*/
static int md_make_request(struct request_queue *q, struct bio *bio)
{
+ const int rw = bio_data_dir(bio);
mddev_t *mddev = q->queuedata;
int rv;
+ int cpu;
+
if (mddev == NULL || mddev->pers == NULL) {
bio_io_error(bio);
return 0;
}
atomic_inc(&mddev->active_io);
rcu_read_unlock();
- rv = mddev->pers->make_request(q, bio);
+
+ rv = mddev->pers->make_request(mddev, bio);
+
+ cpu = part_stat_lock();
+ part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
+ part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw],
+ bio_sectors(bio));
+ part_stat_unlock();
+
if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended)
wake_up(&mddev->sb_wait);
bio_endio(bio, 0);
else {
bio->bi_rw &= ~(1<<BIO_RW_BARRIER);
- if (mddev->pers->make_request(mddev->queue, bio))
+ if (mddev->pers->make_request(mddev, bio))
generic_make_request(bio);
mddev->barrier = POST_REQUEST_BARRIER;
submit_barriers(mddev);
return mutex_trylock(&mddev->reconfig_mutex);
}
-static inline void mddev_unlock(mddev_t * mddev)
+static struct attribute_group md_redundancy_group;
+
+static void mddev_unlock(mddev_t * mddev)
{
- mutex_unlock(&mddev->reconfig_mutex);
+ if (mddev->to_remove) {
+ /* These cannot be removed under reconfig_mutex as
+ * an access to the files will try to take reconfig_mutex
+ * while holding the file unremovable, which leads to
+ * a deadlock.
+ * So hold open_mutex instead - we are allowed to take
+ * it while holding reconfig_mutex, and md_run can
+ * use it to wait for the remove to complete.
+ */
+ struct attribute_group *to_remove = mddev->to_remove;
+ mddev->to_remove = NULL;
+ mutex_lock(&mddev->open_mutex);
+ mutex_unlock(&mddev->reconfig_mutex);
+
+ if (to_remove != &md_redundancy_group)
+ sysfs_remove_group(&mddev->kobj, to_remove);
+ if (mddev->pers == NULL ||
+ mddev->pers->sync_request == NULL) {
+ sysfs_remove_group(&mddev->kobj, &md_redundancy_group);
+ if (mddev->sysfs_action)
+ sysfs_put(mddev->sysfs_action);
+ mddev->sysfs_action = NULL;
+ }
+ mutex_unlock(&mddev->open_mutex);
+ } else
+ mutex_unlock(&mddev->reconfig_mutex);
md_wakeup_thread(mddev->thread);
}
return err;
sprintf(nm, "rd%d", rdev->raid_disk);
sysfs_remove_link(&rdev->mddev->kobj, nm);
+ rdev->raid_disk = -1;
set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
md_wakeup_thread(rdev->mddev->thread);
} else if (rdev->mddev->pers) {
i = 0;
rdev_for_each(rdev, tmp, mddev) {
- if (rdev->desc_nr >= mddev->max_disks ||
- i > mddev->max_disks) {
+ if (mddev->max_disks &&
+ (rdev->desc_nr >= mddev->max_disks ||
+ i > mddev->max_disks)) {
printk(KERN_WARNING
"md: %s: %s: only %d devices permitted\n",
mdname(mddev), bdevname(rdev->bdev, b),
/* Looks like we have a winner */
mddev_suspend(mddev);
mddev->pers->stop(mddev);
+
+ if (mddev->pers->sync_request == NULL &&
+ pers->sync_request != NULL) {
+ /* need to add the md_redundancy_group */
+ if (sysfs_create_group(&mddev->kobj, &md_redundancy_group))
+ printk(KERN_WARNING
+ "md: cannot register extra attributes for %s\n",
+ mdname(mddev));
+ mddev->sysfs_action = sysfs_get_dirent(mddev->kobj.sd, "sync_action");
+ }
+ if (mddev->pers->sync_request != NULL &&
+ pers->sync_request == NULL) {
+ /* need to remove the md_redundancy_group */
+ if (mddev->to_remove == NULL)
+ mddev->to_remove = &md_redundancy_group;
+ }
+
+ if (mddev->pers->sync_request == NULL &&
+ mddev->external) {
+ /* We are converting from a no-redundancy array
+ * to a redundancy array and metadata is managed
+ * externally so we need to be sure that writes
+ * won't block due to a need to transition
+ * clean->dirty
+ * until external management is started.
+ */
+ mddev->in_sync = 0;
+ mddev->safemode_delay = 0;
+ mddev->safemode = 0;
+ }
+
module_put(mddev->pers->owner);
/* Invalidate devices that are now superfluous */
list_for_each_entry(rdev, &mddev->disks, same_set)
mddev->layout = mddev->new_layout;
mddev->chunk_sectors = mddev->new_chunk_sectors;
mddev->delta_disks = 0;
+ if (mddev->pers->sync_request == NULL) {
+ /* this is now an array without redundancy, so
+ * it must always be in_sync
+ */
+ mddev->in_sync = 1;
+ del_timer_sync(&mddev->safemode_timer);
+ }
pers->run(mddev);
mddev_resume(mddev);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
+ sysfs_notify(&mddev->kobj, NULL, "level");
return rv;
}
}
static int do_md_stop(mddev_t * mddev, int ro, int is_open);
+static int md_set_readonly(mddev_t * mddev, int is_open);
static int do_md_run(mddev_t * mddev);
static int restart_array(mddev_t *mddev);
break; /* not supported yet */
case readonly:
if (mddev->pers)
- err = do_md_stop(mddev, 1, 0);
+ err = md_set_readonly(mddev, 0);
else {
mddev->ro = 1;
set_disk_ro(mddev->gendisk, 1);
case read_auto:
if (mddev->pers) {
if (mddev->ro == 0)
- err = do_md_stop(mddev, 1, 0);
+ err = md_set_readonly(mddev, 0);
else if (mddev->ro == 1)
err = restart_array(mddev);
if (err == 0) {
{
mddev_t *mddev = container_of(ws, mddev_t, del_work);
- if (mddev->private) {
- sysfs_remove_group(&mddev->kobj, &md_redundancy_group);
- if (mddev->private != (void*)1)
- sysfs_remove_group(&mddev->kobj, mddev->private);
- if (mddev->sysfs_action)
- sysfs_put(mddev->sysfs_action);
- mddev->sysfs_action = NULL;
- mddev->private = NULL;
- }
sysfs_remove_group(&mddev->kobj, &md_bitmap_group);
kobject_del(&mddev->kobj);
kobject_put(&mddev->kobj);
static int start_dirty_degraded;
-static int do_md_run(mddev_t * mddev)
+static int md_run(mddev_t *mddev)
{
int err;
mdk_rdev_t *rdev;
- struct gendisk *disk;
struct mdk_personality *pers;
if (list_empty(&mddev->disks))
if (mddev->pers)
return -EBUSY;
+ /* These two calls synchronise us with the
+ * sysfs_remove_group calls in mddev_unlock,
+ * so they must have completed.
+ */
+ mutex_lock(&mddev->open_mutex);
+ mutex_unlock(&mddev->open_mutex);
+
/*
* Analyze all RAID superblock(s)
*/
sysfs_notify_dirent(rdev->sysfs_state);
}
- disk = mddev->gendisk;
-
spin_lock(&pers_lock);
pers = find_pers(mddev->level, mddev->clevel);
if (!pers || !try_module_get(pers->owner)) {
if (mddev->flags)
md_update_sb(mddev, 0);
- set_capacity(disk, mddev->array_sectors);
-
md_wakeup_thread(mddev->thread);
md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
- revalidate_disk(mddev->gendisk);
- mddev->changed = 1;
md_new_event(mddev);
sysfs_notify_dirent(mddev->sysfs_state);
if (mddev->sysfs_action)
sysfs_notify_dirent(mddev->sysfs_action);
sysfs_notify(&mddev->kobj, NULL, "degraded");
- kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
return 0;
}
+static int do_md_run(mddev_t *mddev)
+{
+ int err;
+
+ err = md_run(mddev);
+ if (err)
+ goto out;
+
+ set_capacity(mddev->gendisk, mddev->array_sectors);
+ revalidate_disk(mddev->gendisk);
+ kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
+out:
+ return err;
+}
+
static int restart_array(mddev_t *mddev)
{
struct gendisk *disk = mddev->gendisk;
spin_unlock(&inode->i_lock);
}
+static void md_clean(mddev_t *mddev)
+{
+ mddev->array_sectors = 0;
+ mddev->external_size = 0;
+ mddev->dev_sectors = 0;
+ mddev->raid_disks = 0;
+ mddev->recovery_cp = 0;
+ mddev->resync_min = 0;
+ mddev->resync_max = MaxSector;
+ mddev->reshape_position = MaxSector;
+ mddev->external = 0;
+ mddev->persistent = 0;
+ mddev->level = LEVEL_NONE;
+ mddev->clevel[0] = 0;
+ mddev->flags = 0;
+ mddev->ro = 0;
+ mddev->metadata_type[0] = 0;
+ mddev->chunk_sectors = 0;
+ mddev->ctime = mddev->utime = 0;
+ mddev->layout = 0;
+ mddev->max_disks = 0;
+ mddev->events = 0;
+ mddev->delta_disks = 0;
+ mddev->new_level = LEVEL_NONE;
+ mddev->new_layout = 0;
+ mddev->new_chunk_sectors = 0;
+ mddev->curr_resync = 0;
+ mddev->resync_mismatches = 0;
+ mddev->suspend_lo = mddev->suspend_hi = 0;
+ mddev->sync_speed_min = mddev->sync_speed_max = 0;
+ mddev->recovery = 0;
+ mddev->in_sync = 0;
+ mddev->degraded = 0;
+ mddev->barriers_work = 0;
+ mddev->safemode = 0;
+ mddev->bitmap_info.offset = 0;
+ mddev->bitmap_info.default_offset = 0;
+ mddev->bitmap_info.chunksize = 0;
+ mddev->bitmap_info.daemon_sleep = 0;
+ mddev->bitmap_info.max_write_behind = 0;
+}
+
+static void md_stop_writes(mddev_t *mddev)
+{
+ if (mddev->sync_thread) {
+ set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+ md_unregister_thread(mddev->sync_thread);
+ mddev->sync_thread = NULL;
+ }
+
+ del_timer_sync(&mddev->safemode_timer);
+
+ bitmap_flush(mddev);
+ md_super_wait(mddev);
+
+ if (!mddev->in_sync || mddev->flags) {
+ /* mark array as shutdown cleanly */
+ mddev->in_sync = 1;
+ md_update_sb(mddev, 1);
+ }
+}
+
+static void md_stop(mddev_t *mddev)
+{
+ md_stop_writes(mddev);
+
+ mddev->pers->stop(mddev);
+ if (mddev->pers->sync_request && mddev->to_remove == NULL)
+ mddev->to_remove = &md_redundancy_group;
+ module_put(mddev->pers->owner);
+ mddev->pers = NULL;
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+}
+
+static int md_set_readonly(mddev_t *mddev, int is_open)
+{
+ int err = 0;
+ mutex_lock(&mddev->open_mutex);
+ if (atomic_read(&mddev->openers) > is_open) {
+ printk("md: %s still in use.\n",mdname(mddev));
+ err = -EBUSY;
+ goto out;
+ }
+ if (mddev->pers) {
+ md_stop_writes(mddev);
+
+ err = -ENXIO;
+ if (mddev->ro==1)
+ goto out;
+ mddev->ro = 1;
+ set_disk_ro(mddev->gendisk, 1);
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+ sysfs_notify_dirent(mddev->sysfs_state);
+ err = 0;
+ }
+out:
+ mutex_unlock(&mddev->open_mutex);
+ return err;
+}
+
/* mode:
* 0 - completely stop and dis-assemble array
- * 1 - switch to readonly
* 2 - stop but do not disassemble array
*/
static int do_md_stop(mddev_t * mddev, int mode, int is_open)
err = -EBUSY;
} else if (mddev->pers) {
- if (mddev->sync_thread) {
- set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
- set_bit(MD_RECOVERY_INTR, &mddev->recovery);
- md_unregister_thread(mddev->sync_thread);
- mddev->sync_thread = NULL;
- }
-
- del_timer_sync(&mddev->safemode_timer);
+ if (mddev->ro)
+ set_disk_ro(disk, 0);
- switch(mode) {
- case 1: /* readonly */
- err = -ENXIO;
- if (mddev->ro==1)
- goto out;
- mddev->ro = 1;
- break;
- case 0: /* disassemble */
- case 2: /* stop */
- bitmap_flush(mddev);
- md_super_wait(mddev);
- if (mddev->ro)
- set_disk_ro(disk, 0);
+ md_stop(mddev);
+ mddev->queue->merge_bvec_fn = NULL;
+ mddev->queue->unplug_fn = NULL;
+ mddev->queue->backing_dev_info.congested_fn = NULL;
- mddev->pers->stop(mddev);
- mddev->queue->merge_bvec_fn = NULL;
- mddev->queue->unplug_fn = NULL;
- mddev->queue->backing_dev_info.congested_fn = NULL;
- module_put(mddev->pers->owner);
- if (mddev->pers->sync_request && mddev->private == NULL)
- mddev->private = (void*)1;
- mddev->pers = NULL;
- /* tell userspace to handle 'inactive' */
- sysfs_notify_dirent(mddev->sysfs_state);
+ /* tell userspace to handle 'inactive' */
+ sysfs_notify_dirent(mddev->sysfs_state);
- list_for_each_entry(rdev, &mddev->disks, same_set)
- if (rdev->raid_disk >= 0) {
- char nm[20];
- sprintf(nm, "rd%d", rdev->raid_disk);
- sysfs_remove_link(&mddev->kobj, nm);
- }
+ list_for_each_entry(rdev, &mddev->disks, same_set)
+ if (rdev->raid_disk >= 0) {
+ char nm[20];
+ sprintf(nm, "rd%d", rdev->raid_disk);
+ sysfs_remove_link(&mddev->kobj, nm);
+ }
- set_capacity(disk, 0);
- mddev->changed = 1;
+ set_capacity(disk, 0);
+ revalidate_disk(disk);
- if (mddev->ro)
- mddev->ro = 0;
- }
- if (!mddev->in_sync || mddev->flags) {
- /* mark array as shutdown cleanly */
- mddev->in_sync = 1;
- md_update_sb(mddev, 1);
- }
- if (mode == 1)
- set_disk_ro(disk, 1);
- clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+ if (mddev->ro)
+ mddev->ro = 0;
+
err = 0;
}
-out:
mutex_unlock(&mddev->open_mutex);
if (err)
return err;
export_array(mddev);
- mddev->array_sectors = 0;
- mddev->external_size = 0;
- mddev->dev_sectors = 0;
- mddev->raid_disks = 0;
- mddev->recovery_cp = 0;
- mddev->resync_min = 0;
- mddev->resync_max = MaxSector;
- mddev->reshape_position = MaxSector;
- mddev->external = 0;
- mddev->persistent = 0;
- mddev->level = LEVEL_NONE;
- mddev->clevel[0] = 0;
- mddev->flags = 0;
- mddev->ro = 0;
- mddev->metadata_type[0] = 0;
- mddev->chunk_sectors = 0;
- mddev->ctime = mddev->utime = 0;
- mddev->layout = 0;
- mddev->max_disks = 0;
- mddev->events = 0;
- mddev->delta_disks = 0;
- mddev->new_level = LEVEL_NONE;
- mddev->new_layout = 0;
- mddev->new_chunk_sectors = 0;
- mddev->curr_resync = 0;
- mddev->resync_mismatches = 0;
- mddev->suspend_lo = mddev->suspend_hi = 0;
- mddev->sync_speed_min = mddev->sync_speed_max = 0;
- mddev->recovery = 0;
- mddev->in_sync = 0;
- mddev->changed = 0;
- mddev->degraded = 0;
- mddev->barriers_work = 0;
- mddev->safemode = 0;
- mddev->bitmap_info.offset = 0;
- mddev->bitmap_info.default_offset = 0;
- mddev->bitmap_info.chunksize = 0;
- mddev->bitmap_info.daemon_sleep = 0;
- mddev->bitmap_info.max_write_behind = 0;
+ md_clean(mddev);
kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
if (mddev->hold_active == UNTIL_STOP)
mddev->hold_active = 0;
- } else if (mddev->pers)
- printk(KERN_INFO "md: %s switched to read-only mode.\n",
- mdname(mddev));
+ }
err = 0;
blk_integrity_unregister(disk);
md_new_event(mddev);
if (mddev->pers->check_reshape == NULL)
return -EINVAL;
if (raid_disks <= 0 ||
- raid_disks >= mddev->max_disks)
+ (mddev->max_disks && raid_disks >= mddev->max_disks))
return -EINVAL;
if (mddev->sync_thread || mddev->reshape_position != MaxSector)
return -EBUSY;
geo->heads = 2;
geo->sectors = 4;
- geo->cylinders = get_capacity(mddev->gendisk) / 8;
+ geo->cylinders = mddev->array_sectors / 8;
return 0;
}
int err = 0;
void __user *argp = (void __user *)arg;
mddev_t *mddev = NULL;
+ int ro;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
goto done_unlock;
case STOP_ARRAY_RO:
- err = do_md_stop(mddev, 1, 1);
+ err = md_set_readonly(mddev, 1);
goto done_unlock;
+ case BLKROSET:
+ if (get_user(ro, (int __user *)(arg))) {
+ err = -EFAULT;
+ goto done_unlock;
+ }
+ err = -EINVAL;
+
+ /* if the bdev is going readonly the value of mddev->ro
+ * does not matter, no writes are coming
+ */
+ if (ro)
+ goto done_unlock;
+
+ /* are we are already prepared for writes? */
+ if (mddev->ro != 1)
+ goto done_unlock;
+
+ /* transitioning to readauto need only happen for
+ * arrays that call md_write_start
+ */
+ if (mddev->pers) {
+ err = restart_array(mddev);
+ if (err == 0) {
+ mddev->ro = 2;
+ set_disk_ro(mddev->gendisk, 0);
+ }
+ }
+ goto done_unlock;
}
/*
atomic_inc(&mddev->openers);
mutex_unlock(&mddev->open_mutex);
- check_disk_change(bdev);
out:
return err;
}
return 0;
}
-
-static int md_media_changed(struct gendisk *disk)
-{
- mddev_t *mddev = disk->private_data;
-
- return mddev->changed;
-}
-
-static int md_revalidate(struct gendisk *disk)
-{
- mddev_t *mddev = disk->private_data;
-
- mddev->changed = 0;
- return 0;
-}
static const struct block_device_operations md_fops =
{
.owner = THIS_MODULE,
.compat_ioctl = md_compat_ioctl,
#endif
.getgeo = md_getgeo,
- .media_changed = md_media_changed,
- .revalidate_disk= md_revalidate,
};
static int md_thread(void * arg)
mddev->pers->error_handler(mddev,rdev);
if (mddev->degraded)
set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
- set_bit(StateChanged, &rdev->flags);
+ sysfs_notify_dirent(rdev->sysfs_state);
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
if (mddev->flags)
md_update_sb(mddev, 0);
- list_for_each_entry(rdev, &mddev->disks, same_set)
- if (test_and_clear_bit(StateChanged, &rdev->flags))
- sysfs_notify_dirent(rdev->sysfs_state);
-
-
if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) &&
!test_bit(MD_RECOVERY_DONE, &mddev->recovery)) {
/* resync/recovery still happening */
* appears to still be in use. Hence
* the '100'.
*/
- do_md_stop(mddev, 1, 100);
+ md_set_readonly(mddev, 100);
mddev_unlock(mddev);
}
/*