#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>
static void autostart_arrays (int part);
#endif
-static mdk_personality_t *pers[MAX_PERSONALITY];
+static LIST_HEAD(pers_list);
static DEFINE_SPINLOCK(pers_lock);
/*
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.
}
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);
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;
}
+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;
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(rdev->mddev, rdev);
+ md_error(mddev, rdev);
- if (atomic_dec_and_test(&rdev->mddev->pending_writes))
- wake_up(&rdev->mddev->sb_wait);
+ 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)
{
* 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);
- submit_bio((1<<BIO_RW)|(1<<BIO_RW_SYNC), bio);
+ 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)
bio_put(bio);
return ret;
}
+EXPORT_SYMBOL_GPL(sync_page_io);
static int read_disk_sb(mdk_rdev_t * rdev, int size)
{
mdp_super_t *sb = (mdp_super_t *)page_address(rdev->sb_page);
rdev->raid_disk = -1;
- rdev->in_sync = 0;
+ 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;
if (sb->state & (1<<MD_SB_BITMAP_PRESENT) &&
mddev->bitmap_file == NULL) {
- if (mddev->level != 1 && mddev->level != 5 && mddev->level != 6) {
+ if (mddev->level != 1 && mddev->level != 5 && mddev->level != 6
+ && mddev->level != 10) {
/* FIXME use a better test */
- printk(KERN_WARNING "md: bitmaps only support for raid1\n");
+ printk(KERN_WARNING "md: bitmaps not supported for this level.\n");
return -EINVAL;
}
mddev->bitmap_offset = mddev->default_bitmap_offset;
return 0;
if (mddev->level != LEVEL_MULTIPATH) {
- rdev->faulty = 0;
- rdev->flags = 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 */
- rdev->in_sync = 1;
+ 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;
- unsigned int fixdesc=0;
rdev->sb_size = MD_SB_BYTES;
ITERATE_RDEV(mddev,rdev2,tmp) {
mdp_disk_t *d;
int desc_nr;
- if (rdev2->raid_disk >= 0 && rdev2->in_sync && !rdev2->faulty)
+ if (rdev2->raid_disk >= 0 && test_bit(In_sync, &rdev2->flags)
+ && !test_bit(Faulty, &rdev2->flags))
desc_nr = rdev2->raid_disk;
else
desc_nr = next_spare++;
- if (desc_nr != rdev2->desc_nr) {
- fixdesc |= (1 << desc_nr);
- rdev2->desc_nr = desc_nr;
- if (rdev2->raid_disk >= 0) {
- char nm[20];
- sprintf(nm, "rd%d", rdev2->raid_disk);
- sysfs_remove_link(&mddev->kobj, nm);
- }
- sysfs_remove_link(&rdev2->kobj, "block");
- kobject_del(&rdev2->kobj);
- }
+ 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 && rdev2->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++;
if (test_bit(WriteMostly, &rdev2->flags))
d->state |= (1<<MD_DISK_WRITEMOSTLY);
}
- if (fixdesc)
- ITERATE_RDEV(mddev,rdev2,tmp)
- if (fixdesc & (1<<rdev2->desc_nr)) {
- snprintf(rdev2->kobj.name, KOBJ_NAME_LEN, "dev%d",
- rdev2->desc_nr);
- kobject_add(&rdev2->kobj);
- sysfs_create_link(&rdev2->kobj,
- &rdev2->bdev->bd_disk->kobj,
- "block");
- if (rdev2->raid_disk >= 0) {
- char nm[20];
- sprintf(nm, "rd%d", rdev2->raid_disk);
- sysfs_create_link(&mddev->kobj,
- &rdev2->kobj, nm);
- }
- }
/* 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];
}
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;
struct mdp_superblock_1 *sb = (struct mdp_superblock_1*)page_address(rdev->sb_page);
rdev->raid_disk = -1;
- rdev->in_sync = 0;
+ rdev->flags = 0;
if (mddev->raid_disks == 0) {
mddev->major_version = 1;
mddev->patch_version = 0;
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 = le64_to_cpu(sb->size)/2;
mddev->events = le64_to_cpu(sb->events);
mddev->bitmap_offset = 0;
- mddev->default_bitmap_offset = 0;
mddev->default_bitmap_offset = 1024;
mddev->recovery_cp = le64_to_cpu(sb->resync_offset);
if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET) &&
mddev->bitmap_file == NULL ) {
- if (mddev->level != 1) {
- printk(KERN_WARNING "md: bitmaps only supported for raid1\n");
+ 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);
role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
switch(role) {
case 0xffff: /* spare */
- rdev->faulty = 0;
break;
case 0xfffe: /* faulty */
- rdev->faulty = 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;
}
- rdev->flags = 0;
if (sb->devflags & WriteMostly1)
set_bit(WriteMostly, &rdev->flags);
} else /* MULTIPATH are always insync */
- rdev->in_sync = 1;
+ 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);
+
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);
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);
{
mdk_rdev_t *same_pdev;
char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
+ struct kobject *ko;
if (rdev->mddev) {
MD_BUG();
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;
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.k_name = NULL;
- snprintf(rdev->kobj.name, KOBJ_NAME_LEN, "dev%d", rdev->desc_nr);
- rdev->kobj.parent = kobject_get(&mddev->kobj);
+ rdev->kobj.parent = &mddev->kobj;
kobject_add(&rdev->kobj);
- sysfs_create_link(&rdev->kobj, &rdev->bdev->bd_disk->kobj, "block");
+ 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;
}
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));
int sync_req;
repeat:
- spin_lock(&mddev->write_lock);
+ spin_lock_irq(&mddev->write_lock);
sync_req = mddev->in_sync;
mddev->utime = get_seconds();
mddev->events ++;
*/
if (!mddev->persistent) {
mddev->sb_dirty = 0;
- spin_unlock(&mddev->write_lock);
+ spin_unlock_irq(&mddev->write_lock);
wake_up(&mddev->sb_wait);
return;
}
- spin_unlock(&mddev->write_lock);
+ spin_unlock_irq(&mddev->write_lock);
dprintk(KERN_INFO
"md: updating %s RAID superblock on device (in sync %d)\n",
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) {
+ if (!test_bit(Faulty, &rdev->flags)) {
md_super_write(mddev,rdev,
rdev->sb_offset<<1, rdev->sb_size,
rdev->sb_page);
/* only need to write one superblock... */
break;
}
- wait_event(mddev->sb_wait, atomic_read(&mddev->pending_writes)==0);
+ md_super_wait(mddev);
/* if there was a failure, sb_dirty was set to 1, and we re-write super */
- spin_lock(&mddev->write_lock);
+ spin_lock_irq(&mddev->write_lock);
if (mddev->in_sync != sync_req|| mddev->sb_dirty == 1) {
/* have to write it out again */
- spin_unlock(&mddev->write_lock);
+ spin_unlock_irq(&mddev->write_lock);
goto repeat;
}
mddev->sb_dirty = 0;
- spin_unlock(&mddev->write_lock);
+ 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 *);
};
static ssize_t
-rdev_show_state(mdk_rdev_t *rdev, char *page)
+state_show(mdk_rdev_t *rdev, char *page)
{
char *sep = "";
int len=0;
- if (rdev->faulty) {
+ if (test_bit(Faulty, &rdev->flags)) {
len+= sprintf(page+len, "%sfaulty",sep);
sep = ",";
}
- if (rdev->in_sync) {
+ if (test_bit(In_sync, &rdev->flags)) {
len += sprintf(page+len, "%sin_sync",sep);
sep = ",";
}
- if (!rdev->faulty && !rdev->in_sync) {
+ 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 = {.name = "state", .mode = S_IRUGO },
- .show = rdev_show_state,
-};
+static struct rdev_sysfs_entry
+rdev_state = __ATTR_RO(state);
static ssize_t
-rdev_show_super(mdk_rdev_t *rdev, char *page)
+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);
} else
return 0;
}
-static struct rdev_sysfs_entry rdev_super = {
- .attr = {.name = "super", .mode = S_IRUGO },
- .show = rdev_show_super,
-};
+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 struct attribute *rdev_default_attrs[] = {
&rdev_state.attr,
&rdev_super.attr,
+ &rdev_errors.attr,
NULL,
};
static ssize_t
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 new device!\n");
return ERR_PTR(-ENOMEM);
}
- memset(rdev, 0, sizeof(*rdev));
if ((err = alloc_disk_sb(rdev)))
goto abort_free;
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) {
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);
}
}
}
-struct md_sysfs_entry {
- struct attribute attr;
- ssize_t (*show)(mddev_t *, char *);
- ssize_t (*store)(mddev_t *, const char *, size_t);
-};
+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 ssize_t
-md_show_level(mddev_t *mddev, char *page)
+level_store(mddev_t *mddev, const char *buf, size_t len)
{
- mdk_personality_t *p = mddev->pers;
- if (p == NULL)
+ int rv = len;
+ if (mddev->pers)
+ return -EBUSY;
+ if (len == 0)
return 0;
- if (mddev->level >= 0)
- return sprintf(page, "RAID-%d\n", mddev->level);
- else
- return sprintf(page, "%s\n", p->name);
+ 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;
}
-static struct md_sysfs_entry md_level = {
- .attr = {.name = "level", .mode = S_IRUGO },
- .show = md_show_level,
-};
+static struct md_sysfs_entry md_level =
+__ATTR(level, 0644, level_show, level_store);
static ssize_t
-md_show_rdisks(mddev_t *mddev, char *page)
+raid_disks_show(mddev_t *mddev, char *page)
{
+ if (mddev->raid_disks == 0)
+ return 0;
return sprintf(page, "%d\n", mddev->raid_disks);
}
-static struct md_sysfs_entry md_raid_disks = {
- .attr = {.name = "raid_disks", .mode = S_IRUGO },
- .show = md_show_rdisks,
-};
+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
+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
-md_show_scan(mddev_t *mddev, char *page)
+metadata_store(mddev_t *mddev, const char *buf, size_t len)
{
- char *type = "none";
- if (mddev->recovery &
- ((1<<MD_RECOVERY_RUNNING) || (1<<MD_RECOVERY_NEEDED))) {
- if (mddev->recovery & (1<<MD_RECOVERY_SYNC)) {
+ 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))
}
static ssize_t
-md_store_scan(mddev_t *mddev, const char *page, size_t len)
+action_store(mddev_t *mddev, const char *page, size_t len)
{
- int canscan=0;
- if (mddev->recovery &
- ((1<<MD_RECOVERY_RUNNING) || (1<<MD_RECOVERY_NEEDED)))
- return -EBUSY;
- down(&mddev->reconfig_sem);
- if (mddev->pers && mddev->pers->sync_request)
- canscan=1;
- up(&mddev->reconfig_sem);
- if (!canscan)
+ if (!mddev->pers || !mddev->pers->sync_request)
return -EINVAL;
- if (strcmp(page, "check")==0 || strcmp(page, "check\n")==0)
- set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
- else if (strcmp(page, "repair")!=0 && strcmp(page, "repair\n")!=0)
- return -EINVAL;
- set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
- set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+ 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
-md_show_mismatch(mddev_t *mddev, char *page)
+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 = {.name = "scan_mode", .mode = S_IRUGO|S_IWUSR },
- .show = md_show_scan,
- .store = md_store_scan,
-};
+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 = {.name = "mismatch_cnt", .mode = S_IRUGO },
- .show = md_show_mismatch,
-};
+
+static struct md_sysfs_entry
+md_mismatches = __ATTR_RO(mismatch_cnt);
static struct attribute *md_default_attrs[] = {
&md_level.attr,
&md_raid_disks.attr,
+ &md_chunk_size.attr,
+ &md_size.attr,
+ &md_metadata.attr,
+ NULL,
+};
+
+static struct attribute *md_redundancy_attrs[] = {
&md_scan_mode.attr,
&md_mismatches.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;
- return entry->show(mddev, page);
+ mddev_lock(mddev);
+ rv = entry->show(mddev, page);
+ mddev_unlock(mddev);
+ return rv;
}
static ssize_t
{
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;
- return entry->store(mddev, page, length);
+ mddev_lock(mddev);
+ rv = entry->store(mddev, page, length);
+ mddev_unlock(mddev);
+ return rv;
}
static void md_free(struct kobject *ko)
add_disk(disk);
mddev->gendisk = disk;
up(&disks_sem);
- mddev->kobj.parent = kobject_get(&disk->kobj);
+ mddev->kobj.parent = &disk->kobj;
mddev->kobj.k_name = NULL;
snprintf(mddev->kobj.name, KOBJ_NAME_LEN, "%s", "md");
mddev->kobj.ktype = &md_ktype;
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))
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);
/* 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
}
#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;
- /* before we start the array running, initialise the bitmap */
- err = bitmap_create(mddev);
- if (err)
- printk(KERN_ERR "%s: failed to create bitmap (%d)\n",
- mdname(mddev), err);
- else
- err = mddev->pers->run(mddev);
+ 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);
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->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);
- wait_event(mddev->sb_wait, atomic_read(&mddev->pending_writes)==0);
+ 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)
printk(KERN_INFO "md: %s switched to read-only mode.\n",
mdname(mddev));
err = 0;
+ md_new_event(mddev);
out:
return err;
}
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));
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.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);
}
validate_super(mddev, rdev);
rdev->saved_raid_disk = rdev->raid_disk;
- rdev->in_sync = 0; /* just to be sure */
+ clear_bit(In_sync, &rdev->flags); /* just to be sure */
if (info->state & (1<<MD_DISK_WRITEMOSTLY))
set_bit(WriteMostly, &rdev->flags);
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);
if (info->state & (1<<MD_DISK_WRITEMOSTLY))
set_bit(WriteMostly, &rdev->flags);
kick_rdev_from_array(rdev);
md_update_sb(mddev);
+ md_new_event(mddev);
return 0;
busy:
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);
*/
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
-
+ md_new_event(mddev);
return 0;
abort_unbind_export:
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;
+
+ 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;
+ int fit = (size == 0);
+ 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) {
+ down(&bdev->bd_inode->i_sem);
+ i_size_write(bdev->bd_inode, mddev->array_size << 10);
+ up(&bdev->bd_inode->i_sem);
+ 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);
+ if (!rv) {
+ struct block_device *bdev;
+
+ bdev = bdget_disk(mddev->gendisk, 0);
+ if (bdev) {
+ down(&bdev->bd_inode->i_sem);
+ i_size_write(bdev->bd_inode, mddev->array_size << 10);
+ up(&bdev->bd_inode->i_sem);
+ bdput(bdev);
+ }
+ }
+ return rv;
+}
+
+
/*
* update_array_info is used to change the configuration of an
* on-line array.
else
return mddev->pers->reconfig(mddev, info->layout, -1);
}
- if (mddev->size != info->size) {
- mdk_rdev_t * rdev;
- struct list_head *tmp;
- 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;
- int fit = (info->size == 0);
- 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 && (info->size == 0 || info->size > avail/2))
- info->size = avail/2;
- if (avail < ((sector_t)info->size << 1))
- return -ENOSPC;
- }
- rv = mddev->pers->resize(mddev, (sector_t)info->size *2);
- if (!rv) {
- struct block_device *bdev;
-
- bdev = bdget_disk(mddev->gendisk, 0);
- if (bdev) {
- down(&bdev->bd_inode->i_sem);
- i_size_write(bdev->bd_inode, mddev->array_size << 10);
- up(&bdev->bd_inode->i_sem);
- bdput(bdev);
- }
- }
- }
- if (mddev->raid_disks != info->raid_disks) {
- /* change the number of raid disks */
- if (mddev->pers->reshape == NULL)
- return -EINVAL;
- if (info->raid_disks <= 0 ||
- info->raid_disks >= mddev->max_disks)
- return -EINVAL;
- if (mddev->sync_thread)
- return -EBUSY;
- rv = mddev->pers->reshape(mddev, info->raid_disks);
- if (!rv) {
- struct block_device *bdev;
-
- bdev = bdget_disk(mddev->gendisk, 0);
- if (bdev) {
- down(&bdev->bd_inode->i_sem);
- i_size_write(bdev->bd_inode, mddev->array_size << 10);
- up(&bdev->bd_inode->i_sem);
- bdput(bdev);
- }
- }
- }
+ if (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 (cnt > 0 ) {
printk(KERN_WARNING
"md: %s(pid %d) used deprecated START_ARRAY ioctl. "
- "This will not be supported beyond 2.6\n",
+ "This will not be supported beyond July 2006\n",
current->comm, current->pid);
cnt--;
}
/*
* 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)
*/
allow_signal(SIGKILL);
- complete(thread->event);
while (!kthread_should_stop()) {
- void (*run)(mddev_t *);
- wait_event_interruptible_timeout(thread->wqueue,
- test_bit(THREAD_WAKEUP, &thread->flags)
- || kthread_should_stop(),
- thread->timeout);
+ /* 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_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);
+ thread->run(thread->mddev);
}
return 0;
const char *name)
{
mdk_thread_t *thread;
- struct completion event;
- thread = 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;
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;
}
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",
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 */
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);
}
bdevname(rdev->bdev,b), rdev->desc_nr);
if (test_bit(WriteMostly, &rdev->flags))
seq_printf(seq, "(W)");
- if (rdev->faulty) {
+ if (test_bit(Faulty, &rdev->flags)) {
seq_printf(seq, "(F)");
continue;
} else if (rdev->raid_disk < 0)
if (mddev->pers) {
mddev->pers->status (seq, mddev);
seq_printf(seq, "\n ");
- 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, " resync=DELAYED\n ");
+ 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 ");
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);
- 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)
- 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;
}
curr_events = disk_stat_read(disk, sectors[0]) +
disk_stat_read(disk, sectors[1]) -
atomic_read(&disk->sync_io);
- /* Allow some slack between valud of curr_events and last_events,
- * as there are some uninteresting races.
+ /* 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 + 32) > 64) {
+ if ((curr_events - rdev->last_events + 4096) > 8192) {
rdev->last_events = curr_events;
idle = 0;
}
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(&mddev->write_lock);
+ spin_lock_irq(&mddev->write_lock);
if (mddev->in_sync) {
mddev->in_sync = 0;
mddev->sb_dirty = 1;
md_wakeup_thread(mddev->thread);
}
- spin_unlock(&mddev->write_lock);
+ spin_unlock_irq(&mddev->write_lock);
}
wait_event(mddev->sb_wait, mddev->sb_dirty==0);
}
mddev->curr_resync = 2;
try_again:
- if (signal_pending(current) ||
- kthread_should_stop()) {
- flush_signals(current);
+ if (kthread_should_stop()) {
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
goto skip;
}
* time 'round when curr_resync == 2
*/
continue;
- prepare_to_wait(&resync_wait, &wq, TASK_INTERRUPTIBLE);
- if (!signal_pending(current) &&
- !kthread_should_stop() &&
+ 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"
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 > io_sectors || j == max_sectors)
continue;
}
- if (signal_pending(current) || kthread_should_stop()) {
+ 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;
}
if (currspeed > sysctl_speed_limit_min) {
if ((currspeed > sysctl_speed_limit_max) ||
!is_mddev_idle(mddev)) {
- msleep_interruptible(250);
+ msleep(500);
goto repeat;
}
}
if (mddev_trylock(mddev)==0) {
int spares =0;
- spin_lock(&mddev->write_lock);
+ 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;
}
if (mddev->safemode == 1)
mddev->safemode = 0;
- spin_unlock(&mddev->write_lock);
+ spin_unlock_irq(&mddev->write_lock);
if (mddev->sb_dirty)
md_update_sb(mddev);
mddev->recovery = 0;
/* flag recovery needed just to double check */
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ md_new_event(mddev);
goto unlock;
}
/* Clear some bits that don't mean anything, but
*/
ITERATE_RDEV(mddev,rdev,rtmp)
if (rdev->raid_disk >= 0 &&
- (rdev->faulty || ! rdev->in_sync) &&
+ (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];
if (mddev->degraded) {
ITERATE_RDEV(mddev,rdev,rtmp)
if (rdev->raid_disk < 0
- && !rdev->faulty) {
+ && !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++;
+ md_new_event(mddev);
} else
break;
}
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);
" 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,
+ printk(KERN_INFO "md: bitmap version %d.%d\n", BITMAP_MAJOR_HI,
BITMAP_MINOR);
if (register_blkdev(MAJOR_NR, "md"))
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);