[PATCH] md: fix BUG when raid10 rebuilds without enough drives

[sfrench/cifs-2.6.git] / drivers / md / raid10.c

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 62ebb1bc72be24cc32ecc775c5bd71603d44e5c6..5bd1e9ec899d8b23f02d498664ca7d29c76a9a7c 100644 (file)
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -538,7 +538,8 @@ static int read_balance(conf_t *conf, r10bio_t *r10_bio)
        }
 
 
-       current_distance = abs(this_sector - conf->mirrors[disk].head_position);
+       current_distance = abs(r10_bio->devs[slot].addr -
+                              conf->mirrors[disk].head_position);
 
        /* Find the disk whose head is closest */
 
@@ -668,6 +669,11 @@ static int make_request(request_queue_t *q, struct bio * bio)
        int i;
        int chunk_sects = conf->chunk_mask + 1;
 
+       if (unlikely(bio_barrier(bio))) {
+               bio_endio(bio, bio->bi_size, -EOPNOTSUPP);
+               return 0;
+       }
+
        /* If this request crosses a chunk boundary, we need to
         * split it.  This will only happen for 1 PAGE (or less) requests.
         */
@@ -900,6 +906,27 @@ static void close_sync(conf_t *conf)
        conf->r10buf_pool = NULL;
 }
 
+/* check if there are enough drives for
+ * every block to appear on atleast one
+ */
+static int enough(conf_t *conf)
+{
+       int first = 0;
+
+       do {
+               int n = conf->copies;
+               int cnt = 0;
+               while (n--) {
+                       if (conf->mirrors[first].rdev)
+                               cnt++;
+                       first = (first+1) % conf->raid_disks;
+               }
+               if (cnt == 0)
+                       return 0;
+       } while (first != 0);
+       return 1;
+}
+
 static int raid10_spare_active(mddev_t *mddev)
 {
        int i;
@@ -938,6 +965,8 @@ static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
                 * very different from resync
                 */
                return 0;
+       if (!enough(conf))
+               return 0;
 
        for (mirror=0; mirror < mddev->raid_disks; mirror++)
                if ( !(p=conf->mirrors+mirror)->rdev) {
@@ -1445,7 +1474,13 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
                                        }
                                }
                                if (j == conf->copies) {
-                                       BUG();
+                                       /* Cannot recover, so abort the recovery */
+                                       put_buf(r10_bio);
+                                       r10_bio = rb2;
+                                       if (!test_and_set_bit(MD_RECOVERY_ERR, &mddev->recovery))
+                                               printk(KERN_INFO "raid10: %s: insufficient working devices for recovery.\n",
+                                                      mdname(mddev));
+                                       break;
                                }
                        }
                if (biolist == NULL) {
@@ -1678,9 +1713,10 @@ static int run(mddev_t *mddev)
        init_waitqueue_head(&conf->wait_idle);
        init_waitqueue_head(&conf->wait_resume);
 
-       if (!conf->working_disks) {
-               printk(KERN_ERR "raid10: no operational mirrors for %s\n",
-                       mdname(mddev));
+       /* need to check that every block has at least one working mirror */
+       if (!enough(conf)) {
+               printk(KERN_ERR "raid10: not enough operational mirrors for %s\n",
+                      mdname(mddev));
                goto out_free_conf;
        }