btrfs: scrub: try to fix super block errors

[ Upstream commit f9eab5f ]

[BUG]
The following script shows that, although scrub can detect super block
errors, it never tries to fix it:

	mkfs.btrfs -f -d raid1 -m raid1 $dev1 $dev2
	xfs_io -c "pwrite 67108864 4k" $dev2

	mount $dev1 $mnt
	btrfs scrub start -B $dev2
	btrfs scrub start -Br $dev2
	umount $mnt

The first scrub reports the super error correctly:

  scrub done for f3289218-abd3-41ac-a630-202f766c0859
  Scrub started:    Tue Aug  2 14:44:11 2022
  Status:           finished
  Duration:         0:00:00
  Total to scrub:   1.26GiB
  Rate:             0.00B/s
  Error summary:    super=1
    Corrected:      0
    Uncorrectable:  0
    Unverified:     0

But the second read-only scrub still reports the same super error:

  Scrub started:    Tue Aug  2 14:44:11 2022
  Status:           finished
  Duration:         0:00:00
  Total to scrub:   1.26GiB
  Rate:             0.00B/s
  Error summary:    super=1
    Corrected:      0
    Uncorrectable:  0
    Unverified:     0

[CAUSE]
The comments already shows that super block can be easily fixed by
committing a transaction:

	/*
	 * If we find an error in a super block, we just report it.
	 * They will get written with the next transaction commit
	 * anyway
	 */

But the truth is, such assumption is not always true, and since scrub
should try to repair every error it found (except for read-only scrub),
we should really actively commit a transaction to fix this.

[FIX]
Just commit a transaction if we found any super block errors, after
everything else is done.

We cannot do this just after scrub_supers(), as
btrfs_commit_transaction() will try to pause and wait for the running
scrub, thus we can not call it with scrub_lock hold.

Signed-off-by: Qu Wenruo <[email protected]>
Reviewed-by: David Sterba <[email protected]>
Signed-off-by: David Sterba <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>

Author: adam900710

fs/btrfs/scrub.c

@@ -4072,6 +4072,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 	int ret;
 	struct btrfs_device *dev;
 	unsigned int nofs_flag;
+	bool need_commit = false;
 
 	if (btrfs_fs_closing(fs_info))
 		return -EAGAIN;
@@ -4177,6 +4178,12 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 	 */
 	nofs_flag = memalloc_nofs_save();
 	if (!is_dev_replace) {
+		u64 old_super_errors;
+
+		spin_lock(&sctx->stat_lock);
+		old_super_errors = sctx->stat.super_errors;
+		spin_unlock(&sctx->stat_lock);
+
 		btrfs_info(fs_info, "scrub: started on devid %llu", devid);
 		/*
 		 * by holding device list mutex, we can
@@ -4185,6 +4192,16 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 		mutex_lock(&fs_info->fs_devices->device_list_mutex);
 		ret = scrub_supers(sctx, dev);
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+
+		spin_lock(&sctx->stat_lock);
+		/*
+		 * Super block errors found, but we can not commit transaction
+		 * at current context, since btrfs_commit_transaction() needs
+		 * to pause the current running scrub (hold by ourselves).
+		 */
+		if (sctx->stat.super_errors > old_super_errors && !sctx->readonly)
+			need_commit = true;
+		spin_unlock(&sctx->stat_lock);
 	}
 
 	if (!ret)
@@ -4211,6 +4228,25 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 	scrub_workers_put(fs_info);
 	scrub_put_ctx(sctx);
 
+	/*
+	 * We found some super block errors before, now try to force a
+	 * transaction commit, as scrub has finished.
+	 */
+	if (need_commit) {
+		struct btrfs_trans_handle *trans;
+
+		trans = btrfs_start_transaction(fs_info->tree_root, 0);
+		if (IS_ERR(trans)) {
+			ret = PTR_ERR(trans);
+			btrfs_err(fs_info,
+	"scrub: failed to start transaction to fix super block errors: %d", ret);
+			return ret;
+		}
+		ret = btrfs_commit_transaction(trans);
+		if (ret < 0)
+			btrfs_err(fs_info,
+	"scrub: failed to commit transaction to fix super block errors: %d", ret);
+	}
 	return ret;
 out:
 	scrub_workers_put(fs_info);