+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2008 Oracle. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public
- * License v2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public
- * License along with this program; if not, write to the
- * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
- * Boston, MA 021110-1307, USA.
*/
#include <linux/sched.h>
#include <linux/blkdev.h>
#include <linux/list_sort.h>
#include <linux/iversion.h>
+#include "ctree.h"
#include "tree-log.h"
#include "disk-io.h"
#include "locking.h"
#include "print-tree.h"
#include "backref.h"
-#include "hash.h"
#include "compression.h"
#include "qgroup.h"
#include "inode-map.h"
* inside it
*/
int (*process_func)(struct btrfs_root *log, struct extent_buffer *eb,
- struct walk_control *wc, u64 gen);
+ struct walk_control *wc, u64 gen, int level);
};
/*
*/
static int process_one_buffer(struct btrfs_root *log,
struct extent_buffer *eb,
- struct walk_control *wc, u64 gen)
+ struct walk_control *wc, u64 gen, int level)
{
struct btrfs_fs_info *fs_info = log->fs_info;
int ret = 0;
* pin down any logged extents, so we have to read the block.
*/
if (btrfs_fs_incompat(fs_info, MIXED_GROUPS)) {
- ret = btrfs_read_buffer(eb, gen);
+ ret = btrfs_read_buffer(eb, gen, level, NULL);
if (ret)
return ret;
}
struct btrfs_inode *dir,
struct btrfs_dir_item *di)
{
- struct btrfs_fs_info *fs_info = root->fs_info;
struct inode *inode;
char *name;
int name_len;
if (ret)
goto out;
else
- ret = btrfs_run_delayed_items(trans, fs_info);
+ ret = btrfs_run_delayed_items(trans);
out:
kfree(name);
iput(inode);
ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]);
if (key->type == BTRFS_INODE_EXTREF_KEY) {
- if (btrfs_find_name_in_ext_backref(path, ref_objectid,
+ if (btrfs_find_name_in_ext_backref(path->nodes[0],
+ path->slots[0],
+ ref_objectid,
name, namelen, NULL))
match = 1;
u64 ref_index, char *name, int namelen,
int *search_done)
{
- struct btrfs_fs_info *fs_info = root->fs_info;
int ret;
char *victim_name;
int victim_name_len;
kfree(victim_name);
if (ret)
return ret;
- ret = btrfs_run_delayed_items(trans, fs_info);
+ ret = btrfs_run_delayed_items(trans);
if (ret)
return ret;
*search_done = 1;
victim_name_len);
if (!ret)
ret = btrfs_run_delayed_items(
- trans,
- fs_info);
+ trans);
}
iput(victim_parent);
kfree(victim_name);
read_extent_buffer(eb, *name, (unsigned long)&extref->name,
*namelen);
- *index = btrfs_inode_extref_index(eb, extref);
+ if (index)
+ *index = btrfs_inode_extref_index(eb, extref);
if (parent_objectid)
*parent_objectid = btrfs_inode_extref_parent(eb, extref);
read_extent_buffer(eb, *name, (unsigned long)(ref + 1), *namelen);
- *index = btrfs_inode_ref_index(eb, ref);
+ if (index)
+ *index = btrfs_inode_ref_index(eb, ref);
return 0;
}
+/*
+ * Take an inode reference item from the log tree and iterate all names from the
+ * inode reference item in the subvolume tree with the same key (if it exists).
+ * For any name that is not in the inode reference item from the log tree, do a
+ * proper unlink of that name (that is, remove its entry from the inode
+ * reference item and both dir index keys).
+ */
+static int unlink_old_inode_refs(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_path *path,
+ struct btrfs_inode *inode,
+ struct extent_buffer *log_eb,
+ int log_slot,
+ struct btrfs_key *key)
+{
+ int ret;
+ unsigned long ref_ptr;
+ unsigned long ref_end;
+ struct extent_buffer *eb;
+
+again:
+ btrfs_release_path(path);
+ ret = btrfs_search_slot(NULL, root, key, path, 0, 0);
+ if (ret > 0) {
+ ret = 0;
+ goto out;
+ }
+ if (ret < 0)
+ goto out;
+
+ eb = path->nodes[0];
+ ref_ptr = btrfs_item_ptr_offset(eb, path->slots[0]);
+ ref_end = ref_ptr + btrfs_item_size_nr(eb, path->slots[0]);
+ while (ref_ptr < ref_end) {
+ char *name = NULL;
+ int namelen;
+ u64 parent_id;
+
+ if (key->type == BTRFS_INODE_EXTREF_KEY) {
+ ret = extref_get_fields(eb, ref_ptr, &namelen, &name,
+ NULL, &parent_id);
+ } else {
+ parent_id = key->offset;
+ ret = ref_get_fields(eb, ref_ptr, &namelen, &name,
+ NULL);
+ }
+ if (ret)
+ goto out;
+
+ if (key->type == BTRFS_INODE_EXTREF_KEY)
+ ret = btrfs_find_name_in_ext_backref(log_eb, log_slot,
+ parent_id, name,
+ namelen, NULL);
+ else
+ ret = btrfs_find_name_in_backref(log_eb, log_slot, name,
+ namelen, NULL);
+
+ if (!ret) {
+ struct inode *dir;
+
+ btrfs_release_path(path);
+ dir = read_one_inode(root, parent_id);
+ if (!dir) {
+ ret = -ENOENT;
+ kfree(name);
+ goto out;
+ }
+ ret = btrfs_unlink_inode(trans, root, BTRFS_I(dir),
+ inode, name, namelen);
+ kfree(name);
+ iput(dir);
+ if (ret)
+ goto out;
+ goto again;
+ }
+
+ kfree(name);
+ ref_ptr += namelen;
+ if (key->type == BTRFS_INODE_EXTREF_KEY)
+ ref_ptr += sizeof(struct btrfs_inode_extref);
+ else
+ ref_ptr += sizeof(struct btrfs_inode_ref);
+ }
+ ret = 0;
+ out:
+ btrfs_release_path(path);
+ return ret;
+}
+
/*
* replay one inode back reference item found in the log tree.
* eb, slot and key refer to the buffer and key found in the log tree.
}
}
+ /*
+ * Before we overwrite the inode reference item in the subvolume tree
+ * with the item from the log tree, we must unlink all names from the
+ * parent directory that are in the subvolume's tree inode reference
+ * item, otherwise we end up with an inconsistent subvolume tree where
+ * dir index entries exist for a name but there is no inode reference
+ * item with the same name.
+ */
+ ret = unlink_old_inode_refs(trans, root, path, BTRFS_I(inode), eb, slot,
+ key);
+ if (ret)
+ goto out;
+
/* finally write the back reference in the inode */
ret = overwrite_item(trans, root, path, eb, slot, key);
out:
struct inode *dir,
struct btrfs_key *dir_key)
{
- struct btrfs_fs_info *fs_info = root->fs_info;
int ret;
struct extent_buffer *eb;
int slot;
ret = btrfs_unlink_inode(trans, root, BTRFS_I(dir),
BTRFS_I(inode), name, name_len);
if (!ret)
- ret = btrfs_run_delayed_items(trans, fs_info);
+ ret = btrfs_run_delayed_items(trans);
kfree(name);
iput(inode);
if (ret)
nritems = btrfs_header_nritems(path->nodes[0]);
if (path->slots[0] >= nritems) {
ret = btrfs_next_leaf(root, path);
- if (ret)
+ if (ret == 1)
break;
+ else if (ret < 0)
+ goto out;
}
btrfs_item_key_to_cpu(path->nodes[0], &found_key,
path->slots[0]);
* back refs).
*/
static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb,
- struct walk_control *wc, u64 gen)
+ struct walk_control *wc, u64 gen, int level)
{
int nritems;
struct btrfs_path *path;
struct btrfs_root *root = wc->replay_dest;
struct btrfs_key key;
- int level;
int i;
int ret;
- ret = btrfs_read_buffer(eb, gen);
+ ret = btrfs_read_buffer(eb, gen, level, NULL);
if (ret)
return ret;
if (ret)
break;
- /* for regular files, make sure corresponding
- * orphan item exist. extents past the new EOF
- * will be truncated later by orphan cleanup.
+ /*
+ * Before replaying extents, truncate the inode to its
+ * size. We need to do it now and not after log replay
+ * because before an fsync we can have prealloc extents
+ * added beyond the inode's i_size. If we did it after,
+ * through orphan cleanup for example, we would drop
+ * those prealloc extents just after replaying them.
*/
if (S_ISREG(mode)) {
- ret = insert_orphan_item(wc->trans, root,
- key.objectid);
+ struct inode *inode;
+ u64 from;
+
+ inode = read_one_inode(root, key.objectid);
+ if (!inode) {
+ ret = -EIO;
+ break;
+ }
+ from = ALIGN(i_size_read(inode),
+ root->fs_info->sectorsize);
+ ret = btrfs_drop_extents(wc->trans, root, inode,
+ from, (u64)-1, 1);
+ /*
+ * If the nlink count is zero here, the iput
+ * will free the inode. We bump it to make
+ * sure it doesn't get freed until the link
+ * count fixup is done.
+ */
+ if (!ret) {
+ if (inode->i_nlink == 0)
+ inc_nlink(inode);
+ /* Update link count and nbytes. */
+ ret = btrfs_update_inode(wc->trans,
+ root, inode);
+ }
+ iput(inode);
if (ret)
break;
}
WARN_ON(*level >= BTRFS_MAX_LEVEL);
while (*level > 0) {
+ struct btrfs_key first_key;
+
WARN_ON(*level < 0);
WARN_ON(*level >= BTRFS_MAX_LEVEL);
cur = path->nodes[*level];
bytenr = btrfs_node_blockptr(cur, path->slots[*level]);
ptr_gen = btrfs_node_ptr_generation(cur, path->slots[*level]);
+ btrfs_node_key_to_cpu(cur, &first_key, path->slots[*level]);
blocksize = fs_info->nodesize;
parent = path->nodes[*level];
return PTR_ERR(next);
if (*level == 1) {
- ret = wc->process_func(root, next, wc, ptr_gen);
+ ret = wc->process_func(root, next, wc, ptr_gen,
+ *level - 1);
if (ret) {
free_extent_buffer(next);
return ret;
path->slots[*level]++;
if (wc->free) {
- ret = btrfs_read_buffer(next, ptr_gen);
+ ret = btrfs_read_buffer(next, ptr_gen,
+ *level - 1, &first_key);
if (ret) {
free_extent_buffer(next);
return ret;
free_extent_buffer(next);
continue;
}
- ret = btrfs_read_buffer(next, ptr_gen);
+ ret = btrfs_read_buffer(next, ptr_gen, *level - 1, &first_key);
if (ret) {
free_extent_buffer(next);
return ret;
root_owner = btrfs_header_owner(parent);
ret = wc->process_func(root, path->nodes[*level], wc,
- btrfs_header_generation(path->nodes[*level]));
+ btrfs_header_generation(path->nodes[*level]),
+ *level);
if (ret)
return ret;
/* was the root node processed? if not, catch it here */
if (path->nodes[orig_level]) {
ret = wc->process_func(log, path->nodes[orig_level], wc,
- btrfs_header_generation(path->nodes[orig_level]));
+ btrfs_header_generation(path->nodes[orig_level]),
+ orig_level);
if (ret)
goto out;
if (wc->free) {
* from this directory and from this transaction
*/
ret = btrfs_next_leaf(root, path);
- if (ret == 1) {
- last_offset = (u64)-1;
+ if (ret) {
+ if (ret == 1)
+ last_offset = (u64)-1;
+ else
+ err = ret;
goto done;
}
btrfs_item_key_to_cpu(path->nodes[0], &tmp, path->slots[0]);
ASSERT(ret == 0);
src = src_path->nodes[0];
i = 0;
+ need_find_last_extent = true;
}
btrfs_item_key_to_cpu(src, &key, i);
break;
*last_extent = extent_end;
}
+
+ /*
+ * Check if there is a hole between the last extent found in our leaf
+ * and the first extent in the next leaf. If there is one, we need to
+ * log an explicit hole so that at replay time we can punch the hole.
+ */
+ if (ret == 0 &&
+ key.objectid == btrfs_ino(inode) &&
+ key.type == BTRFS_EXTENT_DATA_KEY &&
+ i == btrfs_header_nritems(src_path->nodes[0])) {
+ ret = btrfs_next_leaf(inode->root, src_path);
+ need_find_last_extent = true;
+ if (ret > 0) {
+ ret = 0;
+ } else if (ret == 0) {
+ btrfs_item_key_to_cpu(src_path->nodes[0], &key,
+ src_path->slots[0]);
+ if (key.objectid == btrfs_ino(inode) &&
+ key.type == BTRFS_EXTENT_DATA_KEY &&
+ *last_extent < key.offset) {
+ const u64 len = key.offset - *last_extent;
+
+ ret = btrfs_insert_file_extent(trans, log,
+ btrfs_ino(inode),
+ *last_extent, 0,
+ 0, len, 0, len,
+ 0, 0, 0);
+ }
+ }
+ }
/*
* Need to let the callers know we dropped the path so they should
* re-search.
num++;
}
+ /*
+ * Add all prealloc extents beyond the inode's i_size to make sure we
+ * don't lose them after doing a fast fsync and replaying the log.
+ */
+ if (inode->flags & BTRFS_INODE_PREALLOC) {
+ struct rb_node *node;
+
+ for (node = rb_last(&tree->map); node; node = rb_prev(node)) {
+ em = rb_entry(node, struct extent_map, rb_node);
+ if (em->start < i_size_read(&inode->vfs_inode))
+ break;
+ if (!list_empty(&em->list))
+ continue;
+ /* Same as above loop. */
+ if (++num > 32768) {
+ list_del_init(&tree->modified_extents);
+ ret = -EFBIG;
+ goto process;
+ }
+ refcount_inc(&em->refs);
+ set_bit(EXTENT_FLAG_LOGGING, &em->flags);
+ list_add_tail(&em->list, &extents);
+ }
+ }
+
list_sort(NULL, &extents, extent_cmp);
btrfs_get_logged_extents(inode, logged_list, logged_start, logged_end);
/*
struct extent_map_tree *em_tree = &inode->extent_tree;
u64 logged_isize = 0;
bool need_log_inode_item = true;
+ bool xattrs_logged = false;
path = btrfs_alloc_path();
if (!path)
err = btrfs_log_all_xattrs(trans, root, inode, path, dst_path);
if (err)
goto out_unlock;
+ xattrs_logged = true;
if (max_key.type >= BTRFS_EXTENT_DATA_KEY && !fast_search) {
btrfs_release_path(path);
btrfs_release_path(dst_path);
btrfs_release_path(dst_path);
if (need_log_inode_item) {
err = log_inode_item(trans, log, dst_path, inode);
+ if (!err && !xattrs_logged) {
+ err = btrfs_log_all_xattrs(trans, root, inode, path,
+ dst_path);
+ btrfs_release_path(path);
+ }
if (err)
goto out_unlock;
}
* the last committed transaction
*/
static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
struct btrfs_inode *inode,
struct dentry *parent,
const loff_t start,
int inode_only,
struct btrfs_log_ctx *ctx)
{
+ struct btrfs_root *root = inode->root;
struct btrfs_fs_info *fs_info = root->fs_info;
struct super_block *sb;
struct dentry *old_parent = NULL;
goto end_no_trans;
}
- if (root != inode->root || btrfs_root_refs(&root->root_item) == 0) {
+ if (btrfs_root_refs(&root->root_item) == 0) {
ret = 1;
goto end_no_trans;
}
* data on disk.
*/
int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans,
- struct btrfs_root *root, struct dentry *dentry,
+ struct dentry *dentry,
const loff_t start,
const loff_t end,
struct btrfs_log_ctx *ctx)
struct dentry *parent = dget_parent(dentry);
int ret;
- ret = btrfs_log_inode_parent(trans, root, BTRFS_I(d_inode(dentry)),
- parent, start, end, LOG_INODE_ALL, ctx);
+ ret = btrfs_log_inode_parent(trans, BTRFS_I(d_inode(dentry)), parent,
+ start, end, LOG_INODE_ALL, ctx);
dput(parent);
return ret;
struct dentry *parent)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
- struct btrfs_root *root = inode->root;
/*
* this will force the logging code to walk the dentry chain
* up for the file
*/
- if (S_ISREG(inode->vfs_inode.i_mode))
+ if (!S_ISDIR(inode->vfs_inode.i_mode))
inode->last_unlink_trans = trans->transid;
/*
(!old_dir || old_dir->logged_trans <= fs_info->last_trans_committed))
return 0;
- return btrfs_log_inode_parent(trans, root, inode, parent, 0,
- LLONG_MAX, LOG_INODE_EXISTS, NULL);
+ return btrfs_log_inode_parent(trans, inode, parent, 0, LLONG_MAX,
+ LOG_INODE_EXISTS, NULL);
}
git.samba.org / sfrench / cifs-2.6.git / blobdiff