From 9d81bfe48291964eaf658c08a71f04c3839592d0 Mon Sep 17 00:00:00 2001
Message-Id: <9d81bfe48291964eaf658c08a71f04c3839592d0.1672117970.git.wqu@suse.com>
From: Qu Wenruo <wqu@suse.com>
Date: Mon, 26 Dec 2022 16:44:08 +0800
Subject: [PATCH v4] btrfs: add extra debug for level mismatch

Currently I assume there is some race or uninitialized value for
check::level.

The extra output are for two locations:

- validate_extent_buffer()
  Output the error message for read error and the members of check.

- read_extent_buffer_pages()
  This will dump the stack for us to catch the offender.

Signed-off-by: Qu Wenruo <wqu@suse.com>
---
Changelog:
v2:
- Extra submission time output
  This would greately enlarge the dmesg size

- Extra warning when submitting a metadata bio
  If we have an uninitialized check structure, do a warning and stack
  dump to show the offending call trace.

v3:
- Fix a compiling error

v4:
- Add extra mb for test
---
 fs/btrfs/disk-io.c   | 19 +++++++++++++++++--
 fs/btrfs/extent_io.c | 15 ++++++++++++++-
 2 files changed, 31 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index f8b5955f003f..49b077acf359 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -530,6 +530,10 @@ static int validate_extent_buffer(struct extent_buffer *eb,
 	}
 
 	if (found_level != check->level) {
+		btrfs_err(eb->fs_info,
+"level verify failed on logical %llu mirror %u wanted %u found %u",
+			  eb->start, eb->read_mirror, check->level,
+			  found_level);
 		ret = -EIO;
 		goto out;
 	}
@@ -581,13 +585,20 @@ static int validate_extent_buffer(struct extent_buffer *eb,
 	if (found_level > 0 && btrfs_check_node(eb))
 		ret = -EIO;
 
+out:
 	if (!ret)
 		set_extent_buffer_uptodate(eb);
-	else
+	else {
 		btrfs_err(fs_info,
 		"read time tree block corruption detected on logical %llu mirror %u",
 			  eb->start, eb->read_mirror);
-out:
+		btrfs_err(eb->fs_info,
+"check owner_root=%llu transid=%llu first_key=(%llu %u %llu) has_first_key=%d level=%u",
+			  check->owner_root,
+			  check->transid, check->first_key.objectid,
+			  check->first_key.type, check->first_key.offset,
+			  check->has_first_key, check->level);
+	}
 	return ret;
 }
 
@@ -652,6 +663,7 @@ int btrfs_validate_metadata_buffer(struct btrfs_bio *bbio,
 	int reads_done;
 
 	ASSERT(page->private);
+	WARN_ON(!bbio->is_metadata);
 
 	if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE)
 		return validate_subpage_buffer(page, start, end, mirror,
@@ -833,12 +845,15 @@ void btrfs_submit_metadata_bio(struct btrfs_inode *inode, struct bio *bio, int m
 {
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct btrfs_bio *bbio = btrfs_bio(bio);
+	struct btrfs_tree_parent_check check = {0};
 	blk_status_t ret;
 
 	bio->bi_opf |= REQ_META;
 	bbio->is_metadata = 1;
 
 	if (btrfs_op(bio) != BTRFS_MAP_WRITE) {
+		WARN_ON(!memcmp(&check, &bbio->parent_check,
+			sizeof(struct btrfs_tree_parent_check)));
 		btrfs_submit_bio(fs_info, bio, mirror_num);
 		return;
 	}
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 83dd3aa59663..2920642df2a3 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4878,6 +4878,7 @@ static int read_extent_buffer_subpage(struct extent_buffer *eb, int wait,
 		 */
 		atomic_dec(&eb->io_pages);
 	}
+	smp_mb();
 	memcpy(&btrfs_bio(bio_ctrl.bio)->parent_check, check, sizeof(*check));
 	submit_one_bio(&bio_ctrl);
 	if (ret || wait != WAIT_COMPLETE) {
@@ -4996,6 +4997,7 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num,
 		}
 	}
 
+	smp_mb();
 	memcpy(&btrfs_bio(bio_ctrl.bio)->parent_check, check, sizeof(*check));
 	submit_one_bio(&bio_ctrl);
 
@@ -5005,8 +5007,19 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num,
 	for (i = 0; i < num_pages; i++) {
 		page = eb->pages[i];
 		wait_on_page_locked(page);
-		if (!PageUptodate(page))
+		if (!PageUptodate(page)) {
 			ret = -EIO;
+			btrfs_err(eb->fs_info,
+"read failed, bytenr=%llu check owner_root=%llu transid=%llu has_first_key=%d first_key=(%llu %u %llu) level=%u",
+				  eb->start,
+				  check->owner_root, check->transid,
+				  check->has_first_key,
+				  check->first_key.objectid,
+				  check->first_key.type,
+				  check->first_key.offset,
+				  check->level);
+			dump_stack();
+		}
 	}
 
 	return ret;
-- 
2.39.0