2 files changed, 60 insertions, 4 deletions

diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 11108165e264..059704fbb753 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -1160,6 +1160,22 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect
                         return 0;
                 }
 
+                if (unlikely((*bmc & COUNTER_MAX) == COUNTER_MAX)) {
+                        DEFINE_WAIT(__wait);
+                        /* note that it is safe to do the prepare_to_wait
+                         * after the test as long as we do it before dropping
+                         * the spinlock.
+                         */
+                        prepare_to_wait(&bitmap->overflow_wait, &__wait,
+                                        TASK_UNINTERRUPTIBLE);
+                        spin_unlock_irq(&bitmap->lock);
+                        bitmap->mddev->queue
+                                ->unplug_fn(bitmap->mddev->queue);
+                        schedule();
+                        finish_wait(&bitmap->overflow_wait, &__wait);
+                        continue;
+                }
+
                 switch(*bmc) {
                 case 0:
                         bitmap_file_set_bit(bitmap, offset);
@@ -1169,7 +1185,7 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect
                 case 1:
                         *bmc = 2;
                 }
-                BUG_ON((*bmc & COUNTER_MAX) == COUNTER_MAX);
+
                 (*bmc)++;
 
                 spin_unlock_irq(&bitmap->lock);
@@ -1207,6 +1223,9 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto
                 if (!success && ! (*bmc & NEEDED_MASK))
                         *bmc |= NEEDED_MASK;
 
+                if ((*bmc & COUNTER_MAX) == COUNTER_MAX)
+                        wake_up(&bitmap->overflow_wait);
+
                 (*bmc)--;
                 if (*bmc <= 2) {
                         set_page_attr(bitmap,
@@ -1431,6 +1450,7 @@ int bitmap_create(mddev_t *mddev)
         spin_lock_init(&bitmap->lock);
         atomic_set(&bitmap->pending_writes, 0);
         init_waitqueue_head(&bitmap->write_wait);
+        init_waitqueue_head(&bitmap->overflow_wait);
 
         bitmap->mddev = mddev;
 
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 467c16982d02..11c3d7bfa797 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2620,7 +2620,7 @@ static struct bio *remove_bio_from_retry(raid5_conf_t *conf)
         }
         bi = conf->retry_read_aligned_list;
         if(bi) {
-                conf->retry_read_aligned = bi->bi_next;
+                conf->retry_read_aligned_list = bi->bi_next;
                 bi->bi_next = NULL;
                 bi->bi_phys_segments = 1; /* biased count of active stripes */
                 bi->bi_hw_segments = 0; /* count of processed stripes */
@@ -2669,6 +2669,27 @@ static int raid5_align_endio(struct bio *bi, unsigned int bytes, int error)
         return 0;
 }
 
+static int bio_fits_rdev(struct bio *bi)
+{
+        request_queue_t *q = bdev_get_queue(bi->bi_bdev);
+
+        if ((bi->bi_size>>9) > q->max_sectors)
+                return 0;
+        blk_recount_segments(q, bi);
+        if (bi->bi_phys_segments > q->max_phys_segments ||
+            bi->bi_hw_segments > q->max_hw_segments)
+                return 0;
+
+        if (q->merge_bvec_fn)
+                /* it's too hard to apply the merge_bvec_fn at this stage,
+                 * just just give up
+                 */
+                return 0;
+
+        return 1;
+}
+
+
 static int chunk_aligned_read(request_queue_t *q, struct bio * raid_bio)
 {
         mddev_t *mddev = q->queuedata;
@@ -2715,6 +2736,13 @@ static int chunk_aligned_read(request_queue_t *q, struct bio * raid_bio)
                 align_bi->bi_flags &= ~(1 << BIO_SEG_VALID);
                 align_bi->bi_sector += rdev->data_offset;
 
+                if (!bio_fits_rdev(align_bi)) {
+                        /* too big in some way */
+                        bio_put(align_bi);
+                        rdev_dec_pending(rdev, mddev);
+                        return 0;
+                }
+
                 spin_lock_irq(&conf->device_lock);
                 wait_event_lock_irq(conf->wait_for_stripe,
                                     conf->quiesce == 0,
@@ -3107,7 +3135,9 @@ static int  retry_aligned_read(raid5_conf_t *conf, struct bio *raid_bio)
         last_sector = raid_bio->bi_sector + (raid_bio->bi_size>>9);
 
         for (; logical_sector < last_sector;
-             logical_sector += STRIPE_SECTORS, scnt++) {
+             logical_sector += STRIPE_SECTORS,
+                     sector += STRIPE_SECTORS,
+                     scnt++) {
 
                 if (scnt < raid_bio->bi_hw_segments)
                         /* already done this stripe */
@@ -3123,7 +3153,13 @@ static int  retry_aligned_read(raid5_conf_t *conf, struct bio *raid_bio)
                 }
 
                 set_bit(R5_ReadError, &sh->dev[dd_idx].flags);
-                add_stripe_bio(sh, raid_bio, dd_idx, 0);
+                if (!add_stripe_bio(sh, raid_bio, dd_idx, 0)) {
+                        release_stripe(sh);
+                        raid_bio->bi_hw_segments = scnt;
+                        conf->retry_read_aligned = raid_bio;
+                        return handled;
+                }
+
                 handle_stripe(sh, NULL);
                 release_stripe(sh);
                 handled++;