3 files changed, 29 insertions, 61 deletions

diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index be625475cf6d..4b22feb01a0c 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -503,16 +503,15 @@ int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
                 return 0;
         }
 
-        if (blk_stack_limits(limits, &q->limits, start << 9) < 0)
-                DMWARN("%s: target device %s is misaligned: "
+        if (bdev_stack_limits(limits, bdev, start) < 0)
+                DMWARN("%s: adding target device %s caused an alignment inconsistency: "
                        "physical_block_size=%u, logical_block_size=%u, "
                        "alignment_offset=%u, start=%llu",
                        dm_device_name(ti->table->md), bdevname(bdev, b),
                        q->limits.physical_block_size,
                        q->limits.logical_block_size,
                        q->limits.alignment_offset,
-                       (unsigned long long) start << 9);
-
+                       (unsigned long long) start << SECTOR_SHIFT);
 
         /*
          * Check if merge fn is supported.
@@ -1026,9 +1025,9 @@ combine_limits:
                  * for the table.
                  */
                 if (blk_stack_limits(limits, &ti_limits, 0) < 0)
-                        DMWARN("%s: target device "
+                        DMWARN("%s: adding target device "
                                "(start sect %llu len %llu) "
-                               "is misaligned",
+                               "caused an alignment inconsistency",
                                dm_device_name(table->md),
                                (unsigned long long) ti->begin,
                                (unsigned long long) ti->len);
@@ -1080,15 +1079,6 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
                                struct queue_limits *limits)
 {
         /*
-         * Each target device in the table has a data area that should normally
-         * be aligned such that the DM device's alignment_offset is 0.
-         * FIXME: Propagate alignment_offsets up the stack and warn of
-         *        sub-optimal or inconsistent settings.
-         */
-        limits->alignment_offset = 0;
-        limits->misaligned = 0;
-
-        /*
          * Copy table's limits to the DM device's request_queue
          */
         q->limits = *limits;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index f4f5f82f9f53..a20a71e5efd3 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -386,7 +386,9 @@ static void mddev_put(mddev_t *mddev)
         if (!atomic_dec_and_lock(&mddev->active, &all_mddevs_lock))
                 return;
         if (!mddev->raid_disks && list_empty(&mddev->disks) &&
-            !mddev->hold_active) {
+            mddev->ctime == 0 && !mddev->hold_active) {
+                /* Array is not configured at all, and not held active,
+                 * so destroy it */
                 list_del(&mddev->all_mddevs);
                 if (mddev->gendisk) {
                         /* we did a probe so need to clean up.
@@ -4073,8 +4075,10 @@ static void mddev_delayed_delete(struct work_struct *ws)
 {
         mddev_t *mddev = container_of(ws, mddev_t, del_work);
 
-        if (mddev->private == &md_redundancy_group) {
+        if (mddev->private) {
                 sysfs_remove_group(&mddev->kobj, &md_redundancy_group);
+                if (mddev->private != (void*)1)
+                        sysfs_remove_group(&mddev->kobj, mddev->private);
                 if (mddev->sysfs_action)
                         sysfs_put(mddev->sysfs_action);
                 mddev->sysfs_action = NULL;
@@ -4285,10 +4289,7 @@ static int do_md_run(mddev_t * mddev)
                 sysfs_notify_dirent(rdev->sysfs_state);
         }
 
-        md_probe(mddev->unit, NULL, NULL);
         disk = mddev->gendisk;
-        if (!disk)
-                return -ENOMEM;
 
         spin_lock(&pers_lock);
         pers = find_pers(mddev->level, mddev->clevel);
@@ -4355,7 +4356,7 @@ static int do_md_run(mddev_t * mddev)
         mddev->barriers_work = 1;
         mddev->ok_start_degraded = start_dirty_degraded;
 
-        if (start_readonly)
+        if (start_readonly && mddev->ro == 0)
                 mddev->ro = 2; /* read-only, but switch on first write */
 
         err = mddev->pers->run(mddev);
@@ -4419,33 +4420,6 @@ static int do_md_run(mddev_t * mddev)
 
         set_capacity(disk, mddev->array_sectors);
 
-        /* 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 && !mddev->sync_thread) {
-                int spares = 0;
-                list_for_each_entry(rdev, &mddev->disks, same_set)
-                        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,
-                                                                "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;
-                        }
-                }
-        }
         md_wakeup_thread(mddev->thread);
         md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
 
@@ -4555,8 +4529,8 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
                         mddev->queue->unplug_fn = NULL;
                         mddev->queue->backing_dev_info.congested_fn = NULL;
                         module_put(mddev->pers->owner);
-                        if (mddev->pers->sync_request)
-                                mddev->private = &md_redundancy_group;
+                        if (mddev->pers->sync_request && mddev->private == NULL)
+                                mddev->private = (void*)1;
                         mddev->pers = NULL;
                         /* tell userspace to handle 'inactive' */
                         sysfs_notify_dirent(mddev->sysfs_state);
@@ -4603,9 +4577,6 @@ out:
                 }
                 mddev->bitmap_info.offset = 0;
 
-                /* make sure all md_delayed_delete calls have finished */
-                flush_scheduled_work();
-
                 export_array(mddev);
 
                 mddev->array_sectors = 0;
@@ -5262,6 +5233,10 @@ static int set_array_info(mddev_t * mddev, mdu_array_info_t *info)
                 mddev->minor_version = info->minor_version;
                 mddev->patch_version = info->patch_version;
                 mddev->persistent = !info->not_persistent;
+                /* ensure mddev_put doesn't delete this now that there
+                 * is some minimal configuration.
+                 */
+                mddev->ctime         = get_seconds();
                 return 0;
         }
         mddev->major_version = MD_MAJOR_VERSION;
@@ -6494,10 +6469,11 @@ void md_do_sync(mddev_t *mddev)
                 mddev->curr_resync = 2;
 
         try_again:
-                if (kthread_should_stop()) {
+                if (kthread_should_stop())
                         set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+
+                if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
                         goto skip;
-                }
                 for_each_mddev(mddev2, tmp) {
                         if (mddev2 == mddev)
                                 continue;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index e84204eb12df..ceb24afdc147 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5136,9 +5136,8 @@ static int stop(mddev_t *mddev)
         mddev->thread = NULL;
         mddev->queue->backing_dev_info.congested_fn = NULL;
         blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
-        sysfs_remove_group(&mddev->kobj, &raid5_attrs_group);
         free_conf(conf);
-        mddev->private = NULL;
+        mddev->private = &raid5_attrs_group;
         return 0;
 }
 
@@ -5464,11 +5463,11 @@ static int raid5_start_reshape(mddev_t *mddev)
                     !test_bit(Faulty, &rdev->flags)) {
                         if (raid5_add_disk(mddev, rdev) == 0) {
                                 char nm[20];
-                                if (rdev->raid_disk >= conf->previous_raid_disks)
+                                if (rdev->raid_disk >= conf->previous_raid_disks) {
                                         set_bit(In_sync, &rdev->flags);
-                                else
+                                        added_devices++;
+                                } else
                                         rdev->recovery_offset = 0;
-                                added_devices++;
                                 sprintf(nm, "rd%d", rdev->raid_disk);
                                 if (sysfs_create_link(&mddev->kobj,
                                                       &rdev->kobj, nm))
@@ -5480,9 +5479,12 @@ static int raid5_start_reshape(mddev_t *mddev)
                                 break;
                 }
 
+        /* When a reshape changes the number of devices, ->degraded
+         * is measured against the large of the pre and post number of
+         * devices.*/
         if (mddev->delta_disks > 0) {
                 spin_lock_irqsave(&conf->device_lock, flags);
-                mddev->degraded = (conf->raid_disks - conf->previous_raid_disks)
+                mddev->degraded += (conf->raid_disks - conf->previous_raid_disks)
                         - added_devices;
                 spin_unlock_irqrestore(&conf->device_lock, flags);
         }