while (compressed_size > 0) {
cpage = compressed_pages[i];
cur_size = min_t(unsigned long, compressed_size,
- PAGE_CACHE_SIZE);
+ PAGE_SIZE);
kaddr = kmap_atomic(cpage);
write_extent_buffer(leaf, kaddr, ptr, cur_size);
compress_type);
} else {
page = find_get_page(inode->i_mapping,
- start >> PAGE_CACHE_SHIFT);
+ start >> PAGE_SHIFT);
btrfs_set_file_extent_compression(leaf, ei, 0);
kaddr = kmap_atomic(page);
- offset = start & (PAGE_CACHE_SIZE - 1);
+ offset = start & (PAGE_SIZE - 1);
write_extent_buffer(leaf, kaddr + offset, ptr, size);
kunmap_atomic(kaddr);
- page_cache_release(page);
+ put_page(page);
}
btrfs_mark_buffer_dirty(leaf);
btrfs_release_path(path);
* And at reserve time, it's always aligned to page size, so
* just free one page here.
*/
- btrfs_qgroup_free_data(inode, 0, PAGE_CACHE_SIZE);
+ btrfs_qgroup_free_data(inode, 0, PAGE_SIZE);
btrfs_free_path(path);
btrfs_end_transaction(trans, root);
return ret;
actual_end = min_t(u64, isize, end + 1);
again:
will_compress = 0;
- nr_pages = (end >> PAGE_CACHE_SHIFT) - (start >> PAGE_CACHE_SHIFT) + 1;
- nr_pages = min_t(unsigned long, nr_pages, SZ_128K / PAGE_CACHE_SIZE);
+ nr_pages = (end >> PAGE_SHIFT) - (start >> PAGE_SHIFT) + 1;
+ nr_pages = min_t(unsigned long, nr_pages, SZ_128K / PAGE_SIZE);
/*
* we don't want to send crud past the end of i_size through
if (!ret) {
unsigned long offset = total_compressed &
- (PAGE_CACHE_SIZE - 1);
+ (PAGE_SIZE - 1);
struct page *page = pages[nr_pages_ret - 1];
char *kaddr;
if (offset) {
kaddr = kmap_atomic(page);
memset(kaddr + offset, 0,
- PAGE_CACHE_SIZE - offset);
+ PAGE_SIZE - offset);
kunmap_atomic(kaddr);
}
will_compress = 1;
* one last check to make sure the compression is really a
* win, compare the page count read with the blocks on disk
*/
- total_in = ALIGN(total_in, PAGE_CACHE_SIZE);
+ total_in = ALIGN(total_in, PAGE_SIZE);
if (total_compressed >= total_in) {
will_compress = 0;
} else {
*/
for (i = 0; i < nr_pages_ret; i++) {
WARN_ON(pages[i]->mapping);
- page_cache_release(pages[i]);
+ put_page(pages[i]);
}
kfree(pages);
pages = NULL;
free_pages_out:
for (i = 0; i < nr_pages_ret; i++) {
WARN_ON(pages[i]->mapping);
- page_cache_release(pages[i]);
+ put_page(pages[i]);
}
kfree(pages);
}
for (i = 0; i < async_extent->nr_pages; i++) {
WARN_ON(async_extent->pages[i]->mapping);
- page_cache_release(async_extent->pages[i]);
+ put_page(async_extent->pages[i]);
}
kfree(async_extent->pages);
async_extent->nr_pages = 0;
async_extent->ram_size - 1, 0);
goto out_free_reserve;
}
+ btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
/*
* clear dirty, set writeback and unlock the pages.
}
return;
out_free_reserve:
+ btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
out_free:
extent_clear_unlock_delalloc(inode, async_extent->start,
PAGE_END_WRITEBACK);
*nr_written = *nr_written +
- (end - start + PAGE_CACHE_SIZE) / PAGE_CACHE_SIZE;
+ (end - start + PAGE_SIZE) / PAGE_SIZE;
*page_started = 1;
goto out;
} else if (ret < 0) {
goto out_drop_extent_cache;
}
+ btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
+
if (disk_num_bytes < cur_alloc_size)
break;
out_drop_extent_cache:
btrfs_drop_extent_cache(inode, start, start + ram_size - 1, 0);
out_reserve:
+ btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
out_unlock:
extent_clear_unlock_delalloc(inode, start, end, locked_page,
async_cow = container_of(work, struct async_cow, work);
root = async_cow->root;
- nr_pages = (async_cow->end - async_cow->start + PAGE_CACHE_SIZE) >>
- PAGE_CACHE_SHIFT;
+ nr_pages = (async_cow->end - async_cow->start + PAGE_SIZE) >>
+ PAGE_SHIFT;
/*
* atomic_sub_return implies a barrier for waitqueue_active
async_cow_start, async_cow_submit,
async_cow_free);
- nr_pages = (cur_end - start + PAGE_CACHE_SIZE) >>
- PAGE_CACHE_SHIFT;
+ nr_pages = (cur_end - start + PAGE_SIZE) >>
+ PAGE_SHIFT;
atomic_add(nr_pages, &root->fs_info->async_delalloc_pages);
btrfs_queue_work(root->fs_info->delalloc_workers,
int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
struct extent_state **cached_state)
{
- WARN_ON((end & (PAGE_CACHE_SIZE - 1)) == 0);
+ WARN_ON((end & (PAGE_SIZE - 1)) == 0);
return set_extent_delalloc(&BTRFS_I(inode)->io_tree, start, end,
cached_state, GFP_NOFS);
}
inode = page->mapping->host;
page_start = page_offset(page);
- page_end = page_offset(page) + PAGE_CACHE_SIZE - 1;
+ page_end = page_offset(page) + PAGE_SIZE - 1;
lock_extent_bits(&BTRFS_I(inode)->io_tree, page_start, page_end,
&cached_state);
goto out;
ordered = btrfs_lookup_ordered_range(inode, page_start,
- PAGE_CACHE_SIZE);
+ PAGE_SIZE);
if (ordered) {
unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start,
page_end, &cached_state, GFP_NOFS);
}
ret = btrfs_delalloc_reserve_space(inode, page_start,
- PAGE_CACHE_SIZE);
+ PAGE_SIZE);
if (ret) {
mapping_set_error(page->mapping, ret);
end_extent_writepage(page, ret, page_start, page_end);
&cached_state, GFP_NOFS);
out_page:
unlock_page(page);
- page_cache_release(page);
+ put_page(page);
kfree(fixup);
}
return -EAGAIN;
SetPageChecked(page);
- page_cache_get(page);
+ get_page(page);
btrfs_init_work(&fixup->work, btrfs_fixup_helper,
btrfs_writepage_fixup_worker, NULL, NULL);
fixup->page = page;
if (btrfs_file_extent_compression(leaf, fi) != BTRFS_COMPRESS_NONE) {
loff_t offset = new_size;
- loff_t page_end = ALIGN(offset, PAGE_CACHE_SIZE);
+ loff_t page_end = ALIGN(offset, PAGE_SIZE);
/*
* Zero out the remaining of the last page of our inline extent,
struct extent_state *cached_state = NULL;
char *kaddr;
u32 blocksize = root->sectorsize;
- pgoff_t index = from >> PAGE_CACHE_SHIFT;
+ pgoff_t index = from >> PAGE_SHIFT;
unsigned offset = from & (blocksize - 1);
struct page *page;
gfp_t mask = btrfs_alloc_write_mask(mapping);
lock_page(page);
if (page->mapping != mapping) {
unlock_page(page);
- page_cache_release(page);
+ put_page(page);
goto again;
}
if (!PageUptodate(page)) {
unlock_extent_cached(io_tree, block_start, block_end,
&cached_state, GFP_NOFS);
unlock_page(page);
- page_cache_release(page);
+ put_page(page);
btrfs_start_ordered_extent(inode, ordered, 1);
btrfs_put_ordered_extent(ordered);
goto again;
btrfs_delalloc_release_space(inode, block_start,
blocksize);
unlock_page(page);
- page_cache_release(page);
+ put_page(page);
out:
return ret;
}
read_extent_buffer(leaf, tmp, ptr, inline_size);
- max_size = min_t(unsigned long, PAGE_CACHE_SIZE, max_size);
+ max_size = min_t(unsigned long, PAGE_SIZE, max_size);
ret = btrfs_decompress(compress_type, tmp, page,
extent_offset, inline_size, max_size);
kfree(tmp);
size = btrfs_file_extent_inline_len(leaf, path->slots[0], item);
extent_offset = page_offset(page) + pg_offset - extent_start;
- copy_size = min_t(u64, PAGE_CACHE_SIZE - pg_offset,
- size - extent_offset);
+ copy_size = min_t(u64, PAGE_SIZE - pg_offset,
+ size - extent_offset);
em->start = extent_start + extent_offset;
em->len = ALIGN(copy_size, root->sectorsize);
em->orig_block_len = em->len;
map = kmap(page);
read_extent_buffer(leaf, map + pg_offset, ptr,
copy_size);
- if (pg_offset + copy_size < PAGE_CACHE_SIZE) {
+ if (pg_offset + copy_size < PAGE_SIZE) {
memset(map + pg_offset + copy_size, 0,
- PAGE_CACHE_SIZE - pg_offset -
+ PAGE_SIZE - pg_offset -
copy_size);
}
kunmap(page);
return ERR_PTR(ret);
}
+ btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
+
em = create_pinned_em(inode, start, ins.offset, start, ins.objectid,
ins.offset, ins.offset, ins.offset, 0);
if (IS_ERR(em)) {
int start_idx;
int end_idx;
- start_idx = start >> PAGE_CACHE_SHIFT;
+ start_idx = start >> PAGE_SHIFT;
/*
* end is the last byte in the last page. end == start is legal
*/
- end_idx = end >> PAGE_CACHE_SHIFT;
+ end_idx = end >> PAGE_SHIFT;
rcu_read_lock();
* include/linux/pagemap.h for details.
*/
if (unlikely(page != *pagep)) {
- page_cache_release(page);
+ put_page(page);
page = NULL;
}
}
if (page) {
if (page->index <= end_idx)
found = true;
- page_cache_release(page);
+ put_page(page);
}
rcu_read_unlock();
if (ret == 1) {
ClearPagePrivate(page);
set_page_private(page, 0);
- page_cache_release(page);
+ put_page(page);
}
return ret;
}
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;
+ u64 page_end = page_start + PAGE_SIZE - 1;
u64 start;
u64 end;
int inode_evicting = inode->i_state & I_FREEING;
* 2) Not written to disk
* This means the reserved space should be freed here.
*/
- btrfs_qgroup_free_data(inode, page_start, PAGE_CACHE_SIZE);
+ btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE);
if (!inode_evicting) {
clear_extent_bit(tree, page_start, page_end,
EXTENT_LOCKED | EXTENT_DIRTY |
if (PagePrivate(page)) {
ClearPagePrivate(page);
set_page_private(page, 0);
- page_cache_release(page);
+ put_page(page);
}
}
u64 page_end;
u64 end;
- reserved_space = PAGE_CACHE_SIZE;
+ reserved_space = PAGE_SIZE;
sb_start_pagefault(inode->i_sb);
page_start = page_offset(page);
- page_end = page_start + PAGE_CACHE_SIZE - 1;
+ page_end = page_start + PAGE_SIZE - 1;
end = page_end;
/*
goto again;
}
- if (page->index == ((size - 1) >> PAGE_CACHE_SHIFT)) {
+ if (page->index == ((size - 1) >> PAGE_SHIFT)) {
reserved_space = round_up(size - page_start, root->sectorsize);
- if (reserved_space < PAGE_CACHE_SIZE) {
+ if (reserved_space < PAGE_SIZE) {
end = page_start + reserved_space - 1;
spin_lock(&BTRFS_I(inode)->lock);
BTRFS_I(inode)->outstanding_extents++;
spin_unlock(&BTRFS_I(inode)->lock);
btrfs_delalloc_release_space(inode, page_start,
- PAGE_CACHE_SIZE - reserved_space);
+ PAGE_SIZE - reserved_space);
}
}
ret = 0;
/* page is wholly or partially inside EOF */
- if (page_start + PAGE_CACHE_SIZE > size)
- zero_start = size & ~PAGE_CACHE_MASK;
+ if (page_start + PAGE_SIZE > size)
+ zero_start = size & ~PAGE_MASK;
else
- zero_start = PAGE_CACHE_SIZE;
+ zero_start = PAGE_SIZE;
- if (zero_start != PAGE_CACHE_SIZE) {
+ if (zero_start != PAGE_SIZE) {
kaddr = kmap(page);
- memset(kaddr + zero_start, 0, PAGE_CACHE_SIZE - zero_start);
+ memset(kaddr + zero_start, 0, PAGE_SIZE - zero_start);
flush_dcache_page(page);
kunmap(page);
}
return 0;
}
+static int btrfs_rename_exchange(struct inode *old_dir,
+ struct dentry *old_dentry,
+ struct inode *new_dir,
+ struct dentry *new_dentry)
+{
+ struct btrfs_trans_handle *trans;
+ struct btrfs_root *root = BTRFS_I(old_dir)->root;
+ struct btrfs_root *dest = BTRFS_I(new_dir)->root;
+ struct inode *new_inode = new_dentry->d_inode;
+ struct inode *old_inode = old_dentry->d_inode;
+ struct timespec ctime = CURRENT_TIME;
+ struct dentry *parent;
+ u64 old_ino = btrfs_ino(old_inode);
+ u64 new_ino = btrfs_ino(new_inode);
+ u64 old_idx = 0;
+ u64 new_idx = 0;
+ u64 root_objectid;
+ int ret;
+ bool root_log_pinned = false;
+ bool dest_log_pinned = false;
+
+ /* we only allow rename subvolume link between subvolumes */
+ if (old_ino != BTRFS_FIRST_FREE_OBJECTID && root != dest)
+ return -EXDEV;
+
+ /* close the race window with snapshot create/destroy ioctl */
+ if (old_ino == BTRFS_FIRST_FREE_OBJECTID)
+ down_read(&root->fs_info->subvol_sem);
+ if (new_ino == BTRFS_FIRST_FREE_OBJECTID)
+ down_read(&dest->fs_info->subvol_sem);
+
+ /*
+ * We want to reserve the absolute worst case amount of items. So if
+ * both inodes are subvols and we need to unlink them then that would
+ * require 4 item modifications, but if they are both normal inodes it
+ * would require 5 item modifications, so we'll assume their normal
+ * inodes. So 5 * 2 is 10, plus 2 for the new links, so 12 total items
+ * should cover the worst case number of items we'll modify.
+ */
+ trans = btrfs_start_transaction(root, 12);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ goto out_notrans;
+ }
+
+ /*
+ * We need to find a free sequence number both in the source and
+ * in the destination directory for the exchange.
+ */
+ ret = btrfs_set_inode_index(new_dir, &old_idx);
+ if (ret)
+ goto out_fail;
+ ret = btrfs_set_inode_index(old_dir, &new_idx);
+ if (ret)
+ goto out_fail;
+
+ BTRFS_I(old_inode)->dir_index = 0ULL;
+ BTRFS_I(new_inode)->dir_index = 0ULL;
+
+ /* Reference for the source. */
+ if (old_ino == BTRFS_FIRST_FREE_OBJECTID) {
+ /* force full log commit if subvolume involved. */
+ btrfs_set_log_full_commit(root->fs_info, trans);
+ } else {
+ btrfs_pin_log_trans(root);
+ root_log_pinned = true;
+ ret = btrfs_insert_inode_ref(trans, dest,
+ new_dentry->d_name.name,
+ new_dentry->d_name.len,
+ old_ino,
+ btrfs_ino(new_dir), old_idx);
+ if (ret)
+ goto out_fail;
+ }
+
+ /* And now for the dest. */
+ if (new_ino == BTRFS_FIRST_FREE_OBJECTID) {
+ /* force full log commit if subvolume involved. */
+ btrfs_set_log_full_commit(dest->fs_info, trans);
+ } else {
+ btrfs_pin_log_trans(dest);
+ dest_log_pinned = true;
+ ret = btrfs_insert_inode_ref(trans, root,
+ old_dentry->d_name.name,
+ old_dentry->d_name.len,
+ new_ino,
+ btrfs_ino(old_dir), new_idx);
+ if (ret)
+ goto out_fail;
+ }
+
+ /* Update inode version and ctime/mtime. */
+ inode_inc_iversion(old_dir);
+ inode_inc_iversion(new_dir);
+ inode_inc_iversion(old_inode);
+ inode_inc_iversion(new_inode);
+ old_dir->i_ctime = old_dir->i_mtime = ctime;
+ new_dir->i_ctime = new_dir->i_mtime = ctime;
+ old_inode->i_ctime = ctime;
+ new_inode->i_ctime = ctime;
+
+ if (old_dentry->d_parent != new_dentry->d_parent) {
+ btrfs_record_unlink_dir(trans, old_dir, old_inode, 1);
+ btrfs_record_unlink_dir(trans, new_dir, new_inode, 1);
+ }
+
+ /* src is a subvolume */
+ if (old_ino == BTRFS_FIRST_FREE_OBJECTID) {
+ root_objectid = BTRFS_I(old_inode)->root->root_key.objectid;
+ ret = btrfs_unlink_subvol(trans, root, old_dir,
+ root_objectid,
+ old_dentry->d_name.name,
+ old_dentry->d_name.len);
+ } else { /* src is an inode */
+ ret = __btrfs_unlink_inode(trans, root, old_dir,
+ old_dentry->d_inode,
+ old_dentry->d_name.name,
+ old_dentry->d_name.len);
+ if (!ret)
+ ret = btrfs_update_inode(trans, root, old_inode);
+ }
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto out_fail;
+ }
+
+ /* dest is a subvolume */
+ if (new_ino == BTRFS_FIRST_FREE_OBJECTID) {
+ root_objectid = BTRFS_I(new_inode)->root->root_key.objectid;
+ ret = btrfs_unlink_subvol(trans, dest, new_dir,
+ root_objectid,
+ new_dentry->d_name.name,
+ new_dentry->d_name.len);
+ } else { /* dest is an inode */
+ ret = __btrfs_unlink_inode(trans, dest, new_dir,
+ new_dentry->d_inode,
+ new_dentry->d_name.name,
+ new_dentry->d_name.len);
+ if (!ret)
+ ret = btrfs_update_inode(trans, dest, new_inode);
+ }
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto out_fail;
+ }
+
+ ret = btrfs_add_link(trans, new_dir, old_inode,
+ new_dentry->d_name.name,
+ new_dentry->d_name.len, 0, old_idx);
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto out_fail;
+ }
+
+ ret = btrfs_add_link(trans, old_dir, new_inode,
+ old_dentry->d_name.name,
+ old_dentry->d_name.len, 0, new_idx);
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto out_fail;
+ }
+
+ if (old_inode->i_nlink == 1)
+ BTRFS_I(old_inode)->dir_index = old_idx;
+ if (new_inode->i_nlink == 1)
+ BTRFS_I(new_inode)->dir_index = new_idx;
+
+ if (root_log_pinned) {
+ parent = new_dentry->d_parent;
+ btrfs_log_new_name(trans, old_inode, old_dir, parent);
+ btrfs_end_log_trans(root);
+ root_log_pinned = false;
+ }
+ if (dest_log_pinned) {
+ parent = old_dentry->d_parent;
+ btrfs_log_new_name(trans, new_inode, new_dir, parent);
+ btrfs_end_log_trans(dest);
+ dest_log_pinned = false;
+ }
+out_fail:
+ /*
+ * If we have pinned a log and an error happened, we unpin tasks
+ * trying to sync the log and force them to fallback to a transaction
+ * commit if the log currently contains any of the inodes involved in
+ * this rename operation (to ensure we do not persist a log with an
+ * inconsistent state for any of these inodes or leading to any
+ * inconsistencies when replayed). If the transaction was aborted, the
+ * abortion reason is propagated to userspace when attempting to commit
+ * the transaction. If the log does not contain any of these inodes, we
+ * allow the tasks to sync it.
+ */
+ if (ret && (root_log_pinned || dest_log_pinned)) {
+ if (btrfs_inode_in_log(old_dir, root->fs_info->generation) ||
+ btrfs_inode_in_log(new_dir, root->fs_info->generation) ||
+ btrfs_inode_in_log(old_inode, root->fs_info->generation) ||
+ (new_inode &&
+ btrfs_inode_in_log(new_inode, root->fs_info->generation)))
+ btrfs_set_log_full_commit(root->fs_info, trans);
+
+ if (root_log_pinned) {
+ btrfs_end_log_trans(root);
+ root_log_pinned = false;
+ }
+ if (dest_log_pinned) {
+ btrfs_end_log_trans(dest);
+ dest_log_pinned = false;
+ }
+ }
+ ret = btrfs_end_transaction(trans, root);
+out_notrans:
+ if (new_ino == BTRFS_FIRST_FREE_OBJECTID)
+ up_read(&dest->fs_info->subvol_sem);
+ if (old_ino == BTRFS_FIRST_FREE_OBJECTID)
+ up_read(&root->fs_info->subvol_sem);
+
+ return ret;
+}
+
+static int btrfs_whiteout_for_rename(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct inode *dir,
+ struct dentry *dentry)
+{
+ int ret;
+ struct inode *inode;
+ u64 objectid;
+ u64 index;
+
+ ret = btrfs_find_free_ino(root, &objectid);
+ if (ret)
+ return ret;
+
+ inode = btrfs_new_inode(trans, root, dir,
+ dentry->d_name.name,
+ dentry->d_name.len,
+ btrfs_ino(dir),
+ objectid,
+ S_IFCHR | WHITEOUT_MODE,
+ &index);
+
+ if (IS_ERR(inode)) {
+ ret = PTR_ERR(inode);
+ return ret;
+ }
+
+ inode->i_op = &btrfs_special_inode_operations;
+ init_special_inode(inode, inode->i_mode,
+ WHITEOUT_DEV);
+
+ ret = btrfs_init_inode_security(trans, inode, dir,
+ &dentry->d_name);
+ if (ret)
+ goto out;
+
+ ret = btrfs_add_nondir(trans, dir, dentry,
+ inode, 0, index);
+ if (ret)
+ goto out;
+
+ ret = btrfs_update_inode(trans, root, inode);
+out:
+ unlock_new_inode(inode);
+ if (ret)
+ inode_dec_link_count(inode);
+ iput(inode);
+
+ return ret;
+}
+
static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry)
+ struct inode *new_dir, struct dentry *new_dentry,
+ unsigned int flags)
{
struct btrfs_trans_handle *trans;
+ unsigned int trans_num_items;
struct btrfs_root *root = BTRFS_I(old_dir)->root;
struct btrfs_root *dest = BTRFS_I(new_dir)->root;
struct inode *new_inode = d_inode(new_dentry);
u64 root_objectid;
int ret;
u64 old_ino = btrfs_ino(old_inode);
+ bool log_pinned = false;
if (btrfs_ino(new_dir) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)
return -EPERM;
* We want to reserve the absolute worst case amount of items. So if
* both inodes are subvols and we need to unlink them then that would
* require 4 item modifications, but if they are both normal inodes it
- * would require 5 item modifications, so we'll assume their normal
+ * would require 5 item modifications, so we'll assume they are normal
* inodes. So 5 * 2 is 10, plus 1 for the new link, so 11 total items
* should cover the worst case number of items we'll modify.
+ * If our rename has the whiteout flag, we need more 5 units for the
+ * new inode (1 inode item, 1 inode ref, 2 dir items and 1 xattr item
+ * when selinux is enabled).
*/
- trans = btrfs_start_transaction(root, 11);
+ trans_num_items = 11;
+ if (flags & RENAME_WHITEOUT)
+ trans_num_items += 5;
+ trans = btrfs_start_transaction(root, trans_num_items);
if (IS_ERR(trans)) {
- ret = PTR_ERR(trans);
- goto out_notrans;
- }
+ ret = PTR_ERR(trans);
+ goto out_notrans;
+ }
if (dest != root)
btrfs_record_root_in_trans(trans, dest);
/* force full log commit if subvolume involved. */
btrfs_set_log_full_commit(root->fs_info, trans);
} else {
+ btrfs_pin_log_trans(root);
+ log_pinned = true;
ret = btrfs_insert_inode_ref(trans, dest,
new_dentry->d_name.name,
new_dentry->d_name.len,
btrfs_ino(new_dir), index);
if (ret)
goto out_fail;
- /*
- * this is an ugly little race, but the rename is required
- * to make sure that if we crash, the inode is either at the
- * old name or the new one. pinning the log transaction lets
- * us make sure we don't allow a log commit to come in after
- * we unlink the name but before we add the new name back in.
- */
- btrfs_pin_log_trans(root);
}
inode_inc_iversion(old_dir);
if (old_inode->i_nlink == 1)
BTRFS_I(old_inode)->dir_index = index;
- if (old_ino != BTRFS_FIRST_FREE_OBJECTID) {
+ if (log_pinned) {
struct dentry *parent = new_dentry->d_parent;
+
btrfs_log_new_name(trans, old_inode, old_dir, parent);
btrfs_end_log_trans(root);
+ log_pinned = false;
+ }
+
+ if (flags & RENAME_WHITEOUT) {
+ ret = btrfs_whiteout_for_rename(trans, root, old_dir,
+ old_dentry);
+
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto out_fail;
+ }
}
out_fail:
+ /*
+ * If we have pinned the log and an error happened, we unpin tasks
+ * trying to sync the log and force them to fallback to a transaction
+ * commit if the log currently contains any of the inodes involved in
+ * this rename operation (to ensure we do not persist a log with an
+ * inconsistent state for any of these inodes or leading to any
+ * inconsistencies when replayed). If the transaction was aborted, the
+ * abortion reason is propagated to userspace when attempting to commit
+ * the transaction. If the log does not contain any of these inodes, we
+ * allow the tasks to sync it.
+ */
+ if (ret && log_pinned) {
+ if (btrfs_inode_in_log(old_dir, root->fs_info->generation) ||
+ btrfs_inode_in_log(new_dir, root->fs_info->generation) ||
+ btrfs_inode_in_log(old_inode, root->fs_info->generation) ||
+ (new_inode &&
+ btrfs_inode_in_log(new_inode, root->fs_info->generation)))
+ btrfs_set_log_full_commit(root->fs_info, trans);
+
+ btrfs_end_log_trans(root);
+ log_pinned = false;
+ }
btrfs_end_transaction(trans, root);
out_notrans:
if (old_ino == BTRFS_FIRST_FREE_OBJECTID)
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
- if (flags & ~RENAME_NOREPLACE)
+ if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
return -EINVAL;
- return btrfs_rename(old_dir, old_dentry, new_dir, new_dentry);
+ if (flags & RENAME_EXCHANGE)
+ return btrfs_rename_exchange(old_dir, old_dentry, new_dir,
+ new_dentry);
+
+ return btrfs_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
}
static void btrfs_run_delalloc_work(struct btrfs_work *work)
btrfs_end_transaction(trans, root);
break;
}
+ btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
last_alloc = ins.offset;
ret = insert_reserved_file_extent(trans, inode,