1 files changed, 42 insertions, 79 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 1c2f9048e1ae..3f6203a4c7ea 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -498,61 +498,13 @@ void md_flush_request(struct mddev *mddev, struct bio *bio)
 }
 EXPORT_SYMBOL(md_flush_request);
 
-/* Support for plugging.
- * This mirrors the plugging support in request_queue, but does not
- * 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.
- */
-struct md_plug_cb {
-        struct blk_plug_cb cb;
-        struct mddev *mddev;
-};
-
-static void plugger_unplug(struct blk_plug_cb *cb)
+void md_unplug(struct blk_plug_cb *cb, bool from_schedule)
 {
-        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);
-}
-
-/* Check that an unplug wakeup will come shortly.
- * If not, wakeup the md thread immediately
- */
-int mddev_check_plugged(struct mddev *mddev)
-{
-        struct blk_plug *plug = current->plug;
-        struct md_plug_cb *mdcb;
-
-        if (!plug)
-                return 0;
-
-        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;
+        struct mddev *mddev = cb->data;
+        md_wakeup_thread(mddev->thread);
+        kfree(cb);
 }
-EXPORT_SYMBOL_GPL(mddev_check_plugged);
+EXPORT_SYMBOL(md_unplug);
 
 static inline struct mddev *mddev_get(struct mddev *mddev)
 {
@@ -602,7 +554,6 @@ void mddev_init(struct mddev *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);
@@ -1157,8 +1108,11 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
                         ret = 0;
         }
         rdev->sectors = rdev->sb_start;
-        /* Limit to 4TB as metadata cannot record more than that */
-        if (rdev->sectors >= (2ULL << 32))
+        /* Limit to 4TB as metadata cannot record more than that.
+         * (not needed for Linear and RAID0 as metadata doesn't
+         * record this size)
+         */
+        if (rdev->sectors >= (2ULL << 32) && sb->level >= 1)
                 rdev->sectors = (2ULL << 32) - 2;
 
         if (rdev->sectors < ((sector_t)sb->size) * 2 && sb->level >= 1)
@@ -1449,7 +1403,7 @@ super_90_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors)
         /* Limit to 4TB as metadata cannot record more than that.
          * 4TB == 2^32 KB, or 2*2^32 sectors.
          */
-        if (num_sectors >= (2ULL << 32))
+        if (num_sectors >= (2ULL << 32) && rdev->mddev->level >= 1)
                 num_sectors = (2ULL << 32) - 2;
         md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
                        rdev->sb_page);
@@ -2931,6 +2885,7 @@ offset_store(struct md_rdev *rdev, const char *buf, size_t len)
                  * can be sane */
                 return -EBUSY;
         rdev->data_offset = offset;
+        rdev->new_data_offset = offset;
         return len;
 }
 
@@ -3926,8 +3881,8 @@ array_state_show(struct mddev *mddev, char *page)
         return sprintf(page, "%s\n", array_states[st]);
 }
 
-static int do_md_stop(struct mddev * mddev, int ro, int is_open);
-static int md_set_readonly(struct mddev * mddev, int is_open);
+static int do_md_stop(struct mddev * mddev, int ro, struct block_device *bdev);
+static int md_set_readonly(struct mddev * mddev, struct block_device *bdev);
 static int do_md_run(struct mddev * mddev);
 static int restart_array(struct mddev *mddev);
 
@@ -3941,24 +3896,20 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
                 break;
         case clear:
                 /* stopping an active array */
-                if (atomic_read(&mddev->openers) > 0)
-                        return -EBUSY;
-                err = do_md_stop(mddev, 0, 0);
+                err = do_md_stop(mddev, 0, NULL);
                 break;
         case inactive:
                 /* stopping an active array */
-                if (mddev->pers) {
-                        if (atomic_read(&mddev->openers) > 0)
-                                return -EBUSY;
-                        err = do_md_stop(mddev, 2, 0);
-                } else
+                if (mddev->pers)
+                        err = do_md_stop(mddev, 2, NULL);
+                else
                         err = 0; /* already inactive */
                 break;
         case suspended:
                 break; /* not supported yet */
         case readonly:
                 if (mddev->pers)
-                        err = md_set_readonly(mddev, 0);
+                        err = md_set_readonly(mddev, NULL);
                 else {
                         mddev->ro = 1;
                         set_disk_ro(mddev->gendisk, 1);
@@ -3968,7 +3919,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
         case read_auto:
                 if (mddev->pers) {
                         if (mddev->ro == 0)
-                                err = md_set_readonly(mddev, 0);
+                                err = md_set_readonly(mddev, NULL);
                         else if (mddev->ro == 1)
                                 err = restart_array(mddev);
                         if (err == 0) {
@@ -5351,15 +5302,17 @@ void md_stop(struct mddev *mddev)
 }
 EXPORT_SYMBOL_GPL(md_stop);
 
-static int md_set_readonly(struct mddev *mddev, int is_open)
+static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
 {
         int err = 0;
         mutex_lock(&mddev->open_mutex);
-        if (atomic_read(&mddev->openers) > is_open) {
+        if (atomic_read(&mddev->openers) > !!bdev) {
                 printk("md: %s still in use.\n",mdname(mddev));
                 err = -EBUSY;
                 goto out;
         }
+        if (bdev)
+                sync_blockdev(bdev);
         if (mddev->pers) {
                 __md_stop_writes(mddev);
 
@@ -5381,18 +5334,26 @@ out:
  *   0 - completely stop and dis-assemble array
  *   2 - stop but do not disassemble array
  */
-static int do_md_stop(struct mddev * mddev, int mode, int is_open)
+static int do_md_stop(struct mddev * mddev, int mode,
+                      struct block_device *bdev)
 {
         struct gendisk *disk = mddev->gendisk;
         struct md_rdev *rdev;
 
         mutex_lock(&mddev->open_mutex);
-        if (atomic_read(&mddev->openers) > is_open ||
+        if (atomic_read(&mddev->openers) > !!bdev ||
             mddev->sysfs_active) {
                 printk("md: %s still in use.\n",mdname(mddev));
                 mutex_unlock(&mddev->open_mutex);
                 return -EBUSY;
         }
+        if (bdev)
+                /* It is possible IO was issued on some other
+                 * open file which was closed before we took ->open_mutex.
+                 * As that was not the last close __blkdev_put will not
+                 * have called sync_blockdev, so we must.
+                 */
+                sync_blockdev(bdev);
 
         if (mddev->pers) {
                 if (mddev->ro)
@@ -5466,7 +5427,7 @@ static void autorun_array(struct mddev *mddev)
         err = do_md_run(mddev);
         if (err) {
                 printk(KERN_WARNING "md: do_md_run() returned %d\n", err);
-                do_md_stop(mddev, 0, 0);
+                do_md_stop(mddev, 0, NULL);
         }
 }
 
@@ -5784,8 +5745,7 @@ static int add_new_disk(struct mddev * mddev, mdu_disk_info_t *info)
                         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)) {
+                     rdev->raid_disk != info->raid_disk) {
                         /* This was a hot-add request, but events doesn't
                          * match, so reject it.
                          */
@@ -6482,11 +6442,11 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
                         goto done_unlock;
 
                 case STOP_ARRAY:
-                        err = do_md_stop(mddev, 0, 1);
+                        err = do_md_stop(mddev, 0, bdev);
                         goto done_unlock;
 
                 case STOP_ARRAY_RO:
-                        err = md_set_readonly(mddev, 1);
+                        err = md_set_readonly(mddev, bdev);
                         goto done_unlock;
 
                 case BLKROSET:
@@ -6751,7 +6711,7 @@ struct md_thread *md_register_thread(void (*run) (struct mddev *), struct mddev
         thread->tsk = kthread_run(md_thread, thread,
                                   "%s_%s",
                                   mdname(thread->mddev),
-                                  name ?: mddev->pers->name);
+                                  name);
         if (IS_ERR(thread->tsk)) {
                 kfree(thread);
                 return NULL;
@@ -7298,6 +7258,7 @@ void md_do_sync(struct mddev *mddev)
         int skipped = 0;
         struct md_rdev *rdev;
         char *desc;
+        struct blk_plug plug;
 
         /* just incase thread restarts... */
         if (test_bit(MD_RECOVERY_DONE, &mddev->recovery))
@@ -7447,6 +7408,7 @@ void md_do_sync(struct mddev *mddev)
         }
         mddev->curr_resync_completed = j;
 
+        blk_start_plug(&plug);
         while (j < max_sectors) {
                 sector_t sectors;
 
@@ -7552,6 +7514,7 @@ void md_do_sync(struct mddev *mddev)
          * this also signals 'finished resyncing' to md_stop
          */
  out:
+        blk_finish_plug(&plug);
         wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active));
 
         /* tell personality that we are finished */