*/
/*
* This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Sun Microsystems, Inc.
- *
- * lustre/include/lustre/lustre_idl.h
*
* Lustre wire protocol definitions.
*/
* that are used in interfaces with userspace should go in lustre_user.h.
*
* All structs being declared here should be built from simple fixed-size
- * types (__u8, __u16, __u32, __u64) or be built from other types or
+ * types defined in linux/types.h or be built from other types or
* structs also declared in this file. Similarly, all flags and magic
* values in those structs should also be declared here. This ensures
* that the Lustre wire protocol is not influenced by external dependencies.
#include <asm/byteorder.h>
#include <linux/errno.h>
+#include <linux/fiemap.h>
#include <linux/types.h>
-
-/*
- * This is due to us being out of kernel and the way the OpenSFS branch
- * handles CFLAGS.
- */
-#ifdef __KERNEL__
-# include <uapi/linux/lnet/lnet-types.h>
-# include <uapi/linux/lustre/lustre_user.h> /* Defn's shared with user-space. */
-# include <uapi/linux/lustre/lustre_ver.h>
-#else
-# include <linux/lnet/lnet-types.h>
-# include <linux/lustre/lustre_user.h>
-# include <linux/lustre/lustre_ver.h>
-#endif
+#include <linux/lnet/lnet-types.h>
+#include <linux/lustre/lustre_user.h>
+#include <linux/lustre/lustre_ver.h>
#if defined(__cplusplus)
extern "C" {
#define CONNMGR_REQUEST_PORTAL 1
#define CONNMGR_REPLY_PORTAL 2
-//#define OSC_REQUEST_PORTAL 3
+/* #define OSC_REQUEST_PORTAL 3*/
#define OSC_REPLY_PORTAL 4
-//#define OSC_BULK_PORTAL 5
+/*#define OSC_BULK_PORTAL 5*/
#define OST_IO_PORTAL 6
#define OST_CREATE_PORTAL 7
#define OST_BULK_PORTAL 8
-//#define MDC_REQUEST_PORTAL 9
+/*#define MDC_REQUEST_PORTAL 9*/
#define MDC_REPLY_PORTAL 10
-//#define MDC_BULK_PORTAL 11
+/*#define MDC_BULK_PORTAL 11*/
#define MDS_REQUEST_PORTAL 12
#define MDS_IO_PORTAL 13
#define MDS_BULK_PORTAL 14
#define LDLM_CB_REPLY_PORTAL 16
#define LDLM_CANCEL_REQUEST_PORTAL 17
#define LDLM_CANCEL_REPLY_PORTAL 18
-//#define PTLBD_REQUEST_PORTAL 19
-//#define PTLBD_REPLY_PORTAL 20
-//#define PTLBD_BULK_PORTAL 21
+/*#define PTLBD_REQUEST_PORTAL 19*/
+/*#define PTLBD_REPLY_PORTAL 20*/
+/*#define PTLBD_BULK_PORTAL 21*/
#define MDS_SETATTR_PORTAL 22
#define MDS_READPAGE_PORTAL 23
#define OUT_PORTAL 24
return next;
}
-static inline size_t lu_dirent_calc_size(size_t namelen, __u16 attr)
+static inline __kernel_size_t lu_dirent_calc_size(size_t namelen, __u16 attr)
{
- size_t size;
+ __kernel_size_t size;
if (attr & LUDA_TYPE) {
- const size_t align = sizeof(struct luda_type) - 1;
+ const __kernel_size_t align = sizeof(struct luda_type) - 1;
size = (sizeof(struct lu_dirent) + namelen + 1 + align) &
~align;
return (size + 7) & ~7;
}
+static inline __u16 lu_dirent_type_get(struct lu_dirent *ent)
+{
+ __u16 type = 0;
+ struct luda_type *lt;
+ int len = 0;
+
+ if (__le32_to_cpu(ent->lde_attrs) & LUDA_TYPE) {
+ const unsigned int align = sizeof(struct luda_type) - 1;
+
+ len = __le16_to_cpu(ent->lde_namelen);
+ len = (len + align) & ~align;
+ lt = (void *)ent->lde_name + len;
+ type = __le16_to_cpu(lt->lt_type);
+ }
+
+ return type;
+}
+
#define MDS_DIR_END_OFF 0xfffffffffffffffeULL
/**
RPCs in parallel */
#define OBD_CONNECT_DIR_STRIPE 0x400000000000000ULL /* striped DNE dir */
#define OBD_CONNECT_SUBTREE 0x800000000000000ULL /* fileset mount */
-#define OBD_CONNECT_LOCKAHEAD_OLD 0x1000000000000000ULL /* Old Cray lockahead */
+/* was OBD_CONNECT_LOCKAHEAD_OLD 0x1000000000000000ULL old lockahead 2.12-2.13*/
/** bulk matchbits is sent within ptlrpc_body */
#define OBD_CONNECT_BULK_MBITS 0x2000000000000000ULL
#define OBD_CONNECT2_LOCKAHEAD 0x2ULL /* ladvise lockahead v2 */
#define OBD_CONNECT2_DIR_MIGRATE 0x4ULL /* migrate striped dir */
#define OBD_CONNECT2_SUM_STATFS 0x8ULL /* MDT return aggregated stats */
+#define OBD_CONNECT2_OVERSTRIPING 0x10ULL /* OST overstriping support */
#define OBD_CONNECT2_FLR 0x20ULL /* FLR support */
#define OBD_CONNECT2_WBC_INTENTS 0x40ULL /* create/unlink/... intents for wbc, also operations under client-held parent locks */
#define OBD_CONNECT2_LOCK_CONVERT 0x80ULL /* IBITS lock convert support */
#define OBD_CONNECT2_ARCHIVE_ID_ARRAY 0x100ULL /* store HSM archive_id in array */
+#define OBD_CONNECT2_INC_XID 0x200ULL /* Increasing xid */
#define OBD_CONNECT2_SELINUX_POLICY 0x400ULL /* has client SELinux policy */
#define OBD_CONNECT2_LSOM 0x800ULL /* LSOM support */
#define OBD_CONNECT2_PCC 0x1000ULL /* Persistent Client Cache */
-#define OBD_CONNECT2_PLAIN_LAYOUT 0x2000ULL /* Plain Directory Layout */
-
+#define OBD_CONNECT2_CRUSH 0x2000ULL /* crush hash striped directory */
+#define OBD_CONNECT2_ASYNC_DISCARD 0x4000ULL /* support async DoM data discard */
+#define OBD_CONNECT2_ENCRYPT 0x8000ULL /* client-to-disk encrypt */
+#define OBD_CONNECT2_FIDMAP 0x10000ULL /* FID map */
+#define OBD_CONNECT2_GETATTR_PFID 0x20000ULL /* pack parent FID in getattr */
+#define OBD_CONNECT2_LSEEK 0x40000ULL /* SEEK_HOLE/DATA RPC */
+#define OBD_CONNECT2_DOM_LVB 0x80000ULL /* pack DOM glimpse data in LVB */
+#define OBD_CONNECT2_REP_MBITS 0x100000ULL /* match reply mbits not xid*/
+#define OBD_CONNECT2_MODE_CONVERT 0x200000ULL /* LDLM mode convert */
+#define OBD_CONNECT2_BATCH_RPC 0x400000ULL /* Multi-RPC batch request */
+#define OBD_CONNECT2_PCCRO 0x800000ULL /* Read-only PCC */
+#define OBD_CONNECT2_ATOMIC_OPEN_LOCK 0x4000000ULL/* request lock on 1st open */
/* 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
* changes with senior engineers before starting to use a new flag. Then,
* submit a small patch against EVERY branch that ONLY adds the new flag,
- * updates obd_connect_names[] for lprocfs_rd_connect_flags(), adds the
- * flag to check_obd_connect_data(), and updates wiretests accordingly, so it
- * can be approved and landed easily to reserve the flag for future use. */
-
-/* The MNE_SWAB flag is overloading the MDS_MDS bit only for the MGS
- * connection. It is a temporary bug fix for Imperative Recovery interop
- * between 2.2 and 2.3 x86/ppc nodes, and can be removed when interop for
- * 2.2 clients/servers is no longer needed. LU-1252/LU-1644. */
-#define OBD_CONNECT_MNE_SWAB OBD_CONNECT_MDS_MDS
+ * updates obd_connect_names[], adds the flag to check_obd_connect_data(),
+ * and updates wiretests accordingly, so it can be approved and landed easily
+ * to reserve the flag for future use.
+ */
#define OCD_HAS_FLAG(ocd, flg) \
(!!((ocd)->ocd_connect_flags & OBD_CONNECT_##flg))
OBD_CONNECT_GRANT_PARAM | \
OBD_CONNECT_SHORTIO | OBD_CONNECT_FLAGS2)
-#define MDT_CONNECT_SUPPORTED2 (OBD_CONNECT2_FILE_SECCTX | OBD_CONNECT2_FLR | \
- OBD_CONNECT2_SUM_STATFS | \
- OBD_CONNECT2_LOCK_CONVERT | \
+#define MDT_CONNECT_SUPPORTED2 (OBD_CONNECT2_FILE_SECCTX | \
OBD_CONNECT2_DIR_MIGRATE | \
+ OBD_CONNECT2_SUM_STATFS | \
+ OBD_CONNECT2_OVERSTRIPING | \
+ OBD_CONNECT2_FLR |\
+ OBD_CONNECT2_LOCK_CONVERT | \
OBD_CONNECT2_ARCHIVE_ID_ARRAY | \
+ OBD_CONNECT2_INC_XID | \
OBD_CONNECT2_SELINUX_POLICY | \
- OBD_CONNECT2_LSOM)
+ OBD_CONNECT2_LSOM | \
+ OBD_CONNECT2_ASYNC_DISCARD | \
+ OBD_CONNECT2_PCC | \
+ OBD_CONNECT2_CRUSH | \
+ OBD_CONNECT2_ENCRYPT | \
+ OBD_CONNECT2_GETATTR_PFID |\
+ OBD_CONNECT2_LSEEK | OBD_CONNECT2_DOM_LVB |\
+ OBD_CONNECT2_REP_MBITS | \
+ OBD_CONNECT2_ATOMIC_OPEN_LOCK)
#define OST_CONNECT_SUPPORTED (OBD_CONNECT_SRVLOCK | OBD_CONNECT_GRANT | \
OBD_CONNECT_REQPORTAL | OBD_CONNECT_VERSION | \
OBD_CONNECT_GRANT_PARAM | \
OBD_CONNECT_SHORTIO | OBD_CONNECT_FLAGS2)
-#define OST_CONNECT_SUPPORTED2 OBD_CONNECT2_LOCKAHEAD
+#define OST_CONNECT_SUPPORTED2 (OBD_CONNECT2_LOCKAHEAD | OBD_CONNECT2_INC_XID |\
+ OBD_CONNECT2_ENCRYPT | OBD_CONNECT2_LSEEK |\
+ OBD_CONNECT2_REP_MBITS)
-#define ECHO_CONNECT_SUPPORTED (OBD_CONNECT_FID)
-#define ECHO_CONNECT_SUPPORTED2 0
+#define ECHO_CONNECT_SUPPORTED (OBD_CONNECT_FID | OBD_CONNECT_FLAGS2)
+#define ECHO_CONNECT_SUPPORTED2 OBD_CONNECT2_REP_MBITS
#define MGS_CONNECT_SUPPORTED (OBD_CONNECT_VERSION | OBD_CONNECT_AT | \
OBD_CONNECT_FULL20 | OBD_CONNECT_IMP_RECOV | \
- OBD_CONNECT_MNE_SWAB | OBD_CONNECT_PINGLESS |\
- OBD_CONNECT_BULK_MBITS | OBD_CONNECT_BARRIER)
+ OBD_CONNECT_PINGLESS |\
+ OBD_CONNECT_BULK_MBITS | OBD_CONNECT_BARRIER | \
+ OBD_CONNECT_FLAGS2)
-#define MGS_CONNECT_SUPPORTED2 0
+#define MGS_CONNECT_SUPPORTED2 OBD_CONNECT2_REP_MBITS
/* Features required for this version of the client to work with server */
#define CLIENT_CONNECT_MDT_REQD (OBD_CONNECT_FID | \
OST_SYNC = 16,
OST_SET_INFO = 17,
OST_QUOTACHECK = 18, /* not used since 2.4 */
- OST_QUOTACTL = 19,
+ OST_QUOTACTL = 19,
OST_QUOTA_ADJUST_QUNIT = 20, /* not used since 2.4 */
OST_LADVISE = 21,
+ OST_FALLOCATE = 22,
+ OST_SEEK = 23,
OST_LAST_OPC /* must be < 33 to avoid MDS_GETATTR */
};
#define OST_FIRST_OPC OST_REPLY
#define LOV_MAGIC_SPECIFIC (0x0BD50000 | LOV_MAGIC_MAGIC)
#define LOV_MAGIC LOV_MAGIC_V1
#define LOV_MAGIC_COMP_V1 (0x0BD60000 | LOV_MAGIC_MAGIC)
+#define LOV_MAGIC_FOREIGN (0x0BD70000 | LOV_MAGIC_MAGIC)
+#define LOV_MAGIC_SEL (0x0BD80000 | LOV_MAGIC_MAGIC)
/*
* magic for fully defined striping
#define XATTR_NAME_LFSCK_BITMAP "trusted.lfsck_bitmap"
#define XATTR_NAME_DUMMY "trusted.dummy"
+#define LL_XATTR_NAME_ENCRYPTION_CONTEXT XATTR_SECURITY_PREFIX"c"
+
#define XATTR_NAME_LFSCK_NAMESPACE "trusted.lfsck_ns"
#define XATTR_NAME_MAX_LEN 32 /* increase this, if there is longer name. */
}
static inline __u32
-lov_mds_md_max_stripe_count(size_t buf_size, __u32 lmm_magic)
+lov_mds_md_max_stripe_count(__kernel_size_t buf_size, __u32 lmm_magic)
{
switch (lmm_magic) {
case LOV_MAGIC_V1: {
#define OBD_MD_FLOSTLAYOUT (0x0080000000000000ULL) /* contain ost_layout */
#define OBD_MD_FLPROJID (0x0100000000000000ULL) /* project ID */
#define OBD_MD_SECCTX (0x0200000000000000ULL) /* embed security xattr */
-
-#define OBD_MD_FLLSIZE (0x0200000000000000ULL) /* Lazy size */
-#define OBD_MD_FLLBLOCKS (0x0400000000000000ULL) /* Lazy blocks */
+#define OBD_MD_FLLAZYSIZE (0x0400000000000000ULL) /* Lazy size */
+#define OBD_MD_FLLAZYBLOCKS (0x0800000000000000ULL) /* Lazy blocks */
+#define OBD_MD_FLBTIME (0x1000000000000000ULL) /* birth time */
+#define OBD_MD_ENCCTX (0x2000000000000000ULL) /* embed encryption ctx */
#define OBD_MD_FLALLQUOTA (OBD_MD_FLUSRQUOTA | \
OBD_MD_FLGRPQUOTA | \
OBD_MD_FLMODE | OBD_MD_FLTYPE | OBD_MD_FLUID | \
OBD_MD_FLGID | OBD_MD_FLFLAGS | OBD_MD_FLNLINK | \
OBD_MD_FLPARENT | OBD_MD_FLRDEV | OBD_MD_FLGROUP | \
- OBD_MD_FLPROJID)
+ OBD_MD_FLPROJID | OBD_MD_FLBTIME)
#define OBD_MD_FLXATTRALL (OBD_MD_FLXATTR | OBD_MD_FLXATTRLS)
#define OBD_BRW_CHECK 0x10
#define OBD_BRW_FROM_GRANT 0x20 /* the osc manages this under llite */
#define OBD_BRW_GRANTED 0x40 /* the ost manages this */
+/* OBD_BRW_NOCACHE is currently neither set nor tested */
#define OBD_BRW_NOCACHE 0x80 /* this page is a part of non-cached IO */
#define OBD_BRW_NOQUOTA 0x100
#define OBD_BRW_SRVLOCK 0x200 /* Client holds no lock over this page */
* space for unstable pages; asking
* it to sync quickly */
#define OBD_BRW_OVER_PRJQUOTA 0x8000 /* Running out of project quota */
+#define OBD_BRW_RDMA_ONLY 0x20000 /* RPC contains RDMA-only pages*/
#define OBD_BRW_OVER_ALLQUOTA (OBD_BRW_OVER_USRQUOTA | \
OBD_BRW_OVER_GRPQUOTA | \
OBD_BRW_OVER_PRJQUOTA)
+#define OBD_BRW_DONE 0x40000000UL /*
+ * osd-ldiskfs inernal,
+ * IO has been issued before
+ */
#define OBD_BRW_LOCAL1 0x80000000UL /*
* osd-ldiskfs internal,
* page mapped to real block
*/
-#define OBD_BRW_LOCALS (OBD_BRW_LOCAL1)
+#define OBD_BRW_LOCALS (OBD_BRW_LOCAL1 | OBD_BRW_DONE)
#define OBD_MAX_GRANT 0x7fffffffUL /* Max grant allowed to one client: 2 GiB */
__u32 qc_stat;
struct obd_dqinfo qc_dqinfo;
struct obd_dqblk qc_dqblk;
+ char qc_poolname[0];
};
#define Q_COPY(out, in, member) (out)->member = (in)->member
-#define QCTL_COPY(out, in) \
-do { \
- Q_COPY(out, in, qc_cmd); \
- Q_COPY(out, in, qc_type); \
- Q_COPY(out, in, qc_id); \
- Q_COPY(out, in, qc_stat); \
- Q_COPY(out, in, qc_dqinfo); \
- Q_COPY(out, in, qc_dqblk); \
+#define QCTL_COPY(out, in) \
+do { \
+ Q_COPY(out, in, qc_cmd); \
+ Q_COPY(out, in, qc_type); \
+ Q_COPY(out, in, qc_id); \
+ Q_COPY(out, in, qc_stat); \
+ Q_COPY(out, in, qc_dqinfo); \
+ Q_COPY(out, in, qc_dqblk); \
+ if (LUSTRE_Q_CMD_IS_POOL(in->qc_cmd)) \
+ memcpy(out->qc_poolname, \
+ in->qc_poolname, \
+ LOV_MAXPOOLNAME + 1); \
} while (0)
/* Body of quota request used for quota acquire/release RPCs between quota
MDS_HSM_CT_REGISTER = 59,
MDS_HSM_CT_UNREGISTER = 60,
MDS_SWAP_LAYOUTS = 61,
+ MDS_RMFID = 62,
MDS_LAST_OPC
};
#define DISP_OPEN_DENY 0x10000000
/* INODE LOCK PARTS */
-#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_DOM 0x000040 /* Data for data-on-mdt files */
-
-#define MDS_INODELOCK_MAXSHIFT 6
+enum mds_ibits_locks {
+ MDS_INODELOCK_LOOKUP = 0x000001, /* For namespace, dentry etc. Was
+ * used to protect permission (mode,
+ * owner, group, etc) before 2.4. */
+ MDS_INODELOCK_UPDATE = 0x000002, /* size, links, timestamps */
+ MDS_INODELOCK_OPEN = 0x000004, /* For opened files */
+ MDS_INODELOCK_LAYOUT = 0x000008, /* for layout */
+
+ /* The PERM bit is added in 2.4, and is used to protect permission
+ * (mode, owner, group, ACL, etc.) separate from LOOKUP lock.
+ * For remote directories (in DNE) these locks will be granted by
+ * different MDTs (different LDLM namespace).
+ *
+ * For local directory, the MDT always grants UPDATE|PERM together.
+ * For remote directory, master MDT (where remote directory is) grants
+ * UPDATE|PERM, and remote MDT (where name entry is) grants LOOKUP_LOCK.
+ */
+ MDS_INODELOCK_PERM = 0x000010,
+ MDS_INODELOCK_XATTR = 0x000020, /* non-permission extended attrs */
+ MDS_INODELOCK_DOM = 0x000040, /* Data for Data-on-MDT files */
+ /* Do not forget to increase MDS_INODELOCK_NUMBITS when adding bits */
+};
+#define MDS_INODELOCK_NUMBITS 7
/* This FULL lock is useful to take on unlink sort of operations */
-#define MDS_INODELOCK_FULL ((1<<(MDS_INODELOCK_MAXSHIFT+1))-1)
+#define MDS_INODELOCK_FULL ((1 << MDS_INODELOCK_NUMBITS) - 1)
/* DOM lock shouldn't be canceled early, use this macro for ELC */
#define MDS_INODELOCK_ELC (MDS_INODELOCK_FULL & ~MDS_INODELOCK_DOM)
LUSTRE_INDEX_FL = 0x00001000, /* hash-indexed directory */
LUSTRE_DIRSYNC_FL = 0x00010000, /* dirsync behaviour (dir only) */
LUSTRE_TOPDIR_FL = 0x00020000, /* Top of directory hierarchies*/
- LUSTRE_DIRECTIO_FL = 0x00100000, /* Use direct i/o */
LUSTRE_INLINE_DATA_FL = 0x10000000, /* Inode has inline data. */
LUSTRE_PROJINHERIT_FL = 0x20000000, /* Create with parents projid */
* stored in LMA. see LMAI_XXXX */
LUSTRE_ORPHAN_FL = 0x00002000,
LUSTRE_SET_SYNC_FL = 0x00040000, /* Synchronous setattr on OSTs */
+ LUSTRE_ENCRYPT_FL = 0x00800000, /* encrypted file */
- LUSTRE_LMA_FL_MASKS = LUSTRE_ORPHAN_FL,
+ LUSTRE_LMA_FL_MASKS = LUSTRE_ENCRYPT_FL | LUSTRE_ORPHAN_FL,
};
#ifndef FS_XFLAG_SYNC
#define FS_XFLAG_PROJINHERIT 0x00000200 /* create with parents projid */
#endif
-#ifdef __KERNEL__
-/* Convert wire LUSTRE_*_FL to corresponding client local VFS S_* values
- * for the client inode i_flags. The LUSTRE_*_FL are the Lustre wire
- * protocol equivalents of LDISKFS_*_FL values stored on disk, while
- * the S_* flags are kernel-internal values that change between kernel
- * versions. These flags are set/cleared via FSFILT_IOC_{GET,SET}_FLAGS.
- * See b=16526 for a full history. */
-static inline int ll_ext_to_inode_flags(int flags)
-{
- return (((flags & LUSTRE_SYNC_FL) ? S_SYNC : 0) |
- ((flags & LUSTRE_NOATIME_FL) ? S_NOATIME : 0) |
- ((flags & LUSTRE_APPEND_FL) ? S_APPEND : 0) |
-#if defined(S_DIRSYNC)
- ((flags & LUSTRE_DIRSYNC_FL) ? S_DIRSYNC : 0) |
-#endif
- ((flags & LUSTRE_IMMUTABLE_FL) ? S_IMMUTABLE : 0));
-}
-
-static inline int ll_inode_to_ext_flags(int iflags)
-{
- return (((iflags & S_SYNC) ? LUSTRE_SYNC_FL : 0) |
- ((iflags & S_NOATIME) ? LUSTRE_NOATIME_FL : 0) |
- ((iflags & S_APPEND) ? LUSTRE_APPEND_FL : 0) |
-#if defined(S_DIRSYNC)
- ((iflags & S_DIRSYNC) ? LUSTRE_DIRSYNC_FL : 0) |
-#endif
- ((iflags & S_IMMUTABLE) ? LUSTRE_IMMUTABLE_FL : 0));
-}
-
-static inline int ll_xflags_to_inode_flags(int xflags)
-{
- return ((xflags & FS_XFLAG_SYNC) ? S_SYNC : 0) |
- ((xflags & FS_XFLAG_NOATIME) ? S_NOATIME : 0) |
- ((xflags & FS_XFLAG_APPEND) ? S_APPEND : 0) |
- ((xflags & FS_XFLAG_IMMUTABLE) ? S_IMMUTABLE : 0);
-}
-
-static inline int ll_inode_flags_to_xflags(int flags)
-{
- return ((flags & S_SYNC) ? FS_XFLAG_SYNC : 0) |
- ((flags & S_NOATIME) ? FS_XFLAG_NOATIME : 0) |
- ((flags & S_APPEND) ? FS_XFLAG_APPEND : 0) |
- ((flags & S_IMMUTABLE) ? FS_XFLAG_IMMUTABLE : 0);
-}
-#endif
-
/* 64 possible states */
enum md_transient_state {
MS_RESTORE = (1 << 0), /* restore is running */
__u32 mbo_mode;
__u32 mbo_uid;
__u32 mbo_gid;
- __u32 mbo_flags; /* LUSTRE_*_FL file attributes */
+ __u32 mbo_flags; /* most replies: LUSTRE_*_FL file attributes,
+ * data_version: OBD_FL_* flags
+ */
__u32 mbo_rdev;
__u32 mbo_nlink; /* #bytes to read in the case of MDS_READPAGE */
__u32 mbo_layout_gen; /* was "generation" until 2.4.0 */
__u32 mbo_projid;
__u64 mbo_dom_size; /* size of DOM component */
__u64 mbo_dom_blocks; /* blocks consumed by DOM component */
- __u64 mbo_padding_8; /* also fix lustre_swab_mdt_body */
- __u64 mbo_padding_9;
+ __u64 mbo_btime;
+ __u64 mbo_padding_9; /* also fix lustre_swab_mdt_body */
__u64 mbo_padding_10;
}; /* 216 */
* since the client and MDS may run different kernels (see bug 13828)
* Therefore, we should only use MDS_ATTR_* attributes for sa_valid.
*/
-#define MDS_ATTR_MODE 0x1ULL /* = 1 */
-#define MDS_ATTR_UID 0x2ULL /* = 2 */
-#define MDS_ATTR_GID 0x4ULL /* = 4 */
-#define MDS_ATTR_SIZE 0x8ULL /* = 8 */
-#define MDS_ATTR_ATIME 0x10ULL /* = 16 */
-#define MDS_ATTR_MTIME 0x20ULL /* = 32 */
-#define MDS_ATTR_CTIME 0x40ULL /* = 64 */
-#define MDS_ATTR_ATIME_SET 0x80ULL /* = 128 */
-#define MDS_ATTR_MTIME_SET 0x100ULL /* = 256 */
-#define MDS_ATTR_FORCE 0x200ULL /* = 512, Not a change, but a change it */
-#define MDS_ATTR_ATTR_FLAG 0x400ULL /* = 1024 */
-#define MDS_ATTR_KILL_SUID 0x800ULL /* = 2048 */
-#define MDS_ATTR_KILL_SGID 0x1000ULL /* = 4096 */
-#define MDS_ATTR_CTIME_SET 0x2000ULL /* = 8192 */
-#define MDS_ATTR_FROM_OPEN 0x4000ULL /* = 16384, called from open path, ie O_TRUNC */
-#define MDS_ATTR_BLOCKS 0x8000ULL /* = 32768 */
-#define MDS_ATTR_PROJID 0x10000ULL /* = 65536 */
-#define MDS_ATTR_LSIZE 0x20000ULL /* = 131072 */
-#define MDS_ATTR_LBLOCKS 0x40000ULL /* = 262144 */
-#define MDS_ATTR_OVERRIDE 0x2000000ULL /* = 33554432 */
+enum mds_attr_flags {
+ MDS_ATTR_MODE = 0x1ULL, /* = 1 */
+ MDS_ATTR_UID = 0x2ULL, /* = 2 */
+ MDS_ATTR_GID = 0x4ULL, /* = 4 */
+ MDS_ATTR_SIZE = 0x8ULL, /* = 8 */
+ MDS_ATTR_ATIME = 0x10ULL, /* = 16 */
+ MDS_ATTR_MTIME = 0x20ULL, /* = 32 */
+ MDS_ATTR_CTIME = 0x40ULL, /* = 64 */
+ MDS_ATTR_ATIME_SET = 0x80ULL, /* = 128 */
+ MDS_ATTR_MTIME_SET = 0x100ULL, /* = 256 */
+ MDS_ATTR_FORCE = 0x200ULL, /* = 512, change it */
+ MDS_ATTR_ATTR_FLAG = 0x400ULL, /* = 1024 */
+ MDS_ATTR_KILL_SUID = 0x800ULL, /* = 2048 */
+ MDS_ATTR_KILL_SGID = 0x1000ULL, /* = 4096 */
+ MDS_ATTR_CTIME_SET = 0x2000ULL, /* = 8192 */
+ MDS_ATTR_FROM_OPEN = 0x4000ULL, /* = 16384, from open O_TRUNC */
+ MDS_ATTR_BLOCKS = 0x8000ULL, /* = 32768 */
+ MDS_ATTR_PROJID = 0x10000ULL, /* = 65536 */
+ MDS_ATTR_LSIZE = 0x20000ULL, /* = 131072 */
+ MDS_ATTR_LBLOCKS = 0x40000ULL, /* = 262144 */
+ MDS_ATTR_OVERRIDE = 0x2000000ULL, /* = 33554432 */
+};
enum mds_op_bias {
/* MDS_CHECK_SPLIT = 1 << 0, obsolete before 2.3.58 */
+ /* used for remote object getattr/open by name: in the original
+ * getattr/open request, MDT found the object against name is on another
+ * MDT, then packed FID and LOOKUP lock in reply and returned -EREMOTE,
+ * and client knew it's a remote object, then set this flag in
+ * getattr/open request and sent to the corresponding MDT to finish
+ * getattr/open, which fetched attributes and UPDATE lock/opened file.
+ */
MDS_CROSS_REF = 1 << 1,
/* MDS_VTX_BYPASS = 1 << 2, obsolete since 2.3.54 */
MDS_PERM_BYPASS = 1 << 3,
MDS_CLOSE_RESYNC_DONE = 1 << 16,
MDS_CLOSE_LAYOUT_SPLIT = 1 << 17,
MDS_TRUNC_KEEP_LEASE = 1 << 18,
+ MDS_PCC_ATTACH = 1 << 19,
+ MDS_CLOSE_UPDATE_TIMES = 1 << 20,
+ /* setstripe create only, don't restripe if target exists */
+ MDS_SETSTRIPE_CREATE = 1 << 21,
};
#define MDS_CLOSE_INTENT (MDS_HSM_RELEASE | MDS_CLOSE_LAYOUT_SWAP | \
struct lu_fid cr_fid2;
struct lustre_handle cr_open_handle_old; /* in case of open replay */
__s64 cr_time;
- __u64 cr_rdev;
+ union {
+ __u64 cr_rdev;
+ __u32 cr_archive_id;
+ };
__u64 cr_ioepoch;
__u64 cr_padding_1; /* rr_blocks */
__u32 cr_mode;
__u16 rr_padding_4; /* also fix lustre_swab_mdt_rec_reint */
};
+#define LMV_DESC_QOS_MAXAGE_DEFAULT 60 /* Seconds */
+
/* lmv structures */
struct lmv_desc {
__u32 ld_tgt_count; /* how many MDS's */
struct lu_fid lmv_stripe_fids[0]; /* FIDs for each stripe */
};
+/* stripe count before directory split */
+#define lmv_split_offset lmv_migrate_offset
+/* stripe count after directory merge */
+#define lmv_merge_offset lmv_migrate_offset
+/* directory hash type after merge */
+#define lmv_merge_hash lmv_migrate_hash
+
+/* foreign LMV EA */
+struct lmv_foreign_md {
+ __u32 lfm_magic; /* magic number = LMV_MAGIC_FOREIGN */
+ __u32 lfm_length; /* length of lfm_value */
+ __u32 lfm_type; /* type, see LU_FOREIGN_TYPE_ */
+ __u32 lfm_flags; /* flags, type specific */
+ char lfm_value[]; /* free format value */
+};
+
#define LMV_MAGIC_V1 0x0CD20CD0 /* normal stripe lmv magic */
#define LMV_MAGIC LMV_MAGIC_V1
/* #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
-
-#if LUSTRE_VERSION_CODE < OBD_OCD_VERSION(2, 12, 53, 0)
-/* Since lustre 2.8, this flag will not be needed, instead this DEAD
- * and orphan flags will be stored in LMA (see LMAI_ORPHAN)
- * Keep this flag just for LFSCK, because it still might meet such
- * flag when it checks the old FS */
-#define LMV_HASH_FLAG_DEAD 0x40000000
-#endif
-#define LMV_HASH_FLAG_BAD_TYPE 0x20000000
-
-/* 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
+#define LMV_MAGIC_FOREIGN 0x0CD50CD0 /* magic for lmv foreign */
/**
* The FNV-1a hash algorithm is as follows:
**/
#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)
+static inline __u64 lustre_hash_fnv_1a_64(const void *buf, __kernel_size_t size)
{
__u64 hash = LUSTRE_FNV_1A_64_OFFSET_BIAS;
const unsigned char *p = buf;
- size_t i;
+ __kernel_size_t i;
for (i = 0; i < size; i++) {
hash ^= p[i];
return hash;
}
+/* CRUSH placement group count */
+#define LMV_CRUSH_PG_COUNT 4096
+
union lmv_mds_md {
__u32 lmv_magic;
struct lmv_mds_md_v1 lmv_md_v1;
struct lmv_user_md lmv_user_md;
+ struct lmv_foreign_md lmv_foreign_md;
};
-static inline int lmv_mds_md_size(int stripe_count, unsigned int lmm_magic)
+static inline __kernel_ssize_t lmv_mds_md_size(int stripe_count,
+ unsigned int lmm_magic)
{
+ __kernel_ssize_t len = -EINVAL;
+
switch (lmm_magic) {
- case LMV_MAGIC_V1:{
+ case LMV_MAGIC_V1: {
struct lmv_mds_md_v1 *lmm1;
- return sizeof(*lmm1) + stripe_count *
- sizeof(lmm1->lmv_stripe_fids[0]);
- }
+ len = sizeof(*lmm1);
+ len += stripe_count * sizeof(lmm1->lmv_stripe_fids[0]);
+ break; }
default:
- return -EINVAL;
+ break;
}
+ return len;
}
static inline int lmv_mds_md_stripe_count_get(const union lmv_mds_md *lmm)
__u64 try_bits; /* optional bits to try */
__u64 cancel_bits; /* for lock convert */
};
+ __u64 li_gid;
};
struct ldlm_flock_wire {
MGS_FIRST_OPC = MGS_CONNECT
};
-#if LUSTRE_VERSION_CODE < OBD_OCD_VERSION(2, 13, 53, 0)
+#if LUSTRE_VERSION_CODE < OBD_OCD_VERSION(2, 18, 53, 0)
#define MGS_PARAM_MAXLEN 1024
#define KEY_SET_INFO "set_info"
struct mgs_send_param {
- char mgs_param[MGS_PARAM_MAXLEN];
+ char mgs_param[MGS_PARAM_MAXLEN];
};
#endif
} u;
};
-enum {
- CONFIG_T_CONFIG = 0,
- CONFIG_T_SPTLRPC = 1,
- CONFIG_T_RECOVER = 2,
- CONFIG_T_PARAMS = 3,
- CONFIG_T_NODEMAP = 4,
- CONFIG_T_BARRIER = 5,
- CONFIG_T_MAX
+enum mgs_cfg_type {
+ MGS_CFG_T_CONFIG = 0,
+ MGS_CFG_T_SPTLRPC = 1,
+ MGS_CFG_T_RECOVER = 2,
+ MGS_CFG_T_PARAMS = 3,
+ MGS_CFG_T_NODEMAP = 4,
+ MGS_CFG_T_BARRIER = 5,
+ MGS_CFG_T_MAX
};
struct mgs_config_body {
char mcb_name[MTI_NAME_MAXLEN]; /* logname */
__u64 mcb_offset; /* next index of config log to request */
- __u16 mcb_type; /* type of log: CONFIG_T_[CONFIG|RECOVER] */
+ __u16 mcb_type; /* type of log: MGS_CFG_T_[CONFIG|RECOVER] */
__u8 mcb_nm_cur_pass;
__u8 mcb_bits; /* bits unit size of config log */
__u32 mcb_units; /* # of units for bulk transfer */
/* LLOG_JOIN_REC = LLOG_OP_MAGIC | 0x50000, obsolete 1.8.0 */
CHANGELOG_REC = LLOG_OP_MAGIC | 0x60000,
CHANGELOG_USER_REC = LLOG_OP_MAGIC | 0x70000,
+ CHANGELOG_USER_REC2 = LLOG_OP_MAGIC | 0x70002,
HSM_AGENT_REC = LLOG_OP_MAGIC | 0x80000,
UPDATE_REC = LLOG_OP_MAGIC | 0xa0000,
LLOG_HDR_MAGIC = LLOG_OP_MAGIC | 0x45539,
__u32 lrh_index;
__u32 lrh_type;
__u32 lrh_id;
-};
+} __attribute__((packed));
struct llog_rec_tail {
__u32 lrt_len;
__u32 lrt_index;
-};
+} __attribute__((packed));
/* Where data follow just after header */
#define REC_DATA(ptr) \
#define CHANGELOG_MAGIC 0xca103000
/** \a changelog_rec_type's that can't be masked */
-#define CHANGELOG_MINMASK (1 << CL_MARK)
+#define CHANGELOG_MINMASK BIT(CL_MARK)
/** bits covering all \a changelog_rec_type's */
-#define CHANGELOG_ALLMASK 0XFFFFFFFF
+#define CHANGELOG_ALLMASK (BIT(CL_LAST) - 1)
/** 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.
* be costly and only necessary for audit purpose.
*/
#define CHANGELOG_DEFMASK (CHANGELOG_ALLMASK & \
- ~(1 << CL_ATIME | 1 << CL_OPEN | 1 << CL_GETXATTR | \
- 1 << CL_DN_OPEN))
+ ~(BIT(CL_ATIME) | BIT(CL_OPEN) | BIT(CL_GETXATTR) | BIT(CL_DN_OPEN)))
/* changelog llog name, needed by client replicators */
#define CHANGELOG_CATALOG "changelog_catalog"
} __attribute__((packed));
#define CHANGELOG_USER_PREFIX "cl"
+#define CHANGELOG_USER_NAMELEN 16 /* base name including NUL terminator */
+#define CHANGELOG_USER_NAMELEN_FULL 30 /* basename plus 'cl$ID-' prefix */
struct llog_changelog_user_rec {
struct llog_rec_hdr cur_hdr;
struct llog_rec_tail cur_tail;
} __attribute__((packed));
+/* this is twice the size of CHANGELOG_USER_REC */
+struct llog_changelog_user_rec2 {
+ struct llog_rec_hdr cur_hdr;
+ __u32 cur_id;
+ /* only for use in relative time comparisons to detect idle users */
+ __u32 cur_time;
+ __u64 cur_endrec;
+ __u32 cur_mask;
+ __u32 cur_padding1;
+ char cur_name[CHANGELOG_USER_NAMELEN];
+ __u64 cur_padding2;
+ __u64 cur_padding3;
+ struct llog_rec_tail cur_tail;
+} __attribute__((packed));
+
enum agent_req_status {
ARS_WAITING,
ARS_STARTED,
LLOG_F_EXT_X_NID = 0x80,
LLOG_F_EXT_X_OMODE = 0x100,
LLOG_F_EXT_X_XATTR = 0x200,
+ LLOG_F_RM_ON_ERR = 0x400,
/* Note: Flags covered by LLOG_F_EXT_MASK will be inherited from
* catlog to plain log, so do not add LLOG_F_IS_FIXSIZE here,
#define o_dropped o_misc
#define o_cksum o_nlink
#define o_grant_used o_data_version
+#define o_falloc_mode o_nlink
struct lfsck_request {
__u32 lr_event;
SEC_FIRST_OPC = SEC_CTX_INIT
};
-/*
- * capa related definitions
- */
-#define CAPA_HMAC_MAX_LEN 64
-#define CAPA_HMAC_KEY_MAX_LEN 56
-
-/* NB take care when changing the sequence of elements this struct,
- * because the offset info is used in find_capa() */
-struct lustre_capa {
- struct lu_fid lc_fid; /** fid */
- __u64 lc_opc; /** operations allowed */
- __u64 lc_uid; /** file owner */
- __u64 lc_gid; /** file group */
- __u32 lc_flags; /** HMAC algorithm & flags */
- __u32 lc_keyid; /** key# used for the capability */
- __u32 lc_timeout; /** capa timeout value (sec) */
- __u32 lc_expiry; /** expiry time (sec) */
- __u8 lc_hmac[CAPA_HMAC_MAX_LEN]; /** HMAC */
-} __attribute__((packed));
-
-/** lustre_capa::lc_opc */
-enum {
- CAPA_OPC_BODY_WRITE = 1<<0, /**< write object data */
- CAPA_OPC_BODY_READ = 1<<1, /**< read object data */
- CAPA_OPC_INDEX_LOOKUP = 1<<2, /**< lookup object fid */
- CAPA_OPC_INDEX_INSERT = 1<<3, /**< insert object fid */
- CAPA_OPC_INDEX_DELETE = 1<<4, /**< delete object fid */
- CAPA_OPC_OSS_WRITE = 1<<5, /**< write oss object data */
- CAPA_OPC_OSS_READ = 1<<6, /**< read oss object data */
- CAPA_OPC_OSS_TRUNC = 1<<7, /**< truncate oss object */
- CAPA_OPC_OSS_DESTROY = 1<<8, /**< destroy oss object */
- CAPA_OPC_META_WRITE = 1<<9, /**< write object meta data */
- CAPA_OPC_META_READ = 1<<10, /**< read object meta data */
-};
-
-#define CAPA_OPC_OSS_RW (CAPA_OPC_OSS_READ | CAPA_OPC_OSS_WRITE)
-#define CAPA_OPC_MDS_ONLY \
- (CAPA_OPC_BODY_WRITE | CAPA_OPC_BODY_READ | CAPA_OPC_INDEX_LOOKUP | \
- CAPA_OPC_INDEX_INSERT | CAPA_OPC_INDEX_DELETE)
-#define CAPA_OPC_OSS_ONLY \
- (CAPA_OPC_OSS_WRITE | CAPA_OPC_OSS_READ | CAPA_OPC_OSS_TRUNC | \
- CAPA_OPC_OSS_DESTROY)
-#define CAPA_OPC_MDS_DEFAULT ~CAPA_OPC_OSS_ONLY
-#define CAPA_OPC_OSS_DEFAULT ~(CAPA_OPC_MDS_ONLY | CAPA_OPC_OSS_ONLY)
-
-/* lustre_capa::lc_hmac_alg */
-enum {
- CAPA_HMAC_ALG_SHA1 = 1, /**< sha1 algorithm */
- CAPA_HMAC_ALG_MAX,
-};
-
-#define CAPA_FL_MASK 0x00ffffff
-#define CAPA_HMAC_ALG_MASK 0xff000000
-
-struct lustre_capa_key {
- __u64 lk_seq; /**< mds# */
- __u32 lk_keyid; /**< key# */
- __u32 lk_padding;
- __u8 lk_key[CAPA_HMAC_KEY_MAX_LEN]; /**< key */
-} __attribute__((packed));
-
/** The link ea holds 1 \a link_ea_entry for each hardlink */
#define LINK_EA_MAGIC 0x11EAF1DFUL
struct link_ea_header {
unsigned char lee_reclen[2];
unsigned char lee_parent_fid[sizeof(struct lu_fid)];
char lee_name[0];
-}__attribute__((packed));
+} __attribute__((packed));
/** fid2path request/reply structure */
struct getinfo_fid2path {
struct close_data_resync_done cd_resync;
/* split close */
__u16 cd_mirror_id;
+ /* PCC release */
+ __u32 cd_archive_id;
};
};
struct lu_fid uop_fid;
__u16 uop_type;
__u16 uop_param_count;
- __u16 uop_params_off[0];
-};
+ __u16 uop_params_off[];
+} __attribute__((packed));
struct update_ops {
struct update_op uops_op[0];
git://git.whamcloud.com / fs / lustre-release.git / blobdiff