[PULL 13/39] block: use topological sort for permission update

[Kevin Wolf <kwolf@redhat.com>]

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

Rewrite bdrv_check_perm(), bdrv_abort_perm_update() and bdrv_set_perm()
to update nodes in topological sort order instead of simple DFS. With
topologically sorted nodes, we update a node only when all its parents
already updated. With DFS it's not so.

Consider the following example:

    A -+
    |  |
    |  v
    |  B
    |  |
    v  |
    C<-+

A is parent for B and C, B is parent for C.

Obviously, to update permissions, we should go in order A B C, so, when
we update C, all parent permissions already updated. But with current
approach (simple recursion) we can update in sequence A C B C (C is
updated twice). On first update of C, we consider old B permissions, so
doing wrong thing. If it succeed, all is OK, on second C update we will
finish with correct graph. But if the wrong thing failed, we break the
whole process for no reason (it's possible that updated B permission
will be less strict, but we will never check it).

Also new approach gives a way to simultaneously and correctly update
several nodes, we just need to run bdrv_topological_dfs() several times
to add all nodes and their subtrees into one topologically sorted list
(next patch will update bdrv_replace_node() in this manner).

Test test_parallel_perm_update() is now passing, so move it out of
debugging "if".

We also need to support ignore_children in
bdrv_parent_perms_conflict()

For test 283 order of conflicting parents check is changed.

Note also that in bdrv_check_perm() we don't check for parents conflict
at root bs, as we may be in the middle of permission update in
bdrv_reopen_multiple(). bdrv_reopen_multiple() will be updated soon.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20210428151804.439460-14-vsementsov@virtuozzo.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
 block.c                          | 116 +++++++++++++++++++++++++------
 tests/unit/test-bdrv-graph-mod.c |   4 +-
 tests/qemu-iotests/283.out       |   2 +-
 3 files changed, 99 insertions(+), 23 deletions(-)

diff --git a/block.c b/block.c
index e5af4cdae9..cbcc4c15a0 100644
--- a/block.c
+++ b/block.c
@@ -2054,7 +2054,9 @@ static bool bdrv_a_allow_b(BdrvChild *a, BdrvChild *b, Error **errp)
     return false;
 }
 
-static bool bdrv_parent_perms_conflict(BlockDriverState *bs, Error **errp)
+static bool bdrv_parent_perms_conflict(BlockDriverState *bs,
+                                       GSList *ignore_children,
+                                       Error **errp)
 {
     BdrvChild *a, *b;
 
@@ -2064,8 +2066,12 @@ static bool bdrv_parent_perms_conflict(BlockDriverState *bs, Error **errp)
      * directions.
      */
     QLIST_FOREACH(a, &bs->parents, next_parent) {
+        if (g_slist_find(ignore_children, a)) {
+            continue;
+        }
+
         QLIST_FOREACH(b, &bs->parents, next_parent) {
-            if (a == b) {
+            if (a == b || g_slist_find(ignore_children, b)) {
                 continue;
             }
 
@@ -2094,6 +2100,40 @@ static void bdrv_child_perm(BlockDriverState *bs, BlockDriverState *child_bs,
     }
 }
 
+/*
+ * Adds the whole subtree of @bs (including @bs itself) to the @list (except for
+ * nodes that are already in the @list, of course) so that final list is
+ * topologically sorted. Return the result (GSList @list object is updated, so
+ * don't use old reference after function call).
+ *
+ * On function start @list must be already topologically sorted and for any node
+ * in the @list the whole subtree of the node must be in the @list as well. The
+ * simplest way to satisfy this criteria: use only result of
+ * bdrv_topological_dfs() or NULL as @list parameter.
+ */
+static GSList *bdrv_topological_dfs(GSList *list, GHashTable *found,
+                                    BlockDriverState *bs)
+{
+    BdrvChild *child;
+    g_autoptr(GHashTable) local_found = NULL;
+
+    if (!found) {
+        assert(!list);
+        found = local_found = g_hash_table_new(NULL, NULL);
+    }
+
+    if (g_hash_table_contains(found, bs)) {
+        return list;
+    }
+    g_hash_table_add(found, bs);
+
+    QLIST_FOREACH(child, &bs->children, next) {
+        list = bdrv_topological_dfs(list, found, child->bs);
+    }
+
+    return g_slist_prepend(list, bs);
+}
+
 static void bdrv_child_set_perm_commit(void *opaque)
 {
     BdrvChild *c = opaque;
@@ -2158,10 +2198,10 @@ static void bdrv_child_set_perm_safe(BdrvChild *c, uint64_t perm,
  * A call to this function must always be followed by a call to bdrv_set_perm()
  * or bdrv_abort_perm_update().
  */
-static int bdrv_check_perm(BlockDriverState *bs, BlockReopenQueue *q,
-                           uint64_t cumulative_perms,
-                           uint64_t cumulative_shared_perms,
-                           GSList *ignore_children, Error **errp)
+static int bdrv_node_check_perm(BlockDriverState *bs, BlockReopenQueue *q,
+                                uint64_t cumulative_perms,
+                                uint64_t cumulative_shared_perms,
+                                GSList *ignore_children, Error **errp)
 {
     BlockDriver *drv = bs->drv;
     BdrvChild *c;
@@ -2226,21 +2266,43 @@ static int bdrv_check_perm(BlockDriverState *bs, BlockReopenQueue *q,
     /* Check all children */
     QLIST_FOREACH(c, &bs->children, next) {
         uint64_t cur_perm, cur_shared;
-        GSList *cur_ignore_children;
 
         bdrv_child_perm(bs, c->bs, c, c->role, q,
                         cumulative_perms, cumulative_shared_perms,
                         &cur_perm, &cur_shared);
+        bdrv_child_set_perm_safe(c, cur_perm, cur_shared, NULL);
+    }
+
+    return 0;
+}
+
+static int bdrv_check_perm(BlockDriverState *bs, BlockReopenQueue *q,
+                           uint64_t cumulative_perms,
+                           uint64_t cumulative_shared_perms,
+                           GSList *ignore_children, Error **errp)
+{
+    int ret;
+    BlockDriverState *root = bs;
+    g_autoptr(GSList) list = bdrv_topological_dfs(NULL, NULL, root);
 
-        cur_ignore_children = g_slist_prepend(g_slist_copy(ignore_children), c);
-        ret = bdrv_check_update_perm(c->bs, q, cur_perm, cur_shared,
-                                     cur_ignore_children, errp);
-        g_slist_free(cur_ignore_children);
+    for ( ; list; list = list->next) {
+        bs = list->data;
+
+        if (bs != root) {
+            if (bdrv_parent_perms_conflict(bs, ignore_children, errp)) {
+                return -EINVAL;
+            }
+
+            bdrv_get_cumulative_perm(bs, &cumulative_perms,
+                                     &cumulative_shared_perms);
+        }
+
+        ret = bdrv_node_check_perm(bs, q, cumulative_perms,
+                                   cumulative_shared_perms,
+                                   ignore_children, errp);
         if (ret < 0) {
             return ret;
         }
-
-        bdrv_child_set_perm_safe(c, cur_perm, cur_shared, NULL);
     }
 
     return 0;
@@ -2250,10 +2312,8 @@ static int bdrv_check_perm(BlockDriverState *bs, BlockReopenQueue *q,
  * Notifies drivers that after a previous bdrv_check_perm() call, the
  * permission update is not performed and any preparations made for it (e.g.
  * taken file locks) need to be undone.
- *
- * This function recursively notifies all child nodes.
  */
-static void bdrv_abort_perm_update(BlockDriverState *bs)
+static void bdrv_node_abort_perm_update(BlockDriverState *bs)
 {
     BlockDriver *drv = bs->drv;
     BdrvChild *c;
@@ -2268,11 +2328,19 @@ static void bdrv_abort_perm_update(BlockDriverState *bs)
 
     QLIST_FOREACH(c, &bs->children, next) {
         bdrv_child_set_perm_abort(c);
-        bdrv_abort_perm_update(c->bs);
     }
 }
 
-static void bdrv_set_perm(BlockDriverState *bs)
+static void bdrv_abort_perm_update(BlockDriverState *bs)
+{
+    g_autoptr(GSList) list = bdrv_topological_dfs(NULL, NULL, bs);
+
+    for ( ; list; list = list->next) {
+        bdrv_node_abort_perm_update((BlockDriverState *)list->data);
+    }
+}
+
+static void bdrv_node_set_perm(BlockDriverState *bs)
 {
     uint64_t cumulative_perms, cumulative_shared_perms;
     BlockDriver *drv = bs->drv;
@@ -2298,7 +2366,15 @@ static void bdrv_set_perm(BlockDriverState *bs)
     /* Update all children */
     QLIST_FOREACH(c, &bs->children, next) {
         bdrv_child_set_perm_commit(c);
-        bdrv_set_perm(c->bs);
+    }
+}
+
+static void bdrv_set_perm(BlockDriverState *bs)
+{
+    g_autoptr(GSList) list = bdrv_topological_dfs(NULL, NULL, bs);
+
+    for ( ; list; list = list->next) {
+        bdrv_node_set_perm((BlockDriverState *)list->data);
     }
 }
 
@@ -2411,7 +2487,7 @@ static int bdrv_refresh_perms(BlockDriverState *bs, Error **errp)
     int ret;
     uint64_t perm, shared_perm;
 
-    if (bdrv_parent_perms_conflict(bs, errp)) {
+    if (bdrv_parent_perms_conflict(bs, NULL, errp)) {
         return -EPERM;
     }
     bdrv_get_cumulative_perm(bs, &perm, &shared_perm);
diff --git a/tests/unit/test-bdrv-graph-mod.c b/tests/unit/test-bdrv-graph-mod.c
index a6064b1863..e64e81a07c 100644
--- a/tests/unit/test-bdrv-graph-mod.c
+++ b/tests/unit/test-bdrv-graph-mod.c
@@ -406,12 +406,12 @@ int main(int argc, char *argv[])
     g_test_add_func("/bdrv-graph-mod/update-perm-tree", test_update_perm_tree);
     g_test_add_func("/bdrv-graph-mod/should-update-child",
                     test_should_update_child);
+    g_test_add_func("/bdrv-graph-mod/parallel-perm-update",
+                    test_parallel_perm_update);
 
     if (debug) {
         g_test_add_func("/bdrv-graph-mod/parallel-exclusive-write",
                         test_parallel_exclusive_write);
-        g_test_add_func("/bdrv-graph-mod/parallel-perm-update",
-                        test_parallel_perm_update);
         g_test_add_func("/bdrv-graph-mod/append-greedy-filter",
                         test_append_greedy_filter);
     }
diff --git a/tests/qemu-iotests/283.out b/tests/qemu-iotests/283.out
index 37c35058ae..73eb75102f 100644
--- a/tests/qemu-iotests/283.out
+++ b/tests/qemu-iotests/283.out
@@ -5,7 +5,7 @@
 {"execute": "blockdev-add", "arguments": {"driver": "blkdebug", "image": "base", "node-name": "other", "take-child-perms": ["write"]}}
 {"return": {}}
 {"execute": "blockdev-backup", "arguments": {"device": "source", "sync": "full", "target": "target"}}
-{"error": {"class": "GenericError", "desc": "Cannot set permissions for backup-top filter: Conflicts with use by other as 'image', which uses 'write' on base"}}
+{"error": {"class": "GenericError", "desc": "Cannot set permissions for backup-top filter: Conflicts with use by source as 'image', which does not allow 'write' on base"}}
 
 === backup-top should be gone after job-finalize ===
 
-- 
2.30.2