From 42a1aaeec47bc34ae4a923e3e8b2e55b59c01711 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Jul 26 2019 15:46:42 +0000
Subject: btrfs-progs: deal with drop_progress properly in fsck


While testing snapshot deletion with dm-log-writes I saw that I was
failing the fsck sometimes when the fs was actually in the correct
state.  This is because we only skip blocks on the same level of
root_item->drop_level.  If the drop_level < the root level then we could
very well walk into nodes that we wouldn't actually walk into on fs
mount, because the drop_progress is further ahead in the slot of the
root.  Instead only process the slots of the nodes that are above the
drop_progress key.  With this patch in place we no longer improperly
fail to check fs'es that have a drop_progress set with a drop_level <
root level.

Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>

---

diff --git a/check/main.c b/check/main.c
index bb57933..8b340e5 100644
--- a/check/main.c
+++ b/check/main.c
@@ -6319,15 +6319,28 @@ static int run_next_block(struct btrfs_root *root,
 		int level;
 
 		level = btrfs_header_level(buf);
-		for (i = 0; i < nritems; i++) {
+		i = 0;
+
+		/*
+		 * If we have a drop key we need to not walk down any slots we
+		 * would have ignored when mounting the fs.  These blocks are
+		 * technically unreferenced and don't need to be worried about.
+		 */
+		if (ri != NULL && ri->drop_level && level > ri->drop_level) {
+			ret = btrfs_bin_search(buf, &ri->drop_key, level, &i);
+			if (ret && i > 0)
+				i--;
+		}
+
+		for (; i < nritems; i++) {
 			struct extent_record tmpl;
 
 			ptr = btrfs_node_blockptr(buf, i);
 			size = root->fs_info->nodesize;
 			btrfs_node_key_to_cpu(buf, &key, i);
 			if (ri != NULL) {
-				if ((level == ri->drop_level)
-				    && is_dropped_key(&key, &ri->drop_key)) {
+				if ((level == ri->drop_level) &&
+				    is_dropped_key(&key, &ri->drop_key)) {
 					continue;
 				}
 			}
diff --git a/ctree.c b/ctree.c
index 76bc9c5..c97fbb4 100644
--- a/ctree.c
+++ b/ctree.c
@@ -633,8 +633,8 @@ static int generic_bin_search(struct extent_buffer *eb, unsigned long p,
  * simple bin_search frontend that does the right thing for
  * leaves vs nodes
  */
-static int bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
-		      int level, int *slot)
+int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
+		     int level, int *slot)
 {
 	if (level == 0)
 		return generic_bin_search(eb,
@@ -1167,7 +1167,7 @@ again:
 		ret = check_block(fs_info, p, level);
 		if (ret)
 			return -1;
-		ret = bin_search(b, key, level, &slot);
+		ret = btrfs_bin_search(b, key, level, &slot);
 		if (level != 0) {
 			if (ret && slot > 0)
 				slot -= 1;
diff --git a/ctree.h b/ctree.h
index c63fad8..b73abe1 100644
--- a/ctree.h
+++ b/ctree.h
@@ -2628,6 +2628,8 @@ int btrfs_search_slot_for_read(struct btrfs_root *root,
                                const struct btrfs_key *key,
                                struct btrfs_path *p, int find_higher,
                                int return_any);
+int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
+		     int level, int *slot);
 int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *found_path,
 		u64 iobjectid, u64 ioff, u8 key_type,
 		struct btrfs_key *found_key);