* Copyright (c) 2003, 2010, Oracle and/or its affiliates. All rights reserved.
* Use is subject to license terms.
*
- * Copyright (c) 2010, 2012, Intel Corporation.
+ * Copyright (c) 2010, 2014, Intel Corporation.
*/
/*
* This file is part of Lustre, http://www.lustre.org/
* @{
*/
-#ifndef __KERNEL__
-#include <libcfs/posix/posix-types.h>
-#endif
+#include <libcfs/types.h>
+
+#ifdef __KERNEL__
+# include <linux/quota.h>
+# include <linux/string.h> /* snprintf() */
+# include <linux/version.h>
+#else /* !__KERNEL__ */
+# define NEED_QUOTA_DEFS
+# include <stdio.h> /* snprintf() */
+# include <string.h>
+# include <sys/quota.h>
+# include <sys/stat.h>
+#endif /* __KERNEL__ */
#include <lustre/ll_fiemap.h>
-#if defined(__linux__)
-#include <linux/lustre_user.h>
-#elif defined(__APPLE__)
-#include <darwin/lustre_user.h>
-#elif defined(__WINNT__)
-#include <winnt/lustre_user.h>
-#else
-#error Unsupported operating system.
+
+#if defined(__x86_64__) || defined(__ia64__) || defined(__ppc64__) || \
+ defined(__craynv) || defined(__mips64__) || defined(__powerpc64__)
+typedef struct stat lstat_t;
+# define lstat_f lstat
+# define HAVE_LOV_USER_MDS_DATA
+#elif defined(__USE_LARGEFILE64) || defined(__KERNEL__)
+typedef struct stat64 lstat_t;
+# define lstat_f lstat64
+# define HAVE_LOV_USER_MDS_DATA
#endif
+#define LUSTRE_EOF 0xffffffffffffffffULL
+
/* for statfs() */
#define LL_SUPER_MAGIC 0x0BD00BD0
};
/**
- * OST object IDentifier.
- */
-struct ost_id {
- __u64 oi_id;
- __u64 oi_seq;
-};
-
-#define DOSTID LPX64":"LPU64
-#define POSTID(oi) (oi)->oi_seq, (oi)->oi_id
-
-/**
* File IDentifier.
*
* FID is a cluster-wide unique identifier of a file or an object (stripe).
__u32 f_ver;
};
+static inline bool fid_is_zero(const struct lu_fid *fid)
+{
+ return fid->f_seq == 0 && fid->f_oid == 0;
+}
+
+/* Currently, the filter_fid::ff_parent::f_ver is not the real parent
+ * MDT-object's FID::f_ver, instead it is the OST-object index in its
+ * parent MDT-object's layout EA. */
+#define f_stripe_idx f_ver
+
struct filter_fid {
struct lu_fid ff_parent; /* ff_parent.f_ver == file stripe number */
};
*/
#define LMA_OLD_SIZE (sizeof(struct lustre_mdt_attrs) + 5 * sizeof(__u64))
+/**
+ * OST object IDentifier.
+ */
+struct ost_id {
+ union {
+ struct {
+ __u64 oi_id;
+ __u64 oi_seq;
+ } oi;
+ struct lu_fid oi_fid;
+ };
+};
+
+#define DOSTID LPX64":"LPU64
+#define POSTID(oi) ostid_seq(oi), ostid_id(oi)
+
/*
* The ioctl naming rules:
* LL_* - works on the currently opened filehandle instead of parent dir
* *STRIPE* - set/get lov_user_md
* *INFO - set/get lov_user_mds_data
*/
-/* see <lustre_lib.h> for ioctl numberss 101-150 */
+/* lustre_ioctl.h 101-150 */
#define LL_IOC_GETFLAGS _IOR ('f', 151, long)
#define LL_IOC_SETFLAGS _IOW ('f', 152, long)
#define LL_IOC_CLRFLAGS _IOW ('f', 153, long)
-/* LL_IOC_LOV_SETSTRIPE: See also OBD_IOC_LOV_SETSTRIPE */
#define LL_IOC_LOV_SETSTRIPE _IOW ('f', 154, long)
-/* LL_IOC_LOV_GETSTRIPE: See also OBD_IOC_LOV_GETSTRIPE */
#define LL_IOC_LOV_GETSTRIPE _IOW ('f', 155, long)
-/* LL_IOC_LOV_SETEA: See also OBD_IOC_LOV_SETEA */
#define LL_IOC_LOV_SETEA _IOW ('f', 156, long)
-#define LL_IOC_RECREATE_OBJ _IOW ('f', 157, long)
-#define LL_IOC_RECREATE_FID _IOW ('f', 157, struct lu_fid)
+/* LL_IOC_RECREATE_OBJ 157 obsolete */
+/* LL_IOC_RECREATE_FID 157 obsolete */
#define LL_IOC_GROUP_LOCK _IOW ('f', 158, long)
#define LL_IOC_GROUP_UNLOCK _IOW ('f', 159, long)
-/* LL_IOC_QUOTACHECK: See also OBD_IOC_QUOTACHECK */
-#define LL_IOC_QUOTACHECK _IOW ('f', 160, int)
-/* LL_IOC_POLL_QUOTACHECK: See also OBD_IOC_POLL_QUOTACHECK */
-#define LL_IOC_POLL_QUOTACHECK _IOR ('f', 161, struct if_quotacheck *)
-/* LL_IOC_QUOTACTL: See also OBD_IOC_QUOTACTL */
-#define LL_IOC_QUOTACTL _IOWR('f', 162, struct if_quotactl)
+/* LL_IOC_QUOTACHECK 160 OBD_IOC_QUOTACHECK */
+/* LL_IOC_POLL_QUOTACHECK 161 OBD_IOC_POLL_QUOTACHECK */
+/* LL_IOC_QUOTACTL 162 OBD_IOC_QUOTACTL */
#define IOC_OBD_STATFS _IOWR('f', 164, struct obd_statfs *)
#define IOC_LOV_GETINFO _IOWR('f', 165, struct lov_user_mds_data *)
#define LL_IOC_FLUSHCTX _IOW ('f', 166, long)
#define LL_IOC_PATH2FID _IOR ('f', 173, long)
#define LL_IOC_GET_CONNECT_FLAGS _IOWR('f', 174, __u64 *)
#define LL_IOC_GET_MDTIDX _IOR ('f', 175, int)
-
-/* see <lustre_lib.h> for ioctl numbers 177-210 */
-
+/* 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_HSM_CT_START _IOW('f', 213, struct lustre_kernelcomm)
struct lustre_swap_layouts)
#define LL_IOC_HSM_ACTION _IOR('f', 220, \
struct hsm_current_action)
-/* see <lustre_lib.h> for ioctl numbers 221-232 */
-
-#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)
+/* lustre_ioctl.h 221-232 */
+#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_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)
+#define LL_IOC_MIGRATE _IOR('f', 247, int)
+#define LL_IOC_FID2MDTIDX _IOWR('f', 248, struct lu_fid)
+#define LL_IOC_GETPARENT _IOWR('f', 249, struct getparent)
+
+/* 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_LMV 1
+#define LL_STATFS_LOV 2
#define LL_STATFS_NODELAY 4
#define IOC_MDC_TYPE 'i'
#define IOC_MDC_GETFILEINFO _IOWR(IOC_MDC_TYPE, 22, struct lov_user_mds_data *)
#define LL_IOC_MDC_GETINFO _IOWR(IOC_MDC_TYPE, 23, struct lov_user_mds_data *)
-/* Keep these for backward compartability. */
-#define LL_IOC_OBD_STATFS IOC_OBD_STATFS
-#define IOC_MDC_GETSTRIPE IOC_MDC_GETFILESTRIPE
-
-
#define MAX_OBD_NAME 128 /* If this changes, a NEW ioctl must be added */
-/* Hopefully O_LOV_DELAY_CREATE does not conflict with standard O_xxx flags.
- * Previously it was defined as 0100000000 and conflicts with FMODE_NONOTIFY
- * which was added since kernel 2.6.36, so we redefine it as 020000000.
- * To be compatible with old version's statically linked binary, finally we
- * define it as (020000000 | 0100000000).
- * */
-#define O_LOV_DELAY_CREATE 0120000000
+/* Define O_LOV_DELAY_CREATE to be a mask that is not useful for regular
+ * files, but are unlikely to be used in practice and are not harmful if
+ * used incorrectly. O_NOCTTY and FASYNC are only meaningful for character
+ * devices and are safe for use on new files. See LU-4209. */
+/* To be compatible with old statically linked binary we keep the check for
+ * the older 0100000000 flag. This is already removed upstream. LU-812. */
+#define O_LOV_DELAY_CREATE_1_8 0100000000 /* FMODE_NONOTIFY masked in 2.6.36 */
+#define O_LOV_DELAY_CREATE_MASK (O_NOCTTY | FASYNC)
+#define O_LOV_DELAY_CREATE (O_LOV_DELAY_CREATE_1_8 | \
+ O_LOV_DELAY_CREATE_MASK)
#define LL_FILE_IGNORE_LOCK 0x00000001
#define LL_FILE_GROUP_LOCKED 0x00000002
#define LL_FILE_LOCKLESS_IO 0x00000010 /* server-side locks with cio */
#define LL_FILE_RMTACL 0x00000020
-#define LOV_USER_MAGIC_V1 0x0BD10BD0
-#define LOV_USER_MAGIC LOV_USER_MAGIC_V1
-#define LOV_USER_MAGIC_JOIN_V1 0x0BD20BD0
-#define LOV_USER_MAGIC_V3 0x0BD30BD0
+#define LOV_USER_MAGIC_V1 0x0BD10BD0
+#define LOV_USER_MAGIC LOV_USER_MAGIC_V1
+#define LOV_USER_MAGIC_JOIN_V1 0x0BD20BD0
+#define LOV_USER_MAGIC_V3 0x0BD30BD0
+/* 0x0BD40BD0 is occupied by LOV_MAGIC_MIGRATE */
+#define LOV_USER_MAGIC_SPECIFIC 0x0BD50BD0 /* for specific OSTs */
-#define LMV_MAGIC_V1 0x0CD10CD0 /*normal stripe lmv magic */
-#define LMV_USER_MAGIC 0x0CD20CD0 /*default lmv magic*/
+#define LMV_USER_MAGIC 0x0CD30CD0 /*default lmv magic*/
-#define LOV_PATTERN_RAID0 0x001
-#define LOV_PATTERN_RAID1 0x002
-#define LOV_PATTERN_FIRST 0x100
+#define LOV_PATTERN_RAID0 0x001
+#define LOV_PATTERN_RAID1 0x002
+#define LOV_PATTERN_FIRST 0x100
+#define LOV_PATTERN_CMOBD 0x200
-#define LOV_MAXPOOLNAME 16
-#define LOV_POOLNAMEF "%.16s"
+#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_MAXPOOLNAME 15
+#define LOV_POOLNAMEF "%.15s"
#define LOV_MIN_STRIPE_BITS 16 /* maximum PAGE_SIZE (ia64), power of 2 */
#define LOV_MIN_STRIPE_SIZE (1 << LOV_MIN_STRIPE_BITS)
#define LOV_ALL_STRIPES 0xffff /* only valid for directories */
#define LOV_V1_INSANE_STRIPE_COUNT 65532 /* maximum stripe count bz13933 */
+#define XATTR_LUSTRE_PREFIX "lustre."
+#define XATTR_LUSTRE_LOV XATTR_LUSTRE_PREFIX"lov"
+
#define lov_user_ost_data lov_user_ost_data_v1
struct lov_user_ost_data_v1 { /* per-stripe data structure */
struct ost_id l_ost_oi; /* OST object ID */
__u32 l_ost_gen; /* generation of this OST index */
__u32 l_ost_idx; /* OST index in LOV */
} __attribute__((packed));
-#define l_object_id l_ost_oi.oi_id
-#define l_object_seq l_ost_oi.oi_seq
#define lov_user_md lov_user_md_v1
struct lov_user_md_v1 { /* LOV EA user data (host-endian) */
__u16 lmm_layout_gen; /* layout generation number
* used when reading */
};
- char lmm_pool_name[LOV_MAXPOOLNAME]; /* pool name */
+ char lmm_pool_name[LOV_MAXPOOLNAME + 1]; /* pool name */
struct lov_user_ost_data_v1 lmm_objects[0]; /* per-stripe data */
} __attribute__((packed));
+static inline __u32 lov_user_md_size(__u16 stripes, __u32 lmm_magic)
+{
+ if (lmm_magic == LOV_USER_MAGIC_V1)
+ return sizeof(struct lov_user_md_v1) +
+ stripes * sizeof(struct lov_user_ost_data_v1);
+ return sizeof(struct lov_user_md_v3) +
+ stripes * sizeof(struct lov_user_ost_data_v1);
+}
+
/* Compile with -D_LARGEFILE64_SOURCE or -D_GNU_SOURCE (or #define) to
* use this. It is unsafe to #define those values in this header as it
* is possible the application has already #included <sys/stat.h>. */
} __attribute__((packed));
#endif
-/* keep this to be the same size as lov_user_ost_data_v1 */
struct lmv_user_mds_data {
struct lu_fid lum_fid;
__u32 lum_padding;
__u32 lum_mds;
};
-/* lum_type */
-enum {
- LMV_STRIPE_TYPE = 0,
- LMV_DEFAULT_TYPE = 1,
+enum lmv_hash_type {
+ LMV_HASH_TYPE_UNKNOWN = 0, /* 0 is reserved for testing purpose */
+ LMV_HASH_TYPE_ALL_CHARS = 1,
+ LMV_HASH_TYPE_FNV_1A_64 = 2,
};
+#define LMV_HASH_NAME_ALL_CHARS "all_char"
+#define LMV_HASH_NAME_FNV_1A_64 "fnv_1a_64"
+
+/* Got this according to how get LOV_MAX_STRIPE_COUNT, see above,
+ * (max buffer size - lmv+rpc header) / sizeof(struct lmv_user_mds_data) */
+#define LMV_MAX_STRIPE_COUNT 2000 /* ((12 * 4096 - 256) / 24) */
#define lmv_user_md lmv_user_md_v1
struct lmv_user_md_v1 {
__u32 lum_magic; /* must be the first field */
__u32 lum_padding1;
__u32 lum_padding2;
__u32 lum_padding3;
- char lum_pool_name[LOV_MAXPOOLNAME];
+ char lum_pool_name[LOV_MAXPOOLNAME + 1];
struct lmv_user_mds_data lum_objects[0];
-};
+} __attribute__((packed));
static inline int lmv_user_md_size(int stripes, int lmm_magic)
{
char uuid[UUID_MAX];
};
-static inline int obd_uuid_equals(const struct obd_uuid *u1,
- const struct obd_uuid *u2)
+static inline bool obd_uuid_equals(const struct obd_uuid *u1,
+ const struct obd_uuid *u2)
{
- return strcmp((char *)u1->uuid, (char *)u2->uuid) == 0;
+ return strcmp((char *)u1->uuid, (char *)u2->uuid) == 0;
}
static inline int obd_uuid_empty(struct obd_uuid *uuid)
}
/* For printf's only, make sure uuid is terminated */
-static inline char *obd_uuid2str(struct obd_uuid *uuid)
+static inline char *obd_uuid2str(const struct obd_uuid *uuid)
{
+ if (uuid == NULL)
+ return NULL;
+
if (uuid->uuid[sizeof(*uuid) - 1] != '\0') {
/* Obviously not safe, but for printfs, no real harm done...
we're always null-terminated, even in a race. */
strncpy(buf, uuid, buflen - 1);
buf[buflen - 1] = '\0';
p = strrchr(buf, '-');
- if (p)
- *p = '\0';
+ if (p != NULL)
+ *p = '\0';
}
/* printf display format
e.g. printf("file FID is "DFID"\n", PFID(fid)); */
+#define FID_NOBRACE_LEN 40
+#define FID_LEN (FID_NOBRACE_LEN + 2)
#define DFID_NOBRACE LPX64":0x%x:0x%x"
#define DFID "["DFID_NOBRACE"]"
#define PFID(fid) \
/********* Quotas **********/
+#define LUSTRE_QUOTABLOCK_BITS 10
+#define LUSTRE_QUOTABLOCK_SIZE (1 << LUSTRE_QUOTABLOCK_BITS)
+
+static inline __u64 lustre_stoqb(size_t space)
+{
+ return (space + LUSTRE_QUOTABLOCK_SIZE - 1) >> LUSTRE_QUOTABLOCK_BITS;
+}
+
+#define Q_QUOTACHECK 0x800100 /* deprecated as of 2.4 */
+#define Q_INITQUOTA 0x800101 /* deprecated as of 2.4 */
+#define Q_GETOINFO 0x800102 /* get obd quota info */
+#define Q_GETOQUOTA 0x800103 /* get obd quotas */
+#define Q_FINVALIDATE 0x800104 /* deprecated as of 2.4 */
+
/* these must be explicitly translated into linux Q_* in ll_dir_ioctl */
#define LUSTRE_Q_QUOTAON 0x800002 /* turn quotas on */
#define LUSTRE_Q_QUOTAOFF 0x800003 /* turn quotas off */
*/
#define LUSTRE_VOLATILE_HDR ".\x0c\x13\x14\x12:VOLATILE"
#define LUSTRE_VOLATILE_HDR_LEN 14
-/* hdr + MDT index */
-#define LUSTRE_VOLATILE_IDX LUSTRE_VOLATILE_HDR":%.4X:"
typedef enum lustre_quota_version {
LUSTRE_QUOTA_V2 = 1
};
/* swap layout flags */
-#define SWAP_LAYOUTS_CHECK_DV1 (1 << 0)
-#define SWAP_LAYOUTS_CHECK_DV2 (1 << 1)
-#define SWAP_LAYOUTS_KEEP_MTIME (1 << 2)
-#define SWAP_LAYOUTS_KEEP_ATIME (1 << 3)
+#define SWAP_LAYOUTS_CHECK_DV1 (1 << 0)
+#define SWAP_LAYOUTS_CHECK_DV2 (1 << 1)
+#define SWAP_LAYOUTS_KEEP_MTIME (1 << 2)
+#define SWAP_LAYOUTS_KEEP_ATIME (1 << 3)
+
+/* Swap XATTR_NAME_HSM as well, only on the MDT so far */
+#define SWAP_LAYOUTS_MDS_HSM (1 << 31)
struct lustre_swap_layouts {
__u64 sl_flags;
__u32 sl_fd;
CL_EXT = 9, /* namespace extended record (2nd half of rename) */
CL_OPEN = 10, /* not currently used */
CL_CLOSE = 11, /* may be written to log only with mtime change */
- CL_IOCTL = 12,
- CL_TRUNC = 13,
- CL_SETATTR = 14,
- CL_XATTR = 15,
- CL_HSM = 16, /* HSM specific events, see flags */
- CL_MTIME = 17, /* Precedence: setattr > mtime > ctime > atime */
- CL_CTIME = 18,
- CL_ATIME = 19,
- CL_LAST
+ CL_LAYOUT = 12, /* file layout/striping modified */
+ CL_TRUNC = 13,
+ CL_SETATTR = 14,
+ CL_XATTR = 15,
+ CL_HSM = 16, /* HSM specific events, see flags */
+ CL_MTIME = 17, /* Precedence: setattr > mtime > ctime > atime */
+ CL_CTIME = 18,
+ CL_ATIME = 19,
+ CL_LAST
};
static inline const char *changelog_type2str(int type) {
static const char *changelog_str[] = {
"MARK", "CREAT", "MKDIR", "HLINK", "SLINK", "MKNOD", "UNLNK",
- "RMDIR", "RENME", "RNMTO", "OPEN", "CLOSE", "IOCTL", "TRUNC",
- "SATTR", "XATTR", "HSM", "MTIME", "CTIME", "ATIME" };
+ "RMDIR", "RENME", "RNMTO", "OPEN", "CLOSE", "LYOUT", "TRUNC",
+ "SATTR", "XATTR", "HSM", "MTIME", "CTIME", "ATIME",
+ };
+
if (type >= 0 && type < CL_LAST)
return changelog_str[type];
return NULL;
}
/* per-record flags */
-#define CLF_VERSION 0x1000
-#define CLF_EXT_VERSION 0x2000
#define CLF_FLAGSHIFT 12
#define CLF_FLAGMASK ((1U << CLF_FLAGSHIFT) - 1)
#define CLF_VERMASK (~CLF_FLAGMASK)
+enum changelog_rec_flags {
+ CLF_VERSION = 0x1000,
+ CLF_RENAME = 0x2000,
+ CLF_JOBID = 0x4000,
+ CLF_SUPPORTED = CLF_VERSION | CLF_RENAME | CLF_JOBID
+};
+
+
/* Anything under the flagmask may be per-type (if desired) */
/* Flags for unlink */
#define CLF_UNLINK_LAST 0x0001 /* Unlink of last hardlink */
#define CLF_UNLINK_HSM_EXISTS 0x0002 /* File has something in HSM */
/* HSM cleaning needed */
/* Flags for rename */
-#define CLF_RENAME_LAST 0x0001 /* rename unlink last hardlink of target */
+#define CLF_RENAME_LAST 0x0001 /* rename unlink last hardlink
+ * of target */
+#define CLF_RENAME_LAST_EXISTS 0x0002 /* rename unlink last hardlink of target
+ * has an archive in backend */
/* Flags for HSM */
/* 12b used (from high weight to low weight):
static inline enum hsm_event hsm_get_cl_event(__u16 flags)
{
- return CLF_GET_BITS(flags, CLF_HSM_EVENT_H, CLF_HSM_EVENT_L);
+ return (enum hsm_event)CLF_GET_BITS(flags, CLF_HSM_EVENT_H,
+ CLF_HSM_EVENT_L);
}
static inline void hsm_set_cl_event(int *flags, enum hsm_event he)
*flags |= (error << CLF_HSM_ERR_L);
}
-#define CR_MAXSIZE cfs_size_round(2*NAME_MAX + 1 + sizeof(struct changelog_rec))
+enum changelog_send_flag {
+ /* Not yet implemented */
+ 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,
+ /* Pack jobid into the changelog records if available. */
+ CHANGELOG_FLAG_JOBID = 0x04,
+};
-struct changelog_rec {
- __u16 cr_namelen;
- __u16 cr_flags; /**< (flags&CLF_FLAGMASK)|CLF_VERSION */
- __u32 cr_type; /**< \a changelog_rec_type */
- __u64 cr_index; /**< changelog record number */
- __u64 cr_prev; /**< last index for this target fid */
- __u64 cr_time;
- union {
- lustre_fid cr_tfid; /**< target fid */
- __u32 cr_markerflags; /**< CL_MARK flags */
- };
- lustre_fid cr_pfid; /**< parent fid */
- char cr_name[0]; /**< last element */
-} __attribute__((packed));
+#define CR_MAXSIZE cfs_size_round(2 * NAME_MAX + 2 + \
+ changelog_rec_offset(CLF_SUPPORTED))
+
+/* 31 usable bytes string + null terminator. */
+#define LUSTRE_JOBID_SIZE 32
-/* changelog_ext_rec is 2*sizeof(lu_fid) bigger than changelog_rec, to save
- * space, only rename uses changelog_ext_rec, while others use changelog_rec to
- * store records.
+/* 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.
+ *
+ * Extensions are packed in the same order as their corresponding flags.
*/
-struct changelog_ext_rec {
+struct changelog_rec {
__u16 cr_namelen;
- __u16 cr_flags; /**< (flags & CLF_FLAGMASK) |
- CLF_EXT_VERSION */
+ __u16 cr_flags; /**< \a changelog_rec_flags */
__u32 cr_type; /**< \a changelog_rec_type */
__u64 cr_index; /**< changelog record number */
__u64 cr_prev; /**< last index for this target fid */
__u64 cr_time;
union {
- lustre_fid cr_tfid; /**< target fid */
+ lustre_fid cr_tfid; /**< target fid */
__u32 cr_markerflags; /**< CL_MARK flags */
};
- lustre_fid cr_pfid; /**< target parent fid */
- lustre_fid cr_sfid; /**< source fid, or zero */
- lustre_fid cr_spfid; /**< source parent fid, or zero */
- char cr_name[0]; /**< last element */
-} __attribute__((packed));
+ lustre_fid cr_pfid; /**< parent fid */
+};
-#define CHANGELOG_REC_EXTENDED(rec) \
- (((rec)->cr_flags & CLF_VERMASK) == CLF_EXT_VERSION)
+/* 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 */
+};
-static inline int changelog_rec_size(struct changelog_rec *rec)
+/* Changelog extension to include JOBID. */
+struct changelog_ext_jobid {
+ char cr_jobid[LUSTRE_JOBID_SIZE]; /**< zero-terminated string. */
+};
+
+
+static inline size_t changelog_rec_offset(enum changelog_rec_flags crf)
+{
+ size_t size = sizeof(struct changelog_rec);
+
+ if (crf & CLF_RENAME)
+ size += sizeof(struct changelog_ext_rename);
+
+ if (crf & CLF_JOBID)
+ size += sizeof(struct changelog_ext_jobid);
+
+ return size;
+}
+
+static inline size_t changelog_rec_size(struct changelog_rec *rec)
+{
+ return changelog_rec_offset(rec->cr_flags);
+}
+
+static inline size_t changelog_rec_varsize(struct changelog_rec *rec)
+{
+ return changelog_rec_size(rec) - sizeof(*rec) + rec->cr_namelen;
+}
+
+static inline
+struct changelog_ext_rename *changelog_rec_rename(struct changelog_rec *rec)
{
- return CHANGELOG_REC_EXTENDED(rec) ? sizeof(struct changelog_ext_rec):
- sizeof(*rec);
+ enum changelog_rec_flags crf = rec->cr_flags & CLF_VERSION;
+
+ return (struct changelog_ext_rename *)((char *)rec +
+ changelog_rec_offset(crf));
+}
+
+/* The jobid follows the rename extension, if present */
+static inline
+struct changelog_ext_jobid *changelog_rec_jobid(struct changelog_rec *rec)
+{
+ enum changelog_rec_flags crf = rec->cr_flags &
+ (CLF_VERSION | CLF_RENAME);
+
+ return (struct changelog_ext_jobid *)((char *)rec +
+ changelog_rec_offset(crf));
}
+/* The name follows the rename and jobid extensions, if present */
static inline char *changelog_rec_name(struct changelog_rec *rec)
{
- return CHANGELOG_REC_EXTENDED(rec) ?
- ((struct changelog_ext_rec *)rec)->cr_name: rec->cr_name;
+ return (char *)rec + changelog_rec_offset(rec->cr_flags &
+ CLF_SUPPORTED);
}
-static inline int changelog_rec_snamelen(struct changelog_ext_rec *rec)
+static inline size_t changelog_rec_snamelen(struct changelog_rec *rec)
{
- return rec->cr_namelen - strlen(rec->cr_name) - 1;
+ return rec->cr_namelen - strlen(changelog_rec_name(rec)) - 1;
}
-static inline char *changelog_rec_sname(struct changelog_ext_rec *rec)
+static inline char *changelog_rec_sname(struct changelog_rec *rec)
{
- return rec->cr_name + strlen(rec->cr_name) + 1;
+ char *cr_name = changelog_rec_name(rec);
+
+ return cr_name + strlen(cr_name) + 1;
+}
+
+/**
+ * Remap a record to the desired format as specified by the crf flags.
+ * The record must be big enough to contain the final remapped version.
+ * Superfluous extension fields are removed and missing ones are added
+ * and zeroed. The flags of the record are updated accordingly.
+ *
+ * The jobid and rename extensions can be added to a record, to match the
+ * format an application expects, typically. In this case, the newly added
+ * fields will be zeroed.
+ * The Jobid field can be removed, to guarantee compatibility with older
+ * clients that don't expect this field in the records they process.
+ *
+ * The following assumptions are being made:
+ * - CLF_RENAME will not be removed
+ * - CLF_JOBID will not be added without CLF_RENAME being added too
+ *
+ * @param[in,out] rec The record to remap.
+ * @param[in] crf_wanted Flags describing the desired extensions.
+ */
+static inline void changelog_remap_rec(struct changelog_rec *rec,
+ enum changelog_rec_flags crf_wanted)
+{
+ char *jid_mov;
+ char *rnm_mov;
+
+ crf_wanted &= CLF_SUPPORTED;
+
+ if ((rec->cr_flags & CLF_SUPPORTED) == crf_wanted)
+ return;
+
+ /* First move the variable-length name field */
+ memmove((char *)rec + changelog_rec_offset(crf_wanted),
+ changelog_rec_name(rec), rec->cr_namelen);
+
+ /* Locations of jobid and rename extensions in the remapped record */
+ jid_mov = (char *)rec +
+ changelog_rec_offset(crf_wanted & ~CLF_JOBID);
+ rnm_mov = (char *)rec +
+ changelog_rec_offset(crf_wanted & ~(CLF_JOBID | CLF_RENAME));
+
+ /* Move the extension fields to the desired positions */
+ if ((crf_wanted & CLF_JOBID) && (rec->cr_flags & CLF_JOBID))
+ memmove(jid_mov, changelog_rec_jobid(rec),
+ sizeof(struct changelog_ext_jobid));
+
+ if ((crf_wanted & CLF_RENAME) && (rec->cr_flags & CLF_RENAME))
+ memmove(rnm_mov, changelog_rec_rename(rec),
+ sizeof(struct changelog_ext_rename));
+
+ /* Clear newly added fields */
+ if ((crf_wanted & CLF_JOBID) && !(rec->cr_flags & CLF_JOBID))
+ memset(jid_mov, 0, sizeof(struct changelog_ext_jobid));
+
+ if ((crf_wanted & CLF_RENAME) && !(rec->cr_flags & CLF_RENAME))
+ memset(rnm_mov, 0, sizeof(struct changelog_ext_rename));
+
+ /* Update the record's flags accordingly */
+ rec->cr_flags = (rec->cr_flags & CLF_FLAGMASK) | crf_wanted;
}
struct ioc_changelog {
__u64 idv_version;
__u64 idv_flags; /* See LL_DV_xxx */
};
-#define LL_DV_NOFLUSH 0x01 /* Do not take READ EXTENT LOCK before sampling
- version. Dirty caches are left unchanged. */
+#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)))
+#define offsetof(typ, memb) ((unsigned long)((char *)&(((typ *)0)->memb)))
#endif
#define dot_lustre_name ".lustre"
};
#define HPS_NONE 0
-static inline char *hsm_progress_state2name(enum hsm_progress_states s)
+static inline const char *hsm_progress_state2name(enum hsm_progress_states s)
{
switch (s) {
case HPS_WAITING: return "waiting";
HUA_CANCEL = 14 /* cancel a request */
};
-static inline char *hsm_user_action2name(enum hsm_user_action a)
+static inline const char *hsm_user_action2name(enum hsm_user_action a)
{
switch (a) {
case HUA_NONE: return "NOOP";
return &(hur->hur_user_item[hur->hur_request.hr_itemcount]);
}
-/** Compute the current length of the provided hsm_user_request. */
-static inline int hur_len(struct hsm_user_request *hur)
+/**
+ * Compute the current length of the provided hsm_user_request. This returns -1
+ * instead of an errno because ssize_t is defined to be only [ -1, SSIZE_MAX ]
+ *
+ * return -1 on bounds check error.
+ */
+static inline ssize_t hur_len(struct hsm_user_request *hur)
{
- return offsetof(struct hsm_user_request,
- hur_user_item[hur->hur_request.hr_itemcount]) +
- hur->hur_request.hr_data_len;
+ __u64 size;
+
+ /* can't overflow a __u64 since hr_itemcount is only __u32 */
+ size = offsetof(struct hsm_user_request, hur_user_item[0]) +
+ (__u64)hur->hur_request.hr_itemcount *
+ sizeof(hur->hur_user_item[0]) + hur->hur_request.hr_data_len;
+
+ if (size != (ssize_t)size)
+ return -1;
+
+ return size;
}
/****** HSM RPCs to copytool *****/
HSMA_CANCEL = 23
};
-static inline char *hsm_copytool_action2name(enum hsm_copytool_action a)
+static inline const char *hsm_copytool_action2name(enum hsm_copytool_action a)
{
switch (a) {
case HSMA_NONE: return "NOOP";
* \param len [IN] max buffer len
* \retval buffer
*/
-static inline char *hai_dump_data_field(struct hsm_action_item *hai,
+static inline char *hai_dump_data_field(const struct hsm_action_item *hai,
char *buffer, int len)
{
int i, sz, data_len;
#endif
/* Return pointer to first hai in action list */
-static inline struct hsm_action_item * hai_zero(struct hsm_action_list *hal)
+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)));
+ return (struct hsm_action_item *)(hal->hal_fsname +
+ cfs_size_round(strlen(hal-> \
+ hal_fsname)
+ + 1));
}
/* Return pointer to next hai */
static inline struct hsm_action_item * hai_next(struct hsm_action_item *hai)
}
/* Return size of an hsm_action_list */
-static inline int hal_size(struct hsm_action_list *hal)
+static inline size_t hal_size(struct hsm_action_list *hal)
{
- int i, sz;
- struct hsm_action_item *hai;
-
- sz = sizeof(*hal) + cfs_size_round(strlen(hal->hal_fsname));
- hai = hai_zero(hal);
- for (i = 0 ; i < hal->hal_count ; i++) {
- sz += cfs_size_round(hai->hai_len);
- hai = hai_next(hai);
- }
- return(sz);
+ __u32 i;
+ size_t sz;
+ struct hsm_action_item *hai;
+
+ sz = sizeof(*hal) + cfs_size_round(strlen(hal->hal_fsname) + 1);
+ hai = hai_first(hal);
+ for (i = 0; i < hal->hal_count ; i++, hai = hai_next(hai))
+ sz += cfs_size_round(hai->hai_len);
+
+ return sz;
}
+/* HSM file import
+ * describe the attributes to be set on imported file
+ */
+struct hsm_user_import {
+ __u64 hui_size;
+ __u64 hui_atime;
+ __u64 hui_mtime;
+ __u32 hui_atime_ns;
+ __u32 hui_mtime_ns;
+ __u32 hui_uid;
+ __u32 hui_gid;
+ __u32 hui_mode;
+ __u32 hui_archive_id;
+};
+
/* Copytool progress reporting */
#define HP_FLAG_COMPLETED 0x01
#define HP_FLAG_RETRY 0x02
__u32 padding;
};
-/**
- * Use by copytool during any hsm request they handled.
- * This structure is initialized by llapi_hsm_copy_start()
- * which is an helper over the ioctl() interface
- * Store Lustre, internal use only, data.
- */
struct hsm_copy {
__u64 hc_data_version;
__u16 hc_flags;
struct hsm_action_item hc_hai;
};
+/* JSON objects */
+enum llapi_json_types {
+ LLAPI_JSON_INTEGER = 1,
+ LLAPI_JSON_BIGNUM,
+ LLAPI_JSON_REAL,
+ LLAPI_JSON_STRING
+};
+
+struct llapi_json_item {
+ char *lji_key;
+ __u32 lji_type;
+ union {
+ int lji_integer;
+ __u64 lji_u64;
+ double lji_real;
+ char *lji_string;
+ };
+ struct llapi_json_item *lji_next;
+};
+
+struct llapi_json_item_list {
+ int ljil_item_count;
+ struct llapi_json_item *ljil_items;
+};
+
/** @} lustreuser */
#endif /* _LUSTRE_USER_H */