summaryrefslogtreecommitdiffstats
path: root/drivers/md/md.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md/md.c')
-rw-r--r--drivers/md/md.c113
1 files changed, 67 insertions, 46 deletions
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 8b66e04c2ea..aa640a85bb2 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -447,48 +447,59 @@ EXPORT_SYMBOL(md_flush_request);
/* Support for plugging.
* This mirrors the plugging support in request_queue, but does not
- * require having a whole queue
+ * require having a whole queue or request structures.
+ * We allocate an md_plug_cb for each md device and each thread it gets
+ * plugged on. This links tot the private plug_handle structure in the
+ * personality data where we keep a count of the number of outstanding
+ * plugs so other code can see if a plug is active.
*/
-static void plugger_work(struct work_struct *work)
-{
- struct plug_handle *plug =
- container_of(work, struct plug_handle, unplug_work);
- plug->unplug_fn(plug);
-}
-static void plugger_timeout(unsigned long data)
-{
- struct plug_handle *plug = (void *)data;
- kblockd_schedule_work(NULL, &plug->unplug_work);
-}
-void plugger_init(struct plug_handle *plug,
- void (*unplug_fn)(struct plug_handle *))
-{
- plug->unplug_flag = 0;
- plug->unplug_fn = unplug_fn;
- init_timer(&plug->unplug_timer);
- plug->unplug_timer.function = plugger_timeout;
- plug->unplug_timer.data = (unsigned long)plug;
- INIT_WORK(&plug->unplug_work, plugger_work);
-}
-EXPORT_SYMBOL_GPL(plugger_init);
+struct md_plug_cb {
+ struct blk_plug_cb cb;
+ mddev_t *mddev;
+};
-void plugger_set_plug(struct plug_handle *plug)
+static void plugger_unplug(struct blk_plug_cb *cb)
{
- if (!test_and_set_bit(PLUGGED_FLAG, &plug->unplug_flag))
- mod_timer(&plug->unplug_timer, jiffies + msecs_to_jiffies(3)+1);
+ struct md_plug_cb *mdcb = container_of(cb, struct md_plug_cb, cb);
+ if (atomic_dec_and_test(&mdcb->mddev->plug_cnt))
+ md_wakeup_thread(mdcb->mddev->thread);
+ kfree(mdcb);
}
-EXPORT_SYMBOL_GPL(plugger_set_plug);
-int plugger_remove_plug(struct plug_handle *plug)
+/* Check that an unplug wakeup will come shortly.
+ * If not, wakeup the md thread immediately
+ */
+int mddev_check_plugged(mddev_t *mddev)
{
- if (test_and_clear_bit(PLUGGED_FLAG, &plug->unplug_flag)) {
- del_timer(&plug->unplug_timer);
- return 1;
- } else
+ struct blk_plug *plug = current->plug;
+ struct md_plug_cb *mdcb;
+
+ if (!plug)
return 0;
-}
-EXPORT_SYMBOL_GPL(plugger_remove_plug);
+ list_for_each_entry(mdcb, &plug->cb_list, cb.list) {
+ if (mdcb->cb.callback == plugger_unplug &&
+ mdcb->mddev == mddev) {
+ /* Already on the list, move to top */
+ if (mdcb != list_first_entry(&plug->cb_list,
+ struct md_plug_cb,
+ cb.list))
+ list_move(&mdcb->cb.list, &plug->cb_list);
+ return 1;
+ }
+ }
+ /* Not currently on the callback list */
+ mdcb = kmalloc(sizeof(*mdcb), GFP_ATOMIC);
+ if (!mdcb)
+ return 0;
+
+ mdcb->mddev = mddev;
+ mdcb->cb.callback = plugger_unplug;
+ atomic_inc(&mddev->plug_cnt);
+ list_add(&mdcb->cb.list, &plug->cb_list);
+ return 1;
+}
+EXPORT_SYMBOL_GPL(mddev_check_plugged);
static inline mddev_t *mddev_get(mddev_t *mddev)
{
@@ -538,6 +549,7 @@ void mddev_init(mddev_t *mddev)
atomic_set(&mddev->active, 1);
atomic_set(&mddev->openers, 0);
atomic_set(&mddev->active_io, 0);
+ atomic_set(&mddev->plug_cnt, 0);
spin_lock_init(&mddev->write_lock);
atomic_set(&mddev->flush_pending, 0);
init_waitqueue_head(&mddev->sb_wait);
@@ -3158,6 +3170,7 @@ level_store(mddev_t *mddev, const char *buf, size_t len)
mddev->layout = mddev->new_layout;
mddev->chunk_sectors = mddev->new_chunk_sectors;
mddev->delta_disks = 0;
+ mddev->degraded = 0;
if (mddev->pers->sync_request == NULL) {
/* this is now an array without redundancy, so
* it must always be in_sync
@@ -3311,7 +3324,7 @@ resync_start_store(mddev_t *mddev, const char *buf, size_t len)
char *e;
unsigned long long n = simple_strtoull(buf, &e, 10);
- if (mddev->pers)
+ if (mddev->pers && !test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
return -EBUSY;
if (cmd_match(buf, "none"))
n = MaxSector;
@@ -4334,13 +4347,19 @@ static int md_alloc(dev_t dev, char *name)
disk->fops = &md_fops;
disk->private_data = mddev;
disk->queue = mddev->queue;
+ blk_queue_flush(mddev->queue, REQ_FLUSH | REQ_FUA);
/* Allow extended partitions. This makes the
* 'mdp' device redundant, but we can't really
* remove it now.
*/
disk->flags |= GENHD_FL_EXT_DEVT;
- add_disk(disk);
mddev->gendisk = disk;
+ /* As soon as we call add_disk(), another thread could get
+ * through to md_open, so make sure it doesn't get too far
+ */
+ mutex_lock(&mddev->open_mutex);
+ add_disk(disk);
+
error = kobject_init_and_add(&mddev->kobj, &md_ktype,
&disk_to_dev(disk)->kobj, "%s", "md");
if (error) {
@@ -4354,8 +4373,7 @@ static int md_alloc(dev_t dev, char *name)
if (mddev->kobj.sd &&
sysfs_create_group(&mddev->kobj, &md_bitmap_group))
printk(KERN_DEBUG "pointless warning\n");
-
- blk_queue_flush(mddev->queue, REQ_FLUSH | REQ_FUA);
+ mutex_unlock(&mddev->open_mutex);
abort:
mutex_unlock(&disks_mutex);
if (!error && mddev->kobj.sd) {
@@ -4723,7 +4741,6 @@ static void md_clean(mddev_t *mddev)
mddev->bitmap_info.chunksize = 0;
mddev->bitmap_info.daemon_sleep = 0;
mddev->bitmap_info.max_write_behind = 0;
- mddev->plug = NULL;
}
static void __md_stop_writes(mddev_t *mddev)
@@ -5199,6 +5216,16 @@ static int add_new_disk(mddev_t * mddev, mdu_disk_info_t *info)
} else
super_types[mddev->major_version].
validate_super(mddev, rdev);
+ if ((info->state & (1<<MD_DISK_SYNC)) &&
+ (!test_bit(In_sync, &rdev->flags) ||
+ rdev->raid_disk != info->raid_disk)) {
+ /* This was a hot-add request, but events doesn't
+ * match, so reject it.
+ */
+ export_rdev(rdev);
+ return -EINVAL;
+ }
+
if (test_bit(In_sync, &rdev->flags))
rdev->saved_raid_disk = rdev->raid_disk;
else
@@ -6266,7 +6293,7 @@ static void status_resync(struct seq_file *seq, mddev_t * mddev)
* rt is a sector_t, so could be 32bit or 64bit.
* So we divide before multiply in case it is 32bit and close
* to the limit.
- * We scale the divisor (db) by 32 to avoid loosing precision
+ * We scale the divisor (db) by 32 to avoid losing precision
* near the end of resync when the number of remaining sectors
* is close to 'db'.
* We then divide rt by 32 after multiplying by db to compensate.
@@ -6688,12 +6715,6 @@ int md_allow_write(mddev_t *mddev)
}
EXPORT_SYMBOL_GPL(md_allow_write);
-void md_unplug(mddev_t *mddev)
-{
- if (mddev->plug)
- mddev->plug->unplug_fn(mddev->plug);
-}
-
#define SYNC_MARKS 10
#define SYNC_MARK_STEP (3*HZ)
void md_do_sync(mddev_t *mddev)