Merge git://git.kernel.org/pub/scm/linux/kernel/git/sam/kbuild

[linux-2.6] / drivers / md / md.c

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 3d5a6beb333b95a0d8efc29ca1fb78b4885533be..65ddc887dfd72dc97a2ace8bb4c8bbf93c8e5f94 100644 (file)
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1640,7 +1640,6 @@ static void sync_sbs(mddev_t * mddev, int nospares)
 
 static void md_update_sb(mddev_t * mddev, int force_change)
 {
-       int err;
        struct list_head *tmp;
        mdk_rdev_t *rdev;
        int sync_req;
@@ -1727,7 +1726,7 @@ repeat:
                "md: updating %s RAID superblock on device (in sync %d)\n",
                mdname(mddev),mddev->in_sync);
 
-       err = bitmap_update_sb(mddev->bitmap);
+       bitmap_update_sb(mddev->bitmap);
        ITERATE_RDEV(mddev,rdev,tmp) {
                char b[BDEVNAME_SIZE];
                dprintk(KERN_INFO "md: ");
@@ -3176,13 +3175,33 @@ static int do_md_run(mddev_t * mddev)
         * Drop all container device buffers, from now on
         * the only valid external interface is through the md
         * device.
-        * Also find largest hardsector size
         */
        ITERATE_RDEV(mddev,rdev,tmp) {
                if (test_bit(Faulty, &rdev->flags))
                        continue;
                sync_blockdev(rdev->bdev);
                invalidate_bdev(rdev->bdev);
+
+               /* perform some consistency tests on the device.
+                * We don't want the data to overlap the metadata,
+                * Internal Bitmap issues has handled elsewhere.
+                */
+               if (rdev->data_offset < rdev->sb_offset) {
+                       if (mddev->size &&
+                           rdev->data_offset + mddev->size*2
+                           > rdev->sb_offset*2) {
+                               printk("md: %s: data overlaps metadata\n",
+                                      mdname(mddev));
+                               return -EINVAL;
+                       }
+               } else {
+                       if (rdev->sb_offset*2 + rdev->sb_size/512
+                           > rdev->data_offset) {
+                               printk("md: %s: metadata overlaps data\n",
+                                      mdname(mddev));
+                               return -EINVAL;
+                       }
+               }
        }
 
        md_probe(mddev->unit, NULL, NULL);
@@ -5091,7 +5110,7 @@ static int is_mddev_idle(mddev_t *mddev)
        mdk_rdev_t * rdev;
        struct list_head *tmp;
        int idle;
-       unsigned long curr_events;
+       long curr_events;
 
        idle = 1;
        ITERATE_RDEV(mddev,rdev,tmp) {
@@ -5099,20 +5118,29 @@ static int is_mddev_idle(mddev_t *mddev)
                curr_events = disk_stat_read(disk, sectors[0]) + 
                                disk_stat_read(disk, sectors[1]) - 
                                atomic_read(&disk->sync_io);
-               /* The difference between curr_events and last_events
-                * will be affected by any new non-sync IO (making
-                * curr_events bigger) and any difference in the amount of
-                * in-flight syncio (making current_events bigger or smaller)
-                * The amount in-flight is currently limited to
-                * 32*64K in raid1/10 and 256*PAGE_SIZE in raid5/6
-                * which is at most 4096 sectors.
-                * These numbers are fairly fragile and should be made
-                * more robust, probably by enforcing the
-                * 'window size' that md_do_sync sort-of uses.
+               /* sync IO will cause sync_io to increase before the disk_stats
+                * as sync_io is counted when a request starts, and
+                * disk_stats is counted when it completes.
+                * So resync activity will cause curr_events to be smaller than
+                * when there was no such activity.
+                * non-sync IO will cause disk_stat to increase without
+                * increasing sync_io so curr_events will (eventually)
+                * be larger than it was before.  Once it becomes
+                * substantially larger, the test below will cause
+                * the array to appear non-idle, and resync will slow
+                * down.
+                * If there is a lot of outstanding resync activity when
+                * we set last_event to curr_events, then all that activity
+                * completing might cause the array to appear non-idle
+                * and resync will be slowed down even though there might
+                * not have been non-resync activity.  This will only
+                * happen once though.  'last_events' will soon reflect
+                * the state where there is little or no outstanding
+                * resync requests, and further resync activity will
+                * always make curr_events less than last_events.
                 *
-                * Note: the following is an unsigned comparison.
                 */
-               if ((long)curr_events - (long)rdev->last_events > 4096) {
+               if (curr_events - rdev->last_events > 4096) {
                        rdev->last_events = curr_events;
                        idle = 0;
                }