[Devel] [PATCH hci-8.1 v9 08/10] dm-qcow2: flag the image for check if reftable relocation fails late

[Alexander Ivanov <alexander.ivanov@virtuozzo.com>]

Once relocate_refcount_table() has issued the header write pointing to
the new reftable, any failure returns -EIO. The header on disk may
already point to the new reftable even if its own write fails: a short
write is reported as -ENODATA, and the old reftable position is
restored only in the cached header page, which a v2 image never
rewrites on suspend. The new reftable on disk may then be unfilled or
miss the new refblocks, while refcounts of the new and old reftable
clusters may not be updated. Refcounts no longer match the header, but
nothing reports that, so the device can be resumed and the image
reopened as if it were consistent.

Set md_writeback_error on these paths, so wants_check reports the image
and resume is refused until it is checked, and log the failure.

https://virtuozzo.atlassian.net/browse/VSTOR-148171
Feature: dm-qcow2: block device over QCOW2 files driver

Signed-off-by: Alexander Ivanov <alexander.ivanov@virtuozzo.com>
---
 drivers/md/dm-qcow2-map.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/md/dm-qcow2-map.c b/drivers/md/dm-qcow2-map.c
index f6e66799bf27..185243584e0c 100644
--- a/drivers/md/dm-qcow2-map.c
+++ b/drivers/md/dm-qcow2-map.c
@@ -2351,6 +2351,8 @@ static int relocate_refcount_table(struct qcow2 *qcow2, struct qio **qio)
 	if (ret) {
 		/* Restore old R1 */
 		set_reftable_in_raw_hdr(md0->page, old_pos, old_clus);
+		QC_ERR(qcow2->tgt->ti, "failed to relocate refcount table");
+		qcow2->tgt->md_writeback_error = true;
 		goto err_free_r2_pages;
 	}
 
@@ -2376,17 +2378,17 @@ static int relocate_refcount_table(struct qcow2 *qcow2, struct qio **qio)
 	}
 	spin_unlock_irq(&qcow2->md_pages_lock);
 	if (i != nr_pages)
-		return -EIO;
+		goto err_hdr_written;
 
 	/* Connect new R2 to new R1 */
 	for (i = end; i < r2_end; i += clu_size) {
 		if (calc_refcounters_map(qcow2, i, &r1, &r2) < 0) {
 			WARN_ON_ONCE(1);
-			return -EIO;
+			goto err_hdr_written;
 		}
 		ret = handle_md_page(qcow2, r1.page_id, NULL, &md);
 		if (WARN_ON_ONCE(ret <= 0))
-			return -EIO;
+			goto err_hdr_written;
 		spin_lock_irq(&qcow2->md_pages_lock);
 		set_u64_to_be_page(md->page, r1.index_in_page, i);
 		qcow2_md_make_dirty(qcow2, md, true);
@@ -2397,7 +2399,7 @@ static int relocate_refcount_table(struct qcow2 *qcow2, struct qio **qio)
 	for (i = pos; i < r2_end; i += clu_size) {
 		ret = qcow2_handle_r1r2_maps(qcow2, i, NULL, &r1, &r2, false);
 		if (WARN_ON_ONCE(ret <= 0))
-			return -EIO;
+			goto err_hdr_written;
 		mark_cluster_used(qcow2, r2.md, r2.index_in_page);
 	}
 
@@ -2405,12 +2407,16 @@ static int relocate_refcount_table(struct qcow2 *qcow2, struct qio **qio)
 	for (i = old_pos; i < old_end; i += clu_size) {
 		ret = qcow2_handle_r1r2_maps(qcow2, i, NULL, &r1, &r2, false);
 		if (WARN_ON_ONCE(ret <= 0))
-			return -EIO;
+			goto err_hdr_written;
 		mark_cluster_unused(qcow2, r2.md, r2.index_in_page, i);
 	}
 
 	return 1;
 
+err_hdr_written:
+	QC_ERR(qcow2->tgt->ti, "failed to relocate refcount table");
+	qcow2->tgt->md_writeback_error = true;
+	return -EIO;
 err_free_r2_pages:
 	while (i > pos + (u64)old_clus * clu_size) {
 		i -= PAGE_SIZE;
-- 
2.53.0

_______________________________________________
Devel mailing list
Devel@openvz.org
https://lists.openvz.org/mailman/listinfo/devel