#ifndef _LUSTRE_IDL_H_
#define _LUSTRE_IDL_H_
-#if !defined(LASSERT) && !defined(LPU64)
-#include <libcfs/libcfs.h> /* for LASSERT, LPUX64, etc */
+#if !defined(LPU64)
+#include <libcfs/libcfs.h> /* for LPUX64, etc */
#endif
/* Defn's shared with user-space. */
#include <lustre/lustre_user.h>
+#include <lustre/lustre_errno.h>
+
/*
* GENERAL STUFF
*/
//#define PTLBD_BULK_PORTAL 21
#define MDS_SETATTR_PORTAL 22
#define MDS_READPAGE_PORTAL 23
-#define MDS_MDS_PORTAL 24
-
+#define OUT_PORTAL 24
#define MGC_REPLY_PORTAL 25
#define MGS_REQUEST_PORTAL 26
#define MGS_REPLY_PORTAL 27
__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
static inline void fld_range_set_type(struct lu_seq_range *range,
unsigned flags)
{
- LASSERT(!(flags & ~LU_SEQ_RANGE_MASK));
range->lsr_flags |= flags;
}
static inline void range_init(struct lu_seq_range *range)
{
- range->lsr_start = range->lsr_end = range->lsr_index = 0;
+ memset(range, 0, sizeof(*range));
}
/**
* xattr.
*/
enum lma_compat {
- LMAC_HSM = 0x00000001,
- LMAC_SOM = 0x00000002,
+ LMAC_HSM = 0x00000001,
+ LMAC_SOM = 0x00000002,
+ 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/<seq>/d<x>. */
};
/**
* This information is stored in lustre_mdt_attrs::lma_incompat.
*/
enum lma_incompat {
- LMAI_RELEASED = 0x0000001, /* file is released */
- LMAI_AGENT = 0x00000002, /* agent inode */
- LMAI_REMOTE_PARENT = 0x00000004, /* the parent of the object
- is on the remote MDT */
+ LMAI_RELEASED = 0x00000001, /* file is released */
+ LMAI_AGENT = 0x00000002, /* agent inode */
+ LMAI_REMOTE_PARENT = 0x00000004, /* the parent of the object
+ is on the remote MDT */
};
#define LMA_INCOMPAT_SUPP (LMAI_AGENT | LMAI_REMOTE_PARENT)
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 incompat);
+ const struct lu_fid *fid,
+ __u32 compat, __u32 incompat);
/**
* SOM on-disk attributes stored in a separate xattr.
*/
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
};
return ((__u64)ver << 48) | ((seq & 0xffff) << 32) | oid;
}
+static inline __u32 idif_ost_idx(obd_seq seq)
+{
+ return (seq >> 16) & 0xffff;
+}
+
/* extract ost index from IDIF FID */
static inline __u32 fid_idif_ost_idx(const struct lu_fid *fid)
{
- LASSERT(fid_is_idif(fid));
- return (fid_seq(fid) >> 16) & 0xffff;
+ return idif_ost_idx(fid_seq(fid));
}
/* extract OST sequence (group) from a wire ost_id (id/seq) pair */
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 */
*/
static inline void fid_cpu_to_le(struct lu_fid *dst, const struct lu_fid *src)
{
- /* check that all fields are converted */
- CLASSERT(sizeof *src ==
- sizeof fid_seq(src) +
- sizeof fid_oid(src) + sizeof fid_ver(src));
dst->f_seq = cpu_to_le64(fid_seq(src));
dst->f_oid = cpu_to_le32(fid_oid(src));
dst->f_ver = cpu_to_le32(fid_ver(src));
static inline void fid_le_to_cpu(struct lu_fid *dst, const struct lu_fid *src)
{
- /* check that all fields are converted */
- CLASSERT(sizeof *src ==
- sizeof fid_seq(src) +
- sizeof fid_oid(src) + sizeof fid_ver(src));
dst->f_seq = le64_to_cpu(fid_seq(src));
dst->f_oid = le32_to_cpu(fid_oid(src));
dst->f_ver = le32_to_cpu(fid_ver(src));
static inline void fid_cpu_to_be(struct lu_fid *dst, const struct lu_fid *src)
{
- /* check that all fields are converted */
- CLASSERT(sizeof *src ==
- sizeof fid_seq(src) +
- sizeof fid_oid(src) + sizeof fid_ver(src));
dst->f_seq = cpu_to_be64(fid_seq(src));
dst->f_oid = cpu_to_be32(fid_oid(src));
dst->f_ver = cpu_to_be32(fid_ver(src));
static inline void fid_be_to_cpu(struct lu_fid *dst, const struct lu_fid *src)
{
- /* check that all fields are converted */
- CLASSERT(sizeof *src ==
- sizeof fid_seq(src) +
- sizeof fid_oid(src) + sizeof fid_ver(src));
dst->f_seq = be64_to_cpu(fid_seq(src));
dst->f_oid = be32_to_cpu(fid_oid(src));
dst->f_ver = be32_to_cpu(fid_ver(src));
static inline int lu_fid_eq(const struct lu_fid *f0, const struct lu_fid *f1)
{
- /* Check that there is no alignment padding. */
- CLASSERT(sizeof *f0 ==
- sizeof f0->f_seq + sizeof f0->f_oid + sizeof f0->f_ver);
return memcmp(f0, f1, sizeof *f0) == 0;
}
__diff_normalize(fid_ver(f0), fid_ver(f1));
}
-static inline void ostid_cpu_to_le(struct ost_id *src_oi,
+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))) {
}
}
-static inline void ostid_le_to_cpu(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))) {
* MDS_READPAGE page size
*
* This is the directory page size packed in MDS_READPAGE RPC.
- * It's different than CFS_PAGE_SIZE because the client needs to
+ * It's different than PAGE_CACHE_SIZE because the client needs to
* access the struct lu_dirpage header packed at the beginning of
* the "page" and without this there isn't any way to know find the
- * lu_dirpage header is if client and server CFS_PAGE_SIZE differ.
+ * lu_dirpage header is if client and server PAGE_CACHE_SIZE differ.
*/
#define LU_PAGE_SHIFT 12
#define LU_PAGE_SIZE (1UL << LU_PAGE_SHIFT)
#define LU_PAGE_MASK (~(LU_PAGE_SIZE - 1))
-#define LU_PAGE_COUNT (1 << (CFS_PAGE_SHIFT - LU_PAGE_SHIFT))
+#define LU_PAGE_COUNT (1 << (PAGE_CACHE_SHIFT - LU_PAGE_SHIFT))
/** @} lu_dir */
#define OBD_CONNECT_LIGHTWEIGHT 0x1000000000000ULL/* lightweight connection */
#define OBD_CONNECT_SHORTIO 0x2000000000000ULL/* short io */
#define OBD_CONNECT_PINGLESS 0x4000000000000ULL/* pings not required */
+#define OBD_CONNECT_FLOCK_DEAD 0x8000000000000ULL/* improved flock deadlock detection */
+#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
* flag value is not in use on some other branch. Please clear any such
OBD_CONNECT_EINPROGRESS | \
OBD_CONNECT_LIGHTWEIGHT | OBD_CONNECT_UMASK | \
OBD_CONNECT_LVB_TYPE | OBD_CONNECT_LAYOUTLOCK |\
- OBD_CONNECT_PINGLESS)
+ OBD_CONNECT_PINGLESS | OBD_CONNECT_MAX_EASIZE |\
+ OBD_CONNECT_FLOCK_DEAD | \
+ 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_TRUNCLOCK | OBD_CONNECT_INDEX | \
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 | \
* clients prior than 2.2 */
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. */
#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_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)
#define lov_ost_data lov_ost_data_v1
struct lov_ost_data_v1 { /* per-stripe data structure (little-endian)*/
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"
struct lov_ost_data_v1 lmm_objects[0]; /* per-stripe data */
};
+static inline __u32 lov_mds_md_size(__u16 stripes, __u32 lmm_magic)
+{
+ if (lmm_magic == LOV_MAGIC_V3)
+ return sizeof(struct lov_mds_md_v3) +
+ stripes * sizeof(struct lov_ost_data_v1);
+ else
+ return sizeof(struct lov_mds_md_v1) +
+ stripes * sizeof(struct lov_ost_data_v1);
+}
+
+
#define OBD_MD_FLID (0x00000001ULL) /* object ID */
#define OBD_MD_FLATIME (0x00000002ULL) /* access time */
#define OBD_MD_FLMTIME (0x00000004ULL) /* data modification time */
#define OBD_MD_MDS (0x0000000100000000ULL) /* where an inode lives on */
#define OBD_MD_REINT (0x0000000200000000ULL) /* reintegrate oa */
#define OBD_MD_MEA (0x0000000400000000ULL) /* CMD split EA */
-
-/* OBD_MD_MDTIDX is used to get MDT index, but it is never been used overwire,
- * and it is already obsolete since 2.3 */
-/* #define OBD_MD_MDTIDX (0x0000000800000000ULL) */
+#define OBD_MD_TSTATE (0x0000000800000000ULL) /* transient state field */
#define OBD_MD_FLXATTR (0x0000001000000000ULL) /* xattr */
#define OBD_MD_FLXATTRLS (0x0000002000000000ULL) /* xattr list */
#define OBD_MD_FLCKSPLIT (0x0000080000000000ULL) /* Check split on server */
#define OBD_MD_FLCROSSREF (0x0000100000000000ULL) /* Cross-ref case */
#define OBD_MD_FLGETATTRLOCK (0x0000200000000000ULL) /* Get IOEpoch attributes
- * under lock */
+ * under lock; for xattr
+ * requests means the
+ * client holds the lock */
#define OBD_MD_FLOBJCOUNT (0x0000400000000000ULL) /* for multiple destroy */
#define OBD_MD_FLRMTLSETFACL (0x0001000000000000ULL) /* lfs lsetfacl case */
#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_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_FLGID | OBD_MD_FLFLAGS | OBD_MD_FLNLINK | \
OBD_MD_FLGENER | OBD_MD_FLRDEV | OBD_MD_FLGROUP)
+#define OBD_MD_FLXATTRALL (OBD_MD_FLXATTR | OBD_MD_FLXATTRLS)
+
/* don't forget obdo_fid which is way down at the bottom so it can
* come after the definition of llog_cookie */
#define OBD_BRW_MEMALLOC 0x800 /* Client runs in the "kswapd" context */
#define OBD_BRW_OVER_USRQUOTA 0x1000 /* Running out of user quota */
#define OBD_BRW_OVER_GRPQUOTA 0x2000 /* Running out of group quota */
+#define OBD_BRW_SOFT_SYNC 0x4000 /* This flag notifies the server
+ * that the client is running low on
+ * space for unstable pages; asking
+ * it to sync quickly */
#define OBD_OBJECT_EOF 0xffffffffffffffffULL
#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_LEASE 0x04000000
+#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_MAXSHIFT 4
+#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 */
#define MDS_INODELOCK_FULL ((1<<(MDS_INODELOCK_MAXSHIFT+1))-1)
}
#endif
+/* 64 possible states */
+enum md_transient_state {
+ MS_RESTORE = (1 << 0), /* restore is running */
+};
+
struct mdt_body {
struct lu_fid fid1;
struct lu_fid fid2;
obd_time ctime;
__u64 blocks; /* XID, in the case of MDS_READPAGE */
__u64 ioepoch;
- __u64 unused1; /* was "ino" until 2.4.0 */
+ __u64 t_state; /* transient file state defined in
+ * enum md_transient_state
+ * was "ino" until 2.4.0 */
__u32 fsuid;
__u32 fsgid;
__u32 capability;
* hsm restore) */
#define MDS_OPEN_VOLATILE 0400000000000ULL /* File is volatile = created
unlinked */
+#define MDS_OPEN_LEASE 01000000000000ULL /* Open the file and grant lease
+ * delegation, succeed if it's not
+ * being opened with conflict mode.
+ */
+#define MDS_OPEN_RELEASE 02000000000000ULL /* Open the file for HSM release */
/* permission for create non-directory file */
#define MAY_CREATE (1 << 7)
/* lfs rgetfacl permission check */
#define MAY_RGETFACL (1 << 14)
-enum {
+enum mds_op_bias {
MDS_CHECK_SPLIT = 1 << 0,
MDS_CROSS_REF = 1 << 1,
MDS_VTX_BYPASS = 1 << 2,
MDS_PERM_BYPASS = 1 << 3,
MDS_SOM = 1 << 4,
MDS_QUOTA_IGNORE = 1 << 5,
- MDS_CLOSE_CLEANUP = 1 << 6,
+ /* Was MDS_CLOSE_CLEANUP (1 << 6), No more used */
MDS_KEEP_ORPHAN = 1 << 7,
MDS_RECOV_OPEN = 1 << 8,
MDS_DATA_MODIFIED = 1 << 9,
MDS_CREATE_VOLATILE = 1 << 10,
MDS_OWNEROVERRIDE = 1 << 11,
+ MDS_HSM_RELEASE = 1 << 12,
};
/* instance of mdt_reint_rec */
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;
+ }
+
+ 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 */
+};
-#define MAX_HASH_SIZE_32 0x7fffffffUL
-#define MAX_HASH_SIZE 0x7fffffffffffffffULL
-#define MAX_HASH_HIGHEST_BIT 0x1000000000000000ULL
+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
*/
__u64 name[RES_NAME_SIZE];
};
+#define DLDLMRES "["LPX64":"LPX64":"LPX64"]."LPX64i
+#define PLDLMRES(res) (res)->lr_name.name[0], (res)->lr_name.name[1], \
+ (res)->lr_name.name[2], (res)->lr_name.name[3]
+
extern void lustre_swab_ldlm_res_id (struct ldlm_res_id *id);
static inline int ldlm_res_eq(const struct ldlm_res_id *res0,
/* LLOG_JOIN_REC = LLOG_OP_MAGIC | 0x50000, obsolete 1.8.0 */
CHANGELOG_REC = LLOG_OP_MAGIC | 0x60000,
CHANGELOG_USER_REC = LLOG_OP_MAGIC | 0x70000,
+ HSM_AGENT_REC = LLOG_OP_MAGIC | 0x80000,
LLOG_HDR_MAGIC = LLOG_OP_MAGIC | 0x45539,
LLOG_LOGID_MAGIC = LLOG_OP_MAGIC | 0x4553b,
} llog_op_type;
struct llog_rec_tail cur_tail;
} __attribute__((packed));
+enum agent_req_status {
+ ARS_WAITING,
+ ARS_STARTED,
+ ARS_FAILED,
+ ARS_CANCELED,
+ ARS_SUCCEED,
+};
+
+static inline char *agent_req_status2name(enum agent_req_status ars)
+{
+ switch (ars) {
+ case ARS_WAITING:
+ return "WAITING";
+ case ARS_STARTED:
+ return "STARTED";
+ case ARS_FAILED:
+ return "FAILED";
+ case ARS_CANCELED:
+ return "CANCELED";
+ case ARS_SUCCEED:
+ return "SUCCEED";
+ default:
+ return "UNKNOWN";
+ }
+}
+
+static inline bool agent_req_in_final_state(enum agent_req_status ars)
+{
+ return ((ars == ARS_SUCCEED) || (ars == ARS_FAILED) ||
+ (ars == ARS_CANCELED));
+}
+
+struct llog_agent_req_rec {
+ struct llog_rec_hdr arr_hdr; /**< record header */
+ __u32 arr_status; /**< status of the request */
+ /* must match enum
+ * agent_req_status */
+ __u32 arr_archive_id; /**< backend archive number */
+ __u64 arr_flags; /**< req flags */
+ __u64 arr_compound_id; /**< compound cookie */
+ __u64 arr_req_create; /**< req. creation time */
+ __u64 arr_req_change; /**< req. status change time */
+ struct hsm_action_item arr_hai; /**< req. to the agent */
+ struct llog_rec_tail arr_tail; /**< record tail for_sizezof_only */
+} __attribute__((packed));
+
/* Old llog gen for compatibility */
struct llog_gen {
__u64 mnt_cnt;
#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, struct obdo *lobdo)
+ struct obdo *wobdo,
+ const struct obdo *lobdo)
{
- memcpy(wobdo, lobdo, sizeof(*lobdo));
+ *wobdo = *lobdo;
wobdo->o_flags &= ~OBD_FL_LOCAL_MASK;
if (ocd == NULL)
return;
if (unlikely(!(ocd->ocd_connect_flags & OBD_CONNECT_FID)) &&
- fid_seq_is_echo(fid_seq(&lobdo->o_oi.oi_fid))) {
+ fid_seq_is_echo(ostid_seq(&lobdo->o_oi))) {
/* Currently OBD_FL_OSTID will only be used when 2.4 echo
* client communicate with pre-2.4 server */
wobdo->o_oi.oi.oi_id = fid_oid(&lobdo->o_oi.oi_fid);
}
static inline void lustre_get_wire_obdo(struct obd_connect_data *ocd,
- struct obdo *lobdo, struct obdo *wobdo)
+ struct obdo *lobdo,
+ const struct obdo *wobdo)
{
obd_flag local_flags = 0;
if (lobdo->o_valid & OBD_MD_FLFLAGS)
local_flags = lobdo->o_flags & OBD_FL_LOCAL_MASK;
- LASSERT(!(wobdo->o_flags & OBD_FL_LOCAL_MASK));
-
- memcpy(lobdo, wobdo, sizeof(*lobdo));
+ *lobdo = *wobdo;
if (local_flags != 0) {
lobdo->o_valid |= OBD_MD_FLFLAGS;
lobdo->o_flags &= ~OBD_FL_LOCAL_MASK;
void lustre_swab_swap_layouts(struct mdc_swap_layouts *msl);
+struct close_data {
+ struct lustre_handle cd_handle;
+ struct lu_fid cd_fid;
+ __u64 cd_data_version;
+ __u64 cd_reserved[8];
+};
+
+void lustre_swab_close_data(struct close_data *data);
+
#endif
/** @} lustreidl */