static ctl_table raid_table[] = {
{
- .ctl_name = DEV_RAID_SPEED_LIMIT_MIN,
.procname = "speed_limit_min",
.data = &sysctl_speed_limit_min,
.maxlen = sizeof(int),
.mode = S_IRUGO|S_IWUSR,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = DEV_RAID_SPEED_LIMIT_MAX,
.procname = "speed_limit_max",
.data = &sysctl_speed_limit_max,
.maxlen = sizeof(int),
.mode = S_IRUGO|S_IWUSR,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
- { .ctl_name = 0 }
+ { }
};
static ctl_table raid_dir_table[] = {
{
- .ctl_name = DEV_RAID,
.procname = "raid",
.maxlen = 0,
.mode = S_IRUGO|S_IXUGO,
.child = raid_table,
},
- { .ctl_name = 0 }
+ { }
};
static ctl_table raid_root_table[] = {
{
- .ctl_name = CTL_DEV,
.procname = "dev",
.maxlen = 0,
.mode = 0555,
.child = raid_dir_table,
},
- { .ctl_name = 0 }
+ { }
};
static const struct block_device_operations md_fops;
return 0;
}
rcu_read_lock();
- if (mddev->suspended) {
+ if (mddev->suspended || mddev->barrier) {
DEFINE_WAIT(__wait);
for (;;) {
prepare_to_wait(&mddev->sb_wait, &__wait,
TASK_UNINTERRUPTIBLE);
- if (!mddev->suspended)
+ if (!mddev->suspended && !mddev->barrier)
break;
rcu_read_unlock();
schedule();
mddev->pers->quiesce(mddev, 0);
}
+int mddev_congested(mddev_t *mddev, int bits)
+{
+ if (mddev->barrier)
+ return 1;
+ return mddev->suspended;
+}
+EXPORT_SYMBOL(mddev_congested);
+
+/*
+ * Generic barrier handling for md
+ */
+
+#define POST_REQUEST_BARRIER ((void*)1)
+
+static void md_end_barrier(struct bio *bio, int err)
+{
+ mdk_rdev_t *rdev = bio->bi_private;
+ mddev_t *mddev = rdev->mddev;
+ if (err == -EOPNOTSUPP && mddev->barrier != POST_REQUEST_BARRIER)
+ set_bit(BIO_EOPNOTSUPP, &mddev->barrier->bi_flags);
+
+ rdev_dec_pending(rdev, mddev);
+
+ if (atomic_dec_and_test(&mddev->flush_pending)) {
+ if (mddev->barrier == POST_REQUEST_BARRIER) {
+ /* This was a post-request barrier */
+ mddev->barrier = NULL;
+ wake_up(&mddev->sb_wait);
+ } else
+ /* The pre-request barrier has finished */
+ schedule_work(&mddev->barrier_work);
+ }
+ bio_put(bio);
+}
+
+static void submit_barriers(mddev_t *mddev)
+{
+ mdk_rdev_t *rdev;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(rdev, &mddev->disks, same_set)
+ if (rdev->raid_disk >= 0 &&
+ !test_bit(Faulty, &rdev->flags)) {
+ /* Take two references, one is dropped
+ * when request finishes, one after
+ * we reclaim rcu_read_lock
+ */
+ struct bio *bi;
+ atomic_inc(&rdev->nr_pending);
+ atomic_inc(&rdev->nr_pending);
+ rcu_read_unlock();
+ bi = bio_alloc(GFP_KERNEL, 0);
+ bi->bi_end_io = md_end_barrier;
+ bi->bi_private = rdev;
+ bi->bi_bdev = rdev->bdev;
+ atomic_inc(&mddev->flush_pending);
+ submit_bio(WRITE_BARRIER, bi);
+ rcu_read_lock();
+ rdev_dec_pending(rdev, mddev);
+ }
+ rcu_read_unlock();
+}
+
+static void md_submit_barrier(struct work_struct *ws)
+{
+ mddev_t *mddev = container_of(ws, mddev_t, barrier_work);
+ struct bio *bio = mddev->barrier;
+
+ atomic_set(&mddev->flush_pending, 1);
+
+ if (test_bit(BIO_EOPNOTSUPP, &bio->bi_flags))
+ bio_endio(bio, -EOPNOTSUPP);
+ else if (bio->bi_size == 0)
+ /* an empty barrier - all done */
+ bio_endio(bio, 0);
+ else {
+ bio->bi_rw &= ~(1<<BIO_RW_BARRIER);
+ if (mddev->pers->make_request(mddev->queue, bio))
+ generic_make_request(bio);
+ mddev->barrier = POST_REQUEST_BARRIER;
+ submit_barriers(mddev);
+ }
+ if (atomic_dec_and_test(&mddev->flush_pending)) {
+ mddev->barrier = NULL;
+ wake_up(&mddev->sb_wait);
+ }
+}
+
+void md_barrier_request(mddev_t *mddev, struct bio *bio)
+{
+ spin_lock_irq(&mddev->write_lock);
+ wait_event_lock_irq(mddev->sb_wait,
+ !mddev->barrier,
+ mddev->write_lock, /*nothing*/);
+ mddev->barrier = bio;
+ spin_unlock_irq(&mddev->write_lock);
+
+ atomic_set(&mddev->flush_pending, 1);
+ INIT_WORK(&mddev->barrier_work, md_submit_barrier);
+
+ submit_barriers(mddev);
+
+ if (atomic_dec_and_test(&mddev->flush_pending))
+ schedule_work(&mddev->barrier_work);
+}
+EXPORT_SYMBOL(md_barrier_request);
static inline mddev_t *mddev_get(mddev_t *mddev)
{
mutex_init(&new->open_mutex);
mutex_init(&new->reconfig_mutex);
+ mutex_init(&new->bitmap_info.mutex);
INIT_LIST_HEAD(&new->disks);
INIT_LIST_HEAD(&new->all_mddevs);
init_timer(&new->safemode_timer);
atomic_set(&new->openers, 0);
atomic_set(&new->active_io, 0);
spin_lock_init(&new->write_lock);
+ atomic_set(&new->flush_pending, 0);
init_waitqueue_head(&new->sb_wait);
init_waitqueue_head(&new->recovery_wait);
new->reshape_position = MaxSector;
*/
int md_check_no_bitmap(mddev_t *mddev)
{
- if (!mddev->bitmap_file && !mddev->bitmap_offset)
+ if (!mddev->bitmap_info.file && !mddev->bitmap_info.offset)
return 0;
printk(KERN_ERR "%s: bitmaps are not supported for %s\n",
mdname(mddev), mddev->pers->name);
mddev->raid_disks = sb->raid_disks;
mddev->dev_sectors = sb->size * 2;
mddev->events = ev1;
- mddev->bitmap_offset = 0;
- mddev->default_bitmap_offset = MD_SB_BYTES >> 9;
+ mddev->bitmap_info.offset = 0;
+ mddev->bitmap_info.default_offset = MD_SB_BYTES >> 9;
if (mddev->minor_version >= 91) {
mddev->reshape_position = sb->reshape_position;
mddev->max_disks = MD_SB_DISKS;
if (sb->state & (1<<MD_SB_BITMAP_PRESENT) &&
- mddev->bitmap_file == NULL)
- mddev->bitmap_offset = mddev->default_bitmap_offset;
+ mddev->bitmap_info.file == NULL)
+ mddev->bitmap_info.offset =
+ mddev->bitmap_info.default_offset;
} else if (mddev->pers == NULL) {
/* Insist on good event counter while assembling */
desc->raid_disk < mddev->raid_disks */) {
set_bit(In_sync, &rdev->flags);
rdev->raid_disk = desc->raid_disk;
+ } else if (desc->state & (1<<MD_DISK_ACTIVE)) {
+ /* active but not in sync implies recovery up to
+ * reshape position. We don't know exactly where
+ * that is, so set to zero for now */
+ if (mddev->minor_version >= 91) {
+ rdev->recovery_offset = 0;
+ rdev->raid_disk = desc->raid_disk;
+ }
}
if (desc->state & (1<<MD_DISK_WRITEMOSTLY))
set_bit(WriteMostly, &rdev->flags);
sb->layout = mddev->layout;
sb->chunk_size = mddev->chunk_sectors << 9;
- if (mddev->bitmap && mddev->bitmap_file == NULL)
+ if (mddev->bitmap && mddev->bitmap_info.file == NULL)
sb->state |= (1<<MD_SB_BITMAP_PRESENT);
sb->disks[0].state = (1<<MD_DISK_REMOVED);
list_for_each_entry(rdev2, &mddev->disks, same_set) {
mdp_disk_t *d;
int desc_nr;
- if (rdev2->raid_disk >= 0 && test_bit(In_sync, &rdev2->flags)
- && !test_bit(Faulty, &rdev2->flags))
+ int is_active = test_bit(In_sync, &rdev2->flags);
+
+ if (rdev2->raid_disk >= 0 &&
+ sb->minor_version >= 91)
+ /* we have nowhere to store the recovery_offset,
+ * but if it is not below the reshape_position,
+ * we can piggy-back on that.
+ */
+ is_active = 1;
+ if (rdev2->raid_disk < 0 ||
+ test_bit(Faulty, &rdev2->flags))
+ is_active = 0;
+ if (is_active)
desc_nr = rdev2->raid_disk;
else
desc_nr = next_spare++;
d->number = rdev2->desc_nr;
d->major = MAJOR(rdev2->bdev->bd_dev);
d->minor = MINOR(rdev2->bdev->bd_dev);
- if (rdev2->raid_disk >= 0 && test_bit(In_sync, &rdev2->flags)
- && !test_bit(Faulty, &rdev2->flags))
+ if (is_active)
d->raid_disk = rdev2->raid_disk;
else
d->raid_disk = rdev2->desc_nr; /* compatibility */
if (test_bit(Faulty, &rdev2->flags))
d->state = (1<<MD_DISK_FAULTY);
- else if (test_bit(In_sync, &rdev2->flags)) {
+ else if (is_active) {
d->state = (1<<MD_DISK_ACTIVE);
- d->state |= (1<<MD_DISK_SYNC);
+ if (test_bit(In_sync, &rdev2->flags))
+ d->state |= (1<<MD_DISK_SYNC);
active++;
working++;
} else {
{
if (num_sectors && num_sectors < rdev->mddev->dev_sectors)
return 0; /* component must fit device */
- if (rdev->mddev->bitmap_offset)
+ if (rdev->mddev->bitmap_info.offset)
return 0; /* can't move bitmap */
rdev->sb_start = calc_dev_sboffset(rdev->bdev);
if (!num_sectors || num_sectors > rdev->sb_start)
mddev->raid_disks = le32_to_cpu(sb->raid_disks);
mddev->dev_sectors = le64_to_cpu(sb->size);
mddev->events = ev1;
- mddev->bitmap_offset = 0;
- mddev->default_bitmap_offset = 1024 >> 9;
+ mddev->bitmap_info.offset = 0;
+ mddev->bitmap_info.default_offset = 1024 >> 9;
mddev->recovery_cp = le64_to_cpu(sb->resync_offset);
memcpy(mddev->uuid, sb->set_uuid, 16);
mddev->max_disks = (4096-256)/2;
if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET) &&
- mddev->bitmap_file == NULL )
- mddev->bitmap_offset = (__s32)le32_to_cpu(sb->bitmap_offset);
+ mddev->bitmap_info.file == NULL )
+ mddev->bitmap_info.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);
sb->level = cpu_to_le32(mddev->level);
sb->layout = cpu_to_le32(mddev->layout);
- if (mddev->bitmap && mddev->bitmap_file == NULL) {
- sb->bitmap_offset = cpu_to_le32((__u32)mddev->bitmap_offset);
+ if (mddev->bitmap && mddev->bitmap_info.file == NULL) {
+ sb->bitmap_offset = cpu_to_le32((__u32)mddev->bitmap_info.offset);
sb->feature_map = cpu_to_le32(MD_FEATURE_BITMAP_OFFSET);
}
if (rdev->raid_disk >= 0 &&
!test_bit(In_sync, &rdev->flags)) {
- if (mddev->curr_resync_completed > rdev->recovery_offset)
- rdev->recovery_offset = mddev->curr_resync_completed;
if (rdev->recovery_offset > 0) {
sb->feature_map |=
cpu_to_le32(MD_FEATURE_RECOVERY_OFFSET);
max_sectors -= rdev->data_offset;
if (!num_sectors || num_sectors > max_sectors)
num_sectors = max_sectors;
- } else if (rdev->mddev->bitmap_offset) {
+ } else if (rdev->mddev->bitmap_info.offset) {
/* minor version 0 with bitmap we can't move */
return 0;
} else {
*/
mdk_rdev_t *rdev;
+ /* First make sure individual recovery_offsets are correct */
+ list_for_each_entry(rdev, &mddev->disks, same_set) {
+ if (rdev->raid_disk >= 0 &&
+ !test_bit(In_sync, &rdev->flags) &&
+ mddev->curr_resync_completed > rdev->recovery_offset)
+ rdev->recovery_offset = mddev->curr_resync_completed;
+
+ }
list_for_each_entry(rdev, &mddev->disks, same_set) {
if (rdev->sb_events == mddev->events ||
(nospares &&
rdev->desc_nr = i++;
rdev->raid_disk = rdev->desc_nr;
set_bit(In_sync, &rdev->flags);
- } else if (rdev->raid_disk >= mddev->raid_disks) {
+ } else if (rdev->raid_disk >= (mddev->raid_disks - min(0, mddev->delta_disks))) {
rdev->raid_disk = -1;
clear_bit(In_sync, &rdev->flags);
}
set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
mddev->sync_thread = md_register_thread(md_do_sync,
mddev,
- "%s_resync");
+ "resync");
if (!mddev->sync_thread) {
printk(KERN_ERR "%s: could not start resync"
" thread...\n",
printk(KERN_INFO "md: %s stopped.\n", mdname(mddev));
bitmap_destroy(mddev);
- if (mddev->bitmap_file) {
- restore_bitmap_write_access(mddev->bitmap_file);
- fput(mddev->bitmap_file);
- mddev->bitmap_file = NULL;
+ if (mddev->bitmap_info.file) {
+ restore_bitmap_write_access(mddev->bitmap_info.file);
+ fput(mddev->bitmap_info.file);
+ mddev->bitmap_info.file = NULL;
}
- mddev->bitmap_offset = 0;
+ mddev->bitmap_info.offset = 0;
/* make sure all md_delayed_delete calls have finished */
flush_scheduled_work();
mddev->degraded = 0;
mddev->barriers_work = 0;
mddev->safemode = 0;
+ mddev->bitmap_info.offset = 0;
+ mddev->bitmap_info.default_offset = 0;
+ mddev->bitmap_info.chunksize = 0;
+ mddev->bitmap_info.daemon_sleep = 0;
+ mddev->bitmap_info.max_write_behind = 0;
kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
if (mddev->hold_active == UNTIL_STOP)
mddev->hold_active = 0;
info.state = 0;
if (mddev->in_sync)
info.state = (1<<MD_SB_CLEAN);
- if (mddev->bitmap && mddev->bitmap_offset)
+ if (mddev->bitmap && mddev->bitmap_info.offset)
info.state = (1<<MD_SB_BITMAP_PRESENT);
info.active_disks = insync;
info.working_disks = working;
if (fd >= 0) {
if (mddev->bitmap)
return -EEXIST; /* cannot add when bitmap is present */
- mddev->bitmap_file = fget(fd);
+ mddev->bitmap_info.file = fget(fd);
- if (mddev->bitmap_file == NULL) {
+ if (mddev->bitmap_info.file == NULL) {
printk(KERN_ERR "%s: error: failed to get bitmap file\n",
mdname(mddev));
return -EBADF;
}
- err = deny_bitmap_write_access(mddev->bitmap_file);
+ err = deny_bitmap_write_access(mddev->bitmap_info.file);
if (err) {
printk(KERN_ERR "%s: error: bitmap file is already in use\n",
mdname(mddev));
- fput(mddev->bitmap_file);
- mddev->bitmap_file = NULL;
+ fput(mddev->bitmap_info.file);
+ mddev->bitmap_info.file = NULL;
return err;
}
- mddev->bitmap_offset = 0; /* file overrides offset */
+ mddev->bitmap_info.offset = 0; /* file overrides offset */
} else if (mddev->bitmap == NULL)
return -ENOENT; /* cannot remove what isn't there */
err = 0;
mddev->pers->quiesce(mddev, 0);
}
if (fd < 0) {
- if (mddev->bitmap_file) {
- restore_bitmap_write_access(mddev->bitmap_file);
- fput(mddev->bitmap_file);
+ if (mddev->bitmap_info.file) {
+ restore_bitmap_write_access(mddev->bitmap_info.file);
+ fput(mddev->bitmap_info.file);
}
- mddev->bitmap_file = NULL;
+ mddev->bitmap_info.file = NULL;
}
return err;
mddev->flags = 0;
set_bit(MD_CHANGE_DEVS, &mddev->flags);
- mddev->default_bitmap_offset = MD_SB_BYTES >> 9;
- mddev->bitmap_offset = 0;
+ mddev->bitmap_info.default_offset = MD_SB_BYTES >> 9;
+ mddev->bitmap_info.offset = 0;
mddev->reshape_position = MaxSector;
int state = 0;
/* calculate expected state,ignoring low bits */
- if (mddev->bitmap && mddev->bitmap_offset)
+ if (mddev->bitmap && mddev->bitmap_info.offset)
state |= (1 << MD_SB_BITMAP_PRESENT);
if (mddev->major_version != info->major_version ||
/* add the bitmap */
if (mddev->bitmap)
return -EEXIST;
- if (mddev->default_bitmap_offset == 0)
+ if (mddev->bitmap_info.default_offset == 0)
return -EINVAL;
- mddev->bitmap_offset = mddev->default_bitmap_offset;
+ mddev->bitmap_info.offset =
+ mddev->bitmap_info.default_offset;
mddev->pers->quiesce(mddev, 1);
rv = bitmap_create(mddev);
if (rv)
mddev->pers->quiesce(mddev, 1);
bitmap_destroy(mddev);
mddev->pers->quiesce(mddev, 0);
- mddev->bitmap_offset = 0;
+ mddev->bitmap_info.offset = 0;
}
}
md_update_sb(mddev, 1);
thread->run = run;
thread->mddev = mddev;
thread->timeout = MAX_SCHEDULE_TIMEOUT;
- thread->tsk = kthread_run(md_thread, thread, name, mdname(thread->mddev));
+ thread->tsk = kthread_run(md_thread, thread,
+ "%s_%s",
+ mdname(thread->mddev),
+ name ?: mddev->pers->name);
if (IS_ERR(thread->tsk)) {
kfree(thread);
return NULL;
unsigned long chunk_kb;
unsigned long flags;
spin_lock_irqsave(&bitmap->lock, flags);
- chunk_kb = bitmap->chunksize >> 10;
+ chunk_kb = mddev->bitmap_info.chunksize >> 10;
seq_printf(seq, "bitmap: %lu/%lu pages [%luKB], "
"%lu%s chunk",
bitmap->pages - bitmap->missing_pages,
bitmap->pages,
(bitmap->pages - bitmap->missing_pages)
<< (PAGE_SHIFT - 10),
- chunk_kb ? chunk_kb : bitmap->chunksize,
+ chunk_kb ? chunk_kb : mddev->bitmap_info.chunksize,
chunk_kb ? "KB" : "B");
if (bitmap->file) {
seq_printf(seq, ", file: ");
desc, mdname(mddev));
mddev->curr_resync = j;
}
+ mddev->curr_resync_completed = mddev->curr_resync;
while (j < max_sectors) {
sector_t sectors;
set_bit(MD_CHANGE_DEVS, &mddev->flags);
skip:
+ if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
+ /* We completed so min/max setting can be forgotten if used. */
+ if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
+ mddev->resync_min = 0;
+ mddev->resync_max = MaxSector;
+ } else if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
+ mddev->resync_min = mddev->curr_resync_completed;
mddev->curr_resync = 0;
- mddev->curr_resync_completed = 0;
- mddev->resync_min = 0;
- mddev->resync_max = MaxSector;
+ if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery))
+ mddev->curr_resync_completed = 0;
sysfs_notify(&mddev->kobj, NULL, "sync_completed");
wake_up(&resync_wait);
set_bit(MD_RECOVERY_DONE, &mddev->recovery);
if (mddev->bitmap)
- bitmap_daemon_work(mddev->bitmap);
+ bitmap_daemon_work(mddev);
if (mddev->ro)
return;
}
mddev->sync_thread = md_register_thread(md_do_sync,
mddev,
- "%s_resync");
+ "resync");
if (!mddev->sync_thread) {
printk(KERN_ERR "%s: could not start resync"
" thread...\n",
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff