diff options
Diffstat (limited to 'drivers/md/md.c')
| -rw-r--r-- | drivers/md/md.c | 593 |
1 files changed, 435 insertions, 158 deletions
diff --git a/drivers/md/md.c b/drivers/md/md.c index 717daad71fb1..d429c30cd514 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -53,6 +53,7 @@ #include <linux/slab.h> #include "md.h" #include "bitmap.h" +#include "md-cluster.h" #ifndef MODULE static void autostart_arrays(int part); @@ -66,6 +67,11 @@ static void autostart_arrays(int part); static LIST_HEAD(pers_list); static DEFINE_SPINLOCK(pers_lock); +struct md_cluster_operations *md_cluster_ops; +EXPORT_SYMBOL(md_cluster_ops); +struct module *md_cluster_mod; +EXPORT_SYMBOL(md_cluster_mod); + static DECLARE_WAIT_QUEUE_HEAD(resync_wait); static struct workqueue_struct *md_wq; static struct workqueue_struct *md_misc_wq; @@ -249,6 +255,7 @@ static void md_make_request(struct request_queue *q, struct bio *bio) const int rw = bio_data_dir(bio); struct mddev *mddev = q->queuedata; unsigned int sectors; + int cpu; if (mddev == NULL || mddev->pers == NULL || !mddev->ready) { @@ -284,7 +291,10 @@ static void md_make_request(struct request_queue *q, struct bio *bio) sectors = bio_sectors(bio); mddev->pers->make_request(mddev, bio); - generic_start_io_acct(rw, sectors, &mddev->gendisk->part0); + cpu = part_stat_lock(); + part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]); + part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors); + part_stat_unlock(); if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended) wake_up(&mddev->sb_wait); @@ -636,7 +646,7 @@ void mddev_unlock(struct mddev *mddev) } EXPORT_SYMBOL_GPL(mddev_unlock); -static struct md_rdev *find_rdev_nr_rcu(struct mddev *mddev, int nr) +struct md_rdev *md_find_rdev_nr_rcu(struct mddev *mddev, int nr) { struct md_rdev *rdev; @@ -646,6 +656,7 @@ static struct md_rdev *find_rdev_nr_rcu(struct mddev *mddev, int nr) return NULL; } +EXPORT_SYMBOL_GPL(md_find_rdev_nr_rcu); static struct md_rdev *find_rdev(struct mddev *mddev, dev_t dev) { @@ -2013,7 +2024,6 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev) { char b[BDEVNAME_SIZE]; struct kobject *ko; - char *s; int err; /* prevent duplicates */ @@ -2043,11 +2053,11 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev) int choice = 0; if (mddev->pers) choice = mddev->raid_disks; - while (find_rdev_nr_rcu(mddev, choice)) + while (md_find_rdev_nr_rcu(mddev, choice)) choice++; rdev->desc_nr = choice; } else { - if (find_rdev_nr_rcu(mddev, rdev->desc_nr)) { + if (md_find_rdev_nr_rcu(mddev, rdev->desc_nr)) { rcu_read_unlock(); return -EBUSY; } @@ -2059,8 +2069,7 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev) return -EBUSY; } bdevname(rdev->bdev,b); - while ( (s=strchr(b, '/')) != NULL) - *s = '!'; + strreplace(b, '/', '!'); rdev->mddev = mddev; printk(KERN_INFO "md: bind<%s>\n", b); @@ -2162,11 +2171,12 @@ static void export_rdev(struct md_rdev *rdev) kobject_put(&rdev->kobj); } -static void kick_rdev_from_array(struct md_rdev *rdev) +void md_kick_rdev_from_array(struct md_rdev *rdev) { unbind_rdev_from_array(rdev); export_rdev(rdev); } +EXPORT_SYMBOL_GPL(md_kick_rdev_from_array); static void export_array(struct mddev *mddev) { @@ -2175,7 +2185,7 @@ static void export_array(struct mddev *mddev) while (!list_empty(&mddev->disks)) { rdev = list_first_entry(&mddev->disks, struct md_rdev, same_set); - kick_rdev_from_array(rdev); + md_kick_rdev_from_array(rdev); } mddev->raid_disks = 0; mddev->major_version = 0; @@ -2204,7 +2214,7 @@ static void sync_sbs(struct mddev *mddev, int nospares) } } -static void md_update_sb(struct mddev *mddev, int force_change) +void md_update_sb(struct mddev *mddev, int force_change) { struct md_rdev *rdev; int sync_req; @@ -2365,6 +2375,37 @@ repeat: wake_up(&rdev->blocked_wait); } } +EXPORT_SYMBOL(md_update_sb); + +static int add_bound_rdev(struct md_rdev *rdev) +{ + struct mddev *mddev = rdev->mddev; + int err = 0; + + if (!mddev->pers->hot_remove_disk) { + /* If there is hot_add_disk but no hot_remove_disk + * then added disks for geometry changes, + * and should be added immediately. + */ + super_types[mddev->major_version]. + validate_super(mddev, rdev); + err = mddev->pers->hot_add_disk(mddev, rdev); + if (err) { + unbind_rdev_from_array(rdev); + export_rdev(rdev); + return err; + } + } + sysfs_notify_dirent_safe(rdev->sysfs_state); + + set_bit(MD_CHANGE_DEVS, &mddev->flags); + if (mddev->degraded) + set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + md_new_event(mddev); + md_wakeup_thread(mddev->thread); + return 0; +} /* words written to sysfs files may, or may not, be \n terminated. * We want to accept with case. For this we use cmd_match. @@ -2467,10 +2508,16 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len) err = -EBUSY; else { struct mddev *mddev = rdev->mddev; - kick_rdev_from_array(rdev); + if (mddev_is_clustered(mddev)) + md_cluster_ops->remove_disk(mddev, rdev); + md_kick_rdev_from_array(rdev); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); if (mddev->pers) md_update_sb(mddev, 1); md_new_event(mddev); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); err = 0; } } else if (cmd_match(buf, "writemostly")) { @@ -2549,6 +2596,21 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len) clear_bit(Replacement, &rdev->flags); err = 0; } + } else if (cmd_match(buf, "re-add")) { + if (test_bit(Faulty, &rdev->flags) && (rdev->raid_disk == -1)) { + /* clear_bit is performed _after_ all the devices + * have their local Faulty bit cleared. If any writes + * happen in the meantime in the local node, they + * will land in the local bitmap, which will be synced + * by this node eventually + */ + if (!mddev_is_clustered(rdev->mddev) || + (err = md_cluster_ops->gather_bitmaps(rdev)) == 0) { + clear_bit(Faulty, &rdev->flags); + err = add_bound_rdev(rdev); + } + } else + err = -EBUSY; } if (!err) sysfs_notify_dirent_safe(rdev->sysfs_state); @@ -2566,13 +2628,14 @@ errors_show(struct md_rdev *rdev, char *page) static ssize_t errors_store(struct md_rdev *rdev, const char *buf, size_t len) { - char *e; - unsigned long n = simple_strtoul(buf, &e, 10); - if (*buf && (*e == 0 || *e == '\n')) { - atomic_set(&rdev->corrected_errors, n); - return len; - } - return -EINVAL; + unsigned int n; + int rv; + + rv = kstrtouint(buf, 10, &n); + if (rv < 0) + return rv; + atomic_set(&rdev->corrected_errors, n); + return len; } static struct rdev_sysfs_entry rdev_errors = __ATTR(errors, S_IRUGO|S_IWUSR, errors_show, errors_store); @@ -2589,13 +2652,16 @@ slot_show(struct md_rdev *rdev, char *page) static ssize_t slot_store(struct md_rdev *rdev, const char *buf, size_t len) { - char *e; + int slot; int err; - int slot = simple_strtoul(buf, &e, 10); + if (strncmp(buf, "none", 4)==0) slot = -1; - else if (e==buf || (*e && *e!= '\n')) - return -EINVAL; + else { + err = kstrtouint(buf, 10, (unsigned int *)&slot); + if (err < 0) + return err; + } if (rdev->mddev->pers && slot == -1) { /* Setting 'slot' on an active array requires also * updating the 'rd%d' link, and communicating @@ -3123,7 +3189,7 @@ static void analyze_sbs(struct mddev *mddev) "md: fatal superblock inconsistency in %s" " -- removing from array\n", bdevname(rdev->bdev,b)); - kick_rdev_from_array(rdev); + md_kick_rdev_from_array(rdev); } super_types[mddev->major_version]. @@ -3138,18 +3204,27 @@ static void analyze_sbs(struct mddev *mddev) "md: %s: %s: only %d devices permitted\n", mdname(mddev), bdevname(rdev->bdev, b), mddev->max_disks); - kick_rdev_from_array(rdev); + md_kick_rdev_from_array(rdev); continue; } - if (rdev != freshest) + if (rdev != freshest) { if (super_types[mddev->major_version]. validate_super(mddev, rdev)) { printk(KERN_WARNING "md: kicking non-fresh %s" " from array!\n", bdevname(rdev->bdev,b)); - kick_rdev_from_array(rdev); + md_kick_rdev_from_array(rdev); continue; } + /* No device should have a Candidate flag + * when reading devices + */ + if (test_bit(Candidate, &rdev->flags)) { + pr_info("md: kicking Cluster Candidate %s from array!\n", + bdevname(rdev->bdev, b)); + md_kick_rdev_from_array(rdev); + } + } if (mddev->level == LEVEL_MULTIPATH) { rdev->desc_nr = i++; rdev->raid_disk = rdev->desc_nr; @@ -3471,12 +3546,12 @@ layout_show(struct mddev *mddev, char *page) static ssize_t layout_store(struct mddev *mddev, const char *buf, size_t len) { - char *e; - unsigned long n = simple_strtoul(buf, &e, 10); + unsigned int n; int err; - if (!*buf || (*e && *e != '\n')) - return -EINVAL; + err = kstrtouint(buf, 10, &n); + if (err < 0) + return err; err = mddev_lock(mddev); if (err) return err; @@ -3520,12 +3595,12 @@ static int update_raid_disks(struct mddev *mddev, int raid_disks); static ssize_t raid_disks_store(struct mddev *mddev, const char *buf, size_t len) { - char *e; + unsigned int n; int err; - unsigned long n = simple_strtoul(buf, &e, 10); - if (!*buf || (*e && *e != '\n')) - return -EINVAL; + err = kstrtouint(buf, 10, &n); + if (err < 0) + return err; err = mddev_lock(mddev); if (err) @@ -3572,12 +3647,12 @@ chunk_size_show(struct mddev *mddev, char *page) static ssize_t chunk_size_store(struct mddev *mddev, const char *buf, size_t len) { + unsigned long n; int err; - char *e; - unsigned long n = simple_strtoul(buf, &e, 10); - if (!*buf || (*e && *e != '\n')) - return -EINVAL; + err = kstrtoul(buf, 10, &n); + if (err < 0) + return err; err = mddev_lock(mddev); if (err) @@ -3615,19 +3690,24 @@ resync_start_show(struct mddev *mddev, char *page) static ssize_t resync_start_store(struct mddev *mddev, const char *buf, size_t len) { + unsigned long long n; int err; - char *e; - unsigned long long n = simple_strtoull(buf, &e, 10); + + if (cmd_match(buf, "none")) + n = MaxSector; + else { + err = kstrtoull(buf, 10, &n); + if (err < 0) + return err; + if (n != (sector_t)n) + return -EINVAL; + } err = mddev_lock(mddev); if (err) return err; if (mddev->pers && !test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) err = -EBUSY; - else if (cmd_match(buf, "none")) - n = MaxSector; - else if (!*buf || (*e && *e != '\n')) - err = -EINVAL; if (!err) { mddev->recovery_cp = n; @@ -3761,7 +3841,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len) err = -EBUSY; } spin_unlock(&mddev->lock); - return err; + return err ?: len; } err = mddev_lock(mddev); if (err) @@ -3863,14 +3943,14 @@ max_corrected_read_errors_show(struct mddev *mddev, char *page) { static ssize_t max_corrected_read_errors_store(struct mddev *mddev, const char *buf, size_t len) { - char *e; - unsigned long n = simple_strtoul(buf, &e, 10); + unsigned int n; + int rv; - if (*buf && (*e == 0 || *e == '\n')) { - atomic_set(&mddev->max_corr_read_errors, n); - return len; - } - return -EINVAL; + rv = kstrtouint(buf, 10, &n); + if (rv < 0) + return rv; + atomic_set(&mddev->max_corr_read_errors, n); + return len; } static struct md_sysfs_entry max_corr_read_errors = @@ -3932,8 +4012,10 @@ new_dev_store(struct mddev *mddev, const char *buf, size_t len) else rdev = md_import_device(dev, -1, -1); - if (IS_ERR(rdev)) + if (IS_ERR(rdev)) { + mddev_unlock(mddev); return PTR_ERR(rdev); + } err = bind_rdev_to_array(rdev, mddev); out: if (err) @@ -4004,8 +4086,12 @@ size_store(struct mddev *mddev, const char *buf, size_t len) if (err) return err; if (mddev->pers) { + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); err = update_size(mddev, sectors); md_update_sb(mddev, 1); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); } else { if (mddev->dev_sectors == 0 || mddev->dev_sectors > sectors) @@ -4134,34 +4220,36 @@ action_store(struct mddev *mddev, const char *page, size_t len) if (!mddev->pers || !mddev->pers->sync_request) return -EINVAL; - if (cmd_match(page, "frozen")) - set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - else - clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); if (cmd_match(page, "idle") || cmd_match(page, "frozen")) { - flush_workqueue(md_misc_wq); - if (mddev->sync_thread) { - set_bit(MD_RECOVERY_INTR, &mddev->recovery); - if (mddev_lock(mddev) == 0) { + if (cmd_match(page, "frozen")) + set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + else + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) && + mddev_lock(mddev) == 0) { + flush_workqueue(md_misc_wq); + if (mddev->sync_thread) { + set_bit(MD_RECOVERY_INTR, &mddev->recovery); md_reap_sync_thread(mddev); - mddev_unlock(mddev); } + mddev_unlock(mddev); } } else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) || test_bit(MD_RECOVERY_NEEDED, &mddev->recovery)) return -EBUSY; else if (cmd_match(page, "resync")) - set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); else if (cmd_match(page, "recover")) { + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); - set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); } else if (cmd_match(page, "reshape")) { int err; if (mddev->pers->start_reshape == NULL) return -EINVAL; err = mddev_lock(mddev); if (!err) { + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); err = mddev->pers->start_reshape(mddev); mddev_unlock(mddev); } @@ -4173,6 +4261,7 @@ action_store(struct mddev *mddev, const char *page, size_t len) set_bit(MD_RECOVERY_CHECK, &mddev->recovery); else if (!cmd_match(page, "repair")) return -EINVAL; + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery); set_bit(MD_RECOVERY_SYNC, &mddev->recovery); } @@ -4220,15 +4309,18 @@ sync_min_show(struct mddev *mddev, char *page) static ssize_t sync_min_store(struct mddev *mddev, const char *buf, size_t len) { - int min; - char *e; + unsigned int min; + int rv; + if (strncmp(buf, "system", 6)==0) { - mddev->sync_speed_min = 0; - return len; + min = 0; + } else { + rv = kstrtouint(buf, 10, &min); + if (rv < 0) + return rv; + if (min == 0) + return -EINVAL; } - min = simple_strtoul(buf, &e, 10); - if (buf == e || (*e && *e != '\n') || min <= 0) - return -EINVAL; mddev->sync_speed_min = min; return len; } @@ -4246,15 +4338,18 @@ sync_max_show(struct mddev *mddev, char *page) static ssize_t sync_max_store(struct mddev *mddev, const char *buf, size_t len) { - int max; - char *e; + unsigned int max; + int rv; + if (strncmp(buf, "system", 6)==0) { - mddev->sync_speed_max = 0; - return len; + max = 0; + } else { + rv = kstrtouint(buf, 10, &max); + if (rv < 0) + return rv; + if (max == 0) + return -EINVAL; } - max = simple_strtoul(buf, &e, 10); - if (buf == e || (*e && *e != '\n') || max <= 0) - return -EINVAL; mddev->sync_speed_max = max; return len; } @@ -4350,7 +4445,6 @@ min_sync_store(struct mddev *mddev, const char *buf, size_t len) { unsigned long long min; int err; - int chunk; if (kstrtoull(buf, 10, &min)) return -EINVAL; @@ -4364,16 +4458,8 @@ min_sync_store(struct mddev *mddev, const char *buf, size_t len) if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) goto out_unlock; - /* Must be a multiple of chunk_size */ - chunk = mddev->chunk_sectors; - if (chunk) { - sector_t temp = min; - - err = -EINVAL; - if (sector_div(temp, chunk)) - goto out_unlock; - } - mddev->resync_min = min; + /* Round down to multiple of 4K for safety */ + mddev->resync_min = round_down(min, 8); err = 0; out_unlock: @@ -4446,12 +4532,13 @@ suspend_lo_show(struct mddev *mddev, char *page) static ssize_t suspend_lo_store(struct mddev *mddev, const char *buf, size_t len) { - char *e; - unsigned long long new = simple_strtoull(buf, &e, 10); - unsigned long long old; + unsigned long long old, new; int err; - if (buf == e || (*e && *e != '\n')) + err = kstrtoull(buf, 10, &new); + if (err < 0) + return err; + if (new != (sector_t)new) return -EINVAL; err = mddev_lock(mddev); @@ -4488,12 +4575,13 @@ suspend_hi_show(struct mddev *mddev, char *page) static ssize_t suspend_hi_store(struct mddev *mddev, const char *buf, size_t len) { - char *e; - unsigned long long new = simple_strtoull(buf, &e, 10); - unsigned long long old; + unsigned long long old, new; int err; - if (buf == e || (*e && *e != '\n')) + err = kstrtoull(buf, 10, &new); + if (err < 0) + return err; + if (new != (sector_t)new) return -EINVAL; err = mddev_lock(mddev); @@ -4535,11 +4623,13 @@ static ssize_t reshape_position_store(struct mddev *mddev, const char *buf, size_t len) { struct md_rdev *rdev; - char *e; + unsigned long long new; int err; - unsigned long long new = simple_strtoull(buf, &e, 10); - if (buf == e || (*e && *e != '\n')) + err = kstrtoull(buf, 10, &new); + if (err < 0) + return err; + if (new != (sector_t)new) return -EINVAL; err = mddev_lock(mddev); if (err) @@ -4750,12 +4840,12 @@ static void md_free(struct kobject *ko) if (mddev->sysfs_state) sysfs_put(mddev->sysfs_state); + if (mddev->queue) + blk_cleanup_queue(mddev->queue); if (mddev->gendisk) { del_gendisk(mddev->gendisk); put_disk(mddev->gendisk); } - if (mddev->queue) - blk_cleanup_queue(mddev->queue); kfree(mddev); } @@ -5073,15 +5163,22 @@ int md_run(struct mddev *mddev) } if (err == 0 && pers->sync_request && (mddev->bitmap_info.file || mddev->bitmap_info.offset)) { - err = bitmap_create(mddev); - if (err) + struct bitmap *bitmap; + + bitmap = bitmap_create(mddev, -1); + if (IS_ERR(bitmap)) { + err = PTR_ERR(bitmap); printk(KERN_ERR "%s: failed to create bitmap (%d)\n", mdname(mddev), err); + } else + mddev->bitmap = bitmap; + } if (err) { mddev_detach(mddev); if (mddev->private) pers->free(mddev, mddev->private); + mddev->private = NULL; module_put(pers->owner); bitmap_destroy(mddev); return err; @@ -5217,6 +5314,7 @@ static void md_clean(struct mddev *mddev) mddev->changed = 0; mddev->degraded = 0; mddev->safemode = 0; + mddev->private = NULL; mddev->merge_check_needed = 0; mddev->bitmap_info.offset = 0; mddev->bitmap_info.default_offset = 0; @@ -5228,6 +5326,8 @@ static void md_clean(struct mddev *mddev) static void __md_stop_writes(struct mddev *mddev) { + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); flush_workqueue(md_misc_wq); if (mddev->sync_thread) { @@ -5246,6 +5346,8 @@ static void __md_stop_writes(struct mddev *mddev) mddev->in_sync = 1; md_update_sb(mddev, 1); } + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); } void md_stop_writes(struct mddev *mddev) @@ -5285,6 +5387,7 @@ static void __md_stop(struct mddev *mddev) mddev->pers = NULL; spin_unlock(&mddev->lock); pers->free(mddev, mddev->private); + mddev->private = NULL; if (pers->sync_request && mddev->to_remove == NULL) mddev->to_remove = &md_redundancy_group; module_put(pers->owner); @@ -5632,6 +5735,8 @@ static int get_array_info(struct mddev *mddev, void __user *arg) info.state = (1<<MD_SB_CLEAN); if (mddev->bitmap && mddev->bitmap_info.offset) info.state |= (1<<MD_SB_BITMAP_PRESENT); + if (mddev_is_clustered(mddev)) + info.state |= (1<<MD_SB_CLUSTERED); info.active_disks = insync; info.working_disks = working; info.failed_disks = failed; @@ -5661,7 +5766,7 @@ static int get_bitmap_file(struct mddev *mddev, void __user * arg) /* bitmap disabled, zero the first byte and copy out */ if (!mddev->bitmap_info.file) file->pathname[0] = '\0'; - else if ((ptr = d_path(&mddev->bitmap_info.file->f_path, + else if ((ptr = file_path(mddev->bitmap_info.file, file->pathname, sizeof(file->pathname))), IS_ERR(ptr)) err = PTR_ERR(ptr); @@ -5687,7 +5792,7 @@ static int get_disk_info(struct mddev *mddev, void __user * arg) return -EFAULT; rcu_read_lock(); - rdev = find_rdev_nr_rcu(mddev, info.number); + rdev = md_find_rdev_nr_rcu(mddev, info.number); if (rdev) { info.major = MAJOR(rdev->bdev->bd_dev); info.minor = MINOR(rdev->bdev->bd_dev); @@ -5720,6 +5825,13 @@ static int add_new_disk(struct mddev *mddev, mdu_disk_info_t *info) struct md_rdev *rdev; dev_t dev = MKDEV(info->major,info->minor); + if (mddev_is_clustered(mddev) && + !(info->state & ((1 << MD_DISK_CLUSTER_ADD) | (1 << MD_DISK_CANDIDATE)))) { + pr_err("%s: Cannot add to clustered mddev.\n", + mdname(mddev)); + return -EINVAL; + } + if (info->major != MAJOR(dev) || info->minor != MINOR(dev)) return -EOVERFLOW; @@ -5806,31 +5918,38 @@ static int add_new_disk(struct mddev *mddev, mdu_disk_info_t *info) else clear_bit(WriteMostly, &rdev->flags); + /* + * check whether the device shows up in other nodes + */ + if (mddev_is_clustered(mddev)) { + if (info->state & (1 << MD_DISK_CANDIDATE)) { + /* Through --cluster-confirm */ + set_bit(Candidate, &rdev->flags); + err = md_cluster_ops->new_disk_ack(mddev, true); + if (err) { + export_rdev(rdev); + return err; + } + } else if (info->state & (1 << MD_DISK_CLUSTER_ADD)) { + /* --add initiated by this node */ + err = md_cluster_ops->add_new_disk_start(mddev, rdev); + if (err) { + md_cluster_ops->add_new_disk_finish(mddev); + export_rdev(rdev); + return err; + } + } + } + rdev->raid_disk = -1; err = bind_rdev_to_array(rdev, mddev); - if (!err && !mddev->pers->hot_remove_disk) { - /* If there is hot_add_disk but no hot_remove_disk - * then added disks for geometry changes, - * and should be added immediately. - */ - super_types[mddev->major_version]. - validate_super(mddev, rdev); - err = mddev->pers->hot_add_disk(mddev, rdev); - if (err) - unbind_rdev_from_array(rdev); - } if (err) export_rdev(rdev); else - sysfs_notify_dirent_safe(rdev->sysfs_state); - - set_bit(MD_CHANGE_DEVS, &mddev->flags); - if (mddev->degraded) - set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); - set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); - if (!err) - md_new_event(mddev); - md_wakeup_thread(mddev->thread); + err = add_bound_rdev(rdev); + if (mddev_is_clustered(mddev) && + (info->state & (1 << MD_DISK_CLUSTER_ADD))) + md_cluster_ops->add_new_disk_finish(mddev); return err; } @@ -5891,18 +6010,29 @@ static int hot_remove_disk(struct mddev *mddev, dev_t dev) if (!rdev) return -ENXIO; + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); + clear_bit(Blocked, &rdev->flags); remove_and_add_spares(mddev, rdev); if (rdev->raid_disk >= 0) goto busy; - kick_rdev_from_array(rdev); + if (mddev_is_clustered(mddev)) + md_cluster_ops->remove_disk(mddev, rdev); + + md_kick_rdev_from_array(rdev); md_update_sb(mddev, 1); md_new_event(mddev); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); + return 0; busy: + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_cancel(mddev); printk(KERN_WARNING "md: cannot remove active disk %s from %s ...\n", bdevname(rdev->bdev,b), mdname(mddev)); return -EBUSY; @@ -5952,12 +6082,15 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev) err = -EINVAL; goto abort_export; } + + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); clear_bit(In_sync, &rdev->flags); rdev->desc_nr = -1; rdev->saved_raid_disk = -1; err = bind_rdev_to_array(rdev, mddev); if (err) - goto abort_export; + goto abort_clustered; /* * The rest should better be atomic, we can have disk failures @@ -5968,6 +6101,8 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev) md_update_sb(mddev, 1); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); /* * Kick recovery, maybe this spare has to be added to the * array immediately. @@ -5977,6 +6112,9 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev) md_new_event(mddev); return 0; +abort_clustered: + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_cancel(mddev); abort_export: export_rdev(rdev); return err; @@ -6034,9 +6172,14 @@ static int set_bitmap_file(struct mddev *mddev, int fd) if (mddev->pers) { mddev->pers->quiesce(mddev, 1); if (fd >= 0) { - err = bitmap_create(mddev); - if (!err) + struct bitmap *bitmap; + + bitmap = bitmap_create(mddev, -1); + if (!IS_ERR(bitmap)) { + mddev->bitmap = bitmap; err = bitmap_load(mddev); + } else + err = PTR_ERR(bitmap); } if (fd < 0 || err) { bitmap_destroy(mddev); @@ -6254,7 +6397,7 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) mddev->ctime != info->ctime || mddev->level != info->level || /* mddev->layout != info->layout || */ - !mddev->persistent != info->not_persistent|| + mddev->persistent != !info->not_persistent || mddev->chunk_sectors != info->chunk_size >> 9 || /* ignore bottom 8 bits of state, and allow SB_BITMAP_PRESENT to change */ ((state^info->state) & 0xfffffe00) @@ -6289,6 +6432,8 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) return rv; } } + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); if (info->size >= 0 && mddev->dev_sectors / 2 != info->size) rv = update_size(mddev, (sector_t)info->size * 2); @@ -6296,33 +6441,49 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) rv = update_raid_disks(mddev, info->raid_disks); if ((state ^ info->state) & (1<<MD_SB_BITMAP_PRESENT)) { - if (mddev->pers->quiesce == NULL || mddev->thread == NULL) - return -EINVAL; - if (mddev->recovery || mddev->sync_thread) - return -EBUSY; + if (mddev->pers->quiesce == NULL || mddev->thread == NULL) { + rv = -EINVAL; + goto err; + } + if (mddev->recovery || mddev->sync_thread) { + rv = -EBUSY; + goto err; + } if (info->state & (1<<MD_SB_BITMAP_PRESENT)) { + struct bitmap *bitmap; /* add the bitmap */ - if (mddev->bitmap) - return -EEXIST; - if (mddev->bitmap_info.default_offset == 0) - return -EINVAL; + if (mddev->bitmap) { + rv = -EEXIST; + goto err; + } + if (mddev->bitmap_info.default_offset == 0) { + rv = -EINVAL; + goto err; + } mddev->bitmap_info.offset = mddev->bitmap_info.default_offset; mddev->bitmap_info.space = mddev->bitmap_info.default_space; mddev->pers->quiesce(mddev, 1); - rv = bitmap_create(mddev); - if (!rv) + bitmap = bitmap_create(mddev, -1); + if (!IS_ERR(bitmap)) { + mddev->bitmap = bitmap; rv = bitmap_load(mddev); + } else + rv = PTR_ERR(bitmap); if (rv) bitmap_destroy(mddev); mddev->pers->quiesce(mddev, 0); } else { /* remove the bitmap */ - if (!mddev->bitmap) - return -ENOENT; - if (mddev->bitmap->storage.file) - return -EINVAL; + if (!mddev->bitmap) { + rv = -ENOENT; + goto err; + } + if (mddev->bitmap->storage.file) { + rv = -EINVAL; + goto err; + } mddev->pers->quiesce(mddev, 1); bitmap_destroy(mddev); mddev->pers->quiesce(mddev, 0); @@ -6330,6 +6491,12 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) } } md_update_sb(mddev, 1); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); + return rv; +err: + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_cancel(mddev); return rv; } @@ -6389,6 +6556,7 @@ static inline bool md_ioctl_valid(unsigned int cmd) case SET_DISK_FAULTY: case STOP_ARRAY: case STOP_ARRAY_RO: + case CLUSTERED_DISK_NACK: return true; default: return false; @@ -6661,6 +6829,13 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode, goto unlock; } + case CLUSTERED_DISK_NACK: + if (mddev_is_clustered(mddev)) + md_cluster_ops->new_disk_ack(mddev, false); + else + err = -EINVAL; + goto unlock; + case HOT_ADD_DISK: err = hot_add_disk(mddev, new_decode_dev(arg)); goto unlock; @@ -7234,6 +7409,55 @@ int unregister_md_personality(struct md_personality *p) } EXPORT_SYMBOL(unregister_md_personality); +int register_md_cluster_operations(struct md_cluster_operations *ops, struct module *module) +{ + if (md_cluster_ops != NULL) + return -EALREADY; + spin_lock(&pers_lock); + md_cluster_ops = ops; + md_cluster_mod = module; + spin_unlock(&pers_lock); + return 0; +} +EXPORT_SYMBOL(register_md_cluster_operations); + +int unregister_md_cluster_operations(void) +{ + spin_lock(&pers_lock); + md_cluster_ops = NULL; + spin_unlock(&pers_lock); + return 0; +} +EXPORT_SYMBOL(unregister_md_cluster_operations); + +int md_setup_cluster(struct mddev *mddev, int nodes) +{ + int err; + + err = request_module("md-cluster"); + if (err) { + pr_err("md-cluster module not found.\n"); + return err; + } + + spin_lock(&pers_lock); + if (!md_cluster_ops || !try_module_get(md_cluster_mod)) { + spin_unlock(&pers_lock); + return -ENOENT; + } + spin_unlock(&pers_lock); + + return md_cluster_ops->join(mddev, nodes); +} + +void md_cluster_stop(struct mddev *mddev) +{ + if (!md_cluster_ops) + return; + md_cluster_ops->leave(mddev); + module_put(md_cluster_mod); +} + static int is_mddev_idle(struct mddev *mddev, int init) { struct md_rdev *rdev; @@ -7371,7 +7595,11 @@ int md_allow_write(struct mddev *mddev) mddev->safemode == 0) mddev->safemode = 1; spin_unlock(&mddev->lock); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); md_update_sb(mddev, 0); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); sysfs_notify_dirent_safe(mddev->sysfs_state); } else spin_unlock(&mddev->lock); @@ -7572,6 +7800,9 @@ void md_do_sync(struct md_thread *thread) md_new_event(mddev); update_time = jiffies; + if (mddev_is_clustered(mddev)) + md_cluster_ops->resync_start(mddev, j, max_sectors); + blk_start_plug(&plug); while (j < max_sectors) { sector_t sectors; @@ -7614,8 +7845,7 @@ void md_do_sync(struct md_thread *thread) if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) break; - sectors = mddev->pers->sync_request(mddev, j, &skipped, - currspeed < speed_min(mddev)); + sectors = mddev->pers->sync_request(mddev, j, &skipped); if (sectors == 0) { set_bit(MD_RECOVERY_INTR, &mddev->recovery); break; @@ -7632,6 +7862,8 @@ void md_do_sync(struct md_thread *thread) j += sectors; if (j > 2) mddev->curr_resync = j; + if (mddev_is_clustered(mddev)) + md_cluster_ops->resync_info_update(mddev, j, max_sectors); mddev->curr_mark_cnt = io_sectors; if (last_check == 0) /* this is the earliest that rebuild will be @@ -7673,11 +7905,18 @@ void md_do_sync(struct md_thread *thread) /((jiffies-mddev->resync_mark)/HZ +1) +1; if (currspeed > speed_min(mddev)) { - if ((currspeed > speed_max(mddev)) || - !is_mddev_idle(mddev, 0)) { + if (currspeed > speed_max(mddev)) { msleep(500); goto repeat; } + if (!is_mddev_idle(mddev, 0)) { + /* + * Give other IO more of a chance. + * The faster the devices, the less we wait. + */ + wait_event(mddev->recovery_wait, + !atomic_read(&mddev->recovery_active)); + } } } printk(KERN_INFO "md: %s: %s %s.\n",mdname(mddev), desc, @@ -7690,7 +7929,10 @@ void md_do_sync(struct md_thread *thread) wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active)); /* tell personality that we are finished */ - mddev->pers->sync_request(mddev, max_sectors, &skipped, 1); + mddev->pers->sync_request(mddev, max_sectors, &skipped); + + if (mddev_is_clustered(mddev)) + md_cluster_ops->resync_finish(mddev); if (!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) && mddev->curr_resync > 2) { @@ -7886,6 +8128,15 @@ void md_check_recovery(struct mddev *mddev) int spares = 0; if (mddev->ro) { + struct md_rdev *rdev; + if (!mddev->external && mddev->in_sync) + /* 'Blocked' flag not needed as failed devices + * will be recorded if array switched to read/write. + * Leaving it set will prevent the device + * from being removed. + */ + rdev_for_each(rdev, mddev) + clear_bit(Blocked, &rdev->flags); /* On a read-only array we can: * - remove failed devices * - add already-in_sync devices if the array itself @@ -7921,8 +8172,13 @@ void md_check_recovery(struct mddev *mddev) sysfs_notify_dirent_safe(mddev->sysfs_state); } - if (mddev->flags & MD_UPDATE_SB_FLAGS) + if (mddev->flags & MD_UPDATE_SB_FLAGS) { + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); md_update_sb(mddev, 0); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); + } if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) && !test_bit(MD_RECOVERY_DONE, &mddev->recovery)) { @@ -8020,6 +8276,8 @@ void md_reap_sync_thread(struct mddev *mddev) set_bit(MD_CHANGE_DEVS, &mddev->flags); } } + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && mddev->pers->finish_reshape) mddev->pers->finish_reshape(mddev); @@ -8032,7 +8290,10 @@ void md_reap_sync_thread(struct mddev *mddev) rdev->saved_raid_disk = -1; md_update_sb(mddev, 1); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery); + clear_bit(MD_RECOVERY_DONE, &mddev->recovery); clear_bit(MD_RECOVERY_SYNC, &mddev->recovery); clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery); @@ -8652,6 +8913,28 @@ err_wq: return ret; } +void md_reload_sb(struct mddev *mddev) +{ + struct md_rdev *rdev, *tmp; + + rdev_for_each_safe(rdev, tmp, mddev) { + rdev->sb_loaded = 0; + ClearPageUptodate(rdev->sb_page); + } + mddev->raid_disks = 0; + analyze_sbs(mddev); + rdev_for_each_safe(rdev, tmp, mddev) { + struct mdp_superblock_1 *sb = page_address(rdev->sb_page); + /* since we don't write to faulty devices, we figure out if the + * disk is faulty by comparing events + */ + if (mddev->events > sb->events) + set_bit(Faulty, &rdev->flags); + } + +} +EXPORT_SYMBOL(md_reload_sb); + #ifndef MODULE /* @@ -8761,13 +9044,7 @@ static int get_ro(char *buffer, struct kernel_param *kp) } static int set_ro(const char *val, struct kernel_param *kp) { - char *e; - int num = simple_strtoul(val, &e, 10); - if (*val && (*e == '\0' || *e == '\n')) { - start_readonly = num; - return 0; - } - return -EINVAL; + return kstrtouint(val, 10, (unsigned int *)&start_readonly); } module_param_call(start_ro, set_ro, get_ro, NULL, S_IRUSR|S_IWUSR); |