[PATCH] md: fix some small races in bitmap plugging in raid5

The comment gives more details, but I didn't quite have the sequencing write,
so there was room for races to leave bits unset in the on-disk bitmap for
short periods of time.

Signed-off-by: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 6ba39408212967341ab370e32f154fae2d1a5753..56303ff3173072162871d6fdb57b897411055fd3 100644 (file)
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -18,6 +18,30 @@
  * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+/*
+ * BITMAP UNPLUGGING:
+ *
+ * The sequencing for updating the bitmap reliably is a little
+ * subtle (and I got it wrong the first time) so it deserves some
+ * explanation.
+ *
+ * We group bitmap updates into batches.  Each batch has a number.
+ * We may write out several batches at once, but that isn't very important.
+ * conf->bm_write is the number of the last batch successfully written.
+ * conf->bm_flush is the number of the last batch that was closed to
+ *    new additions.
+ * When we discover that we will need to write to any block in a stripe
+ * (in add_stripe_bio) we update the in-memory bitmap and record in sh->bm_seq
+ * the number of the batch it will be in. This is bm_flush+1.
+ * When we are ready to do a write, if that batch hasn't been written yet,
+ *   we plug the array and queue the stripe for later.
+ * When an unplug happens, we increment bm_flush, thus closing the current
+ *   batch.
+ * When we notice that bm_flush > bm_write, we write out all pending updates
+ * to the bitmap, and advance bm_write to where bm_flush was.
+ * This may occasionally write a bit out twice, but is sure never to
+ * miss any bits.
+ */
 
 #include <linux/module.h>
 #include <linux/slab.h>
@@ -92,7 +116,7 @@ static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh)
                                list_add_tail(&sh->lru, &conf->delayed_list);
                                blk_plug_device(conf->mddev->queue);
                        } else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
-                                  conf->seq_write == sh->bm_seq) {
+                                  sh->bm_seq - conf->seq_write > 0) {
                                list_add_tail(&sh->lru, &conf->bitmap_list);
                                blk_plug_device(conf->mddev->queue);
                        } else {
@@ -1273,9 +1297,9 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
                (unsigned long long)sh->sector, dd_idx);
 
        if (conf->mddev->bitmap && firstwrite) {
-               sh->bm_seq = conf->seq_write;
                bitmap_startwrite(conf->mddev->bitmap, sh->sector,
                                  STRIPE_SECTORS, 0);
+               sh->bm_seq = conf->seq_flush+1;
                set_bit(STRIPE_BIT_DELAY, &sh->state);
        }
 
@@ -2918,7 +2942,7 @@ static void raid5d (mddev_t *mddev)
        while (1) {
                struct list_head *first;
 
-               if (conf->seq_flush - conf->seq_write > 0) {
+               if (conf->seq_flush != conf->seq_write) {
                        int seq = conf->seq_flush;
                        spin_unlock_irq(&conf->device_lock);
                        bitmap_unplug(mddev->bitmap);