*/
#include <linux/module.h>
+#include <linux/kernel.h>
#include <linux/kthread.h>
#include <linux/linkage.h>
#include <linux/raid/md.h>
* Any code which breaks out of this loop while own
* a reference to the current mddev and must mddev_put it.
*/
-#define ITERATE_MDDEV(mddev,tmp) \
+#define for_each_mddev(mddev,tmp) \
\
for (({ spin_lock(&all_mddevs_lock); \
tmp = all_mddevs.next; \
)
-static int md_fail_request (request_queue_t *q, struct bio *bio)
+static int md_fail_request (struct request_queue *q, struct bio *bio)
{
- bio_io_error(bio, bio->bi_size);
+ bio_io_error(bio);
return 0;
}
list_del(&mddev->all_mddevs);
spin_unlock(&all_mddevs_lock);
blk_cleanup_queue(mddev->queue);
- kobject_unregister(&mddev->kobj);
+ kobject_put(&mddev->kobj);
} else
spin_unlock(&all_mddevs_lock);
}
atomic_set(&new->active, 1);
spin_lock_init(&new->write_lock);
init_waitqueue_head(&new->sb_wait);
+ new->reshape_position = MaxSector;
+ new->resync_max = MaxSector;
new->queue = blk_alloc_queue(GFP_KERNEL);
if (!new->queue) {
mdk_rdev_t * rdev;
struct list_head *tmp;
- ITERATE_RDEV(mddev,rdev,tmp) {
+ rdev_for_each(rdev, tmp, mddev) {
if (rdev->desc_nr == nr)
return rdev;
}
struct list_head *tmp;
mdk_rdev_t *rdev;
- ITERATE_RDEV(mddev,rdev,tmp) {
+ rdev_for_each(rdev, tmp, mddev) {
if (rdev->bdev->bd_dev == dev)
return rdev;
}
}
-static int super_written(struct bio *bio, unsigned int bytes_done, int error)
+static void super_written(struct bio *bio, 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)) {
printk("md: super_written gets error=%d, uptodate=%d\n",
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)
+static void super_written_barrier(struct bio *bio, 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) {
spin_unlock_irqrestore(&mddev->write_lock, flags);
wake_up(&mddev->sb_wait);
bio_put(bio);
- return 0;
+ } else {
+ bio_put(bio2);
+ bio->bi_private = rdev;
+ super_written(bio, error);
}
- 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,
finish_wait(&mddev->sb_wait, &wq);
}
-static int bi_complete(struct bio *bio, unsigned int bytes_done, int error)
+static void bi_complete(struct bio *bio, int error)
{
- if (bio->bi_size)
- return 1;
-
complete((struct completion*)bio->bi_private);
- return 0;
}
int sync_page_io(struct block_device *bdev, sector_t sector, int size,
return ret;
}
+
+static u32 md_csum_fold(u32 csum)
+{
+ csum = (csum & 0xffff) + (csum >> 16);
+ return (csum & 0xffff) + (csum >> 16);
+}
+
static unsigned int calc_sb_csum(mdp_super_t * sb)
{
+ u64 newcsum = 0;
+ u32 *sb32 = (u32*)sb;
+ int i;
unsigned int disk_csum, csum;
disk_csum = sb->sb_csum;
sb->sb_csum = 0;
- csum = csum_partial((void *)sb, MD_SB_BYTES, 0);
+
+ for (i = 0; i < MD_SB_BYTES/4 ; i++)
+ newcsum += sb32[i];
+ csum = (newcsum & 0xffffffff) + (newcsum>>32);
+
+
+#ifdef CONFIG_ALPHA
+ /* This used to use csum_partial, which was wrong for several
+ * reasons including that different results are returned on
+ * different architectures. It isn't critical that we get exactly
+ * the same return value as before (we always csum_fold before
+ * testing, and that removes any differences). However as we
+ * know that csum_partial always returned a 16bit value on
+ * alphas, do a fold to maximise conformity to previous behaviour.
+ */
+ sb->sb_csum = md_csum_fold(disk_csum);
+#else
sb->sb_csum = disk_csum;
+#endif
return csum;
}
if (sb->raid_disks <= 0)
goto abort;
- if (csum_fold(calc_sb_csum(sb)) != csum_fold(sb->sb_csum)) {
+ if (md_csum_fold(calc_sb_csum(sb)) != md_csum_fold(sb->sb_csum)) {
printk(KERN_WARNING "md: invalid superblock checksum on %s\n",
b);
goto abort;
rdev->data_offset = 0;
rdev->sb_size = MD_SB_BYTES;
+ if (sb->state & (1<<MD_SB_BITMAP_PRESENT)) {
+ if (sb->level != 1 && sb->level != 4
+ && sb->level != 5 && sb->level != 6
+ && sb->level != 10) {
+ /* FIXME use a better test */
+ printk(KERN_WARNING
+ "md: bitmaps not supported for this level.\n");
+ goto abort;
+ }
+ }
+
if (sb->level == LEVEL_MULTIPATH)
rdev->desc_nr = -1;
else
__u64 ev1 = md_event(sb);
rdev->raid_disk = -1;
- rdev->flags = 0;
+ clear_bit(Faulty, &rdev->flags);
+ clear_bit(In_sync, &rdev->flags);
+ clear_bit(WriteMostly, &rdev->flags);
+ clear_bit(BarriersNotsupp, &rdev->flags);
+
if (mddev->raid_disks == 0) {
mddev->major_version = 0;
mddev->minor_version = sb->minor_version;
mddev->patch_version = sb->patch_version;
- mddev->persistent = ! sb->not_persistent;
+ mddev->external = 0;
mddev->chunk_size = sb->chunk_size;
mddev->ctime = sb->ctime;
mddev->utime = sb->utime;
mddev->max_disks = MD_SB_DISKS;
if (sb->state & (1<<MD_SB_BITMAP_PRESENT) &&
- mddev->bitmap_file == NULL) {
- if (mddev->level != 1 && mddev->level != 4
- && 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_file == NULL)
mddev->bitmap_offset = mddev->default_bitmap_offset;
- }
} else if (mddev->pers == NULL) {
/* Insist on good event counter while assembling */
sb->size = mddev->size;
sb->raid_disks = mddev->raid_disks;
sb->md_minor = mddev->md_minor;
- sb->not_persistent = !mddev->persistent;
+ sb->not_persistent = 0;
sb->utime = mddev->utime;
sb->state = 0;
sb->events_hi = (mddev->events>>32);
sb->state |= (1<<MD_SB_BITMAP_PRESENT);
sb->disks[0].state = (1<<MD_DISK_REMOVED);
- ITERATE_RDEV(mddev,rdev2,tmp) {
+ rdev_for_each(rdev2, tmp, mddev) {
mdp_disk_t *d;
int desc_nr;
if (rdev2->raid_disk >= 0 && test_bit(In_sync, &rdev2->flags)
bdevname(rdev->bdev,b));
return -EINVAL;
}
+ if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET)) {
+ if (sb->level != cpu_to_le32(1) &&
+ sb->level != cpu_to_le32(4) &&
+ sb->level != cpu_to_le32(5) &&
+ sb->level != cpu_to_le32(6) &&
+ sb->level != cpu_to_le32(10)) {
+ printk(KERN_WARNING
+ "md: bitmaps not supported for this level.\n");
+ 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;
+ rdev->sb_size = (rdev->sb_size | bmask) + 1;
+
+ if (minor_version
+ && rdev->data_offset < sb_offset + (rdev->sb_size/512))
+ return -EINVAL;
if (sb->level == cpu_to_le32(LEVEL_MULTIPATH))
rdev->desc_nr = -1;
else
ret = 0;
}
- if (minor_version)
+ if (minor_version)
rdev->size = ((rdev->bdev->bd_inode->i_size>>9) - le64_to_cpu(sb->data_offset)) / 2;
else
rdev->size = rdev->sb_offset;
__u64 ev1 = le64_to_cpu(sb->events);
rdev->raid_disk = -1;
- rdev->flags = 0;
+ clear_bit(Faulty, &rdev->flags);
+ clear_bit(In_sync, &rdev->flags);
+ clear_bit(WriteMostly, &rdev->flags);
+ clear_bit(BarriersNotsupp, &rdev->flags);
+
if (mddev->raid_disks == 0) {
mddev->major_version = 1;
mddev->patch_version = 0;
- mddev->persistent = 1;
+ mddev->external = 0;
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->max_disks = (4096-256)/2;
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_file == NULL )
mddev->bitmap_offset = (__s32)le32_to_cpu(sb->bitmap_offset);
- }
+
if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_ACTIVE)) {
mddev->reshape_position = le64_to_cpu(sb->reshape_position);
mddev->delta_disks = le32_to_cpu(sb->delta_disks);
}
max_dev = 0;
- ITERATE_RDEV(mddev,rdev2,tmp)
+ rdev_for_each(rdev2, tmp, mddev)
if (rdev2->desc_nr+1 > max_dev)
max_dev = rdev2->desc_nr+1;
-
- sb->max_dev = cpu_to_le32(max_dev);
+
+ if (max_dev > le32_to_cpu(sb->max_dev))
+ sb->max_dev = cpu_to_le32(max_dev);
for (i=0; i<max_dev;i++)
sb->dev_roles[i] = cpu_to_le16(0xfffe);
- ITERATE_RDEV(mddev,rdev2,tmp) {
+ rdev_for_each(rdev2, tmp, mddev) {
i = rdev2->desc_nr;
if (test_bit(Faulty, &rdev2->flags))
sb->dev_roles[i] = cpu_to_le16(0xfffe);
.sync_super = super_1_sync,
},
};
-
-static mdk_rdev_t * match_dev_unit(mddev_t *mddev, mdk_rdev_t *dev)
-{
- struct list_head *tmp;
- mdk_rdev_t *rdev;
-
- ITERATE_RDEV(mddev,rdev,tmp)
- if (rdev->bdev->bd_contains == dev->bdev->bd_contains)
- return rdev;
-
- return NULL;
-}
static int match_mddev_units(mddev_t *mddev1, mddev_t *mddev2)
{
- struct list_head *tmp;
- mdk_rdev_t *rdev;
+ struct list_head *tmp, *tmp2;
+ mdk_rdev_t *rdev, *rdev2;
- ITERATE_RDEV(mddev1,rdev,tmp)
- if (match_dev_unit(mddev2, rdev))
- return 1;
+ rdev_for_each(rdev, tmp, mddev1)
+ rdev_for_each(rdev2, tmp2, mddev2)
+ if (rdev->bdev->bd_contains ==
+ rdev2->bdev->bd_contains)
+ return 1;
return 0;
}
static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev)
{
- mdk_rdev_t *same_pdev;
- char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
+ char b[BDEVNAME_SIZE];
struct kobject *ko;
char *s;
+ int err;
if (rdev->mddev) {
MD_BUG();
}
/* 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
+ if (mddev->pers) {
+ /* Cannot change size, so fail
+ * If mddev->level <= 0, then we don't care
+ * about aligning sizes (e.g. linear)
+ */
+ if (mddev->level > 0)
+ return -ENOSPC;
+ } else
mddev->size = rdev->size;
}
- same_pdev = match_dev_unit(mddev, rdev);
- if (same_pdev)
- printk(KERN_WARNING
- "%s: WARNING: %s appears to be on the same physical"
- " disk as %s. True\n protection against single-disk"
- " failure might be compromised.\n",
- mdname(mddev), bdevname(rdev->bdev,b),
- bdevname(same_pdev->bdev,b2));
/* Verify rdev->desc_nr is unique.
* If it is -1, assign a free number, else
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)
+ while ( (s=strchr(b, '/')) != NULL)
*s = '!';
-
- list_add(&rdev->same_set, &mddev->disks);
+
rdev->mddev = mddev;
printk(KERN_INFO "md: bind<%s>\n", b);
- rdev->kobj.parent = &mddev->kobj;
- kobject_add(&rdev->kobj);
+ if ((err = kobject_add(&rdev->kobj, &mddev->kobj, "dev-%s", b)))
+ goto fail;
if (rdev->bdev->bd_part)
- ko = &rdev->bdev->bd_part->kobj;
+ ko = &rdev->bdev->bd_part->dev.kobj;
else
- ko = &rdev->bdev->bd_disk->kobj;
- sysfs_create_link(&rdev->kobj, ko, "block");
- bd_claim_by_disk(rdev->bdev, rdev, mddev->gendisk);
+ ko = &rdev->bdev->bd_disk->dev.kobj;
+ if ((err = sysfs_create_link(&rdev->kobj, ko, "block"))) {
+ kobject_del(&rdev->kobj);
+ goto fail;
+ }
+ list_add(&rdev->same_set, &mddev->disks);
+ bd_claim_by_disk(rdev->bdev, rdev->bdev->bd_holder, mddev->gendisk);
return 0;
+
+ fail:
+ printk(KERN_WARNING "md: failed to register dev-%s for %s\n",
+ b, mdname(mddev));
+ return err;
+}
+
+static void md_delayed_delete(struct work_struct *ws)
+{
+ mdk_rdev_t *rdev = container_of(ws, mdk_rdev_t, del_work);
+ kobject_del(&rdev->kobj);
+ kobject_put(&rdev->kobj);
}
static void unbind_rdev_from_array(mdk_rdev_t * rdev)
printk(KERN_INFO "md: unbind<%s>\n", bdevname(rdev->bdev,b));
rdev->mddev = NULL;
sysfs_remove_link(&rdev->kobj, "block");
- kobject_del(&rdev->kobj);
+
+ /* We need to delay this, otherwise we can deadlock when
+ * writing to 'remove' to "dev/state"
+ */
+ INIT_WORK(&rdev->del_work, md_delayed_delete);
+ kobject_get(&rdev->kobj);
+ schedule_work(&rdev->del_work);
}
/*
* otherwise reused by a RAID array (or any other kernel
* subsystem), by bd_claiming the device.
*/
-static int lock_rdev(mdk_rdev_t *rdev, dev_t dev)
+static int lock_rdev(mdk_rdev_t *rdev, dev_t dev, int shared)
{
int err = 0;
struct block_device *bdev;
__bdevname(dev, b));
return PTR_ERR(bdev);
}
- err = bd_claim(bdev, rdev);
+ err = bd_claim(bdev, shared ? (mdk_rdev_t *)lock_rdev : rdev);
if (err) {
printk(KERN_ERR "md: could not bd_claim %s.\n",
bdevname(bdev, b));
blkdev_put(bdev);
return err;
}
+ if (!shared)
+ set_bit(AllReserved, &rdev->flags);
rdev->bdev = bdev;
return err;
}
free_disk_sb(rdev);
list_del_init(&rdev->same_set);
#ifndef MODULE
- md_autodetect_dev(rdev->bdev->bd_dev);
+ if (test_bit(AutoDetected, &rdev->flags))
+ md_autodetect_dev(rdev->bdev->bd_dev);
#endif
unlock_rdev(rdev);
kobject_put(&rdev->kobj);
struct list_head *tmp;
mdk_rdev_t *rdev;
- ITERATE_RDEV(mddev,rdev,tmp) {
+ rdev_for_each(rdev, tmp, mddev) {
if (!rdev->mddev) {
MD_BUG();
continue;
printk("md: **********************************\n");
printk("md: * <COMPLETE RAID STATE PRINTOUT> *\n");
printk("md: **********************************\n");
- ITERATE_MDDEV(mddev,tmp) {
+ for_each_mddev(mddev, tmp) {
if (mddev->bitmap)
bitmap_print_sb(mddev->bitmap);
else
printk("%s: ", mdname(mddev));
- ITERATE_RDEV(mddev,rdev,tmp2)
+ rdev_for_each(rdev, tmp2, mddev)
printk("<%s>", bdevname(rdev->bdev,b));
printk("\n");
- ITERATE_RDEV(mddev,rdev,tmp2)
+ rdev_for_each(rdev, tmp2, mddev)
print_rdev(rdev);
}
printk("md: **********************************\n");
mdk_rdev_t *rdev;
struct list_head *tmp;
- ITERATE_RDEV(mddev,rdev,tmp) {
+ rdev_for_each(rdev, tmp, mddev) {
if (rdev->sb_events == mddev->events ||
(nospares &&
rdev->raid_disk < 0 &&
static void md_update_sb(mddev_t * mddev, int force_change)
{
- int err;
struct list_head *tmp;
mdk_rdev_t *rdev;
int sync_req;
* and 'events' is odd, we can roll back to the previous clean state */
if (nospares
&& (mddev->in_sync && mddev->recovery_cp == MaxSector)
- && (mddev->events & 1))
+ && (mddev->events & 1)
+ && mddev->events != 1)
mddev->events--;
else {
/* otherwise we have to go forward and ... */
MD_BUG();
mddev->events --;
}
- sync_sbs(mddev, nospares);
/*
* do not write anything to disk if using
* nonpersistent superblocks
*/
if (!mddev->persistent) {
- clear_bit(MD_CHANGE_PENDING, &mddev->flags);
+ if (!mddev->external)
+ clear_bit(MD_CHANGE_PENDING, &mddev->flags);
+
spin_unlock_irq(&mddev->write_lock);
wake_up(&mddev->sb_wait);
return;
}
+ sync_sbs(mddev, nospares);
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 = bitmap_update_sb(mddev->bitmap);
- ITERATE_RDEV(mddev,rdev,tmp) {
+ bitmap_update_sb(mddev->bitmap);
+ rdev_for_each(rdev, tmp, mddev) {
char b[BDEVNAME_SIZE];
dprintk(KERN_INFO "md: ");
if (rdev->sb_loaded != 1)
state_show(mdk_rdev_t *rdev, char *page)
{
char *sep = "";
- int len=0;
+ size_t len = 0;
if (test_bit(Faulty, &rdev->flags)) {
len+= sprintf(page+len, "%sfaulty",sep);
else {
mddev_t *mddev = rdev->mddev;
kick_rdev_from_array(rdev);
- md_update_sb(mddev, 1);
+ if (mddev->pers)
+ md_update_sb(mddev, 1);
md_new_event(mddev);
err = 0;
}
__ATTR(state, S_IRUGO|S_IWUSR, state_show, state_store);
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));
slot_store(mdk_rdev_t *rdev, const char *buf, size_t len)
{
char *e;
+ int err;
+ char nm[20];
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);
+ if (rdev->mddev->pers) {
+ /* Setting 'slot' on an active array requires also
+ * updating the 'rd%d' link, and communicating
+ * with the personality with ->hot_*_disk.
+ * For now we only support removing
+ * failed/spare devices. This normally happens automatically,
+ * but not when the metadata is externally managed.
+ */
+ if (slot != -1)
+ return -EBUSY;
+ if (rdev->raid_disk == -1)
+ return -EEXIST;
+ /* personality does all needed checks */
+ if (rdev->mddev->pers->hot_add_disk == NULL)
+ return -EINVAL;
+ err = rdev->mddev->pers->
+ hot_remove_disk(rdev->mddev, rdev->raid_disk);
+ if (err)
+ return err;
+ sprintf(nm, "rd%d", rdev->raid_disk);
+ sysfs_remove_link(&rdev->mddev->kobj, nm);
+ set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
+ md_wakeup_thread(rdev->mddev->thread);
+ } else {
+ if (slot >= rdev->mddev->raid_disks)
+ return -ENOSPC;
+ rdev->raid_disk = slot;
+ /* assume it is working */
+ clear_bit(Faulty, &rdev->flags);
+ clear_bit(WriteMostly, &rdev->flags);
+ set_bit(In_sync, &rdev->flags);
+ }
return len;
}
return -EINVAL;
if (rdev->mddev->pers)
return -EBUSY;
+ if (rdev->size && rdev->mddev->external)
+ /* Must set offset before size, so overlap checks
+ * can be sane */
+ return -EBUSY;
rdev->data_offset = offset;
return len;
}
return sprintf(page, "%llu\n", (unsigned long long)rdev->size);
}
+static int overlaps(sector_t s1, sector_t l1, sector_t s2, sector_t l2)
+{
+ /* check if two start/length pairs overlap */
+ if (s1+l1 <= s2)
+ return 0;
+ if (s2+l2 <= s1)
+ return 0;
+ return 1;
+}
+
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);
+ unsigned long long oldsize = rdev->size;
+ mddev_t *my_mddev = rdev->mddev;
+
if (e==buf || (*e && *e != '\n'))
return -EINVAL;
- if (rdev->mddev->pers)
+ if (my_mddev->pers)
return -EBUSY;
rdev->size = size;
- if (size < rdev->mddev->size || rdev->mddev->size == 0)
- rdev->mddev->size = size;
+ if (size > oldsize && rdev->mddev->external) {
+ /* need to check that all other rdevs with the same ->bdev
+ * do not overlap. We need to unlock the mddev to avoid
+ * a deadlock. We have already changed rdev->size, and if
+ * we have to change it back, we will have the lock again.
+ */
+ mddev_t *mddev;
+ int overlap = 0;
+ struct list_head *tmp, *tmp2;
+
+ mddev_unlock(my_mddev);
+ for_each_mddev(mddev, tmp) {
+ mdk_rdev_t *rdev2;
+
+ mddev_lock(mddev);
+ rdev_for_each(rdev2, tmp2, mddev)
+ if (test_bit(AllReserved, &rdev2->flags) ||
+ (rdev->bdev == rdev2->bdev &&
+ rdev != rdev2 &&
+ overlaps(rdev->data_offset, rdev->size,
+ rdev2->data_offset, rdev2->size))) {
+ overlap = 1;
+ break;
+ }
+ mddev_unlock(mddev);
+ if (overlap) {
+ mddev_put(mddev);
+ break;
+ }
+ }
+ mddev_lock(my_mddev);
+ if (overlap) {
+ /* Someone else could have slipped in a size
+ * change here, but doing so is just silly.
+ * We put oldsize back because we *know* it is
+ * safe, and trust userspace not to race with
+ * itself
+ */
+ rdev->size = oldsize;
+ return -EBUSY;
+ }
+ }
+ if (size < my_mddev->size || my_mddev->size == 0)
+ my_mddev->size = size;
return len;
}
static struct attribute *rdev_default_attrs[] = {
&rdev_state.attr,
- &rdev_super.attr,
&rdev_errors.attr,
&rdev_slot.attr,
&rdev_offset.attr,
{
struct rdev_sysfs_entry *entry = container_of(attr, struct rdev_sysfs_entry, attr);
mdk_rdev_t *rdev = container_of(kobj, mdk_rdev_t, kobj);
+ mddev_t *mddev = rdev->mddev;
+ ssize_t rv;
if (!entry->show)
return -EIO;
- return entry->show(rdev, page);
+
+ rv = mddev ? mddev_lock(mddev) : -EBUSY;
+ if (!rv) {
+ if (rdev->mddev == NULL)
+ rv = -EBUSY;
+ else
+ rv = entry->show(rdev, page);
+ mddev_unlock(mddev);
+ }
+ return rv;
}
static ssize_t
{
struct rdev_sysfs_entry *entry = container_of(attr, struct rdev_sysfs_entry, attr);
mdk_rdev_t *rdev = container_of(kobj, mdk_rdev_t, kobj);
+ ssize_t rv;
+ mddev_t *mddev = rdev->mddev;
if (!entry->store)
return -EIO;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
- return entry->store(rdev, page, length);
+ rv = mddev ? mddev_lock(mddev): -EBUSY;
+ if (!rv) {
+ if (rdev->mddev == NULL)
+ rv = -EBUSY;
+ else
+ rv = entry->store(rdev, page, length);
+ mddev_unlock(rdev->mddev);
+ }
+ return rv;
}
static void rdev_free(struct kobject *ko)
if ((err = alloc_disk_sb(rdev)))
goto abort_free;
- err = lock_rdev(rdev, newdev);
+ err = lock_rdev(rdev, newdev, super_format == -2);
if (err)
goto abort_free;
- rdev->kobj.parent = NULL;
- rdev->kobj.ktype = &rdev_ktype;
- kobject_init(&rdev->kobj);
+ kobject_init(&rdev->kobj, &rdev_ktype);
rdev->desc_nr = -1;
rdev->saved_raid_disk = -1;
+ rdev->raid_disk = -1;
rdev->flags = 0;
rdev->data_offset = 0;
rdev->sb_events = 0;
err = super_types[super_format].
load_super(rdev, NULL, super_minor);
if (err == -EINVAL) {
- printk(KERN_WARNING
- "md: %s has invalid sb, not importing!\n",
- bdevname(rdev->bdev,b));
+ printk(KERN_WARNING
+ "md: %s does not have a valid v%d.%d "
+ "superblock, not importing!\n",
+ bdevname(rdev->bdev,b),
+ super_format, super_minor);
goto abort_free;
}
if (err < 0) {
char b[BDEVNAME_SIZE];
freshest = NULL;
- ITERATE_RDEV(mddev,rdev,tmp)
+ rdev_for_each(rdev, tmp, mddev)
switch (super_types[mddev->major_version].
load_super(rdev, freshest, mddev->minor_version)) {
case 1:
validate_super(mddev, freshest);
i = 0;
- ITERATE_RDEV(mddev,rdev,tmp) {
+ rdev_for_each(rdev, tmp, mddev) {
if (rdev != freshest)
if (super_types[mddev->major_version].
validate_super(mddev, rdev)) {
rdev->desc_nr = i++;
rdev->raid_disk = rdev->desc_nr;
set_bit(In_sync, &rdev->flags);
+ } else if (rdev->raid_disk >= mddev->raid_disks) {
+ rdev->raid_disk = -1;
+ clear_bit(In_sync, &rdev->flags);
}
}
static ssize_t
level_store(mddev_t *mddev, const char *buf, size_t len)
{
- int rv = len;
+ ssize_t rv = len;
if (mddev->pers)
return -EBUSY;
if (len == 0)
layout_show(mddev_t *mddev, char *page)
{
/* just a number, not meaningful for all levels */
+ if (mddev->reshape_position != MaxSector &&
+ mddev->layout != mddev->new_layout)
+ return sprintf(page, "%d (%d)\n",
+ mddev->new_layout, mddev->layout);
return sprintf(page, "%d\n", mddev->layout);
}
{
char *e;
unsigned long n = simple_strtoul(buf, &e, 10);
- if (mddev->pers)
- return -EBUSY;
if (!*buf || (*e && *e != '\n'))
return -EINVAL;
- mddev->layout = n;
+ if (mddev->pers)
+ return -EBUSY;
+ if (mddev->reshape_position != MaxSector)
+ mddev->new_layout = n;
+ else
+ mddev->layout = n;
return len;
}
static struct md_sysfs_entry md_layout =
{
if (mddev->raid_disks == 0)
return 0;
+ if (mddev->reshape_position != MaxSector &&
+ mddev->delta_disks != 0)
+ return sprintf(page, "%d (%d)\n", mddev->raid_disks,
+ mddev->raid_disks - mddev->delta_disks);
return sprintf(page, "%d\n", mddev->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 (mddev->pers)
rv = update_raid_disks(mddev, n);
- else
+ else if (mddev->reshape_position != MaxSector) {
+ int olddisks = mddev->raid_disks - mddev->delta_disks;
+ mddev->delta_disks = n - olddisks;
+ mddev->raid_disks = n;
+ } else
mddev->raid_disks = n;
return rv ? rv : len;
}
static ssize_t
chunk_size_show(mddev_t *mddev, char *page)
{
+ if (mddev->reshape_position != MaxSector &&
+ mddev->chunk_size != mddev->new_chunk)
+ return sprintf(page, "%d (%d)\n", mddev->new_chunk,
+ mddev->chunk_size);
return sprintf(page, "%d\n", mddev->chunk_size);
}
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;
+ if (mddev->pers)
+ return -EBUSY;
+ else if (mddev->reshape_position != MaxSector)
+ mddev->new_chunk = n;
+ else
+ mddev->chunk_size = n;
return len;
}
static struct md_sysfs_entry md_chunk_size =
case 0:
if (mddev->in_sync)
st = clean;
+ else if (test_bit(MD_CHANGE_CLEAN, &mddev->flags))
+ st = write_pending;
else if (mddev->safemode)
st = active_idle;
else
break;
case clear:
/* stopping an active array */
- if (mddev->pers) {
- if (atomic_read(&mddev->active) > 1)
- return -EBUSY;
- err = do_md_stop(mddev, 0);
- }
+ if (atomic_read(&mddev->active) > 1)
+ return -EBUSY;
+ err = do_md_stop(mddev, 0);
break;
case inactive:
/* stopping an active array */
if (atomic_read(&mddev->active) > 1)
return -EBUSY;
err = do_md_stop(mddev, 2);
- }
+ } else
+ err = 0; /* already inactive */
break;
case suspended:
break; /* not supported yet */
restart_array(mddev);
spin_lock_irq(&mddev->write_lock);
if (atomic_read(&mddev->writes_pending) == 0) {
- mddev->in_sync = 1;
- set_bit(MD_CHANGE_CLEAN, &mddev->flags);
- }
+ if (mddev->in_sync == 0) {
+ mddev->in_sync = 1;
+ if (mddev->persistent)
+ set_bit(MD_CHANGE_CLEAN,
+ &mddev->flags);
+ }
+ err = 0;
+ } else
+ err = -EBUSY;
spin_unlock_irq(&mddev->write_lock);
} else {
mddev->ro = 0;
case active:
if (mddev->pers) {
restart_array(mddev);
- clear_bit(MD_CHANGE_CLEAN, &mddev->flags);
+ if (mddev->external)
+ clear_bit(MD_CHANGE_CLEAN, &mddev->flags);
wake_up(&mddev->sb_wait);
err = 0;
} else {
if (err < 0)
goto out;
}
- } else
+ } else if (mddev->external)
+ rdev = md_import_device(dev, -2, -1);
+ else
rdev = md_import_device(dev, -1, -1);
if (IS_ERR(rdev))
/* Metdata version.
- * This is either 'none' for arrays with externally managed metadata,
+ * This is one of
+ * 'none' for arrays with no metadata (good luck...)
+ * 'external' for arrays with externally managed metadata,
* or N.M for internally known formats
*/
static ssize_t
if (mddev->persistent)
return sprintf(page, "%d.%d\n",
mddev->major_version, mddev->minor_version);
+ else if (mddev->external)
+ return sprintf(page, "external:%s\n", mddev->metadata_type);
else
return sprintf(page, "none\n");
}
if (cmd_match(buf, "none")) {
mddev->persistent = 0;
+ mddev->external = 0;
+ mddev->major_version = 0;
+ mddev->minor_version = 90;
+ return len;
+ }
+ if (strncmp(buf, "external:", 9) == 0) {
+ size_t namelen = len-9;
+ if (namelen >= sizeof(mddev->metadata_type))
+ namelen = sizeof(mddev->metadata_type)-1;
+ strncpy(mddev->metadata_type, buf+9, namelen);
+ mddev->metadata_type[namelen] = 0;
+ if (namelen && mddev->metadata_type[namelen-1] == '\n')
+ mddev->metadata_type[--namelen] = 0;
+ mddev->persistent = 0;
+ mddev->external = 1;
mddev->major_version = 0;
mddev->minor_version = 90;
return len;
return -EINVAL;
buf = e+1;
minor = simple_strtoul(buf, &e, 10);
- if (e==buf || *e != '\n')
+ if (e==buf || (*e && *e != '\n') )
return -EINVAL;
- if (major >= sizeof(super_types)/sizeof(super_types[0]) ||
- super_types[major].name == NULL)
+ if (major >= ARRAY_SIZE(super_types) || super_types[major].name == NULL)
return -ENOENT;
mddev->major_version = major;
mddev->minor_version = minor;
mddev->persistent = 1;
+ mddev->external = 0;
return len;
}
{
char *type = "idle";
if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
- test_bit(MD_RECOVERY_NEEDED, &mddev->recovery)) {
+ (!mddev->ro && test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))) {
if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
type = "reshape";
else if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
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
+degraded_show(mddev_t *mddev, char *page)
+{
+ return sprintf(page, "%d\n", mddev->degraded);
+}
+static struct md_sysfs_entry md_degraded = __ATTR_RO(degraded);
static ssize_t
sync_speed_show(mddev_t *mddev, char *page)
static struct md_sysfs_entry md_sync_completed = __ATTR_RO(sync_completed);
static ssize_t
+max_sync_show(mddev_t *mddev, char *page)
+{
+ if (mddev->resync_max == MaxSector)
+ return sprintf(page, "max\n");
+ else
+ return sprintf(page, "%llu\n",
+ (unsigned long long)mddev->resync_max);
+}
+static ssize_t
+max_sync_store(mddev_t *mddev, const char *buf, size_t len)
+{
+ if (strncmp(buf, "max", 3) == 0)
+ mddev->resync_max = MaxSector;
+ else {
+ char *ep;
+ unsigned long long max = simple_strtoull(buf, &ep, 10);
+ if (ep == buf || (*ep != 0 && *ep != '\n'))
+ return -EINVAL;
+ if (max < mddev->resync_max &&
+ test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
+ return -EBUSY;
+
+ /* Must be a multiple of chunk_size */
+ if (mddev->chunk_size) {
+ if (max & (sector_t)((mddev->chunk_size>>9)-1))
+ return -EINVAL;
+ }
+ mddev->resync_max = max;
+ }
+ wake_up(&mddev->recovery_wait);
+ return len;
+}
+
+static struct md_sysfs_entry md_max_sync =
+__ATTR(sync_max, S_IRUGO|S_IWUSR, max_sync_show, max_sync_store);
+
+static ssize_t
suspend_lo_show(mddev_t *mddev, char *page)
{
return sprintf(page, "%llu\n", (unsigned long long)mddev->suspend_lo);
static struct md_sysfs_entry md_suspend_hi =
__ATTR(suspend_hi, S_IRUGO|S_IWUSR, suspend_hi_show, suspend_hi_store);
+static ssize_t
+reshape_position_show(mddev_t *mddev, char *page)
+{
+ if (mddev->reshape_position != MaxSector)
+ return sprintf(page, "%llu\n",
+ (unsigned long long)mddev->reshape_position);
+ strcpy(page, "none\n");
+ return 5;
+}
+
+static ssize_t
+reshape_position_store(mddev_t *mddev, const char *buf, size_t len)
+{
+ char *e;
+ unsigned long long new = simple_strtoull(buf, &e, 10);
+ if (mddev->pers)
+ return -EBUSY;
+ if (buf == e || (*e && *e != '\n'))
+ return -EINVAL;
+ mddev->reshape_position = new;
+ mddev->delta_disks = 0;
+ mddev->new_level = mddev->level;
+ mddev->new_layout = mddev->layout;
+ mddev->new_chunk = mddev->chunk_size;
+ return len;
+}
+
+static struct md_sysfs_entry md_reshape_position =
+__ATTR(reshape_position, S_IRUGO|S_IWUSR, reshape_position_show,
+ reshape_position_store);
+
static struct attribute *md_default_attrs[] = {
&md_level.attr,
&md_new_device.attr,
&md_safe_delay.attr,
&md_array_state.attr,
+ &md_reshape_position.attr,
NULL,
};
&md_sync_max.attr,
&md_sync_speed.attr,
&md_sync_completed.attr,
+ &md_max_sync.attr,
&md_suspend_lo.attr,
&md_suspend_hi.attr,
&md_bitmap.attr,
+ &md_degraded.attr,
NULL,
};
static struct attribute_group md_redundancy_group = {
int partitioned = (MAJOR(dev) != MD_MAJOR);
int shift = partitioned ? MdpMinorShift : 0;
int unit = MINOR(dev) >> shift;
+ int error;
if (!mddev)
return NULL;
add_disk(disk);
mddev->gendisk = disk;
mutex_unlock(&disks_mutex);
- 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);
+ error = kobject_init_and_add(&mddev->kobj, &md_ktype, &disk->dev.kobj,
+ "%s", "md");
+ if (error)
+ printk(KERN_WARNING "md: cannot register %s/md - name in use\n",
+ disk->disk_name);
+ else
+ kobject_uevent(&mddev->kobj, KOBJ_ADD);
return NULL;
}
/*
* Analyze all RAID superblock(s)
*/
- if (!mddev->raid_disks)
+ if (!mddev->raid_disks) {
+ if (!mddev->persistent)
+ return -EINVAL;
analyze_sbs(mddev);
+ }
chunk_size = mddev->chunk_size;
}
/* devices must have minimum size of one chunk */
- ITERATE_RDEV(mddev,rdev,tmp) {
+ rdev_for_each(rdev, tmp, mddev) {
if (test_bit(Faulty, &rdev->flags))
continue;
if (rdev->size < chunk_size / 1024) {
* Drop all container device buffers, from now on
* the only valid external interface is through the md
* device.
- * Also find largest hardsector size
*/
- ITERATE_RDEV(mddev,rdev,tmp) {
+ rdev_for_each(rdev, tmp, mddev) {
if (test_bit(Faulty, &rdev->flags))
continue;
sync_blockdev(rdev->bdev);
- invalidate_bdev(rdev->bdev, 0);
+ invalidate_bdev(rdev->bdev);
+
+ /* perform some consistency tests on the device.
+ * We don't want the data to overlap the metadata,
+ * Internal Bitmap issues has handled elsewhere.
+ */
+ if (rdev->data_offset < rdev->sb_offset) {
+ if (mddev->size &&
+ rdev->data_offset + mddev->size*2
+ > rdev->sb_offset*2) {
+ printk("md: %s: data overlaps metadata\n",
+ mdname(mddev));
+ return -EINVAL;
+ }
+ } else {
+ if (rdev->sb_offset*2 + rdev->sb_size/512
+ > rdev->data_offset) {
+ printk("md: %s: metadata overlaps data\n",
+ mdname(mddev));
+ return -EINVAL;
+ }
+ }
}
md_probe(mddev->unit, NULL, NULL);
return -EINVAL;
}
+ if (pers->sync_request) {
+ /* Warn if this is a potentially silly
+ * configuration.
+ */
+ char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
+ mdk_rdev_t *rdev2;
+ struct list_head *tmp2;
+ int warned = 0;
+ rdev_for_each(rdev, tmp, mddev) {
+ rdev_for_each(rdev2, tmp2, mddev) {
+ if (rdev < rdev2 &&
+ rdev->bdev->bd_contains ==
+ rdev2->bdev->bd_contains) {
+ printk(KERN_WARNING
+ "%s: WARNING: %s appears to be"
+ " on the same physical disk as"
+ " %s.\n",
+ mdname(mddev),
+ bdevname(rdev->bdev,b),
+ bdevname(rdev2->bdev,b2));
+ warned = 1;
+ }
+ }
+ }
+ if (warned)
+ printk(KERN_WARNING
+ "True protection against single-disk"
+ " failure might be compromised.\n");
+ }
+
mddev->recovery = 0;
mddev->resync_max_sectors = mddev->size << 1; /* may be over-ridden by personality */
mddev->barriers_work = 1;
bitmap_destroy(mddev);
return err;
}
- if (mddev->pers->sync_request)
- sysfs_create_group(&mddev->kobj, &md_redundancy_group);
- else if (mddev->ro == 2) /* auto-readonly not meaningful */
+ if (mddev->pers->sync_request) {
+ if (sysfs_create_group(&mddev->kobj, &md_redundancy_group))
+ printk(KERN_WARNING
+ "md: cannot register extra attributes for %s\n",
+ mdname(mddev));
+ } else if (mddev->ro == 2) /* auto-readonly not meaningful */
mddev->ro = 0;
atomic_set(&mddev->writes_pending,0);
mddev->safemode_delay = (200 * HZ)/1000 +1; /* 200 msec delay */
mddev->in_sync = 1;
- ITERATE_RDEV(mddev,rdev,tmp)
+ rdev_for_each(rdev, tmp, mddev)
if (rdev->raid_disk >= 0) {
char nm[20];
sprintf(nm, "rd%d", rdev->raid_disk);
- sysfs_create_link(&mddev->kobj, &rdev->kobj, nm);
+ if (sysfs_create_link(&mddev->kobj, &rdev->kobj, nm))
+ printk("md: cannot register %s for %s\n",
+ nm, mdname(mddev));
}
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
if (mddev->degraded && !mddev->sync_thread) {
struct list_head *rtmp;
int spares = 0;
- ITERATE_RDEV(mddev,rdev,rtmp)
+ rdev_for_each(rdev, rtmp, mddev)
if (rdev->raid_disk >= 0 &&
!test_bit(In_sync, &rdev->flags) &&
!test_bit(Faulty, &rdev->flags))
mddev->changed = 1;
md_new_event(mddev);
- kobject_uevent(&mddev->gendisk->kobj, KOBJ_CHANGE);
+ kobject_uevent(&mddev->gendisk->dev.kobj, KOBJ_CHANGE);
return 0;
}
set_disk_ro(disk, 0);
blk_queue_make_request(mddev->queue, md_fail_request);
mddev->pers->stop(mddev);
+ mddev->queue->merge_bvec_fn = NULL;
+ mddev->queue->unplug_fn = NULL;
+ mddev->queue->backing_dev_info.congested_fn = NULL;
if (mddev->pers->sync_request)
sysfs_remove_group(&mddev->kobj, &md_redundancy_group);
module_put(mddev->pers->owner);
mddev->pers = NULL;
+
+ set_capacity(disk, 0);
+ mddev->changed = 1;
+
if (mddev->ro)
mddev->ro = 0;
}
if (mode == 0) {
mdk_rdev_t *rdev;
struct list_head *tmp;
- struct gendisk *disk;
+
printk(KERN_INFO "md: %s stopped.\n", mdname(mddev));
bitmap_destroy(mddev);
}
mddev->bitmap_offset = 0;
- ITERATE_RDEV(mddev,rdev,tmp)
+ rdev_for_each(rdev, tmp, mddev)
if (rdev->raid_disk >= 0) {
char nm[20];
sprintf(nm, "rd%d", rdev->raid_disk);
sysfs_remove_link(&mddev->kobj, nm);
}
+ /* make sure all md_delayed_delete calls have finished */
+ flush_scheduled_work();
+
export_array(mddev);
mddev->array_size = 0;
mddev->size = 0;
mddev->raid_disks = 0;
mddev->recovery_cp = 0;
+ mddev->resync_max = MaxSector;
+ mddev->reshape_position = MaxSector;
+ mddev->external = 0;
+ mddev->persistent = 0;
- disk = mddev->gendisk;
- if (disk)
- set_capacity(disk, 0);
- mddev->changed = 1;
} else if (mddev->pers)
printk(KERN_INFO "md: %s switched to read-only mode.\n",
mdname(mddev));
return err;
}
+#ifndef MODULE
static void autorun_array(mddev_t *mddev)
{
mdk_rdev_t *rdev;
printk(KERN_INFO "md: running: ");
- ITERATE_RDEV(mddev,rdev,tmp) {
+ rdev_for_each(rdev, tmp, mddev) {
char b[BDEVNAME_SIZE];
printk("<%s>", bdevname(rdev->bdev,b));
}
printk(KERN_INFO "md: considering %s ...\n",
bdevname(rdev0->bdev,b));
INIT_LIST_HEAD(&candidates);
- ITERATE_RDEV_PENDING(rdev,tmp)
+ rdev_for_each_list(rdev, tmp, pending_raid_disks)
if (super_90_load(rdev, rdev0, 0) >= 0) {
printk(KERN_INFO "md: adding %s ...\n",
bdevname(rdev->bdev,b));
mddev_unlock(mddev);
} else {
printk(KERN_INFO "md: created %s\n", mdname(mddev));
- ITERATE_RDEV_GENERIC(candidates,rdev,tmp) {
+ mddev->persistent = 1;
+ rdev_for_each_list(rdev, tmp, candidates) {
list_del_init(&rdev->same_set);
if (bind_rdev_to_array(rdev, mddev))
export_rdev(rdev);
/* on success, candidates will be empty, on error
* it won't...
*/
- ITERATE_RDEV_GENERIC(candidates,rdev,tmp)
+ rdev_for_each_list(rdev, tmp, candidates)
export_rdev(rdev);
mddev_put(mddev);
}
printk(KERN_INFO "md: ... autorun DONE.\n");
}
+#endif /* !MODULE */
static int get_version(void __user * arg)
{
struct list_head *tmp;
nr=working=active=failed=spare=0;
- ITERATE_RDEV(mddev,rdev,tmp) {
+ rdev_for_each(rdev, tmp, mddev) {
nr++;
if (test_bit(Faulty, &rdev->flags))
failed++;
char *ptr, *buf = NULL;
int err = -ENOMEM;
+ md_allow_write(mddev);
+
file = kmalloc(sizeof(*file), GFP_KERNEL);
if (!file)
goto out;
if (err)
export_rdev(rdev);
+ md_update_sb(mddev, 1);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
return err;
else
rdev->raid_disk = -1;
- rdev->flags = 0;
-
if (rdev->raid_disk < mddev->raid_disks)
if (info->state & (1<<MD_DISK_SYNC))
set_bit(In_sync, &rdev->flags);
if (info->raid_disks == 0) {
/* just setting version number for superblock loading */
if (info->major_version < 0 ||
- info->major_version >= sizeof(super_types)/sizeof(super_types[0]) ||
+ info->major_version >= ARRAY_SIZE(super_types) ||
super_types[info->major_version].name == NULL) {
/* maybe try to auto-load a module? */
printk(KERN_INFO
mddev->major_version = info->major_version;
mddev->minor_version = info->minor_version;
mddev->patch_version = info->patch_version;
+ mddev->persistent = !info->not_persistent;
return 0;
}
mddev->major_version = MD_MAJOR_VERSION;
else
mddev->recovery_cp = 0;
mddev->persistent = ! info->not_persistent;
+ mddev->external = 0;
mddev->layout = info->layout;
mddev->chunk_size = info->chunk_size;
mddev->max_disks = MD_SB_DISKS;
- mddev->flags = 0;
+ if (mddev->persistent)
+ mddev->flags = 0;
set_bit(MD_CHANGE_DEVS, &mddev->flags);
mddev->default_bitmap_offset = MD_SB_BYTES >> 9;
*/
if (mddev->sync_thread)
return -EBUSY;
- ITERATE_RDEV(mddev,rdev,tmp) {
+ rdev_for_each(rdev, tmp, mddev) {
sector_t avail;
avail = rdev->size * 2;
* Commands querying/configuring an existing array:
*/
/* if we are not initialised yet, only ADD_NEW_DISK, STOP_ARRAY,
- * RUN_ARRAY, and SET_BITMAP_FILE are allowed */
- if (!mddev->raid_disks && cmd != ADD_NEW_DISK && cmd != STOP_ARRAY
- && cmd != RUN_ARRAY && cmd != SET_BITMAP_FILE) {
+ * RUN_ARRAY, and GET_ and SET_BITMAP_FILE are allowed */
+ if ((!mddev->raid_disks && !mddev->external)
+ && cmd != ADD_NEW_DISK && cmd != STOP_ARRAY
+ && cmd != RUN_ARRAY && cmd != SET_BITMAP_FILE
+ && cmd != GET_BITMAP_FILE) {
err = -ENODEV;
goto abort_unlock;
}
mddev_t *mddev = inode->i_bdev->bd_disk->private_data;
int err;
- if ((err = mddev_lock(mddev)))
+ if ((err = mutex_lock_interruptible_nested(&mddev->reconfig_mutex, 1)))
goto out;
err = 0;
* many dirty RAID5 blocks.
*/
- current->flags |= PF_NOFREEZE;
allow_signal(SIGKILL);
while (!kthread_should_stop()) {
void md_unregister_thread(mdk_thread_t *thread)
{
- dprintk("interrupting MD-thread pid %d\n", thread->tsk->pid);
+ dprintk("interrupting MD-thread pid %d\n", task_pid_nr(thread->tsk));
kthread_stop(thread->tsk);
kfree(thread);
seq_printf(seq, "unused devices: ");
- ITERATE_RDEV_PENDING(rdev,tmp) {
+ rdev_for_each_list(rdev, tmp, pending_raid_disks) {
char b[BDEVNAME_SIZE];
i++;
seq_printf(seq, "%s ",
if (mddev->ro==1)
seq_printf(seq, " (read-only)");
if (mddev->ro==2)
- seq_printf(seq, "(auto-read-only)");
+ seq_printf(seq, " (auto-read-only)");
seq_printf(seq, " %s", mddev->pers->name);
}
size = 0;
- ITERATE_RDEV(mddev,rdev,tmp2) {
+ rdev_for_each(rdev, tmp2, mddev) {
char b[BDEVNAME_SIZE];
seq_printf(seq, " %s[%d]",
bdevname(rdev->bdev,b), rdev->desc_nr);
mddev->major_version,
mddev->minor_version);
}
- } else
+ } else if (mddev->external)
+ seq_printf(seq, " super external:%s",
+ mddev->metadata_type);
+ else
seq_printf(seq, " super non-persistent");
if (mddev->pers) {
chunk_kb ? "KB" : "B");
if (bitmap->file) {
seq_printf(seq, ", file: ");
- seq_path(seq, bitmap->file->f_vfsmnt,
- bitmap->file->f_dentry," \t\n");
+ seq_path(seq, &bitmap->file->f_path, " \t\n");
}
seq_printf(seq, "\n");
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;
return mask;
}
-static struct file_operations md_seq_fops = {
+static const struct file_operations md_seq_fops = {
.owner = THIS_MODULE,
.open = md_seq_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = md_seq_release,
+ .release = seq_release_private,
.poll = mdstat_poll,
};
mdk_rdev_t * rdev;
struct list_head *tmp;
int idle;
- unsigned long curr_events;
+ long curr_events;
idle = 1;
- ITERATE_RDEV(mddev,rdev,tmp) {
+ rdev_for_each(rdev, tmp, mddev) {
struct gendisk *disk = rdev->bdev->bd_contains->bd_disk;
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.
+ /* sync IO will cause sync_io to increase before the disk_stats
+ * as sync_io is counted when a request starts, and
+ * disk_stats is counted when it completes.
+ * So resync activity will cause curr_events to be smaller than
+ * when there was no such activity.
+ * non-sync IO will cause disk_stat to increase without
+ * increasing sync_io so curr_events will (eventually)
+ * be larger than it was before. Once it becomes
+ * substantially larger, the test below will cause
+ * the array to appear non-idle, and resync will slow
+ * down.
+ * If there is a lot of outstanding resync activity when
+ * we set last_event to curr_events, then all that activity
+ * completing might cause the array to appear non-idle
+ * and resync will be slowed down even though there might
+ * not have been non-resync activity. This will only
+ * happen once though. 'last_events' will soon reflect
+ * the state where there is little or no outstanding
+ * resync requests, and further resync activity will
+ * always make curr_events less than last_events.
*
- * Note: the following is an unsigned comparison.
*/
- if ((curr_events - rdev->last_events + 4096) > 8192) {
+ if (curr_events - rdev->last_events > 4096) {
rdev->last_events = curr_events;
idle = 0;
}
mddev->ro = 0;
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
+ md_wakeup_thread(mddev->sync_thread);
}
atomic_inc(&mddev->writes_pending);
if (mddev->in_sync) {
}
}
+/* md_allow_write(mddev)
+ * Calling this ensures that the array is marked 'active' so that writes
+ * may proceed without blocking. It is important to call this before
+ * attempting a GFP_KERNEL allocation while holding the mddev lock.
+ * Must be called with mddev_lock held.
+ */
+void md_allow_write(mddev_t *mddev)
+{
+ if (!mddev->pers)
+ return;
+ if (mddev->ro)
+ return;
+
+ spin_lock_irq(&mddev->write_lock);
+ if (mddev->in_sync) {
+ mddev->in_sync = 0;
+ set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+ if (mddev->safemode_delay &&
+ mddev->safemode == 0)
+ mddev->safemode = 1;
+ spin_unlock_irq(&mddev->write_lock);
+ md_update_sb(mddev, 0);
+ } else
+ spin_unlock_irq(&mddev->write_lock);
+}
+EXPORT_SYMBOL_GPL(md_allow_write);
+
static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
#define SYNC_MARKS 10
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
goto skip;
}
- ITERATE_MDDEV(mddev2,tmp) {
+ for_each_mddev(mddev2, tmp) {
if (mddev2 == mddev)
continue;
if (mddev2->curr_resync &&
/* recovery follows the physical size of devices */
max_sectors = mddev->size << 1;
j = MaxSector;
- ITERATE_RDEV(mddev,rdev,rtmp)
+ rdev_for_each(rdev, rtmp, mddev)
if (rdev->raid_disk >= 0 &&
!test_bit(Faulty, &rdev->flags) &&
!test_bit(In_sync, &rdev->flags) &&
sector_t sectors;
skipped = 0;
+ if (j >= mddev->resync_max) {
+ sysfs_notify(&mddev->kobj, NULL, "sync_completed");
+ wait_event(mddev->recovery_wait,
+ mddev->resync_max > j
+ || kthread_should_stop());
+ }
+ if (kthread_should_stop())
+ goto interrupted;
sectors = mddev->pers->sync_request(mddev, j, &skipped,
- currspeed < speed_min(mddev));
+ currspeed < speed_min(mddev));
if (sectors == 0) {
set_bit(MD_RECOVERY_ERR, &mddev->recovery);
goto out;
}
- if (kthread_should_stop()) {
- /*
- * got a signal, exit.
- */
- printk(KERN_INFO
- "md: md_do_sync() got signal ... exiting\n");
- set_bit(MD_RECOVERY_INTR, &mddev->recovery);
- goto out;
- }
+ if (kthread_should_stop())
+ goto interrupted;
+
/*
* this loop exits only if either when we are slower than
* about not overloading the IO subsystem. (things like an
* e2fsck being done on the RAID array should execute fast)
*/
- mddev->queue->unplug_fn(mddev->queue);
+ blk_unplug(mddev->queue);
cond_resched();
currspeed = ((unsigned long)(io_sectors-mddev->resync_mark_cnt))/2
* this also signals 'finished resyncing' to md_stop
*/
out:
- mddev->queue->unplug_fn(mddev->queue);
+ blk_unplug(mddev->queue);
wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active));
mddev->pers->sync_request(mddev, max_sectors, &skipped, 1);
if (!test_bit(MD_RECOVERY_ERR, &mddev->recovery) &&
- test_bit(MD_RECOVERY_SYNC, &mddev->recovery) &&
!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) &&
mddev->curr_resync > 2) {
if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
} else {
if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery))
mddev->curr_resync = MaxSector;
- ITERATE_RDEV(mddev,rdev,rtmp)
+ rdev_for_each(rdev, rtmp, mddev)
if (rdev->raid_disk >= 0 &&
!test_bit(Faulty, &rdev->flags) &&
!test_bit(In_sync, &rdev->flags) &&
rdev->recovery_offset = mddev->curr_resync;
}
}
+ set_bit(MD_CHANGE_DEVS, &mddev->flags);
skip:
mddev->curr_resync = 0;
+ mddev->resync_max = MaxSector;
+ sysfs_notify(&mddev->kobj, NULL, "sync_completed");
wake_up(&resync_wait);
set_bit(MD_RECOVERY_DONE, &mddev->recovery);
md_wakeup_thread(mddev->thread);
+ return;
+
+ interrupted:
+ /*
+ * got a signal, exit.
+ */
+ printk(KERN_INFO
+ "md: md_do_sync() got signal ... exiting\n");
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+ goto out;
+
}
EXPORT_SYMBOL_GPL(md_do_sync);
+static int remove_and_add_spares(mddev_t *mddev)
+{
+ mdk_rdev_t *rdev;
+ struct list_head *rtmp;
+ int spares = 0;
+
+ rdev_for_each(rdev, rtmp, mddev)
+ if (rdev->raid_disk >= 0 &&
+ !mddev->external &&
+ (test_bit(Faulty, &rdev->flags) ||
+ ! test_bit(In_sync, &rdev->flags)) &&
+ atomic_read(&rdev->nr_pending)==0) {
+ if (mddev->pers->hot_remove_disk(
+ mddev, rdev->raid_disk)==0) {
+ char nm[20];
+ sprintf(nm,"rd%d", rdev->raid_disk);
+ sysfs_remove_link(&mddev->kobj, nm);
+ rdev->raid_disk = -1;
+ }
+ }
+
+ if (mddev->degraded) {
+ rdev_for_each(rdev, rtmp, mddev)
+ if (rdev->raid_disk < 0
+ && !test_bit(Faulty, &rdev->flags)) {
+ rdev->recovery_offset = 0;
+ if (mddev->pers->hot_add_disk(mddev,rdev)) {
+ char nm[20];
+ sprintf(nm, "rd%d", rdev->raid_disk);
+ if (sysfs_create_link(&mddev->kobj,
+ &rdev->kobj, nm))
+ printk(KERN_WARNING
+ "md: cannot register "
+ "%s for %s\n",
+ nm, mdname(mddev));
+ spares++;
+ md_new_event(mddev);
+ } else
+ break;
+ }
+ }
+ return spares;
+}
/*
* This routine is regularly called by all per-raid-array threads to
* deal with generic issues like resync and super-block update.
}
if ( ! (
- mddev->flags ||
+ (mddev->flags && !mddev->external) ||
test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) ||
test_bit(MD_RECOVERY_DONE, &mddev->recovery) ||
(mddev->safemode == 1) ||
return;
if (mddev_trylock(mddev)) {
- int spares =0;
+ int spares = 0;
spin_lock_irq(&mddev->write_lock);
if (mddev->safemode && !atomic_read(&mddev->writes_pending) &&
!mddev->in_sync && mddev->recovery_cp == MaxSector) {
mddev->in_sync = 1;
- set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+ if (mddev->persistent)
+ set_bit(MD_CHANGE_CLEAN, &mddev->flags);
}
if (mddev->safemode == 1)
mddev->safemode = 0;
* information must be scrapped
*/
if (!mddev->degraded)
- ITERATE_RDEV(mddev,rdev,rtmp)
+ rdev_for_each(rdev, rtmp, mddev)
rdev->saved_raid_disk = -1;
mddev->recovery = 0;
* Spare are also removed and re-added, to allow
* the personality to fail the re-add.
*/
- ITERATE_RDEV(mddev,rdev,rtmp)
- if (rdev->raid_disk >= 0 &&
- (test_bit(Faulty, &rdev->flags) || ! test_bit(In_sync, &rdev->flags)) &&
- atomic_read(&rdev->nr_pending)==0) {
- if (mddev->pers->hot_remove_disk(mddev, rdev->raid_disk)==0) {
- char nm[20];
- sprintf(nm,"rd%d", rdev->raid_disk);
- sysfs_remove_link(&mddev->kobj, nm);
- rdev->raid_disk = -1;
- }
- }
- if (mddev->degraded) {
- ITERATE_RDEV(mddev,rdev,rtmp)
- if (rdev->raid_disk < 0
- && !test_bit(Faulty, &rdev->flags)) {
- rdev->recovery_offset = 0;
- if (mddev->pers->hot_add_disk(mddev,rdev)) {
- char nm[20];
- sprintf(nm, "rd%d", rdev->raid_disk);
- sysfs_create_link(&mddev->kobj, &rdev->kobj, nm);
- spares++;
- md_new_event(mddev);
- } else
- break;
- }
- }
-
- if (spares) {
+ if (mddev->reshape_position != MaxSector) {
+ if (mddev->pers->check_reshape(mddev) != 0)
+ /* Cannot proceed */
+ goto unlock;
+ set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
+ } else if ((spares = remove_and_add_spares(mddev))) {
clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
} else if (mddev->recovery_cp < MaxSector) {
printk(KERN_INFO "md: stopping all md devices.\n");
- ITERATE_MDDEV(mddev,tmp)
+ for_each_mddev(mddev, tmp)
if (mddev_trylock(mddev)) {
do_md_stop (mddev, 1);
mddev_unlock(mddev);
md_probe, NULL, NULL);
register_reboot_notifier(&md_notifier);
- raid_table_header = register_sysctl_table(raid_root_table, 1);
+ raid_table_header = register_sysctl_table(raid_root_table);
md_geninit();
return (0);
* Searches all registered partitions for autorun RAID arrays
* at boot time.
*/
-static dev_t detected_devices[128];
-static int dev_cnt;
+
+static LIST_HEAD(all_detected_devices);
+struct detected_devices_node {
+ struct list_head list;
+ dev_t dev;
+};
void md_autodetect_dev(dev_t dev)
{
- if (dev_cnt >= 0 && dev_cnt < 127)
- detected_devices[dev_cnt++] = dev;
+ struct detected_devices_node *node_detected_dev;
+
+ node_detected_dev = kzalloc(sizeof(*node_detected_dev), GFP_KERNEL);
+ if (node_detected_dev) {
+ node_detected_dev->dev = dev;
+ list_add_tail(&node_detected_dev->list, &all_detected_devices);
+ } else {
+ printk(KERN_CRIT "md: md_autodetect_dev: kzalloc failed"
+ ", skipping dev(%d,%d)\n", MAJOR(dev), MINOR(dev));
+ }
}
static void autostart_arrays(int part)
{
mdk_rdev_t *rdev;
- int i;
+ struct detected_devices_node *node_detected_dev;
+ dev_t dev;
+ int i_scanned, i_passed;
- printk(KERN_INFO "md: Autodetecting RAID arrays.\n");
+ i_scanned = 0;
+ i_passed = 0;
- for (i = 0; i < dev_cnt; i++) {
- dev_t dev = detected_devices[i];
+ printk(KERN_INFO "md: Autodetecting RAID arrays.\n");
- rdev = md_import_device(dev,0, 0);
+ while (!list_empty(&all_detected_devices) && i_scanned < INT_MAX) {
+ i_scanned++;
+ node_detected_dev = list_entry(all_detected_devices.next,
+ struct detected_devices_node, list);
+ list_del(&node_detected_dev->list);
+ dev = node_detected_dev->dev;
+ kfree(node_detected_dev);
+ rdev = md_import_device(dev,0, 90);
if (IS_ERR(rdev))
continue;
MD_BUG();
continue;
}
+ set_bit(AutoDetected, &rdev->flags);
list_add(&rdev->same_set, &pending_raid_disks);
+ i_passed++;
}
- dev_cnt = 0;
+
+ printk(KERN_INFO "md: Scanned %d and added %d devices.\n",
+ i_scanned, i_passed);
autorun_devices(part);
}
-#endif
+#endif /* !MODULE */
static __exit void md_exit(void)
{
unregister_reboot_notifier(&md_notifier);
unregister_sysctl_table(raid_table_header);
remove_proc_entry("mdstat", NULL);
- ITERATE_MDDEV(mddev,tmp) {
+ for_each_mddev(mddev, tmp) {
struct gendisk *disk = mddev->gendisk;
if (!disk)
continue;
}
}
-module_init(md_init)
+subsys_initcall(md_init);
module_exit(md_exit)
static int get_ro(char *buffer, struct kernel_param *kp)
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff