* Copyright (c) 2003, 2010, Oracle and/or its affiliates. All rights reserved.
* Use is subject to license terms.
*
- * Copyright (c) 2010, 2016, Intel Corporation.
+ * Copyright (c) 2010, 2017, Intel Corporation.
*/
/*
* This file is part of Lustre, http://www.lustre.org/
* @{
*/
+#include <linux/kernel.h>
#include <linux/types.h>
#ifdef __KERNEL__
# include <linux/lustre/lustre_fiemap.h>
#endif /* __KERNEL__ */
+/* Handle older distros */
+#ifndef __ALIGN_KERNEL
+# define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1)
+# define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask))
+#endif
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
/*
* This is a temporary solution of adding quota type.
* Should be removed as soon as system header is updated.
};
#define PRJQUOTA 2
-#if defined(__x86_64__) || defined(__ia64__) || defined(__ppc64__) || \
- defined(__craynv) || defined(__mips64__) || defined(__powerpc64__) || \
- defined(__aarch64__)
-typedef struct stat lstat_t;
-# define lstat_f lstat
-# define fstat_f fstat
-# define fstatat_f fstatat
-# define HAVE_LOV_USER_MDS_DATA
-#elif defined(__USE_LARGEFILE64) || defined(__KERNEL__)
-typedef struct stat64 lstat_t;
-# define lstat_f lstat64
-# define fstat_f fstat64
-# define fstatat_f fstatat64
-# define HAVE_LOV_USER_MDS_DATA
+/*
+ * We need to always use 64bit version because the structure
+ * is shared across entire cluster where 32bit and 64bit machines
+ * are co-existing.
+ */
+#if __BITS_PER_LONG != 64 || defined(__ARCH_WANT_STAT64)
+typedef struct stat64 lstat_t;
+#define lstat_f lstat64
+#define fstat_f fstat64
+#define fstatat_f fstatat64
+#else
+typedef struct stat lstat_t;
+#define lstat_f lstat
+#define fstat_f fstat
+#define fstatat_f fstatat
#endif
+#define HAVE_LOV_USER_MDS_DATA
+
#define LUSTRE_EOF 0xffffffffffffffffULL
/* for statfs() */
OS_STATE_ENOINO = 0x00000040, /**< not enough inodes */
};
+/** filesystem statistics/attributes for target device */
struct obd_statfs {
- __u64 os_type;
- __u64 os_blocks;
- __u64 os_bfree;
- __u64 os_bavail;
- __u64 os_files;
- __u64 os_ffree;
- __u8 os_fsid[40];
- __u32 os_bsize;
- __u32 os_namelen;
- __u64 os_maxbytes;
- __u32 os_state; /**< obd_statfs_state OS_STATE_* flag */
- __u32 os_fprecreated; /* objs available now to the caller */
+ __u64 os_type; /* EXT4_SUPER_MAGIC, UBERBLOCK_MAGIC */
+ __u64 os_blocks; /* total size in #os_bsize blocks */
+ __u64 os_bfree; /* number of unused blocks */
+ __u64 os_bavail; /* blocks available for allocation */
+ __u64 os_files; /* total number of objects */
+ __u64 os_ffree; /* # objects that could be created */
+ __u8 os_fsid[40]; /* identifier for filesystem */
+ __u32 os_bsize; /* block size in bytes for os_blocks */
+ __u32 os_namelen; /* maximum length of filename in bytes*/
+ __u64 os_maxbytes; /* maximum object size in bytes */
+ __u32 os_state; /**< obd_statfs_state OS_STATE_* flag */
+ __u32 os_fprecreated; /* objs available now to the caller */
/* used in QoS code to find preferred
* OSTs */
- __u32 os_spare2;
- __u32 os_spare3;
- __u32 os_spare4;
- __u32 os_spare5;
- __u32 os_spare6;
- __u32 os_spare7;
- __u32 os_spare8;
- __u32 os_spare9;
+ __u32 os_spare2; /* Unused padding fields. Remember */
+ __u32 os_spare3; /* to fix lustre_swab_obd_statfs() */
+ __u32 os_spare4;
+ __u32 os_spare5;
+ __u32 os_spare6;
+ __u32 os_spare7;
+ __u32 os_spare8;
+ __u32 os_spare9;
};
/**
struct filter_fid {
struct lu_fid ff_parent;
struct ost_layout ff_layout;
+ __u32 ff_layout_version;
+ __u32 ff_range; /* range of layout version that
+ * write are allowed */
} __attribute__((packed));
/* Userspace should treat lu_fid as opaque, and only use the following methods
* to print or parse them. Other functions (e.g. compare, swab) could be moved
* here from lustre_idl.h if needed. */
-typedef struct lu_fid lustre_fid;
+struct lu_fid;
enum lma_compat {
LMAC_HSM = 0x00000001,
* under /O/<seq>/d<x>. */
LMAC_STRIPE_INFO = 0x00000010, /* stripe info in the LMA EA. */
LMAC_COMP_INFO = 0x00000020, /* Component info in the LMA EA. */
+ LMAC_IDX_BACKUP = 0x00000040, /* Has index backup. */
};
/**
*/
#define LMA_OLD_SIZE (sizeof(struct lustre_mdt_attrs) + 5 * sizeof(__u64))
+enum {
+ LSOM_FL_VALID = 1 << 0,
+};
+
+struct lustre_som_attrs {
+ __u16 lsa_valid;
+ __u16 lsa_reserved[3];
+ __u64 lsa_size;
+ __u64 lsa_blocks;
+};
+
/**
* OST object IDentifier.
*/
};
/*
+ * Maximum number of mirrors currently implemented.
+ */
+#define LUSTRE_MIRROR_COUNT_MAX 16
+
+/* Lease types for use as arg and return of LL_IOC_{GET,SET}_LEASE ioctl. */
+enum ll_lease_mode {
+ LL_LEASE_RDLCK = 0x01,
+ LL_LEASE_WRLCK = 0x02,
+ LL_LEASE_UNLCK = 0x04,
+};
+
+enum ll_lease_flags {
+ LL_LEASE_RESYNC = 0x1,
+ LL_LEASE_RESYNC_DONE = 0x2,
+ LL_LEASE_LAYOUT_MERGE = 0x4,
+ LL_LEASE_LAYOUT_SPLIT = 0x8,
+};
+
+#define IOC_IDS_MAX 4096
+struct ll_ioc_lease {
+ __u32 lil_mode;
+ __u32 lil_flags;
+ __u32 lil_count;
+ __u32 lil_ids[0];
+};
+
+/*
* The ioctl naming rules:
* LL_* - works on the currently opened filehandle instead of parent dir
* *_OBD_* - gets data for both OSC or MDC (LOV, LMV indirectly)
#define LL_IOC_GET_CONNECT_FLAGS _IOWR('f', 174, __u64 *)
#define LL_IOC_GET_MDTIDX _IOR ('f', 175, int)
#define LL_IOC_FUTIMES_3 _IOWR('f', 176, struct ll_futimes_3)
+#define LL_IOC_FLR_SET_MIRROR _IOW ('f', 177, long)
/* lustre_ioctl.h 177-210 */
#define LL_IOC_HSM_STATE_GET _IOR('f', 211, struct hsm_user_state)
#define LL_IOC_HSM_STATE_SET _IOW('f', 212, struct hsm_state_set)
#define LL_IOC_LMV_SETSTRIPE _IOWR('f', 240, struct lmv_user_md)
#define LL_IOC_LMV_GETSTRIPE _IOWR('f', 241, struct lmv_user_md)
#define LL_IOC_REMOVE_ENTRY _IOWR('f', 242, __u64)
-#define LL_IOC_SET_LEASE _IOWR('f', 243, long)
+#define LL_IOC_SET_LEASE _IOWR('f', 243, struct ll_ioc_lease)
+#define LL_IOC_SET_LEASE_OLD _IOWR('f', 243, long)
#define LL_IOC_GET_LEASE _IO('f', 244)
#define LL_IOC_HSM_IMPORT _IOWR('f', 245, struct hsm_user_import)
#define LL_IOC_LMV_SET_DEFAULT_STRIPE _IOWR('f', 246, struct lmv_user_md)
#endif
#define LL_IOC_FSGETXATTR FS_IOC_FSGETXATTR
#define LL_IOC_FSSETXATTR FS_IOC_FSSETXATTR
+#define LL_PROJINHERIT_FL 0x20000000
-/* Lease types for use as arg and return of LL_IOC_{GET,SET}_LEASE ioctl. */
-enum ll_lease_type {
- LL_LEASE_RDLCK = 0x1,
- LL_LEASE_WRLCK = 0x2,
- LL_LEASE_UNLCK = 0x4,
-};
-
#define LL_STATFS_LMV 1
#define LL_STATFS_LOV 2
#define LL_STATFS_NODELAY 4
#define LOV_USER_MAGIC_SPECIFIC 0x0BD50BD0 /* for specific OSTs */
#define LOV_USER_MAGIC_COMP_V1 0x0BD60BD0
-#define LMV_USER_MAGIC 0x0CD30CD0 /*default lmv magic*/
+#define LMV_USER_MAGIC 0x0CD30CD0 /* default lmv magic */
+#define LMV_USER_MAGIC_V0 0x0CD20CD0 /* old default lmv magic*/
+#define LMV_USER_MAGIC_SPECIFIC 0x0CD40CD0
+#define LOV_PATTERN_NONE 0x000
#define LOV_PATTERN_RAID0 0x001
#define LOV_PATTERN_RAID1 0x002
-#define LOV_PATTERN_FIRST 0x100
+#define LOV_PATTERN_MDT 0x100
#define LOV_PATTERN_CMOBD 0x200
#define LOV_PATTERN_F_MASK 0xffff0000
#define LOV_PATTERN_F_HOLE 0x40000000 /* there is hole in LOV EA */
#define LOV_PATTERN_F_RELEASED 0x80000000 /* HSM released file */
+#define LOV_PATTERN_DEFAULT 0xffffffff
static inline bool lov_pattern_supported(__u32 pattern)
{
- return pattern == LOV_PATTERN_RAID0 ||
- pattern == (LOV_PATTERN_RAID0 | LOV_PATTERN_F_RELEASED);
+ return (pattern & ~LOV_PATTERN_F_RELEASED) == LOV_PATTERN_RAID0 ||
+ (pattern & ~LOV_PATTERN_F_RELEASED) == LOV_PATTERN_MDT;
}
#define LOV_MAXPOOLNAME 15
__u64 e_end;
};
-#define DEXT "[ %#llx , %#llx )"
+#define DEXT "[%#llx, %#llx)"
#define PEXT(ext) (ext)->e_start, (ext)->e_end
static inline bool lu_extent_is_overlapped(struct lu_extent *e1,
return e1->e_start < e2->e_end && e2->e_start < e1->e_end;
}
+static inline bool lu_extent_is_whole(struct lu_extent *e)
+{
+ return e->e_start == 0 && e->e_end == LUSTRE_EOF;
+}
+
enum lov_comp_md_entry_flags {
- LCME_FL_PRIMARY = 0x00000001, /* Not used */
- LCME_FL_STALE = 0x00000002, /* Not used */
- LCME_FL_OFFLINE = 0x00000004, /* Not used */
- LCME_FL_PREFERRED = 0x00000008, /* Not used */
+ LCME_FL_STALE = 0x00000001, /* FLR: stale data */
+ LCME_FL_PREF_RD = 0x00000002, /* FLR: preferred for reading */
+ LCME_FL_PREF_WR = 0x00000004, /* FLR: preferred for writing */
+ LCME_FL_PREF_RW = LCME_FL_PREF_RD | LCME_FL_PREF_WR,
+ LCME_FL_OFFLINE = 0x00000008, /* Not used */
LCME_FL_INIT = 0x00000010, /* instantiated */
LCME_FL_NEG = 0x80000000 /* used to indicate a negative flag,
won't be stored on disk */
};
-#define LCME_KNOWN_FLAGS (LCME_FL_NEG | LCME_FL_INIT)
+#define LCME_KNOWN_FLAGS (LCME_FL_NEG | LCME_FL_INIT | LCME_FL_STALE | \
+ LCME_FL_PREF_RW)
+/* The flags can be set by users at mirror creation time. */
+#define LCME_USER_FLAGS (LCME_FL_PREF_RW)
+
+/* the highest bit in obdo::o_layout_version is used to mark if the file is
+ * being resynced. */
+#define LU_LAYOUT_RESYNC LCME_FL_NEG
/* lcme_id can be specified as certain flags, and the the first
* bit of lcme_id is used to indicate that the ID is representing
__u64 lcme_padding[2];
} __attribute__((packed));
-enum lov_comp_md_flags;
+#define SEQ_ID_MAX 0x0000FFFF
+#define SEQ_ID_MASK SEQ_ID_MAX
+/* bit 30:16 of lcme_id is used to store mirror id */
+#define MIRROR_ID_MASK 0x7FFF0000
+#define MIRROR_ID_SHIFT 16
+
+static inline __u32 pflr_id(__u16 mirror_id, __u16 seqid)
+{
+ return ((mirror_id << MIRROR_ID_SHIFT) & MIRROR_ID_MASK) | seqid;
+}
+
+static inline __u16 mirror_id_of(__u32 id)
+{
+ return (id & MIRROR_ID_MASK) >> MIRROR_ID_SHIFT;
+}
+
+/**
+ * on-disk data for lcm_flags. Valid if lcm_magic is LOV_MAGIC_COMP_V1.
+ */
+enum lov_comp_md_flags {
+ /* the least 2 bits are used by FLR to record file state */
+ LCM_FL_NONE = 0,
+ LCM_FL_RDONLY = 1,
+ LCM_FL_WRITE_PENDING = 2,
+ LCM_FL_SYNC_PENDING = 3,
+ LCM_FL_FLR_MASK = 0x3,
+};
struct lov_comp_md_v1 {
__u32 lcm_magic; /* LOV_USER_MAGIC_COMP_V1 */
__u32 lcm_layout_gen;
__u16 lcm_flags;
__u16 lcm_entry_count;
- __u64 lcm_padding1;
+ /* lcm_mirror_count stores the number of actual mirrors minus 1,
+ * so that non-flr files will have value 0 meaning 1 mirror. */
+ __u16 lcm_mirror_count;
+ __u16 lcm_padding1[3];
__u64 lcm_padding2;
struct lov_comp_md_entry_v1 lcm_entries[0];
} __attribute__((packed));
lstat_t lmd_st; /* MDS stat struct */
struct lov_user_md_v1 lmd_lmm; /* LOV EA V1 user data */
} __attribute__((packed));
-
-struct lov_user_mds_data_v3 {
- lstat_t lmd_st; /* MDS stat struct */
- struct lov_user_md_v3 lmd_lmm; /* LOV EA V3 user data */
-} __attribute__((packed));
#endif
struct lmv_user_mds_data {
#endif /* !__KERNEL__ */
/* lustre volatile file support
- * file name header: .^L^S^T^R:volatile"
+ * file name header: ".^L^S^T^R:volatile"
*/
#define LUSTRE_VOLATILE_HDR ".\x0c\x13\x14\x12:VOLATILE"
#define LUSTRE_VOLATILE_HDR_LEN 14
-typedef enum lustre_quota_version {
+enum lustre_quota_version {
LUSTRE_QUOTA_V2 = 1
-} lustre_quota_version_t;
+};
/* XXX: same as if_dqinfo struct in kernel */
struct obd_dqinfo {
__u64 sl_dv2;
};
+/** Bit-mask of valid attributes */
+/* The LA_* flags are written to disk as part of the ChangeLog records
+ * so they are part of the on-disk and network protocol, and cannot be changed.
+ * Only the first 12 bits are currently saved.
+ */
+enum la_valid {
+ LA_ATIME = 1 << 0,
+ LA_MTIME = 1 << 1,
+ LA_CTIME = 1 << 2,
+ LA_SIZE = 1 << 3,
+ LA_MODE = 1 << 4,
+ LA_UID = 1 << 5,
+ LA_GID = 1 << 6,
+ LA_BLOCKS = 1 << 7,
+ LA_TYPE = 1 << 8,
+ LA_FLAGS = 1 << 9,
+ LA_NLINK = 1 << 10,
+ LA_RDEV = 1 << 11,
+ LA_BLKSIZE = 1 << 12,
+ LA_KILL_SUID = 1 << 13,
+ LA_KILL_SGID = 1 << 14,
+ LA_PROJID = 1 << 15,
+ LA_LAYOUT_VERSION = 1 << 16,
+ /**
+ * Attributes must be transmitted to OST objects
+ */
+ LA_REMOTE_ATTR_SET = (LA_UID | LA_GID | LA_PROJID | LA_LAYOUT_VERSION)
+};
+
+#define MDS_FMODE_READ 00000001
+#define MDS_FMODE_WRITE 00000002
+
+#define MDS_FMODE_CLOSED 00000000
+#define MDS_FMODE_EXEC 00000004
+/* 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
+
+#define MDS_OPEN_CREAT 00000100
+#define MDS_OPEN_EXCL 00000200
+#define MDS_OPEN_TRUNC 00001000
+#define MDS_OPEN_APPEND 00002000
+#define MDS_OPEN_SYNC 00010000
+#define MDS_OPEN_DIRECTORY 00200000
+
+#define MDS_OPEN_BY_FID 040000000 /* open_by_fid for known object */
+#define MDS_OPEN_DELAY_CREATE 0100000000 /* delay initial object create */
+#define MDS_OPEN_OWNEROVERRIDE 0200000000 /* NFSD rw-reopen ro file for owner */
+#define MDS_OPEN_JOIN_FILE 0400000000 /* open for join file.
+ * We do not support JOIN FILE
+ * anymore, reserve this flags
+ * just for preventing such bit
+ * to be reused. */
+
+#define MDS_OPEN_LOCK 04000000000 /* This open requires open lock */
+#define MDS_OPEN_HAS_EA 010000000000 /* specify object create pattern */
+#define MDS_OPEN_HAS_OBJS 020000000000 /* Just set the EA the obj exist */
+#define MDS_OPEN_NORESTORE 0100000000000ULL /* Do not restore file at open */
+#define MDS_OPEN_NEWSTRIPE 0200000000000ULL /* New stripe needed (restripe or
+ * 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 */
+
+#define MDS_OPEN_RESYNC 04000000000000ULL /* FLR: file resync */
+
+/* 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 | MDS_OPEN_RESYNC)
+
/********* Changelogs **********/
/** Changelog record types */
CL_LAYOUT = 12, /* file layout/striping modified */
CL_TRUNC = 13,
CL_SETATTR = 14,
- CL_XATTR = 15,
+ CL_SETXATTR = 15,
+ CL_XATTR = CL_SETXATTR, /* Deprecated name */
CL_HSM = 16, /* HSM specific events, see flags */
CL_MTIME = 17, /* Precedence: setattr > mtime > ctime > atime */
CL_CTIME = 18,
CL_ATIME = 19,
CL_MIGRATE = 20,
+ CL_FLRW = 21, /* FLR: file was firstly written */
+ CL_RESYNC = 22, /* FLR: file was resync-ed */
+ CL_GETXATTR = 23,
+ CL_DN_OPEN = 24, /* denied open */
CL_LAST
};
static const char *changelog_str[] = {
"MARK", "CREAT", "MKDIR", "HLINK", "SLINK", "MKNOD", "UNLNK",
"RMDIR", "RENME", "RNMTO", "OPEN", "CLOSE", "LYOUT", "TRUNC",
- "SATTR", "XATTR", "HSM", "MTIME", "CTIME", "ATIME", "MIGRT"
+ "SATTR", "XATTR", "HSM", "MTIME", "CTIME", "ATIME", "MIGRT",
+ "FLRW", "RESYNC","GXATR", "NOPEN",
};
if (type >= 0 && type < CL_LAST)
CLF_VERSION = 0x1000,
CLF_RENAME = 0x2000,
CLF_JOBID = 0x4000,
- CLF_SUPPORTED = CLF_VERSION | CLF_RENAME | CLF_JOBID
+ CLF_EXTRA_FLAGS = 0x8000,
+ CLF_SUPPORTED = CLF_VERSION | CLF_RENAME | CLF_JOBID | CLF_EXTRA_FLAGS
};
*flags |= (error << CLF_HSM_ERR_L);
}
+enum changelog_rec_extra_flags {
+ CLFE_INVALID = 0,
+ CLFE_UIDGID = 0x0001,
+ CLFE_NID = 0x0002,
+ CLFE_OPEN = 0x0004,
+ CLFE_XATTR = 0x0008,
+ CLFE_SUPPORTED = CLFE_UIDGID | CLFE_NID | CLFE_OPEN | CLFE_XATTR
+};
+
enum changelog_send_flag {
/* Not yet implemented */
- CHANGELOG_FLAG_FOLLOW = 0x01,
+ CHANGELOG_FLAG_FOLLOW = 0x01,
/* Blocking IO makes sense in case of slow user parsing of the records,
* but it also prevents us from cleaning up if the records are not
* consumed. */
- CHANGELOG_FLAG_BLOCK = 0x02,
+ CHANGELOG_FLAG_BLOCK = 0x02,
/* Pack jobid into the changelog records if available. */
- CHANGELOG_FLAG_JOBID = 0x04,
+ CHANGELOG_FLAG_JOBID = 0x04,
+ /* Pack additional flag bits into the changelog record */
+ CHANGELOG_FLAG_EXTRA_FLAGS = 0x08,
};
-#define CR_MAXSIZE cfs_size_round(2 * NAME_MAX + 2 + \
- changelog_rec_offset(CLF_SUPPORTED))
+enum changelog_send_extra_flag {
+ /* Pack uid/gid into the changelog record */
+ CHANGELOG_EXTRA_FLAG_UIDGID = 0x01,
+ /* Pack nid into the changelog record */
+ CHANGELOG_EXTRA_FLAG_NID = 0x02,
+ /* Pack open mode into the changelog record */
+ CHANGELOG_EXTRA_FLAG_OMODE = 0x04,
+ /* Pack xattr name into the changelog record */
+ CHANGELOG_EXTRA_FLAG_XATTR = 0x08,
+};
+
+#define CR_MAXSIZE __ALIGN_KERNEL(2 * NAME_MAX + 2 + \
+ changelog_rec_offset(CLF_SUPPORTED, \
+ CLFE_SUPPORTED), 8)
/* 31 usable bytes string + null terminator. */
#define LUSTRE_JOBID_SIZE 32
/* This is the minimal changelog record. It can contain extensions
* such as rename fields or process jobid. Its exact content is described
- * by the cr_flags.
+ * by the cr_flags and cr_extra_flags.
*
- * Extensions are packed in the same order as their corresponding flags.
+ * Extensions are packed in the same order as their corresponding flags,
+ * then in the same order as their corresponding extra flags.
*/
struct changelog_rec {
__u16 cr_namelen;
__u64 cr_prev; /**< last index for this target fid */
__u64 cr_time;
union {
- lustre_fid cr_tfid; /**< target fid */
+ struct lu_fid cr_tfid; /**< target fid */
__u32 cr_markerflags; /**< CL_MARK flags */
};
- lustre_fid cr_pfid; /**< parent fid */
+ struct lu_fid cr_pfid; /**< parent fid */
};
/* Changelog extension for RENAME. */
struct changelog_ext_rename {
- lustre_fid cr_sfid; /**< source fid, or zero */
- lustre_fid cr_spfid; /**< source parent fid, or zero */
+ struct lu_fid cr_sfid; /**< source fid, or zero */
+ struct lu_fid cr_spfid; /**< source parent fid, or zero */
};
/* Changelog extension to include JOBID. */
char cr_jobid[LUSTRE_JOBID_SIZE]; /**< zero-terminated string. */
};
+/* Changelog extension to include additional flags. */
+struct changelog_ext_extra_flags {
+ __u64 cr_extra_flags; /* Additional CLFE_* flags */
+};
+
+/* Changelog extra extension to include UID/GID. */
+struct changelog_ext_uidgid {
+ __u64 cr_uid;
+ __u64 cr_gid;
+};
+
+/* Changelog extra extension to include NID. */
+struct changelog_ext_nid {
+ /* have __u64 instead of lnet_nid_t type for use by client api */
+ __u64 cr_nid;
+ /* for use when IPv6 support is added */
+ __u64 extra;
+ __u32 padding;
+};
+
+/* Changelog extra extension to include OPEN mode. */
+struct changelog_ext_openmode {
+ __u32 cr_openflags;
+};
+
+/* Changelog extra extension to include xattr */
+struct changelog_ext_xattr {
+ char cr_xattr[XATTR_NAME_MAX + 1]; /**< zero-terminated string. */
+};
+
+static inline struct changelog_ext_extra_flags *changelog_rec_extra_flags(
+ const struct changelog_rec *rec);
-static inline size_t changelog_rec_offset(enum changelog_rec_flags crf)
+static inline size_t changelog_rec_offset(enum changelog_rec_flags crf,
+ enum changelog_rec_extra_flags cref)
{
size_t size = sizeof(struct changelog_rec);
if (crf & CLF_JOBID)
size += sizeof(struct changelog_ext_jobid);
+ if (crf & CLF_EXTRA_FLAGS) {
+ size += sizeof(struct changelog_ext_extra_flags);
+ if (cref & CLFE_UIDGID)
+ size += sizeof(struct changelog_ext_uidgid);
+ if (cref & CLFE_NID)
+ size += sizeof(struct changelog_ext_nid);
+ if (cref & CLFE_OPEN)
+ size += sizeof(struct changelog_ext_openmode);
+ if (cref & CLFE_XATTR)
+ size += sizeof(struct changelog_ext_xattr);
+ }
+
return size;
}
static inline size_t changelog_rec_size(const struct changelog_rec *rec)
{
- return changelog_rec_offset(rec->cr_flags);
+ enum changelog_rec_extra_flags cref = CLFE_INVALID;
+
+ if (rec->cr_flags & CLF_EXTRA_FLAGS)
+ cref = changelog_rec_extra_flags(rec)->cr_extra_flags;
+
+ return changelog_rec_offset(rec->cr_flags, cref);
}
static inline size_t changelog_rec_varsize(const struct changelog_rec *rec)
enum changelog_rec_flags crf = rec->cr_flags & CLF_VERSION;
return (struct changelog_ext_rename *)((char *)rec +
- changelog_rec_offset(crf));
+ changelog_rec_offset(crf,
+ CLFE_INVALID));
}
/* The jobid follows the rename extension, if present */
(CLF_VERSION | CLF_RENAME);
return (struct changelog_ext_jobid *)((char *)rec +
- changelog_rec_offset(crf));
+ changelog_rec_offset(crf,
+ CLFE_INVALID));
}
-/* The name follows the rename and jobid extensions, if present */
+/* The additional flags follow the rename and jobid extensions, if present */
+static inline
+struct changelog_ext_extra_flags *changelog_rec_extra_flags(
+ const struct changelog_rec *rec)
+{
+ enum changelog_rec_flags crf = rec->cr_flags &
+ (CLF_VERSION | CLF_RENAME | CLF_JOBID);
+
+ return (struct changelog_ext_extra_flags *)((char *)rec +
+ changelog_rec_offset(crf,
+ CLFE_INVALID));
+}
+
+/* The uid/gid is the first extra extension */
+static inline
+struct changelog_ext_uidgid *changelog_rec_uidgid(
+ const struct changelog_rec *rec)
+{
+ enum changelog_rec_flags crf = rec->cr_flags &
+ (CLF_VERSION | CLF_RENAME | CLF_JOBID | CLF_EXTRA_FLAGS);
+
+ return (struct changelog_ext_uidgid *)((char *)rec +
+ changelog_rec_offset(crf,
+ CLFE_INVALID));
+}
+
+/* The nid is the second extra extension */
+static inline
+struct changelog_ext_nid *changelog_rec_nid(const struct changelog_rec *rec)
+{
+ enum changelog_rec_flags crf = rec->cr_flags &
+ (CLF_VERSION | CLF_RENAME | CLF_JOBID | CLF_EXTRA_FLAGS);
+ enum changelog_rec_extra_flags cref = CLFE_INVALID;
+
+ if (rec->cr_flags & CLF_EXTRA_FLAGS)
+ cref = changelog_rec_extra_flags(rec)->cr_extra_flags &
+ CLFE_UIDGID;
+
+ return (struct changelog_ext_nid *)((char *)rec +
+ changelog_rec_offset(crf, cref));
+}
+
+/* The OPEN mode is the third extra extension */
+static inline
+struct changelog_ext_openmode *changelog_rec_openmode(
+ const struct changelog_rec *rec)
+{
+ enum changelog_rec_flags crf = rec->cr_flags &
+ (CLF_VERSION | CLF_RENAME | CLF_JOBID | CLF_EXTRA_FLAGS);
+ enum changelog_rec_extra_flags cref = CLFE_INVALID;
+
+ if (rec->cr_flags & CLF_EXTRA_FLAGS)
+ cref = changelog_rec_extra_flags(rec)->cr_extra_flags &
+ (CLFE_UIDGID | CLFE_NID);
+
+ return (struct changelog_ext_openmode *)((char *)rec +
+ changelog_rec_offset(crf, cref));
+}
+
+/* The xattr name is the fourth extra extension */
+static inline
+struct changelog_ext_xattr *changelog_rec_xattr(
+ const struct changelog_rec *rec)
+{
+ enum changelog_rec_flags crf = rec->cr_flags &
+ (CLF_VERSION | CLF_RENAME | CLF_JOBID | CLF_EXTRA_FLAGS);
+ enum changelog_rec_extra_flags cref = CLFE_INVALID;
+
+ if (rec->cr_flags & CLF_EXTRA_FLAGS)
+ cref = changelog_rec_extra_flags(rec)->cr_extra_flags &
+ (CLFE_UIDGID | CLFE_NID | CLFE_OPEN);
+
+ return (struct changelog_ext_xattr *)((char *)rec +
+ changelog_rec_offset(crf, cref));
+}
+
+/* The name follows the rename, jobid and extra flags extns, if present */
static inline char *changelog_rec_name(const struct changelog_rec *rec)
{
- return (char *)rec + changelog_rec_offset(rec->cr_flags &
- CLF_SUPPORTED);
+ enum changelog_rec_extra_flags cref = CLFE_INVALID;
+
+ if (rec->cr_flags & CLF_EXTRA_FLAGS)
+ cref = changelog_rec_extra_flags(rec)->cr_extra_flags;
+
+ return (char *)rec + changelog_rec_offset(rec->cr_flags & CLF_SUPPORTED,
+ cref & CLFE_SUPPORTED);
}
static inline size_t changelog_rec_snamelen(const struct changelog_rec *rec)
* The following assumptions are being made:
* - CLF_RENAME will not be removed
* - CLF_JOBID will not be added without CLF_RENAME being added too
+ * - CLF_EXTRA_FLAGS will not be added without CLF_JOBID being added too
*
* @param[in,out] rec The record to remap.
* @param[in] crf_wanted Flags describing the desired extensions.
+ * @param[in] cref_want Flags describing the desired extra extensions.
*/
static inline void changelog_remap_rec(struct changelog_rec *rec,
- enum changelog_rec_flags crf_wanted)
+ enum changelog_rec_flags crf_wanted,
+ enum changelog_rec_extra_flags cref_want)
{
+ char *xattr_mov = NULL;
+ char *omd_mov = NULL;
+ char *nid_mov = NULL;
+ char *uidgid_mov = NULL;
+ char *ef_mov;
char *jid_mov;
char *rnm_mov;
+ enum changelog_rec_extra_flags cref = CLFE_INVALID;
crf_wanted &= CLF_SUPPORTED;
-
- if ((rec->cr_flags & CLF_SUPPORTED) == crf_wanted)
- return;
+ cref_want &= CLFE_SUPPORTED;
+
+ if ((rec->cr_flags & CLF_SUPPORTED) == crf_wanted) {
+ if (!(rec->cr_flags & CLF_EXTRA_FLAGS) ||
+ (rec->cr_flags & CLF_EXTRA_FLAGS &&
+ (changelog_rec_extra_flags(rec)->cr_extra_flags &
+ CLFE_SUPPORTED) ==
+ cref_want))
+ return;
+ }
/* First move the variable-length name field */
- memmove((char *)rec + changelog_rec_offset(crf_wanted),
+ memmove((char *)rec + changelog_rec_offset(crf_wanted, cref_want),
changelog_rec_name(rec), rec->cr_namelen);
- /* Locations of jobid and rename extensions in the remapped record */
+ /* Locations of extensions in the remapped record */
+ if (rec->cr_flags & CLF_EXTRA_FLAGS) {
+ xattr_mov = (char *)rec +
+ changelog_rec_offset(crf_wanted & CLF_SUPPORTED,
+ cref_want & ~CLFE_XATTR);
+ omd_mov = (char *)rec +
+ changelog_rec_offset(crf_wanted & CLF_SUPPORTED,
+ cref_want & ~(CLFE_OPEN |
+ CLFE_XATTR));
+ nid_mov = (char *)rec +
+ changelog_rec_offset(crf_wanted & CLF_SUPPORTED,
+ cref_want & ~(CLFE_NID |
+ CLFE_OPEN |
+ CLFE_XATTR));
+ uidgid_mov = (char *)rec +
+ changelog_rec_offset(crf_wanted & CLF_SUPPORTED,
+ cref_want & ~(CLFE_UIDGID |
+ CLFE_NID |
+ CLFE_OPEN |
+ CLFE_XATTR));
+ cref = changelog_rec_extra_flags(rec)->cr_extra_flags;
+ }
+
+ ef_mov = (char *)rec +
+ changelog_rec_offset(crf_wanted & ~CLF_EXTRA_FLAGS,
+ CLFE_INVALID);
jid_mov = (char *)rec +
- changelog_rec_offset(crf_wanted & ~CLF_JOBID);
+ changelog_rec_offset(crf_wanted &
+ ~(CLF_EXTRA_FLAGS | CLF_JOBID),
+ CLFE_INVALID);
rnm_mov = (char *)rec +
- changelog_rec_offset(crf_wanted & ~(CLF_JOBID | CLF_RENAME));
+ changelog_rec_offset(crf_wanted &
+ ~(CLF_EXTRA_FLAGS |
+ CLF_JOBID |
+ CLF_RENAME),
+ CLFE_INVALID);
/* Move the extension fields to the desired positions */
+ if ((crf_wanted & CLF_EXTRA_FLAGS) &&
+ (rec->cr_flags & CLF_EXTRA_FLAGS)) {
+ if ((cref_want & CLFE_XATTR) && (cref & CLFE_XATTR))
+ memmove(xattr_mov, changelog_rec_xattr(rec),
+ sizeof(struct changelog_ext_xattr));
+
+ if ((cref_want & CLFE_OPEN) && (cref & CLFE_OPEN))
+ memmove(omd_mov, changelog_rec_openmode(rec),
+ sizeof(struct changelog_ext_openmode));
+
+ if ((cref_want & CLFE_NID) && (cref & CLFE_NID))
+ memmove(nid_mov, changelog_rec_nid(rec),
+ sizeof(struct changelog_ext_nid));
+
+ if ((cref_want & CLFE_UIDGID) && (cref & CLFE_UIDGID))
+ memmove(uidgid_mov, changelog_rec_uidgid(rec),
+ sizeof(struct changelog_ext_uidgid));
+
+ memmove(ef_mov, changelog_rec_extra_flags(rec),
+ sizeof(struct changelog_ext_extra_flags));
+ }
+
if ((crf_wanted & CLF_JOBID) && (rec->cr_flags & CLF_JOBID))
memmove(jid_mov, changelog_rec_jobid(rec),
sizeof(struct changelog_ext_jobid));
sizeof(struct changelog_ext_rename));
/* Clear newly added fields */
+ if (xattr_mov && (cref_want & CLFE_XATTR) &&
+ !(cref & CLFE_XATTR))
+ memset(xattr_mov, 0, sizeof(struct changelog_ext_xattr));
+
+ if (omd_mov && (cref_want & CLFE_OPEN) &&
+ !(cref & CLFE_OPEN))
+ memset(omd_mov, 0, sizeof(struct changelog_ext_openmode));
+
+ if (nid_mov && (cref_want & CLFE_NID) &&
+ !(cref & CLFE_NID))
+ memset(nid_mov, 0, sizeof(struct changelog_ext_nid));
+
+ if (uidgid_mov && (cref_want & CLFE_UIDGID) &&
+ !(cref & CLFE_UIDGID))
+ memset(uidgid_mov, 0, sizeof(struct changelog_ext_uidgid));
+
+ if ((crf_wanted & CLF_EXTRA_FLAGS) &&
+ !(rec->cr_flags & CLF_EXTRA_FLAGS))
+ memset(ef_mov, 0, sizeof(struct changelog_ext_extra_flags));
+
if ((crf_wanted & CLF_JOBID) && !(rec->cr_flags & CLF_JOBID))
memset(jid_mov, 0, sizeof(struct changelog_ext_jobid));
/* Update the record's flags accordingly */
rec->cr_flags = (rec->cr_flags & CLF_FLAGMASK) | crf_wanted;
+ if (rec->cr_flags & CLF_EXTRA_FLAGS)
+ changelog_rec_extra_flags(rec)->cr_extra_flags =
+ changelog_rec_extra_flags(rec)->cr_extra_flags |
+ cref_want;
}
enum changelog_message_type {
/********* Misc **********/
struct ioc_data_version {
- __u64 idv_version;
- __u64 idv_flags; /* See LL_DV_xxx */
+ __u64 idv_version;
+ __u32 idv_layout_version; /* FLR: layout version for OST objects */
+ __u32 idv_flags; /* enum ioc_data_version_flags */
+};
+
+enum ioc_data_version_flags {
+ LL_DV_RD_FLUSH = (1 << 0), /* Flush dirty pages from clients */
+ LL_DV_WR_FLUSH = (1 << 1), /* Flush all caching pages from clients */
};
-#define LL_DV_RD_FLUSH (1 << 0) /* Flush dirty pages from clients */
-#define LL_DV_WR_FLUSH (1 << 1) /* Flush all caching pages from clients */
#ifndef offsetof
#define offsetof(typ, memb) ((unsigned long)((char *)&(((typ *)0)->memb)))
};
struct hsm_user_item {
- lustre_fid hui_fid;
+ struct lu_fid hui_fid;
struct hsm_extent hui_extent;
} __attribute__((packed));
struct hsm_action_item {
__u32 hai_len; /* valid size of this struct */
__u32 hai_action; /* hsm_copytool_action, but use known size */
- lustre_fid hai_fid; /* Lustre FID to operate on */
- lustre_fid hai_dfid; /* fid used for data access */
+ struct lu_fid hai_fid; /* Lustre FID to operate on */
+ struct lu_fid hai_dfid; /* fid used for data access */
struct hsm_extent hai_extent; /* byte range to operate on */
__u64 hai_cookie; /* action cookie from coordinator */
__u64 hai_gid; /* grouplock id */
boundaries. See hai_zero */
} __attribute__((packed));
-#ifndef HAVE_CFS_SIZE_ROUND
-static inline int cfs_size_round (int val)
-{
- return (val + 7) & (~0x7);
-}
-#define HAVE_CFS_SIZE_ROUND
-#endif
-
/* Return pointer to first hai in action list */
static inline struct hsm_action_item *hai_first(struct hsm_action_list *hal)
{
- return (struct hsm_action_item *)(hal->hal_fsname +
- cfs_size_round(strlen(hal-> \
- hal_fsname)
- + 1));
+ size_t offset = __ALIGN_KERNEL(strlen(hal->hal_fsname) + 1, 8);
+
+ return (struct hsm_action_item *)(hal->hal_fsname + offset);
}
+
/* Return pointer to next hai */
static inline struct hsm_action_item * hai_next(struct hsm_action_item *hai)
{
- return (struct hsm_action_item *)((char *)hai +
- cfs_size_round(hai->hai_len));
+ size_t offset = __ALIGN_KERNEL(hai->hai_len, 8);
+
+ return (struct hsm_action_item *)((char *)hai + offset);
}
/* Return size of an hsm_action_list */
size_t sz;
struct hsm_action_item *hai;
- sz = sizeof(*hal) + cfs_size_round(strlen(hal->hal_fsname) + 1);
+ sz = sizeof(*hal) + __ALIGN_KERNEL(strlen(hal->hal_fsname) + 1, 8);
hai = hai_first(hal);
for (i = 0; i < hal->hal_count ; i++, hai = hai_next(hai))
- sz += cfs_size_round(hai->hai_len);
+ sz += __ALIGN_KERNEL(hai->hai_len, 8);
return sz;
}
#define HP_FLAG_RETRY 0x02
struct hsm_progress {
- lustre_fid hp_fid;
+ struct lu_fid hp_fid;
__u64 hp_cookie;
struct hsm_extent hp_extent;
__u16 hp_flags;
LU_LADVISE_INVALID = 0,
LU_LADVISE_WILLREAD = 1,
LU_LADVISE_DONTNEED = 2,
+ LU_LADVISE_LOCKNOEXPAND = 3,
+ LU_LADVISE_LOCKAHEAD = 4,
+ LU_LADVISE_MAX
};
#define LU_LADVISE_NAMES { \
- [LU_LADVISE_WILLREAD] = "willread", \
- [LU_LADVISE_DONTNEED] = "dontneed", \
+ [LU_LADVISE_WILLREAD] = "willread", \
+ [LU_LADVISE_DONTNEED] = "dontneed", \
+ [LU_LADVISE_LOCKNOEXPAND] = "locknoexpand", \
+ [LU_LADVISE_LOCKAHEAD] = "lockahead", \
}
/* This is the userspace argument for ladvise. It is currently the same as
enum ladvise_flag {
LF_ASYNC = 0x00000001,
+ LF_UNSET = 0x00000002,
};
#define LADVISE_MAGIC 0x1ADF1CE0
-#define LF_MASK LF_ASYNC
+/* Masks of valid flags for each advice */
+#define LF_LOCKNOEXPAND_MASK LF_UNSET
+/* Flags valid for all advices not explicitly specified */
+#define LF_DEFAULT_MASK LF_ASYNC
+/* All flags */
+#define LF_MASK (LF_ASYNC | LF_UNSET)
+
+#define lla_lockahead_mode lla_value1
+#define lla_peradvice_flags lla_value2
+#define lla_lockahead_result lla_value3
/* This is the userspace argument for ladvise, corresponds to ladvise_hdr which
* is used on the wire. It is defined separately as we may need info which is
size_t sht_bytes;
};
+enum lock_mode_user {
+ MODE_READ_USER = 1,
+ MODE_WRITE_USER,
+ MODE_MAX_USER,
+};
+
+#define LOCK_MODE_NAMES { \
+ [MODE_READ_USER] = "READ",\
+ [MODE_WRITE_USER] = "WRITE"\
+}
+
+enum lockahead_results {
+ LLA_RESULT_SENT = 0,
+ LLA_RESULT_DIFFERENT,
+ LLA_RESULT_SAME,
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
/** @} lustreuser */
+
#endif /* _LUSTRE_USER_H */
git://git.whamcloud.com / fs / lustre-release.git / blobdiff