OST for 9 years, or combinations thereof. */
- if (ostid_id(ostid) >= IDIF_MAX_OID) {
+ if (oid >= IDIF_MAX_OID) {
CERROR("bad MDT0 id, "DOSTID" ost_idx:%u\n",
POSTID(ostid), ost_idx);
return -EBADF;
}
- fid->f_seq = fid_idif_seq(ostid_id(ostid), ost_idx);
+ fid->f_seq = fid_idif_seq(oid, ost_idx);
/* truncate to 32 bits by assignment */
- fid->f_oid = ostid_id(ostid);
+ fid->f_oid = oid;
/* in theory, not currently used */
- fid->f_ver = ostid_id(ostid) >> 48;
- } else /* if (fid_seq_is_idif(seq) || fid_seq_is_norm(seq)) */ {
- /* This is either an IDIF object, which identifies objects across
- * all OSTs, or a regular FID. The IDIF namespace maps legacy
- * OST objects into the FID namespace. In both cases, we just
- * pass the FID through, no conversion needed. */
+ fid->f_ver = oid >> 48;
+ } else if (likely(!fid_seq_is_default(seq)))
+ /* if (fid_seq_is_idif(seq) || fid_seq_is_norm(seq)) */ {
+ /* This is either an IDIF object, which identifies objects across
+ * all OSTs, or a regular FID. The IDIF namespace maps legacy
+ * 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",
POSTID(ostid), ost_idx);
*fid = ostid->oi_fid;
}
- return 0;
+ return 0;
}
/* pack any OST FID into an ostid (id/seq) for the wire/disk */
}
}
+struct lu_orphan_rec {
+ /* The MDT-object's FID referenced by the orphan OST-object */
+ struct lu_fid lor_fid;
+ __u32 lor_uid;
+ __u32 lor_gid;
+};
+
+struct lu_orphan_ent {
+ /* The orphan OST-object's FID */
+ struct lu_fid loe_key;
+ struct lu_orphan_rec loe_rec;
+};
+void lustre_swab_orphan_ent(struct lu_orphan_ent *ent);
+
/** @} lu_fid */
/** \defgroup lu_dir lu_dir
#define OBD_CONNECT_DISP_STRIPE 0x10000000000000ULL/* create stripe disposition*/
#define OBD_CONNECT_OPEN_BY_FID 0x20000000000000ULL /* open by fid won't pack
name in request */
+#define OBD_CONNECT_LFSCK 0x40000000000000ULL/* support online LFSCK */
/* XXX README XXX:
* Please DO NOT add flag values here before first ensuring that this same
OBD_CONNECT_LVB_TYPE | OBD_CONNECT_LAYOUTLOCK |\
OBD_CONNECT_PINGLESS | OBD_CONNECT_MAX_EASIZE |\
OBD_CONNECT_FLOCK_DEAD | \
- OBD_CONNECT_DISP_STRIPE)
+ OBD_CONNECT_DISP_STRIPE | OBD_CONNECT_LFSCK)
#define OST_CONNECT_SUPPORTED (OBD_CONNECT_SRVLOCK | OBD_CONNECT_GRANT | \
OBD_CONNECT_REQPORTAL | OBD_CONNECT_VERSION | \
OBD_CONNECT_JOBSTATS | \
OBD_CONNECT_LIGHTWEIGHT | OBD_CONNECT_LVB_TYPE|\
OBD_CONNECT_LAYOUTLOCK | OBD_CONNECT_FID | \
- OBD_CONNECT_PINGLESS)
+ OBD_CONNECT_PINGLESS | OBD_CONNECT_LFSCK)
#define ECHO_CONNECT_SUPPORTED (0)
#define MGS_CONNECT_SUPPORTED (OBD_CONNECT_VERSION | OBD_CONNECT_AT | \
OBD_CONNECT_FULL20 | OBD_CONNECT_IMP_RECOV | \
OBD_FL_RECOV_RESEND = 0x00080000, /* recoverable resent */
OBD_FL_NOSPC_BLK = 0x00100000, /* no more block space on OST */
OBD_FL_FLUSH = 0x00200000, /* flush pages on the OST */
+ OBD_FL_SHORT_IO = 0x00400000, /* short io request */
/* Note that while these checksum values are currently separate bits,
* in 2.x we can actually allow all values from 1-31 if we wanted. */
oi->oi.oi_seq = seq;
}
+static inline void lmm_oi_set_id(struct ost_id *oi, __u64 oid)
+{
+ oi->oi.oi_id = oid;
+}
+
static inline __u64 lmm_oi_id(struct ost_id *oi)
{
return oi->oi.oi_id;
#define XATTR_NAME_LOV "trusted.lov"
#define XATTR_NAME_LMA "trusted.lma"
#define XATTR_NAME_LMV "trusted.lmv"
+#define XATTR_NAME_DEFAULT_LMV "trusted.dmv"
#define XATTR_NAME_LINK "trusted.link"
#define XATTR_NAME_FID "trusted.fid"
#define XATTR_NAME_VERSION "trusted.version"
#define OBD_MD_FLDATAVERSION (0x0010000000000000ULL) /* iversion sum */
#define OBD_MD_FLRELEASED (0x0020000000000000ULL) /* file released */
+#define OBD_MD_DEFAULT_MEA (0x0040000000000000ULL) /* default MEA */
+
#define OBD_MD_FLGETATTR (OBD_MD_FLID | OBD_MD_FLATIME | OBD_MD_FLMTIME | \
OBD_MD_FLCTIME | OBD_MD_FLSIZE | OBD_MD_FLBLKSZ | \
OBD_MD_FLMODE | OBD_MD_FLTYPE | OBD_MD_FLUID | \
#define DISP_LOOKUP_POS 0x00000008
#define DISP_OPEN_CREATE 0x00000010
#define DISP_OPEN_OPEN 0x00000020
-#define DISP_ENQ_COMPLETE 0x00400000
+#define DISP_ENQ_COMPLETE 0x00400000 /* obsolete and unused */
#define DISP_ENQ_OPEN_REF 0x00800000
#define DISP_ENQ_CREATE_REF 0x01000000
#define DISP_OPEN_LOCK 0x02000000
#define DISP_OPEN_STRIPE 0x08000000
/* INODE LOCK PARTS */
-#define MDS_INODELOCK_LOOKUP 0x000001 /* dentry, mode, owner, group */
-#define MDS_INODELOCK_UPDATE 0x000002 /* size, links, timestamps */
-#define MDS_INODELOCK_OPEN 0x000004 /* For opened files */
-#define MDS_INODELOCK_LAYOUT 0x000008 /* for layout */
-#define MDS_INODELOCK_PERM 0x000010 /* for permission */
-#define MDS_INODELOCK_XATTR 0x000020 /* extended attributes */
+#define MDS_INODELOCK_LOOKUP 0x000001 /* For namespace, dentry etc, and also
+ * was used to protect permission (mode,
+ * owner, group etc) before 2.4. */
+#define MDS_INODELOCK_UPDATE 0x000002 /* size, links, timestamps */
+#define MDS_INODELOCK_OPEN 0x000004 /* For opened files */
+#define MDS_INODELOCK_LAYOUT 0x000008 /* for layout */
+
+/* The PERM bit is added int 2.4, and it is used to protect permission(mode,
+ * owner, group, acl etc), so to separate the permission from LOOKUP lock.
+ * Because for remote directories(in DNE), these locks will be granted by
+ * different MDTs(different ldlm namespace).
+ *
+ * For local directory, MDT will always grant UPDATE_LOCK|PERM_LOCK together.
+ * For Remote directory, the master MDT, where the remote directory is, will
+ * grant UPDATE_LOCK|PERM_LOCK, and the remote MDT, where the name entry is,
+ * will grant LOOKUP_LOCK. */
+#define MDS_INODELOCK_PERM 0x000010
+#define MDS_INODELOCK_XATTR 0x000020 /* extended attributes */
#define MDS_INODELOCK_MAXSHIFT 5
/* This FULL lock is useful to take on unlink sort of operations */
extern void lustre_swab_mdt_rec_reint(struct mdt_rec_reint *rr);
+/* lmv structures */
struct lmv_desc {
__u32 ld_tgt_count; /* how many MDS's */
__u32 ld_active_tgt_count; /* how many active */
__u32 ld_default_stripe_count; /* how many objects are used */
- __u32 ld_pattern; /* default MEA_MAGIC_* */
+ __u32 ld_pattern; /* default hash pattern */
__u64 ld_default_hash_size;
__u64 ld_padding_1; /* also fix lustre_swab_lmv_desc */
__u32 ld_padding_2; /* also fix lustre_swab_lmv_desc */
extern void lustre_swab_lmv_desc (struct lmv_desc *ld);
-/* TODO: lmv_stripe_md should contain mds capabilities for all slave fids */
-struct lmv_stripe_md {
- __u32 mea_magic;
- __u32 mea_count;
- __u32 mea_master;
- __u32 mea_padding;
- char mea_pool_name[LOV_MAXPOOLNAME];
- struct lu_fid mea_ids[0];
+/* lmv structures */
+#define LMV_MAGIC_V1 0x0CD10CD0 /* normal stripe lmv magic */
+#define LMV_USER_MAGIC 0x0CD20CD0 /* default 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,
};
-extern void lustre_swab_lmv_stripe_md(struct lmv_stripe_md *mea);
+#define LMV_HASH_NAME_ALL_CHARS "all_char"
+#define LMV_HASH_NAME_FNV_1A_64 "fnv_1a_64"
-/* lmv structures */
-#define MEA_MAGIC_LAST_CHAR 0xb2221ca1
-#define MEA_MAGIC_ALL_CHARS 0xb222a11c
-#define MEA_MAGIC_HASH_SEGMENT 0xb222a11b
+/**
+ * The FNV-1a hash algorithm is as follows:
+ * hash = FNV_offset_basis
+ * for each octet_of_data to be hashed
+ * hash = hash XOR octet_of_data
+ * hash = hash × FNV_prime
+ * return hash
+ * http://en.wikipedia.org/wiki/Fowler–Noll–Vo_hash_function#FNV-1a_hash
+ *
+ * http://www.isthe.com/chongo/tech/comp/fnv/index.html#FNV-reference-source
+ * FNV_prime is 2^40 + 2^8 + 0xb3 = 0x100000001b3ULL
+ **/
+#define LUSTRE_FNV_1A_64_PRIME 0x100000001b3ULL
+#define LUSTRE_FNV_1A_64_OFFSET_BIAS 0xcbf29ce484222325ULL
+static inline __u64 lustre_hash_fnv_1a_64(const void *buf, size_t size)
+{
+ __u64 hash = LUSTRE_FNV_1A_64_OFFSET_BIAS;
+ const unsigned char *p = buf;
+ size_t i;
+
+ for (i = 0; i < size; i++) {
+ hash ^= p[i];
+ hash *= LUSTRE_FNV_1A_64_PRIME;
+ }
-#define MAX_HASH_SIZE_32 0x7fffffffUL
-#define MAX_HASH_SIZE 0x7fffffffffffffffULL
-#define MAX_HASH_HIGHEST_BIT 0x1000000000000000ULL
+ 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;
+ struct lmv_user_md lmv_user_md;
+};
+
+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: {
+ struct lmv_mds_md_v1 *lmm1;
+
+ return sizeof(*lmm1) + stripe_count *
+ sizeof(lmm1->lmv_stripe_fids[0]);
+ }
+ default:
+ return -EINVAL;
+ }
+}
+
+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:
+ 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);
+ default:
+ return -EINVAL;
+ }
+}
+
+static inline int lmv_mds_md_stripe_count_set(union lmv_mds_md *lmm,
+ unsigned int stripe_count)
+{
+ switch (le32_to_cpu(lmm->lmv_magic)) {
+ case LMV_MAGIC_V1:
+ lmm->lmv_md_v1.lmv_stripe_count = cpu_to_le32(stripe_count);
+ break;
+ case LMV_USER_MAGIC:
+ lmm->lmv_user_md.lum_stripe_count = cpu_to_le32(stripe_count);
+ break;
+ default:
+ return -EINVAL;
+ }
+ return 0;
+}
enum fld_rpc_opc {
- FLD_QUERY = 900,
- FLD_LAST_OPC,
- FLD_FIRST_OPC = FLD_QUERY
+ FLD_QUERY = 900,
+ FLD_READ = 901,
+ FLD_LAST_OPC,
+ FLD_FIRST_OPC = FLD_QUERY
};
enum seq_rpc_opc {
SEQ_ALLOC_META = 1
};
+enum fld_op {
+ FLD_CREATE = 0,
+ FLD_DELETE = 1,
+ FLD_LOOKUP = 2,
+};
+
+/* LFSCK opcodes */
+typedef enum {
+ LFSCK_NOTIFY = 1101,
+ LFSCK_QUERY = 1102,
+ LFSCK_LAST_OPC,
+ LFSCK_FIRST_OPC = LFSCK_NOTIFY
+} lfsck_cmd_t;
+
/*
* LOV data structures
*/
#define o_cksum o_nlink
#define o_grant_used o_data_version
+struct lfsck_request {
+ __u32 lr_event;
+ __u32 lr_index;
+ __u32 lr_flags;
+ __u32 lr_valid;
+ union {
+ __u32 lr_speed;
+ __u32 lr_status;
+ };
+ __u16 lr_version;
+ __u16 lr_active;
+ __u16 lr_param;
+ __u16 lr_async_windows;
+ __u32 lr_padding_1;
+ /* lr_fid is used on server-side only, and can be
+ * reused as others by client in the future. */
+ struct lu_fid lr_fid;
+ __u64 lr_padding_2;
+ __u64 lr_padding_3;
+};
+
+void lustre_swab_lfsck_request(struct lfsck_request *lr);
+
+struct lfsck_reply {
+ __u32 lr_status;
+ __u32 lr_padding_1;
+ __u64 lr_padding_2;
+};
+
+void lustre_swab_lfsck_reply(struct lfsck_reply *lr);
+
static inline void lustre_set_wire_obdo(struct obd_connect_data *ocd,
struct obdo *wobdo,
const struct obdo *lobdo)