#include <linux/raid/bitmap.h>
#include <linux/sysctl.h>
#include <linux/buffer_head.h> /* for invalidate_bdev */
-#include <linux/suspend.h>
#include <linux/poll.h>
#include <linux/mutex.h>
#include <linux/ctype.h>
+#include <linux/freezer.h>
#include <linux/init.h>
.sync_super = super_1_sync,
},
};
-
-static mdk_rdev_t * match_dev_unit(mddev_t *mddev, mdk_rdev_t *dev)
-{
- struct list_head *tmp;
- mdk_rdev_t *rdev;
-
- ITERATE_RDEV(mddev,rdev,tmp)
- if (rdev->bdev->bd_contains == dev->bdev->bd_contains)
- return rdev;
-
- return NULL;
-}
static int match_mddev_units(mddev_t *mddev1, mddev_t *mddev2)
{
- struct list_head *tmp;
- mdk_rdev_t *rdev;
+ struct list_head *tmp, *tmp2;
+ mdk_rdev_t *rdev, *rdev2;
ITERATE_RDEV(mddev1,rdev,tmp)
- if (match_dev_unit(mddev2, rdev))
- return 1;
+ ITERATE_RDEV(mddev2, rdev2, tmp2)
+ if (rdev->bdev->bd_contains ==
+ rdev2->bdev->bd_contains)
+ return 1;
return 0;
}
static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev)
{
- mdk_rdev_t *same_pdev;
- char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
+ char b[BDEVNAME_SIZE];
struct kobject *ko;
char *s;
+ int err;
if (rdev->mddev) {
MD_BUG();
else
mddev->size = rdev->size;
}
- same_pdev = match_dev_unit(mddev, rdev);
- if (same_pdev)
- printk(KERN_WARNING
- "%s: WARNING: %s appears to be on the same physical"
- " disk as %s. True\n protection against single-disk"
- " failure might be compromised.\n",
- mdname(mddev), bdevname(rdev->bdev,b),
- bdevname(same_pdev->bdev,b2));
/* Verify rdev->desc_nr is unique.
* If it is -1, assign a free number, else
while ( (s=strchr(rdev->kobj.k_name, '/')) != NULL)
*s = '!';
- list_add(&rdev->same_set, &mddev->disks);
rdev->mddev = mddev;
printk(KERN_INFO "md: bind<%s>\n", b);
rdev->kobj.parent = &mddev->kobj;
- kobject_add(&rdev->kobj);
+ if ((err = kobject_add(&rdev->kobj)))
+ goto fail;
if (rdev->bdev->bd_part)
ko = &rdev->bdev->bd_part->kobj;
else
ko = &rdev->bdev->bd_disk->kobj;
- sysfs_create_link(&rdev->kobj, ko, "block");
+ if ((err = sysfs_create_link(&rdev->kobj, ko, "block"))) {
+ kobject_del(&rdev->kobj);
+ goto fail;
+ }
+ list_add(&rdev->same_set, &mddev->disks);
bd_claim_by_disk(rdev->bdev, rdev, mddev->gendisk);
return 0;
+
+ fail:
+ printk(KERN_WARNING "md: failed to register dev-%s for %s\n",
+ b, mdname(mddev));
+ return err;
+}
+
+static void delayed_delete(struct work_struct *ws)
+{
+ mdk_rdev_t *rdev = container_of(ws, mdk_rdev_t, del_work);
+ kobject_del(&rdev->kobj);
}
static void unbind_rdev_from_array(mdk_rdev_t * rdev)
printk(KERN_INFO "md: unbind<%s>\n", bdevname(rdev->bdev,b));
rdev->mddev = NULL;
sysfs_remove_link(&rdev->kobj, "block");
- kobject_del(&rdev->kobj);
+
+ /* We need to delay this, otherwise we can deadlock when
+ * writing to 'remove' to "dev/state"
+ */
+ INIT_WORK(&rdev->del_work, delayed_delete);
+ schedule_work(&rdev->del_work);
}
/*
struct block_device *bdev;
char b[BDEVNAME_SIZE];
- bdev = open_partition_by_devnum(dev, FMODE_READ|FMODE_WRITE);
+ bdev = open_by_devnum(dev, FMODE_READ|FMODE_WRITE);
if (IS_ERR(bdev)) {
printk(KERN_ERR "md: could not open %s.\n",
__bdevname(dev, b));
if (err) {
printk(KERN_ERR "md: could not bd_claim %s.\n",
bdevname(bdev, b));
- blkdev_put_partition(bdev);
+ blkdev_put(bdev);
return err;
}
rdev->bdev = bdev;
if (!bdev)
MD_BUG();
bd_release(bdev);
- blkdev_put_partition(bdev);
+ blkdev_put(bdev);
}
void md_autodetect_dev(dev_t dev);
* and 'events' is odd, we can roll back to the previous clean state */
if (nospares
&& (mddev->in_sync && mddev->recovery_cp == MaxSector)
- && (mddev->events & 1))
+ && (mddev->events & 1)
+ && mddev->events != 1)
mddev->events--;
else {
/* otherwise we have to go forward and ... */
else {
mddev_t *mddev = rdev->mddev;
kick_rdev_from_array(rdev);
- md_update_sb(mddev, 1);
+ if (mddev->pers)
+ md_update_sb(mddev, 1);
md_new_event(mddev);
err = 0;
}
rdev->desc_nr = -1;
rdev->saved_raid_disk = -1;
+ rdev->raid_disk = -1;
rdev->flags = 0;
rdev->data_offset = 0;
rdev->sb_events = 0;
static ssize_t
raid_disks_store(mddev_t *mddev, const char *buf, size_t len)
{
- /* can only set raid_disks if array is not yet active */
char *e;
int rv = 0;
unsigned long n = simple_strtoul(buf, &e, 10);
return -EINVAL;
buf = e+1;
minor = simple_strtoul(buf, &e, 10);
- if (e==buf || *e != '\n')
+ if (e==buf || (*e && *e != '\n') )
return -EINVAL;
if (major >= sizeof(super_types)/sizeof(super_types[0]) ||
super_types[major].name == NULL)
mddev->kobj.k_name = NULL;
snprintf(mddev->kobj.name, KOBJ_NAME_LEN, "%s", "md");
mddev->kobj.ktype = &md_ktype;
- kobject_register(&mddev->kobj);
+ if (kobject_register(&mddev->kobj))
+ printk(KERN_WARNING "md: cannot register %s/md - name in use\n",
+ disk->disk_name);
return NULL;
}
if (test_bit(Faulty, &rdev->flags))
continue;
sync_blockdev(rdev->bdev);
- invalidate_bdev(rdev->bdev, 0);
+ invalidate_bdev(rdev->bdev);
}
md_probe(mddev->unit, NULL, NULL);
return -EINVAL;
}
+ if (pers->sync_request) {
+ /* Warn if this is a potentially silly
+ * configuration.
+ */
+ char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
+ mdk_rdev_t *rdev2;
+ struct list_head *tmp2;
+ int warned = 0;
+ ITERATE_RDEV(mddev, rdev, tmp) {
+ ITERATE_RDEV(mddev, rdev2, tmp2) {
+ if (rdev < rdev2 &&
+ rdev->bdev->bd_contains ==
+ rdev2->bdev->bd_contains) {
+ printk(KERN_WARNING
+ "%s: WARNING: %s appears to be"
+ " on the same physical disk as"
+ " %s.\n",
+ mdname(mddev),
+ bdevname(rdev->bdev,b),
+ bdevname(rdev2->bdev,b2));
+ warned = 1;
+ }
+ }
+ }
+ if (warned)
+ printk(KERN_WARNING
+ "True protection against single-disk"
+ " failure might be compromised.\n");
+ }
+
mddev->recovery = 0;
mddev->resync_max_sectors = mddev->size << 1; /* may be over-ridden by personality */
mddev->barriers_work = 1;
bitmap_destroy(mddev);
return err;
}
- if (mddev->pers->sync_request)
- sysfs_create_group(&mddev->kobj, &md_redundancy_group);
- else if (mddev->ro == 2) /* auto-readonly not meaningful */
+ if (mddev->pers->sync_request) {
+ if (sysfs_create_group(&mddev->kobj, &md_redundancy_group))
+ printk(KERN_WARNING
+ "md: cannot register extra attributes for %s\n",
+ mdname(mddev));
+ } else if (mddev->ro == 2) /* auto-readonly not meaningful */
mddev->ro = 0;
atomic_set(&mddev->writes_pending,0);
if (rdev->raid_disk >= 0) {
char nm[20];
sprintf(nm, "rd%d", rdev->raid_disk);
- sysfs_create_link(&mddev->kobj, &rdev->kobj, nm);
+ if (sysfs_create_link(&mddev->kobj, &rdev->kobj, nm))
+ printk("md: cannot register %s for %s\n",
+ nm, mdname(mddev));
}
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
set_disk_ro(disk, 0);
blk_queue_make_request(mddev->queue, md_fail_request);
mddev->pers->stop(mddev);
+ mddev->queue->merge_bvec_fn = NULL;
+ mddev->queue->unplug_fn = NULL;
+ mddev->queue->issue_flush_fn = NULL;
+ mddev->queue->backing_dev_info.congested_fn = NULL;
if (mddev->pers->sync_request)
sysfs_remove_group(&mddev->kobj, &md_redundancy_group);
module_put(mddev->pers->owner);
mddev->pers = NULL;
+
+ set_capacity(disk, 0);
+ mddev->changed = 1;
+
if (mddev->ro)
mddev->ro = 0;
}
if (mode == 0) {
mdk_rdev_t *rdev;
struct list_head *tmp;
- struct gendisk *disk;
+
printk(KERN_INFO "md: %s stopped.\n", mdname(mddev));
bitmap_destroy(mddev);
sysfs_remove_link(&mddev->kobj, nm);
}
+ /* make sure all delayed_delete calls have finished */
+ flush_scheduled_work();
+
export_array(mddev);
mddev->array_size = 0;
mddev->raid_disks = 0;
mddev->recovery_cp = 0;
- disk = mddev->gendisk;
- if (disk)
- set_capacity(disk, 0);
- mddev->changed = 1;
} else if (mddev->pers)
printk(KERN_INFO "md: %s switched to read-only mode.\n",
mdname(mddev));
return err;
}
+#ifndef MODULE
static void autorun_array(mddev_t *mddev)
{
mdk_rdev_t *rdev;
}
printk(KERN_INFO "md: ... autorun DONE.\n");
}
+#endif /* !MODULE */
static int get_version(void __user * arg)
{
char *ptr, *buf = NULL;
int err = -ENOMEM;
+ md_allow_write(mddev);
+
file = kmalloc(sizeof(*file), GFP_KERNEL);
if (!file)
goto out;
if (err)
export_rdev(rdev);
+ md_update_sb(mddev, 1);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
return err;
mddev->major_version = info->major_version;
mddev->minor_version = info->minor_version;
mddev->patch_version = info->patch_version;
+ mddev->persistent = !info->not_persistent;
return 0;
}
mddev->major_version = MD_MAJOR_VERSION;
* Commands querying/configuring an existing array:
*/
/* if we are not initialised yet, only ADD_NEW_DISK, STOP_ARRAY,
- * RUN_ARRAY, and SET_BITMAP_FILE are allowed */
+ * RUN_ARRAY, and GET_ and SET_BITMAP_FILE are allowed */
if (!mddev->raid_disks && cmd != ADD_NEW_DISK && cmd != STOP_ARRAY
- && cmd != RUN_ARRAY && cmd != SET_BITMAP_FILE) {
+ && cmd != RUN_ARRAY && cmd != SET_BITMAP_FILE
+ && cmd != GET_BITMAP_FILE) {
err = -ENODEV;
goto abort_unlock;
}
mddev_t *mddev = inode->i_bdev->bd_disk->private_data;
int err;
- if ((err = mddev_lock(mddev)))
+ if ((err = mutex_lock_interruptible_nested(&mddev->reconfig_mutex, 1)))
goto out;
err = 0;
chunk_kb ? "KB" : "B");
if (bitmap->file) {
seq_printf(seq, ", file: ");
- seq_path(seq, bitmap->file->f_vfsmnt,
- bitmap->file->f_dentry," \t\n");
+ seq_path(seq, bitmap->file->f_path.mnt,
+ bitmap->file->f_path.dentry," \t\n");
}
seq_printf(seq, "\n");
return mask;
}
-static struct file_operations md_seq_fops = {
+static const struct file_operations md_seq_fops = {
.owner = THIS_MODULE,
.open = md_seq_open,
.read = seq_read,
}
}
+/* md_allow_write(mddev)
+ * Calling this ensures that the array is marked 'active' so that writes
+ * may proceed without blocking. It is important to call this before
+ * attempting a GFP_KERNEL allocation while holding the mddev lock.
+ * Must be called with mddev_lock held.
+ */
+void md_allow_write(mddev_t *mddev)
+{
+ if (!mddev->pers)
+ return;
+ if (mddev->ro)
+ return;
+
+ spin_lock_irq(&mddev->write_lock);
+ if (mddev->in_sync) {
+ mddev->in_sync = 0;
+ set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+ if (mddev->safemode_delay &&
+ mddev->safemode == 0)
+ mddev->safemode = 1;
+ spin_unlock_irq(&mddev->write_lock);
+ md_update_sb(mddev, 0);
+ } else
+ spin_unlock_irq(&mddev->write_lock);
+}
+EXPORT_SYMBOL_GPL(md_allow_write);
+
static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
#define SYNC_MARKS 10
mddev->pers->sync_request(mddev, max_sectors, &skipped, 1);
if (!test_bit(MD_RECOVERY_ERR, &mddev->recovery) &&
- test_bit(MD_RECOVERY_SYNC, &mddev->recovery) &&
!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) &&
mddev->curr_resync > 2) {
if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
rdev->recovery_offset = mddev->curr_resync;
}
}
+ set_bit(MD_CHANGE_DEVS, &mddev->flags);
skip:
mddev->curr_resync = 0;
EXPORT_SYMBOL_GPL(md_do_sync);
+static int remove_and_add_spares(mddev_t *mddev)
+{
+ mdk_rdev_t *rdev;
+ struct list_head *rtmp;
+ int spares = 0;
+
+ ITERATE_RDEV(mddev,rdev,rtmp)
+ if (rdev->raid_disk >= 0 &&
+ (test_bit(Faulty, &rdev->flags) ||
+ ! test_bit(In_sync, &rdev->flags)) &&
+ atomic_read(&rdev->nr_pending)==0) {
+ if (mddev->pers->hot_remove_disk(
+ mddev, rdev->raid_disk)==0) {
+ char nm[20];
+ sprintf(nm,"rd%d", rdev->raid_disk);
+ sysfs_remove_link(&mddev->kobj, nm);
+ rdev->raid_disk = -1;
+ }
+ }
+
+ if (mddev->degraded) {
+ ITERATE_RDEV(mddev,rdev,rtmp)
+ if (rdev->raid_disk < 0
+ && !test_bit(Faulty, &rdev->flags)) {
+ rdev->recovery_offset = 0;
+ if (mddev->pers->hot_add_disk(mddev,rdev)) {
+ char nm[20];
+ 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));
+ spares++;
+ md_new_event(mddev);
+ } else
+ break;
+ }
+ }
+ return spares;
+}
/*
* This routine is regularly called by all per-raid-array threads to
* deal with generic issues like resync and super-block update.
return;
if (mddev_trylock(mddev)) {
- int spares =0;
+ int spares = 0;
spin_lock_irq(&mddev->write_lock);
if (mddev->safemode && !atomic_read(&mddev->writes_pending) &&
* Spare are also removed and re-added, to allow
* the personality to fail the re-add.
*/
- ITERATE_RDEV(mddev,rdev,rtmp)
- if (rdev->raid_disk >= 0 &&
- (test_bit(Faulty, &rdev->flags) || ! test_bit(In_sync, &rdev->flags)) &&
- atomic_read(&rdev->nr_pending)==0) {
- if (mddev->pers->hot_remove_disk(mddev, rdev->raid_disk)==0) {
- char nm[20];
- sprintf(nm,"rd%d", rdev->raid_disk);
- sysfs_remove_link(&mddev->kobj, nm);
- rdev->raid_disk = -1;
- }
- }
- if (mddev->degraded) {
- ITERATE_RDEV(mddev,rdev,rtmp)
- if (rdev->raid_disk < 0
- && !test_bit(Faulty, &rdev->flags)) {
- rdev->recovery_offset = 0;
- if (mddev->pers->hot_add_disk(mddev,rdev)) {
- char nm[20];
- sprintf(nm, "rd%d", rdev->raid_disk);
- sysfs_create_link(&mddev->kobj, &rdev->kobj, nm);
- spares++;
- md_new_event(mddev);
- } else
- break;
- }
- }
-
- if (spares) {
+ if (mddev->reshape_position != MaxSector) {
+ if (mddev->pers->check_reshape(mddev) != 0)
+ /* Cannot proceed */
+ goto unlock;
+ set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
+ } else if ((spares = remove_and_add_spares(mddev))) {
clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
} else if (mddev->recovery_cp < MaxSector) {
md_probe, NULL, NULL);
register_reboot_notifier(&md_notifier);
- raid_table_header = register_sysctl_table(raid_root_table, 1);
+ raid_table_header = register_sysctl_table(raid_root_table);
md_geninit();
return (0);
autorun_devices(part);
}
-#endif
+#endif /* !MODULE */
static __exit void md_exit(void)
{