#define _GNU_SOURCE
#define _FILE_OFFSET_BITS 64
#include <unistd.h>
-#if !defined(__dietlibc__) && !defined(__KLIBC__)
+#ifdef __GLIBC__
extern __off64_t lseek64 __P ((int __fd, __off64_t __offset, int __whence));
-#else
+#elif !defined(lseek64)
# if defined(__NO_STAT64) || __WORDSIZE != 32
# define lseek64 lseek
# endif
#include <sys/types.h>
#include <sys/stat.h>
+#include <stdint.h>
#include <stdlib.h>
#include <time.h>
#include <sys/time.h>
#include <errno.h>
#include <string.h>
#include <syslog.h>
+#ifdef __GLIBC__
+/* Newer glibc requires sys/sysmacros.h directly for makedev() */
+#include <sys/sysmacros.h>
+#endif
#ifdef __dietlibc__
#include <strings.h>
/* dietlibc has deprecated random and srandom!! */
#define srandom srand
#endif
+#ifdef NO_COROSYNC
+#define CS_OK 1
+typedef uint64_t cmap_handle_t;
+#else
+#include <corosync/cmap.h>
+#endif
+
+#ifndef NO_DLM
+#include <libdlm.h>
+#include <errno.h>
+#else
+#define LKF_NOQUEUE 0x00000001
+#define LKM_PWMODE 4
+#define EUNLOCK 0x10002
+
+typedef void *dlm_lshandle_t;
+
+struct dlm_lksb {
+ int sb_status;
+ uint32_t sb_lkid;
+ char sb_flags;
+ char *sb_lvbptr;
+};
+#endif
#include <linux/kdev_t.h>
/*#include <linux/fs.h> */
* and there is no standard conversion function so... */
/* And dietlibc doesn't think byteswap is ok, so.. */
/* #include <byteswap.h> */
-#define bswap_16(x) (((x) & 0x00ffU) << 8 | \
- ((x) & 0xff00U) >> 8)
-#define bswap_32(x) (((x) & 0x000000ffU) << 24 | \
- ((x) & 0xff000000U) >> 24 | \
- ((x) & 0x0000ff00U) << 8 | \
- ((x) & 0x00ff0000U) >> 8)
-#define bswap_64(x) (((x) & 0x00000000000000ffULL) << 56 | \
- ((x) & 0xff00000000000000ULL) >> 56 | \
- ((x) & 0x000000000000ff00ULL) << 40 | \
- ((x) & 0x00ff000000000000ULL) >> 40 | \
- ((x) & 0x0000000000ff0000ULL) << 24 | \
- ((x) & 0x0000ff0000000000ULL) >> 24 | \
- ((x) & 0x00000000ff000000ULL) << 8 | \
- ((x) & 0x000000ff00000000ULL) >> 8)
+#define __mdadm_bswap_16(x) (((x) & 0x00ffU) << 8 | \
+ ((x) & 0xff00U) >> 8)
+#define __mdadm_bswap_32(x) (((x) & 0x000000ffU) << 24 | \
+ ((x) & 0xff000000U) >> 24 | \
+ ((x) & 0x0000ff00U) << 8 | \
+ ((x) & 0x00ff0000U) >> 8)
+#define __mdadm_bswap_64(x) (((x) & 0x00000000000000ffULL) << 56 | \
+ ((x) & 0xff00000000000000ULL) >> 56 | \
+ ((x) & 0x000000000000ff00ULL) << 40 | \
+ ((x) & 0x00ff000000000000ULL) >> 40 | \
+ ((x) & 0x0000000000ff0000ULL) << 24 | \
+ ((x) & 0x0000ff0000000000ULL) >> 24 | \
+ ((x) & 0x00000000ff000000ULL) << 8 | \
+ ((x) & 0x000000ff00000000ULL) >> 8)
#if !defined(__KLIBC__)
#if BYTE_ORDER == LITTLE_ENDIAN
-#define __cpu_to_le16(_x) (_x)
-#define __cpu_to_le32(_x) (_x)
-#define __cpu_to_le64(_x) (_x)
-#define __le16_to_cpu(_x) (_x)
-#define __le32_to_cpu(_x) (_x)
-#define __le64_to_cpu(_x) (_x)
-
-#define __cpu_to_be16(_x) bswap_16(_x)
-#define __cpu_to_be32(_x) bswap_32(_x)
-#define __cpu_to_be64(_x) bswap_64(_x)
-#define __be16_to_cpu(_x) bswap_16(_x)
-#define __be32_to_cpu(_x) bswap_32(_x)
-#define __be64_to_cpu(_x) bswap_64(_x)
+#define __cpu_to_le16(_x) (unsigned int)(_x)
+#define __cpu_to_le32(_x) (unsigned int)(_x)
+#define __cpu_to_le64(_x) (unsigned long long)(_x)
+#define __le16_to_cpu(_x) (unsigned int)(_x)
+#define __le32_to_cpu(_x) (unsigned int)(_x)
+#define __le64_to_cpu(_x) (unsigned long long)(_x)
+
+#define __cpu_to_be16(_x) __mdadm_bswap_16(_x)
+#define __cpu_to_be32(_x) __mdadm_bswap_32(_x)
+#define __cpu_to_be64(_x) __mdadm_bswap_64(_x)
+#define __be16_to_cpu(_x) __mdadm_bswap_16(_x)
+#define __be32_to_cpu(_x) __mdadm_bswap_32(_x)
+#define __be64_to_cpu(_x) __mdadm_bswap_64(_x)
#elif BYTE_ORDER == BIG_ENDIAN
-#define __cpu_to_le16(_x) bswap_16(_x)
-#define __cpu_to_le32(_x) bswap_32(_x)
-#define __cpu_to_le64(_x) bswap_64(_x)
-#define __le16_to_cpu(_x) bswap_16(_x)
-#define __le32_to_cpu(_x) bswap_32(_x)
-#define __le64_to_cpu(_x) bswap_64(_x)
-
-#define __cpu_to_be16(_x) (_x)
-#define __cpu_to_be32(_x) (_x)
-#define __cpu_to_be64(_x) (_x)
-#define __be16_to_cpu(_x) (_x)
-#define __be32_to_cpu(_x) (_x)
-#define __be64_to_cpu(_x) (_x)
+#define __cpu_to_le16(_x) __mdadm_bswap_16(_x)
+#define __cpu_to_le32(_x) __mdadm_bswap_32(_x)
+#define __cpu_to_le64(_x) __mdadm_bswap_64(_x)
+#define __le16_to_cpu(_x) __mdadm_bswap_16(_x)
+#define __le32_to_cpu(_x) __mdadm_bswap_32(_x)
+#define __le64_to_cpu(_x) __mdadm_bswap_64(_x)
+
+#define __cpu_to_be16(_x) (unsigned int)(_x)
+#define __cpu_to_be32(_x) (unsigned int)(_x)
+#define __cpu_to_be64(_x) (unsigned long long)(_x)
+#define __be16_to_cpu(_x) (unsigned int)(_x)
+#define __be32_to_cpu(_x) (unsigned int)(_x)
+#define __be64_to_cpu(_x) (unsigned long long)(_x)
#else
# error "unknown endianness."
#endif
#endif /* __KLIBC__ */
+/*
+ * Check at compile time that something is of a particular type.
+ * Always evaluates to 1 so you may use it easily in comparisons.
+*/
+
+#define typecheck(type,x) \
+({ type __dummy; \
+ typeof(x) __dummy2; \
+ (void)(&__dummy == &__dummy2); \
+ 1; \
+})
+
+/*
+ * These inlines deal with timer wrapping correctly.
+ *
+ * time_after(a,b) returns true if the time a is after time b.
+*/
+
+#define time_after(a,b) \
+ (typecheck(unsigned int, a) && \
+ typecheck(unsigned int, b) && \
+ ((int)((b) - (a)) < 0))
+
+#define time_before(a,b) time_after(b,a)
/*
* min()/max()/clamp() macros that also do
(void) (&_max1 == &_max2); \
_max1 > _max2 ? _max1 : _max2; })
+#define ARRAY_SIZE(x) (sizeof(x)/sizeof(x[0]))
+
+extern const char Name[];
+
+struct md_bb_entry {
+ unsigned long long sector;
+ int length;
+};
+
+struct md_bb {
+ int supported;
+ int count;
+ struct md_bb_entry *entries;
+};
+
/* general information that might be extracted from a superblock */
struct mdinfo {
mdu_array_info_t array;
* for native metadata it is
* reshape_active field mirror
*/
+ int journal_device_required;
+ int journal_clean;
+
+ enum {
+ CONSISTENCY_POLICY_UNKNOWN,
+ CONSISTENCY_POLICY_NONE,
+ CONSISTENCY_POLICY_RESYNC,
+ CONSISTENCY_POLICY_BITMAP,
+ CONSISTENCY_POLICY_JOURNAL,
+ CONSISTENCY_POLICY_PPL,
+ } consistency_policy;
+
/* During reshape we can sometimes change the data_offset to avoid
* over-writing still-valid data. We need to know if there is space.
* So getinfo_super will fill in space_before and space_after in sectors.
#define MaxSector (~0ULL) /* resync/recovery complete position */
};
long bitmap_offset; /* 0 == none, 1 == a file */
+ unsigned int ppl_size;
+ int ppl_offset;
+ unsigned long long ppl_sector;
unsigned long safe_mode_delay; /* ms delay to mark clean */
int new_level, delta_disks, new_layout, new_chunk;
int errors;
int container_enough; /* flag external handlers can set to
* indicate that subarrays have not enough (-1),
* enough to start (0), or all expected disks (1) */
- char sys_name[20];
+ char sys_name[32];
struct mdinfo *devs;
struct mdinfo *next;
/* Device info for mdmon: */
int recovery_fd;
int state_fd;
+ int bb_fd;
+ int ubb_fd;
#define DS_FAULTY 1
#define DS_INSYNC 2
#define DS_WRITE_MOSTLY 4
#define DS_UNBLOCK 2048
int prev_state, curr_state, next_state;
+ /* info read from sysfs */
+ enum {
+ ARRAY_CLEAR,
+ ARRAY_INACTIVE,
+ ARRAY_SUSPENDED,
+ ARRAY_READONLY,
+ ARRAY_READ_AUTO,
+ ARRAY_CLEAN,
+ ARRAY_ACTIVE,
+ ARRAY_WRITE_PENDING,
+ ARRAY_ACTIVE_IDLE,
+ ARRAY_UNKNOWN_STATE,
+ } array_state;
+ struct md_bb bb;
};
struct createinfo {
int autof;
int mode;
int symlinks;
+ int names;
+ int bblist;
struct supertype *supertype;
};
-#define Name "mdadm"
-
enum mode {
ASSEMBLE=1,
BUILD,
Brief,
ManageOpt,
Add,
+ AddSpare,
+ AddJournal,
Remove,
Fail,
Replace,
ConfigFile,
ChunkSize,
WriteMostly,
+ FailFast,
+ NoFailFast,
Layout,
Auto,
Force,
KillOpt,
DataOffset,
ExamineBB,
+ Dump,
+ Restore,
+ Action,
+ Nodes,
+ ClusterName,
+ ClusterConfirm,
+ WriteJournal,
+ ConsistencyPolicy,
};
enum prefix_standard {
IEC
};
+enum bitmap_update {
+ NoUpdate,
+ NameUpdate,
+ NodeNumUpdate,
+};
+
+enum flag_mode {
+ FlagDefault, FlagSet, FlagClear,
+};
+
/* structures read from config file */
/* List of mddevice names and identifiers
* Identifiers can be:
int freeze_reshape;
char *backup_file;
int invalid_backup;
+ char *action;
+ int nodes;
+ char *homecluster;
};
struct shape {
int raiddisks;
int sparedisks;
+ int journaldisks;
int level;
int layout;
char *layout_str;
int assume_clean;
int write_behind;
unsigned long long size;
+ int consistency_policy;
};
/* List of device names - wildcards expanded */
* 'A' for re_add.
* Not set for names read from .config
*/
- char writemostly; /* 1 for 'set writemostly', 2 for 'clear writemostly' */
+ enum flag_mode writemostly;
+ enum flag_mode failfast;
int used; /* set when used */
long long data_offset;
struct mddev_dev *next;
int num;
} mapping_t;
-
struct mdstat_ent {
- char *dev;
- int devnum;
+ char devnm[32];
int active;
char *level;
- char *pattern; /* U or up, _ for down */
+ char *pattern; /* U for up, _ for down */
int percent; /* -1 if no resync */
int resync; /* 3 if check, 2 if reshape, 1 if resync, 0 if recovery */
int devcnt;
struct dev_member {
char *name;
struct dev_member *next;
- } *members;
+ } *members;
struct mdstat_ent *next;
};
extern struct mdstat_ent *mdstat_read(int hold, int start);
+extern void mdstat_close(void);
extern void free_mdstat(struct mdstat_ent *ms);
extern void mdstat_wait(int seconds);
extern void mdstat_wait_fd(int fd, const sigset_t *sigmask);
-extern int mddev_busy(int devnum);
+extern int mddev_busy(char *devnm);
extern struct mdstat_ent *mdstat_by_component(char *name);
-extern struct mdstat_ent *mdstat_by_subdev(char *subdev, int container);
+extern struct mdstat_ent *mdstat_by_subdev(char *subdev, char *container);
struct map_ent {
struct map_ent *next;
- int devnum;
+ char devnm[32];
char metadata[20];
int uuid[4];
int bad;
char *path;
};
-extern int map_update(struct map_ent **mpp, int devnum, char *metadata,
+extern int map_update(struct map_ent **mpp, char *devnm, char *metadata,
int uuid[4], char *path);
-extern void map_remove(struct map_ent **map, int devnum);
+extern void map_remove(struct map_ent **map, char *devnm);
extern struct map_ent *map_by_uuid(struct map_ent **map, int uuid[4]);
-extern struct map_ent *map_by_devnum(struct map_ent **map, int devnum);
+extern struct map_ent *map_by_devnm(struct map_ent **map, char *devnm);
+extern void map_free(struct map_ent *map);
extern struct map_ent *map_by_name(struct map_ent **map, char *name);
extern void map_read(struct map_ent **melp);
extern int map_write(struct map_ent *mel);
-extern void map_delete(struct map_ent **mapp, int devnum);
-extern void map_free(struct map_ent *map);
+extern void map_delete(struct map_ent **mapp, char *devnm);
extern void map_add(struct map_ent **melp,
- int devnum, char *metadata, int uuid[4], char *path);
+ char *devnm, char *metadata, int uuid[4], char *path);
extern int map_lock(struct map_ent **melp);
extern void map_unlock(struct map_ent **melp);
extern void map_fork(void);
GET_SIZE = (1 << 22),
GET_STATE = (1 << 23),
GET_ERROR = (1 << 24),
+ GET_ARRAY_STATE = (1 << 25),
+ GET_CONSISTENCY_POLICY = (1 << 26),
};
/* If fd >= 0, get the array it is open on,
- * else use devnum. >=0 -> major9. <0.....
+ * else use devnm.
*/
-extern int sysfs_open(int devnum, char *devname, char *attr);
-extern void sysfs_init(struct mdinfo *mdi, int fd, int devnum);
+extern int sysfs_open(char *devnm, char *devname, char *attr);
+extern int sysfs_init(struct mdinfo *mdi, int fd, char *devnm);
+extern void sysfs_init_dev(struct mdinfo *mdi, unsigned long devid);
extern void sysfs_free(struct mdinfo *sra);
-extern struct mdinfo *sysfs_read(int fd, int devnum, unsigned long options);
+extern struct mdinfo *sysfs_read(int fd, char *devnm, unsigned long options);
extern int sysfs_attr_match(const char *attr, const char *str);
extern int sysfs_match_word(const char *word, char **list);
extern int sysfs_set_str(struct mdinfo *sra, struct mdinfo *dev,
extern int sysfs_fd_get_ll(int fd, unsigned long long *val);
extern int sysfs_get_ll(struct mdinfo *sra, struct mdinfo *dev,
char *name, unsigned long long *val);
+extern int sysfs_fd_get_two(int fd, unsigned long long *v1, unsigned long long *v2);
+extern int sysfs_get_two(struct mdinfo *sra, struct mdinfo *dev,
+ char *name, unsigned long long *v1, unsigned long long *v2);
extern int sysfs_fd_get_str(int fd, char *val, int size);
extern int sysfs_attribute_available(struct mdinfo *sra, struct mdinfo *dev,
char *name);
extern int sysfs_set_array(struct mdinfo *info, int vers);
extern int sysfs_add_disk(struct mdinfo *sra, struct mdinfo *sd, int resume);
extern int sysfs_disk_to_scsi_id(int fd, __u32 *id);
-extern int sysfs_unique_holder(int devnum, long rdev);
+extern int sysfs_unique_holder(char *devnm, long rdev);
extern int sysfs_freeze_array(struct mdinfo *sra);
-extern int load_sys(char *path, char *buf);
+extern int sysfs_wait(int fd, int *msec);
+extern int load_sys(char *path, char *buf, int len);
extern int reshape_prepare_fdlist(char *devname,
struct mdinfo *sra,
int raid_disks,
long blocks,
int *fdlist,
unsigned long long *offsets,
+ char *sysfs_name,
int restart);
extern unsigned long compute_backup_blocks(int nchunk, int ochunk,
unsigned int ndata, unsigned int odata);
+extern char *locate_backup(char *name);
+extern char *make_backup(char *name);
extern int save_stripes(int *source, unsigned long long *offsets,
int raid_disks, int chunk_size, int level, int layout,
extern char *map_num(mapping_t *map, int num);
extern int map_name(mapping_t *map, char *name);
extern mapping_t r5layout[], r6layout[], pers[], modes[], faultylayout[];
+extern mapping_t consistency_policies[], sysfs_array_states[];
extern char *map_dev_preferred(int major, int minor, int create,
char *prefer);
struct active_array;
struct metadata_update;
-
/* 'struct reshape' records the intermediate states of
* a general reshape.
* The starting geometry is converted to the 'before' geometry
* This will be a multiple of the stripe size in each of the
* 'before' and 'after' geometries.
* If 'blocks' is 0, no restriping is necessary.
+ * 'min_offset_change' is the minimum change to data_offset to
+ * allow the reshape to happen. It is at least the larger of
+ * the old and new chunk sizes, and typically the same as 'blocks'
+ * divided by number of data disks.
*/
struct reshape {
int level;
int data_disks;
} before, after;
unsigned long long backup_blocks;
+ unsigned long long min_offset_change;
unsigned long long stripes; /* number of old stripes that comprise 'blocks'*/
unsigned long long new_size; /* New size of array in sectors */
};
-/* A superswitch provides entry point the a metadata handler.
+/* A superswitch provides entry point to a metadata handler.
*
- * The super_switch primarily operates on some "metadata" that
+ * The superswitch primarily operates on some "metadata" that
* is accessed via the 'supertype'.
* This metadata has one of three possible sources.
* 1/ It is read from a single device. In this case it may not completely
void (*brief_examine_subarrays)(struct supertype *st, int verbose);
void (*export_examine_super)(struct supertype *st);
int (*examine_badblocks)(struct supertype *st, int fd, char *devname);
+ int (*copy_metadata)(struct supertype *st, int from, int to);
/* Used to report details of an active array.
* ->load_super was possibly given a 'component' string.
* linear-grow-update - now change the size of the array.
* writemostly - set the WriteMostly1 bit in the superblock devflags
* readwrite - clear the WriteMostly1 bit in the superblock devflags
+ * failfast - set the FailFast1 bit in the superblock
+ * nofailfast - clear the FailFast1 bit
+ * no-bitmap - clear any record that a bitmap is present.
+ * bbl - add a bad-block-log if possible
+ * no-bbl - remove any bad-block-log is it is empty.
+ * force-no-bbl - remove any bad-block-log even if empty.
+ * revert-reshape - If a reshape is in progress, modify metadata so
+ * it will resume going in the opposite direction.
*/
int (*update_super)(struct supertype *st, struct mdinfo *info,
char *update,
* metadata.
*/
int (*init_super)(struct supertype *st, mdu_array_info_t *info,
- unsigned long long size, char *name,
+ struct shape *s, char *name,
char *homehost, int *uuid,
unsigned long long data_offset);
/* Write all metadata for this array.
*/
int (*write_init_super)(struct supertype *st);
+ /* Check if metadata read from one device is compatible with an array,
+ * used when assembling an array, or pseudo-assembling was with
+ * "--examine --brief"
+ * If "st" has not yet been loaded the superblock from, "tst" is
+ * moved in, otherwise the superblock in 'st' is compared with
+ * 'tst'.
+ */
int (*compare_super)(struct supertype *st, struct supertype *tst);
+ /* Load metadata from a single device. If 'devname' is not NULL
+ * print error messages as appropriate */
int (*load_super)(struct supertype *st, int fd, char *devname);
+ /* 'fd' is a 'container' md array - load array metadata from the
+ * whole container.
+ */
int (*load_container)(struct supertype *st, int fd, char *devname);
+ /* If 'arg' is a valid name of this metadata type, allocate and
+ * return a 'supertype' for the particular minor version */
struct supertype * (*match_metadata_desc)(char *arg);
+ /* If a device has the given size, and the data_offset has been
+ * requested - work out how much space is available for data.
+ * This involves adjusting for reserved space (e.g. bitmaps)
+ * and for any rounding.
+ * 'mdadm' only calls this for existing arrays where a possible
+ * spare is being added. However some super-handlers call it
+ * internally from validate_geometry when creating an array.
+ */
__u64 (*avail_size)(struct supertype *st, __u64 size,
unsigned long long data_offset);
+ /* This is similar to 'avail_size' in purpose, but is used for
+ * containers for which there is no 'component size' to compare.
+ * This reports that whole-device size which is a minimum
+ */
unsigned long long (*min_acceptable_spare_size)(struct supertype *st);
+ /* Find somewhere to put a bitmap - possibly auto-size it - and
+ * update the metadata to record this. The array may be newly
+ * created, in which case data_size may be updated, or it might
+ * already exist. Metadata handler can know if init_super
+ * has been called, but not write_init_super.
+ * 0: Success
+ * -Exxxx: On error
+ */
int (*add_internal_bitmap)(struct supertype *st, int *chunkp,
int delay, int write_behind,
unsigned long long size, int may_change, int major);
- void (*locate_bitmap)(struct supertype *st, int fd);
- int (*write_bitmap)(struct supertype *st, int fd);
+ /* Seek 'fd' to start of write-intent-bitmap. Must be an
+ * md-native format bitmap
+ */
+ int (*locate_bitmap)(struct supertype *st, int fd, int node_num);
+ /* if add_internal_bitmap succeeded for existing array, this
+ * writes it out.
+ */
+ int (*write_bitmap)(struct supertype *st, int fd, enum bitmap_update update);
+ /* Free the superblock and any other allocated data */
void (*free_super)(struct supertype *st);
/* validate_geometry is called with an st returned by
* match_metadata_desc.
- * It should check that the geometry described in compatible with
+ * It should check that the geometry described is compatible with
* the metadata type. It will be called repeatedly as devices
* added to validate changing size and new devices. If there are
* inter-device dependencies, it should record sufficient details
* 1: everything is OK
* 0: not OK for some reason - if 'verbose', then error was reported.
* -1: st->sb was NULL, 'subdev' is a member of a container of this
- * types, but array is not acceptable for some reason
+ * type, but array is not acceptable for some reason
* message was reported even if verbose is 0.
*/
int (*validate_geometry)(struct supertype *st, int level, int layout,
int *chunk, unsigned long long size,
unsigned long long data_offset,
char *subdev, unsigned long long *freesize,
- int verbose);
+ int consistency_policy, int verbose);
+ /* Return a linked list of 'mdinfo' structures for all arrays
+ * in the container. For non-containers, it is like
+ * getinfo_super with an allocated mdinfo.*/
struct mdinfo *(*container_content)(struct supertype *st, char *subarray);
/* query the supertype for default geometry */
void (*default_geometry)(struct supertype *st, int *level, int *layout, int *chunk); /* optional */
* (in a->resync_start).
* resync status is really irrelevant if the array is not consistent,
* but some metadata (DDF!) have a place to record the distinction.
- * If 'consistent' is '2', then the array can mark it dirty if a
+ * If 'consistent' is '2', then the array can mark it dirty if a
* resync/recovery/whatever is required, or leave it clean if not.
* Return value is 0 dirty (not consistent) and 1 if clean.
* it is only really important if consistent is passed in as '2'.
void (*sync_metadata)(struct supertype *st);
void (*process_update)(struct supertype *st,
struct metadata_update *update);
- void (*prepare_update)(struct supertype *st,
+ /* Prepare updates allocates extra memory that might be
+ * needed. If the update cannot be understood, return 0.
+ */
+ int (*prepare_update)(struct supertype *st,
struct metadata_update *update);
/* activate_spare will check if the array is degraded and, if it
/* for external backup area */
int (*recover_backup)(struct supertype *st, struct mdinfo *info);
+ /* validate container after assemble */
+ int (*validate_container)(struct mdinfo *info);
+
+ /* write initial empty PPL on device */
+ int (*write_init_ppl)(struct supertype *st, struct mdinfo *info, int fd);
+
+ /* validate ppl before assemble */
+ int (*validate_ppl)(struct supertype *st, struct mdinfo *info,
+ struct mdinfo *disk);
+
+ /* records new bad block in metadata */
+ int (*record_bad_block)(struct active_array *a, int n,
+ unsigned long long sector, int length);
+
+ /* clears bad block from metadata */
+ int (*clear_bad_block)(struct active_array *a, int n,
+ unsigned long long sector, int length);
+
+ /* get list of bad blocks from metadata */
+ struct md_bb *(*get_bad_blocks)(struct active_array *a, int n);
+
int swapuuid; /* true if uuid is bigending rather than hostendian */
int external;
const char *name; /* canonical metadata name */
struct superswitch *ss;
int minor_version;
int max_devs;
- int container_dev; /* devnum of container */
+ char container_devnm[32]; /* devnm of container */
void *sb;
void *info;
+ void *other; /* Hack used to convert v0.90 to v1.0 */
+ unsigned long long devsize;
+ unsigned long long data_offset; /* used by v1.x only */
int ignore_hw_compat; /* used to inform metadata handlers that it should ignore
HW/firmware related incompatability to load metadata.
Used when examining metadata to display content of disk
/* extra stuff used by mdmon */
struct active_array *arrays;
int sock; /* listen to external programs */
- int devnum;
- char *devname; /* e.g. md0. This appears in metadata_verison:
- * external:/md0/12
- */
+ char devnm[32]; /* e.g. md0. This appears in metadata_version:
+ * external:/md0/12
+ */
int devcnt;
int retry_soon;
+ int nodes;
+ char *cluster_name;
struct mdinfo *devs;
}
extern struct supertype *dup_super(struct supertype *st);
extern int get_dev_size(int fd, char *dname, unsigned long long *sizep);
+extern int get_dev_sector_size(int fd, char *dname, unsigned int *sectsizep);
extern int must_be_container(int fd);
extern int dev_size_from_id(dev_t id, unsigned long long *size);
void wait_for(char *dev, int fd);
extern struct dev_policy *path_policy(char *path, char *type);
extern struct dev_policy *disk_policy(struct mdinfo *disk);
-extern struct dev_policy *devnum_policy(int dev);
+extern struct dev_policy *devid_policy(int devid);
extern void dev_policy_free(struct dev_policy *p);
//extern void pol_new(struct dev_policy **pol, char *name, char *val, char *metadata);
const char *metadata);
extern struct domainlist *domain_from_array(struct mdinfo *mdi,
const char *metadata);
-extern void domainlist_add_dev(struct domainlist **dom, int devnum,
+extern void domainlist_add_dev(struct domainlist **dom, int devid,
const char *metadata);
extern void domain_free(struct domainlist *dl);
extern void domain_merge(struct domainlist **domp, struct dev_policy *pol,
extern int add_dev(const char *name, const struct stat *stb, int flag, struct FTW *s);
-
extern int Manage_ro(char *devname, int fd, int readonly);
-extern int Manage_runstop(char *devname, int fd, int runstop, int quiet,
- int will_retry);
+extern int Manage_run(char *devname, int fd, struct context *c);
+extern int Manage_stop(char *devname, int fd, int quiet,
+ int will_retry);
extern int Manage_subdevs(char *devname, int fd,
struct mddev_dev *devlist, int verbose, int test,
char *update, int force);
int *fdlist, int cnt, char *backup_file, int verbose);
extern int Grow_continue(int mdfd, struct supertype *st,
struct mdinfo *info, char *backup_file,
- int freeze_reshape);
+ int forked, int freeze_reshape);
+extern int Grow_consistency_policy(char *devname, int fd,
+ struct context *c, struct shape *s);
extern int restore_backup(struct supertype *st,
struct mdinfo *content,
int working_disks,
int spares,
- char *backup_file,
+ char **backup_filep,
int verbose);
extern int Grow_continue_command(char *devname, int fd,
char *backup_file, int verbose);
extern int Update_subarray(char *dev, char *subarray, char *update, struct mddev_ident *ident, int quiet);
extern int Wait(char *dev);
extern int WaitClean(char *dev, int sock, int verbose);
+extern int SetAction(char *dev, char *action);
-extern int Incremental(char *devname, struct context *c,
+extern int Incremental(struct mddev_dev *devlist, struct context *c,
struct supertype *st);
extern void RebuildMap(void);
-extern int IncrementalScan(int verbose);
+extern int IncrementalScan(struct context *c, char *devnm);
extern int IncrementalRemove(char *devname, char *path, int verbose);
extern int CreateBitmap(char *filename, int force, char uuid[16],
unsigned long chunksize, unsigned long daemon_sleep,
extern int ExamineBitmap(char *filename, int brief, struct supertype *st);
extern int Write_rules(char *rule_name);
extern int bitmap_update_uuid(int fd, int *uuid, int swap);
-extern unsigned long bitmap_sectors(struct bitmap_super_s *bsb);
-extern int md_get_version(int fd);
+/* calculate the size of the bitmap given the array size and bitmap chunksize */
+static inline unsigned long long
+bitmap_bits(unsigned long long array_size, unsigned long chunksize)
+{
+ return (array_size * 512 + chunksize - 1) / chunksize;
+}
+
+extern int Dump_metadata(char *dev, char *dir, struct context *c,
+ struct supertype *st);
+extern int Restore_metadata(char *dev, char *dir, struct context *c,
+ struct supertype *st, int only);
+
+int md_array_active(int fd);
+int md_get_array_info(int fd, struct mdu_array_info_s *array);
+int md_set_array_info(int fd, struct mdu_array_info_s *array);
+int md_get_disk_info(int fd, struct mdu_disk_info_s *disk);
extern int get_linux_version(void);
extern int mdadm_version(char *version);
extern unsigned long long parse_size(char *size);
extern int parse_layout_10(char *layout);
extern int parse_layout_faulty(char *layout);
extern long parse_num(char *num);
+extern int parse_cluster_confirm_arg(char *inp, char **devname, int *slot);
extern int check_ext2(int fd, char *name);
extern int check_reiser(int fd, char *name);
extern int check_raid(int fd, char *name);
unsigned long long size);
extern int get_mdp_major(void);
+extern int get_maj_min(char *dev, int *major, int *minor);
extern int dev_open(char *dev, int flags);
-extern int open_dev(int devnum);
-extern int open_dev_flags(int devnum, int flags);
-extern int open_dev_excl(int devnum);
+extern int open_dev(char *devnm);
+extern void reopen_mddev(int mdfd);
+extern int open_dev_flags(char *devnm, int flags);
+extern int open_dev_excl(char *devnm);
extern int is_standard(char *dev, int *nump);
extern int same_dev(char *one, char *two);
extern int compare_paths (char* path1,char* path2);
+extern void enable_fds(int devices);
extern int parse_auto(char *str, char *msg, int config);
extern struct mddev_ident *conf_get_ident(char *dev);
extern char *conf_get_mailfrom(void);
extern char *conf_get_program(void);
extern char *conf_get_homehost(int *require_homehostp);
+extern char *conf_get_homecluster(void);
extern char *conf_line(FILE *file);
extern char *conf_word(FILE *file, int allow_key);
extern void print_quoted(char *str);
extern void print_escape(char *str);
extern int use_udev(void);
+extern unsigned long GCD(unsigned long a, unsigned long b);
extern int conf_name_is_free(char *name);
extern int conf_verify_devnames(struct mddev_ident *array_list);
extern int devname_matches(char *name, char *match);
extern unsigned long calc_csum(void *super, int bytes);
extern int enough(int level, int raid_disks, int layout, int clean,
char *avail);
-extern int enough_fd(int fd);
extern int ask(char *mesg);
extern unsigned long long get_component_size(int fd);
extern void remove_partitions(int fd);
extern int assemble_container_content(struct supertype *st, int mdfd,
struct mdinfo *content,
struct context *c,
- char *chosen_name);
+ char *chosen_name, int *result);
+#define INCR_NO 1
+#define INCR_UNSAFE 2
+#define INCR_ALREADY 4
+#define INCR_YES 8
extern struct mdinfo *container_choose_spares(struct supertype *st,
unsigned long long min_size,
struct domainlist *domlist,
struct mdinfo *sra, struct mdinfo *info);
extern int remove_disk(int mdfd, struct supertype *st,
struct mdinfo *sra, struct mdinfo *info);
+extern int hot_remove_disk(int mdfd, unsigned long dev, int force);
+extern int sys_hot_remove_disk(int statefd, int force);
extern int set_array_info(int mdfd, struct supertype *st, struct mdinfo *info);
unsigned long long min_recovery_start(struct mdinfo *array);
extern char *human_size_brief(long long bytes, int prefix);
extern void print_r10_layout(int layout);
-#define NoMdDev (1<<23)
-extern int find_free_devnum(int use_partitions);
+extern char *find_free_devnm(int use_partitions);
extern void put_md_name(char *name);
-extern char *get_md_name(int dev);
+extern char *devid2kname(int devid);
+extern char *devid2devnm(dev_t devid);
+extern dev_t devnm2devid(char *devnm);
+extern char *get_md_name(char *devnm);
extern char DefaultConfFile[];
#define METADATA 3
extern int open_mddev(char *dev, int report_errors);
extern int open_container(int fd);
+extern int metadata_container_matches(char *metadata, char *devnm);
+extern int metadata_subdev_matches(char *metadata, char *devnm);
extern int is_container_member(struct mdstat_ent *ent, char *devname);
extern int is_subarray_active(char *subarray, char *devname);
extern int open_subarray(char *dev, char *subarray, struct supertype *st, int quiet);
extern struct superswitch *version_to_superswitch(char *vers);
-extern int mdmon_running(int devnum);
-extern int mdmon_pid(int devnum);
+extern int mdmon_running(char *devnm);
+extern int mdmon_pid(char *devnm);
extern int check_env(char *name);
extern __u32 random32(void);
-extern int start_mdmon(int devnum);
+extern void random_uuid(__u8 *buf);
+extern int start_mdmon(char *devnm);
extern int child_monitor(int afd, struct mdinfo *sra, struct reshape *reshape,
struct supertype *st, unsigned long stripes,
int dests, int *destfd, unsigned long long *destoffsets);
void abort_reshape(struct mdinfo *sra);
-extern char *devnum2devname(int num);
-extern void fmt_devname(char *name, int num);
-extern int devname2devnum(char *name);
-extern int stat2devnum(struct stat *st);
-extern int fd2devnum(int fd);
+void *super1_make_v0(struct supertype *st, struct mdinfo *info, mdp_super_t *sb0);
-static inline int dev2major(int d)
-{
- if (d >= 0)
- return MD_MAJOR;
- else
- return get_mdp_major();
-}
+extern char *stat2kname(struct stat *st);
+extern char *fd2kname(int fd);
+extern char *stat2devnm(struct stat *st);
+extern char *fd2devnm(int fd);
-static inline int dev2minor(int d)
-{
- if (d >= 0)
- return d;
- return (-1-d) << MdpMinorShift;
-}
+extern int in_initrd(void);
+
+struct cmap_hooks {
+ void *cmap_handle; /* corosync lib related */
+
+ int (*initialize)(cmap_handle_t *handle);
+ int (*get_string)(cmap_handle_t handle,
+ const char *string,
+ char **name);
+ int (*finalize)(cmap_handle_t handle);
+};
+
+extern void set_cmap_hooks(void);
+extern void set_hooks(void);
+
+struct dlm_hooks {
+ void *dlm_handle; /* dlm lib related */
+
+ dlm_lshandle_t (*create_lockspace)(const char *name,
+ unsigned int mode);
+ int (*release_lockspace)(const char *name, dlm_lshandle_t ls,
+ int force);
+ int (*ls_lock)(dlm_lshandle_t lockspace, uint32_t mode,
+ struct dlm_lksb *lksb, uint32_t flags,
+ const void *name, unsigned int namelen,
+ uint32_t parent, void (*astaddr) (void *astarg),
+ void *astarg, void (*bastaddr) (void *astarg),
+ void *range);
+ int (*ls_unlock)(dlm_lshandle_t lockspace, uint32_t lkid,
+ uint32_t flags, struct dlm_lksb *lksb,
+ void *astarg);
+ int (*ls_get_fd)(dlm_lshandle_t ls);
+ int (*dispatch)(int fd);
+};
+
+extern int get_cluster_name(char **name);
+extern int dlm_funs_ready(void);
+extern int cluster_get_dlmlock(int *lockid);
+extern int cluster_release_dlmlock(int lockid);
+extern void set_dlm_hooks(void);
#define _ROUND_UP(val, base) (((val) + (base) - 1) & ~(base - 1))
#define ROUND_UP(val, base) _ROUND_UP(val, (typeof(val))(base))
static inline int is_subarray(char *vers)
{
/* The version string for a 'subarray' (an array in a container)
- * is
+ * is
* /containername/componentname for normal read-write arrays
* -containername/componentname for arrays which mdmon must not
* reconfigure. They might be read-only
#ifdef DEBUG
#define dprintf(fmt, arg...) \
+ fprintf(stderr, "%s: %s: "fmt, Name, __func__, ##arg)
+#define dprintf_cont(fmt, arg...) \
fprintf(stderr, fmt, ##arg)
#else
#define dprintf(fmt, arg...) \
+ ({ if (0) fprintf(stderr, "%s: %s: " fmt, Name, __func__, ##arg); 0; })
+#define dprintf_cont(fmt, arg...) \
({ if (0) fprintf(stderr, fmt, ##arg); 0; })
#endif
#include <assert.h>
return ret;
}
-#define pr_err(fmt ...) fprintf(stderr, Name ": " fmt)
+#ifdef DEBUG
+#define pr_err(fmt, args...) fprintf(stderr, "%s: %s: "fmt, Name, __func__, ##args)
+#else
+#define pr_err(fmt, args...) fprintf(stderr, "%s: "fmt, Name, ##args)
+#endif
#define cont_err(fmt ...) fprintf(stderr, " " fmt)
void *xmalloc(size_t len);
#define LEVEL_CONTAINER (-100)
#define LEVEL_UNSUPPORTED (-200)
+/* the kernel does know about this one ... */
+#define LEVEL_NONE (-1000000)
/* faulty stuff */
#define ModeMask 0x1f
#define ModeShift 5
-
#ifdef __TINYC__
#undef minor
#undef major
#define ALGORITHM_ROTATING_N_RESTART 9 /* DDF PRL=6 RLQ=2 */
#define ALGORITHM_ROTATING_N_CONTINUE 10 /*DDF PRL=6 RLQ=3 */
-
/* For every RAID5 algorithm we define a RAID6 algorithm
* with exactly the same layout for data and parity, and
* with the Q block always on the last device (N-1).