[PATCH] md: avoid possible BUG_ON in md bitmap handling

md/bitmap tracks how many active write requests are pending on blocks
associated with each bit in the bitmap, so that it knows when it can clear
the bit (when count hits zero).

The counter has 14 bits of space, so if there are ever more than 16383, we
cannot cope.

Currently the code just calles BUG_ON as "all" drivers have request queue
limits much smaller than this.

However is seems that some don't.  Apparently some multipath configurations
can allow more than 16383 concurrent write requests.

So, in this unlikely situation, instead of calling BUG_ON we now wait
for the count to drop down a bit.  This requires a new wait_queue_head,
some waiting code, and a wakeup call.

Tested by limiting the counter to 20 instead of 16383 (writes go a lot slower
in that case...).

Signed-off-by: Neil Brown <neilb@suse.de>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 22 insertions, 1 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/include/linux/raid/bitmap.h b/include/linux/raid/bitmap.h
index ebd42a3710b4..6db9a4c15355 100644
--- a/include/linux/raid/bitmap.h
+++ b/include/linux/raid/bitmap.h
@@ -247,6 +247,7 @@ struct bitmap {
 
         atomic_t pending_writes; /* pending writes to the bitmap file */
         wait_queue_head_t write_wait;
+        wait_queue_head_t overflow_wait;
 
 };