#include <linux/slab.h>
#include "md.h"
#include "bitmap.h"
+#include "md-cluster.h"
#ifndef MODULE
static void autostart_arrays(int part);
static LIST_HEAD(pers_list);
static DEFINE_SPINLOCK(pers_lock);
+struct md_cluster_operations *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;
err = -EBUSY;
else {
struct mddev *mddev = rdev->mddev;
+ if (mddev_is_clustered(mddev))
+ md_cluster_ops->metadata_update_start(mddev);
kick_rdev_from_array(rdev);
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")) {
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)
}
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);
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) {
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)
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;
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);
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;
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
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.
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;
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);
+ }
}
if (fd < 0 || err) {
bitmap_destroy(mddev);
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);
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);
+ }
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);
}
}
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;
}
}
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;
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);
md_new_event(mddev);
update_time = jiffies;
+ if (mddev_is_clustered(mddev))
+ md_cluster_ops->resync_info_update(mddev, j, max_sectors);
+
blk_start_plug(&plug);
while (j < max_sectors) {
sector_t sectors;
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
/* tell personality that we are finished */
mddev->pers->sync_request(mddev, max_sectors, &skipped, 1);
+ if (mddev_is_clustered(mddev))
+ md_cluster_ops->resync_info_update(mddev, 0, 0);
+
if (!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) &&
mddev->curr_resync > 2) {
if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
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)) {
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);
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_SYNC, &mddev->recovery);
clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);