* @{
*/
+#include <linux/fs.h>
+#include <linux/limits.h>
#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/quota.h>
#include <linux/types.h>
+#include <linux/unistd.h>
+#include <linux/lustre/lustre_fiemap.h>
+#include <linux/lustre/lustre_ver.h>
-#ifdef __KERNEL__
-# include <linux/fs.h>
-# include <linux/quota.h>
-# include <linux/string.h> /* snprintf() */
-# include <linux/version.h>
-# include <uapi/linux/lustre/lustre_fiemap.h>
-#else /* !__KERNEL__ */
-# include <limits.h>
+#ifndef __KERNEL__
+# define __USE_ISOC99 1
# include <stdbool.h>
# include <stdio.h> /* snprintf() */
-# include <stdint.h>
-# include <string.h>
-# define NEED_QUOTA_DEFS
-/* # include <sys/quota.h> - this causes complaints about caddr_t */
# include <sys/stat.h>
-# 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
+# define FILEID_LUSTRE 0x97 /* for name_to_handle_at() (and llapi_fd2fid()) */
+#endif /* !__KERNEL__ */
#if defined(__cplusplus)
extern "C" {
#endif
+#ifdef __STRICT_ANSI__
+#define typeof __typeof__
+#endif
+
/*
* This is a temporary solution of adding quota type.
* Should be removed as soon as system header is updated.
#define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */
-#endif
+#define AT_STATX_SYNC_TYPE 0x6000 /* Type of synchronisation required from statx() */
+#define AT_STATX_SYNC_AS_STAT 0x0000 /* - Do whatever stat() does */
+#define AT_STATX_FORCE_SYNC 0x2000 /* - Force the attributes to be sync'd with the server */
+#define AT_STATX_DONT_SYNC 0x4000 /* - Don't sync attributes with the server */
+
+#endif /* STATX_BASIC_STATS */
typedef struct statx lstatx_t;
#define LUSTRE_FIEMAP_FLAGS_COMPAT (FIEMAP_FLAG_SYNC | FIEMAP_FLAG_DEVICE_ORDER)
enum obd_statfs_state {
- OS_STATE_DEGRADED = 0x00000001, /**< RAID degraded/rebuilding */
- OS_STATE_READONLY = 0x00000002, /**< filesystem is read-only */
- OS_STATE_NOPRECREATE = 0x00000004, /**< no object precreation */
- OS_STATE_UNUSED1 = 0x00000008, /**< obsolete 1.6, was EROFS=30 */
- OS_STATE_UNUSED2 = 0x00000010, /**< obsolete 1.6, was EROFS=30 */
- OS_STATE_ENOSPC = 0x00000020, /**< not enough free space */
- OS_STATE_ENOINO = 0x00000040, /**< not enough inodes */
- OS_STATE_SUM = 0x00000100, /**< aggregated for all tagrets */
- OS_STATE_NONROT = 0x00000200, /**< non-rotational device */
+ OS_STATFS_DEGRADED = 0x00000001, /**< RAID degraded/rebuilding */
+ OS_STATFS_READONLY = 0x00000002, /**< filesystem is read-only */
+ OS_STATFS_NOPRECREATE = 0x00000004, /**< no object precreation */
+ OS_STATFS_UNUSED1 = 0x00000008, /**< obsolete 1.6, was EROFS=30 */
+ OS_STATFS_UNUSED2 = 0x00000010, /**< obsolete 1.6, was EROFS=30 */
+ OS_STATFS_ENOSPC = 0x00000020, /**< not enough free space */
+ OS_STATFS_ENOINO = 0x00000040, /**< not enough inodes */
+ OS_STATFS_SUM = 0x00000100, /**< aggregated for all tagrets */
+ OS_STATFS_NONROT = 0x00000200, /**< non-rotational device */
};
/** filesystem statistics/attributes for target device */
__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_state; /**< obd_statfs_state OS_STATFS_* */
__u32 os_fprecreated; /* objs available now to the caller */
/* used in QoS code to find preferred
* OSTs */
* used.
**/
__u32 f_ver;
-};
+} __attribute__((packed));
static inline bool fid_is_zero(const struct lu_fid *fid)
{
return fid->f_seq == 0 && fid->f_oid == 0;
}
+/* The data name_to_handle_at() places in a struct file_handle (at f_handle) */
+struct lustre_file_handle {
+ struct lu_fid lfh_child;
+ struct lu_fid lfh_parent;
+};
+
/* 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. */
is on the remote MDT */
LMAI_STRIPED = 0x00000008, /* striped directory inode */
LMAI_ORPHAN = 0x00000010, /* inode is orphan */
+ LMAI_ENCRYPT = 0x00000020, /* inode is encrypted */
LMA_INCOMPAT_SUPP = (LMAI_AGENT | LMAI_REMOTE_PARENT | \
- LMAI_STRIPED | LMAI_ORPHAN)
+ LMAI_STRIPED | LMAI_ORPHAN | LMAI_ENCRYPT)
};
} oi;
struct lu_fid oi_fid;
};
-};
+} __attribute__((packed));
#define DOSTID "%#llx:%llu"
#define POSTID(oi) ((unsigned long long)ostid_seq(oi)), \
#define FS_IOC_FSGETXATTR _IOR('X', 31, struct fsxattr)
#define FS_IOC_FSSETXATTR _IOW('X', 32, struct fsxattr)
#endif
-#define LL_IOC_FSGETXATTR FS_IOC_FSGETXATTR
-#define LL_IOC_FSSETXATTR FS_IOC_FSSETXATTR
#ifndef FS_XFLAG_PROJINHERIT
#define FS_XFLAG_PROJINHERIT 0x00000200
#endif
#define LL_FILE_GROUP_LOCKED 0x00000002
#define LL_FILE_READAHEA 0x00000004
#define LL_FILE_LOCKED_DIRECTIO 0x00000008 /* client-side locks with dio */
-#define LL_FILE_LOCKLESS_IO 0x00000010 /* server-side locks with cio */
#define LL_FILE_FLOCK_WARNING 0x00000020 /* warned about disabled flock */
#define LOV_USER_MAGIC_V1 0x0BD10BD0
#define XATTR_LUSTRE_PREFIX "lustre."
#define XATTR_LUSTRE_LOV XATTR_LUSTRE_PREFIX"lov"
+/* Please update if XATTR_LUSTRE_LOV".set" groks more flags in the future */
+#define allowed_lustre_lov(att) (strcmp((att), XATTR_LUSTRE_LOV".add") == 0 || \
+ strcmp((att), XATTR_LUSTRE_LOV".set") == 0 || \
+ strcmp((att), XATTR_LUSTRE_LOV".set.flags") == 0 || \
+ strcmp((att), XATTR_LUSTRE_LOV".del") == 0)
+
#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 */
* used when reading */
};
struct lov_user_ost_data_v1 lmm_objects[0]; /* per-stripe data */
-} __attribute__((packed, __may_alias__));
+} __attribute__((packed, __may_alias__));
struct lov_user_md_v3 { /* LOV EA user data (host-endian) */
__u32 lmm_magic; /* magic number = LOV_USER_MAGIC_V3 */
};
char lmm_pool_name[LOV_MAXPOOLNAME + 1]; /* pool name */
struct lov_user_ost_data_v1 lmm_objects[0]; /* per-stripe data */
-} __attribute__((packed));
+} __attribute__((packed, __may_alias__));
struct lov_foreign_md {
__u32 lfm_magic; /* magic number = LOV_MAGIC_FOREIGN */
__u32 lfm_type; /* type, see LU_FOREIGN_TYPE_ */
__u32 lfm_flags; /* flags, type specific */
char lfm_value[];
-};
+} __attribute__((packed));
#define foreign_size(lfm) (((struct lov_foreign_md *)lfm)->lfm_length + \
offsetof(struct lov_foreign_md, lfm_value))
struct lu_extent {
__u64 e_start;
__u64 e_end;
-};
+} __attribute__((packed));
#define DEXT "[%#llx, %#llx)"
#define PEXT(ext) (unsigned long long)(ext)->e_start, (unsigned long long)(ext)->e_end
struct lu_fid lum_fid;
__u32 lum_padding;
__u32 lum_mds;
-};
+} __attribute__((packed, __may_alias__));
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,
+ LMV_HASH_TYPE_CRUSH = 3,
LMV_HASH_TYPE_MAX,
};
#define LMV_HASH_NAME_ALL_CHARS "all_char"
#define LMV_HASH_NAME_FNV_1A_64 "fnv_1a_64"
-
-/* not real hash type, but exposed to user as "space" hash type */
-#define LMV_HASH_NAME_SPACE "space"
+#define LMV_HASH_NAME_CRUSH "crush"
/* 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,
static inline bool lmv_is_known_hash_type(__u32 type)
{
return (type & LMV_HASH_TYPE_MASK) == LMV_HASH_TYPE_FNV_1A_64 ||
- (type & LMV_HASH_TYPE_MASK) == LMV_HASH_TYPE_ALL_CHARS;
+ (type & LMV_HASH_TYPE_MASK) == LMV_HASH_TYPE_ALL_CHARS ||
+ (type & LMV_HASH_TYPE_MASK) == LMV_HASH_TYPE_CRUSH;
}
+#define LMV_HASH_FLAG_MERGE 0x04000000
+#define LMV_HASH_FLAG_SPLIT 0x08000000
+
/* 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_HASH_FLAG_LOST_LMV 0x10000000
+
+#define LMV_HASH_FLAG_BAD_TYPE 0x20000000
+#define LMV_HASH_FLAG_MIGRATION 0x80000000
+
+#define LMV_HASH_FLAG_LAYOUT_CHANGE \
+ (LMV_HASH_FLAG_MIGRATION | LMV_HASH_FLAG_SPLIT | LMV_HASH_FLAG_MERGE)
-#define LMV_HASH_FLAG_BAD_TYPE 0x20000000
-#define LMV_HASH_FLAG_MIGRATION 0x80000000
+/* both SPLIT and MIGRATION are set for directory split */
+static inline bool lmv_hash_is_splitting(__u32 hash)
+{
+ return (hash & LMV_HASH_FLAG_LAYOUT_CHANGE) ==
+ (LMV_HASH_FLAG_SPLIT | LMV_HASH_FLAG_MIGRATION);
+}
+
+/* both MERGE and MIGRATION are set for directory merge */
+static inline bool lmv_hash_is_merging(__u32 hash)
+{
+ return (hash & LMV_HASH_FLAG_LAYOUT_CHANGE) ==
+ (LMV_HASH_FLAG_MERGE | LMV_HASH_FLAG_MIGRATION);
+}
+
+/* only MIGRATION is set for directory migration */
+static inline bool lmv_hash_is_migrating(__u32 hash)
+{
+ return (hash & LMV_HASH_FLAG_LAYOUT_CHANGE) == LMV_HASH_FLAG_MIGRATION;
+}
+
+static inline bool lmv_hash_is_restriping(__u32 hash)
+{
+ return lmv_hash_is_splitting(hash) || lmv_hash_is_merging(hash);
+}
+
+static inline bool lmv_hash_is_layout_changing(__u32 hash)
+{
+ return lmv_hash_is_splitting(hash) || lmv_hash_is_merging(hash) ||
+ lmv_hash_is_migrating(hash);
+}
extern char *mdt_hash_name[LMV_HASH_TYPE_MAX];
struct lustre_foreign_type {
- uint32_t lft_type;
- const char *lft_name;
+ __u32 lft_type;
+ const char *lft_name;
};
/**
}
#define LUSTRE_MAXFSNAME 8
+#define LUSTRE_MAXINSTANCE 16
/* Extract fsname from uuid (or target name) of a target
e.g. (myfs-OST0007_UUID -> myfs)
#define LUSTRE_QUOTABLOCK_BITS 10
#define LUSTRE_QUOTABLOCK_SIZE (1 << LUSTRE_QUOTABLOCK_BITS)
-static inline __u64 lustre_stoqb(size_t space)
+static inline __u64 lustre_stoqb(__kernel_size_t space)
{
return (space + LUSTRE_QUOTABLOCK_SIZE - 1) >> LUSTRE_QUOTABLOCK_BITS;
}
#define LUSTRE_Q_FINVALIDATE 0x80000c /* deprecated as of 2.4 */
#define LUSTRE_Q_GETDEFAULT 0x80000d /* get default quota */
#define LUSTRE_Q_SETDEFAULT 0x80000e /* set default quota */
-
+#define LUSTRE_Q_GETQUOTAPOOL 0x80000f /* get user pool quota */
+#define LUSTRE_Q_SETQUOTAPOOL 0x800010 /* set user pool quota */
+#define LUSTRE_Q_GETINFOPOOL 0x800011 /* get pool quota info */
+#define LUSTRE_Q_SETINFOPOOL 0x800012 /* set pool quota info */
/* In the current Lustre implementation, the grace time is either the time
* or the timestamp to be used after some quota ID exceeds the soft limt,
* 48 bits should be enough, its high 16 bits can be used as quota flags.
#define LQUOTA_FLAG(t) (t >> LQUOTA_GRACE_BITS)
#define LQUOTA_GRACE_FLAG(t, f) ((__u64)t | (__u64)f << LQUOTA_GRACE_BITS)
+/* special grace time, only notify the user when its quota is over soft limit
+ * but doesn't block new writes until the hard limit is reached. */
+#define NOTIFY_GRACE "notify"
+#define NOTIFY_GRACE_TIME LQUOTA_GRACE_MASK
+
/* different quota flags */
/* the default quota flag, the corresponding quota ID will use the default
* */
#define LQUOTA_FLAG_DEFAULT 0x0001
+#define LUSTRE_Q_CMD_IS_POOL(cmd) \
+ (cmd == LUSTRE_Q_GETQUOTAPOOL || \
+ cmd == LUSTRE_Q_SETQUOTAPOOL || \
+ cmd == LUSTRE_Q_SETINFOPOOL || \
+ cmd == LUSTRE_Q_GETINFOPOOL)
+
#define ALLQUOTA 255 /* set all quota */
static inline const char *qtype_name(int qtype)
{
}
#define IDENTITY_DOWNCALL_MAGIC 0x6d6dd629
-#define SEPOL_DOWNCALL_MAGIC 0x8b8bb842
/* permission */
#define N_PERMS_MAX 64
__u32 idd_groups[0];
};
+#if LUSTRE_VERSION_CODE < OBD_OCD_VERSION(2, 16, 53, 0)
+/* old interface struct is deprecated in 2.14 */
+#define SEPOL_DOWNCALL_MAGIC_OLD 0x8b8bb842
+struct sepol_downcall_data_old {
+ __u32 sdd_magic;
+ __s64 sdd_sepol_mtime;
+ __u16 sdd_sepol_len;
+ char sdd_sepol[0];
+};
+#endif
+
+#define SEPOL_DOWNCALL_MAGIC 0x8b8bb843
struct sepol_downcall_data {
- __u32 sdd_magic;
- time_t sdd_sepol_mtime;
- __u16 sdd_sepol_len;
- char sdd_sepol[0];
+ __u32 sdd_magic;
+ __u16 sdd_sepol_len;
+ __u16 sdd_padding1;
+ __s64 sdd_sepol_mtime;
+ char sdd_sepol[0];
};
#ifdef NEED_QUOTA_DEFS
/* XXX: same as if_dqblk struct in kernel, plus one padding */
struct obd_dqblk {
- __u64 dqb_bhardlimit;
- __u64 dqb_bsoftlimit;
- __u64 dqb_curspace;
+ __u64 dqb_bhardlimit; /* kbytes unit */
+ __u64 dqb_bsoftlimit; /* kbytes unit */
+ __u64 dqb_curspace; /* bytes unit */
__u64 dqb_ihardlimit;
__u64 dqb_isoftlimit;
__u64 dqb_curinodes;
struct obd_dqblk qc_dqblk;
char obd_type[16];
struct obd_uuid obd_uuid;
+ char qc_poolname[0];
};
/* swap layout flags */
LA_LAYOUT_VERSION = 1 << 16, /* 0x10000 */
LA_LSIZE = 1 << 17, /* 0x20000 */
LA_LBLOCKS = 1 << 18, /* 0x40000 */
+ LA_BTIME = 1 << 19, /* 0x80000 */
/**
* Attributes must be transmitted to OST objects
*/
__u32 cr_markerflags; /**< CL_MARK flags */
};
struct lu_fid cr_pfid; /**< parent fid */
-};
+} __attribute__ ((packed));
/* Changelog extension for RENAME. */
struct changelog_ext_rename {
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 __kernel_size_t changelog_rec_offset(enum changelog_rec_flags crf,
enum changelog_rec_extra_flags cref)
{
- size_t size = sizeof(struct changelog_rec);
+ __kernel_size_t size = sizeof(struct changelog_rec);
if (crf & CLF_RENAME)
size += sizeof(struct changelog_ext_rename);
return size;
}
-static inline size_t changelog_rec_size(const struct changelog_rec *rec)
+static inline __kernel_size_t changelog_rec_size(const struct changelog_rec *rec)
{
enum changelog_rec_extra_flags cref = CLFE_INVALID;
(enum changelog_rec_flags)rec->cr_flags, cref);
}
-static inline size_t changelog_rec_varsize(const struct changelog_rec *rec)
+static inline __kernel_size_t changelog_rec_varsize(const struct changelog_rec *rec)
{
return changelog_rec_size(rec) - sizeof(*rec) + rec->cr_namelen;
}
(enum changelog_rec_extra_flags)(cref & CLFE_SUPPORTED));
}
-static inline size_t changelog_rec_snamelen(const struct changelog_rec *rec)
+static inline __kernel_size_t changelog_rec_snamelen(const struct changelog_rec *rec)
{
return rec->cr_namelen - strlen(changelog_rec_name(rec)) - 1;
}
/**
* 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 ]
+ * instead of an errno because __kernel_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)
+static inline __kernel_size_t hur_len(struct hsm_user_request *hur)
{
__u64 size;
(__u64)hur->hur_request.hr_itemcount *
sizeof(hur->hur_user_item[0]) + hur->hur_request.hr_data_len;
- if ((ssize_t)size < 0)
+ if ((__kernel_ssize_t)size < 0)
return -1;
return size;
* \retval buffer
*/
static inline char *hai_dump_data_field(const struct hsm_action_item *hai,
- char *buffer, size_t len)
+ char *buffer, __kernel_size_t len)
{
int i;
int data_len;
/* Return pointer to first hai in action list */
static inline struct hsm_action_item *hai_first(struct hsm_action_list *hal)
{
- size_t offset = __ALIGN_KERNEL(strlen(hal->hal_fsname) + 1, 8);
+ __kernel_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)
{
- size_t offset = __ALIGN_KERNEL(hai->hai_len, 8);
+ __kernel_size_t offset = __ALIGN_KERNEL(hai->hai_len, 8);
return (struct hsm_action_item *)((char *)hai + offset);
}
/* Return size of an hsm_action_list */
-static inline size_t hal_size(struct hsm_action_list *hal)
+static inline __kernel_size_t hal_size(struct hsm_action_list *hal)
{
__u32 i;
- size_t sz;
+ __kernel_size_t sz;
struct hsm_action_item *hai;
sz = sizeof(*hal) + __ALIGN_KERNEL(strlen(hal->hal_fsname) + 1, 8);
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;
-};
-
enum lu_ladvise_type {
LU_LADVISE_INVALID = 0,
LU_LADVISE_WILLREAD = 1,
PCC_STATE_FL_ATTR_VALID = 0x01,
/* The file is being attached into PCC */
PCC_STATE_FL_ATTACHING = 0x02,
- /* Allow to auto attach at open */
- PCC_STATE_FL_OPEN_ATTACH = 0x04,
- /* Allow to auto attach during I/O after layout lock revocation */
- PCC_STATE_FL_IO_ATTACH = 0x08,
- /* Allow to auto attach at stat */
- PCC_STATE_FL_STAT_ATTACH = 0x10,
- /* Allow to auto attach at the next open or layout refresh */
- PCC_STATE_FL_AUTO_ATTACH = PCC_STATE_FL_OPEN_ATTACH |
- PCC_STATE_FL_IO_ATTACH |
- PCC_STATE_FL_STAT_ATTACH,
};
struct lu_pcc_state {
git://git.whamcloud.com / fs / lustre-release.git / blobdiff