Merge tag 'for-5.19-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "Features:

   - subpage:
      - support for PAGE_SIZE > 4K (previously only 64K)
      - make it work with raid56

   - repair super block num_devices automatically if it does not match
     the number of device items

   - defrag can convert inline extents to regular extents, up to now
     inline files were skipped but the setting of mount option
     max_inline could affect the decision logic

   - zoned:
      - minimal accepted zone size is explicitly set to 4MiB
      - make zone reclaim less aggressive and don't reclaim if there are
        enough free zones
      - add per-profile sysfs tunable of the reclaim threshold

   - allow automatic block group reclaim for non-zoned filesystems, with
     sysfs tunables

   - tree-checker: new check, compare extent buffer owner against owner
     rootid

  Performance:

   - avoid blocking on space reservation when doing nowait direct io
     writes (+7% throughput for reads and writes)

   - NOCOW write throughput improvement due to refined locking (+3%)

   - send: reduce pressure to page cache by dropping extent pages right
     after they're processed

  Core:

   - convert all radix trees to xarray

   - add iterators for b-tree node items

   - support printk message index

   - user bulk page allocation for extent buffers

   - switch to bio_alloc API, use on-stack bios where convenient, other
     bio cleanups

   - use rw lock for block groups to favor concurrent reads

   - simplify workques, don't allocate high priority threads for all
     normal queues as we need only one

   - refactor scrub, process chunks based on their constraints and
     similarity

   - allocate direct io structures on stack and pass around only
     pointers, avoids allocation and reduces potential error handling

  Fixes:

   - fix count of reserved transaction items for various inode
     operations

   - fix deadlock between concurrent dio writes when low on free data
     space

   - fix a few cases when zones need to be finished

  VFS, iomap:

   - add helper to check if sb write has started (usable for assertions)

   - new helper iomap_dio_alloc_bio, export iomap_dio_bio_end_io"

* tag 'for-5.19-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (173 commits)
  btrfs: zoned: introduce a minimal zone size 4M and reject mount
  btrfs: allow defrag to convert inline extents to regular extents
  btrfs: add "0x" prefix for unsupported optional features
  btrfs: do not account twice for inode ref when reserving metadata units
  btrfs: zoned: fix comparison of alloc_offset vs meta_write_pointer
  btrfs: send: avoid trashing the page cache
  btrfs: send: keep the current inode open while processing it
  btrfs: allocate the btrfs_dio_private as part of the iomap dio bio
  btrfs: move struct btrfs_dio_private to inode.c
  btrfs: remove the disk_bytenr in struct btrfs_dio_private
  btrfs: allocate dio_data on stack
  iomap: add per-iomap_iter private data
  iomap: allow the file system to provide a bio_set for direct I/O
  btrfs: add a btrfs_dio_rw wrapper
  btrfs: zoned: zone finish unused block group
  btrfs: zoned: properly finish block group on metadata write
  btrfs: zoned: finish block group when there are no more allocatable bytes left
  btrfs: zoned: consolidate zone finish functions
  btrfs: zoned: introduce btrfs_zoned_bg_is_full
  btrfs: improve error reporting in lookup_inline_extent_backref
  ...

1 files changed, 136 insertions, 132 deletions

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index b2c692b2fd8d..43b6f23bbd89 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -540,9 +540,35 @@ int __pure btrfs_is_empty_uuid(u8 *uuid)
 	return 1;
 }
 
+/*
+ * Calculate the number of transaction items to reserve for creating a subvolume
+ * or snapshot, not including the inode, directory entries, or parent directory.
+ */
+static unsigned int create_subvol_num_items(struct btrfs_qgroup_inherit *inherit)
+{
+	/*
+	 * 1 to add root block
+	 * 1 to add root item
+	 * 1 to add root ref
+	 * 1 to add root backref
+	 * 1 to add UUID item
+	 * 1 to add qgroup info
+	 * 1 to add qgroup limit
+	 *
+	 * Ideally the last two would only be accounted if qgroups are enabled,
+	 * but that can change between now and the time we would insert them.
+	 */
+	unsigned int num_items = 7;
+
+	if (inherit) {
+		/* 2 to add qgroup relations for each inherited qgroup */
+		num_items += 2 * inherit->num_qgroups;
+	}
+	return num_items;
+}
+
 static noinline int create_subvol(struct user_namespace *mnt_userns,
 				  struct inode *dir, struct dentry *dentry,
-				  const char *name, int namelen,
 				  struct btrfs_qgroup_inherit *inherit)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
@@ -555,11 +581,15 @@ static noinline int create_subvol(struct user_namespace *mnt_userns,
 	struct btrfs_root *new_root;
 	struct btrfs_block_rsv block_rsv;
 	struct timespec64 cur_time = current_time(dir);
-	struct inode *inode;
+	struct btrfs_new_inode_args new_inode_args = {
+		.dir = dir,
+		.dentry = dentry,
+		.subvol = true,
+	};
+	unsigned int trans_num_items;
 	int ret;
-	dev_t anon_dev = 0;
+	dev_t anon_dev;
 	u64 objectid;
-	u64 index = 0;
 
 	root_item = kzalloc(sizeof(*root_item), GFP_KERNEL);
 	if (!root_item)
@@ -567,11 +597,7 @@ static noinline int create_subvol(struct user_namespace *mnt_userns,
 
 	ret = btrfs_get_free_objectid(fs_info->tree_root, &objectid);
 	if (ret)
-		goto fail_free;
-
-	ret = get_anon_bdev(&anon_dev);
-	if (ret < 0)
-		goto fail_free;
+		goto out_root_item;
 
 	/*
 	 * Don't create subvolume whose level is not zero. Or qgroup will be
@@ -579,36 +605,47 @@ static noinline int create_subvol(struct user_namespace *mnt_userns,
 	 */
 	if (btrfs_qgroup_level(objectid)) {
 		ret = -ENOSPC;
-		goto fail_free;
+		goto out_root_item;
 	}
 
+	ret = get_anon_bdev(&anon_dev);
+	if (ret < 0)
+		goto out_root_item;
+
+	new_inode_args.inode = btrfs_new_subvol_inode(mnt_userns, dir);
+	if (!new_inode_args.inode) {
+		ret = -ENOMEM;
+		goto out_anon_dev;
+	}
+	ret = btrfs_new_inode_prepare(&new_inode_args, &trans_num_items);
+	if (ret)
+		goto out_inode;
+	trans_num_items += create_subvol_num_items(inherit);
+
 	btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP);
-	/*
-	 * The same as the snapshot creation, please see the comment
-	 * of create_snapshot().
-	 */
-	ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 8, false);
+	ret = btrfs_subvolume_reserve_metadata(root, &block_rsv,
+					       trans_num_items, false);
 	if (ret)
-		goto fail_free;
+		goto out_new_inode_args;
 
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
 		btrfs_subvolume_release_metadata(root, &block_rsv);
-		goto fail_free;
+		goto out_new_inode_args;
 	}
 	trans->block_rsv = &block_rsv;
 	trans->bytes_reserved = block_rsv.size;
 
 	ret = btrfs_qgroup_inherit(trans, 0, objectid, inherit);
 	if (ret)
-		goto fail;
+		goto out;
 
 	leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0,
 				      BTRFS_NESTING_NORMAL);
 	if (IS_ERR(leaf)) {
 		ret = PTR_ERR(leaf);
-		goto fail;
+		goto out;
 	}
 
 	btrfs_mark_buffer_dirty(leaf);
@@ -663,75 +700,46 @@ static noinline int create_subvol(struct user_namespace *mnt_userns,
 		btrfs_tree_unlock(leaf);
 		btrfs_free_tree_block(trans, objectid, leaf, 0, 1);
 		free_extent_buffer(leaf);
-		goto fail;
+		goto out;
 	}
 
 	free_extent_buffer(leaf);
 	leaf = NULL;
 
-	key.offset = (u64)-1;
 	new_root = btrfs_get_new_fs_root(fs_info, objectid, anon_dev);
 	if (IS_ERR(new_root)) {
-		free_anon_bdev(anon_dev);
 		ret = PTR_ERR(new_root);
 		btrfs_abort_transaction(trans, ret);
-		goto fail;
+		goto out;
 	}
-	/* Freeing will be done in btrfs_put_root() of new_root */
+	/* anon_dev is owned by new_root now. */
 	anon_dev = 0;
+	BTRFS_I(new_inode_args.inode)->root = new_root;
+	/* ... and new_root is owned by new_inode_args.inode now. */
 
 	ret = btrfs_record_root_in_trans(trans, new_root);
 	if (ret) {
-		btrfs_put_root(new_root);
-		btrfs_abort_transaction(trans, ret);
-		goto fail;
-	}
-
-	ret = btrfs_create_subvol_root(trans, new_root, root, mnt_userns);
-	btrfs_put_root(new_root);
-	if (ret) {
-		/* We potentially lose an unused inode item here */
 		btrfs_abort_transaction(trans, ret);
-		goto fail;
-	}
-
-	/*
-	 * insert the directory item
-	 */
-	ret = btrfs_set_inode_index(BTRFS_I(dir), &index);
-	if (ret) {
-		btrfs_abort_transaction(trans, ret);
-		goto fail;
-	}
-
-	ret = btrfs_insert_dir_item(trans, name, namelen, BTRFS_I(dir), &key,
-				    BTRFS_FT_DIR, index);
-	if (ret) {
-		btrfs_abort_transaction(trans, ret);
-		goto fail;
+		goto out;
 	}
 
-	btrfs_i_size_write(BTRFS_I(dir), dir->i_size + namelen * 2);
-	ret = btrfs_update_inode(trans, root, BTRFS_I(dir));
+	ret = btrfs_uuid_tree_add(trans, root_item->uuid,
+				  BTRFS_UUID_KEY_SUBVOL, objectid);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
-		goto fail;
+		goto out;
 	}
 
-	ret = btrfs_add_root_ref(trans, objectid, root->root_key.objectid,
-				 btrfs_ino(BTRFS_I(dir)), index, name, namelen);
+	ret = btrfs_create_new_inode(trans, &new_inode_args);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
-		goto fail;
+		goto out;
 	}
 
-	ret = btrfs_uuid_tree_add(trans, root_item->uuid,
-				  BTRFS_UUID_KEY_SUBVOL, objectid);
-	if (ret)
-		btrfs_abort_transaction(trans, ret);
+	d_instantiate_new(dentry, new_inode_args.inode);
+	new_inode_args.inode = NULL;
 
-fail:
-	kfree(root_item);
+out:
 	trans->block_rsv = NULL;
 	trans->bytes_reserved = 0;
 	btrfs_subvolume_release_metadata(root, &block_rsv);
@@ -740,18 +748,14 @@ fail:
 		btrfs_end_transaction(trans);
 	else
 		ret = btrfs_commit_transaction(trans);
-
-	if (!ret) {
-		inode = btrfs_lookup_dentry(dir, dentry);
-		if (IS_ERR(inode))
-			return PTR_ERR(inode);
-		d_instantiate(dentry, inode);
-	}
-	return ret;
-
-fail_free:
+out_new_inode_args:
+	btrfs_new_inode_args_destroy(&new_inode_args);
+out_inode:
+	iput(new_inode_args.inode);
+out_anon_dev:
 	if (anon_dev)
 		free_anon_bdev(anon_dev);
+out_root_item:
 	kfree(root_item);
 	return ret;
 }
@@ -763,6 +767,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
 	struct inode *inode;
 	struct btrfs_pending_snapshot *pending_snapshot;
+	unsigned int trans_num_items;
 	struct btrfs_trans_handle *trans;
 	int ret;
 
@@ -800,16 +805,14 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 	btrfs_init_block_rsv(&pending_snapshot->block_rsv,
 			     BTRFS_BLOCK_RSV_TEMP);
 	/*
-	 * 1 - parent dir inode
-	 * 2 - dir entries
-	 * 1 - root item
-	 * 2 - root ref/backref
-	 * 1 - root of snapshot
-	 * 1 - UUID item
+	 * 1 to add dir item
+	 * 1 to add dir index
+	 * 1 to update parent inode item
 	 */
+	trans_num_items = create_subvol_num_items(inherit) + 3;
 	ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root,
-					&pending_snapshot->block_rsv, 8,
-					false);
+					       &pending_snapshot->block_rsv,
+					       trans_num_items, false);
 	if (ret)
 		goto free_pending;
 
@@ -979,7 +982,7 @@ static noinline int btrfs_mksubvol(const struct path *parent,
 	if (snap_src)
 		error = create_snapshot(snap_src, dir, dentry, readonly, inherit);
 	else
-		error = create_subvol(mnt_userns, dir, dentry, name, namelen, inherit);
+		error = create_subvol(mnt_userns, dir, dentry, inherit);
 
 	if (!error)
 		fsnotify_mkdir(dir, dentry);
@@ -1413,8 +1416,19 @@ static int defrag_collect_targets(struct btrfs_inode *inode,
 		if (!em)
 			break;
 
-		/* Skip hole/inline/preallocated extents */
-		if (em->block_start >= EXTENT_MAP_LAST_BYTE ||
+		/*
+		 * If the file extent is an inlined one, we may still want to
+		 * defrag it (fallthrough) if it will cause a regular extent.
+		 * This is for users who want to convert inline extents to
+		 * regular ones through max_inline= mount option.
+		 */
+		if (em->block_start == EXTENT_MAP_INLINE &&
+		    em->len <= inode->root->fs_info->max_inline)
+			goto next;
+
+		/* Skip hole/delalloc/preallocated extents */
+		if (em->block_start == EXTENT_MAP_HOLE ||
+		    em->block_start == EXTENT_MAP_DELALLOC ||
 		    test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
 			goto next;
 
@@ -1473,6 +1487,15 @@ static int defrag_collect_targets(struct btrfs_inode *inode,
 		if (em->len >= get_extent_max_capacity(em))
 			goto next;
 
+		/*
+		 * Normally there are no more extents after an inline one, thus
+		 * @next_mergeable will normally be false and not defragged.
+		 * So if an inline extent passed all above checks, just add it
+		 * for defrag, and be converted to regular extents.
+		 */
+		if (em->block_start == EXTENT_MAP_INLINE)
+			goto add;
+
 		next_mergeable = defrag_check_next_extent(&inode->vfs_inode, em,
 						extent_thresh, newer_than, locked);
 		if (!next_mergeable) {
@@ -2594,7 +2617,7 @@ err:
 static noinline int btrfs_ioctl_tree_search(struct inode *inode,
 					    void __user *argp)
 {
-	struct btrfs_ioctl_search_args __user *uargs;
+	struct btrfs_ioctl_search_args __user *uargs = argp;
 	struct btrfs_ioctl_search_key sk;
 	int ret;
 	size_t buf_size;
@@ -2602,8 +2625,6 @@ static noinline int btrfs_ioctl_tree_search(struct inode *inode,
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	uargs = (struct btrfs_ioctl_search_args __user *)argp;
-
 	if (copy_from_user(&sk, &uargs->key, sizeof(sk)))
 		return -EFAULT;
 
@@ -2626,7 +2647,7 @@ static noinline int btrfs_ioctl_tree_search(struct inode *inode,
 static noinline int btrfs_ioctl_tree_search_v2(struct inode *inode,
 					       void __user *argp)
 {
-	struct btrfs_ioctl_search_args_v2 __user *uarg;
+	struct btrfs_ioctl_search_args_v2 __user *uarg = argp;
 	struct btrfs_ioctl_search_args_v2 args;
 	int ret;
 	size_t buf_size;
@@ -2636,7 +2657,6 @@ static noinline int btrfs_ioctl_tree_search_v2(struct inode *inode,
 		return -EPERM;
 
 	/* copy search header and buffer size */
-	uarg = (struct btrfs_ioctl_search_args_v2 __user *)argp;
 	if (copy_from_user(&args, uarg, sizeof(args)))
 		return -EFAULT;
 
@@ -4344,10 +4364,6 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg)
 	bool need_unlock; /* for mut. excl. ops lock */
 	int ret;
 
-	if (!arg)
-		btrfs_warn(fs_info,
-	"IOC_BALANCE ioctl (v1) is deprecated and will be removed in kernel 5.18");
-
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
@@ -4355,6 +4371,13 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg)
 	if (ret)
 		return ret;
 
+	bargs = memdup_user(arg, sizeof(*bargs));
+	if (IS_ERR(bargs)) {
+		ret = PTR_ERR(bargs);
+		bargs = NULL;
+		goto out;
+	}
+
 again:
 	if (btrfs_exclop_start(fs_info, BTRFS_EXCLOP_BALANCE)) {
 		mutex_lock(&fs_info->balance_mutex);
@@ -4402,59 +4425,42 @@ again:
 	}
 
 locked:
-
-	if (arg) {
-		bargs = memdup_user(arg, sizeof(*bargs));
-		if (IS_ERR(bargs)) {
-			ret = PTR_ERR(bargs);
+	if (bargs->flags & BTRFS_BALANCE_RESUME) {
+		if (!fs_info->balance_ctl) {
+			ret = -ENOTCONN;
 			goto out_unlock;
 		}
 
-		if (bargs->flags & BTRFS_BALANCE_RESUME) {
-			if (!fs_info->balance_ctl) {
-				ret = -ENOTCONN;
-				goto out_bargs;
-			}
+		bctl = fs_info->balance_ctl;
+		spin_lock(&fs_info->balance_lock);
+		bctl->flags |= BTRFS_BALANCE_RESUME;
+		spin_unlock(&fs_info->balance_lock);
+		btrfs_exclop_balance(fs_info, BTRFS_EXCLOP_BALANCE);
 
-			bctl = fs_info->balance_ctl;
-			spin_lock(&fs_info->balance_lock);
-			bctl->flags |= BTRFS_BALANCE_RESUME;
-			spin_unlock(&fs_info->balance_lock);
-			btrfs_exclop_balance(fs_info, BTRFS_EXCLOP_BALANCE);
+		goto do_balance;
+	}
 
-			goto do_balance;
-		}
-	} else {
-		bargs = NULL;
+	if (bargs->flags & ~(BTRFS_BALANCE_ARGS_MASK | BTRFS_BALANCE_TYPE_MASK)) {
+		ret = -EINVAL;
+		goto out_unlock;
 	}
 
 	if (fs_info->balance_ctl) {
 		ret = -EINPROGRESS;
-		goto out_bargs;
+		goto out_unlock;
 	}
 
 	bctl = kzalloc(sizeof(*bctl), GFP_KERNEL);
 	if (!bctl) {
 		ret = -ENOMEM;
-		goto out_bargs;
-	}
-
-	if (arg) {
-		memcpy(&bctl->data, &bargs->data, sizeof(bctl->data));
-		memcpy(&bctl->meta, &bargs->meta, sizeof(bctl->meta));
-		memcpy(&bctl->sys, &bargs->sys, sizeof(bctl->sys));
-
-		bctl->flags = bargs->flags;
-	} else {
-		/* balance everything - no filters */
-		bctl->flags |= BTRFS_BALANCE_TYPE_MASK;
+		goto out_unlock;
 	}
 
-	if (bctl->flags & ~(BTRFS_BALANCE_ARGS_MASK | BTRFS_BALANCE_TYPE_MASK)) {
-		ret = -EINVAL;
-		goto out_bctl;
-	}
+	memcpy(&bctl->data, &bargs->data, sizeof(bctl->data));
+	memcpy(&bctl->meta, &bargs->meta, sizeof(bctl->meta));
+	memcpy(&bctl->sys, &bargs->sys, sizeof(bctl->sys));
 
+	bctl->flags = bargs->flags;
 do_balance:
 	/*
 	 * Ownership of bctl and exclusive operation goes to btrfs_balance.
@@ -4467,21 +4473,19 @@ do_balance:
 	ret = btrfs_balance(fs_info, bctl, bargs);
 	bctl = NULL;
 
-	if ((ret == 0 || ret == -ECANCELED) && arg) {
+	if (ret == 0 || ret == -ECANCELED) {
 		if (copy_to_user(arg, bargs, sizeof(*bargs)))
 			ret = -EFAULT;
 	}
 
-out_bctl:
 	kfree(bctl);
-out_bargs:
-	kfree(bargs);
 out_unlock:
 	mutex_unlock(&fs_info->balance_mutex);
 	if (need_unlock)
 		btrfs_exclop_finish(fs_info);
 out:
 	mnt_drop_write_file(file);
+	kfree(bargs);
 	return ret;
 }