# include <linux/version.h>
# include <uapi/linux/lustre/lustre_fiemap.h>
#else /* !__KERNEL__ */
-# define NEED_QUOTA_DEFS
# include <limits.h>
# include <stdbool.h>
# include <stdio.h> /* snprintf() */
# include <string.h>
-# include <sys/quota.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__ */
"project", /* PRJQUOTA */ \
"undefined", \
};
+#ifndef USRQUOTA
+#define USRQUOTA 0
+#endif
+#ifndef GRPQUOTA
+#define GRPQUOTA 1
+#endif
+#ifndef PRJQUOTA
#define PRJQUOTA 2
+#endif
/*
* We need to always use 64bit version because the structure
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_ENOSPC = 0x00000020, /**< not enough free space */
OS_STATE_ENOINO = 0x00000040, /**< not enough inodes */
+ OS_STATE_SUM = 0x00000100, /**< aggregated for all tagrets */
};
/** filesystem statistics/attributes for target device */
__u32 os_fprecreated; /* objs available now to the caller */
/* used in QoS code to find preferred
* OSTs */
- __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;
+ __u32 os_granted; /* space granted for MDS */
+ __u32 os_spare3; /* Unused padding fields. Remember */
+ __u32 os_spare4; /* to fix lustre_swab_obd_statfs() */
+ __u32 os_spare5;
+ __u32 os_spare6;
+ __u32 os_spare7;
+ __u32 os_spare8;
+ __u32 os_spare9;
};
/**
__u32 ol_comp_id;
} __attribute__((packed));
-/* keep this one for compatibility */
-struct filter_fid_old {
- struct lu_fid ff_parent;
- __u64 ff_objid;
- __u64 ff_seq;
+/* The filter_fid structure has changed several times over its lifetime.
+ * For a long time "trusted.fid" held the MDT inode parent FID/IGIF and
+ * stripe_index and the "self FID" (objid/seq) to be able to recover the
+ * OST objects in case of corruption. With the move to 2.4 and OSD-API for
+ * the OST, the "trusted.lma" xattr was added to the OST objects to store
+ * the "self FID" to be consistent with the MDT on-disk format, and the
+ * filter_fid only stored the MDT inode parent FID and stripe index.
+ *
+ * In 2.10, the addition of PFL composite layouts required more information
+ * to be stored into the filter_fid in order to be able to identify which
+ * component the OST object belonged. As well, the stripe size may vary
+ * between components, so it was no longer safe to assume the stripe size
+ * or stripe_count of a file. This is also more robust for plain layouts.
+ *
+ * For ldiskfs OSTs that were formatted with 256-byte inodes, there is not
+ * enough space to store both the filter_fid and LMA in the inode, so they
+ * are packed into struct lustre_ost_attrs on disk in trusted.lma to avoid
+ * an extra seek for every OST object access.
+ *
+ * In 2.11, FLR mirror layouts also need to store the layout version and
+ * range so that writes to old versions of the layout are not allowed.
+ * That ensures that mirrored objects are not modified by evicted clients,
+ * and ensures that the components are correctly marked stale on the MDT.
+ */
+struct filter_fid_18_23 {
+ struct lu_fid ff_parent; /* stripe_idx in f_ver */
+ __u64 ff_objid;
+ __u64 ff_seq;
+};
+
+struct filter_fid_24_29 {
+ struct lu_fid ff_parent; /* stripe_idx in f_ver */
+};
+
+struct filter_fid_210 {
+ struct lu_fid ff_parent; /* stripe_idx in f_ver */
+ struct ost_layout ff_layout;
};
struct filter_fid {
- struct lu_fid ff_parent;
+ struct lu_fid ff_parent; /* stripe_idx in f_ver */
struct ost_layout ff_layout;
__u32 ff_layout_version;
__u32 ff_range; /* range of layout version that
*/
#define LMA_OLD_SIZE (sizeof(struct lustre_mdt_attrs) + 5 * sizeof(__u64))
-enum {
- LSOM_FL_VALID = 1 << 0,
+enum lustre_som_flags {
+ /* Unknow or no SoM data, must get size from OSTs. */
+ SOM_FL_UNKNOWN = 0x0000,
+ /* Known strictly correct, FLR or DoM file (SoM guaranteed). */
+ SOM_FL_STRICT = 0x0001,
+ /* Known stale - was right at some point in the past, but it is
+ * known (or likely) to be incorrect now (e.g. opened for write). */
+ SOM_FL_STALE = 0x0002,
+ /* Approximate, may never have been strictly correct,
+ * need to sync SOM data to achieve eventual consistency. */
+ SOM_FL_LAZY = 0x0004,
};
struct lustre_som_attrs {
__u32 lil_ids[0];
};
+struct ll_ioc_lease_id {
+ __u32 lil_mode;
+ __u32 lil_flags;
+ __u32 lil_count;
+ __u16 lil_mirror_id;
+ __u16 lil_padding1;
+ __u64 lil_padding2;
+ __u32 lil_ids[0];
+};
+
/*
* The ioctl naming rules:
* LL_* - works on the currently opened filehandle instead of parent dir
#endif
#define LL_IOC_FSGETXATTR FS_IOC_FSGETXATTR
#define LL_IOC_FSSETXATTR FS_IOC_FSSETXATTR
-#define LL_PROJINHERIT_FL 0x20000000
+#ifndef FS_XFLAG_PROJINHERIT
+#define FS_XFLAG_PROJINHERIT 0x00000200
+#endif
#define LL_STATFS_LMV 1
/* 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 */
+#ifndef FASYNC
+#define FASYNC 00020000 /* fcntl, for BSD compatibility */
+#endif
#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)
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_NOSYNC = 0x00000020, /* FLR: no sync for the mirror */
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 | LCME_FL_STALE | \
- LCME_FL_PREF_RW)
+ LCME_FL_PREF_RW | LCME_FL_NOSYNC)
/* The flags can be set by users at mirror creation time. */
#define LCME_USER_FLAGS (LCME_FL_PREF_RW)
+/* The flags are for mirrors */
+#define LCME_MIRROR_FLAGS (LCME_FL_NOSYNC)
+
+/* These flags have meaning when set in a default layout and will be inherited
+ * from the default/template layout set on a directory.
+ */
+#define LCME_TEMPLATE_FLAGS (LCME_FL_PREF_RW | LCME_FL_NOSYNC)
+
/* 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
__u32 lcme_offset; /* offset of component blob,
start from lov_comp_md_v1 */
__u32 lcme_size; /* size of component blob */
- __u64 lcme_padding[2];
+ __u32 lcme_layout_gen;
+ __u64 lcme_timestamp; /* snapshot time if applicable*/
+ __u32 lcme_padding_1;
} __attribute__((packed));
#define SEQ_ID_MAX 0x0000FFFF
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);
+ int size = sizeof(struct lmv_user_md);
+
+ if (lmm_magic == LMV_USER_MAGIC_SPECIFIC)
+ size += stripes * sizeof(struct lmv_user_mds_data);
+
+ return size;
}
struct ll_recreate_obj {
/* lustre-specific control commands */
#define LUSTRE_Q_INVALIDATE 0x80000b /* deprecated as of 2.4 */
#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 */
+
+/* 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_GRACE_BITS 48
+#define LQUOTA_GRACE_MASK ((1ULL << LQUOTA_GRACE_BITS) - 1)
+#define LQUOTA_GRACE_MAX LQUOTA_GRACE_MASK
+#define LQUOTA_GRACE(t) (t & LQUOTA_GRACE_MASK)
+#define LQUOTA_FLAG(t) (t >> LQUOTA_GRACE_BITS)
+#define LQUOTA_GRACE_FLAG(t, f) ((__u64)t | (__u64)f << LQUOTA_GRACE_BITS)
+
+/* different quota flags */
+
+/* the default quota flag, the corresponding quota ID will use the default
+ * quota setting, the hardlimit and softlimit of its quota record in the global
+ * quota file will be set to 0, the low 48 bits of the grace will be set to 0
+ * and high 16 bits will contain this flag (see above comment).
+ * */
+#define LQUOTA_FLAG_DEFAULT 0x0001
#define ALLQUOTA 255 /* set all quota */
static inline char *qtype_name(int qtype)
LA_KILL_SGID = 1 << 14,
LA_PROJID = 1 << 15,
LA_LAYOUT_VERSION = 1 << 16,
+ LA_LSIZE = 1 << 17,
+ LA_LBLOCKS = 1 << 18,
/**
* Attributes must be transmitted to OST objects
*/
/* MDS_FMODE_SOM 04000000 obsolete since 2.8.0 */
#define MDS_OPEN_CREATED 00000010
-#define MDS_OPEN_CROSS 00000020
+/* MDS_OPEN_CROSS 00000020 obsolete in 2.12, internal use only */
#define MDS_OPEN_CREAT 00000100
#define MDS_OPEN_EXCL 00000200
/********* Changelogs **********/
/** Changelog record types */
enum changelog_rec_type {
+ CL_NONE = -1,
CL_MARK = 0,
CL_CREATE = 1, /* namespace */
CL_MKDIR = 2, /* namespace */
return NULL;
}
-/* per-record flags */
+/* 12 bits of per-record data can be stored in the bottom of the flags */
#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_EXTRA_FLAGS = 0x8000,
- CLF_SUPPORTED = CLF_VERSION | CLF_RENAME | CLF_JOBID | CLF_EXTRA_FLAGS
+ CLF_SUPPORTED = CLF_VERSION | CLF_RENAME | CLF_JOBID |
+ CLF_EXTRA_FLAGS,
+ CLF_FLAGMASK = (1U << CLF_FLAGSHIFT) - 1,
+ CLF_VERMASK = ~CLF_FLAGMASK,
};
CLF_HSM_EVENT_L);
}
-static inline void hsm_set_cl_event(int *flags, enum hsm_event he)
+static inline void hsm_set_cl_event(enum changelog_rec_flags *clf_flags,
+ enum hsm_event he)
{
- *flags |= (he << CLF_HSM_EVENT_L);
+ *clf_flags |= (he << CLF_HSM_EVENT_L);
}
-static inline __u16 hsm_get_cl_flags(int flags)
+static inline __u16 hsm_get_cl_flags(enum changelog_rec_flags clf_flags)
{
- return CLF_GET_BITS(flags, CLF_HSM_FLAG_H, CLF_HSM_FLAG_L);
+ return CLF_GET_BITS(clf_flags, CLF_HSM_FLAG_H, CLF_HSM_FLAG_L);
}
-static inline void hsm_set_cl_flags(int *flags, int bits)
+static inline void hsm_set_cl_flags(enum changelog_rec_flags *clf_flags,
+ unsigned int bits)
{
- *flags |= (bits << CLF_HSM_FLAG_L);
+ *clf_flags |= (bits << CLF_HSM_FLAG_L);
}
-static inline int hsm_get_cl_error(int flags)
+static inline int hsm_get_cl_error(enum changelog_rec_flags clf_flags)
{
- return CLF_GET_BITS(flags, CLF_HSM_ERR_H, CLF_HSM_ERR_L);
+ return CLF_GET_BITS(clf_flags, CLF_HSM_ERR_H, CLF_HSM_ERR_L);
}
-static inline void hsm_set_cl_error(int *flags, int error)
+static inline void hsm_set_cl_error(enum changelog_rec_flags *clf_flags,
+ unsigned int error)
{
- *flags |= (error << CLF_HSM_ERR_L);
+ *clf_flags |= (error << CLF_HSM_ERR_L);
}
enum changelog_rec_extra_flags {
__u32 padding;
};
-/* Changelog extra extension to include OPEN mode. */
+/* Changelog extra extension to include low 32 bits of MDS_OPEN_* flags. */
struct changelog_ext_openmode {
__u32 cr_openflags;
};
SK_CRYPT_INVALID = -1,
SK_CRYPT_EMPTY = 0,
SK_CRYPT_AES256_CTR = 1,
- SK_CRYPT_MAX = 2,
};
enum sk_hmac_alg {
SK_HMAC_EMPTY = 0,
SK_HMAC_SHA256 = 1,
SK_HMAC_SHA512 = 2,
- SK_HMAC_MAX = 3,
};
struct sk_crypt_type {
- char *sct_name;
- size_t sct_bytes;
+ const char *sct_name;
+ int sct_type;
};
struct sk_hmac_type {
- char *sht_name;
- size_t sht_bytes;
+ const char *sht_name;
+ int sht_type;
};
enum lock_mode_user {
git://git.whamcloud.com / fs / lustre-release.git / blobdiff