1 files changed, 148 insertions, 103 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 09be637d52cb..9dd872000cec 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -359,6 +359,7 @@ static mddev_t * mddev_find(dev_t unit)
         else
                 new->md_minor = MINOR(unit) >> MdpMinorShift;
 
+        mutex_init(&new->open_mutex);
         mutex_init(&new->reconfig_mutex);
         INIT_LIST_HEAD(&new->disks);
         INIT_LIST_HEAD(&new->all_mddevs);
@@ -1308,7 +1309,12 @@ 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 +1400,14 @@ 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 +1499,76 @@ 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 +1642,6 @@ 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:
@@ -1756,9 +1806,10 @@ static void print_sb_1(struct mdp_superblock_1 *sb)
         __u8 *uuid;
 
         uuid = sb->set_uuid;
-        printk(KERN_INFO "md:  SB: (V:%u) (F:0x%08x) Array-ID:<%02x%02x%02x%02x"
-                        ":%02x%02x:%02x%02x:%02x%02x:%02x%02x%02x%02x%02x%02x>\n"
-               KERN_INFO "md:    Name: \"%s\" CT:%llu\n",
+        printk(KERN_INFO
+               "md:  SB: (V:%u) (F:0x%08x) Array-ID:<%02x%02x%02x%02x"
+               ":%02x%02x:%02x%02x:%02x%02x:%02x%02x%02x%02x%02x%02x>\n"
+               "md:    Name: \"%s\" CT:%llu\n",
                 le32_to_cpu(sb->major_version),
                 le32_to_cpu(sb->feature_map),
                 uuid[0], uuid[1], uuid[2], uuid[3],
@@ -1770,12 +1821,13 @@ static void print_sb_1(struct mdp_superblock_1 *sb)
                        & MD_SUPERBLOCK_1_TIME_SEC_MASK);
 
         uuid = sb->device_uuid;
-        printk(KERN_INFO "md:       L%u SZ%llu RD:%u LO:%u CS:%u DO:%llu DS:%llu SO:%llu"
+        printk(KERN_INFO
+               "md:       L%u SZ%llu RD:%u LO:%u CS:%u DO:%llu DS:%llu SO:%llu"
                         " RO:%llu\n"
-               KERN_INFO "md:     Dev:%08x UUID: %02x%02x%02x%02x:%02x%02x:%02x%02x:%02x%02x"
-                        ":%02x%02x%02x%02x%02x%02x\n"
-               KERN_INFO "md:       (F:0x%08x) UT:%llu Events:%llu ResyncOffset:%llu CSUM:0x%08x\n"
-               KERN_INFO "md:         (MaxDev:%u) \n",
+               "md:     Dev:%08x UUID: %02x%02x%02x%02x:%02x%02x:%02x%02x:%02x%02x"
+                        ":%02x%02x%02x%02x%02x%02x\n"
+               "md:       (F:0x%08x) UT:%llu Events:%llu ResyncOffset:%llu CSUM:0x%08x\n"
+               "md:         (MaxDev:%u) \n",
                 le32_to_cpu(sb->level),
                 (unsigned long long)le64_to_cpu(sb->size),
                 le32_to_cpu(sb->raid_disks),
@@ -1923,17 +1975,14 @@ repeat:
                 /* otherwise we have to go forward and ... */
                 mddev->events ++;
                 if (!mddev->in_sync || mddev->recovery_cp != MaxSector) { /* not clean */
-                        /* .. if the array isn't clean, insist on an odd 'events' */
-                        if ((mddev->events&1)==0) {
-                                mddev->events++;
+                        /* .. if the array isn't clean, an 'even' event must also go
+                         * to spares. */
+                        if ((mddev->events&1)==0)
                                 nospares = 0;
-                        }
                 } else {
-                        /* otherwise insist on an even 'events' (for clean states) */
-                        if ((mddev->events&1)) {
-                                mddev->events++;
+                        /* otherwise an 'odd' event must go to spares */
+                        if ((mddev->events&1))
                                 nospares = 0;
-                        }
                 }
         }
 
@@ -2655,6 +2704,7 @@ 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)
@@ -2734,6 +2784,12 @@ 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));
@@ -3543,6 +3599,7 @@ max_sync_store(mddev_t *mddev, const char *buf, size_t len)
                 if (max < mddev->resync_min)
                         return -EINVAL;
                 if (max < mddev->resync_max &&
+                    mddev->ro == 0 &&
                     test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
                         return -EBUSY;
 
@@ -3573,7 +3630,8 @@ suspend_lo_store(mddev_t *mddev, const char *buf, size_t len)
         char *e;
         unsigned long long new = simple_strtoull(buf, &e, 10);
 
-        if (mddev->pers->quiesce == NULL)
+        if (mddev->pers == NULL || 
+            mddev->pers->quiesce == NULL)
                 return -EINVAL;
         if (buf == e || (*e && *e != '\n'))
                 return -EINVAL;
@@ -3601,7 +3659,8 @@ suspend_hi_store(mddev_t *mddev, const char *buf, size_t len)
         char *e;
         unsigned long long new = simple_strtoull(buf, &e, 10);
 
-        if (mddev->pers->quiesce == NULL)
+        if (mddev->pers == NULL ||
+            mddev->pers->quiesce == NULL)
                 return -EINVAL;
         if (buf == e || (*e && *e != '\n'))
                 return -EINVAL;
@@ -3681,17 +3740,8 @@ 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;
 }
@@ -3844,11 +3894,9 @@ static int md_alloc(dev_t dev, char *name)
         flush_scheduled_work();
 
         mutex_lock(&disks_mutex);
-        if (mddev->gendisk) {
-                mutex_unlock(&disks_mutex);
-                mddev_put(mddev);
-                return -EEXIST;
-        }
+        error = -EEXIST;
+        if (mddev->gendisk)
+                goto abort;
 
         if (name) {
                 /* Need to ensure that 'name' is not a duplicate.
@@ -3860,17 +3908,15 @@ static int md_alloc(dev_t dev, char *name)
                         if (mddev2->gendisk &&
                             strcmp(mddev2->gendisk->disk_name, name) == 0) {
                                 spin_unlock(&all_mddevs_lock);
-                                return -EEXIST;
+                                goto abort;
                         }
                 spin_unlock(&all_mddevs_lock);
         }
 
+        error = -ENOMEM;
         mddev->queue = blk_alloc_queue(GFP_KERNEL);
-        if (!mddev->queue) {
-                mutex_unlock(&disks_mutex);
-                mddev_put(mddev);
-                return -ENOMEM;
-        }
+        if (!mddev->queue)
+                goto abort;
         mddev->queue->queuedata = mddev;
 
         /* Can be unlocked because the queue is new: no concurrency */
@@ -3880,11 +3926,9 @@ static int md_alloc(dev_t dev, char *name)
 
         disk = alloc_disk(1 << shift);
         if (!disk) {
-                mutex_unlock(&disks_mutex);
                 blk_cleanup_queue(mddev->queue);
                 mddev->queue = NULL;
-                mddev_put(mddev);
-                return -ENOMEM;
+                goto abort;
         }
         disk->major = MAJOR(mddev->unit);
         disk->first_minor = unit << shift;
@@ -3906,16 +3950,22 @@ static int md_alloc(dev_t dev, char *name)
         mddev->gendisk = disk;
         error = kobject_init_and_add(&mddev->kobj, &md_ktype,
                                      &disk_to_dev(disk)->kobj, "%s", "md");
-        mutex_unlock(&disks_mutex);
-        if (error)
+        if (error) {
+                /* This isn't possible, but as kobject_init_and_add is marked
+                 * __must_check, we must do something with the result
+                 */
                 printk(KERN_WARNING "md: cannot register %s/md - name in use\n",
                        disk->disk_name);
-        else {
+                error = 0;
+        }
+ abort:
+        mutex_unlock(&disks_mutex);
+        if (!error) {
                 kobject_uevent(&mddev->kobj, KOBJ_ADD);
                 mddev->sysfs_state = sysfs_get_dirent(mddev->kobj.sd, "array_state");
         }
         mddev_put(mddev);
-        return 0;
+        return error;
 }
 
 static struct kobject *md_probe(dev_t dev, int *part, void *data)
@@ -4044,10 +4094,6 @@ 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... */
@@ -4185,6 +4231,7 @@ 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);
@@ -4256,12 +4303,11 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
         struct gendisk *disk = mddev->gendisk;
         mdk_rdev_t *rdev;
 
+        mutex_lock(&mddev->open_mutex);
         if (atomic_read(&mddev->openers) > is_open) {
                 printk("md: %s still in use.\n",mdname(mddev));
-                return -EBUSY;
-        }
-
-        if (mddev->pers) {
+                err = -EBUSY;
+        } else if (mddev->pers) {
 
                 if (mddev->sync_thread) {
                         set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
@@ -4318,8 +4364,12 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
                 if (mode == 1)
                         set_disk_ro(disk, 1);
                 clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+                err = 0;
         }
-
+out:
+        mutex_unlock(&mddev->open_mutex);
+        if (err)
+                return err;
         /*
          * Free resources if final stop
          */
@@ -4385,7 +4435,6 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
         blk_integrity_unregister(disk);
         md_new_event(mddev);
         sysfs_notify_dirent(mddev->sysfs_state);
-out:
         return err;
 }
 
@@ -5083,18 +5132,8 @@ 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;
 }
 
@@ -5480,12 +5519,12 @@ static int md_open(struct block_device *bdev, fmode_t mode)
         }
         BUG_ON(mddev != bdev->bd_disk->private_data);
 
-        if ((err = mutex_lock_interruptible_nested(&mddev->reconfig_mutex, 1)))
+        if ((err = mutex_lock_interruptible(&mddev->open_mutex)))
                 goto out;
 
         err = 0;
         atomic_inc(&mddev->openers);
-        mddev_unlock(mddev);
+        mutex_unlock(&mddev->open_mutex);
 
         check_disk_change(bdev);
  out:
@@ -6334,10 +6373,16 @@ void md_do_sync(mddev_t *mddev)
                         sysfs_notify(&mddev->kobj, NULL, "sync_completed");
                 }
 
-                if (j >= mddev->resync_max)
-                        wait_event(mddev->recovery_wait,
-                                   mddev->resync_max > j
-                                   || kthread_should_stop());
+                while (j >= mddev->resync_max && !kthread_should_stop()) {
+                        /* As this condition is controlled by user-space,
+                         * we can block indefinitely, so use '_interruptible'
+                         * to avoid triggering warnings.
+                         */
+                        flush_signals(current); /* just in case */
+                        wait_event_interruptible(mddev->recovery_wait,
+                                                 mddev->resync_max > j
+                                                 || kthread_should_stop());
+                }
 
                 if (kthread_should_stop())
                         goto interrupted;