* Once ->stop is called and completes, the module will be completely
* unused.
*/
-static void mddev_suspend(mddev_t *mddev)
+void mddev_suspend(mddev_t *mddev)
{
BUG_ON(mddev->suspended);
mddev->suspended = 1;
wait_event(mddev->sb_wait, atomic_read(&mddev->active_io) == 0);
mddev->pers->quiesce(mddev, 1);
}
+EXPORT_SYMBOL_GPL(mddev_suspend);
-static void mddev_resume(mddev_t *mddev)
+void mddev_resume(mddev_t *mddev)
{
mddev->suspended = 0;
wake_up(&mddev->sb_wait);
mddev->pers->quiesce(mddev, 0);
}
+EXPORT_SYMBOL_GPL(mddev_resume);
int mddev_congested(mddev_t *mddev, int bits)
{
}
EXPORT_SYMBOL(md_barrier_request);
+/* Support for plugging.
+ * This mirrors the plugging support in request_queue, but does not
+ * require having a whole queue
+ */
+static void plugger_work(struct work_struct *work)
+{
+ struct plug_handle *plug =
+ container_of(work, struct plug_handle, unplug_work);
+ plug->unplug_fn(plug);
+}
+static void plugger_timeout(unsigned long data)
+{
+ struct plug_handle *plug = (void *)data;
+ kblockd_schedule_work(NULL, &plug->unplug_work);
+}
+void plugger_init(struct plug_handle *plug,
+ void (*unplug_fn)(struct plug_handle *))
+{
+ plug->unplug_flag = 0;
+ plug->unplug_fn = unplug_fn;
+ init_timer(&plug->unplug_timer);
+ plug->unplug_timer.function = plugger_timeout;
+ plug->unplug_timer.data = (unsigned long)plug;
+ INIT_WORK(&plug->unplug_work, plugger_work);
+}
+EXPORT_SYMBOL_GPL(plugger_init);
+
+void plugger_set_plug(struct plug_handle *plug)
+{
+ if (!test_and_set_bit(PLUGGED_FLAG, &plug->unplug_flag))
+ mod_timer(&plug->unplug_timer, jiffies + msecs_to_jiffies(3)+1);
+}
+EXPORT_SYMBOL_GPL(plugger_set_plug);
+
+int plugger_remove_plug(struct plug_handle *plug)
+{
+ if (test_and_clear_bit(PLUGGED_FLAG, &plug->unplug_flag)) {
+ del_timer(&plug->unplug_timer);
+ return 1;
+ } else
+ return 0;
+}
+EXPORT_SYMBOL_GPL(plugger_remove_plug);
+
+
static inline mddev_t *mddev_get(mddev_t *mddev)
{
atomic_inc(&mddev->active);
spin_unlock(&all_mddevs_lock);
}
-static void mddev_init(mddev_t *mddev)
+void mddev_init(mddev_t *mddev)
{
mutex_init(&mddev->open_mutex);
mutex_init(&mddev->reconfig_mutex);
mddev->resync_max = MaxSector;
mddev->level = LEVEL_NONE;
}
+EXPORT_SYMBOL_GPL(mddev_init);
static mddev_t * mddev_find(dev_t unit)
{
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;
+ if (mddev->kobj.sd) {
+ 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
goto fail;
ko = &part_to_dev(rdev->bdev->bd_part)->kobj;
- if ((err = sysfs_create_link(&rdev->kobj, ko, "block"))) {
- kobject_del(&rdev->kobj);
- goto fail;
- }
- rdev->sysfs_state = sysfs_get_dirent(rdev->kobj.sd, NULL, "state");
+ if (sysfs_create_link(&rdev->kobj, ko, "block"))
+ /* failure here is OK */;
+ rdev->sysfs_state = sysfs_get_dirent_safe(rdev->kobj.sd, "state");
list_add_rcu(&rdev->same_set, &mddev->disks);
bd_claim_by_disk(rdev->bdev, rdev->bdev->bd_holder, mddev->gendisk);
/* First make sure individual recovery_offsets are correct */
list_for_each_entry(rdev, &mddev->disks, same_set) {
if (rdev->raid_disk >= 0 &&
+ mddev->delta_disks >= 0 &&
!test_bit(In_sync, &rdev->flags) &&
mddev->curr_resync_completed > rdev->recovery_offset)
rdev->recovery_offset = mddev->curr_resync_completed;
set_bit(In_sync, &rdev->flags);
err = 0;
}
- if (!err && rdev->sysfs_state)
- sysfs_notify_dirent(rdev->sysfs_state);
+ if (!err)
+ sysfs_notify_dirent_safe(rdev->sysfs_state);
return err ? err : len;
}
static struct rdev_sysfs_entry rdev_state =
rdev->raid_disk = -1;
return err;
} else
- sysfs_notify_dirent(rdev->sysfs_state);
+ sysfs_notify_dirent_safe(rdev->sysfs_state);
sprintf(nm, "rd%d", rdev->raid_disk);
if (sysfs_create_link(&rdev->mddev->kobj, &rdev->kobj, nm))
- printk(KERN_WARNING
- "md: cannot register "
- "%s for %s\n",
- nm, mdname(rdev->mddev));
-
+ /* failure here is OK */;
/* don't wakeup anyone, leave that to userspace. */
} else {
if (slot >= rdev->mddev->raid_disks)
clear_bit(Faulty, &rdev->flags);
clear_bit(WriteMostly, &rdev->flags);
set_bit(In_sync, &rdev->flags);
- sysfs_notify_dirent(rdev->sysfs_state);
+ sysfs_notify_dirent_safe(rdev->sysfs_state);
}
return len;
}
.default_attrs = rdev_default_attrs,
};
+void md_rdev_init(mdk_rdev_t *rdev)
+{
+ rdev->desc_nr = -1;
+ rdev->saved_raid_disk = -1;
+ rdev->raid_disk = -1;
+ rdev->flags = 0;
+ rdev->data_offset = 0;
+ rdev->sb_events = 0;
+ rdev->last_read_error.tv_sec = 0;
+ rdev->last_read_error.tv_nsec = 0;
+ atomic_set(&rdev->nr_pending, 0);
+ atomic_set(&rdev->read_errors, 0);
+ atomic_set(&rdev->corrected_errors, 0);
+
+ INIT_LIST_HEAD(&rdev->same_set);
+ init_waitqueue_head(&rdev->blocked_wait);
+}
+EXPORT_SYMBOL_GPL(md_rdev_init);
/*
* Import a device. If 'super_format' >= 0, then sanity check the superblock
*
return ERR_PTR(-ENOMEM);
}
+ md_rdev_init(rdev);
if ((err = alloc_disk_sb(rdev)))
goto abort_free;
kobject_init(&rdev->kobj, &rdev_ktype);
- rdev->desc_nr = -1;
- rdev->saved_raid_disk = -1;
- rdev->raid_disk = -1;
- rdev->flags = 0;
- rdev->data_offset = 0;
- rdev->sb_events = 0;
- rdev->last_read_error.tv_sec = 0;
- rdev->last_read_error.tv_nsec = 0;
- atomic_set(&rdev->nr_pending, 0);
- atomic_set(&rdev->read_errors, 0);
- atomic_set(&rdev->corrected_errors, 0);
-
size = rdev->bdev->bd_inode->i_size >> BLOCK_SIZE_BITS;
if (!size) {
printk(KERN_WARNING
}
}
- INIT_LIST_HEAD(&rdev->same_set);
- init_waitqueue_head(&rdev->blocked_wait);
-
return rdev;
abort_free:
return -EINVAL;
}
+ list_for_each_entry(rdev, &mddev->disks, same_set)
+ rdev->new_raid_disk = rdev->raid_disk;
+
/* ->takeover must set new_* and/or delta_disks
* if it succeeds, and may set them when it fails.
*/
mddev->safemode = 0;
}
- module_put(mddev->pers->owner);
- /* Invalidate devices that are now superfluous */
- list_for_each_entry(rdev, &mddev->disks, same_set)
- if (rdev->raid_disk >= mddev->raid_disks) {
- rdev->raid_disk = -1;
+ list_for_each_entry(rdev, &mddev->disks, same_set) {
+ char nm[20];
+ if (rdev->raid_disk < 0)
+ continue;
+ if (rdev->new_raid_disk > mddev->raid_disks)
+ rdev->new_raid_disk = -1;
+ if (rdev->new_raid_disk == rdev->raid_disk)
+ continue;
+ 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)
+ continue;
+ if (rdev->new_raid_disk == rdev->raid_disk)
+ continue;
+ rdev->raid_disk = rdev->new_raid_disk;
+ if (rdev->raid_disk < 0)
clear_bit(In_sync, &rdev->flags);
+ else {
+ char nm[20];
+ sprintf(nm, "rd%d", rdev->raid_disk);
+ if(sysfs_create_link(&mddev->kobj, &rdev->kobj, nm))
+ printk("md: cannot register %s for %s after level change\n",
+ nm, mdname(mddev));
}
+ }
+
+ module_put(mddev->pers->owner);
mddev->pers = pers;
mddev->private = priv;
strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
if (err)
return err;
else {
- sysfs_notify_dirent(mddev->sysfs_state);
+ sysfs_notify_dirent_safe(mddev->sysfs_state);
return len;
}
}
}
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
- sysfs_notify_dirent(mddev->sysfs_action);
+ sysfs_notify_dirent_safe(mddev->sysfs_action);
return len;
}
disk->disk_name);
error = 0;
}
- if (sysfs_create_group(&mddev->kobj, &md_bitmap_group))
+ if (mddev->kobj.sd &&
+ sysfs_create_group(&mddev->kobj, &md_bitmap_group))
printk(KERN_DEBUG "pointless warning\n");
abort:
mutex_unlock(&disks_mutex);
- if (!error) {
+ if (!error && mddev->kobj.sd) {
kobject_uevent(&mddev->kobj, KOBJ_ADD);
- mddev->sysfs_state = sysfs_get_dirent(mddev->kobj.sd, NULL, "array_state");
+ mddev->sysfs_state = sysfs_get_dirent_safe(mddev->kobj.sd, "array_state");
}
mddev_put(mddev);
return error;
if (!atomic_read(&mddev->writes_pending)) {
mddev->safemode = 1;
if (mddev->external)
- sysfs_notify_dirent(mddev->sysfs_state);
+ sysfs_notify_dirent_safe(mddev->sysfs_state);
}
md_wakeup_thread(mddev->thread);
}
static int start_dirty_degraded;
-static int md_run(mddev_t *mddev)
+int md_run(mddev_t *mddev)
{
int err;
mdk_rdev_t *rdev;
return -EINVAL;
}
}
- sysfs_notify_dirent(rdev->sysfs_state);
+ sysfs_notify_dirent_safe(rdev->sysfs_state);
}
spin_lock(&pers_lock);
return err;
}
if (mddev->pers->sync_request) {
- if (sysfs_create_group(&mddev->kobj, &md_redundancy_group))
+ if (mddev->kobj.sd &&
+ 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, NULL, "sync_action");
+ mddev->sysfs_action = sysfs_get_dirent_safe(mddev->kobj.sd, "sync_action");
} else if (mddev->ro == 2) /* auto-readonly not meaningful */
mddev->ro = 0;
char nm[20];
sprintf(nm, "rd%d", rdev->raid_disk);
if (sysfs_create_link(&mddev->kobj, &rdev->kobj, nm))
- printk("md: cannot register %s for %s\n",
- nm, mdname(mddev));
+ /* failure here is OK */;
}
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
md_new_event(mddev);
- sysfs_notify_dirent(mddev->sysfs_state);
- if (mddev->sysfs_action)
- sysfs_notify_dirent(mddev->sysfs_action);
+ sysfs_notify_dirent_safe(mddev->sysfs_state);
+ sysfs_notify_dirent_safe(mddev->sysfs_action);
sysfs_notify(&mddev->kobj, NULL, "degraded");
return 0;
}
+EXPORT_SYMBOL_GPL(md_run);
static int do_md_run(mddev_t *mddev)
{
err = md_run(mddev);
if (err)
goto out;
-
+ err = bitmap_load(mddev);
+ if (err) {
+ bitmap_destroy(mddev);
+ goto out;
+ }
set_capacity(mddev->gendisk, mddev->array_sectors);
revalidate_disk(mddev->gendisk);
kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
md_wakeup_thread(mddev->sync_thread);
- sysfs_notify_dirent(mddev->sysfs_state);
+ sysfs_notify_dirent_safe(mddev->sysfs_state);
return 0;
}
mddev->bitmap_info.chunksize = 0;
mddev->bitmap_info.daemon_sleep = 0;
mddev->bitmap_info.max_write_behind = 0;
+ mddev->plug = NULL;
}
-static void md_stop_writes(mddev_t *mddev)
+void md_stop_writes(mddev_t *mddev)
{
if (mddev->sync_thread) {
set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
md_update_sb(mddev, 1);
}
}
+EXPORT_SYMBOL_GPL(md_stop_writes);
-static void md_stop(mddev_t *mddev)
+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;
mddev->pers = NULL;
clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
}
+EXPORT_SYMBOL_GPL(md_stop);
static int md_set_readonly(mddev_t *mddev, int is_open)
{
mddev->ro = 1;
set_disk_ro(mddev->gendisk, 1);
clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
- sysfs_notify_dirent(mddev->sysfs_state);
+ sysfs_notify_dirent_safe(mddev->sysfs_state);
err = 0;
}
out:
*/
static int do_md_stop(mddev_t * mddev, int mode, int is_open)
{
- int err = 0;
+ int err = 0, revalidate = 0;
struct gendisk *disk = mddev->gendisk;
mdk_rdev_t *rdev;
if (mddev->ro)
set_disk_ro(disk, 0);
+ md_stop_writes(mddev);
md_stop(mddev);
mddev->queue->merge_bvec_fn = NULL;
mddev->queue->unplug_fn = NULL;
mddev->queue->backing_dev_info.congested_fn = NULL;
/* tell userspace to handle 'inactive' */
- sysfs_notify_dirent(mddev->sysfs_state);
+ sysfs_notify_dirent_safe(mddev->sysfs_state);
list_for_each_entry(rdev, &mddev->disks, same_set)
if (rdev->raid_disk >= 0) {
}
set_capacity(disk, 0);
- revalidate_disk(disk);
+ revalidate = 1;
if (mddev->ro)
mddev->ro = 0;
err = 0;
}
mutex_unlock(&mddev->open_mutex);
+ if (revalidate)
+ revalidate_disk(disk);
if (err)
return err;
/*
err = 0;
blk_integrity_unregister(disk);
md_new_event(mddev);
- sysfs_notify_dirent(mddev->sysfs_state);
+ sysfs_notify_dirent_safe(mddev->sysfs_state);
return err;
}
if (err)
export_rdev(rdev);
else
- sysfs_notify_dirent(rdev->sysfs_state);
+ sysfs_notify_dirent_safe(rdev->sysfs_state);
md_update_sb(mddev, 1);
if (mddev->degraded)
err = 0;
if (mddev->pers) {
mddev->pers->quiesce(mddev, 1);
- if (fd >= 0)
+ if (fd >= 0) {
err = bitmap_create(mddev);
+ if (!err)
+ err = bitmap_load(mddev);
+ }
if (fd < 0 || err) {
bitmap_destroy(mddev);
fd = -1; /* make sure to put the file */
mddev->bitmap_info.default_offset;
mddev->pers->quiesce(mddev, 1);
rv = bitmap_create(mddev);
+ if (!rv)
+ rv = bitmap_load(mddev);
if (rv)
bitmap_destroy(mddev);
mddev->pers->quiesce(mddev, 0);
if (_IOC_TYPE(cmd) == MD_MAJOR && mddev->ro && mddev->pers) {
if (mddev->ro == 2) {
mddev->ro = 0;
- sysfs_notify_dirent(mddev->sysfs_state);
+ sysfs_notify_dirent_safe(mddev->sysfs_state);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
} else {
atomic_inc(&mddev->openers);
mutex_unlock(&mddev->open_mutex);
+ check_disk_size_change(mddev->gendisk, bdev);
out:
return err;
}
mddev->pers->error_handler(mddev,rdev);
if (mddev->degraded)
set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
- sysfs_notify_dirent(rdev->sysfs_state);
+ sysfs_notify_dirent_safe(rdev->sysfs_state);
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
+ if (mddev->event_work.func)
+ schedule_work(&mddev->event_work);
md_new_event_inintr(mddev);
}
spin_unlock_irq(&mddev->write_lock);
}
if (did_change)
- sysfs_notify_dirent(mddev->sysfs_state);
+ sysfs_notify_dirent_safe(mddev->sysfs_state);
wait_event(mddev->sb_wait,
!test_bit(MD_CHANGE_CLEAN, &mddev->flags) &&
!test_bit(MD_CHANGE_PENDING, &mddev->flags));
mddev->safemode = 1;
spin_unlock_irq(&mddev->write_lock);
md_update_sb(mddev, 0);
- sysfs_notify_dirent(mddev->sysfs_state);
+ sysfs_notify_dirent_safe(mddev->sysfs_state);
} else
spin_unlock_irq(&mddev->write_lock);
}
EXPORT_SYMBOL_GPL(md_allow_write);
+void md_unplug(mddev_t *mddev)
+{
+ if (mddev->queue)
+ blk_unplug(mddev->queue);
+ if (mddev->plug)
+ mddev->plug->unplug_fn(mddev->plug);
+}
+
#define SYNC_MARKS 10
#define SYNC_MARK_STEP (3*HZ)
void md_do_sync(mddev_t *mddev)
>= mddev->resync_max - mddev->curr_resync_completed
)) {
/* time to update curr_resync_completed */
- blk_unplug(mddev->queue);
+ md_unplug(mddev);
wait_event(mddev->recovery_wait,
atomic_read(&mddev->recovery_active) == 0);
mddev->curr_resync_completed =
mddev->curr_resync;
- set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+ if (mddev->persistent)
+ set_bit(MD_CHANGE_CLEAN, &mddev->flags);
sysfs_notify(&mddev->kobj, NULL, "sync_completed");
}
* about not overloading the IO subsystem. (things like an
* e2fsck being done on the RAID array should execute fast)
*/
- blk_unplug(mddev->queue);
+ md_unplug(mddev);
cond_resched();
currspeed = ((unsigned long)(io_sectors-mddev->resync_mark_cnt))/2
* this also signals 'finished resyncing' to md_stop
*/
out:
- blk_unplug(mddev->queue);
+ md_unplug(mddev);
wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active));
rcu_read_lock();
list_for_each_entry_rcu(rdev, &mddev->disks, same_set)
if (rdev->raid_disk >= 0 &&
+ mddev->delta_disks >= 0 &&
!test_bit(Faulty, &rdev->flags) &&
!test_bit(In_sync, &rdev->flags) &&
rdev->recovery_offset < mddev->curr_resync)
sprintf(nm, "rd%d", rdev->raid_disk);
if (sysfs_create_link(&mddev->kobj,
&rdev->kobj, nm))
- printk(KERN_WARNING
- "md: cannot register "
- "%s for %s\n",
- nm, mdname(mddev));
+ /* failure here is OK */;
spares++;
md_new_event(mddev);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
mddev->safemode = 0;
spin_unlock_irq(&mddev->write_lock);
if (did_change)
- sysfs_notify_dirent(mddev->sysfs_state);
+ sysfs_notify_dirent_safe(mddev->sysfs_state);
}
if (mddev->flags)
mddev->recovery = 0;
/* flag recovery needed just to double check */
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
- sysfs_notify_dirent(mddev->sysfs_action);
+ sysfs_notify_dirent_safe(mddev->sysfs_action);
md_new_event(mddev);
goto unlock;
}
mddev->recovery = 0;
} else
md_wakeup_thread(mddev->sync_thread);
- sysfs_notify_dirent(mddev->sysfs_action);
+ sysfs_notify_dirent_safe(mddev->sysfs_action);
md_new_event(mddev);
}
unlock:
if (test_and_clear_bit(MD_RECOVERY_RECOVER,
&mddev->recovery))
if (mddev->sysfs_action)
- sysfs_notify_dirent(mddev->sysfs_action);
+ sysfs_notify_dirent_safe(mddev->sysfs_action);
}
mddev_unlock(mddev);
}
void md_wait_for_blocked_rdev(mdk_rdev_t *rdev, mddev_t *mddev)
{
- sysfs_notify_dirent(rdev->sysfs_state);
+ sysfs_notify_dirent_safe(rdev->sysfs_state);
wait_event_timeout(rdev->blocked_wait,
!test_bit(Blocked, &rdev->flags),
msecs_to_jiffies(5000));
git://bbs.cooldavid.org / net-next-2.6.git / blobdiff