[Devel] [PATCH hci-8.1 v2 6/6] dm-ploop: truncate unused tail of top delta on suspend

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

Preallocated space and clusters at the end of the top delta freed by
discard are never given back, so the file size never shrinks. Now that
ploop reloads metadata on resume, we can truncate the top delta on
suspend: the next resumed ploop (maybe of reloaded table) picks up the
new file size.

Add ploop_calc_used_end(), which returns the end of the last cluster
used by the delta: either BAT area, the last mapped cluster or format
extension. Metadata is read from disk rather than taken from memory:
the next table load checks BAT entries against the file size (-EPROTO
otherwise), while in-memory BAT may differ from on-disk one after
failed BAT writeback. Skip it if md pages are not clean, as on-disk BAT
may miss allocated clusters then.

Userspace writes format extension (CBT) behind the last data cluster
of suspended device on umount, resumes it, and then removes the device,
which suspends it again. So keep the area up to the end of format
extension header, which is the last cluster of the extension, as
userspace does. Name the corresponding header field properly instead
of m_Reserved.

Truncate the top delta to the used end in ploop_postsuspend() after
pending preallocation is completed. Do it under ctl_rwsem, so that
ploop messages (e.g. resize) don't change the image in parallel. Skip
read-only devices and raw top delta. On error just leave the file as is.

https://virtuozzo.atlassian.net/browse/VSTOR-148171
Feature: dm-ploop: ploop target driver

Signed-off-by: Alexander Ivanov <alexander.ivanov@virtuozzo.com>
---
 drivers/md/dm-ploop-bat.c    | 56 ++++++++++++++++++++++++++++++++++++
 drivers/md/dm-ploop-target.c | 49 +++++++++++++++++++++++++++++--
 drivers/md/dm-ploop.h        |  3 +-
 3 files changed, 104 insertions(+), 4 deletions(-)

diff --git a/drivers/md/dm-ploop-bat.c b/drivers/md/dm-ploop-bat.c
index fa87dd248f5b..0a40702fb7d3 100644
--- a/drivers/md/dm-ploop-bat.c
+++ b/drivers/md/dm-ploop-bat.c
@@ -682,6 +682,62 @@ int ploop_reload_metadata(struct ploop *ploop)
 }
 ALLOW_ERROR_INJECTION(ploop_reload_metadata, ERRNO);
 
+/*
+ * Returns the end of the last cluster of delta @file, which is used
+ * according to its header and BAT: either BAT area, the last mapped
+ * cluster or format extension. Clusters freed by discard may leave the
+ * tail of file unused. Metadata is read from disk, as the next table
+ * load checks BAT entries against the file size, while in-memory BAT
+ * may differ from it after failed BAT writeback. Also userspace may
+ * write format extension (e.g. CBT) behind the last data cluster of
+ * suspended device. This must be called on suspended device.
+ */
+loff_t ploop_calc_used_end(struct ploop *ploop, struct file *file)
+{
+	u32 i, end, nr_be, dst_clu, used_clus, *bat_entries;
+	struct rb_root md_root = RB_ROOT;
+	struct ploop_pvd_header *hdr;
+	loff_t used_end, ext_end;
+	struct rb_node *node;
+	struct md_page *md;
+	u64 ext_off;
+	int ret;
+
+	/* BAT on disk may miss allocated clusters until writeback is done */
+	if (WARN_ON_ONCE(!ploop_md_pages_are_clean(ploop)))
+		return -EBUSY;
+
+	ret = ploop_read_delta_metadata(ploop, file, &md_root, &nr_be);
+	if (ret)
+		return ret;
+
+	used_clus = ploop_nr_bat_clusters(ploop, nr_be);
+	rb_root_for_each_md_page(&md_root, md, node) {
+		bat_entries = md->kmpage;
+		init_be_iter(nr_be, md->id, &i, &end);
+		for (; i <= end; i++) {
+			dst_clu = READ_ONCE(bat_entries[i]);
+			if (dst_clu != BAT_ENTRY_NONE && dst_clu >= used_clus)
+				used_clus = dst_clu + 1;
+		}
+	}
+
+	used_end = CLU_TO_POS(ploop, used_clus);
+
+	/* Format extension header is the last cluster of extension */
+	hdr = ploop_md_first_entry(&md_root)->kmpage;
+	ext_off = le64_to_cpu(hdr->m_FormatExtensionOffset);
+	if (ext_off) {
+		ext_end = to_bytes(ext_off) + CLU_SIZE(ploop);
+		if (ext_end > used_end)
+			used_end = ext_end;
+	}
+
+	ploop_free_md_pages_tree(&md_root);
+	return used_end;
+}
+ALLOW_ERROR_INJECTION(ploop_calc_used_end, ERRNO);
+
 void ploop_put_delta(struct ploop *ploop, struct ploop_delta *delta)
 {
 	int i;
diff --git a/drivers/md/dm-ploop-target.c b/drivers/md/dm-ploop-target.c
index c9183fa9d3ca..88cc91a3d03a 100644
--- a/drivers/md/dm-ploop-target.c
+++ b/drivers/md/dm-ploop-target.c
@@ -441,8 +441,9 @@ static struct ploop_worker *ploop_worker_create(struct ploop *ploop,
  * ploop_dtr, as ploop_dtr is called on the old ploop after the new one is
  * resumed, so we can't possibly modify the image from the old ploop context
  * at this point, as new ploop may be already doing its own IO or
- * preallocation. This truncation should be done on ploop_*suspend (see
- * dm-qcow2 as it already implements that in qcow2_truncate_preallocations).
+ * preallocation. So this truncation is done on ploop_postsuspend (see
+ * ploop_truncate_unused_tail), and the new ploop picks up the new size
+ * of the top delta on metadata reload.
  */
 static int ploop_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 {
@@ -733,16 +734,58 @@ static void ploop_presuspend_undo(struct dm_target *ti)
 {
 	ploop_set_wants_suspend(ti, false);
 }
+
+/*
+ * Truncate preallocations and the tail of the top delta, which became
+ * unused after discard. The next resumed ploop (maybe of reloaded
+ * table) re-reads the size of the top delta in ploop_preresume().
+ */
+static void ploop_truncate_unused_tail(struct ploop *ploop)
+{
+	struct ploop_delta *top = ploop_top_delta(ploop);
+	unsigned long flags;
+	loff_t end;
+	int ret;
+
+	lockdep_assert_held_write(&ploop->ctl_rwsem);
+
+	if (ploop_is_ro(ploop) || top->is_raw)
+		return;
+
+	end = ploop_calc_used_end(ploop, top->file);
+	if (end < 0) {
+		PL_ERR("Can't find used end of top delta: %lld", end);
+		return;
+	}
+	if (end >= top->file_size)
+		return;
+
+	ret = do_ftruncate(top->file, end, 0);
+	if (ret) {
+		PL_ERR("Can't truncate unused tail of top delta: %d", ret);
+		return;
+	}
+
+	spin_lock_irqsave(&ploop->bat_lock, flags);
+	top->file_size = end;
+	if (top->file_preallocated_area_start > end)
+		top->file_preallocated_area_start = end;
+	spin_unlock_irqrestore(&ploop->bat_lock, flags);
+}
+
 static void ploop_postsuspend(struct dm_target *ti)
 {
 	struct ploop *ploop = ti->private;
 
+	down_write(&ploop->ctl_rwsem);
 	/*
 	 * Let the next resumed ploop (maybe of reloaded table)
 	 * see final size of the top delta.
 	 */
 	ploop_wait_prealloc(ploop);
-	ploop_set_suspended(ti, true);
+	ploop_truncate_unused_tail(ploop);
+	ploop->suspended = true;
+	up_write(&ploop->ctl_rwsem);
 }
 static int ploop_preresume(struct dm_target *ti)
 {
diff --git a/drivers/md/dm-ploop.h b/drivers/md/dm-ploop.h
index 1cf0d5e0cea8..e46d6efdce59 100644
--- a/drivers/md/dm-ploop.h
+++ b/drivers/md/dm-ploop.h
@@ -35,7 +35,7 @@ struct ploop_pvd_header {
 	__u32 m_DiskInUse;	/* Disk in use */
 	__u32 m_FirstBlockOffset; /* First data block offset (in sectors) */
 	__u32 m_Flags;		/* Misc flags */
-	__u8  m_Reserved[8];	/* Reserved */
+	__u64 m_FormatExtensionOffset; /* Format extension offset (in sectors) */
 };
 #pragma pack(pop)
 
@@ -634,6 +634,7 @@ extern void ploop_pio_prepare_offsets(struct ploop *ploop, struct pio *pio, u32
 extern int ploop_setup_metadata(struct ploop *ploop, struct page *page,
 				bool check_in_use);
 extern int ploop_reload_metadata(struct ploop *ploop);
+extern loff_t ploop_calc_used_end(struct ploop *ploop, struct file *file);
 extern int ploop_read_delta_metadata(struct ploop *ploop, struct file *file,
 				     struct rb_root *md_root, u32 *delta_nr_be);
 extern void ploop_index_wb_init(struct ploop_index_wb *piwb,
-- 
2.53.0

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