static int btrfs_setsize(struct inode *inode, loff_t newsize);
static int btrfs_truncate(struct inode *inode);
-static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end);
+static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent);
static noinline int cow_file_range(struct inode *inode,
struct page *locked_page,
u64 start, u64 end, int *page_started,
if (btrfs_is_free_space_inode(root, inode))
metadata = 2;
- ret = btrfs_bio_wq_end_io(root->fs_info, bio, metadata);
- if (ret)
- return ret;
-
if (!(rw & REQ_WRITE)) {
+ ret = btrfs_bio_wq_end_io(root->fs_info, bio, metadata);
+ if (ret)
+ return ret;
+
if (bio_flags & EXTENT_BIO_COMPRESSED) {
return btrfs_submit_compressed_read(inode, bio,
mirror_num, bio_flags);
* an ordered extent if the range of bytes in the file it covers are
* fully written.
*/
-static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
+static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
{
+ struct inode *inode = ordered_extent->inode;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_trans_handle *trans = NULL;
- struct btrfs_ordered_extent *ordered_extent = NULL;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct extent_state *cached_state = NULL;
int compress_type = 0;
int ret;
bool nolock;
- ret = btrfs_dec_test_ordered_pending(inode, &ordered_extent, start,
- end - start + 1);
- if (!ret)
- return 0;
- BUG_ON(!ordered_extent); /* Logic error */
-
nolock = btrfs_is_free_space_inode(root, inode);
+ if (test_bit(BTRFS_ORDERED_IOERR, &ordered_extent->flags)) {
+ ret = -EIO;
+ goto out;
+ }
+
if (test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags)) {
BUG_ON(!list_empty(&ordered_extent->list)); /* Logic error */
ret = btrfs_ordered_update_i_size(inode, 0, ordered_extent);
ordered_extent->file_offset,
ordered_extent->len);
}
- unlock_extent_cached(io_tree, ordered_extent->file_offset,
- ordered_extent->file_offset +
- ordered_extent->len - 1, &cached_state, GFP_NOFS);
+
if (ret < 0) {
btrfs_abort_transaction(trans, root, ret);
- goto out;
+ goto out_unlock;
}
add_pending_csums(trans, inode, ordered_extent->file_offset,
ret = btrfs_update_inode_fallback(trans, root, inode);
if (ret) { /* -ENOMEM or corruption */
btrfs_abort_transaction(trans, root, ret);
- goto out;
+ goto out_unlock;
}
}
ret = 0;
+out_unlock:
+ unlock_extent_cached(io_tree, ordered_extent->file_offset,
+ ordered_extent->file_offset +
+ ordered_extent->len - 1, &cached_state, GFP_NOFS);
out:
if (root != root->fs_info->tree_root)
btrfs_delalloc_release_metadata(inode, ordered_extent->len);
btrfs_end_transaction(trans, root);
}
+ if (ret)
+ clear_extent_uptodate(io_tree, ordered_extent->file_offset,
+ ordered_extent->file_offset +
+ ordered_extent->len - 1, NULL, GFP_NOFS);
+
+ /*
+ * This needs to be dont to make sure anybody waiting knows we are done
+ * upating everything for this ordered extent.
+ */
+ btrfs_remove_ordered_extent(inode, ordered_extent);
+
/* once for us */
btrfs_put_ordered_extent(ordered_extent);
/* once for the tree */
btrfs_put_ordered_extent(ordered_extent);
- return 0;
-out_unlock:
- unlock_extent_cached(io_tree, ordered_extent->file_offset,
- ordered_extent->file_offset +
- ordered_extent->len - 1, &cached_state, GFP_NOFS);
- goto out;
+ return ret;
+}
+
+static void finish_ordered_fn(struct btrfs_work *work)
+{
+ struct btrfs_ordered_extent *ordered_extent;
+ ordered_extent = container_of(work, struct btrfs_ordered_extent, work);
+ btrfs_finish_ordered_io(ordered_extent);
}
static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
struct extent_state *state, int uptodate)
{
+ 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;
+
trace_btrfs_writepage_end_io_hook(page, start, end, uptodate);
ClearPagePrivate2(page);
- return btrfs_finish_ordered_io(page->mapping->host, start, end);
+ if (!btrfs_dec_test_ordered_pending(inode, &ordered_extent, start,
+ end - start + 1, uptodate))
+ return 0;
+
+ ordered_extent->work.func = finish_ordered_fn;
+ ordered_extent->work.flags = 0;
+
+ if (btrfs_is_free_space_inode(root, inode))
+ workers = &root->fs_info->endio_freespace_worker;
+ else
+ workers = &root->fs_info->endio_write_workers;
+ btrfs_queue_worker(workers, &ordered_extent->work);
+
+ return 0;
}
/*
* extent_io.c will try to find good copies for us.
*/
static int btrfs_readpage_end_io_hook(struct page *page, u64 start, u64 end,
- struct extent_state *state)
+ struct extent_state *state, int mirror)
{
size_t offset = start - ((u64)page->index << PAGE_CACHE_SHIFT);
struct inode *inode = page->mapping->host;
insert = 1;
}
- if (!BTRFS_I(inode)->orphan_meta_reserved) {
- BTRFS_I(inode)->orphan_meta_reserved = 1;
+ if (!test_and_set_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
+ &BTRFS_I(inode)->runtime_flags))
reserve = 1;
- }
spin_unlock(&root->orphan_lock);
/* grab metadata reservation from transaction handle */
delete_item = 1;
}
- if (BTRFS_I(inode)->orphan_meta_reserved) {
- BTRFS_I(inode)->orphan_meta_reserved = 0;
+ if (test_and_clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
+ &BTRFS_I(inode)->runtime_flags))
release_rsv = 1;
- }
spin_unlock(&root->orphan_lock);
if (trans && delete_item) {
inode_set_bytes(inode, btrfs_inode_nbytes(leaf, inode_item));
BTRFS_I(inode)->generation = btrfs_inode_generation(leaf, inode_item);
- BTRFS_I(inode)->sequence = btrfs_inode_sequence(leaf, inode_item);
+ inode->i_version = btrfs_inode_sequence(leaf, inode_item);
inode->i_generation = BTRFS_I(inode)->generation;
inode->i_rdev = 0;
rdev = btrfs_inode_rdev(leaf, inode_item);
btrfs_set_inode_nbytes(leaf, item, inode_get_bytes(inode));
btrfs_set_inode_generation(leaf, item, BTRFS_I(inode)->generation);
- btrfs_set_inode_sequence(leaf, item, BTRFS_I(inode)->sequence);
+ btrfs_set_inode_sequence(leaf, item, inode->i_version);
btrfs_set_inode_transid(leaf, item, trans->transid);
btrfs_set_inode_rdev(leaf, item, inode->i_rdev);
btrfs_set_inode_flags(leaf, item, BTRFS_I(inode)->flags);
goto out;
btrfs_i_size_write(dir, dir->i_size - name_len * 2);
+ inode_inc_iversion(inode);
+ inode_inc_iversion(dir);
inode->i_ctime = dir->i_mtime = dir->i_ctime = CURRENT_TIME;
btrfs_update_inode(trans, root, dir);
out:
}
btrfs_i_size_write(dir, dir->i_size - name_len * 2);
+ inode_inc_iversion(dir);
dir->i_mtime = dir->i_ctime = CURRENT_TIME;
ret = btrfs_update_inode(trans, root, dir);
if (ret)
* any new writes get down to disk quickly.
*/
if (newsize == 0)
- BTRFS_I(inode)->ordered_data_close = 1;
+ set_bit(BTRFS_INODE_ORDERED_DATA_CLOSE,
+ &BTRFS_I(inode)->runtime_flags);
/* we don't support swapfiles, so vmtruncate shouldn't fail */
truncate_setsize(inode, newsize);
if (attr->ia_valid) {
setattr_copy(inode, attr);
+ inode_inc_iversion(inode);
err = btrfs_dirty_inode(inode);
if (!err && attr->ia_valid & ATTR_MODE)
BTRFS_I(inode)->root = root;
memcpy(&BTRFS_I(inode)->location, key, sizeof(*key));
- BTRFS_I(inode)->dummy_inode = 1;
+ set_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags);
inode->i_ino = BTRFS_EMPTY_SUBVOL_DIR_OBJECTID;
- inode->i_op = &simple_dir_inode_operations;
+ inode->i_op = &btrfs_dir_ro_inode_operations;
inode->i_fop = &simple_dir_operations;
inode->i_mode = S_IFDIR | S_IRUGO | S_IWUSR | S_IXUGO;
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
static int btrfs_dentry_delete(const struct dentry *dentry)
{
struct btrfs_root *root;
+ struct inode *inode = dentry->d_inode;
- if (!dentry->d_inode && !IS_ROOT(dentry))
- dentry = dentry->d_parent;
+ if (!inode && !IS_ROOT(dentry))
+ inode = dentry->d_parent->d_inode;
- if (dentry->d_inode) {
- root = BTRFS_I(dentry->d_inode)->root;
+ if (inode) {
+ root = BTRFS_I(inode)->root;
if (btrfs_root_refs(&root->root_item) == 0)
return 1;
+
+ if (btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)
+ return 1;
}
return 0;
}
struct btrfs_path *path;
struct list_head ins_list;
struct list_head del_list;
- struct qstr q;
int ret;
struct extent_buffer *leaf;
int slot;
while (di_cur < di_total) {
struct btrfs_key location;
- struct dentry *tmp;
if (verify_dir_item(root, leaf, di))
break;
d_type = btrfs_filetype_table[btrfs_dir_type(leaf, di)];
btrfs_dir_item_key_to_cpu(leaf, di, &location);
- q.name = name_ptr;
- q.len = name_len;
- q.hash = full_name_hash(q.name, q.len);
- tmp = d_lookup(filp->f_dentry, &q);
- if (!tmp) {
- struct btrfs_key *newkey;
-
- newkey = kzalloc(sizeof(struct btrfs_key),
- GFP_NOFS);
- if (!newkey)
- goto no_dentry;
- tmp = d_alloc(filp->f_dentry, &q);
- if (!tmp) {
- kfree(newkey);
- dput(tmp);
- goto no_dentry;
- }
- memcpy(newkey, &location,
- sizeof(struct btrfs_key));
- tmp->d_fsdata = newkey;
- tmp->d_flags |= DCACHE_NEED_LOOKUP;
- d_rehash(tmp);
- dput(tmp);
- } else {
- dput(tmp);
- }
-no_dentry:
+
/* is this a reference to our own snapshot? If so
- * skip it
+ * skip it.
+ *
+ * In contrast to old kernels, we insert the snapshot's
+ * dir item and dir index after it has been created, so
+ * we won't find a reference to our own snapshot. We
+ * still keep the following code for backward
+ * compatibility.
*/
if (location.type == BTRFS_ROOT_ITEM_KEY &&
location.objectid == root->root_key.objectid) {
int ret = 0;
bool nolock = false;
- if (BTRFS_I(inode)->dummy_inode)
+ if (test_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags))
return 0;
if (btrfs_fs_closing(root->fs_info) && btrfs_is_free_space_inode(root, inode))
struct btrfs_trans_handle *trans;
int ret;
- if (BTRFS_I(inode)->dummy_inode)
+ if (test_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags))
return 0;
trans = btrfs_join_transaction(root);
btrfs_i_size_write(parent_inode, parent_inode->i_size +
name_len * 2);
+ inode_inc_iversion(parent_inode);
parent_inode->i_mtime = parent_inode->i_ctime = CURRENT_TIME;
ret = btrfs_update_inode(trans, root, parent_inode);
if (ret)
}
btrfs_inc_nlink(inode);
+ inode_inc_iversion(inode);
inode->i_ctime = CURRENT_TIME;
ihold(inode);
struct btrfs_dio_private *dip = bio->bi_private;
struct inode *inode = dip->inode;
struct btrfs_root *root = BTRFS_I(inode)->root;
- struct btrfs_trans_handle *trans;
struct btrfs_ordered_extent *ordered = NULL;
- struct extent_state *cached_state = NULL;
u64 ordered_offset = dip->logical_offset;
u64 ordered_bytes = dip->bytes;
int ret;
again:
ret = btrfs_dec_test_first_ordered_pending(inode, &ordered,
&ordered_offset,
- ordered_bytes);
+ ordered_bytes, !err);
if (!ret)
goto out_test;
- BUG_ON(!ordered);
-
- trans = btrfs_join_transaction(root);
- if (IS_ERR(trans)) {
- err = -ENOMEM;
- goto out;
- }
- trans->block_rsv = &root->fs_info->delalloc_block_rsv;
-
- if (test_bit(BTRFS_ORDERED_NOCOW, &ordered->flags)) {
- ret = btrfs_ordered_update_i_size(inode, 0, ordered);
- if (!ret)
- err = btrfs_update_inode_fallback(trans, root, inode);
- goto out;
- }
-
- lock_extent_bits(&BTRFS_I(inode)->io_tree, ordered->file_offset,
- ordered->file_offset + ordered->len - 1, 0,
- &cached_state);
-
- if (test_bit(BTRFS_ORDERED_PREALLOC, &ordered->flags)) {
- ret = btrfs_mark_extent_written(trans, inode,
- ordered->file_offset,
- ordered->file_offset +
- ordered->len);
- if (ret) {
- err = ret;
- goto out_unlock;
- }
- } else {
- ret = insert_reserved_file_extent(trans, inode,
- ordered->file_offset,
- ordered->start,
- ordered->disk_len,
- ordered->len,
- ordered->len,
- 0, 0, 0,
- BTRFS_FILE_EXTENT_REG);
- unpin_extent_cache(&BTRFS_I(inode)->extent_tree,
- ordered->file_offset, ordered->len);
- if (ret) {
- err = ret;
- WARN_ON(1);
- goto out_unlock;
- }
- }
-
- add_pending_csums(trans, inode, ordered->file_offset, &ordered->list);
- ret = btrfs_ordered_update_i_size(inode, 0, ordered);
- if (!ret || !test_bit(BTRFS_ORDERED_PREALLOC, &ordered->flags))
- btrfs_update_inode_fallback(trans, root, inode);
- ret = 0;
-out_unlock:
- unlock_extent_cached(&BTRFS_I(inode)->io_tree, ordered->file_offset,
- ordered->file_offset + ordered->len - 1,
- &cached_state, GFP_NOFS);
-out:
- btrfs_delalloc_release_metadata(inode, ordered->len);
- btrfs_end_transaction(trans, root);
- ordered_offset = ordered->file_offset + ordered->len;
- btrfs_put_ordered_extent(ordered);
- btrfs_put_ordered_extent(ordered);
-
+ ordered->work.func = finish_ordered_fn;
+ ordered->work.flags = 0;
+ btrfs_queue_worker(&root->fs_info->endio_write_workers,
+ &ordered->work);
out_test:
/*
* our bio might span multiple ordered extents. If we haven't
if (ordered_offset < dip->logical_offset + dip->bytes) {
ordered_bytes = dip->logical_offset + dip->bytes -
ordered_offset;
+ ordered = NULL;
goto again;
}
out_done:
bio->bi_private = dip->private;
- kfree(dip->csums);
kfree(dip);
/* If we had an error make sure to clear the uptodate flag */
int ret;
bio_get(bio);
- ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0);
- if (ret)
- goto err;
+
+ if (!write) {
+ ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0);
+ if (ret)
+ goto err;
+ }
if (skip_sum)
goto map;
static void btrfs_invalidatepage(struct page *page, unsigned long offset)
{
+ struct inode *inode = page->mapping->host;
struct extent_io_tree *tree;
struct btrfs_ordered_extent *ordered;
struct extent_state *cached_state = NULL;
u64 page_start = page_offset(page);
u64 page_end = page_start + PAGE_CACHE_SIZE - 1;
-
/*
* we have the page locked, so new writeback can't start,
* and the dirty bit won't be cleared while we are here.
*/
wait_on_page_writeback(page);
- tree = &BTRFS_I(page->mapping->host)->io_tree;
+ tree = &BTRFS_I(inode)->io_tree;
if (offset) {
btrfs_releasepage(page, GFP_NOFS);
return;
}
lock_extent_bits(tree, page_start, page_end, 0, &cached_state);
- ordered = btrfs_lookup_ordered_extent(page->mapping->host,
+ ordered = btrfs_lookup_ordered_extent(inode,
page_offset(page));
if (ordered) {
/*
* whoever cleared the private bit is responsible
* for the finish_ordered_io
*/
- if (TestClearPagePrivate2(page)) {
- btrfs_finish_ordered_io(page->mapping->host,
- page_start, page_end);
+ if (TestClearPagePrivate2(page) &&
+ btrfs_dec_test_ordered_pending(inode, &ordered, page_start,
+ PAGE_CACHE_SIZE, 1)) {
+ btrfs_finish_ordered_io(ordered);
}
btrfs_put_ordered_extent(ordered);
cached_state = NULL;
* using truncate to replace the contents of the file will
* end up with a zero length file after a crash.
*/
- if (inode->i_size == 0 && BTRFS_I(inode)->ordered_data_close)
+ if (inode->i_size == 0 && test_bit(BTRFS_INODE_ORDERED_DATA_CLOSE,
+ &BTRFS_I(inode)->runtime_flags))
btrfs_add_ordered_operation(trans, root, inode);
while (1) {
ei->root = NULL;
ei->space_info = NULL;
ei->generation = 0;
- ei->sequence = 0;
ei->last_trans = 0;
ei->last_sub_trans = 0;
ei->logged_trans = 0;
ei->outstanding_extents = 0;
ei->reserved_extents = 0;
- ei->ordered_data_close = 0;
- ei->orphan_meta_reserved = 0;
- ei->dummy_inode = 0;
- ei->in_defrag = 0;
- ei->delalloc_meta_reserved = 0;
+ ei->runtime_flags = 0;
ei->force_compress = BTRFS_COMPRESS_NONE;
ei->delayed_node = NULL;
if (new_inode && new_inode->i_size && S_ISREG(old_inode->i_mode))
btrfs_add_ordered_operation(trans, root, old_inode);
+ inode_inc_iversion(old_dir);
+ inode_inc_iversion(new_dir);
+ inode_inc_iversion(old_inode);
old_dir->i_ctime = old_dir->i_mtime = ctime;
new_dir->i_ctime = new_dir->i_mtime = ctime;
old_inode->i_ctime = ctime;
}
if (new_inode) {
+ inode_inc_iversion(new_inode);
new_inode->i_ctime = CURRENT_TIME;
if (unlikely(btrfs_ino(new_inode) ==
BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
cur_offset += ins.offset;
*alloc_hint = ins.objectid + ins.offset;
+ inode_inc_iversion(inode);
inode->i_ctime = CURRENT_TIME;
BTRFS_I(inode)->flags |= BTRFS_INODE_PREALLOC;
if (!(mode & FALLOC_FL_KEEP_SIZE) &&
projects / deliverable / linux.git / blobdiff