[PATCH] md: allow a linear array to have drives added while active

Signed-off-by: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

3 files changed, 76 insertions, 15 deletions

diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 777585458c85..ff83c9b5979e 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -111,7 +111,7 @@ static int linear_issue_flush(request_queue_t *q, struct gendisk *disk,
         return ret;
 }
 
-static int linear_run (mddev_t *mddev)
+static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
 {
         linear_conf_t *conf;
         dev_info_t **table;
@@ -121,20 +121,21 @@ static int linear_run (mddev_t *mddev)
         sector_t curr_offset;
         struct list_head *tmp;
 
-        conf = kzalloc (sizeof (*conf) + mddev->raid_disks*sizeof(dev_info_t),
+        conf = kzalloc (sizeof (*conf) + raid_disks*sizeof(dev_info_t),
                         GFP_KERNEL);
         if (!conf)
-                goto out;
+                return NULL;
+
         mddev->private = conf;
 
         cnt = 0;
-        mddev->array_size = 0;
+        conf->array_size = 0;
 
         ITERATE_RDEV(mddev,rdev,tmp) {
                 int j = rdev->raid_disk;
                 dev_info_t *disk = conf->disks + j;
 
-                if (j < 0 || j > mddev->raid_disks || disk->rdev) {
+                if (j < 0 || j > raid_disks || disk->rdev) {
                         printk("linear: disk numbering problem. Aborting!\n");
                         goto out;
                 }
@@ -152,11 +153,11 @@ static int linear_run (mddev_t *mddev)
                         blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
                 disk->size = rdev->size;
-                mddev->array_size += rdev->size;
+                conf->array_size += rdev->size;
 
                 cnt++;
         }
-        if (cnt != mddev->raid_disks) {
+        if (cnt != raid_disks) {
                 printk("linear: not enough drives present. Aborting!\n");
                 goto out;
         }
@@ -200,7 +201,7 @@ static int linear_run (mddev_t *mddev)
                 unsigned round;
                 unsigned long base;
 
-                sz = mddev->array_size >> conf->preshift;
+                sz = conf->array_size >> conf->preshift;
                 sz += 1; /* force round-up */
                 base = conf->hash_spacing >> conf->preshift;
                 round = sector_div(sz, base);
@@ -247,14 +248,56 @@ static int linear_run (mddev_t *mddev)
 
         BUG_ON(table - conf->hash_table > nb_zone);
 
+        return conf;
+
+out:
+        kfree(conf);
+        return NULL;
+}
+
+static int linear_run (mddev_t *mddev)
+{
+        linear_conf_t *conf;
+
+        conf = linear_conf(mddev, mddev->raid_disks);
+
+        if (!conf)
+                return 1;
+        mddev->private = conf;
+        mddev->array_size = conf->array_size;
+
         blk_queue_merge_bvec(mddev->queue, linear_mergeable_bvec);
         mddev->queue->unplug_fn = linear_unplug;
         mddev->queue->issue_flush_fn = linear_issue_flush;
         return 0;
+}
 
-out:
-        kfree(conf);
-        return 1;
+static int linear_add(mddev_t *mddev, mdk_rdev_t *rdev)
+{
+        /* Adding a drive to a linear array allows the array to grow.
+         * It is permitted if the new drive has a matching superblock
+         * already on it, with raid_disk equal to raid_disks.
+         * It is achieved by creating a new linear_private_data structure
+         * and swapping it in in-place of the current one.
+         * The current one is never freed until the array is stopped.
+         * This avoids races.
+         */
+        linear_conf_t *newconf;
+
+        if (rdev->raid_disk != mddev->raid_disks)
+                return -EINVAL;
+
+        newconf = linear_conf(mddev,mddev->raid_disks+1);
+
+        if (!newconf)
+                return -ENOMEM;
+
+        newconf->prev = mddev_to_conf(mddev);
+        mddev->private = newconf;
+        mddev->raid_disks++;
+        mddev->array_size = newconf->array_size;
+        set_capacity(mddev->gendisk, mddev->array_size << 1);
+        return 0;
 }
 
 static int linear_stop (mddev_t *mddev)
@@ -262,8 +305,12 @@ static int linear_stop (mddev_t *mddev)
         linear_conf_t *conf = mddev_to_conf(mddev);
   
         blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
-        kfree(conf->hash_table);
-        kfree(conf);
+        do {
+                linear_conf_t *t = conf->prev;
+                kfree(conf->hash_table);
+                kfree(conf);
+                conf = t;
+        } while (conf);
 
         return 0;
 }
@@ -360,6 +407,7 @@ static struct mdk_personality linear_personality =
         .run            = linear_run,
         .stop           = linear_stop,
         .status         = linear_status,
+        .hot_add_disk   = linear_add,
 };
 
 static int __init linear_init (void)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index a296edd7e1c3..2ce750d4be02 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -817,8 +817,8 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev)
 
                 if (desc->state & (1<<MD_DISK_FAULTY))
                         set_bit(Faulty, &rdev->flags);
-                else if (desc->state & (1<<MD_DISK_SYNC) &&
-                         desc->raid_disk < mddev->raid_disks) {
+                else if (desc->state & (1<<MD_DISK_SYNC) /* &&
+                            desc->raid_disk < mddev->raid_disks */) {
                         set_bit(In_sync, &rdev->flags);
                         rdev->raid_disk = desc->raid_disk;
                 }
@@ -3359,6 +3359,17 @@ static int add_new_disk(mddev_t * mddev, mdu_disk_info_t *info)
 
                 rdev->raid_disk = -1;
                 err = bind_rdev_to_array(rdev, mddev);
+                if (!err && !mddev->pers->hot_remove_disk) {
+                        /* If there is hot_add_disk but no hot_remove_disk
+                         * then added disks for geometry changes,
+                         * and should be added immediately.
+                         */
+                        super_types[mddev->major_version].
+                                validate_super(mddev, rdev);
+                        err = mddev->pers->hot_add_disk(mddev, rdev);
+                        if (err)
+                                unbind_rdev_from_array(rdev);
+                }
                 if (err)
                         export_rdev(rdev);
 
diff --git a/include/linux/raid/linear.h b/include/linux/raid/linear.h
index 7eaf290e10e7..ba15469daf11 100644
--- a/include/linux/raid/linear.h
+++ b/include/linux/raid/linear.h
@@ -13,8 +13,10 @@ typedef struct dev_info dev_info_t;
 
 struct linear_private_data
 {
+        struct linear_private_data *prev;       /* earlier version */
         dev_info_t              **hash_table;
         sector_t                hash_spacing;
+        sector_t                array_size;
         int                     preshift; /* shift before dividing by hash_spacing */
         dev_info_t              disks[0];
 };