Merge tag 'for-6.13-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:
 "A few more fixes. Apart from the one liners and updated bio splitting
  error handling there's a fix for subvolume mount with different flags.
  This was known and fixed for some time but I've delayed it to give it
  more testing.

   - fix unbalanced locking when swapfile activation fails when the
     subvolume gets deleted in the meantime

   - add btrfs error handling after bio_split() calls that got error
     handling recently

   - during unmount, flush delalloc workers at the right time before the
     cleaner thread is shut down

   - fix regression in buffered write folio conversion, explicitly wait
     for writeback as FGP_STABLE flag is currently a no-op on btrfs

   - handle race in subvolume mount with different flags, the conversion
     to the new mount API did not handle the case where multiple
     subvolumes get mounted in parallel, which is a distro use case"

* tag 'for-6.13-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: flush delalloc workers queue before stopping cleaner kthread during unmount
  btrfs: handle bio_split() errors
  btrfs: properly wait for writeback before buffered write
  btrfs: fix missing snapshot drew unlock when root is dead during swap activation
  btrfs: fix mount failure due to remount races

5 files changed, 53 insertions, 41 deletions

diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
index 1f216d07eff6..af3db0a7ae4d 100644
--- a/fs/btrfs/bio.c
+++ b/fs/btrfs/bio.c
@@ -81,6 +81,9 @@ static struct btrfs_bio *btrfs_split_bio(struct btrfs_fs_info *fs_info,
 
 	bio = bio_split(&orig_bbio->bio, map_length >> SECTOR_SHIFT, GFP_NOFS,
 			&btrfs_clone_bioset);
+	if (IS_ERR(bio))
+		return ERR_CAST(bio);
+
 	bbio = btrfs_bio(bio);
 	btrfs_bio_init(bbio, fs_info, NULL, orig_bbio);
 	bbio->inode = orig_bbio->inode;
@@ -678,7 +681,8 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
 				&bioc, &smap, &mirror_num);
 	if (error) {
 		ret = errno_to_blk_status(error);
-		goto fail;
+		btrfs_bio_counter_dec(fs_info);
+		goto end_bbio;
 	}
 
 	map_length = min(map_length, length);
@@ -686,7 +690,15 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
 		map_length = btrfs_append_map_length(bbio, map_length);
 
 	if (map_length < length) {
-		bbio = btrfs_split_bio(fs_info, bbio, map_length);
+		struct btrfs_bio *split;
+
+		split = btrfs_split_bio(fs_info, bbio, map_length);
+		if (IS_ERR(split)) {
+			ret = errno_to_blk_status(PTR_ERR(split));
+			btrfs_bio_counter_dec(fs_info);
+			goto end_bbio;
+		}
+		bbio = split;
 		bio = &bbio->bio;
 	}
 
@@ -760,6 +772,7 @@ fail:
 
 		btrfs_bio_end_io(remaining, ret);
 	}
+end_bbio:
 	btrfs_bio_end_io(bbio, ret);
 	/* Do not submit another chunk */
 	return true;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 814320948645..eff0dd1ae62f 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -4262,6 +4262,15 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 	 * already the cleaner, but below we run all pending delayed iputs.
 	 */
 	btrfs_flush_workqueue(fs_info->fixup_workers);
+	/*
+	 * Similar case here, we have to wait for delalloc workers before we
+	 * proceed below and stop the cleaner kthread, otherwise we trigger a
+	 * use-after-tree on the cleaner kthread task_struct when a delalloc
+	 * worker running submit_compressed_extents() adds a delayed iput, which
+	 * does a wake up on the cleaner kthread, which was already freed below
+	 * when we call kthread_stop().
+	 */
+	btrfs_flush_workqueue(fs_info->delalloc_workers);
 
 	/*
 	 * After we parked the cleaner kthread, ordered extents may have
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 588c353d2969..14e27473c5bc 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -911,6 +911,7 @@ again:
 			ret = PTR_ERR(folio);
 		return ret;
 	}
+	folio_wait_writeback(folio);
 	/* Only support page sized folio yet. */
 	ASSERT(folio_order(folio) == 0);
 	ret = set_folio_extent_mapped(folio);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index fa648ab6fe80..488edca8333a 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -9876,6 +9876,7 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 	if (btrfs_root_dead(root)) {
 		spin_unlock(&root->root_item_lock);
 
+		btrfs_drew_write_unlock(&root->snapshot_lock);
 		btrfs_exclop_finish(fs_info);
 		btrfs_warn(fs_info,
 		"cannot activate swapfile because subvolume %llu is being deleted",
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 97a85d180b61..7dfe5005129a 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1885,18 +1885,21 @@ static int btrfs_get_tree_super(struct fs_context *fc)
 
 	if (sb->s_root) {
 		btrfs_close_devices(fs_devices);
-		if ((fc->sb_flags ^ sb->s_flags) & SB_RDONLY)
-			ret = -EBUSY;
+		/*
+		 * At this stage we may have RO flag mismatch between
+		 * fc->sb_flags and sb->s_flags.  Caller should detect such
+		 * mismatch and reconfigure with sb->s_umount rwsem held if
+		 * needed.
+		 */
 	} else {
 		snprintf(sb->s_id, sizeof(sb->s_id), "%pg", bdev);
 		shrinker_debugfs_rename(sb->s_shrink, "sb-btrfs:%s", sb->s_id);
 		btrfs_sb(sb)->bdev_holder = &btrfs_fs_type;
 		ret = btrfs_fill_super(sb, fs_devices);
-	}
-
-	if (ret) {
-		deactivate_locked_super(sb);
-		return ret;
+		if (ret) {
+			deactivate_locked_super(sb);
+			return ret;
+		}
 	}
 
 	btrfs_clear_oneshot_options(fs_info);
@@ -1982,39 +1985,18 @@ error:
  * btrfs or not, setting the whole super block RO.  To make per-subvolume mounting
  * work with different options work we need to keep backward compatibility.
  */
-static struct vfsmount *btrfs_reconfigure_for_mount(struct fs_context *fc)
+static int btrfs_reconfigure_for_mount(struct fs_context *fc, struct vfsmount *mnt)
 {
-	struct vfsmount *mnt;
-	int ret;
-	const bool ro2rw = !(fc->sb_flags & SB_RDONLY);
-
-	/*
-	 * We got an EBUSY because our SB_RDONLY flag didn't match the existing
-	 * super block, so invert our setting here and retry the mount so we
-	 * can get our vfsmount.
-	 */
-	if (ro2rw)
-		fc->sb_flags |= SB_RDONLY;
-	else
-		fc->sb_flags &= ~SB_RDONLY;
-
-	mnt = fc_mount(fc);
-	if (IS_ERR(mnt))
-		return mnt;
+	int ret = 0;
 
-	if (!ro2rw)
-		return mnt;
+	if (fc->sb_flags & SB_RDONLY)
+		return ret;
 
-	/* We need to convert to rw, call reconfigure. */
-	fc->sb_flags &= ~SB_RDONLY;
 	down_write(&mnt->mnt_sb->s_umount);
-	ret = btrfs_reconfigure(fc);
+	if (!(fc->sb_flags & SB_RDONLY) && (mnt->mnt_sb->s_flags & SB_RDONLY))
+		ret = btrfs_reconfigure(fc);
 	up_write(&mnt->mnt_sb->s_umount);
-	if (ret) {
-		mntput(mnt);
-		return ERR_PTR(ret);
-	}
-	return mnt;
+	return ret;
 }
 
 static int btrfs_get_tree_subvol(struct fs_context *fc)
@@ -2024,6 +2006,7 @@ static int btrfs_get_tree_subvol(struct fs_context *fc)
 	struct fs_context *dup_fc;
 	struct dentry *dentry;
 	struct vfsmount *mnt;
+	int ret = 0;
 
 	/*
 	 * Setup a dummy root and fs_info for test/set super.  This is because
@@ -2066,11 +2049,16 @@ static int btrfs_get_tree_subvol(struct fs_context *fc)
 	fc->security = NULL;
 
 	mnt = fc_mount(dup_fc);
-	if (PTR_ERR_OR_ZERO(mnt) == -EBUSY)
-		mnt = btrfs_reconfigure_for_mount(dup_fc);
-	put_fs_context(dup_fc);
-	if (IS_ERR(mnt))
+	if (IS_ERR(mnt)) {
+		put_fs_context(dup_fc);
 		return PTR_ERR(mnt);
+	}
+	ret = btrfs_reconfigure_for_mount(dup_fc, mnt);
+	put_fs_context(dup_fc);
+	if (ret) {
+		mntput(mnt);
+		return ret;
+	}
 
 	/*
 	 * This free's ->subvol_name, because if it isn't set we have to