drbd: Write all pages of the bitmap after an online resize

We need to write the whole bitmap after we moved the meta data
due to an online resize operation.

With the support for one peta byte devices bitmap IO was optimized
to only write out touched pages. This optimization must be turned
off when writing the bitmap after an online resize.

This issue was introduced with drbd-8.3.10.

The impact of this bug is that after an online resize, the next
resync could become larger than expected.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>

3 files changed, 17 insertions, 3 deletions

diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index ba91b408abad..d84566496746 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/drivers/block/drbd/drbd_bitmap.c
@@ -889,6 +889,7 @@ struct bm_aio_ctx {
 	unsigned int done;
 	unsigned flags;
 #define BM_AIO_COPY_PAGES	1
+#define BM_WRITE_ALL_PAGES	2
 	int error;
 	struct kref kref;
 };
@@ -1059,7 +1060,8 @@ static int bm_rw(struct drbd_conf *mdev, int rw, unsigned flags, unsigned lazy_w
 		if (lazy_writeout_upper_idx && i == lazy_writeout_upper_idx)
 			break;
 		if (rw & WRITE) {
-			if (bm_test_page_unchanged(b->bm_pages[i])) {
+			if (!(flags & BM_WRITE_ALL_PAGES) &&
+			    bm_test_page_unchanged(b->bm_pages[i])) {
 				dynamic_dev_dbg(DEV, "skipped bm write for idx %u\n", i);
 				continue;
 			}
@@ -1141,6 +1143,17 @@ int drbd_bm_write(struct drbd_conf *mdev) __must_hold(local)
 }
 
 /**
+ * drbd_bm_write_all() - Write the whole bitmap to its on disk location.
+ * @mdev:	DRBD device.
+ *
+ * Will write all pages.
+ */
+int drbd_bm_write_all(struct drbd_conf *mdev) __must_hold(local)
+{
+	return bm_rw(mdev, WRITE, BM_WRITE_ALL_PAGES, 0);
+}
+
+/**
  * drbd_bm_lazy_write_out() - Write bitmap pages 0 to @upper_idx-1, if they have changed.
  * @mdev:	DRBD device.
  * @upper_idx:	0: write all changed pages; +ve: page index to stop scanning for changed pages
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index b2ca143d0053..b953cc7c9c00 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1469,6 +1469,7 @@ extern int  drbd_bm_e_weight(struct drbd_conf *mdev, unsigned long enr);
 extern int  drbd_bm_write_page(struct drbd_conf *mdev, unsigned int idx) __must_hold(local);
 extern int  drbd_bm_read(struct drbd_conf *mdev) __must_hold(local);
 extern int  drbd_bm_write(struct drbd_conf *mdev) __must_hold(local);
+extern int drbd_bm_write_all(struct drbd_conf *mdev) __must_hold(local);
 extern int  drbd_bm_write_copy_pages(struct drbd_conf *mdev) __must_hold(local);
 extern unsigned long drbd_bm_ALe_set_all(struct drbd_conf *mdev,
 		unsigned long al_enr);
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index fb9dce8daa24..edb490aad8b4 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -674,8 +674,8 @@ enum determine_dev_size drbd_determine_dev_size(struct drbd_conf *mdev, enum dds
 			 la_size_changed && md_moved ? "size changed and md moved" :
 			 la_size_changed ? "size changed" : "md moved");
 		/* next line implicitly does drbd_suspend_io()+drbd_resume_io() */
-		err = drbd_bitmap_io(mdev, &drbd_bm_write,
-				"size changed", BM_LOCKED_MASK);
+		err = drbd_bitmap_io(mdev, md_moved ? &drbd_bm_write_all : &drbd_bm_write,
+				     "size changed", BM_LOCKED_MASK);
 		if (err) {
 			rv = dev_size_error;
 			goto out;