Merge branch 'for-linus' of git://neil.brown.name/md

* 'for-linus' of git://neil.brown.name/md:
  md: support bitmaps on RAID10 arrays larger then 2 terabytes
  md: update sync_completed and reshape_position even more often.
  md: improve usefulness and accuracy of sysfs file md/sync_completed.
  md: allow setting newly added device to 'in_sync' via sysfs.
  md: tiny md.h cleanups

4 files changed, 51 insertions, 25 deletions

diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index f8a9f7ab2cb8..1fb91edc7de2 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -1479,6 +1479,7 @@ void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector)
                 s += blocks;
         }
         bitmap->last_end_sync = jiffies;
+        sysfs_notify(&bitmap->mddev->kobj, NULL, "sync_completed");
 }
 
 static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed)
@@ -1589,7 +1590,7 @@ void bitmap_destroy(mddev_t *mddev)
 int bitmap_create(mddev_t *mddev)
 {
         struct bitmap *bitmap;
-        unsigned long blocks = mddev->resync_max_sectors;
+        sector_t blocks = mddev->resync_max_sectors;
         unsigned long chunks;
         unsigned long pages;
         struct file *file = mddev->bitmap_file;
@@ -1631,8 +1632,8 @@ int bitmap_create(mddev_t *mddev)
         bitmap->chunkshift = ffz(~bitmap->chunksize);
 
         /* now that chunksize and chunkshift are set, we can use these macros */
-        chunks = (blocks + CHUNK_BLOCK_RATIO(bitmap) - 1) /
-                        CHUNK_BLOCK_RATIO(bitmap);
+        chunks = (blocks + CHUNK_BLOCK_RATIO(bitmap) - 1) >>
+                        CHUNK_BLOCK_SHIFT(bitmap);
         pages = (chunks + PAGE_COUNTER_RATIO - 1) / PAGE_COUNTER_RATIO;
 
         BUG_ON(!pages);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index ed5727c089a9..612343fdde94 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2017,6 +2017,8 @@ repeat:
         clear_bit(MD_CHANGE_PENDING, &mddev->flags);
         spin_unlock_irq(&mddev->write_lock);
         wake_up(&mddev->sb_wait);
+        if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
+                sysfs_notify(&mddev->kobj, NULL, "sync_completed");
 
 }
 
@@ -2086,6 +2088,7 @@ state_store(mdk_rdev_t *rdev, const char *buf, size_t len)
          *  -writemostly - clears write_mostly
          *  blocked - sets the Blocked flag
          *  -blocked - clears the Blocked flag
+         *  insync - sets Insync providing device isn't active
          */
         int err = -EINVAL;
         if (cmd_match(buf, "faulty") && rdev->mddev->pers) {
@@ -2118,6 +2121,9 @@ state_store(mdk_rdev_t *rdev, const char *buf, size_t len)
                 md_wakeup_thread(rdev->mddev->thread);
 
                 err = 0;
+        } else if (cmd_match(buf, "insync") && rdev->raid_disk == -1) {
+                set_bit(In_sync, &rdev->flags);
+                err = 0;
         }
         if (!err && rdev->sysfs_state)
                 sysfs_notify_dirent(rdev->sysfs_state);
@@ -2190,7 +2196,7 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len)
         } else if (rdev->mddev->pers) {
                 mdk_rdev_t *rdev2;
                 /* Activating a spare .. or possibly reactivating
-                 * if we every get bitmaps working here.
+                 * if we ever get bitmaps working here.
                  */
 
                 if (rdev->raid_disk != -1)
@@ -3482,12 +3488,15 @@ sync_completed_show(mddev_t *mddev, char *page)
 {
         unsigned long max_sectors, resync;
 
+        if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
+                return sprintf(page, "none\n");
+
         if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
                 max_sectors = mddev->resync_max_sectors;
         else
                 max_sectors = mddev->dev_sectors;
 
-        resync = (mddev->curr_resync - atomic_read(&mddev->recovery_active));
+        resync = mddev->curr_resync_completed;
         return sprintf(page, "%lu / %lu\n", resync, max_sectors);
 }
 
@@ -6334,18 +6343,13 @@ void md_do_sync(mddev_t *mddev)
                 sector_t sectors;
 
                 skipped = 0;
-                if (j >= mddev->resync_max) {
-                        sysfs_notify(&mddev->kobj, NULL, "sync_completed");
-                        wait_event(mddev->recovery_wait,
-                                   mddev->resync_max > j
-                                   || kthread_should_stop());
-                }
-                if (kthread_should_stop())
-                        goto interrupted;
 
-                if (mddev->curr_resync > mddev->curr_resync_completed &&
-                    (mddev->curr_resync - mddev->curr_resync_completed)
-                    > (max_sectors >> 4)) {
+                if ((mddev->curr_resync > mddev->curr_resync_completed &&
+                     (mddev->curr_resync - mddev->curr_resync_completed)
+                    > (max_sectors >> 4)) ||
+                    (j - mddev->curr_resync_completed)*2
+                    >= mddev->resync_max - mddev->curr_resync_completed
+                        ) {
                         /* time to update curr_resync_completed */
                         blk_unplug(mddev->queue);
                         wait_event(mddev->recovery_wait,
@@ -6353,7 +6357,17 @@ void md_do_sync(mddev_t *mddev)
                         mddev->curr_resync_completed =
                                 mddev->curr_resync;
                         set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+                        sysfs_notify(&mddev->kobj, NULL, "sync_completed");
                 }
+
+                if (j >= mddev->resync_max)
+                        wait_event(mddev->recovery_wait,
+                                   mddev->resync_max > j
+                                   || kthread_should_stop());
+
+                if (kthread_should_stop())
+                        goto interrupted;
+
                 sectors = mddev->pers->sync_request(mddev, j, &skipped,
                                                   currspeed < speed_min(mddev));
                 if (sectors == 0) {
@@ -6461,6 +6475,7 @@ void md_do_sync(mddev_t *mddev)
 
  skip:
         mddev->curr_resync = 0;
+        mddev->curr_resync_completed = 0;
         mddev->resync_min = 0;
         mddev->resync_max = MaxSector;
         sysfs_notify(&mddev->kobj, NULL, "sync_completed");
diff --git a/drivers/md/md.h b/drivers/md/md.h
index e9b7f54c24d6..8227ab909d44 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -12,10 +12,17 @@
    Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.  
 */
 
-#ifndef _MD_K_H
-#define _MD_K_H
-
-#ifdef CONFIG_BLOCK
+#ifndef _MD_MD_H
+#define _MD_MD_H
+
+#include <linux/blkdev.h>
+#include <linux/kobject.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include <linux/timer.h>
+#include <linux/wait.h>
+#include <linux/workqueue.h>
 
 #define MaxSector (~(sector_t)0)
 
@@ -408,10 +415,6 @@ static inline void safe_put_page(struct page *p)
         if (p) put_page(p);
 }
 
-#endif /* CONFIG_BLOCK */
-#endif
-
-
 extern int register_md_personality(struct mdk_personality *p);
 extern int unregister_md_personality(struct mdk_personality *p);
 extern mdk_thread_t * md_register_thread(void (*run) (mddev_t *mddev),
@@ -434,3 +437,5 @@ extern void md_new_event(mddev_t *mddev);
 extern int md_allow_write(mddev_t *mddev);
 extern void md_wait_for_blocked_rdev(mdk_rdev_t *rdev, mddev_t *mddev);
 extern void md_set_array_sectors(mddev_t *mddev, sector_t array_sectors);
+
+#endif /* _MD_MD_H */
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 3bbc6d647044..4616bc3a6e71 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3845,6 +3845,7 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
                 wait_event(conf->wait_for_overlap,
                            atomic_read(&conf->reshape_stripes)==0);
                 mddev->reshape_position = conf->reshape_progress;
+                mddev->curr_resync_completed = mddev->curr_resync;
                 conf->reshape_checkpoint = jiffies;
                 set_bit(MD_CHANGE_DEVS, &mddev->flags);
                 md_wakeup_thread(mddev->thread);
@@ -3854,6 +3855,7 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
                 conf->reshape_safe = mddev->reshape_position;
                 spin_unlock_irq(&conf->device_lock);
                 wake_up(&conf->wait_for_overlap);
+                sysfs_notify(&mddev->kobj, NULL, "sync_completed");
         }
 
         if (mddev->delta_disks < 0) {
@@ -3938,11 +3940,13 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
          * then we need to write out the superblock.
          */
         sector_nr += reshape_sectors;
-        if (sector_nr >= mddev->resync_max) {
+        if ((sector_nr - mddev->curr_resync_completed) * 2
+            >= mddev->resync_max - mddev->curr_resync_completed) {
                 /* Cannot proceed until we've updated the superblock... */
                 wait_event(conf->wait_for_overlap,
                            atomic_read(&conf->reshape_stripes) == 0);
                 mddev->reshape_position = conf->reshape_progress;
+                mddev->curr_resync_completed = mddev->curr_resync;
                 conf->reshape_checkpoint = jiffies;
                 set_bit(MD_CHANGE_DEVS, &mddev->flags);
                 md_wakeup_thread(mddev->thread);
@@ -3953,6 +3957,7 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
                 conf->reshape_safe = mddev->reshape_position;
                 spin_unlock_irq(&conf->device_lock);
                 wake_up(&conf->wait_for_overlap);
+                sysfs_notify(&mddev->kobj, NULL, "sync_completed");
         }
         return reshape_sectors;
 }