8 files changed, 144 insertions, 62 deletions

diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 8a2f767f26d8..0ed7f6bc2a7f 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -216,7 +216,6 @@ static int linear_run (mddev_t *mddev)
 
         if (md_check_no_bitmap(mddev))
                 return -EINVAL;
-        mddev->queue->queue_lock = &mddev->queue->__queue_lock;
         conf = linear_conf(mddev, mddev->raid_disks);
 
         if (!conf)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index b76cfc89e1b5..818313e277e7 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -287,6 +287,7 @@ static int md_make_request(struct request_queue *q, struct bio *bio)
         mddev_t *mddev = q->queuedata;
         int rv;
         int cpu;
+        unsigned int sectors;
 
         if (mddev == NULL || mddev->pers == NULL
             || !mddev->ready) {
@@ -311,12 +312,16 @@ static int md_make_request(struct request_queue *q, struct bio *bio)
         atomic_inc(&mddev->active_io);
         rcu_read_unlock();
 
+        /*
+         * save the sectors now since our bio can
+         * go away inside make_request
+         */
+        sectors = bio_sectors(bio);
         rv = mddev->pers->make_request(mddev, bio);
 
         cpu = part_stat_lock();
         part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
-        part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw],
-                      bio_sectors(bio));
+        part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors);
         part_stat_unlock();
 
         if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended)
@@ -548,6 +553,9 @@ static mddev_t * mddev_find(dev_t unit)
 {
         mddev_t *mddev, *new = NULL;
 
+        if (unit && MAJOR(unit) != MD_MAJOR)
+                unit &= ~((1<<MdpMinorShift)-1);
+
  retry:
         spin_lock(&all_mddevs_lock);
 
@@ -1947,8 +1955,6 @@ static int lock_rdev(mdk_rdev_t *rdev, dev_t dev, int shared)
                         __bdevname(dev, b));
                 return PTR_ERR(bdev);
         }
-        if (!shared)
-                set_bit(AllReserved, &rdev->flags);
         rdev->bdev = bdev;
         return err;
 }
@@ -2465,6 +2471,9 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len)
                 if (rdev->raid_disk != -1)
                         return -EBUSY;
 
+                if (test_bit(MD_RECOVERY_RUNNING, &rdev->mddev->recovery))
+                        return -EBUSY;
+
                 if (rdev->mddev->pers->hot_add_disk == NULL)
                         return -EINVAL;
 
@@ -2610,12 +2619,11 @@ rdev_size_store(mdk_rdev_t *rdev, const char *buf, size_t len)
 
                         mddev_lock(mddev);
                         list_for_each_entry(rdev2, &mddev->disks, same_set)
-                                if (test_bit(AllReserved, &rdev2->flags) ||
-                                    (rdev->bdev == rdev2->bdev &&
-                                     rdev != rdev2 &&
-                                     overlaps(rdev->data_offset, rdev->sectors,
-                                              rdev2->data_offset,
-                                              rdev2->sectors))) {
+                                if (rdev->bdev == rdev2->bdev &&
+                                    rdev != rdev2 &&
+                                    overlaps(rdev->data_offset, rdev->sectors,
+                                             rdev2->data_offset,
+                                             rdev2->sectors)) {
                                         overlap = 1;
                                         break;
                                 }
@@ -4133,10 +4141,10 @@ array_size_store(mddev_t *mddev, const char *buf, size_t len)
         }
 
         mddev->array_sectors = sectors;
-        set_capacity(mddev->gendisk, mddev->array_sectors);
-        if (mddev->pers)
+        if (mddev->pers) {
+                set_capacity(mddev->gendisk, mddev->array_sectors);
                 revalidate_disk(mddev->gendisk);
-
+        }
         return len;
 }
 
@@ -4619,6 +4627,7 @@ static int do_md_run(mddev_t *mddev)
         }
         set_capacity(mddev->gendisk, mddev->array_sectors);
         revalidate_disk(mddev->gendisk);
+        mddev->changed = 1;
         kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
 out:
         return err;
@@ -4707,6 +4716,7 @@ static void md_clean(mddev_t *mddev)
         mddev->sync_speed_min = mddev->sync_speed_max = 0;
         mddev->recovery = 0;
         mddev->in_sync = 0;
+        mddev->changed = 0;
         mddev->degraded = 0;
         mddev->safemode = 0;
         mddev->bitmap_info.offset = 0;
@@ -4822,6 +4832,7 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
 
                 set_capacity(disk, 0);
                 mutex_unlock(&mddev->open_mutex);
+                mddev->changed = 1;
                 revalidate_disk(disk);
 
                 if (mddev->ro)
@@ -5578,6 +5589,8 @@ static int update_raid_disks(mddev_t *mddev, int raid_disks)
         mddev->delta_disks = raid_disks - mddev->raid_disks;
 
         rv = mddev->pers->check_reshape(mddev);
+        if (rv < 0)
+                mddev->delta_disks = 0;
         return rv;
 }
 
@@ -6004,7 +6017,7 @@ static int md_open(struct block_device *bdev, fmode_t mode)
         atomic_inc(&mddev->openers);
         mutex_unlock(&mddev->open_mutex);
 
-        check_disk_size_change(mddev->gendisk, bdev);
+        check_disk_change(bdev);
  out:
         return err;
 }
@@ -6019,6 +6032,21 @@ static int md_release(struct gendisk *disk, fmode_t mode)
 
         return 0;
 }
+
+static int md_media_changed(struct gendisk *disk)
+{
+        mddev_t *mddev = disk->private_data;
+
+        return mddev->changed;
+}
+
+static int md_revalidate(struct gendisk *disk)
+{
+        mddev_t *mddev = disk->private_data;
+
+        mddev->changed = 0;
+        return 0;
+}
 static const struct block_device_operations md_fops =
 {
         .owner          = THIS_MODULE,
@@ -6029,6 +6057,8 @@ static const struct block_device_operations md_fops =
         .compat_ioctl   = md_compat_ioctl,
 #endif
         .getgeo         = md_getgeo,
+        .media_changed  = md_media_changed,
+        .revalidate_disk= md_revalidate,
 };
 
 static int md_thread(void * arg)
@@ -6985,9 +7015,6 @@ void md_do_sync(mddev_t *mddev)
         } else if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
                 mddev->resync_min = mddev->curr_resync_completed;
         mddev->curr_resync = 0;
-        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);
         md_wakeup_thread(mddev->thread);
@@ -7028,7 +7055,7 @@ static int remove_and_add_spares(mddev_t *mddev)
                         }
                 }
 
-        if (mddev->degraded && ! mddev->ro && !mddev->recovery_disabled) {
+        if (mddev->degraded && !mddev->recovery_disabled) {
                 list_for_each_entry(rdev, &mddev->disks, same_set) {
                         if (rdev->raid_disk >= 0 &&
                             !test_bit(In_sync, &rdev->flags) &&
@@ -7151,7 +7178,20 @@ void md_check_recovery(mddev_t *mddev)
                         /* Only thing we do on a ro array is remove
                          * failed devices.
                          */
-                        remove_and_add_spares(mddev);
+                        mdk_rdev_t *rdev;
+                        list_for_each_entry(rdev, &mddev->disks, same_set)
+                                if (rdev->raid_disk >= 0 &&
+                                    !test_bit(Blocked, &rdev->flags) &&
+                                    test_bit(Faulty, &rdev->flags) &&
+                                    atomic_read(&rdev->nr_pending)==0) {
+                                        if (mddev->pers->hot_remove_disk(
+                                                    mddev, rdev->raid_disk)==0) {
+                                                char nm[20];
+                                                sprintf(nm,"rd%d", rdev->raid_disk);
+                                                sysfs_remove_link(&mddev->kobj, nm);
+                                                rdev->raid_disk = -1;
+                                        }
+                                }
                         clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
                         goto unlock;
                 }
diff --git a/drivers/md/md.h b/drivers/md/md.h
index eec517ced31a..12215d437fcc 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -93,8 +93,6 @@ struct mdk_rdev_s
 #define Faulty          1               /* device is known to have a fault */
 #define In_sync         2               /* device is in_sync with rest of array */
 #define WriteMostly     4               /* Avoid reading if at all possible */
-#define AllReserved     6               /* If whole device is reserved for
-                                         * one array */
 #define AutoDetected    7               /* added by auto-detect */
 #define Blocked         8               /* An error occured on an externally
                                          * managed array, don't allow writes
@@ -276,6 +274,8 @@ struct mddev_s
         atomic_t                        active;         /* general refcount */
         atomic_t                        openers;        /* number of active opens */
 
+        int                             changed;        /* True if we might need to
+                                                         * reread partition info */
         int                             degraded;       /* whether md should consider
                                                          * adding a spare
                                                          */
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 6d7ddf32ef2e..3a62d440e27b 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -435,7 +435,6 @@ static int multipath_run (mddev_t *mddev)
          * bookkeeping area. [whatever we allocate in multipath_run(),
          * should be freed in multipath_stop()]
          */
-        mddev->queue->queue_lock = &mddev->queue->__queue_lock;
 
         conf = kzalloc(sizeof(multipath_conf_t), GFP_KERNEL);
         mddev->private = conf;
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index a39f4c355e55..c0ac457f1218 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -179,6 +179,14 @@ static int create_strip_zones(mddev_t *mddev, raid0_conf_t **private_conf)
                         rdev1->new_raid_disk = j;
                 }
 
+                if (mddev->level == 1) {
+                        /* taiking over a raid1 array-
+                         * we have only one active disk
+                         */
+                        j = 0;
+                        rdev1->new_raid_disk = j;
+                }
+
                 if (j < 0 || j >= mddev->raid_disks) {
                         printk(KERN_ERR "md/raid0:%s: bad disk number %d - "
                                "aborting!\n", mdname(mddev), j);
@@ -353,7 +361,6 @@ static int raid0_run(mddev_t *mddev)
         if (md_check_no_bitmap(mddev))
                 return -EINVAL;
         blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
-        mddev->queue->queue_lock = &mddev->queue->__queue_lock;
 
         /* if private is not null, we are here after takeover */
         if (mddev->private == NULL) {
@@ -644,12 +651,39 @@ static void *raid0_takeover_raid10(mddev_t *mddev)
         return priv_conf;
 }
 
+static void *raid0_takeover_raid1(mddev_t *mddev)
+{
+        raid0_conf_t *priv_conf;
+
+        /* Check layout:
+         *  - (N - 1) mirror drives must be already faulty
+         */
+        if ((mddev->raid_disks - 1) != mddev->degraded) {
+                printk(KERN_ERR "md/raid0:%s: (N - 1) mirrors drives must be already faulty!\n",
+                       mdname(mddev));
+                return ERR_PTR(-EINVAL);
+        }
+
+        /* Set new parameters */
+        mddev->new_level = 0;
+        mddev->new_layout = 0;
+        mddev->new_chunk_sectors = 128; /* by default set chunk size to 64k */
+        mddev->delta_disks = 1 - mddev->raid_disks;
+        mddev->raid_disks = 1;
+        /* make sure it will be not marked as dirty */
+        mddev->recovery_cp = MaxSector;
+
+        create_strip_zones(mddev, &priv_conf);
+        return priv_conf;
+}
+
 static void *raid0_takeover(mddev_t *mddev)
 {
         /* raid0 can take over:
          *  raid4 - if all data disks are active.
          *  raid5 - providing it is Raid4 layout and one disk is faulty
          *  raid10 - assuming we have all necessary active disks
+         *  raid1 - with (N -1) mirror drives faulty
          */
         if (mddev->level == 4)
                 return raid0_takeover_raid45(mddev);
@@ -665,6 +699,12 @@ static void *raid0_takeover(mddev_t *mddev)
         if (mddev->level == 10)
                 return raid0_takeover_raid10(mddev);
 
+        if (mddev->level == 1)
+                return raid0_takeover_raid1(mddev);
+
+        printk(KERN_ERR "Takeover from raid%i to raid0 not supported\n",
+                mddev->level);
+
         return ERR_PTR(-EINVAL);
 }
 
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index a23ffa397ba9..06cd712807d0 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -593,7 +593,10 @@ static int flush_pending_writes(conf_t *conf)
         if (conf->pending_bio_list.head) {
                 struct bio *bio;
                 bio = bio_list_get(&conf->pending_bio_list);
+                /* Only take the spinlock to quiet a warning */
+                spin_lock(conf->mddev->queue->queue_lock);
                 blk_remove_plug(conf->mddev->queue);
+                spin_unlock(conf->mddev->queue->queue_lock);
                 spin_unlock_irq(&conf->device_lock);
                 /* flush any pending bitmap writes to
                  * disk before proceeding w/ I/O */
@@ -959,7 +962,7 @@ static int make_request(mddev_t *mddev, struct bio * bio)
                 atomic_inc(&r1_bio->remaining);
                 spin_lock_irqsave(&conf->device_lock, flags);
                 bio_list_add(&conf->pending_bio_list, mbio);
-                blk_plug_device(mddev->queue);
+                blk_plug_device_unlocked(mddev->queue);
                 spin_unlock_irqrestore(&conf->device_lock, flags);
         }
         r1_bio_write_done(r1_bio, bio->bi_vcnt, behind_pages, behind_pages != NULL);
@@ -2021,7 +2024,6 @@ static int run(mddev_t *mddev)
         if (IS_ERR(conf))
                 return PTR_ERR(conf);
 
-        mddev->queue->queue_lock = &conf->device_lock;
         list_for_each_entry(rdev, &mddev->disks, same_set) {
                 disk_stack_limits(mddev->gendisk, rdev->bdev,
                                   rdev->data_offset << 9);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 69b659544390..747d061d8e05 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -662,7 +662,10 @@ static int flush_pending_writes(conf_t *conf)
         if (conf->pending_bio_list.head) {
                 struct bio *bio;
                 bio = bio_list_get(&conf->pending_bio_list);
+                /* Spinlock only taken to quiet a warning */
+                spin_lock(conf->mddev->queue->queue_lock);
                 blk_remove_plug(conf->mddev->queue);
+                spin_unlock(conf->mddev->queue->queue_lock);
                 spin_unlock_irq(&conf->device_lock);
                 /* flush any pending bitmap writes to disk
                  * before proceeding w/ I/O */
@@ -971,7 +974,7 @@ static int make_request(mddev_t *mddev, struct bio * bio)
                 atomic_inc(&r10_bio->remaining);
                 spin_lock_irqsave(&conf->device_lock, flags);
                 bio_list_add(&conf->pending_bio_list, mbio);
-                blk_plug_device(mddev->queue);
+                blk_plug_device_unlocked(mddev->queue);
                 spin_unlock_irqrestore(&conf->device_lock, flags);
         }
 
@@ -2304,8 +2307,6 @@ static int run(mddev_t *mddev)
         if (!conf)
                 goto out;
 
-        mddev->queue->queue_lock = &conf->device_lock;
-
         mddev->thread = conf->thread;
         conf->thread = NULL;
 
@@ -2463,11 +2464,13 @@ static void *raid10_takeover_raid0(mddev_t *mddev)
         mddev->recovery_cp = MaxSector;
 
         conf = setup_conf(mddev);
-        if (!IS_ERR(conf))
+        if (!IS_ERR(conf)) {
                 list_for_each_entry(rdev, &mddev->disks, same_set)
                         if (rdev->raid_disk >= 0)
                                 rdev->new_raid_disk = rdev->raid_disk * 2;
-                
+                conf->barrier = 1;
+        }
+
         return conf;
 }
 
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 5044babfcda0..78536fdbd87f 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5204,7 +5204,6 @@ static int run(mddev_t *mddev)
 
                 mddev->queue->backing_dev_info.congested_data = mddev;
                 mddev->queue->backing_dev_info.congested_fn = raid5_congested;
-                mddev->queue->queue_lock = &conf->device_lock;
                 mddev->queue->unplug_fn = raid5_unplug_queue;
 
                 chunk_size = mddev->chunk_sectors << 9;
@@ -5517,7 +5516,6 @@ static int raid5_start_reshape(mddev_t *mddev)
         raid5_conf_t *conf = mddev->private;
         mdk_rdev_t *rdev;
         int spares = 0;
-        int added_devices = 0;
         unsigned long flags;
 
         if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
@@ -5527,8 +5525,8 @@ static int raid5_start_reshape(mddev_t *mddev)
                 return -ENOSPC;
 
         list_for_each_entry(rdev, &mddev->disks, same_set)
-                if ((rdev->raid_disk < 0 || rdev->raid_disk >= conf->raid_disks)
-                     && !test_bit(Faulty, &rdev->flags))
+                if (!test_bit(In_sync, &rdev->flags)
+                    && !test_bit(Faulty, &rdev->flags))
                         spares++;
 
         if (spares - mddev->degraded < mddev->delta_disks - conf->max_degraded)
@@ -5571,34 +5569,35 @@ static int raid5_start_reshape(mddev_t *mddev)
          * to correctly record the "partially reconstructed" state of
          * such devices during the reshape and confusion could result.
          */
-        if (mddev->delta_disks >= 0)
-            list_for_each_entry(rdev, &mddev->disks, same_set)
-                if (rdev->raid_disk < 0 &&
-                    !test_bit(Faulty, &rdev->flags)) {
-                        if (raid5_add_disk(mddev, rdev) == 0) {
-                                char nm[20];
-                                if (rdev->raid_disk >= conf->previous_raid_disks) {
-                                        set_bit(In_sync, &rdev->flags);
-                                        added_devices++;
-                                } else
-                                        rdev->recovery_offset = 0;
-                                sprintf(nm, "rd%d", rdev->raid_disk);
-                                if (sysfs_create_link(&mddev->kobj,
-                                                      &rdev->kobj, nm))
-                                        /* Failure here is OK */;
-                        } else
-                                break;
-                } else if (rdev->raid_disk >= conf->previous_raid_disks
-                           && !test_bit(Faulty, &rdev->flags)) {
-                        /* This is a spare that was manually added */
-                        set_bit(In_sync, &rdev->flags);
-                        added_devices++;
-                }
+        if (mddev->delta_disks >= 0) {
+                int added_devices = 0;
+                list_for_each_entry(rdev, &mddev->disks, same_set)
+                        if (rdev->raid_disk < 0 &&
+                            !test_bit(Faulty, &rdev->flags)) {
+                                if (raid5_add_disk(mddev, rdev) == 0) {
+                                        char nm[20];
+                                        if (rdev->raid_disk
+                                            >= conf->previous_raid_disks) {
+                                                set_bit(In_sync, &rdev->flags);
+                                                added_devices++;
+                                        } else
+                                                rdev->recovery_offset = 0;
+                                        sprintf(nm, "rd%d", rdev->raid_disk);
+                                        if (sysfs_create_link(&mddev->kobj,
+                                                              &rdev->kobj, nm))
+                                                /* Failure here is OK */;
+                                }
+                        } else if (rdev->raid_disk >= conf->previous_raid_disks
+                                   && !test_bit(Faulty, &rdev->flags)) {
+                                /* This is a spare that was manually added */
+                                set_bit(In_sync, &rdev->flags);
+                                added_devices++;
+                        }
 
-        /* When a reshape changes the number of devices, ->degraded
-         * is measured against the larger of the pre and post number of
-         * devices.*/
-        if (mddev->delta_disks > 0) {
+                /* When a reshape changes the number of devices,
+                 * ->degraded is measured against the larger of the
+                 * pre and post number of devices.
+                 */
                 spin_lock_irqsave(&conf->device_lock, flags);
                 mddev->degraded += (conf->raid_disks - conf->previous_raid_disks)
                         - added_devices;