#include <linux/blkdev.h>
#include <linux/sysctl.h>
#include <linux/seq_file.h>
-#include <linux/mutex.h>
-#include <linux/buffer_head.h> /* for invalidate_bdev */
+#include <linux/fs.h>
#include <linux/poll.h>
#include <linux/ctype.h>
#include <linux/string.h>
#include <linux/hdreg.h>
#include <linux/proc_fs.h>
#include <linux/random.h>
+#include <linux/module.h>
#include <linux/reboot.h>
#include <linux/file.h>
#include <linux/compat.h>
* call has finished, the bio has been linked into some internal structure
* and so is visible to ->quiesce(), so we don't need the refcount any more.
*/
-static int md_make_request(struct request_queue *q, struct bio *bio)
+static void md_make_request(struct request_queue *q, struct bio *bio)
{
const int rw = bio_data_dir(bio);
struct mddev *mddev = q->queuedata;
- int rv;
int cpu;
unsigned int sectors;
if (mddev == NULL || mddev->pers == NULL
|| !mddev->ready) {
bio_io_error(bio);
- return 0;
+ return;
}
smp_rmb(); /* Ensure implications of 'active' are visible */
rcu_read_lock();
* go away inside make_request
*/
sectors = bio_sectors(bio);
- rv = mddev->pers->make_request(mddev, bio);
+ mddev->pers->make_request(mddev, bio);
cpu = part_stat_lock();
part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended)
wake_up(&mddev->sb_wait);
-
- return rv;
}
/* mddev_suspend makes sure no new requests are submitted
synchronize_rcu();
wait_event(mddev->sb_wait, atomic_read(&mddev->active_io) == 0);
mddev->pers->quiesce(mddev, 1);
+
+ del_timer_sync(&mddev->safemode_timer);
}
EXPORT_SYMBOL_GPL(mddev_suspend);
INIT_WORK(&mddev->flush_work, md_submit_flush_data);
atomic_set(&mddev->flush_pending, 1);
rcu_read_lock();
- list_for_each_entry_rcu(rdev, &mddev->disks, same_set)
+ rdev_for_each_rcu(rdev, mddev)
if (rdev->raid_disk >= 0 &&
!test_bit(Faulty, &rdev->flags)) {
/* Take two references, one is dropped
bio_endio(bio, 0);
else {
bio->bi_rw &= ~REQ_FLUSH;
- if (mddev->pers->make_request(mddev, bio))
- generic_make_request(bio);
+ mddev->pers->make_request(mddev, bio);
}
mddev->flush_bio = NULL;
mddev->ctime == 0 && !mddev->hold_active) {
/* Array is not configured at all, and not held active,
* so destroy it */
- list_del(&mddev->all_mddevs);
+ list_del_init(&mddev->all_mddevs);
bs = mddev->bio_set;
mddev->bio_set = NULL;
if (mddev->gendisk) {
} else
mutex_unlock(&mddev->reconfig_mutex);
- /* was we've dropped the mutex we need a spinlock to
- * make sur the thread doesn't disappear
+ /* As we've dropped the mutex we need a spinlock to
+ * make sure the thread doesn't disappear
*/
spin_lock(&pers_lock);
md_wakeup_thread(mddev->thread);
{
struct md_rdev *rdev;
- list_for_each_entry(rdev, &mddev->disks, same_set)
+ rdev_for_each(rdev, mddev)
if (rdev->desc_nr == nr)
return rdev;
{
struct md_rdev *rdev;
- list_for_each_entry(rdev, &mddev->disks, same_set)
+ rdev_for_each(rdev, mddev)
if (rdev->bdev->bd_dev == dev)
return rdev;
sb->state |= (1<<MD_SB_BITMAP_PRESENT);
sb->disks[0].state = (1<<MD_DISK_REMOVED);
- list_for_each_entry(rdev2, &mddev->disks, same_set) {
+ rdev_for_each(rdev2, mddev) {
mdp_disk_t *d;
int desc_nr;
int is_active = test_bit(In_sync, &rdev2->flags);
}
if (sb->devflags & WriteMostly1)
set_bit(WriteMostly, &rdev->flags);
+ if (le32_to_cpu(sb->feature_map) & MD_FEATURE_REPLACEMENT)
+ set_bit(Replacement, &rdev->flags);
} else /* MULTIPATH are always insync */
set_bit(In_sync, &rdev->flags);
sb->recovery_offset =
cpu_to_le64(rdev->recovery_offset);
}
+ if (test_bit(Replacement, &rdev->flags))
+ sb->feature_map |=
+ cpu_to_le32(MD_FEATURE_REPLACEMENT);
if (mddev->reshape_position != MaxSector) {
sb->feature_map |= cpu_to_le32(MD_FEATURE_RESHAPE_ACTIVE);
| BB_LEN(internal_bb));
*bbp++ = cpu_to_le64(store_bb);
}
+ bb->changed = 0;
if (read_seqretry(&bb->lock, seq))
goto retry;
bb->sector = (rdev->sb_start +
(int)le32_to_cpu(sb->bblog_offset));
bb->size = le16_to_cpu(sb->bblog_size);
- bb->changed = 0;
}
}
max_dev = 0;
- list_for_each_entry(rdev2, &mddev->disks, same_set)
+ rdev_for_each(rdev2, mddev)
if (rdev2->desc_nr+1 > max_dev)
max_dev = rdev2->desc_nr+1;
for (i=0; i<max_dev;i++)
sb->dev_roles[i] = cpu_to_le16(0xfffe);
- list_for_each_entry(rdev2, &mddev->disks, same_set) {
+ rdev_for_each(rdev2, mddev) {
i = rdev2->desc_nr;
if (test_bit(Faulty, &rdev2->flags))
sb->dev_roles[i] = cpu_to_le16(0xfffe);
return 0; /* nothing to do */
if (!mddev->gendisk || blk_get_integrity(mddev->gendisk))
return 0; /* shouldn't register, or already is */
- list_for_each_entry(rdev, &mddev->disks, same_set) {
+ rdev_for_each(rdev, mddev) {
/* skip spares and non-functional disks */
if (test_bit(Faulty, &rdev->flags))
continue;
{
struct md_rdev *rdev, *tmp;
- rdev_for_each(rdev, tmp, mddev) {
+ rdev_for_each_safe(rdev, tmp, mddev) {
if (!rdev->mddev) {
MD_BUG();
continue;
bitmap_print_sb(mddev->bitmap);
else
printk("%s: ", mdname(mddev));
- list_for_each_entry(rdev, &mddev->disks, same_set)
+ rdev_for_each(rdev, mddev)
printk("<%s>", bdevname(rdev->bdev,b));
printk("\n");
- list_for_each_entry(rdev, &mddev->disks, same_set)
+ rdev_for_each(rdev, mddev)
print_rdev(rdev, mddev->major_version);
}
printk("md: **********************************\n");
* with the rest of the array)
*/
struct md_rdev *rdev;
- list_for_each_entry(rdev, &mddev->disks, same_set) {
+ rdev_for_each(rdev, mddev) {
if (rdev->sb_events == mddev->events ||
(nospares &&
rdev->raid_disk < 0 &&
repeat:
/* First make sure individual recovery_offsets are correct */
- list_for_each_entry(rdev, &mddev->disks, same_set) {
+ rdev_for_each(rdev, mddev) {
if (rdev->raid_disk >= 0 &&
mddev->delta_disks >= 0 &&
!test_bit(In_sync, &rdev->flags) &&
clear_bit(MD_CHANGE_DEVS, &mddev->flags);
if (!mddev->external) {
clear_bit(MD_CHANGE_PENDING, &mddev->flags);
- list_for_each_entry(rdev, &mddev->disks, same_set) {
+ rdev_for_each(rdev, mddev) {
if (rdev->badblocks.changed) {
+ rdev->badblocks.changed = 0;
md_ack_all_badblocks(&rdev->badblocks);
md_error(mddev, rdev);
}
mddev->events --;
}
- list_for_each_entry(rdev, &mddev->disks, same_set) {
+ rdev_for_each(rdev, mddev) {
if (rdev->badblocks.changed)
any_badblocks_changed++;
if (test_bit(Faulty, &rdev->flags))
mdname(mddev), mddev->in_sync);
bitmap_update_sb(mddev->bitmap);
- list_for_each_entry(rdev, &mddev->disks, same_set) {
+ rdev_for_each(rdev, mddev) {
char b[BDEVNAME_SIZE];
if (rdev->sb_loaded != 1)
continue; /* no noise on spare devices */
- if (!test_bit(Faulty, &rdev->flags)) {
+ if (!test_bit(Faulty, &rdev->flags) &&
+ rdev->saved_raid_disk == -1) {
md_super_write(mddev,rdev,
rdev->sb_start, rdev->sb_size,
rdev->sb_page);
rdev->badblocks.size = 0;
}
- } else
+ } else if (test_bit(Faulty, &rdev->flags))
pr_debug("md: %s (skipping faulty)\n",
bdevname(rdev->bdev, b));
+ else
+ pr_debug("(skipping incremental s/r ");
+
if (mddev->level == LEVEL_MULTIPATH)
/* only need to write one superblock... */
break;
if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
sysfs_notify(&mddev->kobj, NULL, "sync_completed");
- list_for_each_entry(rdev, &mddev->disks, same_set) {
+ rdev_for_each(rdev, mddev) {
if (test_and_clear_bit(FaultRecorded, &rdev->flags))
clear_bit(Blocked, &rdev->flags);
sep = ",";
}
if (test_bit(Blocked, &rdev->flags) ||
- rdev->badblocks.unacked_exist) {
+ (rdev->badblocks.unacked_exist
+ && !test_bit(Faulty, &rdev->flags))) {
len += sprintf(page+len, "%sblocked", sep);
sep = ",";
}
len += sprintf(page+len, "%swrite_error", sep);
sep = ",";
}
+ if (test_bit(WantReplacement, &rdev->flags)) {
+ len += sprintf(page+len, "%swant_replacement", sep);
+ sep = ",";
+ }
+ if (test_bit(Replacement, &rdev->flags)) {
+ len += sprintf(page+len, "%sreplacement", sep);
+ sep = ",";
+ }
+
return len+sprintf(page+len, "\n");
}
} else if (cmd_match(buf, "-write_error")) {
clear_bit(WriteErrorSeen, &rdev->flags);
err = 0;
+ } else if (cmd_match(buf, "want_replacement")) {
+ /* Any non-spare device that is not a replacement can
+ * become want_replacement at any time, but we then need to
+ * check if recovery is needed.
+ */
+ if (rdev->raid_disk >= 0 &&
+ !test_bit(Replacement, &rdev->flags))
+ set_bit(WantReplacement, &rdev->flags);
+ set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
+ md_wakeup_thread(rdev->mddev->thread);
+ err = 0;
+ } else if (cmd_match(buf, "-want_replacement")) {
+ /* Clearing 'want_replacement' is always allowed.
+ * Once replacements starts it is too late though.
+ */
+ err = 0;
+ clear_bit(WantReplacement, &rdev->flags);
+ } else if (cmd_match(buf, "replacement")) {
+ /* Can only set a device as a replacement when array has not
+ * yet been started. Once running, replacement is automatic
+ * from spares, or by assigning 'slot'.
+ */
+ if (rdev->mddev->pers)
+ err = -EBUSY;
+ else {
+ set_bit(Replacement, &rdev->flags);
+ err = 0;
+ }
+ } else if (cmd_match(buf, "-replacement")) {
+ /* Similarly, can only clear Replacement before start */
+ if (rdev->mddev->pers)
+ err = -EBUSY;
+ else {
+ clear_bit(Replacement, &rdev->flags);
+ err = 0;
+ }
}
if (!err)
sysfs_notify_dirent_safe(rdev->sysfs_state);
if (rdev->mddev->pers->hot_remove_disk == NULL)
return -EINVAL;
err = rdev->mddev->pers->
- hot_remove_disk(rdev->mddev, rdev->raid_disk);
+ hot_remove_disk(rdev->mddev, rdev);
if (err)
return err;
sysfs_unlink_rdev(rdev->mddev, rdev);
set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
md_wakeup_thread(rdev->mddev->thread);
} else if (rdev->mddev->pers) {
- struct md_rdev *rdev2;
/* Activating a spare .. or possibly reactivating
* if we ever get bitmaps working here.
*/
if (rdev->mddev->pers->hot_add_disk == NULL)
return -EINVAL;
- list_for_each_entry(rdev2, &rdev->mddev->disks, same_set)
- if (rdev2->raid_disk == slot)
- return -EEXIST;
-
if (slot >= rdev->mddev->raid_disks &&
slot >= rdev->mddev->raid_disks + rdev->mddev->delta_disks)
return -ENOSPC;
struct md_rdev *rdev2;
mddev_lock(mddev);
- list_for_each_entry(rdev2, &mddev->disks, same_set)
+ rdev_for_each(rdev2, mddev)
if (rdev->bdev == rdev2->bdev &&
rdev != rdev2 &&
overlaps(rdev->data_offset, rdev->sectors,
char b[BDEVNAME_SIZE];
freshest = NULL;
- rdev_for_each(rdev, tmp, mddev)
+ rdev_for_each_safe(rdev, tmp, mddev)
switch (super_types[mddev->major_version].
load_super(rdev, freshest, mddev->minor_version)) {
case 1:
validate_super(mddev, freshest);
i = 0;
- rdev_for_each(rdev, tmp, mddev) {
+ rdev_for_each_safe(rdev, tmp, mddev) {
if (mddev->max_disks &&
(rdev->desc_nr >= mddev->max_disks ||
i > mddev->max_disks)) {
return -EINVAL;
}
- list_for_each_entry(rdev, &mddev->disks, same_set)
+ rdev_for_each(rdev, mddev)
rdev->new_raid_disk = rdev->raid_disk;
/* ->takeover must set new_* and/or delta_disks
mddev->safemode = 0;
}
- list_for_each_entry(rdev, &mddev->disks, same_set) {
+ rdev_for_each(rdev, mddev) {
if (rdev->raid_disk < 0)
continue;
if (rdev->new_raid_disk >= mddev->raid_disks)
continue;
sysfs_unlink_rdev(mddev, rdev);
}
- list_for_each_entry(rdev, &mddev->disks, same_set) {
+ rdev_for_each(rdev, mddev) {
if (rdev->raid_disk < 0)
continue;
if (rdev->new_raid_disk == rdev->raid_disk)
if (err)
return err;
else {
+ if (mddev->hold_active == UNTIL_IOCTL)
+ mddev->hold_active = 0;
sysfs_notify_dirent_safe(mddev->sysfs_state);
return len;
}
if (!entry->show)
return -EIO;
+ spin_lock(&all_mddevs_lock);
+ if (list_empty(&mddev->all_mddevs)) {
+ spin_unlock(&all_mddevs_lock);
+ return -EBUSY;
+ }
+ mddev_get(mddev);
+ spin_unlock(&all_mddevs_lock);
+
rv = mddev_lock(mddev);
if (!rv) {
rv = entry->show(mddev, page);
mddev_unlock(mddev);
}
+ mddev_put(mddev);
return rv;
}
return -EIO;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
+ spin_lock(&all_mddevs_lock);
+ if (list_empty(&mddev->all_mddevs)) {
+ spin_unlock(&all_mddevs_lock);
+ return -EBUSY;
+ }
+ mddev_get(mddev);
+ spin_unlock(&all_mddevs_lock);
rv = mddev_lock(mddev);
- if (mddev->hold_active == UNTIL_IOCTL)
- mddev->hold_active = 0;
if (!rv) {
rv = entry->store(mddev, page, length);
mddev_unlock(mddev);
}
+ mddev_put(mddev);
return rv;
}
mddev->queue->queuedata = mddev;
blk_queue_make_request(mddev->queue, md_make_request);
+ blk_set_stacking_limits(&mddev->queue->limits);
disk = alloc_disk(1 << shift);
if (!disk) {
* the only valid external interface is through the md
* device.
*/
- list_for_each_entry(rdev, &mddev->disks, same_set) {
+ rdev_for_each(rdev, mddev) {
if (test_bit(Faulty, &rdev->flags))
continue;
sync_blockdev(rdev->bdev);
struct md_rdev *rdev2;
int warned = 0;
- list_for_each_entry(rdev, &mddev->disks, same_set)
- list_for_each_entry(rdev2, &mddev->disks, same_set) {
+ rdev_for_each(rdev, mddev)
+ rdev_for_each(rdev2, mddev) {
if (rdev < rdev2 &&
rdev->bdev->bd_contains ==
rdev2->bdev->bd_contains) {
mddev->in_sync = 1;
smp_wmb();
mddev->ready = 1;
- list_for_each_entry(rdev, &mddev->disks, same_set)
+ rdev_for_each(rdev, mddev)
if (rdev->raid_disk >= 0)
if (sysfs_link_rdev(mddev, rdev))
/* failure here is OK */;
mddev->changed = 0;
mddev->degraded = 0;
mddev->safemode = 0;
+ mddev->merge_check_needed = 0;
mddev->bitmap_info.offset = 0;
mddev->bitmap_info.default_offset = 0;
mddev->bitmap_info.chunksize = 0;
/* tell userspace to handle 'inactive' */
sysfs_notify_dirent_safe(mddev->sysfs_state);
- list_for_each_entry(rdev, &mddev->disks, same_set)
+ rdev_for_each(rdev, mddev)
if (rdev->raid_disk >= 0)
sysfs_unlink_rdev(mddev, rdev);
printk(KERN_INFO "md: running: ");
- list_for_each_entry(rdev, &mddev->disks, same_set) {
+ rdev_for_each(rdev, mddev) {
char b[BDEVNAME_SIZE];
printk("<%s>", bdevname(rdev->bdev,b));
}
struct md_rdev *rdev;
nr=working=insync=failed=spare=0;
- list_for_each_entry(rdev, &mddev->disks, same_set) {
+ rdev_for_each(rdev, mddev) {
nr++;
if (test_bit(Faulty, &rdev->flags))
failed++;
* grow, and re-add.
*/
return -EBUSY;
- list_for_each_entry(rdev, &mddev->disks, same_set) {
+ rdev_for_each(rdev, mddev) {
sector_t avail = rdev->sectors;
if (fit && (num_sectors == 0 || num_sectors > avail))
struct mddev *mddev = NULL;
int ro;
- if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
+ switch (cmd) {
+ case RAID_VERSION:
+ case GET_ARRAY_INFO:
+ case GET_DISK_INFO:
+ break;
+ default:
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+ }
/*
* Commands dealing with the RAID driver but not any
struct mddev *mddev = v;
sector_t sectors;
struct md_rdev *rdev;
- struct bitmap *bitmap;
if (v == (void*)1) {
struct md_personality *pers;
}
sectors = 0;
- list_for_each_entry(rdev, &mddev->disks, same_set) {
+ rdev_for_each(rdev, mddev) {
char b[BDEVNAME_SIZE];
seq_printf(seq, " %s[%d]",
bdevname(rdev->bdev,b), rdev->desc_nr);
if (test_bit(Faulty, &rdev->flags)) {
seq_printf(seq, "(F)");
continue;
- } else if (rdev->raid_disk < 0)
+ }
+ if (rdev->raid_disk < 0)
seq_printf(seq, "(S)"); /* spare */
+ if (test_bit(Replacement, &rdev->flags))
+ seq_printf(seq, "(R)");
sectors += rdev->sectors;
}
} else
seq_printf(seq, "\n ");
- if ((bitmap = mddev->bitmap)) {
- unsigned long chunk_kb;
- unsigned long flags;
- spin_lock_irqsave(&bitmap->lock, flags);
- chunk_kb = mddev->bitmap_info.chunksize >> 10;
- seq_printf(seq, "bitmap: %lu/%lu pages [%luKB], "
- "%lu%s chunk",
- bitmap->pages - bitmap->missing_pages,
- bitmap->pages,
- (bitmap->pages - bitmap->missing_pages)
- << (PAGE_SHIFT - 10),
- chunk_kb ? chunk_kb : mddev->bitmap_info.chunksize,
- chunk_kb ? "KB" : "B");
- if (bitmap->file) {
- seq_printf(seq, ", file: ");
- seq_path(seq, &bitmap->file->f_path, " \t\n");
- }
-
- seq_printf(seq, "\n");
- spin_unlock_irqrestore(&bitmap->lock, flags);
- }
+ bitmap_status(seq, mddev->bitmap);
seq_printf(seq, "\n");
}
max_sectors = mddev->dev_sectors;
j = MaxSector;
rcu_read_lock();
- list_for_each_entry_rcu(rdev, &mddev->disks, same_set)
+ rdev_for_each_rcu(rdev, mddev)
if (rdev->raid_disk >= 0 &&
!test_bit(Faulty, &rdev->flags) &&
!test_bit(In_sync, &rdev->flags) &&
printk(KERN_INFO
"md: checkpointing %s of %s.\n",
desc, mdname(mddev));
- mddev->recovery_cp = mddev->curr_resync;
+ mddev->recovery_cp =
+ mddev->curr_resync_completed;
}
} else
mddev->recovery_cp = MaxSector;
if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery))
mddev->curr_resync = MaxSector;
rcu_read_lock();
- list_for_each_entry_rcu(rdev, &mddev->disks, same_set)
+ rdev_for_each_rcu(rdev, mddev)
if (rdev->raid_disk >= 0 &&
mddev->delta_disks >= 0 &&
!test_bit(Faulty, &rdev->flags) &&
rcu_read_unlock();
}
}
+ skip:
set_bit(MD_CHANGE_DEVS, &mddev->flags);
- skip:
if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
/* We completed so min/max setting can be forgotten if used. */
if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
{
struct md_rdev *rdev;
int spares = 0;
+ int removed = 0;
mddev->curr_resync_completed = 0;
- list_for_each_entry(rdev, &mddev->disks, same_set)
+ rdev_for_each(rdev, mddev)
if (rdev->raid_disk >= 0 &&
!test_bit(Blocked, &rdev->flags) &&
(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) {
+ mddev, rdev) == 0) {
sysfs_unlink_rdev(mddev, rdev);
rdev->raid_disk = -1;
+ removed++;
}
}
+ if (removed)
+ sysfs_notify(&mddev->kobj, NULL,
+ "degraded");
- if (mddev->degraded) {
- list_for_each_entry(rdev, &mddev->disks, same_set) {
- if (rdev->raid_disk >= 0 &&
- !test_bit(In_sync, &rdev->flags) &&
- !test_bit(Faulty, &rdev->flags))
+
+ rdev_for_each(rdev, mddev) {
+ if (rdev->raid_disk >= 0 &&
+ !test_bit(In_sync, &rdev->flags) &&
+ !test_bit(Faulty, &rdev->flags))
+ spares++;
+ if (rdev->raid_disk < 0
+ && !test_bit(Faulty, &rdev->flags)) {
+ rdev->recovery_offset = 0;
+ if (mddev->pers->
+ hot_add_disk(mddev, rdev) == 0) {
+ if (sysfs_link_rdev(mddev, rdev))
+ /* failure here is OK */;
spares++;
- if (rdev->raid_disk < 0
- && !test_bit(Faulty, &rdev->flags)) {
- rdev->recovery_offset = 0;
- if (mddev->pers->
- hot_add_disk(mddev, rdev) == 0) {
- if (sysfs_link_rdev(mddev, rdev))
- /* failure here is OK */;
- spares++;
- md_new_event(mddev);
- set_bit(MD_CHANGE_DEVS, &mddev->flags);
- } else
- break;
+ md_new_event(mddev);
+ set_bit(MD_CHANGE_DEVS, &mddev->flags);
}
}
}
if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
mddev->pers->finish_reshape)
mddev->pers->finish_reshape(mddev);
- md_update_sb(mddev, 1);
- /* if array is no-longer degraded, then any saved_raid_disk
- * information must be scrapped
+ /* If array is no-longer degraded, then any saved_raid_disk
+ * information must be scrapped. Also if any device is now
+ * In_sync we must scrape the saved_raid_disk for that device
+ * do the superblock for an incrementally recovered device
+ * written out.
*/
- if (!mddev->degraded)
- list_for_each_entry(rdev, &mddev->disks, same_set)
+ rdev_for_each(rdev, mddev)
+ if (!mddev->degraded ||
+ test_bit(In_sync, &rdev->flags))
rdev->saved_raid_disk = -1;
+ md_update_sb(mddev, 1);
clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
* failed devices.
*/
struct md_rdev *rdev;
- list_for_each_entry(rdev, &mddev->disks, same_set)
+ rdev_for_each(rdev, mddev)
if (rdev->raid_disk >= 0 &&
!test_bit(Blocked, &rdev->flags) &&
test_bit(Faulty, &rdev->flags) &&
atomic_read(&rdev->nr_pending)==0) {
if (mddev->pers->hot_remove_disk(
- mddev, rdev->raid_disk)==0) {
+ mddev, rdev) == 0) {
sysfs_unlink_rdev(mddev, rdev);
rdev->raid_disk = -1;
}
* any transients in the value of "sync_action".
*/
set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
- clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
/* Clear some bits that don't mean anything, but
* might be left set
*/
clear_bit(MD_RECOVERY_INTR, &mddev->recovery);
clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
- if (test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
+ if (!test_and_clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery) ||
+ test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
goto unlock;
/* no recovery is running.
* remove any failed drives, then
s + rdev->data_offset, sectors, acknowledged);
if (rv) {
/* Make sure they get written out promptly */
+ sysfs_notify_dirent_safe(rdev->sysfs_state);
set_bit(MD_CHANGE_CLEAN, &rdev->mddev->flags);
md_wakeup_thread(rdev->mddev->thread);
}
return;
write_seqlock_irq(&bb->lock);
- if (bb->changed == 0) {
+ if (bb->changed == 0 && bb->unacked_exist) {
u64 *p = bb->page;
int i;
for (i = 0; i < bb->count ; i++) {
struct mddev *mddev;
int need_delay = 0;
- if ((code == SYS_DOWN) || (code == SYS_HALT) || (code == SYS_POWER_OFF)) {
-
- printk(KERN_INFO "md: stopping all md devices.\n");
-
- for_each_mddev(mddev, tmp) {
- if (mddev_trylock(mddev)) {
- /* Force a switch to readonly even array
- * appears to still be in use. Hence
- * the '100'.
- */
- md_set_readonly(mddev, 100);
- mddev_unlock(mddev);
- }
- need_delay = 1;
+ for_each_mddev(mddev, tmp) {
+ if (mddev_trylock(mddev)) {
+ if (mddev->pers)
+ __md_stop_writes(mddev);
+ mddev->safemode = 2;
+ mddev_unlock(mddev);
}
- /*
- * certain more exotic SCSI devices are known to be
- * volatile wrt too early system reboots. While the
- * right place to handle this issue is the given
- * driver, we do want to have a safe RAID driver ...
- */
- if (need_delay)
- mdelay(1000*1);
+ need_delay = 1;
}
+ /*
+ * certain more exotic SCSI devices are known to be
+ * volatile wrt too early system reboots. While the
+ * right place to handle this issue is the given
+ * driver, we do want to have a safe RAID driver ...
+ */
+ if (need_delay)
+ mdelay(1000*1);
+
return NOTIFY_DONE;
}
projects / linux-flexiantxendom0-3.2.10.git / blobdiff