* 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, 2013, Intel Corporation.
*/
/*
* This file is part of Lustre, http://www.lustre.org/
*/
#ifndef __KERNEL__
+#include <stdio.h>
#include <libcfs/posix/posix-types.h>
+#include <stdio.h>
#endif
#include <lustre/ll_fiemap.h>
#if defined(__linux__)
#error Unsupported operating system.
#endif
+#ifdef __cplusplus
+#define LUSTRE_ANONYMOUS_UNION_NAME u
+#else
+#define LUSTRE_ANONYMOUS_UNION_NAME
+#endif
+
/* for statfs() */
#define LL_SUPER_MAGIC 0x0BD00BD0
__u32 os_spare9;
};
+/**
+ * File IDentifier.
+ *
+ * FID is a cluster-wide unique identifier of a file or an object (stripe).
+ * FIDs are never reused.
+ **/
+struct lu_fid {
+ /**
+ * FID sequence. Sequence is a unit of migration: all files (objects)
+ * with FIDs from a given sequence are stored on the same server.
+ * Lustre should support 2^64 objects, so even if each sequence
+ * has only a single object we can still enumerate 2^64 objects.
+ **/
+ __u64 f_seq;
+ /* FID number within sequence. */
+ __u32 f_oid;
+ /**
+ * FID version, used to distinguish different versions (in the sense
+ * of snapshots, etc.) of the same file system object. Not currently
+ * used.
+ **/
+ __u32 f_ver;
+};
+
+struct filter_fid {
+ struct lu_fid ff_parent; /* ff_parent.f_ver == file stripe number */
+};
+
+/* keep this one for compatibility */
+struct filter_fid_old {
+ struct lu_fid ff_parent;
+ __u64 ff_objid;
+ __u64 ff_seq;
+};
+
+/* 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;
+
+/**
+ * Following struct for object attributes, that will be kept inode's EA.
+ * Introduced in 2.0 release (please see b15993, for details)
+ * Added to all objects since Lustre 2.4 as contains self FID
+ */
+struct lustre_mdt_attrs {
+ /**
+ * Bitfield for supported data in this structure. From enum lma_compat.
+ * lma_self_fid and lma_flags are always available.
+ */
+ __u32 lma_compat;
+ /**
+ * Per-file incompat feature list. Lustre version should support all
+ * flags set in this field. The supported feature mask is available in
+ * LMA_INCOMPAT_SUPP.
+ */
+ __u32 lma_incompat;
+ /** FID of this inode */
+ struct lu_fid lma_self_fid;
+};
+
+/**
+ * Prior to 2.4, the LMA structure also included SOM attributes which has since
+ * been moved to a dedicated xattr
+ * lma_flags was also removed because of lma_compat/incompat fields.
+ */
+#define LMA_OLD_SIZE (sizeof(struct lustre_mdt_attrs) + 5 * sizeof(__u64))
+
+/**
+ * OST object IDentifier.
+ */
+struct ost_id {
+ union {
+ struct ostid {
+ __u64 oi_id;
+ __u64 oi_seq;
+ } oi;
+ struct lu_fid oi_fid;
+ } LUSTRE_ANONYMOUS_UNION_NAME;
+};
+
+#define DOSTID LPX64":"LPU64
+#define POSTID(oi) ostid_seq(oi), ostid_id(oi)
/*
* The ioctl naming rules:
#define LL_IOC_HSM_PROGRESS _IOW('f', 216, struct hsm_user_request)
#define LL_IOC_HSM_REQUEST _IOW('f', 217, struct hsm_user_request)
#define LL_IOC_DATA_VERSION _IOR('f', 218, struct ioc_data_version)
-/* 219 is reserved for swap layouts */
+#define LL_IOC_LOV_SWAP_LAYOUTS _IOW('f', 219, \
+ 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_STATFS_LMV 1
-#define LL_STATFS_LOV 2
+#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_STATFS_LMV 1
+#define LL_STATFS_LOV 2
#define LL_STATFS_NODELAY 4
#define IOC_MDC_TYPE 'i'
#define LOV_USER_MAGIC_JOIN_V1 0x0BD20BD0
#define LOV_USER_MAGIC_V3 0x0BD30BD0
+#define LMV_MAGIC_V1 0x0CD10CD0 /*normal stripe lmv magic */
+#define LMV_USER_MAGIC 0x0CD20CD0 /*default lmv magic*/
+
#define LOV_PATTERN_RAID0 0x001
#define LOV_PATTERN_RAID1 0x002
#define LOV_PATTERN_FIRST 0x100
#define LOV_POOLNAMEF "%.16s"
#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_MIN_STRIPE_SIZE (1 << LOV_MIN_STRIPE_BITS)
#define LOV_MAX_STRIPE_COUNT_OLD 160
/* This calculation is crafted so that input of 4096 will result in 160
* which in turn is equal to old maximal stripe count.
#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 */
- __u64 l_object_id; /* OST object ID */
- __u64 l_object_seq; /* OST object seq number */
- __u32 l_ost_gen; /* generation of this OST index */
- __u32 l_ost_idx; /* OST index in LOV */
+ 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 lov_user_md lov_user_md_v1
-#define lmm_stripe_offset u.lum_stripe_offset
struct lov_user_md_v1 { /* LOV EA user data (host-endian) */
- __u32 lmm_magic; /* magic number = LOV_USER_MAGIC_V1 */
- __u32 lmm_pattern; /* LOV_PATTERN_RAID0, LOV_PATTERN_RAID1 */
- __u64 lmm_object_id; /* LOV object ID */
- __u64 lmm_object_seq; /* LOV object seq */
- __u32 lmm_stripe_size; /* size of stripe in bytes */
- __u16 lmm_stripe_count; /* num stripes in use for this object */
- union {
- __u16 lum_stripe_offset; /* starting stripe offset in
- * lmm_objects, use when writing */
- __u16 lum_layout_gen; /* layout generation number
- * used when reading */
- } u;
- struct lov_user_ost_data_v1 lmm_objects[0]; /* per-stripe data */
+ __u32 lmm_magic; /* magic number = LOV_USER_MAGIC_V1 */
+ __u32 lmm_pattern; /* LOV_PATTERN_RAID0, LOV_PATTERN_RAID1 */
+ struct ost_id lmm_oi; /* LOV object ID */
+ __u32 lmm_stripe_size; /* size of stripe in bytes */
+ __u16 lmm_stripe_count; /* num stripes in use for this object */
+ union {
+ __u16 lmm_stripe_offset; /* starting stripe offset in
+ * lmm_objects, use when writing */
+ __u16 lmm_layout_gen; /* layout generation number
+ * used when reading */
+ };
+ struct lov_user_ost_data_v1 lmm_objects[0]; /* per-stripe data */
} __attribute__((packed, __may_alias__));
struct lov_user_md_v3 { /* LOV EA user data (host-endian) */
- __u32 lmm_magic; /* magic number = LOV_USER_MAGIC_V3 */
- __u32 lmm_pattern; /* LOV_PATTERN_RAID0, LOV_PATTERN_RAID1 */
- __u64 lmm_object_id; /* LOV object ID */
- __u64 lmm_object_seq; /* LOV object seq */
- __u32 lmm_stripe_size; /* size of stripe in bytes */
- __u16 lmm_stripe_count; /* num stripes in use for this object */
- union {
- __u16 lum_stripe_offset; /* starting stripe offset in
- * lmm_objects, use when writing */
- __u16 lum_layout_gen; /* layout generation number
- * used when reading */
- } u;
- char lmm_pool_name[LOV_MAXPOOLNAME]; /* pool name */
- struct lov_user_ost_data_v1 lmm_objects[0]; /* per-stripe data */
+ __u32 lmm_magic; /* magic number = LOV_USER_MAGIC_V3 */
+ __u32 lmm_pattern; /* LOV_PATTERN_RAID0, LOV_PATTERN_RAID1 */
+ struct ost_id lmm_oi; /* LOV object ID */
+ __u32 lmm_stripe_size; /* size of stripe in bytes */
+ __u16 lmm_stripe_count; /* num stripes in use for this object */
+ union {
+ __u16 lmm_stripe_offset; /* starting stripe offset in
+ * lmm_objects, use when writing */
+ __u16 lmm_layout_gen; /* layout generation number
+ * used when reading */
+ };
+ char lmm_pool_name[LOV_MAXPOOLNAME]; /* 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_V3)
+ return sizeof(struct lov_user_md_v3) +
+ stripes * sizeof(struct lov_user_ost_data_v1);
+ else
+ return sizeof(struct lov_user_md_v1) +
+ 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,
+};
+
+#define lmv_user_md lmv_user_md_v1
+struct lmv_user_md_v1 {
+ __u32 lum_magic; /* must be the first field */
+ __u32 lum_stripe_count; /* dirstripe count */
+ __u32 lum_stripe_offset; /* MDT idx for default dirstripe */
+ __u32 lum_hash_type; /* Dir stripe policy */
+ __u32 lum_type; /* LMV type: default or normal */
+ __u32 lum_padding1;
+ __u32 lum_padding2;
+ __u32 lum_padding3;
+ char lum_pool_name[LOV_MAXPOOLNAME];
+ struct lmv_user_mds_data lum_objects[0];
+};
+
+static inline int lmv_user_md_size(int stripes, int lmm_magic)
+{
+ return sizeof(struct lmv_user_md) +
+ stripes * sizeof(struct lmv_user_mds_data);
+}
+
+extern void lustre_swab_lmv_user_md(struct lmv_user_md *lum);
+
struct ll_recreate_obj {
__u64 lrc_id;
__u32 lrc_ost_idx;
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. */
*p = '\0';
}
-/**
- * File IDentifier.
- *
- * FID is a cluster-wide unique identifier of a file or an object (stripe).
- * FIDs are never reused.
- */
-struct lu_fid {
- /**
- * FID sequence. Sequence is a unit of migration: all files (objects)
- * with FIDs from a given sequence are stored on the same server.
- * Lustre should support 2^64 objects, so even if each sequence
- * has only a single object we can still enumerate 2^64 objects.
- */
- __u64 f_seq;
- /** FID number within sequence. */
- __u32 f_oid;
- /**
- * FID version, used to distinguish different versions (in the sense
- * of snapshots, etc.) of the same file system object. Not currently
- * used.
- */
- __u32 f_ver;
-};
-
-struct filter_fid {
- struct lu_fid ff_parent; /* ff_parent.f_ver == file stripe number */
- __u64 ff_objid;
- __u64 ff_seq;
-};
-
-/* 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;
-
/* 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) \
struct obd_uuid obd_uuid;
};
+/* 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)
+
+/* 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;
+ __u32 sl_gid;
+ __u64 sl_dv1;
+ __u64 sl_dv2;
+};
+
/********* Changelogs **********/
/** Changelog record types */
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;
#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))
+#define CR_MAXSIZE cfs_size_round(2*NAME_MAX + 1 + \
+ sizeof(struct changelog_ext_rec))
struct changelog_rec {
__u16 cr_namelen;
__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";
/** Compute the current length of the provided hsm_user_request. */
static inline int hur_len(struct hsm_user_request *hur)
{
- int data_offset;
-
- data_offset = hur_data(hur) - (void *)hur;
- data_offset += hur->hur_request.hr_data_len;
- return data_offset;
+ return offsetof(struct hsm_user_request, hur_user_item[0]) +
+ hur->hur_request.hr_itemcount * sizeof(hur->hur_user_item[0]) +
+ hur->hur_request.hr_data_len;
}
/****** 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-> \
}
/* 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));
+ 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;
git://git.whamcloud.com / fs / lustre-release.git / blobdiff