5 files changed, 60 insertions, 30 deletions

diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 217615b33223..93f701ea87bc 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -710,6 +710,8 @@ static int multipath_ctr(struct dm_target *ti, unsigned int argc,
                 return -EINVAL;
         }
 
+        m->ti = ti;
+
         r = parse_features(&as, m, ti);
         if (r)
                 goto bad;
@@ -751,7 +753,6 @@ static int multipath_ctr(struct dm_target *ti, unsigned int argc,
         }
 
         ti->private = m;
-        m->ti = ti;
 
         return 0;
 
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index be48cedf986b..c54de989eb00 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -255,7 +255,9 @@ static struct region *__rh_alloc(struct region_hash *rh, region_t region)
         struct region *reg, *nreg;
 
         read_unlock(&rh->hash_lock);
-        nreg = mempool_alloc(rh->region_pool, GFP_NOIO);
+        nreg = mempool_alloc(rh->region_pool, GFP_ATOMIC);
+        if (unlikely(!nreg))
+                nreg = kmalloc(sizeof(struct region), GFP_NOIO);
         nreg->state = rh->log->type->in_sync(rh->log, region, 1) ?
                 RH_CLEAN : RH_NOSYNC;
         nreg->rh = rh;
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index ff83c9b5979e..b99c19c7eb22 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -162,7 +162,7 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
                 goto out;
         }
 
-        min_spacing = mddev->array_size;
+        min_spacing = conf->array_size;
         sector_div(min_spacing, PAGE_SIZE/sizeof(struct dev_info *));
 
         /* min_spacing is the minimum spacing that will fit the hash
@@ -171,7 +171,7 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
          * that is larger than min_spacing as use the size of that as
          * the actual spacing
          */
-        conf->hash_spacing = mddev->array_size;
+        conf->hash_spacing = conf->array_size;
         for (i=0; i < cnt-1 ; i++) {
                 sector_t sz = 0;
                 int j;
@@ -228,7 +228,7 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
         curr_offset = 0;
         i = 0;
         for (curr_offset = 0;
-             curr_offset < mddev->array_size;
+             curr_offset < conf->array_size;
              curr_offset += conf->hash_spacing) {
 
                 while (i < mddev->raid_disks-1 &&
diff --git a/drivers/md/md.c b/drivers/md/md.c
index b6d16022a53e..8dbab2ef3885 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1597,6 +1597,19 @@ void md_update_sb(mddev_t * mddev)
 
 repeat:
         spin_lock_irq(&mddev->write_lock);
+
+        if (mddev->degraded && mddev->sb_dirty == 3)
+                /* If the array is degraded, then skipping spares is both
+                 * dangerous and fairly pointless.
+                 * Dangerous because a device that was removed from the array
+                 * might have a event_count that still looks up-to-date,
+                 * so it can be re-added without a resync.
+                 * Pointless because if there are any spares to skip,
+                 * then a recovery will happen and soon that array won't
+                 * be degraded any more and the spare can go back to sleep then.
+                 */
+                mddev->sb_dirty = 1;
+
         sync_req = mddev->in_sync;
         mddev->utime = get_seconds();
         if (mddev->sb_dirty == 3)
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 1efe22a2d041..3b4d69c05623 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -930,10 +930,13 @@ static void status(struct seq_file *seq, mddev_t *mddev)
 
         seq_printf(seq, " [%d/%d] [", conf->raid_disks,
                                                 conf->working_disks);
-        for (i = 0; i < conf->raid_disks; i++)
+        rcu_read_lock();
+        for (i = 0; i < conf->raid_disks; i++) {
+                mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
                 seq_printf(seq, "%s",
-                              conf->mirrors[i].rdev &&
-                              test_bit(In_sync, &conf->mirrors[i].rdev->flags) ? "U" : "_");
+                           rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_");
+        }
+        rcu_read_unlock();
         seq_printf(seq, "]");
 }
 
@@ -975,7 +978,6 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 static void print_conf(conf_t *conf)
 {
         int i;
-        mirror_info_t *tmp;
 
         printk("RAID1 conf printout:\n");
         if (!conf) {
@@ -985,14 +987,17 @@ static void print_conf(conf_t *conf)
         printk(" --- wd:%d rd:%d\n", conf->working_disks,
                 conf->raid_disks);
 
+        rcu_read_lock();
         for (i = 0; i < conf->raid_disks; i++) {
                 char b[BDEVNAME_SIZE];
-                tmp = conf->mirrors + i;
-                if (tmp->rdev)
+                mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
+                if (rdev)
                         printk(" disk %d, wo:%d, o:%d, dev:%s\n",
-                                i, !test_bit(In_sync, &tmp->rdev->flags), !test_bit(Faulty, &tmp->rdev->flags),
-                                bdevname(tmp->rdev->bdev,b));
+                               i, !test_bit(In_sync, &rdev->flags),
+                               !test_bit(Faulty, &rdev->flags),
+                               bdevname(rdev->bdev,b));
         }
+        rcu_read_unlock();
 }
 
 static void close_sync(conf_t *conf)
@@ -1008,20 +1013,20 @@ static int raid1_spare_active(mddev_t *mddev)
 {
         int i;
         conf_t *conf = mddev->private;
-        mirror_info_t *tmp;
 
         /*
          * Find all failed disks within the RAID1 configuration 
-         * and mark them readable
+         * and mark them readable.
+         * Called under mddev lock, so rcu protection not needed.
          */
         for (i = 0; i < conf->raid_disks; i++) {
-                tmp = conf->mirrors + i;
-                if (tmp->rdev 
-                    && !test_bit(Faulty, &tmp->rdev->flags)
-                    && !test_bit(In_sync, &tmp->rdev->flags)) {
+                mdk_rdev_t *rdev = conf->mirrors[i].rdev;
+                if (rdev
+                    && !test_bit(Faulty, &rdev->flags)
+                    && !test_bit(In_sync, &rdev->flags)) {
                         conf->working_disks++;
                         mddev->degraded--;
-                        set_bit(In_sync, &tmp->rdev->flags);
+                        set_bit(In_sync, &rdev->flags);
                 }
         }
 
@@ -1237,7 +1242,7 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
                 /* ouch - failed to read all of that.
                  * Try some synchronous reads of other devices to get
                  * good data, much like with normal read errors.  Only
-                 * read into the pages we already have so they we don't
+                 * read into the pages we already have so we don't
                  * need to re-issue the read request.
                  * We don't need to freeze the array, because being in an
                  * active sync request, there is no normal IO, and
@@ -1257,6 +1262,10 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
                                 s = PAGE_SIZE >> 9;
                         do {
                                 if (r1_bio->bios[d]->bi_end_io == end_sync_read) {
+                                        /* No rcu protection needed here devices
+                                         * can only be removed when no resync is
+                                         * active, and resync is currently active
+                                         */
                                         rdev = conf->mirrors[d].rdev;
                                         if (sync_page_io(rdev->bdev,
                                                          sect + rdev->data_offset,
@@ -1463,6 +1472,11 @@ static void raid1d(mddev_t *mddev)
                                         s = PAGE_SIZE >> 9;
 
                                 do {
+                                        /* Note: no rcu protection needed here
+                                         * as this is synchronous in the raid1d thread
+                                         * which is the thread that might remove
+                                         * a device.  If raid1d ever becomes multi-threaded....
+                                         */
                                         rdev = conf->mirrors[d].rdev;
                                         if (rdev &&
                                             test_bit(In_sync, &rdev->flags) &&
@@ -1486,7 +1500,6 @@ static void raid1d(mddev_t *mddev)
                                                         d = conf->raid_disks;
                                                 d--;
                                                 rdev = conf->mirrors[d].rdev;
-                                                atomic_add(s, &rdev->corrected_errors);
                                                 if (rdev &&
                                                     test_bit(In_sync, &rdev->flags)) {
                                                         if (sync_page_io(rdev->bdev,
@@ -1509,9 +1522,11 @@ static void raid1d(mddev_t *mddev)
                                                                          s<<9, conf->tmppage, READ) == 0)
                                                                 /* Well, this device is dead */
                                                                 md_error(mddev, rdev);
-                                                        else
+                                                        else {
+                                                                atomic_add(s, &rdev->corrected_errors);
                                                                 printk(KERN_INFO "raid1:%s: read error corrected (%d sectors at %llu on %s)\n",
                                                                        mdname(mddev), s, (unsigned long long)(sect + rdev->data_offset), bdevname(rdev->bdev, b));
+                                                        }
                                                 }
                                         }
                                 } else {
@@ -1625,15 +1640,16 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
                 return 0;
         }
 
-        /* before building a request, check if we can skip these blocks..
-         * This call the bitmap_start_sync doesn't actually record anything
-         */
         if (mddev->bitmap == NULL &&
             mddev->recovery_cp == MaxSector &&
+            !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
             conf->fullsync == 0) {
                 *skipped = 1;
                 return max_sector - sector_nr;
         }
+        /* before building a request, check if we can skip these blocks..
+         * This call the bitmap_start_sync doesn't actually record anything
+         */
         if (!bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 1) &&
             !conf->fullsync && !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
                 /* We can skip this block, and probably several more */
@@ -1786,19 +1802,17 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
                 for (i=0; i<conf->raid_disks; i++) {
                         bio = r1_bio->bios[i];
                         if (bio->bi_end_io == end_sync_read) {
-                                md_sync_acct(conf->mirrors[i].rdev->bdev, nr_sectors);
+                                md_sync_acct(bio->bi_bdev, nr_sectors);
                                 generic_make_request(bio);
                         }
                 }
         } else {
                 atomic_set(&r1_bio->remaining, 1);
                 bio = r1_bio->bios[r1_bio->read_disk];
-                md_sync_acct(conf->mirrors[r1_bio->read_disk].rdev->bdev,
-                             nr_sectors);
+                md_sync_acct(bio->bi_bdev, nr_sectors);
                 generic_make_request(bio);
 
         }
-
         return nr_sectors;
 }