/*
* mdadm - manage Linux "md" devices aka RAID arrays.
*
- * Copyright (C) 2001-2006 Neil Brown <neilb@suse.de>
+ * Copyright (C) 2001-2009 Neil Brown <neilb@suse.de>
*
*
* This program is free software; you can redistribute it and/or modify
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Author: Neil Brown
- * Email: <neilb@cse.unsw.edu.au>
- * Paper: Neil Brown
- * School of Computer Science and Engineering
- * The University of New South Wales
- * Sydney, 2052
- * Australia
+ * Email: <neilb@suse.de>
*/
#define _GNU_SOURCE
#define BLKGETSIZE64 _IOR(0x12,114,size_t) /* return device size in bytes (u64 *arg) */
#endif
+#define DEFAULT_CHUNK 512
#define DEFAULT_BITMAP_CHUNK 4096
#define DEFAULT_BITMAP_DELAY 5
#define DEFAULT_MAX_WRITE_BEHIND 256
+/* MAP_DIR should be somewhere that persists across the pivotroot
+ * from early boot to late boot.
+ * Currently /dev seems to be the only option on most distros.
+ */
+#ifndef MAP_DIR
+#define MAP_DIR "/dev/.mdadm"
+#endif /* MAP_DIR */
+/* MAP_FILE is what we name the map file we put in MAP_DIR, in case you
+ * want something other than the default of "map"
+ */
+#ifndef MAP_FILE
+#define MAP_FILE "map"
+#endif /* MAP_FILE */
+/* MDMON_DIR is where pid and socket files used for communicating
+ * with mdmon normally live. It *should* be /var/run, but when
+ * mdmon is needed at early boot then it needs to write there prior
+ * to /var/run being mounted read/write, and it also then needs to
+ * persist beyond when /var/run is mounter read-only. So, to be
+ * safe, the default is somewhere that is read/write early in the
+ * boot process and stays up as long as possible during shutdown.
+ */
+#ifndef MDMON_DIR
+#define MDMON_DIR "/dev/.mdadm/"
+#endif /* MDMON_DIR */
+
+/* FAILED_SLOTS is where to save files storing recent removal of array
+ * member in order to allow future reuse of disk inserted in the same
+ * slot for array recovery
+ */
+#ifndef FAILED_SLOTS_DIR
+#define FAILED_SLOTS_DIR "/dev/.mdadm/failed-slots"
+#endif /* FAILED_SLOTS */
+
#include "md_u.h"
#include "md_p.h"
#include "bitmap.h"
#endif /* __KLIBC__ */
+/*
+ * min()/max()/clamp() macros that also do
+ * strict type-checking.. See the
+ * "unnecessary" pointer comparison.
+ */
+#define min(x, y) ({ \
+ typeof(x) _min1 = (x); \
+ typeof(y) _min2 = (y); \
+ (void) (&_min1 == &_min2); \
+ _min1 < _min2 ? _min1 : _min2; })
+
+#define max(x, y) ({ \
+ typeof(x) _max1 = (x); \
+ typeof(y) _max2 = (y); \
+ (void) (&_max1 == &_max2); \
+ _max1 > _max2 ? _max1 : _max2; })
/* general information that might be extracted from a superblock */
struct mdinfo {
unsigned long long component_size; /* same as array.size, except in
* sectors and up to 64bits.
*/
+ unsigned long long custom_array_size; /* size for non-default sized
+ * arrays (in sectors)
+ */
int reshape_active;
unsigned long long reshape_progress;
- unsigned long long resync_start;
+ union {
+ unsigned long long resync_start; /* per-array resync position */
+ unsigned long long recovery_start; /* per-device rebuild position */
+ #define MaxSector (~0ULL) /* resync/recovery complete position */
+ };
unsigned long safe_mode_delay; /* ms delay to mark clean */
int new_level, delta_disks, new_layout, new_chunk;
int errors;
- int cache_size; /* size of raid456 stripe cache*/
+ unsigned long cache_size; /* size of raid456 stripe cache*/
int mismatch_cnt;
char text_version[50];
+ void *update_private; /* for passing metadata-format
+ * specific update data
+ * between successive calls to
+ * update_super()
+ */
int container_member; /* for assembling external-metatdata arrays
* This is to be used internally by metadata
* handler only */
-
+ 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];
struct mdinfo *devs;
struct mdinfo *next;
/* Device info for mdmon: */
+ int recovery_fd;
int state_fd;
#define DS_FAULTY 1
#define DS_INSYNC 2
Help_manage[], Help_misc[], Help_monitor[], Help_config[];
/* for option that don't have short equivilents, we assign arbitrary
- * small numbers. '1' means an undecorated option, so we start at '2'.
+ * numbers later than any 'short' character option.
*/
enum special_options {
- AssumeClean = 2,
+ AssumeClean = 300,
BitmapChunk,
WriteBehind,
ReAdd,
Symlinks,
AutoDetect,
Waitclean,
+ DetailPlatform,
+ KillSubarray,
+ UpdateSubarray,
+ IncrementalPath,
+ NoSharing,
+ HelpOptions,
+ Brief,
+ ManageOpt,
+ Add,
+ Remove,
+ Fail,
+ MiscOpt,
+ WaitOpt,
+ ConfigFile,
+ ChunkSize,
+ WriteMostly,
+ Layout,
+ Auto,
+ Force,
+ SuperMinor,
+ EMail,
+ ProgramOpt,
+ Increment,
+ Fork,
+ Bitmap,
+ RebuildMapOpt,
+ InvalidBackup,
+ UdevRules,
};
/* structures read from config file */
* devices is considered
*/
#define UnSet (0xfffe)
-typedef struct mddev_ident_s {
+struct mddev_ident {
char *devname;
int uuid_set;
int uuid[4];
char name[33];
- unsigned int super_minor;
+ int super_minor;
char *devices; /* comma separated list of device
* names with wild cards
*/
int level;
- unsigned int raid_disks;
- unsigned int spare_disks;
+ int raid_disks;
+ int spare_disks;
struct supertype *st;
int autof; /* 1 for normal, 2 for partitioned */
char *spare_group;
char *bitmap_file;
int bitmap_fd;
- char *container; /* /dev/whatever name of container. You
- * would expect this to be the 'devname'
+ char *container; /* /dev/whatever name of container, or
+ * uuid of container. You would expect
+ * this to be the 'devname' or UUID
* of some other entry.
*/
char *member; /* subarray within a container */
- struct mddev_ident_s *next;
-} *mddev_ident_t;
+ struct mddev_ident *next;
+ union {
+ /* fields needed by different users of this structure */
+ int assembled; /* set when assembly succeeds */
+ };
+};
/* List of device names - wildcards expanded */
-typedef struct mddev_dev_s {
+struct mddev_dev {
char *devname;
- char disposition; /* 'a' for add, 'r' for remove, 'f' for fail.
+ int disposition; /* 'a' for add, 'r' for remove, 'f' for fail.
* Not set for names read from .config
*/
char writemostly; /* 1 for 'set writemostly', 2 for 'clear writemostly' */
char re_add;
char used; /* set when used */
- struct mddev_dev_s *next;
-} *mddev_dev_t;
+ struct mddev_dev *next;
+};
typedef struct mapping {
char *name;
char *level;
char *pattern; /* U or up, _ for down */
int percent; /* -1 if no resync */
- int resync; /* 1 if resync, 0 if recovery */
+ int resync; /* 3 if check, 2 if reshape, 1 if resync, 0 if recovery */
int devcnt;
int raid_disks;
- int chunk_size;
char * metadata_version;
+ struct dev_member {
+ char *name;
+ struct dev_member *next;
+ } *members;
struct mdstat_ent *next;
};
extern void mdstat_wait(int seconds);
extern void mdstat_wait_fd(int fd, const sigset_t *sigmask);
extern int mddev_busy(int devnum);
+extern struct mdstat_ent *mdstat_by_component(char *name);
+extern struct mdstat_ent *mdstat_by_subdev(char *subdev, int container);
struct map_ent {
struct map_ent *next;
int devnum;
char metadata[20];
int uuid[4];
+ int bad;
char *path;
};
extern int map_update(struct map_ent **mpp, int devnum, char *metadata,
int uuid[4], char *path);
+extern void map_remove(struct map_ent **map, int devnum);
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_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_add(struct map_ent **melp,
int devnum, char *metadata, int uuid[4], char *path);
+extern int map_lock(struct map_ent **melp);
+extern void map_unlock(struct map_ent **melp);
/* various details can be requested */
-#define GET_LEVEL 1
-#define GET_LAYOUT 2
-#define GET_COMPONENT 4
-#define GET_CHUNK 8
-#define GET_CACHE 16
-#define GET_MISMATCH 32
-#define GET_VERSION 64
-#define GET_DISKS 128
-#define GET_DEGRADED 256
-#define GET_SAFEMODE 512
-
-#define GET_DEVS 1024 /* gets role, major, minor */
-#define GET_OFFSET 2048
-#define GET_SIZE 4096
-#define GET_STATE 8192
-#define GET_ERROR 16384
+enum sysfs_read_flags {
+ GET_LEVEL = (1 << 0),
+ GET_LAYOUT = (1 << 1),
+ GET_COMPONENT = (1 << 2),
+ GET_CHUNK = (1 << 3),
+ GET_CACHE = (1 << 4),
+ GET_MISMATCH = (1 << 5),
+ GET_VERSION = (1 << 6),
+ GET_DISKS = (1 << 7),
+ GET_DEGRADED = (1 << 8),
+ GET_SAFEMODE = (1 << 9),
+ GET_DEVS = (1 << 10), /* gets role, major, minor */
+ GET_OFFSET = (1 << 11),
+ GET_SIZE = (1 << 12),
+ GET_STATE = (1 << 13),
+ GET_ERROR = (1 << 14),
+};
/* If fd >= 0, get the array it is open on,
* else use devnum. >=0 -> major9. <0.....
char *name, char *val);
extern int sysfs_set_num(struct mdinfo *sra, struct mdinfo *dev,
char *name, unsigned long long val);
+extern int sysfs_uevent(struct mdinfo *sra, char *event);
+extern int sysfs_get_fd(struct mdinfo *sra, struct mdinfo *dev,
+ char *name);
+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_str(int fd, char *val, int size);
+extern int sysfs_attribute_available(struct mdinfo *sra, struct mdinfo *dev,
+ char *name);
+extern int sysfs_get_str(struct mdinfo *sra, struct mdinfo *dev,
+ char *name, char *val, int size);
extern int sysfs_set_safemode(struct mdinfo *sra, unsigned long ms);
extern int sysfs_set_array(struct mdinfo *info, int vers);
-extern int sysfs_add_disk(struct mdinfo *sra, struct mdinfo *sd);
+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_freeze_array(struct mdinfo *sra);
extern int load_sys(char *path, char *buf);
-
+extern int reshape_prepare_fdlist(char *devname,
+ struct mdinfo *sra,
+ int raid_disks,
+ int nrdisks,
+ unsigned long blocks,
+ char *backup_file,
+ int *fdlist,
+ unsigned long long *offsets);
+extern void reshape_free_fdlist(int *fdlist,
+ unsigned long long *offsets,
+ int size);
+extern int reshape_open_backup_file(char *backup,
+ int fd,
+ char *devname,
+ long blocks,
+ int *fdlist,
+ unsigned long long *offsets,
+ int restart);
+extern unsigned long compute_backup_blocks(int nchunk, int ochunk,
+ unsigned int ndata, unsigned int odata);
extern int save_stripes(int *source, unsigned long long *offsets,
int raid_disks, int chunk_size, int level, int layout,
int nwrites, int *dest,
- unsigned long long start, unsigned long long length);
+ unsigned long long start, unsigned long long length,
+ char *buf);
extern int restore_stripes(int *dest, unsigned long long *offsets,
int raid_disks, int chunk_size, int level, int layout,
int source, unsigned long long read_offset,
extern char *map_num(mapping_t *map, int num);
extern int map_name(mapping_t *map, char *name);
-extern mapping_t r5layout[], pers[], modes[], faultylayout[];
+extern mapping_t r5layout[], r6layout[], pers[], modes[], faultylayout[];
extern char *map_dev(int major, int minor, int create);
struct active_array;
struct metadata_update;
+
+/* 'struct reshape' records the intermediate states
+ * a general reshape.
+ * The starting geometry is converted to the 'before' geometry
+ * by at most an atomic level change. They could be the same.
+ * Similarly the 'after' geometry is converted to the final
+ * geometry by at most a level change.
+ * Note that 'before' and 'after' must have the same level.
+ * 'blocks' is the minimum number of sectors for a reshape unit.
+ * 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.
+ */
+struct reshape {
+ int level;
+ int parity; /* number of parity blocks/devices */
+ struct {
+ int layout;
+ int data_disks;
+ } before, after;
+ unsigned long long backup_blocks;
+ 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.
*
* The super_switch primarily operates on some "metadata" that
* device. ->load_super has been called.
*/
void (*examine_super)(struct supertype *st, char *homehost);
- void (*brief_examine_super)(struct supertype *st);
+ void (*brief_examine_super)(struct supertype *st, int verbose);
+ void (*brief_examine_subarrays)(struct supertype *st, int verbose);
void (*export_examine_super)(struct supertype *st);
/* Used to report details of an active array.
void (*brief_detail_super)(struct supertype *st);
void (*export_detail_super)(struct supertype *st);
+ /* Optional: platform hardware / firmware details */
+ int (*detail_platform)(int verbose, int enumerate_only);
+
/* Used:
* to get uuid to storing in bitmap metadata
* and 'reshape' backup-data metadata
*/
void (*uuid_from_super)(struct supertype *st, int uuid[4]);
- /* Extra generic details from metadata. This could be details about
+ /* Extract generic details from metadata. This could be details about
* the container, or about an individual array within the container.
* The determination is made either by:
* load_super being given a 'component' string.
* The particular device should be:
* The last device added by add_to_super
* The device the metadata was loaded from by load_super
+ * If 'map' is present, then it is an array raid_disks long
+ * (raid_disk must already be set and correct) and it is filled
+ * with 1 for slots that are thought to be active and 0 for slots which
+ * appear to be failed/missing.
*/
- void (*getinfo_super)(struct supertype *st, struct mdinfo *info);
-
+ void (*getinfo_super)(struct supertype *st, struct mdinfo *info, char *map);
+ struct mdinfo *(*getinfo_super_disks)(struct supertype *st);
/* Check if the given metadata is flagged as belonging to "this"
* host. 0 for 'no', 1 for 'yes', -1 for "Don't record homehost"
*/
/* update the metadata to include new device, either at create or
* when hot-adding a spare.
*/
- void (*add_to_super)(struct supertype *st, mdu_disk_info_t *dinfo,
- int fd, char *devname);
+ int (*add_to_super)(struct supertype *st, mdu_disk_info_t *dinfo,
+ int fd, char *devname);
+ /* update the metadata to delete a device,
+ * when hot-removing.
+ */
+ int (*remove_from_super)(struct supertype *st, mdu_disk_info_t *dinfo);
/* Write metadata to one device when fixing problems or adding
* a new device.
int (*write_init_super)(struct supertype *st);
int (*compare_super)(struct supertype *st, struct supertype *tst);
int (*load_super)(struct supertype *st, int fd, char *devname);
+ int (*load_container)(struct supertype *st, int fd, char *devname);
struct supertype * (*match_metadata_desc)(char *arg);
__u64 (*avail_size)(struct supertype *st, __u64 size);
+ unsigned long long (*min_acceptable_spare_size)(struct supertype *st);
int (*add_internal_bitmap)(struct supertype *st, int *chunkp,
int delay, int write_behind,
unsigned long long size, int may_change, int major);
* added to validate changing size and new devices. If there are
* inter-device dependencies, it should record sufficient details
* so these can be validated.
+ * Both 'size' and '*freesize' are in sectors. chunk is KiB.
*/
int (*validate_geometry)(struct supertype *st, int level, int layout,
int raiddisks,
- int chunk, unsigned long long size,
+ int *chunk, unsigned long long size,
char *subdev, unsigned long long *freesize,
int verbose);
- struct mdinfo *(*container_content)(struct supertype *st);
+ 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 */
+ /* Permit subarray's to be deleted from inactive containers */
+ int (*kill_subarray)(struct supertype *st); /* optional */
+ /* Permit subarray's to be modified */
+ int (*update_subarray)(struct supertype *st, char *subarray,
+ char *update, struct mddev_ident *ident); /* optional */
+ /* Check if reshape is supported for this external format.
+ * st is obtained from super_by_fd() where st->subarray[0] is
+ * initialized to indicate if reshape is being performed at the
+ * container or subarray level
+ */
+ int (*reshape_super)(struct supertype *st, long long size, int level,
+ int layout, int chunksize, int raid_disks,
+ int delta_disks, char *backup, char *dev,
+ int verbose); /* optional */
+ int (*manage_reshape)( /* optional */
+ int afd, struct mdinfo *sra, struct reshape *reshape,
+ struct supertype *st, unsigned long blocks,
+ int *fds, unsigned long long *offsets,
+ int dests, int *destfd, unsigned long long *destoffsets);
/* for mdmon */
int (*open_new)(struct supertype *c, struct active_array *a,
*/
struct mdinfo *(*activate_spare)(struct active_array *a,
struct metadata_update **updates);
+ /*
+ * Return statically allocated string that represents metadata specific
+ * controller domain of the disk. The domain is used in disk domain
+ * matching functions. Disks belong to the same domain if the they have
+ * the same domain from mdadm.conf and belong the same metadata domain.
+ * Returning NULL or not providing this handler means that metadata
+ * does not distinguish the differences between disks that belong to
+ * different controllers. They are in the domain specified by
+ * configuration file (mdadm.conf).
+ * In case when the metadata has the notion of domains based on disk
+ * it shall return NULL for disks that do not belong to the controller
+ * the supported domains. Such disks will form another domain and won't
+ * be mixed with supported ones.
+ */
+ const char *(*get_disk_controller_domain)(const char *path);
int swapuuid; /* true if uuid is bigending rather than hostendian */
int external;
-} super0, super1, super_ddf, *superlist[];
+ const char *name; /* canonical metadata name */
+} *superlist[];
-extern struct superswitch super_imsm;
+extern struct superswitch super0, super1;
+extern struct superswitch super_imsm, super_ddf;
+extern struct superswitch mbr, gpt;
struct metadata_update {
int len;
char *buf;
void *space; /* allocated space that monitor will use */
+ void **space_list; /* list of allocated spaces that monitor can
+ * use or that it returned.
+ */
struct metadata_update *next;
};
int minor_version;
int max_devs;
int container_dev; /* devnum of container */
- char subarray[32]; /* name of array inside container */
void *sb;
void *info;
- int loaded_container; /* Set if load_super found a container,
- * not just one device */
-
+ 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
+ when user has no hw/firmare compatible system.
+ */
struct metadata_update *updates;
struct metadata_update **update_tail;
* external:/md0/12
*/
int devcnt;
- char *device_name; /* e.g. /dev/md/whatever */
struct mdinfo *devs;
};
-extern struct supertype *super_by_fd(int fd);
-extern struct supertype *guess_super(int fd);
+extern struct supertype *super_by_fd(int fd, char **subarray);
+enum guess_types { guess_any, guess_array, guess_partitions };
+extern struct supertype *guess_super_type(int fd, enum guess_types guess_type);
+static inline struct supertype *guess_super(int fd) {
+ return guess_super_type(fd, guess_any);
+}
extern struct supertype *dup_super(struct supertype *st);
extern int get_dev_size(int fd, char *dname, unsigned long long *sizep);
+extern int must_be_container(int fd);
+extern int dev_size_from_id(dev_t id, unsigned long long *size);
extern void get_one_disk(int mdfd, mdu_array_info_t *ainf,
mdu_disk_info_t *disk);
+void wait_for(char *dev, int fd);
+
+/*
+ * Data structures for policy management.
+ * Each device can have a policy structure that lists
+ * various name/value pairs each possibly with a metadata associated.
+ * The policy list is sorted by name/value/metadata
+ */
+struct dev_policy {
+ struct dev_policy *next;
+ char *name; /* None of these strings are allocated. They are
+ * all just references to strings which are known
+ * to exist elsewhere.
+ * name and metadata can be compared by address equality.
+ */
+ const char *metadata;
+ const char *value;
+};
+
+extern char pol_act[], pol_domain[], pol_metadata[], pol_auto[];
+
+/* iterate over the sublist starting at list, having the same
+ * 'name' as 'list', and matching the given metadata (Where
+ * NULL matches anything
+ */
+#define pol_for_each(item, list, _metadata) \
+ for (item = list; \
+ item && item->name == list->name; \
+ item = item->next) \
+ if (!(!_metadata || !item->metadata || _metadata == item->metadata)) \
+ ; else
+
+/*
+ * policy records read from mdadm are largely just name-value pairs.
+ * The names are constants, not strdupped
+ */
+struct pol_rule {
+ struct pol_rule *next;
+ char *type; /* rule_policy or rule_part */
+ struct rule {
+ struct rule *next;
+ char *name;
+ char *value;
+ char *dups; /* duplicates of 'value' with a partNN appended */
+ } *rule;
+};
+
+extern char rule_policy[], rule_part[];
+extern char rule_path[], rule_type[];
+extern char type_part[], type_disk[];
+
+extern void policyline(char *line, char *type);
+extern void policy_add(char *type, ...);
+extern void policy_free(void);
+
+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 void dev_policy_free(struct dev_policy *p);
+
+//extern void pol_new(struct dev_policy **pol, char *name, char *val, char *metadata);
+extern void pol_add(struct dev_policy **pol, char *name, char *val, char *metadata);
+extern struct dev_policy *pol_find(struct dev_policy *pol, char *name);
+
+enum policy_action {
+ act_default,
+ act_include,
+ act_re_add,
+ act_spare, /* This only applies to bare devices */
+ act_spare_same_slot, /* this allows non-bare devices,
+ * but only if recent removal */
+ act_force_spare, /* this allow non-bare devices in any case */
+ act_err
+};
+
+extern int policy_action_allows(struct dev_policy *plist, const char *metadata,
+ enum policy_action want);
+extern int disk_action_allows(struct mdinfo *disk, const char *metadata,
+ enum policy_action want);
+
+struct domainlist {
+ struct domainlist *next;
+ const char *dom;
+};
+
+extern int domain_test(struct domainlist *dom, struct dev_policy *pol,
+ 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,
+ const char *metadata);
+extern void domain_free(struct domainlist *dl);
+extern void domain_merge(struct domainlist **domp, struct dev_policy *pol,
+ const char *metadata);
+void domain_add(struct domainlist **domp, char *domain);
+
+extern void policy_save_path(char *id_path, struct map_ent *array);
+extern int policy_check_path(struct mdinfo *disk, struct map_ent *array);
#if __GNUC__ < 3
struct stat64;
#define HAVE_NFTW we assume
#define HAVE_FTW
-#ifdef UCLIBC
+#ifdef __UCLIBC__
# include <features.h>
+# ifndef __UCLIBC_HAS_LFS__
+# define lseek64 lseek
+# endif
# ifndef __UCLIBC_HAS_FTW__
# undef HAVE_FTW
# undef HAVE_NFTW
extern int Manage_ro(char *devname, int fd, int readonly);
extern int Manage_runstop(char *devname, int fd, int runstop, int quiet);
extern int Manage_resize(char *devname, int fd, long long size, int raid_disks);
-extern int Manage_reconfig(char *devname, int fd, int layout);
extern int Manage_subdevs(char *devname, int fd,
- mddev_dev_t devlist, int verbose);
+ struct mddev_dev *devlist, int verbose, int test,
+ char *update);
extern int autodetect(void);
extern int Grow_Add_device(char *devname, int fd, char *newdev);
extern int Grow_addbitmap(char *devname, int fd, char *file, int chunk, int delay, int write_behind, int force);
extern int Grow_reshape(char *devname, int fd, int quiet, char *backup_file,
long long size,
- int level, int layout, int chunksize, int raid_disks);
+ int level, char *layout_str, int chunksize, int raid_disks,
+ struct mddev_dev *devlist,
+ int force);
extern int Grow_restart(struct supertype *st, struct mdinfo *info,
- int *fdlist, int cnt, char *backup_file);
-
-
-extern int Assemble(struct supertype *st, char *mddev, int mdfd,
- mddev_ident_t ident,
- mddev_dev_t devlist, char *backup_file,
+ int *fdlist, int cnt, char *backup_file, int verbose);
+extern int Grow_continue(int mdfd, struct supertype *st,
+ struct mdinfo *info, char *backup_file);
+
+extern int Assemble(struct supertype *st, char *mddev,
+ struct mddev_ident *ident,
+ struct mddev_dev *devlist,
+ char *backup_file, int invalid_backup,
int readonly, int runstop,
- char *update, char *homehost,
+ char *update, char *homehost, int require_homehost,
int verbose, int force);
-extern int Build(char *mddev, int mdfd, int chunk, int level, int layout,
- int raiddisks,
- mddev_dev_t devlist, int assume_clean,
- char *bitmap_file, int bitmap_chunk, int write_behind, int delay, int verbose);
+extern int Build(char *mddev, int chunk, int level, int layout,
+ int raiddisks, struct mddev_dev *devlist, int assume_clean,
+ char *bitmap_file, int bitmap_chunk, int write_behind,
+ int delay, int verbose, int autof, unsigned long long size);
-extern int Create(struct supertype *st, char *mddev, int mdfd,
+extern int Create(struct supertype *st, char *mddev,
int chunk, int level, int layout, unsigned long long size, int raiddisks, int sparedisks,
char *name, char *homehost, int *uuid,
- int subdevs, mddev_dev_t devlist,
+ int subdevs, struct mddev_dev *devlist,
int runstop, int verbose, int force, int assume_clean,
- char *bitmap_file, int bitmap_chunk, int write_behind, int delay);
+ char *bitmap_file, int bitmap_chunk, int write_behind, int delay, int autof);
extern int Detail(char *dev, int brief, int export, int test, char *homehost);
+extern int Detail_Platform(struct superswitch *ss, int scan, int verbose);
extern int Query(char *dev);
-extern int Examine(mddev_dev_t devlist, int brief, int export, int scan,
+extern int Examine(struct mddev_dev *devlist, int brief, int export, int scan,
int SparcAdjust, struct supertype *forcest, char *homehost);
-extern int Monitor(mddev_dev_t devlist,
+extern int Monitor(struct mddev_dev *devlist,
char *mailaddr, char *alert_cmd,
int period, int daemonise, int scan, int oneshot,
- int dosyslog, int test, char *pidfile);
+ int dosyslog, int test, char *pidfile, int increments,
+ int share);
-extern int Kill(char *dev, int force, int quiet, int noexcl);
+extern int Kill(char *dev, struct supertype *st, int force, int quiet, int noexcl);
+extern int Kill_subarray(char *dev, char *subarray, int quiet);
+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 verbose);
+extern int WaitClean(char *dev, int sock, int verbose);
extern int Incremental(char *devname, int verbose, int runstop,
- struct supertype *st, char *homehost, int autof);
-extern int Incremental_container(struct supertype *st, char *devname,
- int verbose, int runstop, int autof);
+ struct supertype *st, char *homehost, int require_homehost,
+ int autof);
extern void RebuildMap(void);
extern int IncrementalScan(int verbose);
-
+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,
unsigned long write_behind,
unsigned long long array_size,
int major);
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);
extern int get_linux_version(void);
+extern int mdadm_version(char *version);
+extern long long parse_size(char *size);
extern int parse_uuid(char *str, int uuid[4]);
+extern int parse_layout_10(char *layout);
+extern int parse_layout_faulty(char *layout);
extern int check_ext2(int fd, char *name);
extern int check_reiser(int fd, char *name);
extern int check_raid(int fd, char *name);
+extern int check_partitions(int fd, char *dname,
+ unsigned long long freesize,
+ unsigned long long size);
extern int get_mdp_major(void);
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 is_standard(char *dev, int *nump);
+extern int same_dev(char *one, char *two);
extern int parse_auto(char *str, char *msg, int config);
-extern mddev_ident_t conf_get_ident(char *dev);
-extern mddev_dev_t conf_get_devs(void);
+extern struct mddev_ident *conf_get_ident(char *dev);
+extern struct mddev_dev *conf_get_devs(void);
extern int conf_test_dev(char *devname);
+extern int conf_test_metadata(const char *version, struct dev_policy *pol, int is_homehost);
extern struct createinfo *conf_get_create_info(void);
extern void set_conffile(char *file);
extern char *conf_get_mailaddr(void);
extern char *conf_get_mailfrom(void);
extern char *conf_get_program(void);
-extern char *conf_get_homehost(void);
+extern char *conf_get_homehost(int *require_homehostp);
extern char *conf_line(FILE *file);
extern char *conf_word(FILE *file, int allow_key);
+extern int conf_name_is_free(char *name);
+extern int devname_matches(char *name, char *match);
+extern struct mddev_ident *conf_match(struct mdinfo *info, struct supertype *st);
+extern int experimental(void);
+
extern void free_line(char *line);
extern int match_oneof(char *devices, char *devname);
extern void uuid_from_super(int uuid[4], mdp_super_t *super);
-extern const int uuid_match_any[4];
+extern const int uuid_zero[4];
extern int same_uuid(int a[4], int b[4], int swapuuid);
extern void copy_uuid(void *a, int b[4], int swapuuid);
+extern char *__fname_from_uuid(int id[4], int swap, char *buf, char sep);
extern char *fname_from_uuid(struct supertype *st,
struct mdinfo *info, char *buf, char sep);
extern unsigned long calc_csum(void *super, int bytes);
extern int enough(int level, int raid_disks, int layout, int clean,
char *avail, int avail_disks);
+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 test_partition(int fd);
+extern int test_partition_from_id(dev_t id);
extern unsigned long long calc_array_size(int level, int raid_disks, int layout,
int chunksize, unsigned long long devsize);
extern int flush_metadata_updates(struct supertype *st);
extern void append_metadata_update(struct supertype *st, void *buf, int len);
-extern struct superswitch *find_metadata_methods(char *vers);
-
+extern int assemble_container_content(struct supertype *st, int mdfd,
+ struct mdinfo *content, int runstop,
+ char *chosen_name, int verbose,
+ char *backup_file);
+extern struct mdinfo *container_choose_spares(struct supertype *st,
+ unsigned long long min_size,
+ struct domainlist *domlist,
+ char *spare_group,
+ const char *metadata, int get_one);
+extern int move_spare(char *from_devname, char *to_devname, dev_t devid);
extern int add_disk(int mdfd, struct supertype *st,
struct mdinfo *sra, struct mdinfo *info);
+extern int remove_disk(int mdfd, struct supertype *st,
+ struct mdinfo *sra, struct mdinfo *info);
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(long long bytes);
extern char *human_size_brief(long long bytes);
extern char DefaultConfFile[];
-extern int open_mddev(char *dev, int autof);
-extern int open_mddev_devnum(char *devname, int devnum, char *name,
- char *chosen_name, int parts);
+extern int create_mddev(char *dev, char *name, int autof, int trustworthy,
+ char *chosen);
+/* values for 'trustworthy' */
+#define LOCAL 1
+#define LOCAL_ANY 10
+#define FOREIGN 2
+#define METADATA 3
+extern int open_mddev(char *dev, int report_errors);
extern int open_container(int fd);
+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 signal_mdmon(int devnum);
-extern int env_no_mdmon(void);
+extern int mdmon_pid(int devnum);
+extern int check_env(char *name);
+extern __u32 random32(void);
extern int start_mdmon(int devnum);
+extern int child_monitor(int afd, struct mdinfo *sra, struct reshape *reshape,
+ struct supertype *st, unsigned long stripes,
+ int *fds, unsigned long long *offsets,
+ int dests, int *destfd, unsigned long long *destoffsets);
+
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);
/* The version string for a 'subarray' (an array in a container)
* is
* /containername/componentname for normal read-write arrays
- * -containername/componentname for read-only arrays.
+ * -containername/componentname for arrays which mdmon must not
+ * reconfigure. They might be read-only
+ * or might be undergoing reshape etc.
* containername is e.g. md0, md_d1
* componentname is dependant on the metadata. e.g. '1' 'S1' ...
*/
return (*vers == '/' || *vers == '-');
}
+static inline char *to_subarray(struct mdstat_ent *ent, char *container)
+{
+ return &ent->metadata_version[10+strlen(container)+1];
+}
+
#ifdef DEBUG
#define dprintf(fmt, arg...) \
fprintf(stderr, fmt, ##arg)
#define dprintf(fmt, arg...) \
({ if (0) fprintf(stderr, fmt, ##arg); 0; })
#endif
+#include <assert.h>
+#include <stdarg.h>
+static inline int xasprintf(char **strp, const char *fmt, ...) {
+ va_list ap;
+ int ret;
+ va_start(ap, fmt);
+ ret = vasprintf(strp, fmt, ap);
+ va_end(ap);
+ assert(ret >= 0);
+ return ret;
+}
#define LEVEL_MULTIPATH (-4)
#define LEVEL_LINEAR (-1)
#define makedev(M,m) (((M)<<8) | (m))
#endif
-/* for raid5 */
+/* for raid4/5/6 */
#define ALGORITHM_LEFT_ASYMMETRIC 0
#define ALGORITHM_RIGHT_ASYMMETRIC 1
#define ALGORITHM_LEFT_SYMMETRIC 2
#define ALGORITHM_RIGHT_SYMMETRIC 3
+
+/* Define non-rotating (raid4) algorithms. These allow
+ * conversion of raid4 to raid5.
+ */
+#define ALGORITHM_PARITY_0 4 /* P or P,Q are initial devices */
+#define ALGORITHM_PARITY_N 5 /* P or P,Q are final devices. */
+
+/* DDF RAID6 layouts differ from md/raid6 layouts in two ways.
+ * Firstly, the exact positioning of the parity block is slightly
+ * different between the 'LEFT_*' modes of md and the "_N_*" modes
+ * of DDF.
+ * Secondly, or order of datablocks over which the Q syndrome is computed
+ * is different.
+ * Consequently we have different layouts for DDF/raid6 than md/raid6.
+ * These layouts are from the DDFv1.2 spec.
+ * Interestingly DDFv1.2-Errata-A does not specify N_CONTINUE but
+ * leaves RLQ=3 as 'Vendor Specific'
+ */
+
+#define ALGORITHM_ROTATING_ZERO_RESTART 8 /* DDF PRL=6 RLQ=1 */
+#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).
+ * This allows trivial conversion from RAID5 to RAID6
+ */
+#define ALGORITHM_LEFT_ASYMMETRIC_6 16
+#define ALGORITHM_RIGHT_ASYMMETRIC_6 17
+#define ALGORITHM_LEFT_SYMMETRIC_6 18
+#define ALGORITHM_RIGHT_SYMMETRIC_6 19
+#define ALGORITHM_PARITY_0_6 20
+#define ALGORITHM_PARITY_N_6 ALGORITHM_PARITY_N
+
+/* Define PATH_MAX in case we don't use glibc or standard library does
+ * not have PATH_MAX defined. Assume max path length is 4K characters.
+ */
+#ifndef PATH_MAX
+#define PATH_MAX 4096
+#endif
+
projects / thirdparty / mdadm.git / blobdiff