char volname[BLKPG_VOLNAMELTH]; /* volume label */
};
+#include "part.h"
+
+/* Force a compilation error if condition is true */
+#define BUILD_BUG_ON(condition) ((void)BUILD_BUG_ON_ZERO(condition))
+
+/* Force a compilation error if condition is true, but also produce a
+ result (of value 0 and type size_t), so the expression can be used
+ e.g. in a structure initializer (or where-ever else comma expressions
+ aren't permitted). */
+#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); }))
+
/*
* Parse a 128 bit uuid in 4 integers
* format is 32 hexx nibbles with options :.<space> separator
return (a*1000000)+(b*1000)+c;
}
+int mdadm_version(char *version)
+{
+ int a, b, c;
+ char *cp;
+
+ if (!version)
+ version = Version;
+
+ cp = strchr(version, '-');
+ if (!cp || *(cp+1) != ' ' || *(cp+2) != 'v')
+ return -1;
+ cp += 3;
+ a = strtoul(cp, &cp, 10);
+ if (*cp != '.')
+ return -1;
+ b = strtoul(cp+1, &cp, 10);
+ if (*cp == '.')
+ c = strtoul(cp+1, &cp, 10);
+ else
+ c = 0;
+ if (*cp != ' ' && *cp != '-')
+ return -1;
+ return (a*1000000)+(b*1000)+c;
+}
+
#ifndef MDASSEMBLE
long long parse_size(char *size)
{
#endif
}
+int test_partition(int fd)
+{
+ /* Check if fd is a whole-disk or a partition.
+ * BLKPG will return EINVAL on a partition, and BLKPG_DEL_PARTITION
+ * will return ENXIO on an invalid partition number.
+ */
+ struct blkpg_ioctl_arg a;
+ struct blkpg_partition p;
+ a.op = BLKPG_DEL_PARTITION;
+ a.data = (void*)&p;
+ a.datalen = sizeof(p);
+ a.flags = 0;
+ memset(a.data, 0, a.datalen);
+ p.pno = 1<<30;
+ if (ioctl(fd, BLKPG, &a) == 0)
+ /* Very unlikely, but not a partition */
+ return 0;
+ if (errno == ENXIO)
+ /* not a partition */
+ return 0;
+
+ return 1;
+}
+
+
int enough(int level, int raid_disks, int layout, int clean,
char *avail, int avail_disks)
{
}
}
+int enough_fd(int fd)
+{
+ struct mdu_array_info_s array;
+ struct mdu_disk_info_s disk;
+ int avail_disks = 0;
+ int i;
+ char *avail;
+
+ if (ioctl(fd, GET_ARRAY_INFO, &array) != 0 ||
+ array.raid_disks <= 0)
+ return 0;
+ avail = calloc(array.raid_disks, 1);
+ for (i=0; i<array.raid_disks + array.nr_disks; i++) {
+ disk.number = i;
+ if (ioctl(fd, GET_DISK_INFO, &disk) != 0)
+ continue;
+ if (! (disk.state & (1<<MD_DISK_SYNC)))
+ continue;
+ if (disk.raid_disk < 0 || disk.raid_disk >= array.raid_disks)
+ continue;
+ avail_disks++;
+ avail[disk.raid_disk] = 1;
+ }
+ /* This is used on an active array, so assume it is clean */
+ return enough(array.level, array.raid_disks, array.layout,
+ 1,
+ avail, avail_disks);
+}
+
+
const int uuid_match_any[4] = { ~0, ~0, ~0, ~0 };
int same_uuid(int a[4], int b[4], int swapuuid)
{
char *fname_from_uuid(struct supertype *st, struct mdinfo *info, char *buf, char sep)
{
- return __fname_from_uuid(info->uuid, st->ss->swapuuid, buf, sep);
+ // dirty hack to work around an issue with super1 superblocks...
+ // super1 superblocks need swapuuid set in order for assembly to
+ // work, but can't have it set if we want this printout to match
+ // all the other uuid printouts in super1.c, so we force swapuuid
+ // to 1 to make our printout match the rest of super1
+ return __fname_from_uuid(info->uuid, (st->ss == &super1) ? 1 : st->ss->swapuuid, buf, sep);
}
#ifndef MDASSEMBLE
/* Looks like a raid array .. */
fprintf(stderr, Name ": %s appears to be part of a raid array:\n",
name);
- st->ss->getinfo_super(st, &info);
+ st->ss->getinfo_super(st, &info, NULL);
st->ss->free_super(st);
crtime = info.array.ctime;
level = map_num(pers, info.array.level);
int minor;
if (!dev) return -1;
+ flags |= O_DIRECT;
major = strtoul(dev, &e, 0);
if (e > dev && *e == ':' && e[1] &&
(minor = strtoul(e+1, &e, 0)) >= 0 &&
*e == 0) {
- snprintf(devname, sizeof(devname), "/dev/.tmp.md.%d:%d:%d",
- (int)getpid(), major, minor);
- if (mknod(devname, S_IFBLK|0600, makedev(major, minor))==0) {
- fd = open(devname, flags|O_DIRECT);
- unlink(devname);
+ char *path = map_dev(major, minor, 0);
+ if (path)
+ fd = open(path, flags);
+ if (fd < 0) {
+ snprintf(devname, sizeof(devname), "/dev/.tmp.md.%d:%d:%d",
+ (int)getpid(), major, minor);
+ if (mknod(devname, S_IFBLK|0600, makedev(major, minor))==0) {
+ fd = open(devname, flags);
+ unlink(devname);
+ }
+ }
+ if (fd < 0) {
+ snprintf(devname, sizeof(devname), "/tmp/.tmp.md.%d:%d:%d",
+ (int)getpid(), major, minor);
+ if (mknod(devname, S_IFBLK|0600, makedev(major, minor))==0) {
+ fd = open(devname, flags);
+ unlink(devname);
+ }
}
} else
- fd = open(dev, flags|O_DIRECT);
+ fd = open(dev, flags);
return fd;
}
dprintf("%s: timeout waiting for %s\n", __func__, dev);
}
-struct superswitch *superlist[] = { &super0, &super1, &super_ddf, &super_imsm, NULL };
+struct superswitch *superlist[] =
+{
+ &super0, &super1,
+ &super_ddf, &super_imsm,
+ &mbr, &gpt,
+ NULL };
#if !defined(MDASSEMBLE) || defined(MDASSEMBLE) && defined(MDASSEMBLE_AUTO)
-struct supertype *super_by_fd(int fd)
+struct supertype *super_by_fd(int fd, char **subarrayp)
{
mdu_array_info_t array;
int vers;
char version[20];
int i;
char *subarray = NULL;
+ int container = NoMdDev;
sra = sysfs_read(fd, 0, GET_VERSION);
}
if (minor == -2 && is_subarray(verstr)) {
char *dev = verstr+1;
+
subarray = strchr(dev, '/');
- int devnum;
if (subarray)
*subarray++ = '\0';
- devnum = devname2devnum(dev);
subarray = strdup(subarray);
+ container = devname2devnum(dev);
if (sra)
sysfs_free(sra);
- sra = sysfs_read(-1, devnum, GET_VERSION);
+ sra = sysfs_read(-1, container, GET_VERSION);
if (sra && sra->text_version[0])
verstr = sra->text_version;
else
sysfs_free(sra);
if (st) {
st->sb = NULL;
- if (subarray) {
- strncpy(st->subarray, subarray, 32);
- st->subarray[31] = 0;
- free(subarray);
- } else
- st->subarray[0] = 0;
- }
+ if (subarrayp)
+ *subarrayp = subarray;
+ st->container_dev = container;
+ st->devnum = fd2devnum(fd);
+ } else
+ free(subarray);
+
return st;
}
#endif /* !defined(MDASSEMBLE) || defined(MDASSEMBLE) && defined(MDASSEMBLE_AUTO) */
+int dev_size_from_id(dev_t id, unsigned long long *size)
+{
+ char buf[20];
+ int fd;
+
+ sprintf(buf, "%d:%d", major(id), minor(id));
+ fd = dev_open(buf, O_RDONLY);
+ if (fd < 0)
+ return 0;
+ if (get_dev_size(fd, NULL, size)) {
+ close(fd);
+ return 1;
+ }
+ close(fd);
+ return 0;
+}
struct supertype *dup_super(struct supertype *orig)
{
st->ss = orig->ss;
st->max_devs = orig->max_devs;
st->minor_version = orig->minor_version;
- strcpy(st->subarray, orig->subarray);
st->sb = NULL;
st->info = NULL;
return st;
}
-struct supertype *guess_super(int fd)
+struct supertype *guess_super_type(int fd, enum guess_types guess_type)
{
/* try each load_super to find the best match,
* and return the best superswitch
*/
struct superswitch *ss;
struct supertype *st;
- unsigned long besttime = 0;
+ time_t besttime = 0;
int bestsuper = -1;
int i;
st = malloc(sizeof(*st));
+ memset(st, 0, sizeof(*st));
+ st->container_dev = NoMdDev;
+
for (i=0 ; superlist[i]; i++) {
int rv;
ss = superlist[i];
+ if (guess_type == guess_array && ss->add_to_super == NULL)
+ continue;
+ if (guess_type == guess_partitions && ss->add_to_super != NULL)
+ continue;
memset(st, 0, sizeof(*st));
rv = ss->load_super(st, fd, NULL);
if (rv == 0) {
struct mdinfo info;
- st->ss->getinfo_super(st, &info);
+ st->ss->getinfo_super(st, &info, NULL);
if (bestsuper == -1 ||
besttime < info.array.ctime) {
bestsuper = i;
return 1;
}
+/* Return true if this can only be a container, not a member device.
+ * i.e. is and md device and size is zero
+ */
+int must_be_container(int fd)
+{
+ unsigned long long size;
+ if (md_get_version(fd) < 0)
+ return 0;
+ if (get_dev_size(fd, NULL, &size) == 0)
+ return 1;
+ if (size == 0)
+ return 1;
+ return 0;
+}
+
+/* Sets endofpart parameter to the last block used by the last GPT partition on the device.
+ * Returns: 1 if successful
+ * -1 for unknown partition type
+ * 0 for other errors
+ */
+static int get_gpt_last_partition_end(int fd, unsigned long long *endofpart)
+{
+ struct GPT gpt;
+ unsigned char buf[512];
+ unsigned char empty_gpt_entry[16]= {0};
+ struct GPT_part_entry *part;
+ unsigned long long curr_part_end;
+ unsigned all_partitions, entry_size;
+ unsigned part_nr;
+
+ *endofpart = 0;
+
+ BUILD_BUG_ON(sizeof(gpt) != 512);
+ /* read GPT header */
+ lseek(fd, 512, SEEK_SET);
+ if (read(fd, &gpt, 512) != 512)
+ return 0;
+
+ /* get the number of partition entries and the entry size */
+ all_partitions = __le32_to_cpu(gpt.part_cnt);
+ entry_size = __le32_to_cpu(gpt.part_size);
+
+ /* Check GPT signature*/
+ if (gpt.magic != GPT_SIGNATURE_MAGIC)
+ return -1;
+
+ /* sanity checks */
+ if (all_partitions > 1024 ||
+ entry_size > 512)
+ return -1;
+
+ /* read first GPT partition entries */
+ if (read(fd, buf, 512) != 512)
+ return 0;
+
+ part = (struct GPT_part_entry*)buf;
+
+ for (part_nr=0; part_nr < all_partitions; part_nr++) {
+ /* is this valid partition? */
+ if (memcmp(part->type_guid, empty_gpt_entry, 16) != 0) {
+ /* check the last lba for the current partition */
+ curr_part_end = __le64_to_cpu(part->ending_lba);
+ if (curr_part_end > *endofpart)
+ *endofpart = curr_part_end;
+ }
+
+ part = (struct GPT_part_entry*)((unsigned char*)part + entry_size);
+
+ if ((unsigned char *)part >= buf + 512) {
+ if (read(fd, buf, 512) != 512)
+ return 0;
+ part = (struct GPT_part_entry*)buf;
+ }
+ }
+ return 1;
+}
+
+/* Sets endofpart parameter to the last block used by the last partition on the device.
+ * Returns: 1 if successful
+ * -1 for unknown partition type
+ * 0 for other errors
+ */
+static int get_last_partition_end(int fd, unsigned long long *endofpart)
+{
+ struct MBR boot_sect;
+ struct MBR_part_record *part;
+ unsigned long long curr_part_end;
+ unsigned part_nr;
+ int retval = 0;
+
+ *endofpart = 0;
+
+ BUILD_BUG_ON(sizeof(boot_sect) != 512);
+ /* read MBR */
+ lseek(fd, 0, 0);
+ if (read(fd, &boot_sect, 512) != 512)
+ goto abort;
+
+ /* check MBP signature */
+ if (boot_sect.magic == MBR_SIGNATURE_MAGIC) {
+ retval = 1;
+ /* found the correct signature */
+ part = boot_sect.parts;
+
+ for (part_nr=0; part_nr < MBR_PARTITIONS; part_nr++) {
+ /* check for GPT type */
+ if (part->part_type == MBR_GPT_PARTITION_TYPE) {
+ retval = get_gpt_last_partition_end(fd, endofpart);
+ break;
+ }
+ /* check the last used lba for the current partition */
+ curr_part_end = __le32_to_cpu(part->first_sect_lba) +
+ __le32_to_cpu(part->blocks_num);
+ if (curr_part_end > *endofpart)
+ *endofpart = curr_part_end;
+
+ part++;
+ }
+ } else {
+ /* Unknown partition table */
+ retval = -1;
+ }
+ abort:
+ return retval;
+}
+
+int check_partitions(int fd, char *dname, unsigned long long freesize)
+{
+ /*
+ * Check where the last partition ends
+ */
+ unsigned long long endofpart;
+ int ret;
+
+ if ((ret = get_last_partition_end(fd, &endofpart)) > 0) {
+ /* There appears to be a partition table here */
+ if (freesize == 0) {
+ /* partitions will not be visible in new device */
+ fprintf(stderr,
+ Name ": partition table exists on %s but will be lost or\n"
+ " meaningless after creating array\n",
+ dname);
+ return 1;
+ } else if (endofpart > freesize) {
+ /* last partition overlaps metadata */
+ fprintf(stderr,
+ Name ": metadata will over-write last partition on %s.\n",
+ dname);
+ return 1;
+ }
+ }
+ return 0;
+}
+
void get_one_disk(int mdfd, mdu_array_info_t *ainf, mdu_disk_info_t *disk)
{
int d;
continue;
n = read(dfd, buf, sizeof(buf));
close(dfd);
- if (n <= 0 || n >= sizeof(buf))
+ if (n <= 0 || (unsigned)n >= sizeof(buf))
continue;
buf[n] = 0;
if (sscanf(buf, "%d:%d", &major, &minor) != 2)
return -1;
}
+struct superswitch *version_to_superswitch(char *vers)
+{
+ int i;
+
+ for (i = 0; superlist[i]; i++) {
+ struct superswitch *ss = superlist[i];
+
+ if (strcmp(vers, ss->name) == 0)
+ return ss;
+ }
+
+ return NULL;
+}
+
+int is_container_member(struct mdstat_ent *mdstat, char *container)
+{
+ if (mdstat->metadata_version == NULL ||
+ strncmp(mdstat->metadata_version, "external:", 9) != 0 ||
+ !is_subarray(mdstat->metadata_version+9) ||
+ strncmp(mdstat->metadata_version+10, container, strlen(container)) != 0 ||
+ mdstat->metadata_version[10+strlen(container)] != '/')
+ return 0;
+
+ return 1;
+}
+
+int is_subarray_active(char *subarray, char *container)
+{
+ struct mdstat_ent *mdstat = mdstat_read(0, 0);
+ struct mdstat_ent *ent;
+
+ for (ent = mdstat; ent; ent = ent->next)
+ if (is_container_member(ent, container))
+ if (!subarray ||
+ strcmp(to_subarray(ent, container), subarray) == 0)
+ break;
+
+ free_mdstat(mdstat);
+
+ return ent != NULL;
+}
+
+int is_container_active(char *container)
+{
+ return is_subarray_active(NULL, container);
+}
+
+/* open_subarray - opens a subarray in a container
+ * @dev: container device name
+ * @st: empty supertype
+ * @quiet: block reporting errors flag
+ *
+ * On success returns an fd to a container and fills in *st
+ */
+int open_subarray(char *dev, char *subarray, struct supertype *st, int quiet)
+{
+ struct mdinfo *mdi;
+ struct mdinfo *info;
+ int fd, err = 1;
+
+ fd = open(dev, O_RDWR|O_EXCL);
+ if (fd < 0) {
+ if (!quiet)
+ fprintf(stderr, Name ": Couldn't open %s, aborting\n",
+ dev);
+ return 2;
+ }
+
+ st->devnum = fd2devnum(fd);
+ if (st->devnum == NoMdDev) {
+ if (!quiet)
+ fprintf(stderr,
+ Name ": Failed to determine device number for %s\n",
+ dev);
+ goto close_fd;
+ }
+
+ mdi = sysfs_read(fd, st->devnum, GET_VERSION|GET_LEVEL);
+ if (!mdi) {
+ if (!quiet)
+ fprintf(stderr, Name ": Failed to read sysfs for %s\n",
+ dev);
+ goto close_fd;
+ }
+
+ if (mdi->array.level != UnSet) {
+ if (!quiet)
+ fprintf(stderr, Name ": %s is not a container\n", dev);
+ goto free_sysfs;
+ }
+
+ st->ss = version_to_superswitch(mdi->text_version);
+ if (!st->ss) {
+ if (!quiet)
+ fprintf(stderr,
+ Name ": Operation not supported for %s metadata\n",
+ mdi->text_version);
+ goto free_sysfs;
+ }
+
+ st->devname = devnum2devname(st->devnum);
+ if (!st->devname) {
+ if (!quiet)
+ fprintf(stderr, Name ": Failed to allocate device name\n");
+ goto free_sysfs;
+ }
+
+ if (!st->ss->load_container) {
+ if (!quiet)
+ fprintf(stderr, Name ": %s is not a container\n", dev);
+ goto free_name;
+ }
+
+ if (st->ss->load_container(st, fd, NULL)) {
+ if (!quiet)
+ fprintf(stderr, Name ": Failed to load metadata for %s\n",
+ dev);
+ goto free_name;
+ }
+
+ info = st->ss->container_content(st, subarray);
+ if (!info) {
+ if (!quiet)
+ fprintf(stderr, Name ": Failed to find subarray-%s in %s\n",
+ subarray, dev);
+ goto free_super;
+ }
+ free(info);
+
+ err = 0;
+
+ free_super:
+ if (err)
+ st->ss->free_super(st);
+ free_name:
+ if (err)
+ free(st->devname);
+ free_sysfs:
+ sysfs_free(mdi);
+ close_fd:
+ if (err)
+ close(fd);
+
+ if (err)
+ return -1;
+ else
+ return fd;
+}
+
int add_disk(int mdfd, struct supertype *st,
struct mdinfo *sra, struct mdinfo *info)
{
int rv;
#ifndef MDASSEMBLE
if (st->ss->external) {
- rv = sysfs_add_disk(sra, info,
- info->disk.state & (1<<MD_DISK_SYNC));
+ if (info->disk.state & (1<<MD_DISK_SYNC))
+ info->recovery_start = MaxSector;
+ else
+ info->recovery_start = 0;
+ rv = sysfs_add_disk(sra, info, 0);
if (! rv) {
struct mdinfo *sd2;
for (sd2 = sra->devs; sd2; sd2=sd2->next)
return rv;
}
+int remove_disk(int mdfd, struct supertype *st,
+ struct mdinfo *sra, struct mdinfo *info)
+{
+ int rv;
+ /* Remove the disk given by 'info' from the array */
+#ifndef MDASSEMBLE
+ if (st->ss->external)
+ rv = sysfs_set_str(sra, info, "slot", "none");
+ else
+#endif
+ rv = ioctl(mdfd, HOT_REMOVE_DISK, makedev(info->disk.major,
+ info->disk.minor));
+ return rv;
+}
+
int set_array_info(int mdfd, struct supertype *st, struct mdinfo *info)
{
/* Initialise kernel's knowledge of array.
return rv;
}
+unsigned long long min_recovery_start(struct mdinfo *array)
+{
+ /* find the minimum recovery_start in an array for metadata
+ * formats that only record per-array recovery progress instead
+ * of per-device
+ */
+ unsigned long long recovery_start = MaxSector;
+ struct mdinfo *d;
+
+ for (d = array->devs; d; d = d->next)
+ recovery_start = min(recovery_start, d->recovery_start);
+
+ return recovery_start;
+}
+
char *devnum2devname(int num)
{
char name[100];
- if (num > 0)
+ if (num >= 0)
sprintf(name, "md%d", num);
else
sprintf(name, "md_d%d", -1-num);
if ((S_IFMT & st->st_mode) == S_IFBLK) {
if (major(st->st_rdev) == MD_MAJOR)
return minor(st->st_rdev);
- else if (major(st->st_rdev) == get_mdp_major())
+ else if (major(st->st_rdev) == (unsigned)get_mdp_major())
return -1- (minor(st->st_rdev)>>MdpMinorShift);
/* must be an extended-minor partition. Look at the
return NoMdDev;
}
-int mdmon_running(int devnum)
+int mdmon_pid(int devnum)
{
char path[100];
char pid[10];
int fd;
int n;
- sprintf(path, "/var/run/mdadm/%s.pid", devnum2devname(devnum));
- fd = open(path, O_RDONLY, 0);
+ char *devname = devnum2devname(devnum);
+
+ sprintf(path, "%s/%s.pid", MDMON_DIR, devname);
+ free(devname);
+
+ fd = open(path, O_RDONLY | O_NOATIME, 0);
if (fd < 0)
- return 0;
+ return -1;
n = read(fd, pid, 9);
close(fd);
if (n <= 0)
- return 0;
- if (kill(atoi(pid), 0) == 0)
- return 1;
- return 0;
+ return -1;
+ return atoi(pid);
}
-int signal_mdmon(int devnum)
+int mdmon_running(int devnum)
{
- char path[100];
- char pid[10];
- int fd;
- int n;
- sprintf(path, "/var/run/mdadm/%s.pid", devnum2devname(devnum));
- fd = open(path, O_RDONLY, 0);
-
- if (fd < 0)
- return 0;
- n = read(fd, pid, 9);
- close(fd);
- if (n <= 0)
+ int pid = mdmon_pid(devnum);
+ if (pid <= 0)
return 0;
- if (kill(atoi(pid), SIGUSR1) == 0)
+ if (kill(pid, 0) == 0)
return 1;
return 0;
}
projects / thirdparty / mdadm.git / blobdiff