Merge branch 'for-linus' of git://neil.brown.name/md

* 'for-linus' of git://neil.brown.name/md:
  md: Use revalidate_disk to effect changes in size of device.
  md: allow raid5_quiesce to work properly when reshape is happening.
  md/raid5: set reshape_position correctly when reshape starts.
  md: Handle growth of v1.x metadata correctly.
  md: avoid array overflow with bad v1.x metadata
  md: when a level change reduces the number of devices, remove the excess.
  md: Push down data integrity code to personalities.
  md/raid6: release spare page at ->stop()

8 files changed, 132 insertions, 84 deletions

diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 5810fa906af0..5fe39c2a3d2b 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -220,6 +220,7 @@ static int linear_run (mddev_t *mddev)
         mddev->queue->unplug_fn = linear_unplug;
         mddev->queue->backing_dev_info.congested_fn = linear_congested;
         mddev->queue->backing_dev_info.congested_data = mddev;
+        md_integrity_register(mddev);
         return 0;
 }
 
@@ -256,6 +257,7 @@ static int linear_add(mddev_t *mddev, mdk_rdev_t *rdev)
         rcu_assign_pointer(mddev->private, newconf);
         md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
         set_capacity(mddev->gendisk, mddev->array_sectors);
+        revalidate_disk(mddev->gendisk);
         call_rcu(&oldconf->rcu, free_conf);
         return 0;
 }
diff --git a/drivers/md/md.c b/drivers/md/md.c
index d4351ff0849f..5b98bea4ff9b 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1308,7 +1308,12 @@ static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev)
         }
         if (mddev->level != LEVEL_MULTIPATH) {
                 int role;
-                role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
+                if (rdev->desc_nr < 0 ||
+                    rdev->desc_nr >= le32_to_cpu(sb->max_dev)) {
+                        role = 0xffff;
+                        rdev->desc_nr = -1;
+                } else
+                        role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
                 switch(role) {
                 case 0xffff: /* spare */
                         break;
@@ -1394,8 +1399,14 @@ static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev)
                 if (rdev2->desc_nr+1 > max_dev)
                         max_dev = rdev2->desc_nr+1;
 
-        if (max_dev > le32_to_cpu(sb->max_dev))
+        if (max_dev > le32_to_cpu(sb->max_dev)) {
+                int bmask;
                 sb->max_dev = cpu_to_le32(max_dev);
+                rdev->sb_size = max_dev * 2 + 256;
+                bmask = queue_logical_block_size(rdev->bdev->bd_disk->queue)-1;
+                if (rdev->sb_size & bmask)
+                        rdev->sb_size = (rdev->sb_size | bmask) + 1;
+        }
         for (i=0; i<max_dev;i++)
                 sb->dev_roles[i] = cpu_to_le16(0xfffe);
         
@@ -1487,37 +1498,76 @@ static int match_mddev_units(mddev_t *mddev1, mddev_t *mddev2)
 
 static LIST_HEAD(pending_raid_disks);
 
-static void md_integrity_check(mdk_rdev_t *rdev, mddev_t *mddev)
+/*
+ * Try to register data integrity profile for an mddev
+ *
+ * This is called when an array is started and after a disk has been kicked
+ * from the array. It only succeeds if all working and active component devices
+ * are integrity capable with matching profiles.
+ */
+int md_integrity_register(mddev_t *mddev)
+{
+        mdk_rdev_t *rdev, *reference = NULL;
+
+        if (list_empty(&mddev->disks))
+                return 0; /* nothing to do */
+        if (blk_get_integrity(mddev->gendisk))
+                return 0; /* already registered */
+        list_for_each_entry(rdev, &mddev->disks, same_set) {
+                /* skip spares and non-functional disks */
+                if (test_bit(Faulty, &rdev->flags))
+                        continue;
+                if (rdev->raid_disk < 0)
+                        continue;
+                /*
+                 * If at least one rdev is not integrity capable, we can not
+                 * enable data integrity for the md device.
+                 */
+                if (!bdev_get_integrity(rdev->bdev))
+                        return -EINVAL;
+                if (!reference) {
+                        /* Use the first rdev as the reference */
+                        reference = rdev;
+                        continue;
+                }
+                /* does this rdev's profile match the reference profile? */
+                if (blk_integrity_compare(reference->bdev->bd_disk,
+                                rdev->bdev->bd_disk) < 0)
+                        return -EINVAL;
+        }
+        /*
+         * All component devices are integrity capable and have matching
+         * profiles, register the common profile for the md device.
+         */
+        if (blk_integrity_register(mddev->gendisk,
+                        bdev_get_integrity(reference->bdev)) != 0) {
+                printk(KERN_ERR "md: failed to register integrity for %s\n",
+                        mdname(mddev));
+                return -EINVAL;
+        }
+        printk(KERN_NOTICE "md: data integrity on %s enabled\n",
+                mdname(mddev));
+        return 0;
+}
+EXPORT_SYMBOL(md_integrity_register);
+
+/* Disable data integrity if non-capable/non-matching disk is being added */
+void md_integrity_add_rdev(mdk_rdev_t *rdev, mddev_t *mddev)
 {
-        struct mdk_personality *pers = mddev->pers;
-        struct gendisk *disk = mddev->gendisk;
         struct blk_integrity *bi_rdev = bdev_get_integrity(rdev->bdev);
-        struct blk_integrity *bi_mddev = blk_get_integrity(disk);
+        struct blk_integrity *bi_mddev = blk_get_integrity(mddev->gendisk);
 
-        /* Data integrity passthrough not supported on RAID 4, 5 and 6 */
-        if (pers && pers->level >= 4 && pers->level <= 6)
+        if (!bi_mddev) /* nothing to do */
                 return;
-
-        /* If rdev is integrity capable, register profile for mddev */
-        if (!bi_mddev && bi_rdev) {
-                if (blk_integrity_register(disk, bi_rdev))
-                        printk(KERN_ERR "%s: %s Could not register integrity!\n",
-                               __func__, disk->disk_name);
-                else
-                        printk(KERN_NOTICE "Enabling data integrity on %s\n",
-                               disk->disk_name);
+        if (rdev->raid_disk < 0) /* skip spares */
                 return;
-        }
-
-        /* Check that mddev and rdev have matching profiles */
-        if (blk_integrity_compare(disk, rdev->bdev->bd_disk) < 0) {
-                printk(KERN_ERR "%s: %s/%s integrity mismatch!\n", __func__,
-                       disk->disk_name, rdev->bdev->bd_disk->disk_name);
-                printk(KERN_NOTICE "Disabling data integrity on %s\n",
-                       disk->disk_name);
-                blk_integrity_unregister(disk);
-        }
+        if (bi_rdev && blk_integrity_compare(mddev->gendisk,
+                                             rdev->bdev->bd_disk) >= 0)
+                return;
+        printk(KERN_NOTICE "disabling data integrity on %s\n", mdname(mddev));
+        blk_integrity_unregister(mddev->gendisk);
 }
+EXPORT_SYMBOL(md_integrity_add_rdev);
 
 static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev)
 {
@@ -1591,7 +1641,6 @@ static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev)
         /* May as well allow recovery to be retried once */
         mddev->recovery_disabled = 0;
 
-        md_integrity_check(rdev, mddev);
         return 0;
 
  fail:
@@ -2657,6 +2706,7 @@ level_store(mddev_t *mddev, const char *buf, size_t len)
         ssize_t rv = len;
         struct mdk_personality *pers;
         void *priv;
+        mdk_rdev_t *rdev;
 
         if (mddev->pers == NULL) {
                 if (len == 0)
@@ -2736,6 +2786,12 @@ level_store(mddev_t *mddev, const char *buf, size_t len)
         mddev_suspend(mddev);
         mddev->pers->stop(mddev);
         module_put(mddev->pers->owner);
+        /* Invalidate devices that are now superfluous */
+        list_for_each_entry(rdev, &mddev->disks, same_set)
+                if (rdev->raid_disk >= mddev->raid_disks) {
+                        rdev->raid_disk = -1;
+                        clear_bit(In_sync, &rdev->flags);
+                }
         mddev->pers = pers;
         mddev->private = priv;
         strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
@@ -3685,17 +3741,8 @@ 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) {
-                struct block_device *bdev = bdget_disk(mddev->gendisk, 0);
-
-                if (bdev) {
-                        mutex_lock(&bdev->bd_inode->i_mutex);
-                        i_size_write(bdev->bd_inode,
-                                     (loff_t)mddev->array_sectors << 9);
-                        mutex_unlock(&bdev->bd_inode->i_mutex);
-                        bdput(bdev);
-                }
-        }
+        if (mddev->pers)
+                revalidate_disk(mddev->gendisk);
 
         return len;
 }
@@ -4048,10 +4095,6 @@ static int do_md_run(mddev_t * mddev)
         }
         strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
 
-        if (pers->level >= 4 && pers->level <= 6)
-                /* Cannot support integrity (yet) */
-                blk_integrity_unregister(mddev->gendisk);
-
         if (mddev->reshape_position != MaxSector &&
             pers->start_reshape == NULL) {
                 /* This personality cannot handle reshaping... */
@@ -4189,6 +4232,7 @@ static int do_md_run(mddev_t * mddev)
         md_wakeup_thread(mddev->thread);
         md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
 
+        revalidate_disk(mddev->gendisk);
         mddev->changed = 1;
         md_new_event(mddev);
         sysfs_notify_dirent(mddev->sysfs_state);
@@ -5087,18 +5131,8 @@ static int update_size(mddev_t *mddev, sector_t num_sectors)
                         return -ENOSPC;
         }
         rv = mddev->pers->resize(mddev, num_sectors);
-        if (!rv) {
-                struct block_device *bdev;
-
-                bdev = bdget_disk(mddev->gendisk, 0);
-                if (bdev) {
-                        mutex_lock(&bdev->bd_inode->i_mutex);
-                        i_size_write(bdev->bd_inode,
-                                     (loff_t)mddev->array_sectors << 9);
-                        mutex_unlock(&bdev->bd_inode->i_mutex);
-                        bdput(bdev);
-                }
-        }
+        if (!rv)
+                revalidate_disk(mddev->gendisk);
         return rv;
 }
 
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 9430a110db93..78f03168baf9 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -431,5 +431,7 @@ extern int md_allow_write(mddev_t *mddev);
 extern void md_wait_for_blocked_rdev(mdk_rdev_t *rdev, mddev_t *mddev);
 extern void md_set_array_sectors(mddev_t *mddev, sector_t array_sectors);
 extern int md_check_no_bitmap(mddev_t *mddev);
+extern int md_integrity_register(mddev_t *mddev);
+void md_integrity_add_rdev(mdk_rdev_t *rdev, mddev_t *mddev);
 
 #endif /* _MD_MD_H */
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 237fe3fd235c..7140909f6662 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -313,6 +313,7 @@ static int multipath_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
                         set_bit(In_sync, &rdev->flags);
                         rcu_assign_pointer(p->rdev, rdev);
                         err = 0;
+                        md_integrity_add_rdev(rdev, mddev);
                         break;
                 }
 
@@ -345,7 +346,9 @@ static int multipath_remove_disk(mddev_t *mddev, int number)
                         /* lost the race, try later */
                         err = -EBUSY;
                         p->rdev = rdev;
+                        goto abort;
                 }
+                md_integrity_register(mddev);
         }
 abort:
 
@@ -519,7 +522,7 @@ static int multipath_run (mddev_t *mddev)
         mddev->queue->unplug_fn = multipath_unplug;
         mddev->queue->backing_dev_info.congested_fn = multipath_congested;
         mddev->queue->backing_dev_info.congested_data = mddev;
-
+        md_integrity_register(mddev);
         return 0;
 
 out_free_conf:
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 335f490dcad6..898e2bdfee47 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -351,6 +351,7 @@ static int raid0_run(mddev_t *mddev)
 
         blk_queue_merge_bvec(mddev->queue, raid0_mergeable_bvec);
         dump_zones(mddev);
+        md_integrity_register(mddev);
         return 0;
 }
 
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 0569efba0c02..8726fd7ebce5 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1144,7 +1144,7 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
                         rcu_assign_pointer(p->rdev, rdev);
                         break;
                 }
-
+        md_integrity_add_rdev(rdev, mddev);
         print_conf(conf);
         return err;
 }
@@ -1178,7 +1178,9 @@ static int raid1_remove_disk(mddev_t *mddev, int number)
                         /* lost the race, try later */
                         err = -EBUSY;
                         p->rdev = rdev;
+                        goto abort;
                 }
+                md_integrity_register(mddev);
         }
 abort:
 
@@ -2067,7 +2069,7 @@ static int run(mddev_t *mddev)
         mddev->queue->unplug_fn = raid1_unplug;
         mddev->queue->backing_dev_info.congested_fn = raid1_congested;
         mddev->queue->backing_dev_info.congested_data = mddev;
-
+        md_integrity_register(mddev);
         return 0;
 
 out_no_mem:
@@ -2132,6 +2134,7 @@ static int raid1_resize(mddev_t *mddev, sector_t sectors)
                 return -EINVAL;
         set_capacity(mddev->gendisk, mddev->array_sectors);
         mddev->changed = 1;
+        revalidate_disk(mddev->gendisk);
         if (sectors > mddev->dev_sectors &&
             mddev->recovery_cp == MaxSector) {
                 mddev->recovery_cp = mddev->dev_sectors;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 7298a5e5a183..3d9020cf6f6e 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1170,6 +1170,7 @@ static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
                         break;
                 }
 
+        md_integrity_add_rdev(rdev, mddev);
         print_conf(conf);
         return err;
 }
@@ -1203,7 +1204,9 @@ static int raid10_remove_disk(mddev_t *mddev, int number)
                         /* lost the race, try later */
                         err = -EBUSY;
                         p->rdev = rdev;
+                        goto abort;
                 }
+                md_integrity_register(mddev);
         }
 abort:
 
@@ -2225,6 +2228,7 @@ static int run(mddev_t *mddev)
 
         if (conf->near_copies < mddev->raid_disks)
                 blk_queue_merge_bvec(mddev->queue, raid10_mergeable_bvec);
+        md_integrity_register(mddev);
         return 0;
 
 out_free_conf:
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 37835538b58e..2b521ee67dfa 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3999,6 +3999,9 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski
                 return 0;
         }
 
+        /* Allow raid5_quiesce to complete */
+        wait_event(conf->wait_for_overlap, conf->quiesce != 2);
+
         if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
                 return reshape_request(mddev, sector_nr, skipped);
 
@@ -4316,6 +4319,15 @@ raid5_size(mddev_t *mddev, sector_t sectors, int raid_disks)
         return sectors * (raid_disks - conf->max_degraded);
 }
 
+static void free_conf(raid5_conf_t *conf)
+{
+        shrink_stripes(conf);
+        safe_put_page(conf->spare_page);
+        kfree(conf->disks);
+        kfree(conf->stripe_hashtbl);
+        kfree(conf);
+}
+
 static raid5_conf_t *setup_conf(mddev_t *mddev)
 {
         raid5_conf_t *conf;
@@ -4447,11 +4459,7 @@ static raid5_conf_t *setup_conf(mddev_t *mddev)
 
  abort:
         if (conf) {
-                shrink_stripes(conf);
-                safe_put_page(conf->spare_page);
-                kfree(conf->disks);
-                kfree(conf->stripe_hashtbl);
-                kfree(conf);
+                free_conf(conf);
                 return ERR_PTR(-EIO);
         } else
                 return ERR_PTR(-ENOMEM);
@@ -4629,12 +4637,8 @@ abort:
         md_unregister_thread(mddev->thread);
         mddev->thread = NULL;
         if (conf) {
-                shrink_stripes(conf);
                 print_raid5_conf(conf);
-                safe_put_page(conf->spare_page);
-                kfree(conf->disks);
-                kfree(conf->stripe_hashtbl);
-                kfree(conf);
+                free_conf(conf);
         }
         mddev->private = NULL;
         printk(KERN_ALERT "raid5: failed to run raid set %s\n", mdname(mddev));
@@ -4649,13 +4653,10 @@ static int stop(mddev_t *mddev)
 
         md_unregister_thread(mddev->thread);
         mddev->thread = NULL;
-        shrink_stripes(conf);
-        kfree(conf->stripe_hashtbl);
         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);
-        kfree(conf->disks);
-        kfree(conf);
+        free_conf(conf);
         mddev->private = NULL;
         return 0;
 }
@@ -4857,6 +4858,7 @@ static int raid5_resize(mddev_t *mddev, sector_t sectors)
                 return -EINVAL;
         set_capacity(mddev->gendisk, mddev->array_sectors);
         mddev->changed = 1;
+        revalidate_disk(mddev->gendisk);
         if (sectors > mddev->dev_sectors && mddev->recovery_cp == MaxSector) {
                 mddev->recovery_cp = mddev->dev_sectors;
                 set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
@@ -5002,7 +5004,7 @@ static int raid5_start_reshape(mddev_t *mddev)
                 spin_unlock_irqrestore(&conf->device_lock, flags);
         }
         mddev->raid_disks = conf->raid_disks;
-        mddev->reshape_position = 0;
+        mddev->reshape_position = conf->reshape_progress;
         set_bit(MD_CHANGE_DEVS, &mddev->flags);
 
         clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
@@ -5057,7 +5059,6 @@ static void end_reshape(raid5_conf_t *conf)
  */
 static void raid5_finish_reshape(mddev_t *mddev)
 {
-        struct block_device *bdev;
         raid5_conf_t *conf = mddev->private;
 
         if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
@@ -5066,15 +5067,7 @@ static void raid5_finish_reshape(mddev_t *mddev)
                         md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
                         set_capacity(mddev->gendisk, mddev->array_sectors);
                         mddev->changed = 1;
-
-                        bdev = bdget_disk(mddev->gendisk, 0);
-                        if (bdev) {
-                                mutex_lock(&bdev->bd_inode->i_mutex);
-                                i_size_write(bdev->bd_inode,
-                                             (loff_t)mddev->array_sectors << 9);
-                                mutex_unlock(&bdev->bd_inode->i_mutex);
-                                bdput(bdev);
-                        }
+                        revalidate_disk(mddev->gendisk);
                 } else {
                         int d;
                         mddev->degraded = conf->raid_disks;
@@ -5106,12 +5099,18 @@ static void raid5_quiesce(mddev_t *mddev, int state)
 
         case 1: /* stop all writes */
                 spin_lock_irq(&conf->device_lock);
-                conf->quiesce = 1;
+                /* '2' tells resync/reshape to pause so that all
+                 * active stripes can drain
+                 */
+                conf->quiesce = 2;
                 wait_event_lock_irq(conf->wait_for_stripe,
                                     atomic_read(&conf->active_stripes) == 0 &&
                                     atomic_read(&conf->active_aligned_reads) == 0,
                                     conf->device_lock, /* nothing */);
+                conf->quiesce = 1;
                 spin_unlock_irq(&conf->device_lock);
+                /* allow reshape to continue */
+                wake_up(&conf->wait_for_overlap);
                 break;
 
         case 0: /* re-enable writes */