Merge tag 'for-5.12-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:
 "Fixes for issues that have some user visibility and are simple enough
  for this time of development cycle:

   - a few fixes for rescue= mount option, adding more checks for
     missing trees

   - fix sleeping in atomic context on qgroup deletion

   - fix subvolume deletion on mount

   - fix build with M= syntax

   - fix checksum mismatch error message for direct io"

* tag 'for-5.12-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: fix check_data_csum() error message for direct I/O
  btrfs: fix sleep while in non-sleep context during qgroup removal
  btrfs: fix subvolume/snapshot deletion not triggered on mount
  btrfs: fix build when using M=fs/btrfs
  btrfs: do not initialize dev replace for bad dev root
  btrfs: initialize device::fs_info always
  btrfs: do not initialize dev stats if we have no dev_root
  btrfs: zoned: remove outdated WARN_ON in direct IO

fs/btrfs/Makefile

@@ -7,10 +7,12 @@ subdir-ccflags-y += -Wmissing-format-attribute
 subdir-ccflags-y += -Wmissing-prototypes
 subdir-ccflags-y += -Wold-style-definition
 subdir-ccflags-y += -Wmissing-include-dirs
-subdir-ccflags-y += $(call cc-option, -Wunused-but-set-variable)
-subdir-ccflags-y += $(call cc-option, -Wunused-const-variable)
-subdir-ccflags-y += $(call cc-option, -Wpacked-not-aligned)
-subdir-ccflags-y += $(call cc-option, -Wstringop-truncation)
+condflags := \
+	$(call cc-option, -Wunused-but-set-variable)		\
+	$(call cc-option, -Wunused-const-variable)		\
+	$(call cc-option, -Wpacked-not-aligned)			\
+	$(call cc-option, -Wstringop-truncation)
+subdir-ccflags-y += $(condflags)
 # The following turn off the warnings enabled by -Wextra
 subdir-ccflags-y += -Wno-missing-field-initializers
 subdir-ccflags-y += -Wno-sign-compare

fs/btrfs/dev-replace.c

@@ -81,6 +81,9 @@ int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info)
 	struct btrfs_dev_replace_item *ptr;
 	u64 src_devid;
 
+	if (!dev_root)
+		return 0;
+
 	path = btrfs_alloc_path();
 	if (!path) {
 		ret = -ENOMEM;

fs/btrfs/disk-io.c

@@ -2387,8 +2387,9 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info)
 	} else {
 		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
 		fs_info->dev_root = root;
-		btrfs_init_devices_late(fs_info);
 	}
+	/* Initialize fs_info for all devices in any case */
+	btrfs_init_devices_late(fs_info);
 
 	/* If IGNOREDATACSUMS is set don't bother reading the csum root. */
 	if (!btrfs_test_opt(fs_info, IGNOREDATACSUMS)) {
@@ -3009,6 +3010,21 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info)
 		}
 	}
 
+	/*
+	 * btrfs_find_orphan_roots() is responsible for finding all the dead
+	 * roots (with 0 refs), flag them with BTRFS_ROOT_DEAD_TREE and load
+	 * them into the fs_info->fs_roots_radix tree. This must be done before
+	 * calling btrfs_orphan_cleanup() on the tree root. If we don't do it
+	 * first, then btrfs_orphan_cleanup() will delete a dead root's orphan
+	 * item before the root's tree is deleted - this means that if we unmount
+	 * or crash before the deletion completes, on the next mount we will not
+	 * delete what remains of the tree because the orphan item does not
+	 * exists anymore, which is what tells us we have a pending deletion.
+	 */
+	ret = btrfs_find_orphan_roots(fs_info);
+	if (ret)
+		goto out;
+
 	ret = btrfs_cleanup_fs_roots(fs_info);
 	if (ret)
 		goto out;
@@ -3068,7 +3084,6 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info)
 		}
 	}
 
-	ret = btrfs_find_orphan_roots(fs_info);
 out:
 	return ret;
 }

fs/btrfs/inode.c

@@ -3099,11 +3099,13 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
  * @bio_offset:	offset to the beginning of the bio (in bytes)
  * @page:	page where is the data to be verified
  * @pgoff:	offset inside the page
+ * @start:	logical offset in the file
  *
  * The length of such check is always one sector size.
  */
 static int check_data_csum(struct inode *inode, struct btrfs_io_bio *io_bio,
-			   u32 bio_offset, struct page *page, u32 pgoff)
+			   u32 bio_offset, struct page *page, u32 pgoff,
+			   u64 start)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
@@ -3130,8 +3132,8 @@ static int check_data_csum(struct inode *inode, struct btrfs_io_bio *io_bio,
 	kunmap_atomic(kaddr);
 	return 0;
 zeroit:
-	btrfs_print_data_csum_error(BTRFS_I(inode), page_offset(page) + pgoff,
-				    csum, csum_expected, io_bio->mirror_num);
+	btrfs_print_data_csum_error(BTRFS_I(inode), start, csum, csum_expected,
+				    io_bio->mirror_num);
 	if (io_bio->device)
 		btrfs_dev_stat_inc_and_print(io_bio->device,
 					     BTRFS_DEV_STAT_CORRUPTION_ERRS);
@@ -3184,7 +3186,8 @@ int btrfs_verify_data_csum(struct btrfs_io_bio *io_bio, u32 bio_offset,
 	     pg_off += sectorsize, bio_offset += sectorsize) {
 		int ret;
 
-		ret = check_data_csum(inode, io_bio, bio_offset, page, pg_off);
+		ret = check_data_csum(inode, io_bio, bio_offset, page, pg_off,
+				      page_offset(page) + pg_off);
 		if (ret < 0)
 			return -EIO;
 	}
@@ -7910,7 +7913,8 @@ static blk_status_t btrfs_check_read_dio_bio(struct inode *inode,
 			ASSERT(pgoff < PAGE_SIZE);
 			if (uptodate &&
 			    (!csum || !check_data_csum(inode, io_bio,
-					bio_offset, bvec.bv_page, pgoff))) {
+						       bio_offset, bvec.bv_page,
+						       pgoff, start))) {
 				clean_io_failure(fs_info, failure_tree, io_tree,
 						 start, bvec.bv_page,
 						 btrfs_ino(BTRFS_I(inode)),
@@ -8169,10 +8173,6 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap,
 		bio->bi_end_io = btrfs_end_dio_bio;
 		btrfs_io_bio(bio)->logical = file_offset;
 
-		WARN_ON_ONCE(write && btrfs_is_zoned(fs_info) &&
-			     fs_info->max_zone_append_size &&
-			     bio_op(bio) != REQ_OP_ZONE_APPEND);
-
 		if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
 			status = extract_ordered_extent(BTRFS_I(inode), bio,
 							file_offset);

fs/btrfs/qgroup.c

@@ -226,7 +226,6 @@ static void __del_qgroup_rb(struct btrfs_fs_info *fs_info,
 {
 	struct btrfs_qgroup_list *list;
 
-	btrfs_sysfs_del_one_qgroup(fs_info, qgroup);
 	list_del(&qgroup->dirty);
 	while (!list_empty(&qgroup->groups)) {
 		list = list_first_entry(&qgroup->groups,
@@ -243,7 +242,6 @@ static void __del_qgroup_rb(struct btrfs_fs_info *fs_info,
 		list_del(&list->next_member);
 		kfree(list);
 	}
-	kfree(qgroup);
 }
 
 /* must be called with qgroup_lock held */
@@ -569,6 +567,8 @@ void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info)
 		qgroup = rb_entry(n, struct btrfs_qgroup, node);
 		rb_erase(n, &fs_info->qgroup_tree);
 		__del_qgroup_rb(fs_info, qgroup);
+		btrfs_sysfs_del_one_qgroup(fs_info, qgroup);
+		kfree(qgroup);
 	}
 	/*
 	 * We call btrfs_free_qgroup_config() when unmounting
@@ -1578,6 +1578,14 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
 	spin_lock(&fs_info->qgroup_lock);
 	del_qgroup_rb(fs_info, qgroupid);
 	spin_unlock(&fs_info->qgroup_lock);
+
+	/*
+	 * Remove the qgroup from sysfs now without holding the qgroup_lock
+	 * spinlock, since the sysfs_remove_group() function needs to take
+	 * the mutex kernfs_mutex through kernfs_remove_by_name_ns().
+	 */
+	btrfs_sysfs_del_one_qgroup(fs_info, qgroup);
+	kfree(qgroup);
 out:
 	mutex_unlock(&fs_info->qgroup_ioctl_lock);
 	return ret;

fs/btrfs/volumes.c

@@ -7448,6 +7448,9 @@ static int btrfs_device_init_dev_stats(struct btrfs_device *device,
 	int item_size;
 	int i, ret, slot;
 
+	if (!device->fs_info->dev_root)
+		return 0;
+
 	key.objectid = BTRFS_DEV_STATS_OBJECTID;
 	key.type = BTRFS_PERSISTENT_ITEM_KEY;
 	key.offset = device->devid;