[Devel] [PATCH hci-8.1 v4 3/3] dm-qcow2: truncate unused tail of image on suspend

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

On postsuspend we truncate the image file only down to
file_preallocated_area_start, i.e. we drop preallocations only.
Clusters at the end of the file freed by discard (refcount dropped
to zero) are never given back, so the file size never shrinks.

Add qcow2_calc_used_end(), which scans refcount blocks backward from
file_preallocated_area_start and returns the end of the last cluster
with non-zero refcount. Refcount ranges with no allocated refblock
are skipped at once. Metadata pages are taken from md cache or read
synchronously. This is called on suspended device after md writeback,
so R1 and R2 can't change under us.

Truncate the file to the used end. Skip the scan if md writeback
failed, as refcounts on disk are stale then, and fall back to the old
behaviour on scan error.

Close and reload to RO go through postsuspend too: on remove,
__dm_destroy() suspends the live table if it isn't suspended yet,
and on table swap do_resume() suspends the old (RW) table before
dm_swap_table(). So the tail is given back in these cases as well.

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    | 56 ++++++++++++++++++++++++++++++++++++
 drivers/md/dm-qcow2-target.c | 12 +++++++-
 drivers/md/dm-qcow2.h        |  1 +
 3 files changed, 68 insertions(+), 1 deletion(-)

diff --git a/drivers/md/dm-qcow2-map.c b/drivers/md/dm-qcow2-map.c
index 78ee7cf5e881..65ee6ae144bf 100644
--- a/drivers/md/dm-qcow2-map.c
+++ b/drivers/md/dm-qcow2-map.c
@@ -2208,6 +2208,62 @@ int qcow2_truncate_safe(struct file *file, loff_t new_len)
 	return do_ftruncate(file, new_len, 0);
 }
 
+/*
+ * Returns the end of the last cluster, which is used according
+ * to refcount table, clamped to file_preallocated_area_start since
+ * the last cluster may be partial. Clusters freed by discard may
+ * leave the tail of file unused. Everything at or above
+ * file_preallocated_area_start is unused by construction, so the scan
+ * starts below it. This must be called on suspended device after md
+ * writeback, so nobody changes R1 and R2.
+ */
+loff_t qcow2_calc_used_end(struct qcow2 *qcow2)
+{
+	u32 clu_size = qcow2->clu_size;
+	struct qcow2_map_item r1, r2;
+	struct md_page *r1_md = NULL;
+	loff_t pos;
+	s32 i;
+	int ret;
+
+	pos = round_down(qcow2->file_preallocated_area_start - 1, clu_size);
+	while (pos >= 0) {
+		if (calc_refcounters_map(qcow2, pos, &r1, &r2) < 0)
+			return -EIO;
+
+		if (!r1_md || r1_md->id != r1.page_id) {
+			ret = qcow2_md_page_read_sync(qcow2, r1.page_id, &r1_md);
+			if (ret)
+				return ret;
+		}
+		r1.md = r1_md;
+
+		ret = calc_r2_page_id(qcow2, &r1, &r2);
+		if (ret == -ENOENT) {
+			/* No R2 cluster, so all clusters it covers are unused */
+			pos = (loff_t)r1.index * qcow2->refblock_entries * clu_size;
+			pos -= clu_size;
+			continue;
+		}
+
+		if (ret < 0)
+			return ret;
+
+		ret = qcow2_md_page_read_sync(qcow2, r2.page_id, &r2.md);
+		if (ret)
+			return ret;
+
+		for (i = r2.index_in_page; i >= 0; i--, pos -= clu_size) {
+			/* Last cluster is partial if size isn't cluster-aligned */
+			if (get_r2_entry(qcow2, r2.md, i))
+				return min_t(loff_t, pos + clu_size,
+					     qcow2->file_preallocated_area_start);
+		}
+	}
+
+	return -EIO;
+}
+
 static int truncate_prealloc_safe(struct qcow2 *qcow2, loff_t len, const char *func)
 {
 	loff_t prealloc_len, max_prealloc_len = qcow2->reftable_max_file_size;
diff --git a/drivers/md/dm-qcow2-target.c b/drivers/md/dm-qcow2-target.c
index bb11b8a74598..8555494a0c1c 100644
--- a/drivers/md/dm-qcow2-target.c
+++ b/drivers/md/dm-qcow2-target.c
@@ -1047,11 +1047,21 @@ static void qcow2_truncate_preallocations(struct dm_target *ti)
 {
 	struct qcow2_target *tgt = to_qcow2_target(ti);
 	struct qcow2 *qcow2 = top_qcow2_protected(ti);
-	loff_t end = qcow2->file_preallocated_area_start;
+	loff_t used_end, end = qcow2->file_preallocated_area_start;
 	int ret;
 
 	if (!(dm_table_get_mode(ti->table) & FMODE_WRITE))
 		return;
+
+	/* Refcounts on disk are stale after failed md writeback */
+	if (!tgt->md_writeback_error) {
+		used_end = qcow2_calc_used_end(qcow2);
+		if (used_end < 0)
+			QC_ERR(ti, "Can't find used end: %pe", ERR_PTR(used_end));
+		else
+			end = used_end;
+	}
+
 	if (end == qcow2->file_size)
 		return;
 
diff --git a/drivers/md/dm-qcow2.h b/drivers/md/dm-qcow2.h
index 69d3ae6fca8a..73d3cf175bbf 100644
--- a/drivers/md/dm-qcow2.h
+++ b/drivers/md/dm-qcow2.h
@@ -411,6 +411,7 @@ void qcow2_ref_dec(struct qcow2_target *tgt, u8 ref_index);
 int qcow2_inflight_ref_switch(struct qcow2_target *tgt);
 void qcow2_flush_deferred_activity(struct qcow2_target *tgt, struct qcow2 *qcow2);
 int qcow2_truncate_safe(struct file *file, loff_t new_len);
+loff_t qcow2_calc_used_end(struct qcow2 *qcow2);
 
 void qcow2_merge_backward_work(struct work_struct *work);
 void qcow2_merge_backward_cancel(struct qcow2_target *tgt);
-- 
2.53.0

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