#include <linux/raid/md.h>
#include <linux/raid/bitmap.h>
#include <linux/sysctl.h>
-#include <linux/devfs_fs_kernel.h>
#include <linux/buffer_head.h> /* for invalidate_bdev */
#include <linux/suspend.h>
#include <linux/poll.h>
+#include <linux/mutex.h>
+#include <linux/ctype.h>
#include <linux/init.h>
static LIST_HEAD(pers_list);
static DEFINE_SPINLOCK(pers_lock);
+static void md_print_devices(void);
+
+#define MD_BUG(x...) { printk("md: bug in file %s, line %d\n", __FILE__, __LINE__); md_print_devices(); }
+
/*
* Current RAID-1,4,5 parallel reconstruction 'guaranteed speed limit'
* is 1000 KB/sec, so the extra system load does not show up that much.
*/
static DECLARE_WAIT_QUEUE_HEAD(md_event_waiters);
static atomic_t md_event_count;
-static void md_new_event(mddev_t *mddev)
+void md_new_event(mddev_t *mddev)
+{
+ atomic_inc(&md_event_count);
+ wake_up(&md_event_waiters);
+ sysfs_notify(&mddev->kobj, NULL, "sync_action");
+}
+EXPORT_SYMBOL_GPL(md_new_event);
+
+/* Alternate version that can be called from interrupts
+ * when calling sysfs_notify isn't needed.
+ */
+static void md_new_event_inintr(mddev_t *mddev)
{
atomic_inc(&md_event_count);
wake_up(&md_event_waiters);
return;
if (!mddev->raid_disks && list_empty(&mddev->disks)) {
list_del(&mddev->all_mddevs);
- blk_put_queue(mddev->queue);
+ spin_unlock(&all_mddevs_lock);
+ blk_cleanup_queue(mddev->queue);
kobject_unregister(&mddev->kobj);
- }
- spin_unlock(&all_mddevs_lock);
+ } else
+ spin_unlock(&all_mddevs_lock);
}
static mddev_t * mddev_find(dev_t unit)
else
new->md_minor = MINOR(unit) >> MdpMinorShift;
- init_MUTEX(&new->reconfig_sem);
+ mutex_init(&new->reconfig_mutex);
INIT_LIST_HEAD(&new->disks);
INIT_LIST_HEAD(&new->all_mddevs);
init_timer(&new->safemode_timer);
kfree(new);
return NULL;
}
+ set_bit(QUEUE_FLAG_CLUSTER, &new->queue->queue_flags);
blk_queue_make_request(new->queue, md_fail_request);
static inline int mddev_lock(mddev_t * mddev)
{
- return down_interruptible(&mddev->reconfig_sem);
-}
-
-static inline void mddev_lock_uninterruptible(mddev_t * mddev)
-{
- down(&mddev->reconfig_sem);
+ return mutex_lock_interruptible(&mddev->reconfig_mutex);
}
static inline int mddev_trylock(mddev_t * mddev)
{
- return down_trylock(&mddev->reconfig_sem);
+ return mutex_trylock(&mddev->reconfig_mutex);
}
static inline void mddev_unlock(mddev_t * mddev)
{
- up(&mddev->reconfig_sem);
+ mutex_unlock(&mddev->reconfig_mutex);
md_wakeup_thread(mddev->thread);
}
}
if (sb->major_version != 0 ||
- sb->minor_version != 90) {
+ sb->minor_version < 90 ||
+ sb->minor_version > 91) {
printk(KERN_WARNING "Bad version number %d.%d on %s\n",
sb->major_version, sb->minor_version,
b);
{
mdp_disk_t *desc;
mdp_super_t *sb = (mdp_super_t *)page_address(rdev->sb_page);
+ __u64 ev1 = md_event(sb);
rdev->raid_disk = -1;
rdev->flags = 0;
mddev->layout = sb->layout;
mddev->raid_disks = sb->raid_disks;
mddev->size = sb->size;
- mddev->events = md_event(sb);
+ mddev->events = ev1;
mddev->bitmap_offset = 0;
mddev->default_bitmap_offset = MD_SB_BYTES >> 9;
+ if (mddev->minor_version >= 91) {
+ mddev->reshape_position = sb->reshape_position;
+ mddev->delta_disks = sb->delta_disks;
+ mddev->new_level = sb->new_level;
+ mddev->new_layout = sb->new_layout;
+ mddev->new_chunk = sb->new_chunk;
+ } else {
+ mddev->reshape_position = MaxSector;
+ mddev->delta_disks = 0;
+ mddev->new_level = mddev->level;
+ mddev->new_layout = mddev->layout;
+ mddev->new_chunk = mddev->chunk_size;
+ }
+
if (sb->state & (1<<MD_SB_CLEAN))
mddev->recovery_cp = MaxSector;
else {
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 != 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");
} else if (mddev->pers == NULL) {
/* Insist on good event counter while assembling */
- __u64 ev1 = md_event(sb);
++ev1;
if (ev1 < mddev->events)
return -EINVAL;
/* if adding to array with a bitmap, then we can accept an
* older device ... but not too old.
*/
- __u64 ev1 = md_event(sb);
if (ev1 < mddev->bitmap->events_cleared)
return 0;
- } else /* just a hot-add of a new device, leave raid_disk at -1 */
- return 0;
+ } else {
+ if (ev1 < mddev->events)
+ /* just a hot-add of a new device, leave raid_disk at -1 */
+ return 0;
+ }
if (mddev->level != LEVEL_MULTIPATH) {
desc = sb->disks + rdev->desc_nr;
if (desc->state & (1<<MD_DISK_FAULTY))
set_bit(Faulty, &rdev->flags);
- else if (desc->state & (1<<MD_DISK_SYNC) &&
- desc->raid_disk < mddev->raid_disks) {
+ else if (desc->state & (1<<MD_DISK_SYNC) /* &&
+ desc->raid_disk < mddev->raid_disks */) {
set_bit(In_sync, &rdev->flags);
rdev->raid_disk = desc->raid_disk;
}
sb->md_magic = MD_SB_MAGIC;
sb->major_version = mddev->major_version;
- sb->minor_version = mddev->minor_version;
sb->patch_version = mddev->patch_version;
sb->gvalid_words = 0; /* ignored */
memcpy(&sb->set_uuid0, mddev->uuid+0, 4);
sb->events_hi = (mddev->events>>32);
sb->events_lo = (u32)mddev->events;
+ if (mddev->reshape_position == MaxSector)
+ sb->minor_version = 90;
+ else {
+ sb->minor_version = 91;
+ sb->reshape_position = mddev->reshape_position;
+ sb->new_level = mddev->new_level;
+ sb->delta_disks = mddev->delta_disks;
+ sb->new_layout = mddev->new_layout;
+ sb->new_chunk = mddev->new_chunk;
+ }
+ mddev->minor_version = sb->minor_version;
if (mddev->in_sync)
{
sb->recovery_cp = mddev->recovery_cp;
d->raid_disk = rdev2->raid_disk;
else
d->raid_disk = rdev2->desc_nr; /* compatibility */
- if (test_bit(Faulty, &rdev2->flags)) {
+ if (test_bit(Faulty, &rdev2->flags))
d->state = (1<<MD_DISK_FAULTY);
- failed++;
- } else if (test_bit(In_sync, &rdev2->flags)) {
+ else if (test_bit(In_sync, &rdev2->flags)) {
d->state = (1<<MD_DISK_ACTIVE);
d->state |= (1<<MD_DISK_SYNC);
active++;
rdev-> sb_size = (rdev->sb_size | bmask)+1;
if (refdev == 0)
- return 1;
+ ret = 1;
else {
__u64 ev1, ev2;
struct mdp_superblock_1 *refsb =
ev2 = le64_to_cpu(refsb->events);
if (ev1 > ev2)
- return 1;
+ ret = 1;
+ else
+ ret = 0;
}
if (minor_version)
rdev->size = ((rdev->bdev->bd_inode->i_size>>9) - le64_to_cpu(sb->data_offset)) / 2;
if (le32_to_cpu(sb->size) > rdev->size*2)
return -EINVAL;
- return 0;
+ return ret;
}
static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev)
{
struct mdp_superblock_1 *sb = (struct mdp_superblock_1*)page_address(rdev->sb_page);
+ __u64 ev1 = le64_to_cpu(sb->events);
rdev->raid_disk = -1;
rdev->flags = 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->events = ev1;
mddev->bitmap_offset = 0;
mddev->default_bitmap_offset = 1024 >> 9;
}
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);
+ mddev->new_level = le32_to_cpu(sb->new_level);
+ mddev->new_layout = le32_to_cpu(sb->new_layout);
+ mddev->new_chunk = le32_to_cpu(sb->new_chunk)<<9;
+ } else {
+ mddev->reshape_position = MaxSector;
+ mddev->delta_disks = 0;
+ mddev->new_level = mddev->level;
+ mddev->new_layout = mddev->layout;
+ mddev->new_chunk = mddev->chunk_size;
+ }
+
} else if (mddev->pers == NULL) {
/* Insist of good event counter while assembling */
- __u64 ev1 = le64_to_cpu(sb->events);
++ev1;
if (ev1 < mddev->events)
return -EINVAL;
/* If adding to array with a bitmap, then we can accept an
* older device, but not too old.
*/
- __u64 ev1 = le64_to_cpu(sb->events);
if (ev1 < mddev->bitmap->events_cleared)
return 0;
- } else /* just a hot-add of a new device, leave raid_disk at -1 */
- return 0;
-
+ } else {
+ if (ev1 < mddev->events)
+ /* just a hot-add of a new device, leave raid_disk at -1 */
+ return 0;
+ }
if (mddev->level != LEVEL_MULTIPATH) {
int role;
rdev->desc_nr = le32_to_cpu(sb->dev_number);
set_bit(Faulty, &rdev->flags);
break;
default:
- set_bit(In_sync, &rdev->flags);
+ if ((le32_to_cpu(sb->feature_map) &
+ MD_FEATURE_RECOVERY_OFFSET))
+ rdev->recovery_offset = le64_to_cpu(sb->recovery_offset);
+ else
+ set_bit(In_sync, &rdev->flags);
rdev->raid_disk = role;
break;
}
sb->feature_map = 0;
sb->pad0 = 0;
+ sb->recovery_offset = cpu_to_le64(0);
memset(sb->pad1, 0, sizeof(sb->pad1));
memset(sb->pad2, 0, sizeof(sb->pad2));
memset(sb->pad3, 0, sizeof(sb->pad3));
sb->feature_map = cpu_to_le32(MD_FEATURE_BITMAP_OFFSET);
}
+ if (rdev->raid_disk >= 0 &&
+ !test_bit(In_sync, &rdev->flags) &&
+ rdev->recovery_offset > 0) {
+ sb->feature_map |= cpu_to_le32(MD_FEATURE_RECOVERY_OFFSET);
+ sb->recovery_offset = cpu_to_le64(rdev->recovery_offset);
+ }
+
+ if (mddev->reshape_position != MaxSector) {
+ sb->feature_map |= cpu_to_le32(MD_FEATURE_RESHAPE_ACTIVE);
+ sb->reshape_position = cpu_to_le64(mddev->reshape_position);
+ sb->new_layout = cpu_to_le32(mddev->new_layout);
+ sb->delta_disks = cpu_to_le32(mddev->delta_disks);
+ sb->new_level = cpu_to_le32(mddev->new_level);
+ sb->new_chunk = cpu_to_le32(mddev->new_chunk>>9);
+ }
+
max_dev = 0;
ITERATE_RDEV(mddev,rdev2,tmp)
if (rdev2->desc_nr+1 > max_dev)
sb->dev_roles[i] = cpu_to_le16(0xfffe);
else if (test_bit(In_sync, &rdev2->flags))
sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk);
+ else if (rdev2->raid_disk >= 0 && rdev2->recovery_offset > 0)
+ sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk);
else
sb->dev_roles[i] = cpu_to_le16(0xffff);
}
- sb->recovery_offset = cpu_to_le64(0); /* not supported yet */
sb->sb_csum = calc_sb_1_csum(sb);
}
else
ko = &rdev->bdev->bd_disk->kobj;
sysfs_create_link(&rdev->kobj, ko, "block");
+ bd_claim_by_disk(rdev->bdev, rdev, mddev->gendisk);
return 0;
}
MD_BUG();
return;
}
+ bd_release_from_disk(rdev->bdev, rdev->mddev->gendisk);
list_del_init(&rdev->same_set);
printk(KERN_INFO "md: unbind<%s>\n", bdevname(rdev->bdev,b));
rdev->mddev = NULL;
printk(KERN_INFO "md: no rdev superblock!\n");
}
-void md_print_devices(void)
+static void md_print_devices(void)
{
struct list_head *tmp, *tmp2;
mdk_rdev_t *rdev;
}
-static void sync_sbs(mddev_t * mddev)
+static void sync_sbs(mddev_t * mddev, int nospares)
{
+ /* Update each superblock (in-memory image), but
+ * if we are allowed to, skip spares which already
+ * have the right event counter, or have one earlier
+ * (which would mean they aren't being marked as dirty
+ * with the rest of the array)
+ */
mdk_rdev_t *rdev;
struct list_head *tmp;
ITERATE_RDEV(mddev,rdev,tmp) {
- super_types[mddev->major_version].
- sync_super(mddev, rdev);
- rdev->sb_loaded = 1;
+ if (rdev->sb_events == mddev->events ||
+ (nospares &&
+ rdev->raid_disk < 0 &&
+ (rdev->sb_events&1)==0 &&
+ rdev->sb_events+1 == mddev->events)) {
+ /* Don't update this superblock */
+ rdev->sb_loaded = 2;
+ } else {
+ super_types[mddev->major_version].
+ sync_super(mddev, rdev);
+ rdev->sb_loaded = 1;
+ }
}
}
-static void md_update_sb(mddev_t * mddev)
+void md_update_sb(mddev_t * mddev)
{
int err;
struct list_head *tmp;
mdk_rdev_t *rdev;
int sync_req;
+ int nospares = 0;
repeat:
spin_lock_irq(&mddev->write_lock);
sync_req = mddev->in_sync;
mddev->utime = get_seconds();
- mddev->events ++;
+ if (mddev->sb_dirty == 3)
+ /* just a clean<-> dirty transition, possibly leave spares alone,
+ * though if events isn't the right even/odd, we will have to do
+ * spares after all
+ */
+ nospares = 1;
+
+ /* If this is just a dirty<->clean transition, and the array is clean
+ * and 'events' is odd, we can roll back to the previous clean state */
+ if (mddev->sb_dirty == 3
+ && (mddev->in_sync && mddev->recovery_cp == MaxSector)
+ && (mddev->events & 1))
+ mddev->events--;
+ else {
+ /* otherwise we have to go forward and ... */
+ mddev->events ++;
+ if (!mddev->in_sync || mddev->recovery_cp != MaxSector) { /* not clean */
+ /* .. if the array isn't clean, insist on an odd 'events' */
+ if ((mddev->events&1)==0) {
+ mddev->events++;
+ nospares = 0;
+ }
+ } else {
+ /* otherwise insist on an even 'events' (for clean states) */
+ if ((mddev->events&1)) {
+ mddev->events++;
+ nospares = 0;
+ }
+ }
+ }
if (!mddev->events) {
/*
mddev->events --;
}
mddev->sb_dirty = 2;
- sync_sbs(mddev);
+ sync_sbs(mddev, nospares);
/*
* do not write anything to disk if using
ITERATE_RDEV(mddev,rdev,tmp) {
char b[BDEVNAME_SIZE];
dprintk(KERN_INFO "md: ");
+ if (rdev->sb_loaded != 1)
+ continue; /* no noise on spare devices */
if (test_bit(Faulty, &rdev->flags))
dprintk("(skipping faulty ");
dprintk(KERN_INFO "(write) %s's sb offset: %llu\n",
bdevname(rdev->bdev,b),
(unsigned long long)rdev->sb_offset);
+ rdev->sb_events = mddev->events;
} else
dprintk(")\n");
wake_up(&mddev->sb_wait);
}
+EXPORT_SYMBOL_GPL(md_update_sb);
/* words written to sysfs files may, or my not, be \n terminated.
* We want to accept with case. For this we use cmd_match.
len += sprintf(page+len, "%sin_sync",sep);
sep = ",";
}
+ if (test_bit(WriteMostly, &rdev->flags)) {
+ len += sprintf(page+len, "%swrite_mostly",sep);
+ sep = ",";
+ }
if (!test_bit(Faulty, &rdev->flags) &&
!test_bit(In_sync, &rdev->flags)) {
len += sprintf(page+len, "%sspare", sep);
return len+sprintf(page+len, "\n");
}
+static ssize_t
+state_store(mdk_rdev_t *rdev, const char *buf, size_t len)
+{
+ /* can write
+ * faulty - simulates and error
+ * remove - disconnects the device
+ * writemostly - sets write_mostly
+ * -writemostly - clears write_mostly
+ */
+ int err = -EINVAL;
+ if (cmd_match(buf, "faulty") && rdev->mddev->pers) {
+ md_error(rdev->mddev, rdev);
+ err = 0;
+ } else if (cmd_match(buf, "remove")) {
+ if (rdev->raid_disk >= 0)
+ err = -EBUSY;
+ else {
+ mddev_t *mddev = rdev->mddev;
+ kick_rdev_from_array(rdev);
+ md_update_sb(mddev);
+ md_new_event(mddev);
+ err = 0;
+ }
+ } else if (cmd_match(buf, "writemostly")) {
+ set_bit(WriteMostly, &rdev->flags);
+ err = 0;
+ } else if (cmd_match(buf, "-writemostly")) {
+ clear_bit(WriteMostly, &rdev->flags);
+ err = 0;
+ }
+ return err ? err : len;
+}
static struct rdev_sysfs_entry
-rdev_state = __ATTR_RO(state);
+rdev_state = __ATTR(state, 0644, state_show, state_store);
static ssize_t
super_show(mdk_rdev_t *rdev, char *page)
rdev->desc_nr = -1;
rdev->flags = 0;
rdev->data_offset = 0;
+ rdev->sb_events = 0;
atomic_set(&rdev->nr_pending, 0);
atomic_set(&rdev->read_errors, 0);
atomic_set(&rdev->corrected_errors, 0);
}
static ssize_t
+safe_delay_show(mddev_t *mddev, char *page)
+{
+ int msec = (mddev->safemode_delay*1000)/HZ;
+ return sprintf(page, "%d.%03d\n", msec/1000, msec%1000);
+}
+static ssize_t
+safe_delay_store(mddev_t *mddev, const char *cbuf, size_t len)
+{
+ int scale=1;
+ int dot=0;
+ int i;
+ unsigned long msec;
+ char buf[30];
+ char *e;
+ /* remove a period, and count digits after it */
+ if (len >= sizeof(buf))
+ return -EINVAL;
+ strlcpy(buf, cbuf, len);
+ buf[len] = 0;
+ for (i=0; i<len; i++) {
+ if (dot) {
+ if (isdigit(buf[i])) {
+ buf[i-1] = buf[i];
+ scale *= 10;
+ }
+ buf[i] = 0;
+ } else if (buf[i] == '.') {
+ dot=1;
+ buf[i] = 0;
+ }
+ }
+ msec = simple_strtoul(buf, &e, 10);
+ if (e == buf || (*e && *e != '\n'))
+ return -EINVAL;
+ msec = (msec * 1000) / scale;
+ if (msec == 0)
+ mddev->safemode_delay = 0;
+ else {
+ mddev->safemode_delay = (msec*HZ)/1000;
+ if (mddev->safemode_delay == 0)
+ mddev->safemode_delay = 1;
+ }
+ return len;
+}
+static struct md_sysfs_entry md_safe_delay =
+__ATTR(safe_mode_delay, 0644,safe_delay_show, safe_delay_store);
+
+static ssize_t
level_show(mddev_t *mddev, char *page)
{
struct mdk_personality *p = mddev->pers;
static struct md_sysfs_entry md_level =
__ATTR(level, 0644, level_show, level_store);
+
+static ssize_t
+layout_show(mddev_t *mddev, char *page)
+{
+ /* just a number, not meaningful for all levels */
+ return sprintf(page, "%d\n", mddev->layout);
+}
+
+static ssize_t
+layout_store(mddev_t *mddev, const char *buf, size_t len)
+{
+ 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;
+ return len;
+}
+static struct md_sysfs_entry md_layout =
+__ATTR(layout, 0655, layout_show, layout_store);
+
+
static ssize_t
raid_disks_show(mddev_t *mddev, char *page)
{
__ATTR(chunk_size, 0644, chunk_size_show, chunk_size_store);
static ssize_t
+resync_start_show(mddev_t *mddev, char *page)
+{
+ return sprintf(page, "%llu\n", (unsigned long long)mddev->recovery_cp);
+}
+
+static ssize_t
+resync_start_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 long n = simple_strtoull(buf, &e, 10);
+
+ if (mddev->pers)
+ return -EBUSY;
+ if (!*buf || (*e && *e != '\n'))
+ return -EINVAL;
+
+ mddev->recovery_cp = n;
+ return len;
+}
+static struct md_sysfs_entry md_resync_start =
+__ATTR(resync_start, 0644, resync_start_show, resync_start_store);
+
+/*
+ * The array state can be:
+ *
+ * clear
+ * No devices, no size, no level
+ * Equivalent to STOP_ARRAY ioctl
+ * inactive
+ * May have some settings, but array is not active
+ * all IO results in error
+ * When written, doesn't tear down array, but just stops it
+ * suspended (not supported yet)
+ * All IO requests will block. The array can be reconfigured.
+ * Writing this, if accepted, will block until array is quiessent
+ * readonly
+ * no resync can happen. no superblocks get written.
+ * write requests fail
+ * read-auto
+ * like readonly, but behaves like 'clean' on a write request.
+ *
+ * clean - no pending writes, but otherwise active.
+ * When written to inactive array, starts without resync
+ * If a write request arrives then
+ * if metadata is known, mark 'dirty' and switch to 'active'.
+ * if not known, block and switch to write-pending
+ * If written to an active array that has pending writes, then fails.
+ * active
+ * fully active: IO and resync can be happening.
+ * When written to inactive array, starts with resync
+ *
+ * write-pending
+ * clean, but writes are blocked waiting for 'active' to be written.
+ *
+ * active-idle
+ * like active, but no writes have been seen for a while (100msec).
+ *
+ */
+enum array_state { clear, inactive, suspended, readonly, read_auto, clean, active,
+ write_pending, active_idle, bad_word};
+static char *array_states[] = {
+ "clear", "inactive", "suspended", "readonly", "read-auto", "clean", "active",
+ "write-pending", "active-idle", NULL };
+
+static int match_word(const char *word, char **list)
+{
+ int n;
+ for (n=0; list[n]; n++)
+ if (cmd_match(word, list[n]))
+ break;
+ return n;
+}
+
+static ssize_t
+array_state_show(mddev_t *mddev, char *page)
+{
+ enum array_state st = inactive;
+
+ if (mddev->pers)
+ switch(mddev->ro) {
+ case 1:
+ st = readonly;
+ break;
+ case 2:
+ st = read_auto;
+ break;
+ case 0:
+ if (mddev->in_sync)
+ st = clean;
+ else if (mddev->safemode)
+ st = active_idle;
+ else
+ st = active;
+ }
+ else {
+ if (list_empty(&mddev->disks) &&
+ mddev->raid_disks == 0 &&
+ mddev->size == 0)
+ st = clear;
+ else
+ st = inactive;
+ }
+ return sprintf(page, "%s\n", array_states[st]);
+}
+
+static int do_md_stop(mddev_t * mddev, int ro);
+static int do_md_run(mddev_t * mddev);
+static int restart_array(mddev_t *mddev);
+
+static ssize_t
+array_state_store(mddev_t *mddev, const char *buf, size_t len)
+{
+ int err = -EINVAL;
+ enum array_state st = match_word(buf, array_states);
+ switch(st) {
+ case bad_word:
+ break;
+ case clear:
+ /* stopping an active array */
+ if (mddev->pers) {
+ if (atomic_read(&mddev->active) > 1)
+ return -EBUSY;
+ err = do_md_stop(mddev, 0);
+ }
+ break;
+ case inactive:
+ /* stopping an active array */
+ if (mddev->pers) {
+ if (atomic_read(&mddev->active) > 1)
+ return -EBUSY;
+ err = do_md_stop(mddev, 2);
+ }
+ break;
+ case suspended:
+ break; /* not supported yet */
+ case readonly:
+ if (mddev->pers)
+ err = do_md_stop(mddev, 1);
+ else {
+ mddev->ro = 1;
+ err = do_md_run(mddev);
+ }
+ break;
+ case read_auto:
+ /* stopping an active array */
+ if (mddev->pers) {
+ err = do_md_stop(mddev, 1);
+ if (err == 0)
+ mddev->ro = 2; /* FIXME mark devices writable */
+ } else {
+ mddev->ro = 2;
+ err = do_md_run(mddev);
+ }
+ break;
+ case clean:
+ if (mddev->pers) {
+ restart_array(mddev);
+ spin_lock_irq(&mddev->write_lock);
+ if (atomic_read(&mddev->writes_pending) == 0) {
+ mddev->in_sync = 1;
+ mddev->sb_dirty = 1;
+ }
+ spin_unlock_irq(&mddev->write_lock);
+ } else {
+ mddev->ro = 0;
+ mddev->recovery_cp = MaxSector;
+ err = do_md_run(mddev);
+ }
+ break;
+ case active:
+ if (mddev->pers) {
+ restart_array(mddev);
+ mddev->sb_dirty = 0;
+ wake_up(&mddev->sb_wait);
+ err = 0;
+ } else {
+ mddev->ro = 0;
+ err = do_md_run(mddev);
+ }
+ break;
+ case write_pending:
+ case active_idle:
+ /* these cannot be set */
+ break;
+ }
+ if (err)
+ return err;
+ else
+ return len;
+}
+static struct md_sysfs_entry md_array_state = __ATTR(array_state, 0644, array_state_show, array_state_store);
+
+static ssize_t
null_show(mddev_t *mddev, char *page)
{
return -EINVAL;
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_RESHAPE, &mddev->recovery))
+ type = "reshape";
+ else 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))
return -EBUSY;
else if (cmd_match(page, "resync") || cmd_match(page, "recover"))
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
- else {
+ else if (cmd_match(page, "reshape")) {
+ int err;
+ if (mddev->pers->start_reshape == NULL)
+ return -EINVAL;
+ err = mddev->pers->start_reshape(mddev);
+ if (err)
+ return err;
+ } else {
if (cmd_match(page, "check"))
set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
- else if (cmd_match(page, "repair"))
+ else if (!cmd_match(page, "repair"))
return -EINVAL;
set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
static struct md_sysfs_entry
md_sync_completed = __ATTR_RO(sync_completed);
+static ssize_t
+suspend_lo_show(mddev_t *mddev, char *page)
+{
+ return sprintf(page, "%llu\n", (unsigned long long)mddev->suspend_lo);
+}
+
+static ssize_t
+suspend_lo_store(mddev_t *mddev, const char *buf, size_t len)
+{
+ char *e;
+ unsigned long long new = simple_strtoull(buf, &e, 10);
+
+ if (mddev->pers->quiesce == NULL)
+ return -EINVAL;
+ if (buf == e || (*e && *e != '\n'))
+ return -EINVAL;
+ if (new >= mddev->suspend_hi ||
+ (new > mddev->suspend_lo && new < mddev->suspend_hi)) {
+ mddev->suspend_lo = new;
+ mddev->pers->quiesce(mddev, 2);
+ return len;
+ } else
+ return -EINVAL;
+}
+static struct md_sysfs_entry md_suspend_lo =
+__ATTR(suspend_lo, S_IRUGO|S_IWUSR, suspend_lo_show, suspend_lo_store);
+
+
+static ssize_t
+suspend_hi_show(mddev_t *mddev, char *page)
+{
+ return sprintf(page, "%llu\n", (unsigned long long)mddev->suspend_hi);
+}
+
+static ssize_t
+suspend_hi_store(mddev_t *mddev, const char *buf, size_t len)
+{
+ char *e;
+ unsigned long long new = simple_strtoull(buf, &e, 10);
+
+ if (mddev->pers->quiesce == NULL)
+ return -EINVAL;
+ if (buf == e || (*e && *e != '\n'))
+ return -EINVAL;
+ if ((new <= mddev->suspend_lo && mddev->suspend_lo >= mddev->suspend_hi) ||
+ (new > mddev->suspend_lo && new > mddev->suspend_hi)) {
+ mddev->suspend_hi = new;
+ mddev->pers->quiesce(mddev, 1);
+ mddev->pers->quiesce(mddev, 0);
+ return len;
+ } else
+ return -EINVAL;
+}
+static struct md_sysfs_entry md_suspend_hi =
+__ATTR(suspend_hi, S_IRUGO|S_IWUSR, suspend_hi_show, suspend_hi_store);
+
+
static struct attribute *md_default_attrs[] = {
&md_level.attr,
+ &md_layout.attr,
&md_raid_disks.attr,
&md_chunk_size.attr,
&md_size.attr,
+ &md_resync_start.attr,
&md_metadata.attr,
&md_new_device.attr,
+ &md_safe_delay.attr,
+ &md_array_state.attr,
NULL,
};
&md_sync_max.attr,
&md_sync_speed.attr,
&md_sync_completed.attr,
+ &md_suspend_lo.attr,
+ &md_suspend_hi.attr,
NULL,
};
static struct attribute_group md_redundancy_group = {
if (!entry->show)
return -EIO;
- mddev_lock(mddev);
- rv = entry->show(mddev, page);
- mddev_unlock(mddev);
+ rv = mddev_lock(mddev);
+ if (!rv) {
+ rv = entry->show(mddev, page);
+ mddev_unlock(mddev);
+ }
return rv;
}
if (!entry->store)
return -EIO;
- mddev_lock(mddev);
- rv = entry->store(mddev, page, length);
- mddev_unlock(mddev);
+ rv = mddev_lock(mddev);
+ if (!rv) {
+ rv = entry->store(mddev, page, length);
+ mddev_unlock(mddev);
+ }
return rv;
}
static struct kobject *md_probe(dev_t dev, int *part, void *data)
{
- static DECLARE_MUTEX(disks_sem);
+ static DEFINE_MUTEX(disks_mutex);
mddev_t *mddev = mddev_find(dev);
struct gendisk *disk;
int partitioned = (MAJOR(dev) != MD_MAJOR);
if (!mddev)
return NULL;
- down(&disks_sem);
+ mutex_lock(&disks_mutex);
if (mddev->gendisk) {
- up(&disks_sem);
+ mutex_unlock(&disks_mutex);
mddev_put(mddev);
return NULL;
}
disk = alloc_disk(1 << shift);
if (!disk) {
- up(&disks_sem);
+ mutex_unlock(&disks_mutex);
mddev_put(mddev);
return NULL;
}
disk->queue = mddev->queue;
add_disk(disk);
mddev->gendisk = disk;
- up(&disks_sem);
+ mutex_unlock(&disks_mutex);
mddev->kobj.parent = &disk->kobj;
mddev->kobj.k_name = NULL;
snprintf(mddev->kobj.name, KOBJ_NAME_LEN, "%s", "md");
return NULL;
}
-void md_wakeup_thread(mdk_thread_t *thread);
-
static void md_safemode_timeout(unsigned long data)
{
mddev_t *mddev = (mddev_t *) data;
mddev->level = pers->level;
strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
+ if (mddev->reshape_position != MaxSector &&
+ pers->start_reshape == NULL) {
+ /* This personality cannot handle reshaping... */
+ mddev->pers = NULL;
+ module_put(pers->owner);
+ return -EINVAL;
+ }
+
mddev->recovery = 0;
mddev->resync_max_sectors = mddev->size << 1; /* may be over-ridden by personality */
mddev->barriers_work = 1;
mddev->safemode = 0;
mddev->safemode_timer.function = md_safemode_timeout;
mddev->safemode_timer.data = (unsigned long) mddev;
- mddev->safemode_delay = (20 * HZ)/1000 +1; /* 20 msec delay */
+ mddev->safemode_delay = (200 * HZ)/1000 +1; /* 200 msec delay */
mddev->in_sync = 1;
ITERATE_RDEV(mddev,rdev,tmp)
mddev->queue->queuedata = mddev;
mddev->queue->make_request_fn = mddev->pers->make_request;
+ /* If there is a partially-recovered drive we need to
+ * start recovery here. If we leave it to md_check_recovery,
+ * it will remove the drives and not do the right thing
+ */
+ if (mddev->degraded) {
+ struct list_head *rtmp;
+ int spares = 0;
+ ITERATE_RDEV(mddev,rdev,rtmp)
+ if (rdev->raid_disk >= 0 &&
+ !test_bit(In_sync, &rdev->flags) &&
+ !test_bit(Faulty, &rdev->flags))
+ /* complete an interrupted recovery */
+ spares++;
+ if (spares && mddev->pers->sync_request) {
+ mddev->recovery = 0;
+ set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
+ mddev->sync_thread = md_register_thread(md_do_sync,
+ mddev,
+ "%s_resync");
+ if (!mddev->sync_thread) {
+ printk(KERN_ERR "%s: could not start resync"
+ " thread...\n",
+ mdname(mddev));
+ /* leave the spares where they are, it shouldn't hurt */
+ mddev->recovery = 0;
+ } else
+ md_wakeup_thread(mddev->sync_thread);
+ }
+ }
+
mddev->changed = 1;
md_new_event(mddev);
return 0;
*/
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
+ md_wakeup_thread(mddev->sync_thread);
err = 0;
- } else {
- printk(KERN_ERR "md: %s has no personality assigned.\n",
- mdname(mddev));
+ } else
err = -EINVAL;
- }
out:
return err;
}
-static int do_md_stop(mddev_t * mddev, int ro)
+/* similar to deny_write_access, but accounts for our holding a reference
+ * to the file ourselves */
+static int deny_bitmap_write_access(struct file * file)
+{
+ struct inode *inode = file->f_mapping->host;
+
+ spin_lock(&inode->i_lock);
+ if (atomic_read(&inode->i_writecount) > 1) {
+ spin_unlock(&inode->i_lock);
+ return -ETXTBSY;
+ }
+ atomic_set(&inode->i_writecount, -1);
+ spin_unlock(&inode->i_lock);
+
+ return 0;
+}
+
+static void restore_bitmap_write_access(struct file *file)
+{
+ struct inode *inode = file->f_mapping->host;
+
+ spin_lock(&inode->i_lock);
+ atomic_set(&inode->i_writecount, 1);
+ spin_unlock(&inode->i_lock);
+}
+
+/* mode:
+ * 0 - completely stop and dis-assemble array
+ * 1 - switch to readonly
+ * 2 - stop but do not disassemble array
+ */
+static int do_md_stop(mddev_t * mddev, int mode)
{
int err = 0;
struct gendisk *disk = mddev->gendisk;
}
if (mddev->sync_thread) {
+ set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
md_unregister_thread(mddev->sync_thread);
mddev->sync_thread = NULL;
invalidate_partition(disk, 0);
- if (ro) {
+ switch(mode) {
+ case 1: /* readonly */
err = -ENXIO;
if (mddev->ro==1)
goto out;
mddev->ro = 1;
- } else {
+ break;
+ case 0: /* disassemble */
+ case 2: /* stop */
bitmap_flush(mddev);
md_super_wait(mddev);
if (mddev->ro)
if (mddev->ro)
mddev->ro = 0;
}
- if (!mddev->in_sync) {
+ if (!mddev->in_sync || mddev->sb_dirty) {
/* mark array as shutdown cleanly */
mddev->in_sync = 1;
md_update_sb(mddev);
}
- if (ro)
+ if (mode == 1)
set_disk_ro(disk, 1);
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
}
/*
* Free resources if final stop
*/
- if (!ro) {
+ if (mode == 0) {
mdk_rdev_t *rdev;
struct list_head *tmp;
struct gendisk *disk;
bitmap_destroy(mddev);
if (mddev->bitmap_file) {
- atomic_set(&mddev->bitmap_file->f_dentry->d_inode->i_writecount, 1);
+ restore_bitmap_write_access(mddev->bitmap_file);
fput(mddev->bitmap_file);
mddev->bitmap_file = NULL;
}
export_array(mddev);
mddev->array_size = 0;
+ mddev->size = 0;
+ mddev->raid_disks = 0;
+ mddev->recovery_cp = 0;
+
disk = mddev->gendisk;
if (disk)
set_capacity(disk, 0);
mddev->changed = 1;
- } else
+ } else if (mddev->pers)
printk(KERN_INFO "md: %s switched to read-only mode.\n",
mdname(mddev));
err = 0;
*/
static void autorun_devices(int part)
{
- struct list_head candidates;
struct list_head *tmp;
mdk_rdev_t *rdev0, *rdev;
mddev_t *mddev;
printk(KERN_INFO "md: autorun ...\n");
while (!list_empty(&pending_raid_disks)) {
dev_t dev;
+ LIST_HEAD(candidates);
rdev0 = list_entry(pending_raid_disks.next,
mdk_rdev_t, same_set);
rdev->raid_disk = -1;
err = bind_rdev_to_array(rdev, mddev);
+ if (!err && !mddev->pers->hot_remove_disk) {
+ /* If there is hot_add_disk but no hot_remove_disk
+ * then added disks for geometry changes,
+ * and should be added immediately.
+ */
+ super_types[mddev->major_version].
+ validate_super(mddev, rdev);
+ err = mddev->pers->hot_add_disk(mddev, rdev);
+ if (err)
+ unbind_rdev_from_array(rdev);
+ }
if (err)
export_rdev(rdev);
return err;
}
-/* similar to deny_write_access, but accounts for our holding a reference
- * to the file ourselves */
-static int deny_bitmap_write_access(struct file * file)
-{
- struct inode *inode = file->f_mapping->host;
-
- spin_lock(&inode->i_lock);
- if (atomic_read(&inode->i_writecount) > 1) {
- spin_unlock(&inode->i_lock);
- return -ETXTBSY;
- }
- atomic_set(&inode->i_writecount, -1);
- spin_unlock(&inode->i_lock);
-
- return 0;
-}
-
static int set_bitmap_file(mddev_t *mddev, int fd)
{
int err;
mddev->pers->quiesce(mddev, 1);
if (fd >= 0)
err = bitmap_create(mddev);
- if (fd < 0 || err)
+ if (fd < 0 || err) {
bitmap_destroy(mddev);
+ fd = -1; /* make sure to put the file */
+ }
mddev->pers->quiesce(mddev, 0);
- } else if (fd < 0) {
- if (mddev->bitmap_file)
+ }
+ if (fd < 0) {
+ if (mddev->bitmap_file) {
+ restore_bitmap_write_access(mddev->bitmap_file);
fput(mddev->bitmap_file);
+ }
mddev->bitmap_file = NULL;
}
mddev->default_bitmap_offset = MD_SB_BYTES >> 9;
mddev->bitmap_offset = 0;
+ mddev->reshape_position = MaxSector;
+
/*
* Generate a 128 bit UUID
*/
get_random_bytes(mddev->uuid, 16);
+ mddev->new_level = mddev->level;
+ mddev->new_chunk = mddev->chunk_size;
+ mddev->new_layout = mddev->layout;
+ mddev->delta_disks = 0;
+
return 0;
}
mdk_rdev_t * rdev;
int rv;
struct list_head *tmp;
+ int fit = (size == 0);
if (mddev->pers->resize == NULL)
return -EINVAL;
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
{
int rv;
/* change the number of raid disks */
- if (mddev->pers->reshape == NULL)
+ if (mddev->pers->check_reshape == NULL)
return -EINVAL;
if (raid_disks <= 0 ||
raid_disks >= mddev->max_disks)
return -EINVAL;
- if (mddev->sync_thread)
+ if (mddev->sync_thread || mddev->reshape_position != MaxSector)
return -EBUSY;
- rv = mddev->pers->reshape(mddev, raid_disks);
+ mddev->delta_disks = raid_disks - mddev->raid_disks;
+
+ rv = mddev->pers->check_reshape(mddev);
return rv;
}
goto done_unlock;
default:
- if (_IOC_TYPE(cmd) == MD_MAJOR)
- printk(KERN_WARNING "md: %s(pid %d) used"
- " obsolete MD ioctl, upgrade your"
- " software to use new ictls.\n",
- current->comm, current->pid);
err = -EINVAL;
goto abort_unlock;
}
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
- md_new_event(mddev);
+ md_new_event_inintr(mddev);
}
/* seq_file implementation /proc/mdstat */
static void status_resync(struct seq_file *seq, mddev_t * mddev)
{
- unsigned long max_blocks, resync, res, dt, db, rt;
+ sector_t max_blocks, resync, res;
+ unsigned long dt, db, rt;
+ int scale;
+ unsigned int per_milli;
resync = (mddev->curr_resync - atomic_read(&mddev->recovery_active))/2;
MD_BUG();
return;
}
- res = (resync/1024)*1000/(max_blocks/1024 + 1);
+ /* Pick 'scale' such that (resync>>scale)*1000 will fit
+ * in a sector_t, and (max_blocks>>scale) will fit in a
+ * u32, as those are the requirements for sector_div.
+ * Thus 'scale' must be at least 10
+ */
+ scale = 10;
+ if (sizeof(sector_t) > sizeof(unsigned long)) {
+ while ( max_blocks/2 > (1ULL<<(scale+32)))
+ scale++;
+ }
+ res = (resync>>scale)*1000;
+ sector_div(res, (u32)((max_blocks>>scale)+1));
+
+ per_milli = res;
{
- int i, x = res/50, y = 20-x;
+ int i, x = per_milli/50, y = 20-x;
seq_printf(seq, "[");
for (i = 0; i < x; i++)
seq_printf(seq, "=");
seq_printf(seq, ".");
seq_printf(seq, "] ");
}
- seq_printf(seq, " %s =%3lu.%lu%% (%lu/%lu)",
+ seq_printf(seq, " %s =%3u.%u%% (%llu/%llu)",
+ (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)?
+ "reshape" :
(test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ?
- "resync" : "recovery"),
- res/10, res % 10, resync, max_blocks);
+ "resync" : "recovery")),
+ per_milli/10, per_milli % 10,
+ (unsigned long long) resync,
+ (unsigned long long) max_blocks);
/*
* We do not want to overflow, so the order of operands and
dt = ((jiffies - mddev->resync_mark) / HZ);
if (!dt) dt++;
db = resync - (mddev->resync_mark_cnt/2);
- rt = (dt * ((max_blocks-resync) / (db/100+1)))/100;
+ rt = (dt * ((unsigned long)(max_blocks-resync) / (db/100+1)))/100;
seq_printf(seq, " finish=%lu.%lumin", rt / 60, (rt % 60)/6);
return 0;
}
- if (mddev_lock(mddev)!=0)
+ if (mddev_lock(mddev) < 0)
return -EINTR;
+
if (mddev->pers || mddev->raid_disks || !list_empty(&mddev->disks)) {
seq_printf(seq, "%s : %sactive", mdname(mddev),
mddev->pers ? "" : "in");
spin_lock_irq(&mddev->write_lock);
if (mddev->in_sync) {
mddev->in_sync = 0;
- mddev->sb_dirty = 1;
+ mddev->sb_dirty = 3;
md_wakeup_thread(mddev->thread);
}
spin_unlock_irq(&mddev->write_lock);
if (atomic_dec_and_test(&mddev->writes_pending)) {
if (mddev->safemode == 2)
md_wakeup_thread(mddev->thread);
- else
+ else if (mddev->safemode_delay)
mod_timer(&mddev->safemode_timer, jiffies + mddev->safemode_delay);
}
}
#define SYNC_MARKS 10
#define SYNC_MARK_STEP (3*HZ)
-static void md_do_sync(mddev_t *mddev)
+void md_do_sync(mddev_t *mddev)
{
mddev_t *mddev2;
unsigned int currspeed = 0,
struct list_head *tmp;
sector_t last_check;
int skipped = 0;
+ struct list_head *rtmp;
+ mdk_rdev_t *rdev;
/* just incase thread restarts... */
if (test_bit(MD_RECOVERY_DONE, &mddev->recovery))
return;
+ if (mddev->ro) /* never try to sync a read-only array */
+ return;
/* we overload curr_resync somewhat here.
* 0 == not engaged in resync at all
}
} while (mddev->curr_resync < 2);
+ j = 0;
if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
/* resync follows the size requested by the personality,
* which defaults to physical size, but can be virtual size
*/
max_sectors = mddev->resync_max_sectors;
mddev->resync_mismatches = 0;
- } else
+ /* we don't use the checkpoint if there's a bitmap */
+ if (!mddev->bitmap &&
+ !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
+ j = mddev->recovery_cp;
+ } else if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
+ max_sectors = mddev->size << 1;
+ else {
/* recovery follows the physical size of devices */
max_sectors = mddev->size << 1;
+ j = MaxSector;
+ ITERATE_RDEV(mddev,rdev,rtmp)
+ if (rdev->raid_disk >= 0 &&
+ !test_bit(Faulty, &rdev->flags) &&
+ !test_bit(In_sync, &rdev->flags) &&
+ rdev->recovery_offset < j)
+ j = rdev->recovery_offset;
+ }
printk(KERN_INFO "md: syncing RAID array %s\n", mdname(mddev));
printk(KERN_INFO "md: minimum _guaranteed_ reconstruction speed:"
speed_max(mddev));
is_mddev_idle(mddev); /* this also initializes IO event counters */
- /* we don't use the checkpoint if there's a bitmap */
- if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) && !mddev->bitmap
- && ! test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
- j = mddev->recovery_cp;
- else
- j = 0;
+
io_sectors = 0;
for (m = 0; m < SYNC_MARKS; m++) {
mark[m] = jiffies;
mddev->pers->sync_request(mddev, max_sectors, &skipped, 1);
if (!test_bit(MD_RECOVERY_ERR, &mddev->recovery) &&
- mddev->curr_resync > 2 &&
- mddev->curr_resync >= mddev->recovery_cp) {
- if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
- printk(KERN_INFO
- "md: checkpointing recovery of %s.\n",
- mdname(mddev));
- mddev->recovery_cp = mddev->curr_resync;
- } else
- mddev->recovery_cp = MaxSector;
+ 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)) {
+ if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
+ if (mddev->curr_resync >= mddev->recovery_cp) {
+ printk(KERN_INFO
+ "md: checkpointing recovery of %s.\n",
+ mdname(mddev));
+ mddev->recovery_cp = mddev->curr_resync;
+ }
+ } else
+ mddev->recovery_cp = MaxSector;
+ } else {
+ if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery))
+ mddev->curr_resync = MaxSector;
+ ITERATE_RDEV(mddev,rdev,rtmp)
+ if (rdev->raid_disk >= 0 &&
+ !test_bit(Faulty, &rdev->flags) &&
+ !test_bit(In_sync, &rdev->flags) &&
+ rdev->recovery_offset < mddev->curr_resync)
+ rdev->recovery_offset = mddev->curr_resync;
+ mddev->sb_dirty = 1;
+ }
}
skip:
set_bit(MD_RECOVERY_DONE, &mddev->recovery);
md_wakeup_thread(mddev->thread);
}
+EXPORT_SYMBOL_GPL(md_do_sync);
/*
))
return;
- if (mddev_trylock(mddev)==0) {
+ if (mddev_trylock(mddev)) {
int spares =0;
spin_lock_irq(&mddev->write_lock);
if (mddev->safemode && !atomic_read(&mddev->writes_pending) &&
!mddev->in_sync && mddev->recovery_cp == MaxSector) {
mddev->in_sync = 1;
- mddev->sb_dirty = 1;
+ mddev->sb_dirty = 3;
}
if (mddev->safemode == 1)
mddev->safemode = 0;
clear_bit(MD_RECOVERY_INTR, &mddev->recovery);
clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
+ if (test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
+ goto unlock;
/* no recovery is running.
* remove any failed drives, then
* add spares if possible.
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);
printk(KERN_INFO "md: stopping all md devices.\n");
ITERATE_MDDEV(mddev,tmp)
- if (mddev_trylock(mddev)==0)
+ if (mddev_trylock(mddev)) {
do_md_stop (mddev, 1);
+ mddev_unlock(mddev);
+ }
/*
* certain more exotic SCSI devices are known to be
* volatile wrt too early system reboots. While the
static int __init md_init(void)
{
- int minor;
-
printk(KERN_INFO "md: md driver %d.%d.%d MAX_MD_DEVS=%d,"
" MD_SB_DISKS=%d\n",
MD_MAJOR_VERSION, MD_MINOR_VERSION,
unregister_blkdev(MAJOR_NR, "md");
return -1;
}
- devfs_mk_dir("md");
blk_register_region(MKDEV(MAJOR_NR, 0), MAX_MD_DEVS, THIS_MODULE,
md_probe, NULL, NULL);
blk_register_region(MKDEV(mdp_major, 0), MAX_MD_DEVS<<MdpMinorShift, THIS_MODULE,
md_probe, NULL, NULL);
- for (minor=0; minor < MAX_MD_DEVS; ++minor)
- devfs_mk_bdev(MKDEV(MAJOR_NR, minor),
- S_IFBLK|S_IRUSR|S_IWUSR,
- "md/%d", minor);
-
- for (minor=0; minor < MAX_MD_DEVS; ++minor)
- devfs_mk_bdev(MKDEV(mdp_major, minor<<MdpMinorShift),
- S_IFBLK|S_IRUSR|S_IWUSR,
- "md/mdp%d", minor);
-
-
register_reboot_notifier(&md_notifier);
raid_table_header = register_sysctl_table(raid_root_table, 1);
{
mddev_t *mddev;
struct list_head *tmp;
- int i;
+
blk_unregister_region(MKDEV(MAJOR_NR,0), MAX_MD_DEVS);
blk_unregister_region(MKDEV(mdp_major,0), MAX_MD_DEVS << MdpMinorShift);
- for (i=0; i < MAX_MD_DEVS; i++)
- devfs_remove("md/%d", i);
- for (i=0; i < MAX_MD_DEVS; i++)
- devfs_remove("md/d%d", i);
-
- devfs_remove("md");
unregister_blkdev(MAJOR_NR,"md");
unregister_blkdev(mdp_major, "mdp");
EXPORT_SYMBOL(md_register_thread);
EXPORT_SYMBOL(md_unregister_thread);
EXPORT_SYMBOL(md_wakeup_thread);
-EXPORT_SYMBOL(md_print_devices);
EXPORT_SYMBOL(md_check_recovery);
MODULE_LICENSE("GPL");
MODULE_ALIAS("md");
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff