dm btree: add ref counting ops for the leaves of top level btrees

When using nested btrees, the top leaves of the top levels contain block addresses for the root of the next tree down. If we shadow a shared leaf node the leaf values (sub tree roots) should be incremented accordingly. This is only an issue if there is metadata sharing in the top levels. Which only occurs if metadata snapshots are being used (as is possible with dm-thinp). And could result in a block from the thinp metadata snap being reused early, thus corrupting the thinp metadata snap. Signed-off-by: Joe Thornber <[email protected]> Signed-off-by: Mike Snitzer <[email protected]> Cc: [email protected]
kyagi · Aug 12, 2015 · b0dc3c8 · b0dc3c8
1 parent 7f518ad
commit b0dc3c8
Show file tree

Hide file tree

Showing 4 changed files with 50 additions and 16 deletions.
diff --git a/drivers/md/persistent-data/dm-btree-internal.h b/drivers/md/persistent-data/dm-btree-internal.h
@@ -138,4 +138,10 @@ int lower_bound(struct btree_node *n, uint64_t key);
 
 extern struct dm_block_validator btree_node_validator;
 
+/*
+ * Value type for upper levels of multi-level btrees.
+ */
+extern void init_le64_type(struct dm_transaction_manager *tm,
+			   struct dm_btree_value_type *vt);
+
 #endif	/* DM_BTREE_INTERNAL_H */
diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c
@@ -544,27 +544,21 @@ static int remove_raw(struct shadow_spine *s, struct dm_btree_info *info,
 	return r;
 }
 
-static struct dm_btree_value_type le64_type = {
-	.context = NULL,
-	.size = sizeof(__le64),
-	.inc = NULL,
-	.dec = NULL,
-	.equal = NULL
-};
-
 int dm_btree_remove(struct dm_btree_info *info, dm_block_t root,
 		    uint64_t *keys, dm_block_t *new_root)
 {
 	unsigned level, last_level = info->levels - 1;
 	int index = 0, r = 0;
 	struct shadow_spine spine;
 	struct btree_node *n;
+	struct dm_btree_value_type le64_vt;
 
+	init_le64_type(info->tm, &le64_vt);
 	init_shadow_spine(&spine, info);
 	for (level = 0; level < info->levels; level++) {
 		r = remove_raw(&spine, info,
 			       (level == last_level ?
-				&info->value_type : &le64_type),
+				&info->value_type : &le64_vt),
 			       root, keys[level], (unsigned *)&index);
 		if (r < 0)
 			break;
@@ -654,11 +648,13 @@ static int remove_one(struct dm_btree_info *info, dm_block_t root,
 	int index = 0, r = 0;
 	struct shadow_spine spine;
 	struct btree_node *n;
+	struct dm_btree_value_type le64_vt;
 	uint64_t k;
 
+	init_le64_type(info->tm, &le64_vt);
 	init_shadow_spine(&spine, info);
 	for (level = 0; level < last_level; level++) {
-		r = remove_raw(&spine, info, &le64_type,
+		r = remove_raw(&spine, info, &le64_vt,
 			       root, keys[level], (unsigned *) &index);
 		if (r < 0)
 			goto out;

diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c
@@ -249,3 +249,40 @@ int shadow_root(struct shadow_spine *s)
 {
 	return s->root;
 }
+
+static void le64_inc(void *context, const void *value_le)
+{
+	struct dm_transaction_manager *tm = context;
+	__le64 v_le;
+
+	memcpy(&v_le, value_le, sizeof(v_le));
+	dm_tm_inc(tm, le64_to_cpu(v_le));
+}
+
+static void le64_dec(void *context, const void *value_le)
+{
+	struct dm_transaction_manager *tm = context;
+	__le64 v_le;
+
+	memcpy(&v_le, value_le, sizeof(v_le));
+	dm_tm_dec(tm, le64_to_cpu(v_le));
+}
+
+static int le64_equal(void *context, const void *value1_le, const void *value2_le)
+{
+	__le64 v1_le, v2_le;
+
+	memcpy(&v1_le, value1_le, sizeof(v1_le));
+	memcpy(&v2_le, value2_le, sizeof(v2_le));
+	return v1_le == v2_le;
+}
+
+void init_le64_type(struct dm_transaction_manager *tm,
+		    struct dm_btree_value_type *vt)
+{
+	vt->context = tm;
+	vt->size = sizeof(__le64);
+	vt->inc = le64_inc;
+	vt->dec = le64_dec;
+	vt->equal = le64_equal;
+}
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
@@ -667,12 +667,7 @@ static int insert(struct dm_btree_info *info, dm_block_t root,
 	struct btree_node *n;
 	struct dm_btree_value_type le64_type;
 
-	le64_type.context = NULL;
-	le64_type.size = sizeof(__le64);
-	le64_type.inc = NULL;
-	le64_type.dec = NULL;
-	le64_type.equal = NULL;
-
+	init_le64_type(info->tm, &le64_type);
 	init_shadow_spine(&spine, info);
 
 	for (level = 0; level < (info->levels - 1); level++) {