Merge with http://kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git

5 files changed, 37 insertions, 10 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 78c7418478d6..cd12fca73b0d 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1028,7 +1028,6 @@ static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev)
                 mddev->size = le64_to_cpu(sb->size)/2;
                 mddev->events = le64_to_cpu(sb->events);
                 mddev->bitmap_offset = 0;
-                mddev->default_bitmap_offset = 0;
                 mddev->default_bitmap_offset = 1024;
                 
                 mddev->recovery_cp = le64_to_cpu(sb->resync_offset);
@@ -2932,6 +2931,9 @@ static int set_array_info(mddev_t * mddev, mdu_array_info_t *info)
 
         mddev->sb_dirty      = 1;
 
+        mddev->default_bitmap_offset = MD_SB_BYTES >> 9;
+        mddev->bitmap_offset = 0;
+
         /*
          * Generate a 128 bit UUID
          */
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 2da9d3ba902d..3066c587b539 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -953,9 +953,6 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
         int mirror = 0;
         mirror_info_t *p;
 
-        if (rdev->saved_raid_disk >= 0 &&
-            conf->mirrors[rdev->saved_raid_disk].rdev == NULL)
-                mirror = rdev->saved_raid_disk;
         for (mirror=0; mirror < mddev->raid_disks; mirror++)
                 if ( !(p=conf->mirrors+mirror)->rdev) {
 
@@ -972,7 +969,10 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
                         p->head_position = 0;
                         rdev->raid_disk = mirror;
                         found = 1;
-                        if (rdev->saved_raid_disk != mirror)
+                        /* As all devices are equivalent, we don't need a full recovery
+                         * if this was recently any drive of the array
+                         */
+                        if (rdev->saved_raid_disk < 0)
                                 conf->fullsync = 1;
                         rcu_assign_pointer(p->rdev, rdev);
                         break;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 867f06ae33d9..713dc9c2c730 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -552,7 +552,11 @@ static int read_balance(conf_t *conf, r10bio_t *r10_bio)
                     !test_bit(In_sync, &rdev->flags))
                         continue;
 
-                if (!atomic_read(&rdev->nr_pending)) {
+                /* This optimisation is debatable, and completely destroys
+                 * sequential read speed for 'far copies' arrays.  So only
+                 * keep it for 'near' arrays, and review those later.
+                 */
+                if (conf->near_copies > 1 && !atomic_read(&rdev->nr_pending)) {
                         disk = ndisk;
                         slot = nslot;
                         break;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index e2a40283e323..36d5f8ac8265 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1704,7 +1704,9 @@ static void raid5d (mddev_t *mddev)
 
                 if (conf->seq_flush - conf->seq_write > 0) {
                         int seq = conf->seq_flush;
+                        spin_unlock_irq(&conf->device_lock);
                         bitmap_unplug(mddev->bitmap);
+                        spin_lock_irq(&conf->device_lock);
                         conf->seq_write = seq;
                         activate_bit_delay(conf);
                 }
diff --git a/drivers/md/raid6main.c b/drivers/md/raid6main.c
index eae5a35629c5..0000d162d198 100644
--- a/drivers/md/raid6main.c
+++ b/drivers/md/raid6main.c
@@ -1702,6 +1702,8 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
         int data_disks = raid_disks - 2;
         sector_t max_sector = mddev->size << 1;
         int sync_blocks;
+        int still_degraded = 0;
+        int i;
 
         if (sector_nr >= max_sector) {
                 /* just being told to finish up .. nothing much to do */
@@ -1710,7 +1712,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
                 if (mddev->curr_resync < max_sector) /* aborted */
                         bitmap_end_sync(mddev->bitmap, mddev->curr_resync,
                                         &sync_blocks, 1);
-                else /* compelted sync */
+                else /* completed sync */
                         conf->fullsync = 0;
                 bitmap_close_sync(mddev->bitmap);
 
@@ -1748,7 +1750,16 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
                  */
                 schedule_timeout_uninterruptible(1);
         }
-        bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 0);
+        /* Need to check if array will still be degraded after recovery/resync
+         * We don't need to check the 'failed' flag as when that gets set,
+         * recovery aborts.
+         */
+        for (i=0; i<mddev->raid_disks; i++)
+                if (conf->disks[i].rdev == NULL)
+                        still_degraded = 1;
+
+        bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, still_degraded);
+
         spin_lock(&sh->lock);
         set_bit(STRIPE_SYNCING, &sh->state);
         clear_bit(STRIPE_INSYNC, &sh->state);
@@ -1784,7 +1795,9 @@ static void raid6d (mddev_t *mddev)
 
                 if (conf->seq_flush - conf->seq_write > 0) {
                         int seq = conf->seq_flush;
+                        spin_unlock_irq(&conf->device_lock);
                         bitmap_unplug(mddev->bitmap);
+                        spin_lock_irq(&conf->device_lock);
                         conf->seq_write = seq;
                         activate_bit_delay(conf);
                 }
@@ -2145,9 +2158,15 @@ static int raid6_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
                 /* no point adding a device */
                 return 0;
         /*
-         * find the disk ...
+         * find the disk ... but prefer rdev->saved_raid_disk
+         * if possible.
          */
-        for (disk=0; disk < mddev->raid_disks; disk++)
+        if (rdev->saved_raid_disk >= 0 &&
+            conf->disks[rdev->saved_raid_disk].rdev == NULL)
+                disk = rdev->saved_raid_disk;
+        else
+                disk = 0;
+        for ( ; disk < mddev->raid_disks; disk++)
                 if ((p=conf->disks + disk)->rdev == NULL) {
                         clear_bit(In_sync, &rdev->flags);
                         rdev->raid_disk = disk;