static ctl_table raid_table[] = {
{
- .ctl_name = DEV_RAID_SPEED_LIMIT_MIN,
.procname = "speed_limit_min",
.data = &sysctl_speed_limit_min,
.maxlen = sizeof(int),
.mode = S_IRUGO|S_IWUSR,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = DEV_RAID_SPEED_LIMIT_MAX,
.procname = "speed_limit_max",
.data = &sysctl_speed_limit_max,
.maxlen = sizeof(int),
.mode = S_IRUGO|S_IWUSR,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
- { .ctl_name = 0 }
+ { }
};
static ctl_table raid_dir_table[] = {
{
- .ctl_name = DEV_RAID,
.procname = "raid",
.maxlen = 0,
.mode = S_IRUGO|S_IXUGO,
.child = raid_table,
},
- { .ctl_name = 0 }
+ { }
};
static ctl_table raid_root_table[] = {
{
- .ctl_name = CTL_DEV,
.procname = "dev",
.maxlen = 0,
.mode = 0555,
.child = raid_dir_table,
},
- { .ctl_name = 0 }
+ { }
};
-static struct block_device_operations md_fops;
+static const struct block_device_operations md_fops;
static int start_readonly;
mddev->pers->quiesce(mddev, 0);
}
+int mddev_congested(mddev_t *mddev, int bits)
+{
+ return mddev->suspended;
+}
+EXPORT_SYMBOL(mddev_congested);
+
static inline mddev_t *mddev_get(mddev_t *mddev)
{
else
new->md_minor = MINOR(unit) >> MdpMinorShift;
+ mutex_init(&new->open_mutex);
mutex_init(&new->reconfig_mutex);
INIT_LIST_HEAD(&new->disks);
INIT_LIST_HEAD(&new->all_mddevs);
desc->raid_disk < mddev->raid_disks */) {
set_bit(In_sync, &rdev->flags);
rdev->raid_disk = desc->raid_disk;
+ } else if (desc->state & (1<<MD_DISK_ACTIVE)) {
+ /* active but not in sync implies recovery up to
+ * reshape position. We don't know exactly where
+ * that is, so set to zero for now */
+ if (mddev->minor_version >= 91) {
+ rdev->recovery_offset = 0;
+ rdev->raid_disk = desc->raid_disk;
+ }
}
if (desc->state & (1<<MD_DISK_WRITEMOSTLY))
set_bit(WriteMostly, &rdev->flags);
list_for_each_entry(rdev2, &mddev->disks, same_set) {
mdp_disk_t *d;
int desc_nr;
- if (rdev2->raid_disk >= 0 && test_bit(In_sync, &rdev2->flags)
- && !test_bit(Faulty, &rdev2->flags))
+ int is_active = test_bit(In_sync, &rdev2->flags);
+
+ if (rdev2->raid_disk >= 0 &&
+ sb->minor_version >= 91)
+ /* we have nowhere to store the recovery_offset,
+ * but if it is not below the reshape_position,
+ * we can piggy-back on that.
+ */
+ is_active = 1;
+ if (rdev2->raid_disk < 0 ||
+ test_bit(Faulty, &rdev2->flags))
+ is_active = 0;
+ if (is_active)
desc_nr = rdev2->raid_disk;
else
desc_nr = next_spare++;
d->number = rdev2->desc_nr;
d->major = MAJOR(rdev2->bdev->bd_dev);
d->minor = MINOR(rdev2->bdev->bd_dev);
- if (rdev2->raid_disk >= 0 && test_bit(In_sync, &rdev2->flags)
- && !test_bit(Faulty, &rdev2->flags))
+ if (is_active)
d->raid_disk = rdev2->raid_disk;
else
d->raid_disk = rdev2->desc_nr; /* compatibility */
if (test_bit(Faulty, &rdev2->flags))
d->state = (1<<MD_DISK_FAULTY);
- else if (test_bit(In_sync, &rdev2->flags)) {
+ else if (is_active) {
d->state = (1<<MD_DISK_ACTIVE);
- d->state |= (1<<MD_DISK_SYNC);
+ if (test_bit(In_sync, &rdev2->flags))
+ d->state |= (1<<MD_DISK_SYNC);
active++;
working++;
} else {
}
if (mddev->level != LEVEL_MULTIPATH) {
int role;
- role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
+ if (rdev->desc_nr < 0 ||
+ rdev->desc_nr >= le32_to_cpu(sb->max_dev)) {
+ role = 0xffff;
+ rdev->desc_nr = -1;
+ } else
+ role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
switch(role) {
case 0xffff: /* spare */
break;
if (rdev->raid_disk >= 0 &&
!test_bit(In_sync, &rdev->flags)) {
- if (mddev->curr_resync_completed > rdev->recovery_offset)
- rdev->recovery_offset = mddev->curr_resync_completed;
if (rdev->recovery_offset > 0) {
sb->feature_map |=
cpu_to_le32(MD_FEATURE_RECOVERY_OFFSET);
if (rdev2->desc_nr+1 > max_dev)
max_dev = rdev2->desc_nr+1;
- if (max_dev > le32_to_cpu(sb->max_dev))
+ if (max_dev > le32_to_cpu(sb->max_dev)) {
+ int bmask;
sb->max_dev = cpu_to_le32(max_dev);
+ rdev->sb_size = max_dev * 2 + 256;
+ bmask = queue_logical_block_size(rdev->bdev->bd_disk->queue)-1;
+ if (rdev->sb_size & bmask)
+ rdev->sb_size = (rdev->sb_size | bmask) + 1;
+ }
for (i=0; i<max_dev;i++)
sb->dev_roles[i] = cpu_to_le16(0xfffe);
static LIST_HEAD(pending_raid_disks);
-static void md_integrity_check(mdk_rdev_t *rdev, mddev_t *mddev)
+/*
+ * Try to register data integrity profile for an mddev
+ *
+ * This is called when an array is started and after a disk has been kicked
+ * from the array. It only succeeds if all working and active component devices
+ * are integrity capable with matching profiles.
+ */
+int md_integrity_register(mddev_t *mddev)
+{
+ mdk_rdev_t *rdev, *reference = NULL;
+
+ if (list_empty(&mddev->disks))
+ return 0; /* nothing to do */
+ if (blk_get_integrity(mddev->gendisk))
+ return 0; /* already registered */
+ list_for_each_entry(rdev, &mddev->disks, same_set) {
+ /* skip spares and non-functional disks */
+ if (test_bit(Faulty, &rdev->flags))
+ continue;
+ if (rdev->raid_disk < 0)
+ continue;
+ /*
+ * If at least one rdev is not integrity capable, we can not
+ * enable data integrity for the md device.
+ */
+ if (!bdev_get_integrity(rdev->bdev))
+ return -EINVAL;
+ if (!reference) {
+ /* Use the first rdev as the reference */
+ reference = rdev;
+ continue;
+ }
+ /* does this rdev's profile match the reference profile? */
+ if (blk_integrity_compare(reference->bdev->bd_disk,
+ rdev->bdev->bd_disk) < 0)
+ return -EINVAL;
+ }
+ /*
+ * All component devices are integrity capable and have matching
+ * profiles, register the common profile for the md device.
+ */
+ if (blk_integrity_register(mddev->gendisk,
+ bdev_get_integrity(reference->bdev)) != 0) {
+ printk(KERN_ERR "md: failed to register integrity for %s\n",
+ mdname(mddev));
+ return -EINVAL;
+ }
+ printk(KERN_NOTICE "md: data integrity on %s enabled\n",
+ mdname(mddev));
+ return 0;
+}
+EXPORT_SYMBOL(md_integrity_register);
+
+/* Disable data integrity if non-capable/non-matching disk is being added */
+void md_integrity_add_rdev(mdk_rdev_t *rdev, mddev_t *mddev)
{
- struct mdk_personality *pers = mddev->pers;
- struct gendisk *disk = mddev->gendisk;
struct blk_integrity *bi_rdev = bdev_get_integrity(rdev->bdev);
- struct blk_integrity *bi_mddev = blk_get_integrity(disk);
+ struct blk_integrity *bi_mddev = blk_get_integrity(mddev->gendisk);
- /* Data integrity passthrough not supported on RAID 4, 5 and 6 */
- if (pers && pers->level >= 4 && pers->level <= 6)
+ if (!bi_mddev) /* nothing to do */
return;
-
- /* If rdev is integrity capable, register profile for mddev */
- if (!bi_mddev && bi_rdev) {
- if (blk_integrity_register(disk, bi_rdev))
- printk(KERN_ERR "%s: %s Could not register integrity!\n",
- __func__, disk->disk_name);
- else
- printk(KERN_NOTICE "Enabling data integrity on %s\n",
- disk->disk_name);
+ if (rdev->raid_disk < 0) /* skip spares */
return;
- }
-
- /* Check that mddev and rdev have matching profiles */
- if (blk_integrity_compare(disk, rdev->bdev->bd_disk) < 0) {
- printk(KERN_ERR "%s: %s/%s integrity mismatch!\n", __func__,
- disk->disk_name, rdev->bdev->bd_disk->disk_name);
- printk(KERN_NOTICE "Disabling data integrity on %s\n",
- disk->disk_name);
- blk_integrity_unregister(disk);
- }
+ if (bi_rdev && blk_integrity_compare(mddev->gendisk,
+ rdev->bdev->bd_disk) >= 0)
+ return;
+ printk(KERN_NOTICE "disabling data integrity on %s\n", mdname(mddev));
+ blk_integrity_unregister(mddev->gendisk);
}
+EXPORT_SYMBOL(md_integrity_add_rdev);
static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev)
{
/* May as well allow recovery to be retried once */
mddev->recovery_disabled = 0;
- md_integrity_check(rdev, mddev);
return 0;
fail:
__u8 *uuid;
uuid = sb->set_uuid;
- printk(KERN_INFO "md: SB: (V:%u) (F:0x%08x) Array-ID:<%02x%02x%02x%02x"
- ":%02x%02x:%02x%02x:%02x%02x:%02x%02x%02x%02x%02x%02x>\n"
- KERN_INFO "md: Name: \"%s\" CT:%llu\n",
+ printk(KERN_INFO
+ "md: SB: (V:%u) (F:0x%08x) Array-ID:<%02x%02x%02x%02x"
+ ":%02x%02x:%02x%02x:%02x%02x:%02x%02x%02x%02x%02x%02x>\n"
+ "md: Name: \"%s\" CT:%llu\n",
le32_to_cpu(sb->major_version),
le32_to_cpu(sb->feature_map),
uuid[0], uuid[1], uuid[2], uuid[3],
& MD_SUPERBLOCK_1_TIME_SEC_MASK);
uuid = sb->device_uuid;
- printk(KERN_INFO "md: L%u SZ%llu RD:%u LO:%u CS:%u DO:%llu DS:%llu SO:%llu"
+ printk(KERN_INFO
+ "md: L%u SZ%llu RD:%u LO:%u CS:%u DO:%llu DS:%llu SO:%llu"
" RO:%llu\n"
- KERN_INFO "md: Dev:%08x UUID: %02x%02x%02x%02x:%02x%02x:%02x%02x:%02x%02x"
- ":%02x%02x%02x%02x%02x%02x\n"
- KERN_INFO "md: (F:0x%08x) UT:%llu Events:%llu ResyncOffset:%llu CSUM:0x%08x\n"
- KERN_INFO "md: (MaxDev:%u) \n",
+ "md: Dev:%08x UUID: %02x%02x%02x%02x:%02x%02x:%02x%02x:%02x%02x"
+ ":%02x%02x%02x%02x%02x%02x\n"
+ "md: (F:0x%08x) UT:%llu Events:%llu ResyncOffset:%llu CSUM:0x%08x\n"
+ "md: (MaxDev:%u) \n",
le32_to_cpu(sb->level),
(unsigned long long)le64_to_cpu(sb->size),
le32_to_cpu(sb->raid_disks),
*/
mdk_rdev_t *rdev;
+ /* First make sure individual recovery_offsets are correct */
+ list_for_each_entry(rdev, &mddev->disks, same_set) {
+ if (rdev->raid_disk >= 0 &&
+ !test_bit(In_sync, &rdev->flags) &&
+ mddev->curr_resync_completed > rdev->recovery_offset)
+ rdev->recovery_offset = mddev->curr_resync_completed;
+
+ }
list_for_each_entry(rdev, &mddev->disks, same_set) {
if (rdev->sb_events == mddev->events ||
(nospares &&
/* otherwise we have to go forward and ... */
mddev->events ++;
if (!mddev->in_sync || mddev->recovery_cp != MaxSector) { /* not clean */
- /* .. if the array isn't clean, insist on an odd 'events' */
- if ((mddev->events&1)==0) {
- mddev->events++;
+ /* .. if the array isn't clean, an 'even' event must also go
+ * to spares. */
+ if ((mddev->events&1)==0)
nospares = 0;
- }
} else {
- /* otherwise insist on an even 'events' (for clean states) */
- if ((mddev->events&1)) {
- mddev->events++;
+ /* otherwise an 'odd' event must go to spares */
+ if ((mddev->events&1))
nospares = 0;
- }
}
}
rdev->desc_nr = i++;
rdev->raid_disk = rdev->desc_nr;
set_bit(In_sync, &rdev->flags);
- } else if (rdev->raid_disk >= mddev->raid_disks) {
+ } else if (rdev->raid_disk >= (mddev->raid_disks - min(0, mddev->delta_disks))) {
rdev->raid_disk = -1;
clear_bit(In_sync, &rdev->flags);
}
ssize_t rv = len;
struct mdk_personality *pers;
void *priv;
+ mdk_rdev_t *rdev;
if (mddev->pers == NULL) {
if (len == 0)
mddev_suspend(mddev);
mddev->pers->stop(mddev);
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;
+ clear_bit(In_sync, &rdev->flags);
+ }
mddev->pers = pers;
mddev->private = priv;
strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
if (max < mddev->resync_min)
return -EINVAL;
if (max < mddev->resync_max &&
+ mddev->ro == 0 &&
test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
return -EBUSY;
mddev->array_sectors = sectors;
set_capacity(mddev->gendisk, mddev->array_sectors);
- if (mddev->pers) {
- struct block_device *bdev = bdget_disk(mddev->gendisk, 0);
-
- if (bdev) {
- mutex_lock(&bdev->bd_inode->i_mutex);
- i_size_write(bdev->bd_inode,
- (loff_t)mddev->array_sectors << 9);
- mutex_unlock(&bdev->bd_inode->i_mutex);
- bdput(bdev);
- }
- }
+ if (mddev->pers)
+ revalidate_disk(mddev->gendisk);
return len;
}
}
strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
- if (pers->level >= 4 && pers->level <= 6)
- /* Cannot support integrity (yet) */
- blk_integrity_unregister(mddev->gendisk);
-
if (mddev->reshape_position != MaxSector &&
pers->start_reshape == NULL) {
/* This personality cannot handle reshaping... */
set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
mddev->sync_thread = md_register_thread(md_do_sync,
mddev,
- "%s_resync");
+ "resync");
if (!mddev->sync_thread) {
printk(KERN_ERR "%s: could not start resync"
" thread...\n",
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);
struct gendisk *disk = mddev->gendisk;
mdk_rdev_t *rdev;
+ mutex_lock(&mddev->open_mutex);
if (atomic_read(&mddev->openers) > is_open) {
printk("md: %s still in use.\n",mdname(mddev));
- return -EBUSY;
- }
-
- if (mddev->pers) {
+ err = -EBUSY;
+ } else if (mddev->pers) {
if (mddev->sync_thread) {
set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
if (mode == 1)
set_disk_ro(disk, 1);
clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+ err = 0;
}
-
+out:
+ mutex_unlock(&mddev->open_mutex);
+ if (err)
+ return err;
/*
* Free resources if final stop
*/
blk_integrity_unregister(disk);
md_new_event(mddev);
sysfs_notify_dirent(mddev->sysfs_state);
-out:
return err;
}
static int get_array_info(mddev_t * mddev, void __user * arg)
{
mdu_array_info_t info;
- int nr,working,active,failed,spare;
+ int nr,working,insync,failed,spare;
mdk_rdev_t *rdev;
- nr=working=active=failed=spare=0;
+ nr=working=insync=failed=spare=0;
list_for_each_entry(rdev, &mddev->disks, same_set) {
nr++;
if (test_bit(Faulty, &rdev->flags))
else {
working++;
if (test_bit(In_sync, &rdev->flags))
- active++;
+ insync++;
else
spare++;
}
info.state = (1<<MD_SB_CLEAN);
if (mddev->bitmap && mddev->bitmap_offset)
info.state = (1<<MD_SB_BITMAP_PRESENT);
- info.active_disks = active;
+ info.active_disks = insync;
info.working_disks = working;
info.failed_disks = failed;
info.spare_disks = spare;
if (!list_empty(&mddev->disks)) {
mdk_rdev_t *rdev0 = list_entry(mddev->disks.next,
mdk_rdev_t, same_set);
- int err = super_types[mddev->major_version]
+ err = super_types[mddev->major_version]
.load_super(rdev, rdev0, mddev->minor_version);
if (err < 0) {
printk(KERN_WARNING
return -ENOSPC;
}
rv = mddev->pers->resize(mddev, num_sectors);
- if (!rv) {
- struct block_device *bdev;
-
- bdev = bdget_disk(mddev->gendisk, 0);
- if (bdev) {
- mutex_lock(&bdev->bd_inode->i_mutex);
- i_size_write(bdev->bd_inode,
- (loff_t)mddev->array_sectors << 9);
- mutex_unlock(&bdev->bd_inode->i_mutex);
- bdput(bdev);
- }
- }
+ if (!rv)
+ revalidate_disk(mddev->gendisk);
return rv;
}
}
BUG_ON(mddev != bdev->bd_disk->private_data);
- if ((err = mutex_lock_interruptible_nested(&mddev->reconfig_mutex, 1)))
+ if ((err = mutex_lock_interruptible(&mddev->open_mutex)))
goto out;
err = 0;
atomic_inc(&mddev->openers);
- mddev_unlock(mddev);
+ mutex_unlock(&mddev->open_mutex);
check_disk_change(bdev);
out:
mddev->changed = 0;
return 0;
}
-static struct block_device_operations md_fops =
+static const struct block_device_operations md_fops =
{
.owner = THIS_MODULE,
.open = md_open,
thread->run = run;
thread->mddev = mddev;
thread->timeout = MAX_SCHEDULE_TIMEOUT;
- thread->tsk = kthread_run(md_thread, thread, name, mdname(thread->mddev));
+ thread->tsk = kthread_run(md_thread, thread,
+ "%s_%s",
+ mdname(thread->mddev),
+ name ?: mddev->pers->name);
if (IS_ERR(thread->tsk)) {
kfree(thread);
return NULL;
sysfs_notify(&mddev->kobj, NULL, "sync_completed");
}
- if (j >= mddev->resync_max)
- wait_event(mddev->recovery_wait,
- mddev->resync_max > j
- || kthread_should_stop());
+ while (j >= mddev->resync_max && !kthread_should_stop()) {
+ /* As this condition is controlled by user-space,
+ * we can block indefinitely, so use '_interruptible'
+ * to avoid triggering warnings.
+ */
+ flush_signals(current); /* just in case */
+ wait_event_interruptible(mddev->recovery_wait,
+ mddev->resync_max > j
+ || kthread_should_stop());
+ }
if (kthread_should_stop())
goto interrupted;
skip:
mddev->curr_resync = 0;
mddev->curr_resync_completed = 0;
- mddev->resync_min = 0;
- mddev->resync_max = MaxSector;
+ if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery))
+ /* We completed so max setting can be forgotten. */
+ mddev->resync_max = MaxSector;
sysfs_notify(&mddev->kobj, NULL, "sync_completed");
wake_up(&resync_wait);
set_bit(MD_RECOVERY_DONE, &mddev->recovery);
}
mddev->sync_thread = md_register_thread(md_do_sync,
mddev,
- "%s_resync");
+ "resync");
if (!mddev->sync_thread) {
printk(KERN_ERR "%s: could not start resync"
" thread...\n",