Neil Brown <neilb@cse.unsw.edu.au>.
+ - persistent bitmap code
+ Copyright (C) 2003-2004, Paul Clements, SteelEye Technology, Inc.
+
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
#include <linux/module.h>
#include <linux/config.h>
+#include <linux/kthread.h>
#include <linux/linkage.h>
#include <linux/raid/md.h>
+#include <linux/raid/bitmap.h>
#include <linux/sysctl.h>
#include <linux/devfs_fs_kernel.h>
#include <linux/buffer_head.h> /* for invalidate_bdev */
#include <linux/suspend.h>
+#include <linux/poll.h>
#include <linux/init.h>
+#include <linux/file.h>
+
#ifdef CONFIG_KMOD
#include <linux/kmod.h>
#endif
static void autostart_arrays (int part);
#endif
-static mdk_personality_t *pers[MAX_PERSONALITY];
-static spinlock_t pers_lock = SPIN_LOCK_UNLOCKED;
+static LIST_HEAD(pers_list);
+static DEFINE_SPINLOCK(pers_lock);
/*
* Current RAID-1,4,5 parallel reconstruction 'guaranteed speed limit'
* is 1000 KB/sec, so the extra system load does not show up that much.
* Increase it if you want to have more _guaranteed_ speed. Note that
- * the RAID driver will use the maximum available bandwith if the IO
+ * the RAID driver will use the maximum available bandwidth if the IO
* subsystem is idle. There is also an 'absolute maximum' reconstruction
* speed limit - in case reconstruction slows down your system despite
* idle IO detection.
*
* you can change it via /proc/sys/dev/raid/speed_limit_min and _max.
+ * or /sys/block/mdX/md/sync_speed_{min,max}
*/
static int sysctl_speed_limit_min = 1000;
static int sysctl_speed_limit_max = 200000;
+static inline int speed_min(mddev_t *mddev)
+{
+ return mddev->sync_speed_min ?
+ mddev->sync_speed_min : sysctl_speed_limit_min;
+}
+
+static inline int speed_max(mddev_t *mddev)
+{
+ return mddev->sync_speed_max ?
+ mddev->sync_speed_max : sysctl_speed_limit_max;
+}
static struct ctl_table_header *raid_table_header;
static struct block_device_operations md_fops;
+static int start_readonly;
+
+/*
+ * We have a system wide 'event count' that is incremented
+ * on any 'interesting' event, and readers of /proc/mdstat
+ * can use 'poll' or 'select' to find out when the event
+ * count increases.
+ *
+ * Events are:
+ * start array, stop array, error, add device, remove device,
+ * start build, activate spare
+ */
+static DECLARE_WAIT_QUEUE_HEAD(md_event_waiters);
+static atomic_t md_event_count;
+static void md_new_event(mddev_t *mddev)
+{
+ atomic_inc(&md_event_count);
+ wake_up(&md_event_waiters);
+}
+
/*
* Enables to iterate over all existing md arrays
* all_mddevs_lock protects this list.
*/
static LIST_HEAD(all_mddevs);
-static spinlock_t all_mddevs_lock = SPIN_LOCK_UNLOCKED;
+static DEFINE_SPINLOCK(all_mddevs_lock);
/*
tmp = tmp->next;}) \
)
+
static int md_fail_request (request_queue_t *q, struct bio *bio)
{
bio_io_error(bio, bio->bi_size);
if (!mddev->raid_disks && list_empty(&mddev->disks)) {
list_del(&mddev->all_mddevs);
blk_put_queue(mddev->queue);
- kfree(mddev);
+ kobject_unregister(&mddev->kobj);
}
spin_unlock(&all_mddevs_lock);
}
if (mddev->unit == unit) {
mddev_get(mddev);
spin_unlock(&all_mddevs_lock);
- if (new)
- kfree(new);
+ kfree(new);
return mddev;
}
}
spin_unlock(&all_mddevs_lock);
- new = (mddev_t *) kmalloc(sizeof(*new), GFP_KERNEL);
+ new = kzalloc(sizeof(*new), GFP_KERNEL);
if (!new)
return NULL;
- memset(new, 0, sizeof(*new));
-
new->unit = unit;
if (MAJOR(unit) == MD_MAJOR)
new->md_minor = MINOR(unit);
INIT_LIST_HEAD(&new->all_mddevs);
init_timer(&new->safemode_timer);
atomic_set(&new->active, 1);
+ spin_lock_init(&new->write_lock);
+ init_waitqueue_head(&new->sb_wait);
new->queue = blk_alloc_queue(GFP_KERNEL);
if (!new->queue) {
{
up(&mddev->reconfig_sem);
- if (mddev->thread)
- md_wakeup_thread(mddev->thread);
+ md_wakeup_thread(mddev->thread);
}
-mdk_rdev_t * find_rdev_nr(mddev_t *mddev, int nr)
+static mdk_rdev_t * find_rdev_nr(mddev_t *mddev, int nr)
{
mdk_rdev_t * rdev;
struct list_head *tmp;
return NULL;
}
-inline static sector_t calc_dev_sboffset(struct block_device *bdev)
+static struct mdk_personality *find_pers(int level, char *clevel)
+{
+ struct mdk_personality *pers;
+ list_for_each_entry(pers, &pers_list, list) {
+ if (level != LEVEL_NONE && pers->level == level)
+ return pers;
+ if (strcmp(pers->name, clevel)==0)
+ return pers;
+ }
+ return NULL;
+}
+
+static inline sector_t calc_dev_sboffset(struct block_device *bdev)
{
sector_t size = bdev->bd_inode->i_size >> BLOCK_SIZE_BITS;
return MD_NEW_SIZE_BLOCKS(size);
static void free_disk_sb(mdk_rdev_t * rdev)
{
if (rdev->sb_page) {
- page_cache_release(rdev->sb_page);
+ put_page(rdev->sb_page);
rdev->sb_loaded = 0;
rdev->sb_page = NULL;
rdev->sb_offset = 0;
}
+static int super_written(struct bio *bio, unsigned int bytes_done, int error)
+{
+ mdk_rdev_t *rdev = bio->bi_private;
+ mddev_t *mddev = rdev->mddev;
+ if (bio->bi_size)
+ return 1;
+
+ if (error || !test_bit(BIO_UPTODATE, &bio->bi_flags))
+ md_error(mddev, rdev);
+
+ if (atomic_dec_and_test(&mddev->pending_writes))
+ wake_up(&mddev->sb_wait);
+ bio_put(bio);
+ return 0;
+}
+
+static int super_written_barrier(struct bio *bio, unsigned int bytes_done, int error)
+{
+ struct bio *bio2 = bio->bi_private;
+ mdk_rdev_t *rdev = bio2->bi_private;
+ mddev_t *mddev = rdev->mddev;
+ if (bio->bi_size)
+ return 1;
+
+ if (!test_bit(BIO_UPTODATE, &bio->bi_flags) &&
+ error == -EOPNOTSUPP) {
+ unsigned long flags;
+ /* barriers don't appear to be supported :-( */
+ set_bit(BarriersNotsupp, &rdev->flags);
+ mddev->barriers_work = 0;
+ spin_lock_irqsave(&mddev->write_lock, flags);
+ bio2->bi_next = mddev->biolist;
+ mddev->biolist = bio2;
+ spin_unlock_irqrestore(&mddev->write_lock, flags);
+ wake_up(&mddev->sb_wait);
+ bio_put(bio);
+ return 0;
+ }
+ bio_put(bio2);
+ bio->bi_private = rdev;
+ return super_written(bio, bytes_done, error);
+}
+
+void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
+ sector_t sector, int size, struct page *page)
+{
+ /* write first size bytes of page to sector of rdev
+ * Increment mddev->pending_writes before returning
+ * and decrement it on completion, waking up sb_wait
+ * if zero is reached.
+ * If an error occurred, call md_error
+ *
+ * As we might need to resubmit the request if BIO_RW_BARRIER
+ * causes ENOTSUPP, we allocate a spare bio...
+ */
+ struct bio *bio = bio_alloc(GFP_NOIO, 1);
+ int rw = (1<<BIO_RW) | (1<<BIO_RW_SYNC);
+
+ bio->bi_bdev = rdev->bdev;
+ bio->bi_sector = sector;
+ bio_add_page(bio, page, size, 0);
+ bio->bi_private = rdev;
+ bio->bi_end_io = super_written;
+ bio->bi_rw = rw;
+
+ atomic_inc(&mddev->pending_writes);
+ if (!test_bit(BarriersNotsupp, &rdev->flags)) {
+ struct bio *rbio;
+ rw |= (1<<BIO_RW_BARRIER);
+ rbio = bio_clone(bio, GFP_NOIO);
+ rbio->bi_private = bio;
+ rbio->bi_end_io = super_written_barrier;
+ submit_bio(rw, rbio);
+ } else
+ submit_bio(rw, bio);
+}
+
+void md_super_wait(mddev_t *mddev)
+{
+ /* wait for all superblock writes that were scheduled to complete.
+ * if any had to be retried (due to BARRIER problems), retry them
+ */
+ DEFINE_WAIT(wq);
+ for(;;) {
+ prepare_to_wait(&mddev->sb_wait, &wq, TASK_UNINTERRUPTIBLE);
+ if (atomic_read(&mddev->pending_writes)==0)
+ break;
+ while (mddev->biolist) {
+ struct bio *bio;
+ spin_lock_irq(&mddev->write_lock);
+ bio = mddev->biolist;
+ mddev->biolist = bio->bi_next ;
+ bio->bi_next = NULL;
+ spin_unlock_irq(&mddev->write_lock);
+ submit_bio(bio->bi_rw, bio);
+ }
+ schedule();
+ }
+ finish_wait(&mddev->sb_wait, &wq);
+}
+
static int bi_complete(struct bio *bio, unsigned int bytes_done, int error)
{
if (bio->bi_size)
return 0;
}
-static int sync_page_io(struct block_device *bdev, sector_t sector, int size,
+int sync_page_io(struct block_device *bdev, sector_t sector, int size,
struct page *page, int rw)
{
- struct bio bio;
- struct bio_vec vec;
+ struct bio *bio = bio_alloc(GFP_NOIO, 1);
struct completion event;
+ int ret;
rw |= (1 << BIO_RW_SYNC);
- bio_init(&bio);
- bio.bi_io_vec = &vec;
- vec.bv_page = page;
- vec.bv_len = size;
- vec.bv_offset = 0;
- bio.bi_vcnt = 1;
- bio.bi_idx = 0;
- bio.bi_size = size;
- bio.bi_bdev = bdev;
- bio.bi_sector = sector;
+ bio->bi_bdev = bdev;
+ bio->bi_sector = sector;
+ bio_add_page(bio, page, size, 0);
init_completion(&event);
- bio.bi_private = &event;
- bio.bi_end_io = bi_complete;
- submit_bio(rw, &bio);
+ bio->bi_private = &event;
+ bio->bi_end_io = bi_complete;
+ submit_bio(rw, bio);
wait_for_completion(&event);
- return test_bit(BIO_UPTODATE, &bio.bi_flags);
+ ret = test_bit(BIO_UPTODATE, &bio->bi_flags);
+ bio_put(bio);
+ return ret;
}
+EXPORT_SYMBOL_GPL(sync_page_io);
-static int read_disk_sb(mdk_rdev_t * rdev)
+static int read_disk_sb(mdk_rdev_t * rdev, int size)
{
char b[BDEVNAME_SIZE];
if (!rdev->sb_page) {
return 0;
- if (!sync_page_io(rdev->bdev, rdev->sb_offset<<1, MD_SB_BYTES, rdev->sb_page, READ))
+ if (!sync_page_io(rdev->bdev, rdev->sb_offset<<1, size, rdev->sb_page, READ))
goto fail;
rdev->sb_loaded = 1;
return 0;
fail:
- printk(KERN_ERR "md: disabled device %s, could not read superblock.\n",
+ printk(KERN_WARNING "md: disabled device %s, could not read superblock.\n",
bdevname(rdev->bdev,b));
return -EINVAL;
}
ret = 1;
abort:
- if (tmp1)
- kfree(tmp1);
- if (tmp2)
- kfree(tmp2);
-
+ kfree(tmp1);
+ kfree(tmp2);
return ret;
}
return csum;
}
+
/*
* Handle superblock details.
* We want to be able to handle multiple superblock formats
sb_offset = calc_dev_sboffset(rdev->bdev);
rdev->sb_offset = sb_offset;
- ret = read_disk_sb(rdev);
+ ret = read_disk_sb(rdev, MD_SB_BYTES);
if (ret) return ret;
ret = -EINVAL;
if (sb->raid_disks <= 0)
goto abort;
- if (calc_sb_csum(sb) != sb->sb_csum) {
+ if (csum_fold(calc_sb_csum(sb)) != csum_fold(sb->sb_csum)) {
printk(KERN_WARNING "md: invalid superblock checksum on %s\n",
b);
goto abort;
rdev->preferred_minor = sb->md_minor;
rdev->data_offset = 0;
+ rdev->sb_size = MD_SB_BYTES;
- if (sb->level == MULTIPATH)
+ if (sb->level == LEVEL_MULTIPATH)
rdev->desc_nr = -1;
else
rdev->desc_nr = sb->this_disk.number;
}
rdev->size = calc_dev_size(rdev, sb->chunk_size);
+ if (rdev->size < sb->size && sb->level > 1)
+ /* "this cannot possibly happen" ... */
+ ret = -EINVAL;
+
abort:
return ret;
}
mdp_disk_t *desc;
mdp_super_t *sb = (mdp_super_t *)page_address(rdev->sb_page);
+ rdev->raid_disk = -1;
+ rdev->flags = 0;
if (mddev->raid_disks == 0) {
mddev->major_version = 0;
mddev->minor_version = sb->minor_version;
mddev->ctime = sb->ctime;
mddev->utime = sb->utime;
mddev->level = sb->level;
+ mddev->clevel[0] = 0;
mddev->layout = sb->layout;
mddev->raid_disks = sb->raid_disks;
mddev->size = sb->size;
mddev->events = md_event(sb);
+ mddev->bitmap_offset = 0;
+ mddev->default_bitmap_offset = MD_SB_BYTES >> 9;
if (sb->state & (1<<MD_SB_CLEAN))
mddev->recovery_cp = MaxSector;
memcpy(mddev->uuid+12,&sb->set_uuid3, 4);
mddev->max_disks = MD_SB_DISKS;
- } else {
- __u64 ev1;
- ev1 = md_event(sb);
+
+ if (sb->state & (1<<MD_SB_BITMAP_PRESENT) &&
+ mddev->bitmap_file == NULL) {
+ if (mddev->level != 1 && mddev->level != 5 && mddev->level != 6
+ && mddev->level != 10) {
+ /* FIXME use a better test */
+ printk(KERN_WARNING "md: bitmaps not supported for this level.\n");
+ return -EINVAL;
+ }
+ mddev->bitmap_offset = mddev->default_bitmap_offset;
+ }
+
+ } else if (mddev->pers == NULL) {
+ /* Insist on good event counter while assembling */
+ __u64 ev1 = md_event(sb);
++ev1;
if (ev1 < mddev->events)
return -EINVAL;
- }
+ } else if (mddev->bitmap) {
+ /* if adding to array with a bitmap, then we can accept an
+ * older device ... but not too old.
+ */
+ __u64 ev1 = md_event(sb);
+ if (ev1 < mddev->bitmap->events_cleared)
+ return 0;
+ } else /* just a hot-add of a new device, leave raid_disk at -1 */
+ return 0;
+
if (mddev->level != LEVEL_MULTIPATH) {
- rdev->raid_disk = -1;
- rdev->in_sync = rdev->faulty = 0;
desc = sb->disks + rdev->desc_nr;
if (desc->state & (1<<MD_DISK_FAULTY))
- rdev->faulty = 1;
+ set_bit(Faulty, &rdev->flags);
else if (desc->state & (1<<MD_DISK_SYNC) &&
desc->raid_disk < mddev->raid_disks) {
- rdev->in_sync = 1;
+ set_bit(In_sync, &rdev->flags);
rdev->raid_disk = desc->raid_disk;
}
- }
+ if (desc->state & (1<<MD_DISK_WRITEMOSTLY))
+ set_bit(WriteMostly, &rdev->flags);
+ } else /* MULTIPATH are always insync */
+ set_bit(In_sync, &rdev->flags);
return 0;
}
mdk_rdev_t *rdev2;
int next_spare = mddev->raid_disks;
+
/* make rdev->sb match mddev data..
*
* 1/ zero out disks
int i;
int active=0, working=0,failed=0,spare=0,nr_disks=0;
+ rdev->sb_size = MD_SB_BYTES;
+
sb = (mdp_super_t*)page_address(rdev->sb_page);
memset(sb, 0, sizeof(*sb));
sb->layout = mddev->layout;
sb->chunk_size = mddev->chunk_size;
+ if (mddev->bitmap && mddev->bitmap_file == NULL)
+ sb->state |= (1<<MD_SB_BITMAP_PRESENT);
+
sb->disks[0].state = (1<<MD_DISK_REMOVED);
ITERATE_RDEV(mddev,rdev2,tmp) {
mdp_disk_t *d;
- if (rdev2->raid_disk >= 0 && rdev2->in_sync && !rdev2->faulty)
- rdev2->desc_nr = rdev2->raid_disk;
+ int desc_nr;
+ if (rdev2->raid_disk >= 0 && test_bit(In_sync, &rdev2->flags)
+ && !test_bit(Faulty, &rdev2->flags))
+ desc_nr = rdev2->raid_disk;
else
- rdev2->desc_nr = next_spare++;
+ desc_nr = next_spare++;
+ rdev2->desc_nr = desc_nr;
d = &sb->disks[rdev2->desc_nr];
nr_disks++;
d->number = rdev2->desc_nr;
d->major = MAJOR(rdev2->bdev->bd_dev);
d->minor = MINOR(rdev2->bdev->bd_dev);
- if (rdev2->raid_disk >= 0 && rdev->in_sync && !rdev2->faulty)
+ if (rdev2->raid_disk >= 0 && test_bit(In_sync, &rdev2->flags)
+ && !test_bit(Faulty, &rdev2->flags))
d->raid_disk = rdev2->raid_disk;
else
d->raid_disk = rdev2->desc_nr; /* compatibility */
- if (rdev2->faulty) {
+ if (test_bit(Faulty, &rdev2->flags)) {
d->state = (1<<MD_DISK_FAULTY);
failed++;
- } else if (rdev2->in_sync) {
+ } else if (test_bit(In_sync, &rdev2->flags)) {
d->state = (1<<MD_DISK_ACTIVE);
d->state |= (1<<MD_DISK_SYNC);
active++;
spare++;
working++;
}
+ if (test_bit(WriteMostly, &rdev2->flags))
+ d->state |= (1<<MD_DISK_WRITEMOSTLY);
}
-
/* now set the "removed" and "faulty" bits on any missing devices */
for (i=0 ; i < mddev->raid_disks ; i++) {
mdp_disk_t *d = &sb->disks[i];
static unsigned int calc_sb_1_csum(struct mdp_superblock_1 * sb)
{
unsigned int disk_csum, csum;
- int size = 256 + sb->max_dev*2;
+ unsigned long long newcsum;
+ int size = 256 + le32_to_cpu(sb->max_dev)*2;
+ unsigned int *isuper = (unsigned int*)sb;
+ int i;
disk_csum = sb->sb_csum;
sb->sb_csum = 0;
- csum = csum_partial((void *)sb, size, 0);
+ newcsum = 0;
+ for (i=0; size>=4; size -= 4 )
+ newcsum += le32_to_cpu(*isuper++);
+
+ if (size == 2)
+ newcsum += le16_to_cpu(*(unsigned short*) isuper);
+
+ csum = (newcsum & 0xffffffff) + (newcsum >> 32);
sb->sb_csum = disk_csum;
- return csum;
+ return cpu_to_le32(csum);
}
static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version)
int ret;
sector_t sb_offset;
char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
+ int bmask;
/*
* Calculate the position of the superblock.
case 0:
sb_offset = rdev->bdev->bd_inode->i_size >> 9;
sb_offset -= 8*2;
- sb_offset &= ~(4*2);
+ sb_offset &= ~(sector_t)(4*2-1);
/* convert from sectors to K */
sb_offset /= 2;
break;
}
rdev->sb_offset = sb_offset;
- ret = read_disk_sb(rdev);
+ /* superblock is rarely larger than 1K, but it can be larger,
+ * and it is safe to read 4k, so we do that
+ */
+ ret = read_disk_sb(rdev, 4096);
if (ret) return ret;
sb->major_version != cpu_to_le32(1) ||
le32_to_cpu(sb->max_dev) > (4096-256)/2 ||
le64_to_cpu(sb->super_offset) != (rdev->sb_offset<<1) ||
- sb->feature_map != 0)
+ (le32_to_cpu(sb->feature_map) & ~MD_FEATURE_ALL) != 0)
return -EINVAL;
if (calc_sb_1_csum(sb) != sb->sb_csum) {
bdevname(rdev->bdev,b));
return -EINVAL;
}
+ if (le64_to_cpu(sb->data_size) < 10) {
+ printk("md: data_size too small on %s\n",
+ bdevname(rdev->bdev,b));
+ return -EINVAL;
+ }
rdev->preferred_minor = 0xffff;
rdev->data_offset = le64_to_cpu(sb->data_offset);
+ atomic_set(&rdev->corrected_errors, le32_to_cpu(sb->cnt_corrected_read));
+
+ rdev->sb_size = le32_to_cpu(sb->max_dev) * 2 + 256;
+ bmask = queue_hardsect_size(rdev->bdev->bd_disk->queue)-1;
+ if (rdev->sb_size & bmask)
+ rdev-> sb_size = (rdev->sb_size | bmask)+1;
if (refdev == 0)
- return 1;
+ ret = 1;
else {
__u64 ev1, ev2;
struct mdp_superblock_1 *refsb =
ev2 = le64_to_cpu(refsb->events);
if (ev1 > ev2)
- return 1;
+ ret = 1;
+ else
+ ret = 0;
}
if (minor_version)
rdev->size = ((rdev->bdev->bd_inode->i_size>>9) - le64_to_cpu(sb->data_offset)) / 2;
rdev->size = le64_to_cpu(sb->data_size)/2;
if (le32_to_cpu(sb->chunksize))
rdev->size &= ~((sector_t)le32_to_cpu(sb->chunksize)/2 - 1);
- return 0;
+
+ if (le32_to_cpu(sb->size) > rdev->size*2)
+ return -EINVAL;
+ return ret;
}
static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev)
{
struct mdp_superblock_1 *sb = (struct mdp_superblock_1*)page_address(rdev->sb_page);
+ rdev->raid_disk = -1;
+ rdev->flags = 0;
if (mddev->raid_disks == 0) {
mddev->major_version = 1;
- mddev->minor_version = 0;
mddev->patch_version = 0;
mddev->persistent = 1;
mddev->chunk_size = le32_to_cpu(sb->chunksize) << 9;
mddev->ctime = le64_to_cpu(sb->ctime) & ((1ULL << 32)-1);
mddev->utime = le64_to_cpu(sb->utime) & ((1ULL << 32)-1);
mddev->level = le32_to_cpu(sb->level);
+ mddev->clevel[0] = 0;
mddev->layout = le32_to_cpu(sb->layout);
mddev->raid_disks = le32_to_cpu(sb->raid_disks);
- mddev->size = (u32)le64_to_cpu(sb->size);
+ mddev->size = le64_to_cpu(sb->size)/2;
mddev->events = le64_to_cpu(sb->events);
+ mddev->bitmap_offset = 0;
+ mddev->default_bitmap_offset = 1024 >> 9;
mddev->recovery_cp = le64_to_cpu(sb->resync_offset);
memcpy(mddev->uuid, sb->set_uuid, 16);
mddev->max_disks = (4096-256)/2;
- } else {
- __u64 ev1;
- ev1 = le64_to_cpu(sb->events);
+
+ if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET) &&
+ mddev->bitmap_file == NULL ) {
+ if (mddev->level != 1 && mddev->level != 5 && mddev->level != 6
+ && mddev->level != 10) {
+ printk(KERN_WARNING "md: bitmaps not supported for this level.\n");
+ return -EINVAL;
+ }
+ mddev->bitmap_offset = (__s32)le32_to_cpu(sb->bitmap_offset);
+ }
+ } else if (mddev->pers == NULL) {
+ /* Insist of good event counter while assembling */
+ __u64 ev1 = le64_to_cpu(sb->events);
++ev1;
if (ev1 < mddev->events)
return -EINVAL;
- }
+ } else if (mddev->bitmap) {
+ /* If adding to array with a bitmap, then we can accept an
+ * older device, but not too old.
+ */
+ __u64 ev1 = le64_to_cpu(sb->events);
+ if (ev1 < mddev->bitmap->events_cleared)
+ return 0;
+ } else /* just a hot-add of a new device, leave raid_disk at -1 */
+ return 0;
if (mddev->level != LEVEL_MULTIPATH) {
int role;
role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
switch(role) {
case 0xffff: /* spare */
- rdev->in_sync = 0;
- rdev->faulty = 0;
- rdev->raid_disk = -1;
break;
case 0xfffe: /* faulty */
- rdev->in_sync = 0;
- rdev->faulty = 1;
- rdev->raid_disk = -1;
+ set_bit(Faulty, &rdev->flags);
break;
default:
- rdev->in_sync = 1;
- rdev->faulty = 0;
+ set_bit(In_sync, &rdev->flags);
rdev->raid_disk = role;
break;
}
- }
+ if (sb->devflags & WriteMostly1)
+ set_bit(WriteMostly, &rdev->flags);
+ } else /* MULTIPATH are always insync */
+ set_bit(In_sync, &rdev->flags);
+
return 0;
}
else
sb->resync_offset = cpu_to_le64(0);
+ sb->cnt_corrected_read = atomic_read(&rdev->corrected_errors);
+
+ sb->raid_disks = cpu_to_le32(mddev->raid_disks);
+ sb->size = cpu_to_le64(mddev->size<<1);
+
+ if (mddev->bitmap && mddev->bitmap_file == NULL) {
+ sb->bitmap_offset = cpu_to_le32((__u32)mddev->bitmap_offset);
+ sb->feature_map = cpu_to_le32(MD_FEATURE_BITMAP_OFFSET);
+ }
+
max_dev = 0;
ITERATE_RDEV(mddev,rdev2,tmp)
- if (rdev2->desc_nr > max_dev)
- max_dev = rdev2->desc_nr;
+ if (rdev2->desc_nr+1 > max_dev)
+ max_dev = rdev2->desc_nr+1;
- sb->max_dev = max_dev;
+ sb->max_dev = cpu_to_le32(max_dev);
for (i=0; i<max_dev;i++)
- sb->dev_roles[max_dev] = cpu_to_le16(0xfffe);
+ sb->dev_roles[i] = cpu_to_le16(0xfffe);
ITERATE_RDEV(mddev,rdev2,tmp) {
i = rdev2->desc_nr;
- if (rdev2->faulty)
+ if (test_bit(Faulty, &rdev2->flags))
sb->dev_roles[i] = cpu_to_le16(0xfffe);
- else if (rdev2->in_sync)
+ else if (test_bit(In_sync, &rdev2->flags))
sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk);
else
sb->dev_roles[i] = cpu_to_le16(0xffff);
}
sb->recovery_offset = cpu_to_le64(0); /* not supported yet */
+ sb->sb_csum = calc_sb_1_csum(sb);
}
-struct super_type super_types[] = {
+static struct super_type super_types[] = {
[0] = {
.name = "0.90.0",
.owner = THIS_MODULE,
{
mdk_rdev_t *same_pdev;
char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
+ struct kobject *ko;
+ char *s;
if (rdev->mddev) {
MD_BUG();
return -EINVAL;
}
+ /* make sure rdev->size exceeds mddev->size */
+ if (rdev->size && (mddev->size == 0 || rdev->size < mddev->size)) {
+ if (mddev->pers)
+ /* Cannot change size, so fail */
+ return -ENOSPC;
+ else
+ mddev->size = rdev->size;
+ }
same_pdev = match_dev_unit(mddev, rdev);
if (same_pdev)
printk(KERN_WARNING
if (find_rdev_nr(mddev, rdev->desc_nr))
return -EBUSY;
}
+ bdevname(rdev->bdev,b);
+ if (kobject_set_name(&rdev->kobj, "dev-%s", b) < 0)
+ return -ENOMEM;
+ 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", bdevname(rdev->bdev,b));
+ printk(KERN_INFO "md: bind<%s>\n", b);
+
+ rdev->kobj.parent = &mddev->kobj;
+ kobject_add(&rdev->kobj);
+
+ 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");
return 0;
}
list_del_init(&rdev->same_set);
printk(KERN_INFO "md: unbind<%s>\n", bdevname(rdev->bdev,b));
rdev->mddev = NULL;
+ sysfs_remove_link(&rdev->kobj, "block");
+ kobject_del(&rdev->kobj);
}
/*
* prevent the device from being mounted, repartitioned or
* otherwise reused by a RAID array (or any other kernel
- * subsystem), by opening the device. [simply getting an
- * inode is not enough, the SCSI module usage code needs
- * an explicit open() on the device]
+ * subsystem), by bd_claiming the device.
*/
static int lock_rdev(mdk_rdev_t *rdev, dev_t dev)
{
int err = 0;
struct block_device *bdev;
+ char b[BDEVNAME_SIZE];
bdev = open_by_devnum(dev, FMODE_READ|FMODE_WRITE);
- if (IS_ERR(bdev))
+ if (IS_ERR(bdev)) {
+ printk(KERN_ERR "md: could not open %s.\n",
+ __bdevname(dev, b));
return PTR_ERR(bdev);
+ }
err = bd_claim(bdev, rdev);
if (err) {
+ printk(KERN_ERR "md: could not bd_claim %s.\n",
+ bdevname(bdev, b));
blkdev_put(bdev);
return err;
}
md_autodetect_dev(rdev->bdev->bd_dev);
#endif
unlock_rdev(rdev);
- kfree(rdev);
+ kobject_put(&rdev->kobj);
}
static void kick_rdev_from_array(mdk_rdev_t * rdev)
static void print_desc(mdp_disk_t *desc)
{
- char b[BDEVNAME_SIZE];
-
- printk(" DISK<N:%d,%s(%d,%d),R:%d,S:%d>\n", desc->number,
- __bdevname(MKDEV(desc->major, desc->minor), b),
+ printk(" DISK<N:%d,(%d,%d),R:%d,S:%d>\n", desc->number,
desc->major,desc->minor,desc->raid_disk,desc->state);
}
char b[BDEVNAME_SIZE];
printk(KERN_INFO "md: rdev %s, SZ:%08llu F:%d S:%d DN:%u\n",
bdevname(rdev->bdev,b), (unsigned long long)rdev->size,
- rdev->faulty, rdev->in_sync, rdev->desc_nr);
+ test_bit(Faulty, &rdev->flags), test_bit(In_sync, &rdev->flags),
+ rdev->desc_nr);
if (rdev->sb_loaded) {
printk(KERN_INFO "md: rdev superblock:\n");
print_sb((mdp_super_t*)page_address(rdev->sb_page));
printk("md: * <COMPLETE RAID STATE PRINTOUT> *\n");
printk("md: **********************************\n");
ITERATE_MDDEV(mddev,tmp) {
- printk("%s: ", mdname(mddev));
+ if (mddev->bitmap)
+ bitmap_print_sb(mddev->bitmap);
+ else
+ printk("%s: ", mdname(mddev));
ITERATE_RDEV(mddev,rdev,tmp2)
printk("<%s>", bdevname(rdev->bdev,b));
printk("\n");
}
-static int write_disk_sb(mdk_rdev_t * rdev)
-{
- char b[BDEVNAME_SIZE];
- if (!rdev->sb_loaded) {
- MD_BUG();
- return 1;
- }
- if (rdev->faulty) {
- MD_BUG();
- return 1;
- }
-
- dprintk(KERN_INFO "(write) %s's sb offset: %llu\n",
- bdevname(rdev->bdev,b),
- (unsigned long long)rdev->sb_offset);
-
- if (sync_page_io(rdev->bdev, rdev->sb_offset<<1, MD_SB_BYTES, rdev->sb_page, WRITE))
- return 0;
-
- printk("md: write_disk_sb failed for device %s\n",
- bdevname(rdev->bdev,b));
- return 1;
-}
-
static void sync_sbs(mddev_t * mddev)
{
mdk_rdev_t *rdev;
static void md_update_sb(mddev_t * mddev)
{
- int err, count = 100;
+ int err;
struct list_head *tmp;
mdk_rdev_t *rdev;
+ int sync_req;
- mddev->sb_dirty = 0;
repeat:
+ spin_lock_irq(&mddev->write_lock);
+ sync_req = mddev->in_sync;
mddev->utime = get_seconds();
mddev->events ++;
MD_BUG();
mddev->events --;
}
+ mddev->sb_dirty = 2;
sync_sbs(mddev);
/*
* do not write anything to disk if using
* nonpersistent superblocks
*/
- if (!mddev->persistent)
+ if (!mddev->persistent) {
+ mddev->sb_dirty = 0;
+ spin_unlock_irq(&mddev->write_lock);
+ wake_up(&mddev->sb_wait);
return;
+ }
+ spin_unlock_irq(&mddev->write_lock);
dprintk(KERN_INFO
"md: updating %s RAID superblock on device (in sync %d)\n",
mdname(mddev),mddev->in_sync);
- err = 0;
+ err = bitmap_update_sb(mddev->bitmap);
ITERATE_RDEV(mddev,rdev,tmp) {
char b[BDEVNAME_SIZE];
dprintk(KERN_INFO "md: ");
- if (rdev->faulty)
+ if (test_bit(Faulty, &rdev->flags))
dprintk("(skipping faulty ");
dprintk("%s ", bdevname(rdev->bdev,b));
- if (!rdev->faulty) {
- err += write_disk_sb(rdev);
+ if (!test_bit(Faulty, &rdev->flags)) {
+ md_super_write(mddev,rdev,
+ rdev->sb_offset<<1, rdev->sb_size,
+ rdev->sb_page);
+ dprintk(KERN_INFO "(write) %s's sb offset: %llu\n",
+ bdevname(rdev->bdev,b),
+ (unsigned long long)rdev->sb_offset);
+
} else
dprintk(")\n");
- if (!err && mddev->level == LEVEL_MULTIPATH)
+ if (mddev->level == LEVEL_MULTIPATH)
/* only need to write one superblock... */
break;
}
- if (err) {
- if (--count) {
- printk(KERN_ERR "md: errors occurred during superblock"
- " update, repeating\n");
- goto repeat;
- }
- printk(KERN_ERR \
- "md: excessive errors occurred during superblock update, exiting\n");
+ md_super_wait(mddev);
+ /* if there was a failure, sb_dirty was set to 1, and we re-write super */
+
+ spin_lock_irq(&mddev->write_lock);
+ if (mddev->in_sync != sync_req|| mddev->sb_dirty == 1) {
+ /* have to write it out again */
+ spin_unlock_irq(&mddev->write_lock);
+ goto repeat;
+ }
+ mddev->sb_dirty = 0;
+ spin_unlock_irq(&mddev->write_lock);
+ wake_up(&mddev->sb_wait);
+
+}
+
+/* words written to sysfs files may, or my not, be \n terminated.
+ * We want to accept with case. For this we use cmd_match.
+ */
+static int cmd_match(const char *cmd, const char *str)
+{
+ /* See if cmd, written into a sysfs file, matches
+ * str. They must either be the same, or cmd can
+ * have a trailing newline
+ */
+ while (*cmd && *str && *cmd == *str) {
+ cmd++;
+ str++;
+ }
+ if (*cmd == '\n')
+ cmd++;
+ if (*str || *cmd)
+ return 0;
+ return 1;
+}
+
+struct rdev_sysfs_entry {
+ struct attribute attr;
+ ssize_t (*show)(mdk_rdev_t *, char *);
+ ssize_t (*store)(mdk_rdev_t *, const char *, size_t);
+};
+
+static ssize_t
+state_show(mdk_rdev_t *rdev, char *page)
+{
+ char *sep = "";
+ int len=0;
+
+ if (test_bit(Faulty, &rdev->flags)) {
+ len+= sprintf(page+len, "%sfaulty",sep);
+ sep = ",";
+ }
+ if (test_bit(In_sync, &rdev->flags)) {
+ len += sprintf(page+len, "%sin_sync",sep);
+ sep = ",";
+ }
+ if (!test_bit(Faulty, &rdev->flags) &&
+ !test_bit(In_sync, &rdev->flags)) {
+ len += sprintf(page+len, "%sspare", sep);
+ sep = ",";
+ }
+ return len+sprintf(page+len, "\n");
+}
+
+static struct rdev_sysfs_entry
+rdev_state = __ATTR_RO(state);
+
+static ssize_t
+super_show(mdk_rdev_t *rdev, char *page)
+{
+ if (rdev->sb_loaded && rdev->sb_size) {
+ memcpy(page, page_address(rdev->sb_page), rdev->sb_size);
+ return rdev->sb_size;
+ } else
+ return 0;
+}
+static struct rdev_sysfs_entry rdev_super = __ATTR_RO(super);
+
+static ssize_t
+errors_show(mdk_rdev_t *rdev, char *page)
+{
+ return sprintf(page, "%d\n", atomic_read(&rdev->corrected_errors));
+}
+
+static ssize_t
+errors_store(mdk_rdev_t *rdev, const char *buf, size_t len)
+{
+ char *e;
+ unsigned long n = simple_strtoul(buf, &e, 10);
+ if (*buf && (*e == 0 || *e == '\n')) {
+ atomic_set(&rdev->corrected_errors, n);
+ return len;
}
+ return -EINVAL;
+}
+static struct rdev_sysfs_entry rdev_errors =
+__ATTR(errors, 0644, errors_show, errors_store);
+
+static ssize_t
+slot_show(mdk_rdev_t *rdev, char *page)
+{
+ if (rdev->raid_disk < 0)
+ return sprintf(page, "none\n");
+ else
+ return sprintf(page, "%d\n", rdev->raid_disk);
+}
+
+static ssize_t
+slot_store(mdk_rdev_t *rdev, const char *buf, size_t len)
+{
+ char *e;
+ int slot = simple_strtoul(buf, &e, 10);
+ if (strncmp(buf, "none", 4)==0)
+ slot = -1;
+ else if (e==buf || (*e && *e!= '\n'))
+ return -EINVAL;
+ if (rdev->mddev->pers)
+ /* Cannot set slot in active array (yet) */
+ return -EBUSY;
+ if (slot >= rdev->mddev->raid_disks)
+ return -ENOSPC;
+ rdev->raid_disk = slot;
+ /* assume it is working */
+ rdev->flags = 0;
+ set_bit(In_sync, &rdev->flags);
+ return len;
+}
+
+
+static struct rdev_sysfs_entry rdev_slot =
+__ATTR(slot, 0644, slot_show, slot_store);
+
+static ssize_t
+offset_show(mdk_rdev_t *rdev, char *page)
+{
+ return sprintf(page, "%llu\n", (unsigned long long)rdev->data_offset);
+}
+
+static ssize_t
+offset_store(mdk_rdev_t *rdev, const char *buf, size_t len)
+{
+ char *e;
+ unsigned long long offset = simple_strtoull(buf, &e, 10);
+ if (e==buf || (*e && *e != '\n'))
+ return -EINVAL;
+ if (rdev->mddev->pers)
+ return -EBUSY;
+ rdev->data_offset = offset;
+ return len;
+}
+
+static struct rdev_sysfs_entry rdev_offset =
+__ATTR(offset, 0644, offset_show, offset_store);
+
+static ssize_t
+rdev_size_show(mdk_rdev_t *rdev, char *page)
+{
+ return sprintf(page, "%llu\n", (unsigned long long)rdev->size);
+}
+
+static ssize_t
+rdev_size_store(mdk_rdev_t *rdev, const char *buf, size_t len)
+{
+ char *e;
+ unsigned long long size = simple_strtoull(buf, &e, 10);
+ if (e==buf || (*e && *e != '\n'))
+ return -EINVAL;
+ if (rdev->mddev->pers)
+ return -EBUSY;
+ rdev->size = size;
+ if (size < rdev->mddev->size || rdev->mddev->size == 0)
+ rdev->mddev->size = size;
+ return len;
+}
+
+static struct rdev_sysfs_entry rdev_size =
+__ATTR(size, 0644, rdev_size_show, rdev_size_store);
+
+static struct attribute *rdev_default_attrs[] = {
+ &rdev_state.attr,
+ &rdev_super.attr,
+ &rdev_errors.attr,
+ &rdev_slot.attr,
+ &rdev_offset.attr,
+ &rdev_size.attr,
+ NULL,
+};
+static ssize_t
+rdev_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
+{
+ struct rdev_sysfs_entry *entry = container_of(attr, struct rdev_sysfs_entry, attr);
+ mdk_rdev_t *rdev = container_of(kobj, mdk_rdev_t, kobj);
+
+ if (!entry->show)
+ return -EIO;
+ return entry->show(rdev, page);
+}
+
+static ssize_t
+rdev_attr_store(struct kobject *kobj, struct attribute *attr,
+ const char *page, size_t length)
+{
+ struct rdev_sysfs_entry *entry = container_of(attr, struct rdev_sysfs_entry, attr);
+ mdk_rdev_t *rdev = container_of(kobj, mdk_rdev_t, kobj);
+
+ if (!entry->store)
+ return -EIO;
+ return entry->store(rdev, page, length);
+}
+
+static void rdev_free(struct kobject *ko)
+{
+ mdk_rdev_t *rdev = container_of(ko, mdk_rdev_t, kobj);
+ kfree(rdev);
}
+static struct sysfs_ops rdev_sysfs_ops = {
+ .show = rdev_attr_show,
+ .store = rdev_attr_store,
+};
+static struct kobj_type rdev_ktype = {
+ .release = rdev_free,
+ .sysfs_ops = &rdev_sysfs_ops,
+ .default_attrs = rdev_default_attrs,
+};
/*
* Import a device. If 'super_format' >= 0, then sanity check the superblock
mdk_rdev_t *rdev;
sector_t size;
- rdev = (mdk_rdev_t *) kmalloc(sizeof(*rdev), GFP_KERNEL);
+ rdev = kzalloc(sizeof(*rdev), GFP_KERNEL);
if (!rdev) {
- printk(KERN_ERR "md: could not alloc mem for %s!\n",
- __bdevname(newdev, b));
+ printk(KERN_ERR "md: could not alloc mem for new device!\n");
return ERR_PTR(-ENOMEM);
}
- memset(rdev, 0, sizeof(*rdev));
if ((err = alloc_disk_sb(rdev)))
goto abort_free;
err = lock_rdev(rdev, newdev);
- if (err) {
- printk(KERN_ERR "md: could not lock %s.\n",
- __bdevname(newdev, b));
+ if (err)
goto abort_free;
- }
+
+ rdev->kobj.parent = NULL;
+ rdev->kobj.ktype = &rdev_ktype;
+ kobject_init(&rdev->kobj);
+
rdev->desc_nr = -1;
- rdev->faulty = 0;
- rdev->in_sync = 0;
+ rdev->flags = 0;
rdev->data_offset = 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) {
*/
-static int analyze_sbs(mddev_t * mddev)
+static void analyze_sbs(mddev_t * mddev)
{
int i;
struct list_head *tmp;
if (mddev->level == LEVEL_MULTIPATH) {
rdev->desc_nr = i++;
rdev->raid_disk = rdev->desc_nr;
- rdev->in_sync = 1;
+ set_bit(In_sync, &rdev->flags);
}
}
- /*
- * Check if we can support this RAID array
- */
- if (mddev->major_version != MD_MAJOR_VERSION ||
- mddev->minor_version > MD_MINOR_VERSION) {
- printk(KERN_ALERT
- "md: %s: unsupported raid array version %d.%d.%d\n",
- mdname(mddev), mddev->major_version,
- mddev->minor_version, mddev->patch_version);
- goto abort;
- }
- if ((mddev->recovery_cp != MaxSector) &&
- ((mddev->level == 1) ||
- ((mddev->level >= 4) && (mddev->level <= 6))))
+ if (mddev->recovery_cp != MaxSector &&
+ mddev->level >= 1)
printk(KERN_ERR "md: %s: raid array is not clean"
" -- starting background reconstruction\n",
mdname(mddev));
- return 0;
-abort:
- return 1;
}
-int mdp_major = 0;
+static ssize_t
+level_show(mddev_t *mddev, char *page)
+{
+ struct mdk_personality *p = mddev->pers;
+ if (p)
+ return sprintf(page, "%s\n", p->name);
+ else if (mddev->clevel[0])
+ return sprintf(page, "%s\n", mddev->clevel);
+ else if (mddev->level != LEVEL_NONE)
+ return sprintf(page, "%d\n", mddev->level);
+ else
+ return 0;
+}
-static struct kobject *md_probe(dev_t dev, int *part, void *data)
+static ssize_t
+level_store(mddev_t *mddev, const char *buf, size_t len)
{
- static DECLARE_MUTEX(disks_sem);
- mddev_t *mddev = mddev_find(dev);
- struct gendisk *disk;
- int partitioned = (MAJOR(dev) != MD_MAJOR);
- int shift = partitioned ? MdpMinorShift : 0;
- int unit = MINOR(dev) >> shift;
+ int rv = len;
+ if (mddev->pers)
+ return -EBUSY;
+ if (len == 0)
+ return 0;
+ if (len >= sizeof(mddev->clevel))
+ return -ENOSPC;
+ strncpy(mddev->clevel, buf, len);
+ if (mddev->clevel[len-1] == '\n')
+ len--;
+ mddev->clevel[len] = 0;
+ mddev->level = LEVEL_NONE;
+ return rv;
+}
- if (!mddev)
- return NULL;
+static struct md_sysfs_entry md_level =
+__ATTR(level, 0644, level_show, level_store);
- down(&disks_sem);
+static ssize_t
+raid_disks_show(mddev_t *mddev, char *page)
+{
+ if (mddev->raid_disks == 0)
+ return 0;
+ return sprintf(page, "%d\n", mddev->raid_disks);
+}
+
+static int update_raid_disks(mddev_t *mddev, int raid_disks);
+
+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);
+
+ if (!*buf || (*e && *e != '\n'))
+ return -EINVAL;
+
+ if (mddev->pers)
+ rv = update_raid_disks(mddev, n);
+ else
+ mddev->raid_disks = n;
+ return rv ? rv : len;
+}
+static struct md_sysfs_entry md_raid_disks =
+__ATTR(raid_disks, 0644, raid_disks_show, raid_disks_store);
+
+static ssize_t
+chunk_size_show(mddev_t *mddev, char *page)
+{
+ return sprintf(page, "%d\n", mddev->chunk_size);
+}
+
+static ssize_t
+chunk_size_store(mddev_t *mddev, const char *buf, size_t len)
+{
+ /* can only set chunk_size if array is not yet active */
+ char *e;
+ unsigned long n = simple_strtoul(buf, &e, 10);
+
+ if (mddev->pers)
+ return -EBUSY;
+ if (!*buf || (*e && *e != '\n'))
+ return -EINVAL;
+
+ mddev->chunk_size = n;
+ return len;
+}
+static struct md_sysfs_entry md_chunk_size =
+__ATTR(chunk_size, 0644, chunk_size_show, chunk_size_store);
+
+static ssize_t
+null_show(mddev_t *mddev, char *page)
+{
+ return -EINVAL;
+}
+
+static ssize_t
+new_dev_store(mddev_t *mddev, const char *buf, size_t len)
+{
+ /* buf must be %d:%d\n? giving major and minor numbers */
+ /* The new device is added to the array.
+ * If the array has a persistent superblock, we read the
+ * superblock to initialise info and check validity.
+ * Otherwise, only checking done is that in bind_rdev_to_array,
+ * which mainly checks size.
+ */
+ char *e;
+ int major = simple_strtoul(buf, &e, 10);
+ int minor;
+ dev_t dev;
+ mdk_rdev_t *rdev;
+ int err;
+
+ if (!*buf || *e != ':' || !e[1] || e[1] == '\n')
+ return -EINVAL;
+ minor = simple_strtoul(e+1, &e, 10);
+ if (*e && *e != '\n')
+ return -EINVAL;
+ dev = MKDEV(major, minor);
+ if (major != MAJOR(dev) ||
+ minor != MINOR(dev))
+ return -EOVERFLOW;
+
+
+ if (mddev->persistent) {
+ rdev = md_import_device(dev, mddev->major_version,
+ mddev->minor_version);
+ if (!IS_ERR(rdev) && !list_empty(&mddev->disks)) {
+ mdk_rdev_t *rdev0 = list_entry(mddev->disks.next,
+ mdk_rdev_t, same_set);
+ err = super_types[mddev->major_version]
+ .load_super(rdev, rdev0, mddev->minor_version);
+ if (err < 0)
+ goto out;
+ }
+ } else
+ rdev = md_import_device(dev, -1, -1);
+
+ if (IS_ERR(rdev))
+ return PTR_ERR(rdev);
+ err = bind_rdev_to_array(rdev, mddev);
+ out:
+ if (err)
+ export_rdev(rdev);
+ return err ? err : len;
+}
+
+static struct md_sysfs_entry md_new_device =
+__ATTR(new_dev, 0200, null_show, new_dev_store);
+
+static ssize_t
+size_show(mddev_t *mddev, char *page)
+{
+ return sprintf(page, "%llu\n", (unsigned long long)mddev->size);
+}
+
+static int update_size(mddev_t *mddev, unsigned long size);
+
+static ssize_t
+size_store(mddev_t *mddev, const char *buf, size_t len)
+{
+ /* If array is inactive, we can reduce the component size, but
+ * not increase it (except from 0).
+ * If array is active, we can try an on-line resize
+ */
+ char *e;
+ int err = 0;
+ unsigned long long size = simple_strtoull(buf, &e, 10);
+ if (!*buf || *buf == '\n' ||
+ (*e && *e != '\n'))
+ return -EINVAL;
+
+ if (mddev->pers) {
+ err = update_size(mddev, size);
+ md_update_sb(mddev);
+ } else {
+ if (mddev->size == 0 ||
+ mddev->size > size)
+ mddev->size = size;
+ else
+ err = -ENOSPC;
+ }
+ return err ? err : len;
+}
+
+static struct md_sysfs_entry md_size =
+__ATTR(component_size, 0644, size_show, size_store);
+
+
+/* Metdata version.
+ * This is either 'none' for arrays with externally managed metadata,
+ * or N.M for internally known formats
+ */
+static ssize_t
+metadata_show(mddev_t *mddev, char *page)
+{
+ if (mddev->persistent)
+ return sprintf(page, "%d.%d\n",
+ mddev->major_version, mddev->minor_version);
+ else
+ return sprintf(page, "none\n");
+}
+
+static ssize_t
+metadata_store(mddev_t *mddev, const char *buf, size_t len)
+{
+ int major, minor;
+ char *e;
+ if (!list_empty(&mddev->disks))
+ return -EBUSY;
+
+ if (cmd_match(buf, "none")) {
+ mddev->persistent = 0;
+ mddev->major_version = 0;
+ mddev->minor_version = 90;
+ return len;
+ }
+ major = simple_strtoul(buf, &e, 10);
+ if (e==buf || *e != '.')
+ return -EINVAL;
+ buf = e+1;
+ minor = simple_strtoul(buf, &e, 10);
+ if (e==buf || *e != '\n')
+ return -EINVAL;
+ if (major >= sizeof(super_types)/sizeof(super_types[0]) ||
+ super_types[major].name == NULL)
+ return -ENOENT;
+ mddev->major_version = major;
+ mddev->minor_version = minor;
+ mddev->persistent = 1;
+ return len;
+}
+
+static struct md_sysfs_entry md_metadata =
+__ATTR(metadata_version, 0644, metadata_show, metadata_store);
+
+static ssize_t
+action_show(mddev_t *mddev, char *page)
+{
+ char *type = "idle";
+ if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+ test_bit(MD_RECOVERY_NEEDED, &mddev->recovery)) {
+ if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
+ if (!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
+ type = "resync";
+ else if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery))
+ type = "check";
+ else
+ type = "repair";
+ } else
+ type = "recover";
+ }
+ return sprintf(page, "%s\n", type);
+}
+
+static ssize_t
+action_store(mddev_t *mddev, const char *page, size_t len)
+{
+ if (!mddev->pers || !mddev->pers->sync_request)
+ return -EINVAL;
+
+ if (cmd_match(page, "idle")) {
+ if (mddev->sync_thread) {
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+ md_unregister_thread(mddev->sync_thread);
+ mddev->sync_thread = NULL;
+ mddev->recovery = 0;
+ }
+ } else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+ test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
+ return -EBUSY;
+ else if (cmd_match(page, "resync") || cmd_match(page, "recover"))
+ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ else {
+ if (cmd_match(page, "check"))
+ set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+ else if (cmd_match(page, "repair"))
+ return -EINVAL;
+ set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
+ set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+ }
+ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ md_wakeup_thread(mddev->thread);
+ return len;
+}
+
+static ssize_t
+mismatch_cnt_show(mddev_t *mddev, char *page)
+{
+ return sprintf(page, "%llu\n",
+ (unsigned long long) mddev->resync_mismatches);
+}
+
+static struct md_sysfs_entry
+md_scan_mode = __ATTR(sync_action, S_IRUGO|S_IWUSR, action_show, action_store);
+
+
+static struct md_sysfs_entry
+md_mismatches = __ATTR_RO(mismatch_cnt);
+
+static ssize_t
+sync_min_show(mddev_t *mddev, char *page)
+{
+ return sprintf(page, "%d (%s)\n", speed_min(mddev),
+ mddev->sync_speed_min ? "local": "system");
+}
+
+static ssize_t
+sync_min_store(mddev_t *mddev, const char *buf, size_t len)
+{
+ int min;
+ char *e;
+ if (strncmp(buf, "system", 6)==0) {
+ mddev->sync_speed_min = 0;
+ return len;
+ }
+ min = simple_strtoul(buf, &e, 10);
+ if (buf == e || (*e && *e != '\n') || min <= 0)
+ return -EINVAL;
+ mddev->sync_speed_min = min;
+ return len;
+}
+
+static struct md_sysfs_entry md_sync_min =
+__ATTR(sync_speed_min, S_IRUGO|S_IWUSR, sync_min_show, sync_min_store);
+
+static ssize_t
+sync_max_show(mddev_t *mddev, char *page)
+{
+ return sprintf(page, "%d (%s)\n", speed_max(mddev),
+ mddev->sync_speed_max ? "local": "system");
+}
+
+static ssize_t
+sync_max_store(mddev_t *mddev, const char *buf, size_t len)
+{
+ int max;
+ char *e;
+ if (strncmp(buf, "system", 6)==0) {
+ mddev->sync_speed_max = 0;
+ return len;
+ }
+ max = simple_strtoul(buf, &e, 10);
+ if (buf == e || (*e && *e != '\n') || max <= 0)
+ return -EINVAL;
+ mddev->sync_speed_max = max;
+ return len;
+}
+
+static struct md_sysfs_entry md_sync_max =
+__ATTR(sync_speed_max, S_IRUGO|S_IWUSR, sync_max_show, sync_max_store);
+
+
+static ssize_t
+sync_speed_show(mddev_t *mddev, char *page)
+{
+ unsigned long resync, dt, db;
+ resync = (mddev->curr_resync - atomic_read(&mddev->recovery_active));
+ dt = ((jiffies - mddev->resync_mark) / HZ);
+ if (!dt) dt++;
+ db = resync - (mddev->resync_mark_cnt);
+ return sprintf(page, "%ld\n", db/dt/2); /* K/sec */
+}
+
+static struct md_sysfs_entry
+md_sync_speed = __ATTR_RO(sync_speed);
+
+static ssize_t
+sync_completed_show(mddev_t *mddev, char *page)
+{
+ unsigned long max_blocks, resync;
+
+ if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
+ max_blocks = mddev->resync_max_sectors;
+ else
+ max_blocks = mddev->size << 1;
+
+ resync = (mddev->curr_resync - atomic_read(&mddev->recovery_active));
+ return sprintf(page, "%lu / %lu\n", resync, max_blocks);
+}
+
+static struct md_sysfs_entry
+md_sync_completed = __ATTR_RO(sync_completed);
+
+static struct attribute *md_default_attrs[] = {
+ &md_level.attr,
+ &md_raid_disks.attr,
+ &md_chunk_size.attr,
+ &md_size.attr,
+ &md_metadata.attr,
+ &md_new_device.attr,
+ NULL,
+};
+
+static struct attribute *md_redundancy_attrs[] = {
+ &md_scan_mode.attr,
+ &md_mismatches.attr,
+ &md_sync_min.attr,
+ &md_sync_max.attr,
+ &md_sync_speed.attr,
+ &md_sync_completed.attr,
+ NULL,
+};
+static struct attribute_group md_redundancy_group = {
+ .name = NULL,
+ .attrs = md_redundancy_attrs,
+};
+
+
+static ssize_t
+md_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
+{
+ struct md_sysfs_entry *entry = container_of(attr, struct md_sysfs_entry, attr);
+ mddev_t *mddev = container_of(kobj, struct mddev_s, kobj);
+ ssize_t rv;
+
+ if (!entry->show)
+ return -EIO;
+ mddev_lock(mddev);
+ rv = entry->show(mddev, page);
+ mddev_unlock(mddev);
+ return rv;
+}
+
+static ssize_t
+md_attr_store(struct kobject *kobj, struct attribute *attr,
+ const char *page, size_t length)
+{
+ struct md_sysfs_entry *entry = container_of(attr, struct md_sysfs_entry, attr);
+ mddev_t *mddev = container_of(kobj, struct mddev_s, kobj);
+ ssize_t rv;
+
+ if (!entry->store)
+ return -EIO;
+ mddev_lock(mddev);
+ rv = entry->store(mddev, page, length);
+ mddev_unlock(mddev);
+ return rv;
+}
+
+static void md_free(struct kobject *ko)
+{
+ mddev_t *mddev = container_of(ko, mddev_t, kobj);
+ kfree(mddev);
+}
+
+static struct sysfs_ops md_sysfs_ops = {
+ .show = md_attr_show,
+ .store = md_attr_store,
+};
+static struct kobj_type md_ktype = {
+ .release = md_free,
+ .sysfs_ops = &md_sysfs_ops,
+ .default_attrs = md_default_attrs,
+};
+
+int mdp_major = 0;
+
+static struct kobject *md_probe(dev_t dev, int *part, void *data)
+{
+ static DECLARE_MUTEX(disks_sem);
+ mddev_t *mddev = mddev_find(dev);
+ struct gendisk *disk;
+ int partitioned = (MAJOR(dev) != MD_MAJOR);
+ int shift = partitioned ? MdpMinorShift : 0;
+ int unit = MINOR(dev) >> shift;
+
+ if (!mddev)
+ return NULL;
+
+ down(&disks_sem);
if (mddev->gendisk) {
up(&disks_sem);
mddev_put(mddev);
}
disk->major = MAJOR(dev);
disk->first_minor = unit << shift;
- if (partitioned)
+ if (partitioned) {
sprintf(disk->disk_name, "md_d%d", unit);
- else
+ sprintf(disk->devfs_name, "md/d%d", unit);
+ } else {
sprintf(disk->disk_name, "md%d", unit);
+ sprintf(disk->devfs_name, "md/%d", unit);
+ }
disk->fops = &md_fops;
disk->private_data = mddev;
disk->queue = mddev->queue;
add_disk(disk);
mddev->gendisk = disk;
up(&disks_sem);
+ mddev->kobj.parent = &disk->kobj;
+ mddev->kobj.k_name = NULL;
+ snprintf(mddev->kobj.name, KOBJ_NAME_LEN, "%s", "md");
+ mddev->kobj.ktype = &md_ktype;
+ kobject_register(&mddev->kobj);
return NULL;
}
md_wakeup_thread(mddev->thread);
}
+static int start_dirty_degraded;
static int do_md_run(mddev_t * mddev)
{
- int pnum, err;
+ int err;
int chunk_size;
struct list_head *tmp;
mdk_rdev_t *rdev;
struct gendisk *disk;
+ struct mdk_personality *pers;
char b[BDEVNAME_SIZE];
- if (list_empty(&mddev->disks)) {
- MD_BUG();
+ if (list_empty(&mddev->disks))
+ /* cannot run an array with no devices.. */
return -EINVAL;
- }
if (mddev->pers)
return -EBUSY;
/*
* Analyze all RAID superblock(s)
*/
- if (!mddev->raid_disks && analyze_sbs(mddev)) {
- MD_BUG();
- return -EINVAL;
- }
+ if (!mddev->raid_disks)
+ analyze_sbs(mddev);
chunk_size = mddev->chunk_size;
- pnum = level_to_pers(mddev->level);
- if ((pnum != MULTIPATH) && (pnum != RAID1)) {
- if (!chunk_size) {
- /*
- * 'default chunksize' in the old md code used to
- * be PAGE_SIZE, baaad.
- * we abort here to be on the safe side. We don't
- * want to continue the bad practice.
- */
- printk(KERN_ERR
- "no chunksize specified, see 'man raidtab'\n");
- return -EINVAL;
- }
+ if (chunk_size) {
if (chunk_size > MAX_CHUNK_SIZE) {
printk(KERN_ERR "too big chunk_size: %d > %d\n",
chunk_size, MAX_CHUNK_SIZE);
* chunk-size has to be a power of 2 and multiples of PAGE_SIZE
*/
if ( (1 << ffz(~chunk_size)) != chunk_size) {
- MD_BUG();
+ printk(KERN_ERR "chunk_size of %d not valid\n", chunk_size);
return -EINVAL;
}
if (chunk_size < PAGE_SIZE) {
/* devices must have minimum size of one chunk */
ITERATE_RDEV(mddev,rdev,tmp) {
- if (rdev->faulty)
+ if (test_bit(Faulty, &rdev->flags))
continue;
if (rdev->size < chunk_size / 1024) {
printk(KERN_WARNING
}
}
- if (pnum >= MAX_PERSONALITY) {
- MD_BUG();
- return -EINVAL;
- }
-
#ifdef CONFIG_KMOD
- if (!pers[pnum])
- {
- request_module("md-personality-%d", pnum);
- }
+ if (mddev->level != LEVEL_NONE)
+ request_module("md-level-%d", mddev->level);
+ else if (mddev->clevel[0])
+ request_module("md-%s", mddev->clevel);
#endif
/*
* Also find largest hardsector size
*/
ITERATE_RDEV(mddev,rdev,tmp) {
- if (rdev->faulty)
+ if (test_bit(Faulty, &rdev->flags))
continue;
sync_blockdev(rdev->bdev);
invalidate_bdev(rdev->bdev, 0);
return -ENOMEM;
spin_lock(&pers_lock);
- if (!pers[pnum] || !try_module_get(pers[pnum]->owner)) {
+ pers = find_pers(mddev->level, mddev->clevel);
+ if (!pers || !try_module_get(pers->owner)) {
spin_unlock(&pers_lock);
- printk(KERN_WARNING "md: personality %d is not loaded!\n",
- pnum);
+ if (mddev->level != LEVEL_NONE)
+ printk(KERN_WARNING "md: personality for level %d is not loaded!\n",
+ mddev->level);
+ else
+ printk(KERN_WARNING "md: personality for level %s is not loaded!\n",
+ mddev->clevel);
return -EINVAL;
}
-
- mddev->pers = pers[pnum];
+ mddev->pers = pers;
spin_unlock(&pers_lock);
+ mddev->level = pers->level;
+ strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
+
+ mddev->recovery = 0;
+ mddev->resync_max_sectors = mddev->size << 1; /* may be over-ridden by personality */
+ mddev->barriers_work = 1;
+ mddev->ok_start_degraded = start_dirty_degraded;
+
+ if (start_readonly)
+ mddev->ro = 2; /* read-only, but switch on first write */
err = mddev->pers->run(mddev);
+ if (!err && mddev->pers->sync_request) {
+ err = bitmap_create(mddev);
+ if (err) {
+ printk(KERN_ERR "%s: failed to create bitmap (%d)\n",
+ mdname(mddev), err);
+ mddev->pers->stop(mddev);
+ }
+ }
if (err) {
printk(KERN_ERR "md: pers->run() failed ...\n");
module_put(mddev->pers->owner);
mddev->pers = NULL;
- return -EINVAL;
+ 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 */
+ mddev->ro = 0;
+
atomic_set(&mddev->writes_pending,0);
mddev->safemode = 0;
mddev->safemode_timer.function = md_safemode_timeout;
mddev->safemode_timer.data = (unsigned long) mddev;
mddev->safemode_delay = (20 * HZ)/1000 +1; /* 20 msec delay */
mddev->in_sync = 1;
+
+ ITERATE_RDEV(mddev,rdev,tmp)
+ if (rdev->raid_disk >= 0) {
+ char nm[20];
+ sprintf(nm, "rd%d", rdev->raid_disk);
+ sysfs_create_link(&mddev->kobj, &rdev->kobj, nm);
+ }
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ md_wakeup_thread(mddev->thread);
if (mddev->sb_dirty)
md_update_sb(mddev);
mddev->queue->make_request_fn = mddev->pers->make_request;
mddev->changed = 1;
+ md_new_event(mddev);
return 0;
}
if (ro) {
err = -ENXIO;
- if (mddev->ro)
+ if (mddev->ro==1)
goto out;
mddev->ro = 1;
} else {
+ bitmap_flush(mddev);
+ md_super_wait(mddev);
if (mddev->ro)
set_disk_ro(disk, 0);
blk_queue_make_request(mddev->queue, md_fail_request);
mddev->pers->stop(mddev);
+ if (mddev->pers->sync_request)
+ sysfs_remove_group(&mddev->kobj, &md_redundancy_group);
+
module_put(mddev->pers->owner);
mddev->pers = NULL;
if (mddev->ro)
if (ro)
set_disk_ro(disk, 1);
}
+
/*
* Free resources if final stop
*/
if (!ro) {
+ mdk_rdev_t *rdev;
+ struct list_head *tmp;
struct gendisk *disk;
printk(KERN_INFO "md: %s stopped.\n", mdname(mddev));
+ bitmap_destroy(mddev);
+ if (mddev->bitmap_file) {
+ atomic_set(&mddev->bitmap_file->f_dentry->d_inode->i_writecount, 1);
+ fput(mddev->bitmap_file);
+ mddev->bitmap_file = NULL;
+ }
+ mddev->bitmap_offset = 0;
+
+ ITERATE_RDEV(mddev,rdev,tmp)
+ if (rdev->raid_disk >= 0) {
+ char nm[20];
+ sprintf(nm, "rd%d", rdev->raid_disk);
+ sysfs_remove_link(&mddev->kobj, nm);
+ }
+
export_array(mddev);
mddev->array_size = 0;
printk(KERN_INFO "md: %s switched to read-only mode.\n",
mdname(mddev));
err = 0;
+ md_new_event(mddev);
out:
return err;
}
struct list_head *tmp;
int err;
- if (list_empty(&mddev->disks)) {
- MD_BUG();
+ if (list_empty(&mddev->disks))
return;
- }
printk(KERN_INFO "md: running: ");
err = do_md_run (mddev);
if (err) {
- printk(KERN_WARNING "md :do_md_run() returned %d\n", err);
+ printk(KERN_WARNING "md: do_md_run() returned %d\n", err);
do_md_stop (mddev, 0);
}
}
mdk_rdev_t *start_rdev = NULL, *rdev;
start_rdev = md_import_device(startdev, 0, 0);
- if (IS_ERR(start_rdev)) {
- printk(KERN_WARNING "md: could not import %s!\n",
- __bdevname(startdev, b));
+ if (IS_ERR(start_rdev))
return err;
- }
+
/* NOTE: this can only work for 0.90.0 superblocks */
sb = (mdp_super_t*)page_address(start_rdev->sb_page);
return err;
}
- if (start_rdev->faulty) {
+ if (test_bit(Faulty, &start_rdev->flags)) {
printk(KERN_WARNING
"md: can not autostart based on faulty %s!\n",
bdevname(start_rdev->bdev,b));
if (MAJOR(dev) != desc->major || MINOR(dev) != desc->minor)
continue;
rdev = md_import_device(dev, 0, 0);
- if (IS_ERR(rdev)) {
- printk(KERN_WARNING "md: could not import %s,"
- " trying to run array nevertheless.\n",
- __bdevname(dev, b));
+ if (IS_ERR(rdev))
continue;
- }
+
list_add(&rdev->same_set, &pending_raid_disks);
}
}
-static int get_version(void * arg)
+static int get_version(void __user * arg)
{
mdu_version_t ver;
return 0;
}
-static int get_array_info(mddev_t * mddev, void * arg)
+static int get_array_info(mddev_t * mddev, void __user * arg)
{
mdu_array_info_t info;
int nr,working,active,failed,spare;
nr=working=active=failed=spare=0;
ITERATE_RDEV(mddev,rdev,tmp) {
nr++;
- if (rdev->faulty)
+ if (test_bit(Faulty, &rdev->flags))
failed++;
else {
working++;
- if (rdev->in_sync)
+ if (test_bit(In_sync, &rdev->flags))
active++;
else
spare++;
info.major_version = mddev->major_version;
info.minor_version = mddev->minor_version;
- info.patch_version = 1;
+ info.patch_version = MD_PATCHLEVEL_VERSION;
info.ctime = mddev->ctime;
info.level = mddev->level;
info.size = mddev->size;
+ if (info.size != mddev->size) /* overflow */
+ info.size = -1;
info.nr_disks = nr;
info.raid_disks = mddev->raid_disks;
info.md_minor = mddev->md_minor;
info.state = 0;
if (mddev->in_sync)
info.state = (1<<MD_SB_CLEAN);
+ if (mddev->bitmap && mddev->bitmap_offset)
+ info.state = (1<<MD_SB_BITMAP_PRESENT);
info.active_disks = active;
info.working_disks = working;
info.failed_disks = failed;
return 0;
}
-static int get_disk_info(mddev_t * mddev, void * arg)
+static int get_bitmap_file(mddev_t * mddev, void __user * arg)
+{
+ mdu_bitmap_file_t *file = NULL; /* too big for stack allocation */
+ char *ptr, *buf = NULL;
+ int err = -ENOMEM;
+
+ file = kmalloc(sizeof(*file), GFP_KERNEL);
+ if (!file)
+ goto out;
+
+ /* bitmap disabled, zero the first byte and copy out */
+ if (!mddev->bitmap || !mddev->bitmap->file) {
+ file->pathname[0] = '\0';
+ goto copy_out;
+ }
+
+ buf = kmalloc(sizeof(file->pathname), GFP_KERNEL);
+ if (!buf)
+ goto out;
+
+ ptr = file_path(mddev->bitmap->file, buf, sizeof(file->pathname));
+ if (!ptr)
+ goto out;
+
+ strcpy(file->pathname, ptr);
+
+copy_out:
+ err = 0;
+ if (copy_to_user(arg, file, sizeof(*file)))
+ err = -EFAULT;
+out:
+ kfree(buf);
+ kfree(file);
+ return err;
+}
+
+static int get_disk_info(mddev_t * mddev, void __user * arg)
{
mdu_disk_info_t info;
unsigned int nr;
info.minor = MINOR(rdev->bdev->bd_dev);
info.raid_disk = rdev->raid_disk;
info.state = 0;
- if (rdev->faulty)
+ if (test_bit(Faulty, &rdev->flags))
info.state |= (1<<MD_DISK_FAULTY);
- else if (rdev->in_sync) {
+ else if (test_bit(In_sync, &rdev->flags)) {
info.state |= (1<<MD_DISK_ACTIVE);
info.state |= (1<<MD_DISK_SYNC);
}
+ if (test_bit(WriteMostly, &rdev->flags))
+ info.state |= (1<<MD_DISK_WRITEMOSTLY);
} else {
info.major = info.minor = 0;
info.raid_disk = -1;
mdname(mddev));
return -EINVAL;
}
- rdev = md_import_device(dev, mddev->major_version,
- mddev->minor_version);
+ if (mddev->persistent)
+ rdev = md_import_device(dev, mddev->major_version,
+ mddev->minor_version);
+ else
+ rdev = md_import_device(dev, -1, -1);
if (IS_ERR(rdev)) {
printk(KERN_WARNING
"md: md_import_device returned %ld\n",
PTR_ERR(rdev));
return PTR_ERR(rdev);
}
- rdev->in_sync = 0; /* just to be sure */
+ /* set save_raid_disk if appropriate */
+ if (!mddev->persistent) {
+ if (info->state & (1<<MD_DISK_SYNC) &&
+ info->raid_disk < mddev->raid_disks)
+ rdev->raid_disk = info->raid_disk;
+ else
+ rdev->raid_disk = -1;
+ } else
+ super_types[mddev->major_version].
+ validate_super(mddev, rdev);
+ rdev->saved_raid_disk = rdev->raid_disk;
+
+ clear_bit(In_sync, &rdev->flags); /* just to be sure */
+ if (info->state & (1<<MD_DISK_WRITEMOSTLY))
+ set_bit(WriteMostly, &rdev->flags);
+
rdev->raid_disk = -1;
err = bind_rdev_to_array(rdev, mddev);
if (err)
export_rdev(rdev);
- if (mddev->thread)
- md_wakeup_thread(mddev->thread);
+
+ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ md_wakeup_thread(mddev->thread);
return err;
}
else
rdev->raid_disk = -1;
- rdev->faulty = 0;
+ rdev->flags = 0;
+
if (rdev->raid_disk < mddev->raid_disks)
- rdev->in_sync = (info->state & (1<<MD_DISK_SYNC));
- else
- rdev->in_sync = 0;
+ if (info->state & (1<<MD_DISK_SYNC))
+ set_bit(In_sync, &rdev->flags);
- err = bind_rdev_to_array(rdev, mddev);
- if (err) {
- export_rdev(rdev);
- return err;
- }
+ if (info->state & (1<<MD_DISK_WRITEMOSTLY))
+ set_bit(WriteMostly, &rdev->flags);
if (!mddev->persistent) {
printk(KERN_INFO "md: nonpersistent superblock ...\n");
rdev->sb_offset = calc_dev_sboffset(rdev->bdev);
rdev->size = calc_dev_size(rdev, mddev->chunk_size);
- if (!mddev->size || (mddev->size > rdev->size))
- mddev->size = rdev->size;
- }
-
- return 0;
-}
-
-static int hot_generate_error(mddev_t * mddev, dev_t dev)
-{
- char b[BDEVNAME_SIZE];
- struct request_queue *q;
- mdk_rdev_t *rdev;
-
- if (!mddev->pers)
- return -ENODEV;
-
- printk(KERN_INFO "md: trying to generate %s error in %s ... \n",
- __bdevname(dev, b), mdname(mddev));
-
- rdev = find_rdev(mddev, dev);
- if (!rdev) {
- /* MD_BUG(); */ /* like hell - it's not a driver bug */
- return -ENXIO;
- }
-
- if (rdev->desc_nr == -1) {
- MD_BUG();
- return -EINVAL;
- }
- if (!rdev->in_sync)
- return -ENODEV;
-
- q = bdev_get_queue(rdev->bdev);
- if (!q) {
- MD_BUG();
- return -ENODEV;
+ err = bind_rdev_to_array(rdev, mddev);
+ if (err) {
+ export_rdev(rdev);
+ return err;
+ }
}
- printk(KERN_INFO "md: okay, generating error!\n");
-// q->oneshot_error = 1; // disabled for now
return 0;
}
if (!mddev->pers)
return -ENODEV;
- printk(KERN_INFO "md: trying to remove %s from %s ... \n",
- __bdevname(dev, b), mdname(mddev));
-
rdev = find_rdev(mddev, dev);
if (!rdev)
return -ENXIO;
kick_rdev_from_array(rdev);
md_update_sb(mddev);
+ md_new_event(mddev);
return 0;
busy:
if (!mddev->pers)
return -ENODEV;
- printk(KERN_INFO "md: trying to hot-add %s to %s ... \n",
- __bdevname(dev, b), mdname(mddev));
-
if (mddev->major_version != 0) {
printk(KERN_WARNING "%s: HOT_ADD may only be used with"
" version-0 superblocks.\n",
return -EINVAL;
}
- rdev->sb_offset = calc_dev_sboffset(rdev->bdev);
+ if (mddev->persistent)
+ rdev->sb_offset = calc_dev_sboffset(rdev->bdev);
+ else
+ rdev->sb_offset =
+ rdev->bdev->bd_inode->i_size >> BLOCK_SIZE_BITS;
+
size = calc_dev_size(rdev, mddev->chunk_size);
rdev->size = size;
- if (size < mddev->size) {
- printk(KERN_WARNING
- "%s: disk size %llu blocks < array size %llu\n",
- mdname(mddev), (unsigned long long)size,
- (unsigned long long)mddev->size);
- err = -ENOSPC;
- goto abort_export;
- }
-
- if (rdev->faulty) {
+ if (test_bit(Faulty, &rdev->flags)) {
printk(KERN_WARNING
"md: can not hot-add faulty %s disk to %s!\n",
bdevname(rdev->bdev,b), mdname(mddev));
err = -EINVAL;
goto abort_export;
}
- rdev->in_sync = 0;
+ clear_bit(In_sync, &rdev->flags);
rdev->desc_nr = -1;
- bind_rdev_to_array(rdev, mddev);
+ err = bind_rdev_to_array(rdev, mddev);
+ if (err)
+ goto abort_export;
/*
* The rest should better be atomic, we can have disk failures
*/
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
+ md_new_event(mddev);
+ return 0;
+
+abort_unbind_export:
+ unbind_rdev_from_array(rdev);
+
+abort_export:
+ export_rdev(rdev);
+ return err;
+}
+
+/* similar to deny_write_access, but accounts for our holding a reference
+ * to the file ourselves */
+static int deny_bitmap_write_access(struct file * file)
+{
+ struct inode *inode = file->f_mapping->host;
+
+ spin_lock(&inode->i_lock);
+ if (atomic_read(&inode->i_writecount) > 1) {
+ spin_unlock(&inode->i_lock);
+ return -ETXTBSY;
+ }
+ atomic_set(&inode->i_writecount, -1);
+ spin_unlock(&inode->i_lock);
return 0;
+}
+
+static int set_bitmap_file(mddev_t *mddev, int fd)
+{
+ int err;
+
+ if (mddev->pers) {
+ if (!mddev->pers->quiesce)
+ return -EBUSY;
+ if (mddev->recovery || mddev->sync_thread)
+ return -EBUSY;
+ /* we should be able to change the bitmap.. */
+ }
+
+
+ if (fd >= 0) {
+ if (mddev->bitmap)
+ return -EEXIST; /* cannot add when bitmap is present */
+ mddev->bitmap_file = fget(fd);
+
+ if (mddev->bitmap_file == NULL) {
+ printk(KERN_ERR "%s: error: failed to get bitmap file\n",
+ mdname(mddev));
+ return -EBADF;
+ }
-abort_unbind_export:
- unbind_rdev_from_array(rdev);
+ err = deny_bitmap_write_access(mddev->bitmap_file);
+ if (err) {
+ printk(KERN_ERR "%s: error: bitmap file is already in use\n",
+ mdname(mddev));
+ fput(mddev->bitmap_file);
+ mddev->bitmap_file = NULL;
+ return err;
+ }
+ mddev->bitmap_offset = 0; /* file overrides offset */
+ } else if (mddev->bitmap == NULL)
+ return -ENOENT; /* cannot remove what isn't there */
+ err = 0;
+ if (mddev->pers) {
+ mddev->pers->quiesce(mddev, 1);
+ if (fd >= 0)
+ err = bitmap_create(mddev);
+ if (fd < 0 || err)
+ bitmap_destroy(mddev);
+ mddev->pers->quiesce(mddev, 0);
+ } else if (fd < 0) {
+ if (mddev->bitmap_file)
+ fput(mddev->bitmap_file);
+ mddev->bitmap_file = NULL;
+ }
-abort_export:
- export_rdev(rdev);
return err;
}
mddev->ctime = get_seconds();
mddev->level = info->level;
+ mddev->clevel[0] = 0;
mddev->size = info->size;
mddev->raid_disks = info->raid_disks;
/* don't set md_minor, it is determined by which /dev/md* was
mddev->sb_dirty = 1;
+ mddev->default_bitmap_offset = MD_SB_BYTES >> 9;
+ mddev->bitmap_offset = 0;
+
/*
* Generate a 128 bit UUID
*/
return 0;
}
+static int update_size(mddev_t *mddev, unsigned long size)
+{
+ mdk_rdev_t * rdev;
+ int rv;
+ struct list_head *tmp;
+ int fit = (size == 0);
+
+ if (mddev->pers->resize == NULL)
+ return -EINVAL;
+ /* The "size" is the amount of each device that is used.
+ * This can only make sense for arrays with redundancy.
+ * linear and raid0 always use whatever space is available
+ * We can only consider changing the size if no resync
+ * or reconstruction is happening, and if the new size
+ * is acceptable. It must fit before the sb_offset or,
+ * if that is <data_offset, it must fit before the
+ * size of each device.
+ * If size is zero, we find the largest size that fits.
+ */
+ if (mddev->sync_thread)
+ return -EBUSY;
+ ITERATE_RDEV(mddev,rdev,tmp) {
+ sector_t avail;
+ if (rdev->sb_offset > rdev->data_offset)
+ avail = (rdev->sb_offset*2) - rdev->data_offset;
+ else
+ avail = get_capacity(rdev->bdev->bd_disk)
+ - rdev->data_offset;
+ if (fit && (size == 0 || size > avail/2))
+ size = avail/2;
+ if (avail < ((sector_t)size << 1))
+ return -ENOSPC;
+ }
+ rv = mddev->pers->resize(mddev, (sector_t)size *2);
+ 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_size << 10);
+ mutex_unlock(&bdev->bd_inode->i_mutex);
+ bdput(bdev);
+ }
+ }
+ return rv;
+}
+
+static int update_raid_disks(mddev_t *mddev, int raid_disks)
+{
+ int rv;
+ /* change the number of raid disks */
+ if (mddev->pers->reshape == NULL)
+ return -EINVAL;
+ if (raid_disks <= 0 ||
+ raid_disks >= mddev->max_disks)
+ return -EINVAL;
+ if (mddev->sync_thread)
+ return -EBUSY;
+ rv = mddev->pers->reshape(mddev, raid_disks);
+ return rv;
+}
+
+
+/*
+ * update_array_info is used to change the configuration of an
+ * on-line array.
+ * The version, ctime,level,size,raid_disks,not_persistent, layout,chunk_size
+ * fields in the info are checked against the array.
+ * Any differences that cannot be handled will cause an error.
+ * Normally, only one change can be managed at a time.
+ */
+static int update_array_info(mddev_t *mddev, mdu_array_info_t *info)
+{
+ int rv = 0;
+ int cnt = 0;
+ int state = 0;
+
+ /* calculate expected state,ignoring low bits */
+ if (mddev->bitmap && mddev->bitmap_offset)
+ state |= (1 << MD_SB_BITMAP_PRESENT);
+
+ if (mddev->major_version != info->major_version ||
+ mddev->minor_version != info->minor_version ||
+/* mddev->patch_version != info->patch_version || */
+ mddev->ctime != info->ctime ||
+ mddev->level != info->level ||
+/* mddev->layout != info->layout || */
+ !mddev->persistent != info->not_persistent||
+ mddev->chunk_size != info->chunk_size ||
+ /* ignore bottom 8 bits of state, and allow SB_BITMAP_PRESENT to change */
+ ((state^info->state) & 0xfffffe00)
+ )
+ return -EINVAL;
+ /* Check there is only one change */
+ if (info->size >= 0 && mddev->size != info->size) cnt++;
+ if (mddev->raid_disks != info->raid_disks) cnt++;
+ if (mddev->layout != info->layout) cnt++;
+ if ((state ^ info->state) & (1<<MD_SB_BITMAP_PRESENT)) cnt++;
+ if (cnt == 0) return 0;
+ if (cnt > 1) return -EINVAL;
+
+ if (mddev->layout != info->layout) {
+ /* Change layout
+ * we don't need to do anything at the md level, the
+ * personality will take care of it all.
+ */
+ if (mddev->pers->reconfig == NULL)
+ return -EINVAL;
+ else
+ return mddev->pers->reconfig(mddev, info->layout, -1);
+ }
+ if (info->size >= 0 && mddev->size != info->size)
+ rv = update_size(mddev, info->size);
+
+ if (mddev->raid_disks != info->raid_disks)
+ rv = update_raid_disks(mddev, info->raid_disks);
+
+ if ((state ^ info->state) & (1<<MD_SB_BITMAP_PRESENT)) {
+ if (mddev->pers->quiesce == NULL)
+ return -EINVAL;
+ if (mddev->recovery || mddev->sync_thread)
+ return -EBUSY;
+ if (info->state & (1<<MD_SB_BITMAP_PRESENT)) {
+ /* add the bitmap */
+ if (mddev->bitmap)
+ return -EEXIST;
+ if (mddev->default_bitmap_offset == 0)
+ return -EINVAL;
+ mddev->bitmap_offset = mddev->default_bitmap_offset;
+ mddev->pers->quiesce(mddev, 1);
+ rv = bitmap_create(mddev);
+ if (rv)
+ bitmap_destroy(mddev);
+ mddev->pers->quiesce(mddev, 0);
+ } else {
+ /* remove the bitmap */
+ if (!mddev->bitmap)
+ return -ENOENT;
+ if (mddev->bitmap->file)
+ return -EINVAL;
+ mddev->pers->quiesce(mddev, 1);
+ bitmap_destroy(mddev);
+ mddev->pers->quiesce(mddev, 0);
+ mddev->bitmap_offset = 0;
+ }
+ }
+ md_update_sb(mddev);
+ return rv;
+}
+
static int set_disk_faulty(mddev_t *mddev, dev_t dev)
{
mdk_rdev_t *rdev;
+ if (mddev->pers == NULL)
+ return -ENODEV;
+
rdev = find_rdev(mddev, dev);
if (!rdev)
return -ENODEV;
return 0;
}
+static int md_getgeo(struct block_device *bdev, struct hd_geometry *geo)
+{
+ mddev_t *mddev = bdev->bd_disk->private_data;
+
+ geo->heads = 2;
+ geo->sectors = 4;
+ geo->cylinders = get_capacity(mddev->gendisk) / 8;
+ return 0;
+}
+
static int md_ioctl(struct inode *inode, struct file *file,
unsigned int cmd, unsigned long arg)
{
- char b[BDEVNAME_SIZE];
int err = 0;
- struct hd_geometry *loc = (struct hd_geometry *) arg;
+ void __user *argp = (void __user *)arg;
mddev_t *mddev = NULL;
if (!capable(CAP_SYS_ADMIN))
switch (cmd)
{
case RAID_VERSION:
- err = get_version((void *)arg);
+ err = get_version(argp);
goto done;
case PRINT_RAID_DEBUG:
if (cnt > 0 ) {
printk(KERN_WARNING
"md: %s(pid %d) used deprecated START_ARRAY ioctl. "
- "This will not be supported beyond 2.6\n",
+ "START_ARRAY is removed in kernel 2.6.19 and above.\n",
current->comm, current->pid);
cnt--;
}
err = autostart_array(new_decode_dev(arg));
if (err) {
- printk(KERN_WARNING "md: autostart %s failed!\n",
- __bdevname(arg, b));
+ printk(KERN_WARNING "md: autostart failed!\n");
goto abort;
}
goto done;
switch (cmd)
{
case SET_ARRAY_INFO:
-
- if (!list_empty(&mddev->disks)) {
- printk(KERN_WARNING
- "md: array %s already has disks!\n",
- mdname(mddev));
- err = -EBUSY;
- goto abort_unlock;
- }
- if (mddev->raid_disks) {
- printk(KERN_WARNING
- "md: array %s already initialised!\n",
- mdname(mddev));
- err = -EBUSY;
- goto abort_unlock;
- }
{
mdu_array_info_t info;
if (!arg)
memset(&info, 0, sizeof(info));
- else if (copy_from_user(&info, (void*)arg, sizeof(info))) {
+ else if (copy_from_user(&info, argp, sizeof(info))) {
err = -EFAULT;
goto abort_unlock;
}
+ if (mddev->pers) {
+ err = update_array_info(mddev, &info);
+ if (err) {
+ printk(KERN_WARNING "md: couldn't update"
+ " array info. %d\n", err);
+ goto abort_unlock;
+ }
+ goto done_unlock;
+ }
+ if (!list_empty(&mddev->disks)) {
+ printk(KERN_WARNING
+ "md: array %s already has disks!\n",
+ mdname(mddev));
+ err = -EBUSY;
+ goto abort_unlock;
+ }
+ if (mddev->raid_disks) {
+ printk(KERN_WARNING
+ "md: array %s already initialised!\n",
+ mdname(mddev));
+ err = -EBUSY;
+ goto abort_unlock;
+ }
err = set_array_info(mddev, &info);
if (err) {
printk(KERN_WARNING "md: couldn't set"
- " array info. %d\n", err);
+ " array info. %d\n", err);
goto abort_unlock;
}
}
/*
* Commands querying/configuring an existing array:
*/
- /* if we are initialised yet, only ADD_NEW_DISK or STOP_ARRAY is allowed */
- if (!mddev->raid_disks && cmd != ADD_NEW_DISK && cmd != STOP_ARRAY && cmd != RUN_ARRAY) {
+ /* if we are not initialised yet, only ADD_NEW_DISK, STOP_ARRAY,
+ * RUN_ARRAY, and SET_BITMAP_FILE are allowed */
+ if (!mddev->raid_disks && cmd != ADD_NEW_DISK && cmd != STOP_ARRAY
+ && cmd != RUN_ARRAY && cmd != SET_BITMAP_FILE) {
err = -ENODEV;
goto abort_unlock;
}
switch (cmd)
{
case GET_ARRAY_INFO:
- err = get_array_info(mddev, (void *)arg);
+ err = get_array_info(mddev, argp);
+ goto done_unlock;
+
+ case GET_BITMAP_FILE:
+ err = get_bitmap_file(mddev, argp);
goto done_unlock;
case GET_DISK_INFO:
- err = get_disk_info(mddev, (void *)arg);
+ err = get_disk_info(mddev, argp);
goto done_unlock;
case RESTART_ARRAY_RW:
* 4 sectors (with a BIG number of cylinders...). This drives
* dosfs just mad... ;-)
*/
- case HDIO_GETGEO:
- if (!loc) {
- err = -EINVAL;
- goto abort_unlock;
- }
- err = put_user (2, (char *) &loc->heads);
- if (err)
- goto abort_unlock;
- err = put_user (4, (char *) &loc->sectors);
- if (err)
- goto abort_unlock;
- err = put_user(get_capacity(mddev->gendisk)/8,
- (short *) &loc->cylinders);
- if (err)
- goto abort_unlock;
- err = put_user (get_start_sect(inode->i_bdev),
- (long *) &loc->start);
- goto done_unlock;
}
/*
* The remaining ioctls are changing the state of the
- * superblock, so we do not allow read-only arrays
- * here:
+ * superblock, so we do not allow them on read-only arrays.
+ * However non-MD ioctls (e.g. get-size) will still come through
+ * here and hit the 'default' below, so only disallow
+ * 'md' ioctls, and switch to rw mode if started auto-readonly.
*/
- if (mddev->ro) {
- err = -EROFS;
- goto abort_unlock;
+ if (_IOC_TYPE(cmd) == MD_MAJOR &&
+ mddev->ro && mddev->pers) {
+ if (mddev->ro == 2) {
+ mddev->ro = 0;
+ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ md_wakeup_thread(mddev->thread);
+
+ } else {
+ err = -EROFS;
+ goto abort_unlock;
+ }
}
switch (cmd)
case ADD_NEW_DISK:
{
mdu_disk_info_t info;
- if (copy_from_user(&info, (void*)arg, sizeof(info)))
+ if (copy_from_user(&info, argp, sizeof(info)))
err = -EFAULT;
else
err = add_new_disk(mddev, &info);
goto done_unlock;
}
- case HOT_GENERATE_ERROR:
- err = hot_generate_error(mddev, new_decode_dev(arg));
- goto done_unlock;
+
case HOT_REMOVE_DISK:
err = hot_remove_disk(mddev, new_decode_dev(arg));
goto done_unlock;
err = do_md_run (mddev);
goto done_unlock;
+ case SET_BITMAP_FILE:
+ err = set_bitmap_file(mddev, (int)arg);
+ goto done_unlock;
+
default:
if (_IOC_TYPE(cmd) == MD_MAJOR)
printk(KERN_WARNING "md: %s(pid %d) used"
.open = md_open,
.release = md_release,
.ioctl = md_ioctl,
+ .getgeo = md_getgeo,
.media_changed = md_media_changed,
.revalidate_disk= md_revalidate,
};
-int md_thread(void * arg)
+static int md_thread(void * arg)
{
mdk_thread_t *thread = arg;
- lock_kernel();
-
- /*
- * Detach thread
- */
-
- daemonize(thread->name, mdname(thread->mddev));
-
- current->exit_signal = SIGCHLD;
- allow_signal(SIGKILL);
- thread->tsk = current;
-
/*
* md_thread is a 'system-thread', it's priority should be very
* high. We avoid resource deadlocks individually in each
* bdflush, otherwise bdflush will deadlock if there are too
* many dirty RAID5 blocks.
*/
- unlock_kernel();
- complete(thread->event);
- while (thread->run) {
- void (*run)(mddev_t *);
+ allow_signal(SIGKILL);
+ while (!kthread_should_stop()) {
+
+ /* We need to wait INTERRUPTIBLE so that
+ * we don't add to the load-average.
+ * That means we need to be sure no signals are
+ * pending
+ */
+ if (signal_pending(current))
+ flush_signals(current);
- wait_event_interruptible(thread->wqueue,
- test_bit(THREAD_WAKEUP, &thread->flags));
- if (current->flags & PF_FREEZE)
- refrigerator(PF_FREEZE);
+ wait_event_interruptible_timeout
+ (thread->wqueue,
+ test_bit(THREAD_WAKEUP, &thread->flags)
+ || kthread_should_stop(),
+ thread->timeout);
+ try_to_freeze();
clear_bit(THREAD_WAKEUP, &thread->flags);
- run = thread->run;
- if (run)
- run(thread->mddev);
-
- if (signal_pending(current))
- flush_signals(current);
+ thread->run(thread->mddev);
}
- complete(thread->event);
+
return 0;
}
const char *name)
{
mdk_thread_t *thread;
- int ret;
- struct completion event;
- thread = (mdk_thread_t *) kmalloc
- (sizeof(mdk_thread_t), GFP_KERNEL);
+ thread = kzalloc(sizeof(mdk_thread_t), GFP_KERNEL);
if (!thread)
return NULL;
- memset(thread, 0, sizeof(mdk_thread_t));
init_waitqueue_head(&thread->wqueue);
- init_completion(&event);
- thread->event = &event;
thread->run = run;
thread->mddev = mddev;
- thread->name = name;
- ret = kernel_thread(md_thread, thread, 0);
- if (ret < 0) {
+ thread->timeout = MAX_SCHEDULE_TIMEOUT;
+ thread->tsk = kthread_run(md_thread, thread, name, mdname(thread->mddev));
+ if (IS_ERR(thread->tsk)) {
kfree(thread);
return NULL;
}
- wait_for_completion(&event);
return thread;
}
-void md_interrupt_thread(mdk_thread_t *thread)
-{
- if (!thread->tsk) {
- MD_BUG();
- return;
- }
- dprintk("interrupting MD-thread pid %d\n", thread->tsk->pid);
- send_sig(SIGKILL, thread->tsk, 1);
-}
-
void md_unregister_thread(mdk_thread_t *thread)
{
- struct completion event;
-
- init_completion(&event);
+ dprintk("interrupting MD-thread pid %d\n", thread->tsk->pid);
- thread->event = &event;
- thread->run = NULL;
- thread->name = NULL;
- md_interrupt_thread(thread);
- wait_for_completion(&event);
+ kthread_stop(thread->tsk);
kfree(thread);
}
return;
}
- if (!rdev || rdev->faulty)
+ if (!rdev || test_bit(Faulty, &rdev->flags))
return;
-
+/*
dprintk("md_error dev:%s, rdev:(%d:%d), (caller: %p,%p,%p,%p).\n",
mdname(mddev),
MAJOR(rdev->bdev->bd_dev), MINOR(rdev->bdev->bd_dev),
__builtin_return_address(0),__builtin_return_address(1),
__builtin_return_address(2),__builtin_return_address(3));
-
+*/
if (!mddev->pers->error_handler)
return;
mddev->pers->error_handler(mddev,rdev);
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
+ md_new_event(mddev);
}
/* seq_file implementation /proc/mdstat */
unsigned long max_blocks, resync, res, dt, db, rt;
resync = (mddev->curr_resync - atomic_read(&mddev->recovery_active))/2;
- max_blocks = mddev->size;
+
+ if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
+ max_blocks = mddev->resync_max_sectors >> 1;
+ else
+ max_blocks = mddev->size;
/*
* Should not happen.
mddev_put(mddev);
}
+struct mdstat_info {
+ int event;
+};
+
static int md_seq_show(struct seq_file *seq, void *v)
{
mddev_t *mddev = v;
sector_t size;
struct list_head *tmp2;
mdk_rdev_t *rdev;
- int i;
+ struct mdstat_info *mi = seq->private;
+ struct bitmap *bitmap;
if (v == (void*)1) {
+ struct mdk_personality *pers;
seq_printf(seq, "Personalities : ");
spin_lock(&pers_lock);
- for (i = 0; i < MAX_PERSONALITY; i++)
- if (pers[i])
- seq_printf(seq, "[%s] ", pers[i]->name);
+ list_for_each_entry(pers, &pers_list, list)
+ seq_printf(seq, "[%s] ", pers->name);
spin_unlock(&pers_lock);
seq_printf(seq, "\n");
+ mi->event = atomic_read(&md_event_count);
return 0;
}
if (v == (void*)2) {
seq_printf(seq, "%s : %sactive", mdname(mddev),
mddev->pers ? "" : "in");
if (mddev->pers) {
- if (mddev->ro)
+ if (mddev->ro==1)
seq_printf(seq, " (read-only)");
+ if (mddev->ro==2)
+ seq_printf(seq, "(auto-read-only)");
seq_printf(seq, " %s", mddev->pers->name);
}
char b[BDEVNAME_SIZE];
seq_printf(seq, " %s[%d]",
bdevname(rdev->bdev,b), rdev->desc_nr);
- if (rdev->faulty) {
+ if (test_bit(WriteMostly, &rdev->flags))
+ seq_printf(seq, "(W)");
+ if (test_bit(Faulty, &rdev->flags)) {
seq_printf(seq, "(F)");
continue;
- }
+ } else if (rdev->raid_disk < 0)
+ seq_printf(seq, "(S)"); /* spare */
size += rdev->size;
}
seq_printf(seq, "\n %llu blocks",
(unsigned long long)size);
}
+ if (mddev->persistent) {
+ if (mddev->major_version != 0 ||
+ mddev->minor_version != 90) {
+ seq_printf(seq," super %d.%d",
+ mddev->major_version,
+ mddev->minor_version);
+ }
+ } else
+ seq_printf(seq, " super non-persistent");
if (mddev->pers) {
mddev->pers->status (seq, mddev);
seq_printf(seq, "\n ");
- if (mddev->curr_resync > 2)
- status_resync (seq, mddev);
- else if (mddev->curr_resync == 1 || mddev->curr_resync == 2)
- seq_printf(seq, " resync=DELAYED");
+ if (mddev->pers->sync_request) {
+ if (mddev->curr_resync > 2) {
+ status_resync (seq, mddev);
+ seq_printf(seq, "\n ");
+ } else if (mddev->curr_resync == 1 || mddev->curr_resync == 2)
+ seq_printf(seq, "\tresync=DELAYED\n ");
+ else if (mddev->recovery_cp < MaxSector)
+ seq_printf(seq, "\tresync=PENDING\n ");
+ }
+ } else
+ seq_printf(seq, "\n ");
+
+ if ((bitmap = mddev->bitmap)) {
+ unsigned long chunk_kb;
+ unsigned long flags;
+ spin_lock_irqsave(&bitmap->lock, flags);
+ chunk_kb = bitmap->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 : bitmap->chunksize,
+ 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_printf(seq, "\n");
+ spin_unlock_irqrestore(&bitmap->lock, flags);
}
seq_printf(seq, "\n");
static int md_seq_open(struct inode *inode, struct file *file)
{
int error;
+ struct mdstat_info *mi = kmalloc(sizeof(*mi), GFP_KERNEL);
+ if (mi == NULL)
+ return -ENOMEM;
error = seq_open(file, &md_seq_ops);
+ if (error)
+ kfree(mi);
+ else {
+ struct seq_file *p = file->private_data;
+ p->private = mi;
+ mi->event = atomic_read(&md_event_count);
+ }
return error;
}
+static int md_seq_release(struct inode *inode, struct file *file)
+{
+ struct seq_file *m = file->private_data;
+ struct mdstat_info *mi = m->private;
+ m->private = NULL;
+ kfree(mi);
+ return seq_release(inode, file);
+}
+
+static unsigned int mdstat_poll(struct file *filp, poll_table *wait)
+{
+ struct seq_file *m = filp->private_data;
+ struct mdstat_info *mi = m->private;
+ int mask;
+
+ poll_wait(filp, &md_event_waiters, wait);
+
+ /* always allow read */
+ mask = POLLIN | POLLRDNORM;
+
+ if (mi->event != atomic_read(&md_event_count))
+ mask |= POLLERR | POLLPRI;
+ return mask;
+}
+
static struct file_operations md_seq_fops = {
.open = md_seq_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release,
+ .release = md_seq_release,
+ .poll = mdstat_poll,
};
-int register_md_personality(int pnum, mdk_personality_t *p)
+int register_md_personality(struct mdk_personality *p)
{
- if (pnum >= MAX_PERSONALITY) {
- printk(KERN_ERR
- "md: tried to install personality %s as nr %d, but max is %lu\n",
- p->name, pnum, MAX_PERSONALITY-1);
- return -EINVAL;
- }
-
spin_lock(&pers_lock);
- if (pers[pnum]) {
- spin_unlock(&pers_lock);
- MD_BUG();
- return -EBUSY;
- }
-
- pers[pnum] = p;
- printk(KERN_INFO "md: %s personality registered as nr %d\n", p->name, pnum);
+ list_add_tail(&p->list, &pers_list);
+ printk(KERN_INFO "md: %s personality registered for level %d\n", p->name, p->level);
spin_unlock(&pers_lock);
return 0;
}
-int unregister_md_personality(int pnum)
+int unregister_md_personality(struct mdk_personality *p)
{
- if (pnum >= MAX_PERSONALITY) {
- MD_BUG();
- return -EINVAL;
- }
-
- printk(KERN_INFO "md: %s personality unregistered\n", pers[pnum]->name);
+ printk(KERN_INFO "md: %s personality unregistered\n", p->name);
spin_lock(&pers_lock);
- pers[pnum] = NULL;
+ list_del_init(&p->list);
spin_unlock(&pers_lock);
return 0;
}
-void md_sync_acct(mdk_rdev_t *rdev, unsigned long nr_sectors)
-{
- rdev->bdev->bd_contains->bd_disk->sync_io += nr_sectors;
-}
-
static int is_mddev_idle(mddev_t *mddev)
{
mdk_rdev_t * rdev;
idle = 1;
ITERATE_RDEV(mddev,rdev,tmp) {
struct gendisk *disk = rdev->bdev->bd_contains->bd_disk;
- curr_events = disk_stat_read(disk, read_sectors) +
- disk_stat_read(disk, write_sectors) -
- disk->sync_io;
- if ((curr_events - rdev->last_events) > 32) {
+ curr_events = disk_stat_read(disk, sectors[0]) +
+ disk_stat_read(disk, sectors[1]) -
+ atomic_read(&disk->sync_io);
+ /* The difference between curr_events and last_events
+ * will be affected by any new non-sync IO (making
+ * curr_events bigger) and any difference in the amount of
+ * in-flight syncio (making current_events bigger or smaller)
+ * The amount in-flight is currently limited to
+ * 32*64K in raid1/10 and 256*PAGE_SIZE in raid5/6
+ * which is at most 4096 sectors.
+ * These numbers are fairly fragile and should be made
+ * more robust, probably by enforcing the
+ * 'window size' that md_do_sync sort-of uses.
+ *
+ * Note: the following is an unsigned comparison.
+ */
+ if ((curr_events - rdev->last_events + 4096) > 8192) {
rdev->last_events = curr_events;
idle = 0;
}
}
-void md_write_start(mddev_t *mddev)
+/* md_write_start(mddev, bi)
+ * If we need to update some array metadata (e.g. 'active' flag
+ * in superblock) before writing, schedule a superblock update
+ * and wait for it to complete.
+ */
+void md_write_start(mddev_t *mddev, struct bio *bi)
{
- if (!atomic_read(&mddev->writes_pending)) {
- mddev_lock_uninterruptible(mddev);
+ if (bio_data_dir(bi) != WRITE)
+ return;
+
+ BUG_ON(mddev->ro == 1);
+ if (mddev->ro == 2) {
+ /* need to switch to read/write */
+ mddev->ro = 0;
+ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ md_wakeup_thread(mddev->thread);
+ }
+ atomic_inc(&mddev->writes_pending);
+ if (mddev->in_sync) {
+ spin_lock_irq(&mddev->write_lock);
if (mddev->in_sync) {
mddev->in_sync = 0;
- del_timer(&mddev->safemode_timer);
- md_update_sb(mddev);
+ mddev->sb_dirty = 1;
+ md_wakeup_thread(mddev->thread);
}
- atomic_inc(&mddev->writes_pending);
- mddev_unlock(mddev);
- } else
- atomic_inc(&mddev->writes_pending);
+ spin_unlock_irq(&mddev->write_lock);
+ }
+ wait_event(mddev->sb_wait, mddev->sb_dirty==0);
}
void md_write_end(mddev_t *mddev)
}
}
-static inline void md_enter_safemode(mddev_t *mddev)
-{
- if (!mddev->safemode) return;
- if (mddev->safemode == 2 &&
- (atomic_read(&mddev->writes_pending) || mddev->in_sync ||
- mddev->recovery_cp != MaxSector))
- return; /* avoid the lock */
- mddev_lock_uninterruptible(mddev);
- if (mddev->safemode && !atomic_read(&mddev->writes_pending) &&
- !mddev->in_sync && mddev->recovery_cp == MaxSector) {
- mddev->in_sync = 1;
- md_update_sb(mddev);
- }
- mddev_unlock(mddev);
-
- if (mddev->safemode == 1)
- mddev->safemode = 0;
-}
-
-void md_handle_safemode(mddev_t *mddev)
-{
- if (signal_pending(current)) {
- printk(KERN_INFO "md: %s in immediate safe mode\n",
- mdname(mddev));
- mddev->safemode = 2;
- flush_signals(current);
- }
- md_enter_safemode(mddev);
-}
-
-
-DECLARE_WAIT_QUEUE_HEAD(resync_wait);
+static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
#define SYNC_MARKS 10
#define SYNC_MARK_STEP (3*HZ)
mddev_t *mddev2;
unsigned int currspeed = 0,
window;
- sector_t max_sectors,j;
+ sector_t max_sectors,j, io_sectors;
unsigned long mark[SYNC_MARKS];
sector_t mark_cnt[SYNC_MARKS];
int last_mark,m;
struct list_head *tmp;
sector_t last_check;
+ int skipped = 0;
/* just incase thread restarts... */
if (test_bit(MD_RECOVERY_DONE, &mddev->recovery))
* 1 == like 2, but have yielded to allow conflicting resync to
* commense
* other == active in resync - this many blocks
+ *
+ * Before starting a resync we must have set curr_resync to
+ * 2, and then checked that every "conflicting" array has curr_resync
+ * less than ours. When we find one that is the same or higher
+ * we wait on resync_wait. To avoid deadlock, we reduce curr_resync
+ * to 1 if we choose to yield (based arbitrarily on address of mddev structure).
+ * This will mean we have to start checking from the beginning again.
+ *
*/
+
do {
mddev->curr_resync = 2;
+ try_again:
+ if (kthread_should_stop()) {
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+ goto skip;
+ }
ITERATE_MDDEV(mddev2,tmp) {
if (mddev2 == mddev)
continue;
if (mddev2->curr_resync &&
match_mddev_units(mddev,mddev2)) {
- printk(KERN_INFO "md: delaying resync of %s"
- " until %s has finished resync (they"
- " share one or more physical units)\n",
- mdname(mddev), mdname(mddev2));
- if (mddev < mddev2) {/* arbitrarily yield */
+ DEFINE_WAIT(wq);
+ if (mddev < mddev2 && mddev->curr_resync == 2) {
+ /* arbitrarily yield */
mddev->curr_resync = 1;
wake_up(&resync_wait);
}
- if (wait_event_interruptible(resync_wait,
- mddev2->curr_resync < mddev->curr_resync)) {
- flush_signals(current);
+ if (mddev > mddev2 && mddev->curr_resync == 1)
+ /* no need to wait here, we can wait the next
+ * time 'round when curr_resync == 2
+ */
+ continue;
+ prepare_to_wait(&resync_wait, &wq, TASK_UNINTERRUPTIBLE);
+ if (!kthread_should_stop() &&
+ mddev2->curr_resync >= mddev->curr_resync) {
+ printk(KERN_INFO "md: delaying resync of %s"
+ " until %s has finished resync (they"
+ " share one or more physical units)\n",
+ mdname(mddev), mdname(mddev2));
mddev_put(mddev2);
- goto skip;
+ schedule();
+ finish_wait(&resync_wait, &wq);
+ goto try_again;
}
- }
- if (mddev->curr_resync == 1) {
- mddev_put(mddev2);
- break;
+ finish_wait(&resync_wait, &wq);
}
}
} while (mddev->curr_resync < 2);
- max_sectors = mddev->size << 1;
+ if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
+ /* resync follows the size requested by the personality,
+ * which defaults to physical size, but can be virtual size
+ */
+ max_sectors = mddev->resync_max_sectors;
+ mddev->resync_mismatches = 0;
+ } else
+ /* recovery follows the physical size of devices */
+ max_sectors = mddev->size << 1;
printk(KERN_INFO "md: syncing RAID array %s\n", mdname(mddev));
printk(KERN_INFO "md: minimum _guaranteed_ reconstruction speed:"
- " %d KB/sec/disc.\n", sysctl_speed_limit_min);
- printk(KERN_INFO "md: using maximum available idle IO bandwith "
+ " %d KB/sec/disc.\n", speed_min(mddev));
+ printk(KERN_INFO "md: using maximum available idle IO bandwidth "
"(but not more than %d KB/sec) for reconstruction.\n",
- sysctl_speed_limit_max);
+ speed_max(mddev));
is_mddev_idle(mddev); /* this also initializes IO event counters */
- if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
+ /* we don't use the checkpoint if there's a bitmap */
+ if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) && !mddev->bitmap
+ && ! test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
j = mddev->recovery_cp;
else
j = 0;
+ io_sectors = 0;
for (m = 0; m < SYNC_MARKS; m++) {
mark[m] = jiffies;
- mark_cnt[m] = j;
+ mark_cnt[m] = io_sectors;
}
last_mark = 0;
mddev->resync_mark = mark[last_mark];
* Tune reconstruction:
*/
window = 32*(PAGE_SIZE/512);
- printk(KERN_INFO "md: using %dk window, over a total of %Lu blocks.\n",
+ printk(KERN_INFO "md: using %dk window, over a total of %llu blocks.\n",
window/2,(unsigned long long) max_sectors/2);
atomic_set(&mddev->recovery_active, 0);
init_waitqueue_head(&mddev->recovery_wait);
last_check = 0;
- if (j)
+ if (j>2) {
printk(KERN_INFO
"md: resuming recovery of %s from checkpoint.\n",
mdname(mddev));
+ mddev->curr_resync = j;
+ }
while (j < max_sectors) {
- int sectors;
+ sector_t sectors;
- sectors = mddev->pers->sync_request(mddev, j, currspeed < sysctl_speed_limit_min);
- if (sectors < 0) {
+ skipped = 0;
+ sectors = mddev->pers->sync_request(mddev, j, &skipped,
+ currspeed < speed_min(mddev));
+ if (sectors == 0) {
set_bit(MD_RECOVERY_ERR, &mddev->recovery);
goto out;
}
- atomic_add(sectors, &mddev->recovery_active);
+
+ if (!skipped) { /* actual IO requested */
+ io_sectors += sectors;
+ atomic_add(sectors, &mddev->recovery_active);
+ }
+
j += sectors;
if (j>1) mddev->curr_resync = j;
+ if (last_check == 0)
+ /* this is the earliers that rebuilt will be
+ * visible in /proc/mdstat
+ */
+ md_new_event(mddev);
- if (last_check + window > j)
+ if (last_check + window > io_sectors || j == max_sectors)
continue;
- last_check = j;
+ last_check = io_sectors;
if (test_bit(MD_RECOVERY_INTR, &mddev->recovery) ||
test_bit(MD_RECOVERY_ERR, &mddev->recovery))
break;
repeat:
- if (jiffies >= mark[last_mark] + SYNC_MARK_STEP ) {
+ if (time_after_eq(jiffies, mark[last_mark] + SYNC_MARK_STEP )) {
/* step marks */
int next = (last_mark+1) % SYNC_MARKS;
mddev->resync_mark = mark[next];
mddev->resync_mark_cnt = mark_cnt[next];
mark[next] = jiffies;
- mark_cnt[next] = j - atomic_read(&mddev->recovery_active);
+ mark_cnt[next] = io_sectors - atomic_read(&mddev->recovery_active);
last_mark = next;
}
- if (signal_pending(current)) {
+ if (kthread_should_stop()) {
/*
* got a signal, exit.
*/
printk(KERN_INFO
"md: md_do_sync() got signal ... exiting\n");
- flush_signals(current);
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
goto out;
}
mddev->queue->unplug_fn(mddev->queue);
cond_resched();
- currspeed = ((unsigned long)(j-mddev->resync_mark_cnt))/2/((jiffies-mddev->resync_mark)/HZ +1) +1;
+ currspeed = ((unsigned long)(io_sectors-mddev->resync_mark_cnt))/2
+ /((jiffies-mddev->resync_mark)/HZ +1) +1;
- if (currspeed > sysctl_speed_limit_min) {
- if ((currspeed > sysctl_speed_limit_max) ||
+ if (currspeed > speed_min(mddev)) {
+ if ((currspeed > speed_max(mddev)) ||
!is_mddev_idle(mddev)) {
- current->state = TASK_INTERRUPTIBLE;
- schedule_timeout(HZ/4);
+ msleep(500);
goto repeat;
}
}
wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active));
/* tell personality that we are finished */
- mddev->pers->sync_request(mddev, max_sectors, 1);
+ mddev->pers->sync_request(mddev, max_sectors, &skipped, 1);
if (!test_bit(MD_RECOVERY_ERR, &mddev->recovery) &&
mddev->curr_resync > 2 &&
- mddev->curr_resync > mddev->recovery_cp) {
+ mddev->curr_resync >= mddev->recovery_cp) {
if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
printk(KERN_INFO
"md: checkpointing recovery of %s.\n",
mddev->recovery_cp = MaxSector;
}
- md_enter_safemode(mddev);
skip:
mddev->curr_resync = 0;
+ wake_up(&resync_wait);
set_bit(MD_RECOVERY_DONE, &mddev->recovery);
md_wakeup_thread(mddev->thread);
}
struct list_head *rtmp;
- dprintk(KERN_INFO "md: recovery thread got woken up ...\n");
+ if (mddev->bitmap)
+ bitmap_daemon_work(mddev->bitmap);
if (mddev->ro)
return;
+
+ if (signal_pending(current)) {
+ if (mddev->pers->sync_request) {
+ printk(KERN_INFO "md: %s in immediate safe mode\n",
+ mdname(mddev));
+ mddev->safemode = 2;
+ }
+ flush_signals(current);
+ }
+
if ( ! (
mddev->sb_dirty ||
test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) ||
- test_bit(MD_RECOVERY_DONE, &mddev->recovery)
+ test_bit(MD_RECOVERY_DONE, &mddev->recovery) ||
+ (mddev->safemode == 1) ||
+ (mddev->safemode == 2 && ! atomic_read(&mddev->writes_pending)
+ && !mddev->in_sync && mddev->recovery_cp == MaxSector)
))
return;
+
if (mddev_trylock(mddev)==0) {
int spares =0;
+
+ spin_lock_irq(&mddev->write_lock);
+ if (mddev->safemode && !atomic_read(&mddev->writes_pending) &&
+ !mddev->in_sync && mddev->recovery_cp == MaxSector) {
+ mddev->in_sync = 1;
+ mddev->sb_dirty = 1;
+ }
+ if (mddev->safemode == 1)
+ mddev->safemode = 0;
+ spin_unlock_irq(&mddev->write_lock);
+
if (mddev->sb_dirty)
md_update_sb(mddev);
+
+
if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) &&
!test_bit(MD_RECOVERY_DONE, &mddev->recovery)) {
/* resync/recovery still happening */
mddev->pers->spare_active(mddev);
}
md_update_sb(mddev);
+
+ /* if array is no-longer degraded, then any saved_raid_disk
+ * information must be scrapped
+ */
+ if (!mddev->degraded)
+ ITERATE_RDEV(mddev,rdev,rtmp)
+ rdev->saved_raid_disk = -1;
+
mddev->recovery = 0;
/* flag recovery needed just to double check */
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
- wake_up(&resync_wait);
+ md_new_event(mddev);
goto unlock;
}
- if (mddev->recovery) {
- /* probably just the RECOVERY_NEEDED flag */
- mddev->recovery = 0;
- wake_up(&resync_wait);
- }
+ /* Clear some bits that don't mean anything, but
+ * might be left set
+ */
+ clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ clear_bit(MD_RECOVERY_ERR, &mddev->recovery);
+ clear_bit(MD_RECOVERY_INTR, &mddev->recovery);
+ clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
/* no recovery is running.
* remove any failed drives, then
- * add spares if possible
+ * add spares if possible.
+ * Spare are also removed and re-added, to allow
+ * the personality to fail the re-add.
*/
- ITERATE_RDEV(mddev,rdev,rtmp) {
+ ITERATE_RDEV(mddev,rdev,rtmp)
if (rdev->raid_disk >= 0 &&
- rdev->faulty &&
+ (test_bit(Faulty, &rdev->flags) || ! test_bit(In_sync, &rdev->flags)) &&
atomic_read(&rdev->nr_pending)==0) {
- mddev->pers->hot_remove_disk(mddev, rdev->raid_disk);
- rdev->raid_disk = -1;
+ 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 (!rdev->faulty && rdev->raid_disk >= 0 && !rdev->in_sync)
- spares++;
- }
+
if (mddev->degraded) {
ITERATE_RDEV(mddev,rdev,rtmp)
if (rdev->raid_disk < 0
- && !rdev->faulty) {
- if (mddev->pers->hot_add_disk(mddev,rdev))
+ && !test_bit(Faulty, &rdev->flags)) {
+ 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++;
- else
+ md_new_event(mddev);
+ } else
break;
}
}
- if (!spares && (mddev->recovery_cp == MaxSector )) {
- /* nothing we can do ... */
+ if (spares) {
+ clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+ clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+ } else if (mddev->recovery_cp < MaxSector) {
+ set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+ } else if (!test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
+ /* nothing to be done ... */
goto unlock;
- }
+
if (mddev->pers->sync_request) {
set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
- if (!spares)
- set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+ if (spares && mddev->bitmap && ! mddev->bitmap->file) {
+ /* We are adding a device or devices to an array
+ * which has the bitmap stored on all devices.
+ * So make sure all bitmap pages get written
+ */
+ bitmap_write_all(mddev->bitmap);
+ }
mddev->sync_thread = md_register_thread(md_do_sync,
mddev,
"%s_resync");
mdname(mddev));
/* leave the spares where they are, it shouldn't hurt */
mddev->recovery = 0;
- } else {
+ } else
md_wakeup_thread(mddev->sync_thread);
- }
+ md_new_event(mddev);
}
unlock:
mddev_unlock(mddev);
}
}
-int md_notify_reboot(struct notifier_block *this,
- unsigned long code, void *x)
+static int md_notify_reboot(struct notifier_block *this,
+ unsigned long code, void *x)
{
struct list_head *tmp;
mddev_t *mddev;
return NOTIFY_DONE;
}
-struct notifier_block md_notifier = {
+static struct notifier_block md_notifier = {
.notifier_call = md_notify_reboot,
.next = NULL,
.priority = INT_MAX, /* before any real devices */
p->proc_fops = &md_seq_fops;
}
-int __init md_init(void)
+static int __init md_init(void)
{
int minor;
" MD_SB_DISKS=%d\n",
MD_MAJOR_VERSION, MD_MINOR_VERSION,
MD_PATCHLEVEL_VERSION, MAX_MD_DEVS, MD_SB_DISKS);
+ printk(KERN_INFO "md: bitmap version %d.%d\n", BITMAP_MAJOR_HI,
+ BITMAP_MINOR);
if (register_blkdev(MAJOR_NR, "md"))
return -1;
for (minor=0; minor < MAX_MD_DEVS; ++minor)
devfs_mk_bdev(MKDEV(mdp_major, minor<<MdpMinorShift),
S_IFBLK|S_IRUSR|S_IWUSR,
- "md/d%d", minor);
+ "md/mdp%d", minor);
register_reboot_notifier(&md_notifier);
static void autostart_arrays(int part)
{
- char b[BDEVNAME_SIZE];
mdk_rdev_t *rdev;
int i;
dev_t dev = detected_devices[i];
rdev = md_import_device(dev,0, 0);
- if (IS_ERR(rdev)) {
- printk(KERN_ALERT "md: could not import %s!\n",
- __bdevname(dev, b));
+ if (IS_ERR(rdev))
continue;
- }
- if (rdev->faulty) {
+
+ if (test_bit(Faulty, &rdev->flags)) {
MD_BUG();
continue;
}
module_init(md_init)
module_exit(md_exit)
+static int get_ro(char *buffer, struct kernel_param *kp)
+{
+ return sprintf(buffer, "%d", start_readonly);
+}
+static int set_ro(const char *val, struct kernel_param *kp)
+{
+ char *e;
+ int num = simple_strtoul(val, &e, 10);
+ if (*val && (*e == '\0' || *e == '\n')) {
+ start_readonly = num;
+ return 0;
+ }
+ return -EINVAL;
+}
+
+module_param_call(start_ro, set_ro, get_ro, NULL, 0600);
+module_param(start_dirty_degraded, int, 0644);
+
+
EXPORT_SYMBOL(register_md_personality);
EXPORT_SYMBOL(unregister_md_personality);
EXPORT_SYMBOL(md_error);
-EXPORT_SYMBOL(md_sync_acct);
EXPORT_SYMBOL(md_done_sync);
EXPORT_SYMBOL(md_write_start);
EXPORT_SYMBOL(md_write_end);
-EXPORT_SYMBOL(md_handle_safemode);
EXPORT_SYMBOL(md_register_thread);
EXPORT_SYMBOL(md_unregister_thread);
EXPORT_SYMBOL(md_wakeup_thread);
EXPORT_SYMBOL(md_print_devices);
-EXPORT_SYMBOL(md_interrupt_thread);
EXPORT_SYMBOL(md_check_recovery);
MODULE_LICENSE("GPL");
+MODULE_ALIAS("md");
+MODULE_ALIAS_BLOCKDEV_MAJOR(MD_MAJOR);