(start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size))
btrfs_add_inode_defrag(NULL, inode);
+ /*
+ * skip compression for a small file range(<=blocksize) that
+ * isn't an inline extent, since it dosen't save disk space at all.
+ */
+ if ((end - start + 1) <= blocksize &&
+ (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size))
+ goto cleanup_and_bail_uncompressed;
+
actual_end = min_t(u64, isize, end + 1);
again:
will_compress = 0;
if (btrfs_is_free_space_inode(inode)) {
WARN_ON_ONCE(1);
- return -EINVAL;
+ ret = -EINVAL;
+ goto out_unlock;
}
num_bytes = ALIGN(end - start + 1, blocksize);
async_cow->end = cur_end;
INIT_LIST_HEAD(&async_cow->extents);
- async_cow->work.func = async_cow_start;
- async_cow->work.ordered_func = async_cow_submit;
- async_cow->work.ordered_free = async_cow_free;
- async_cow->work.flags = 0;
+ btrfs_init_work(&async_cow->work, async_cow_start,
+ async_cow_submit, async_cow_free);
nr_pages = (cur_end - start + PAGE_CACHE_SIZE) >>
PAGE_CACHE_SHIFT;
atomic_add(nr_pages, &root->fs_info->async_delalloc_pages);
- btrfs_queue_worker(&root->fs_info->delalloc_workers,
- &async_cow->work);
+ btrfs_queue_work(root->fs_info->delalloc_workers,
+ &async_cow->work);
if (atomic_read(&root->fs_info->async_delalloc_pages) > limit) {
wait_event(root->fs_info->async_submit_wait,
disk_bytenr += extent_offset;
disk_bytenr += cur_offset - found_key.offset;
num_bytes = min(end + 1, extent_end) - cur_offset;
+ /*
+ * if there are pending snapshots for this root,
+ * we fall into common COW way.
+ */
+ if (!nolock) {
+ err = btrfs_start_nocow_write(root);
+ if (!err)
+ goto out_check;
+ }
/*
* force cow if csum exists in the range.
* this ensure that csum for a given extent are
out_check:
if (extent_end <= start) {
path->slots[0]++;
+ if (!nolock && nocow)
+ btrfs_end_nocow_write(root);
goto next_slot;
}
if (!nocow) {
ret = cow_file_range(inode, locked_page,
cow_start, found_key.offset - 1,
page_started, nr_written, 1);
- if (ret)
+ if (ret) {
+ if (!nolock && nocow)
+ btrfs_end_nocow_write(root);
goto error;
+ }
cow_start = (u64)-1;
}
BTRFS_DATA_RELOC_TREE_OBJECTID) {
ret = btrfs_reloc_clone_csums(inode, cur_offset,
num_bytes);
- if (ret)
+ if (ret) {
+ if (!nolock && nocow)
+ btrfs_end_nocow_write(root);
goto error;
+ }
}
extent_clear_unlock_delalloc(inode, cur_offset,
locked_page, EXTENT_LOCKED |
EXTENT_DELALLOC, PAGE_UNLOCK |
PAGE_SET_PRIVATE2);
+ if (!nolock && nocow)
+ btrfs_end_nocow_write(root);
cur_offset = extent_end;
if (cur_offset > end)
break;
SetPageChecked(page);
page_cache_get(page);
- fixup->work.func = btrfs_writepage_fixup_worker;
+ btrfs_init_work(&fixup->work, btrfs_writepage_fixup_worker, NULL, NULL);
fixup->page = page;
- btrfs_queue_worker(&root->fs_info->fixup_workers, &fixup->work);
+ btrfs_queue_work(root->fs_info->fixup_workers, &fixup->work);
return -EBUSY;
}
return PTR_ERR(root);
}
+ if (btrfs_root_readonly(root)) {
+ srcu_read_unlock(&fs_info->subvol_srcu, index);
+ return 0;
+ }
+
/* step 2: get inode */
key.objectid = backref->inum;
key.type = BTRFS_INODE_ITEM_KEY;
struct inode *inode = page->mapping->host;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_ordered_extent *ordered_extent = NULL;
- struct btrfs_workers *workers;
+ struct btrfs_workqueue *workers;
trace_btrfs_writepage_end_io_hook(page, start, end, uptodate);
end - start + 1, uptodate))
return 0;
- ordered_extent->work.func = finish_ordered_fn;
- ordered_extent->work.flags = 0;
+ btrfs_init_work(&ordered_extent->work, finish_ordered_fn, NULL, NULL);
if (btrfs_is_free_space_inode(inode))
- workers = &root->fs_info->endio_freespace_worker;
+ workers = root->fs_info->endio_freespace_worker;
else
- workers = &root->fs_info->endio_write_workers;
- btrfs_queue_worker(workers, &ordered_extent->work);
+ workers = root->fs_info->endio_write_workers;
+ btrfs_queue_work(workers, &ordered_extent->work);
return 0;
}
root->orphan_block_rsv = NULL;
spin_unlock(&root->orphan_lock);
- if (root->orphan_item_inserted &&
+ if (test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state) &&
btrfs_root_refs(&root->root_item) > 0) {
ret = btrfs_del_orphan_item(trans, root->fs_info->tree_root,
root->root_key.objectid);
if (ret)
btrfs_abort_transaction(trans, root, ret);
else
- root->orphan_item_inserted = 0;
+ clear_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED,
+ &root->state);
}
if (block_rsv) {
btrfs_block_rsv_release(root, root->orphan_block_rsv,
(u64)-1);
- if (root->orphan_block_rsv || root->orphan_item_inserted) {
+ if (root->orphan_block_rsv ||
+ test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state)) {
trans = btrfs_join_transaction(root);
if (!IS_ERR(trans))
btrfs_end_transaction(trans, root);
ret = btrfs_load_inode_props(inode, path);
if (ret)
btrfs_err(root->fs_info,
- "error loading props for ino %llu (root %llu): %d\n",
+ "error loading props for ino %llu (root %llu): %d",
btrfs_ino(inode),
root->root_key.objectid, ret);
}
* not block aligned since we will be keeping the last block of the
* extent just the way it is.
*/
- if (root->ref_cows || root == root->fs_info->tree_root)
+ if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
+ root == root->fs_info->tree_root)
btrfs_drop_extent_cache(inode, ALIGN(new_size,
root->sectorsize), (u64)-1, 0);
extent_num_bytes);
num_dec = (orig_num_bytes -
extent_num_bytes);
- if (root->ref_cows && extent_start != 0)
+ if (test_bit(BTRFS_ROOT_REF_COWS,
+ &root->state) &&
+ extent_start != 0)
inode_sub_bytes(inode, num_dec);
btrfs_mark_buffer_dirty(leaf);
} else {
num_dec = btrfs_file_extent_num_bytes(leaf, fi);
if (extent_start != 0) {
found_extent = 1;
- if (root->ref_cows)
+ if (test_bit(BTRFS_ROOT_REF_COWS,
+ &root->state))
inode_sub_bytes(inode, num_dec);
}
}
btrfs_file_extent_other_encoding(leaf, fi) == 0) {
u32 size = new_size - found_key.offset;
- if (root->ref_cows) {
+ if (test_bit(BTRFS_ROOT_REF_COWS, &root->state))
inode_sub_bytes(inode, item_end + 1 -
new_size);
- }
/*
* update the ram bytes to properly reflect
size =
btrfs_file_extent_calc_inline_size(size);
btrfs_truncate_item(root, path, size, 1);
- } else if (root->ref_cows) {
+ } else if (test_bit(BTRFS_ROOT_REF_COWS,
+ &root->state)) {
inode_sub_bytes(inode, item_end + 1 -
found_key.offset);
}
} else {
break;
}
- if (found_extent && (root->ref_cows ||
- root == root->fs_info->tree_root)) {
+ if (found_extent &&
+ (test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
+ root == root->fs_info->tree_root)) {
btrfs_set_path_blocking(path);
ret = btrfs_free_extent(trans, root, extent_start,
extent_num_bytes, 0,
struct rb_node *node;
ASSERT(inode->i_state & I_FREEING);
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
write_lock(&map_tree->lock);
while (!RB_EMPTY_ROOT(&map_tree->map)) {
struct inode *inode;
u64 objectid = 0;
- WARN_ON(btrfs_root_refs(&root->root_item) != 0);
+ if (!test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state))
+ WARN_ON(btrfs_root_refs(&root->root_item) != 0);
spin_lock(&root->inode_lock);
again:
static void btrfs_dentry_release(struct dentry *dentry)
{
- if (dentry->d_fsdata)
- kfree(dentry->d_fsdata);
+ kfree(dentry->d_fsdata);
}
static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
struct btrfs_inode_ref *ref;
struct btrfs_key key[2];
u32 sizes[2];
+ int nitems = name ? 2 : 1;
unsigned long ptr;
int ret;
*/
inode->i_ino = objectid;
- if (dir) {
+ if (dir && name) {
trace_btrfs_inode_request(dir);
ret = btrfs_set_inode_index(dir, index);
iput(inode);
return ERR_PTR(ret);
}
+ } else if (dir) {
+ *index = 0;
}
/*
* index_cnt is ignored for everything but a dir,
btrfs_set_key_type(&key[0], BTRFS_INODE_ITEM_KEY);
key[0].offset = 0;
- /*
- * Start new inodes with an inode_ref. This is slightly more
- * efficient for small numbers of hard links since they will
- * be packed into one item. Extended refs will kick in if we
- * add more hard links than can fit in the ref item.
- */
- key[1].objectid = objectid;
- btrfs_set_key_type(&key[1], BTRFS_INODE_REF_KEY);
- key[1].offset = ref_objectid;
-
sizes[0] = sizeof(struct btrfs_inode_item);
- sizes[1] = name_len + sizeof(*ref);
+
+ if (name) {
+ /*
+ * Start new inodes with an inode_ref. This is slightly more
+ * efficient for small numbers of hard links since they will
+ * be packed into one item. Extended refs will kick in if we
+ * add more hard links than can fit in the ref item.
+ */
+ key[1].objectid = objectid;
+ btrfs_set_key_type(&key[1], BTRFS_INODE_REF_KEY);
+ key[1].offset = ref_objectid;
+
+ sizes[1] = name_len + sizeof(*ref);
+ }
path->leave_spinning = 1;
- ret = btrfs_insert_empty_items(trans, root, path, key, sizes, 2);
+ ret = btrfs_insert_empty_items(trans, root, path, key, sizes, nitems);
if (ret != 0)
goto fail;
sizeof(*inode_item));
fill_inode_item(trans, path->nodes[0], inode_item, inode);
- ref = btrfs_item_ptr(path->nodes[0], path->slots[0] + 1,
- struct btrfs_inode_ref);
- btrfs_set_inode_ref_name_len(path->nodes[0], ref, name_len);
- btrfs_set_inode_ref_index(path->nodes[0], ref, *index);
- ptr = (unsigned long)(ref + 1);
- write_extent_buffer(path->nodes[0], name, ptr, name_len);
+ if (name) {
+ ref = btrfs_item_ptr(path->nodes[0], path->slots[0] + 1,
+ struct btrfs_inode_ref);
+ btrfs_set_inode_ref_name_len(path->nodes[0], ref, name_len);
+ btrfs_set_inode_ref_index(path->nodes[0], ref, *index);
+ ptr = (unsigned long)(ref + 1);
+ write_extent_buffer(path->nodes[0], name, ptr, name_len);
+ }
btrfs_mark_buffer_dirty(path->nodes[0]);
btrfs_free_path(path);
return inode;
fail:
- if (dir)
+ if (dir && name)
BTRFS_I(dir)->index_cnt--;
btrfs_free_path(path);
iput(inode);
}
out_unlock:
btrfs_end_transaction(trans, root);
+ btrfs_balance_delayed_items(root);
btrfs_btree_balance_dirty(root);
if (drop_inode) {
inode_dec_link_count(inode);
inode_dec_link_count(inode);
iput(inode);
}
+ btrfs_balance_delayed_items(root);
btrfs_btree_balance_dirty(root);
return err;
}
err = btrfs_update_inode(trans, root, inode);
if (err)
goto fail;
+ if (inode->i_nlink == 1) {
+ /*
+ * If new hard link count is 1, it's a file created
+ * with open(2) O_TMPFILE flag.
+ */
+ err = btrfs_orphan_del(trans, inode);
+ if (err)
+ goto fail;
+ }
d_instantiate(dentry, inode);
btrfs_log_new_name(trans, inode, NULL, parent);
}
btrfs_end_transaction(trans, root);
+ btrfs_balance_delayed_items(root);
fail:
if (drop_inode) {
inode_dec_link_count(inode);
btrfs_end_transaction(trans, root);
if (drop_on_err)
iput(inode);
+ btrfs_balance_delayed_items(root);
btrfs_btree_balance_dirty(root);
return err;
}
max_size = min_t(unsigned long, PAGE_CACHE_SIZE, max_size);
ret = btrfs_decompress(compress_type, tmp, page,
extent_offset, inline_size, max_size);
- if (ret) {
- char *kaddr = kmap_atomic(page);
- unsigned long copy_size = min_t(u64,
- PAGE_CACHE_SIZE - pg_offset,
- max_size - extent_offset);
- memset(kaddr + pg_offset, 0, copy_size);
- kunmap_atomic(kaddr);
- }
kfree(tmp);
- return 0;
+ return ret;
}
/*
ret = uncompress_inline(path, inode, page,
pg_offset,
extent_offset, item);
- BUG_ON(ret); /* -ENOMEM */
+ if (ret) {
+ err = ret;
+ goto out;
+ }
} else {
map = kmap(page);
read_extent_buffer(leaf, map + pg_offset, ptr,
int ret;
struct extent_buffer *leaf;
struct btrfs_root *root = BTRFS_I(inode)->root;
+ struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct btrfs_file_extent_item *fi;
struct btrfs_key key;
u64 disk_bytenr;
if (btrfs_extent_readonly(root, disk_bytenr))
goto out;
+
+ num_bytes = min(offset + *len, extent_end) - offset;
+ if (!nocow && found_type == BTRFS_FILE_EXTENT_PREALLOC) {
+ u64 range_end;
+
+ range_end = round_up(offset + num_bytes, root->sectorsize) - 1;
+ ret = test_range_bit(io_tree, offset, range_end,
+ EXTENT_DELALLOC, 0, NULL);
+ if (ret) {
+ ret = -EAGAIN;
+ goto out;
+ }
+ }
+
btrfs_release_path(path);
/*
*/
disk_bytenr += backref_offset;
disk_bytenr += offset - key.offset;
- num_bytes = min(offset + *len, extent_end) - offset;
if (csum_exist_in_range(root, disk_bytenr, num_bytes))
goto out;
/*
if (!ret)
goto out_test;
- ordered->work.func = finish_ordered_fn;
- ordered->work.flags = 0;
- btrfs_queue_worker(&root->fs_info->endio_write_workers,
- &ordered->work);
+ btrfs_init_work(&ordered->work, finish_ordered_fn, NULL, NULL);
+ btrfs_queue_work(root->fs_info->endio_write_workers,
+ &ordered->work);
out_test:
/*
* our bio might span multiple ordered extents. If we haven't
smp_mb__after_atomic_inc();
/*
- * The generic stuff only does filemap_write_and_wait_range, which isn't
- * enough if we've written compressed pages to this area, so we need to
- * call btrfs_wait_ordered_range to make absolutely sure that any
- * outstanding dirty pages are on disk.
+ * The generic stuff only does filemap_write_and_wait_range, which
+ * isn't enough if we've written compressed pages to this area, so
+ * we need to flush the dirty pages again to make absolutely sure
+ * that any outstanding dirty pages are on disk.
*/
count = iov_length(iov, nr_segs);
- ret = btrfs_wait_ordered_range(inode, offset, count);
- if (ret)
- return ret;
+ if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
+ &BTRFS_I(inode)->runtime_flags))
+ filemap_fdatawrite_range(inode->i_mapping, offset, count);
if (rw & WRITE) {
/*
err = btrfs_subvol_inherit_props(trans, new_root, parent_root);
if (err)
btrfs_err(new_root->fs_info,
- "error inheriting subvolume %llu properties: %d\n",
+ "error inheriting subvolume %llu properties: %d",
new_root->root_key.objectid, err);
err = btrfs_update_inode(trans, new_root, inode);
BTRFS_I(old_inode)->dir_index = 0ULL;
if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) {
/* force full log commit if subvolume involved. */
- root->fs_info->last_trans_log_full_commit = trans->transid;
+ btrfs_set_log_full_commit(root->fs_info, trans);
} else {
ret = btrfs_insert_inode_ref(trans, dest,
new_dentry->d_name.name,
work->inode = inode;
work->wait = wait;
work->delay_iput = delay_iput;
- work->work.func = btrfs_run_delalloc_work;
+ btrfs_init_work(&work->work, btrfs_run_delalloc_work, NULL, NULL);
return work;
}
* some fairly slow code that needs optimization. This walks the list
* of all the inodes with pending delalloc and forces them to disk.
*/
-static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
+static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput,
+ int nr)
{
struct btrfs_inode *binode;
struct inode *inode;
INIT_LIST_HEAD(&works);
INIT_LIST_HEAD(&splice);
+ mutex_lock(&root->delalloc_mutex);
spin_lock(&root->delalloc_lock);
list_splice_init(&root->delalloc_inodes, &splice);
while (!list_empty(&splice)) {
goto out;
}
list_add_tail(&work->list, &works);
- btrfs_queue_worker(&root->fs_info->flush_workers,
- &work->work);
-
+ btrfs_queue_work(root->fs_info->flush_workers,
+ &work->work);
+ ret++;
+ if (nr != -1 && ret >= nr)
+ goto out;
cond_resched();
spin_lock(&root->delalloc_lock);
}
spin_unlock(&root->delalloc_lock);
- list_for_each_entry_safe(work, next, &works, list) {
- list_del_init(&work->list);
- btrfs_wait_and_free_delalloc_work(work);
- }
- return 0;
out:
list_for_each_entry_safe(work, next, &works, list) {
list_del_init(&work->list);
list_splice_tail(&splice, &root->delalloc_inodes);
spin_unlock(&root->delalloc_lock);
}
+ mutex_unlock(&root->delalloc_mutex);
return ret;
}
if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state))
return -EROFS;
- ret = __start_delalloc_inodes(root, delay_iput);
+ ret = __start_delalloc_inodes(root, delay_iput, -1);
+ if (ret > 0)
+ ret = 0;
/*
* the filemap_flush will queue IO into the worker threads, but
* we have to make sure the IO is actually started and that
return ret;
}
-int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput)
+int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput,
+ int nr)
{
struct btrfs_root *root;
struct list_head splice;
INIT_LIST_HEAD(&splice);
+ mutex_lock(&fs_info->delalloc_root_mutex);
spin_lock(&fs_info->delalloc_root_lock);
list_splice_init(&fs_info->delalloc_roots, &splice);
- while (!list_empty(&splice)) {
+ while (!list_empty(&splice) && nr) {
root = list_first_entry(&splice, struct btrfs_root,
delalloc_root);
root = btrfs_grab_fs_root(root);
&fs_info->delalloc_roots);
spin_unlock(&fs_info->delalloc_root_lock);
- ret = __start_delalloc_inodes(root, delay_iput);
+ ret = __start_delalloc_inodes(root, delay_iput, nr);
btrfs_put_fs_root(root);
- if (ret)
+ if (ret < 0)
goto out;
+ if (nr != -1) {
+ nr -= ret;
+ WARN_ON(nr < 0);
+ }
spin_lock(&fs_info->delalloc_root_lock);
}
spin_unlock(&fs_info->delalloc_root_lock);
+ ret = 0;
atomic_inc(&fs_info->async_submit_draining);
while (atomic_read(&fs_info->nr_async_submits) ||
atomic_read(&fs_info->async_delalloc_pages)) {
atomic_read(&fs_info->async_delalloc_pages) == 0));
}
atomic_dec(&fs_info->async_submit_draining);
- return 0;
out:
if (!list_empty_careful(&splice)) {
spin_lock(&fs_info->delalloc_root_lock);
list_splice_tail(&splice, &fs_info->delalloc_roots);
spin_unlock(&fs_info->delalloc_root_lock);
}
+ mutex_unlock(&fs_info->delalloc_root_mutex);
return ret;
}
return generic_permission(inode, mask);
}
+static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+ struct btrfs_trans_handle *trans;
+ struct btrfs_root *root = BTRFS_I(dir)->root;
+ struct inode *inode = NULL;
+ u64 objectid;
+ u64 index;
+ int ret = 0;
+
+ /*
+ * 5 units required for adding orphan entry
+ */
+ trans = btrfs_start_transaction(root, 5);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+
+ ret = btrfs_find_free_ino(root, &objectid);
+ if (ret)
+ goto out;
+
+ inode = btrfs_new_inode(trans, root, dir, NULL, 0,
+ btrfs_ino(dir), objectid, mode, &index);
+ if (IS_ERR(inode)) {
+ ret = PTR_ERR(inode);
+ inode = NULL;
+ goto out;
+ }
+
+ ret = btrfs_init_inode_security(trans, inode, dir, NULL);
+ if (ret)
+ goto out;
+
+ ret = btrfs_update_inode(trans, root, inode);
+ if (ret)
+ goto out;
+
+ inode->i_fop = &btrfs_file_operations;
+ inode->i_op = &btrfs_file_inode_operations;
+
+ inode->i_mapping->a_ops = &btrfs_aops;
+ inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
+ BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
+
+ ret = btrfs_orphan_add(trans, inode);
+ if (ret)
+ goto out;
+
+ d_tmpfile(dentry, inode);
+ mark_inode_dirty(inode);
+
+out:
+ btrfs_end_transaction(trans, root);
+ if (ret)
+ iput(inode);
+ btrfs_balance_delayed_items(root);
+ btrfs_btree_balance_dirty(root);
+
+ return ret;
+}
+
static const struct inode_operations btrfs_dir_inode_operations = {
.getattr = btrfs_getattr,
.lookup = btrfs_lookup,
.get_acl = btrfs_get_acl,
.set_acl = btrfs_set_acl,
.update_time = btrfs_update_time,
+ .tmpfile = btrfs_tmpfile,
};
static const struct inode_operations btrfs_dir_ro_inode_operations = {
.lookup = btrfs_lookup,