e09d94c9e4
When logging an inode, if we detect the inode has a reference that conflicts with some other inode that got renamed, we log that other inode while holding the log mutex of the current inode. We then find out if there are other inodes that conflict with the first conflicting inode, and log them while under the log mutex of the original inode. This is fine because the recursion can only happen once. For the upcoming work where we directly log delayed items without flushing them first to the subvolume tree, this recursion adds a lot of complexity and it's hard to keep lockdep happy about it. So collect a list of conflicting inodes and then log the inodes after unlocking the log mutex of the inode we started with. Also limit the maximum number of conflict inodes we log to 10, to avoid spending too much time logging (and maybe allocating too many list elements too), as typically we don't have more than 1 or 2 conflicting inodes - if we go over the limit, simply fallback to a transaction commit. It is possible to have a very long list of conflicting inodes to be intentionally created by a user if he/she creates a very long succession of renames like this: (...) rename E to F rename D to E rename C to D rename B to C rename A to B touch A (create a new file named A) fsync A If that happened for a sequence of hundreds or thousands of renames, it could massively slow down the logging and cause other secondary effects like for example blocking other fsync operations and transaction commits for a very long time (assuming it wouldn't run into -ENOSPC or -ENOMEM first). However such cases are very uncommon to happen in practice, nevertheless it's better to be prepared for them and avoid chaos. Such long sequence of conflicting inodes could be created before this change. Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
105 lines
3.3 KiB
C
105 lines
3.3 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* Copyright (C) 2008 Oracle. All rights reserved.
|
|
*/
|
|
|
|
#ifndef BTRFS_TREE_LOG_H
|
|
#define BTRFS_TREE_LOG_H
|
|
|
|
#include "ctree.h"
|
|
#include "transaction.h"
|
|
|
|
/* return value for btrfs_log_dentry_safe that means we don't need to log it at all */
|
|
#define BTRFS_NO_LOG_SYNC 256
|
|
|
|
/* We can't use the tree log for whatever reason, force a transaction commit */
|
|
#define BTRFS_LOG_FORCE_COMMIT (1)
|
|
|
|
struct btrfs_log_ctx {
|
|
int log_ret;
|
|
int log_transid;
|
|
bool log_new_dentries;
|
|
bool logging_new_name;
|
|
/* Indicate if the inode being logged was logged before. */
|
|
bool logged_before;
|
|
/* Tracks the last logged dir item/index key offset. */
|
|
u64 last_dir_item_offset;
|
|
struct inode *inode;
|
|
struct list_head list;
|
|
/* Only used for fast fsyncs. */
|
|
struct list_head ordered_extents;
|
|
struct list_head conflict_inodes;
|
|
int num_conflict_inodes;
|
|
bool logging_conflict_inodes;
|
|
};
|
|
|
|
static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx,
|
|
struct inode *inode)
|
|
{
|
|
ctx->log_ret = 0;
|
|
ctx->log_transid = 0;
|
|
ctx->log_new_dentries = false;
|
|
ctx->logging_new_name = false;
|
|
ctx->logged_before = false;
|
|
ctx->inode = inode;
|
|
INIT_LIST_HEAD(&ctx->list);
|
|
INIT_LIST_HEAD(&ctx->ordered_extents);
|
|
INIT_LIST_HEAD(&ctx->conflict_inodes);
|
|
ctx->num_conflict_inodes = 0;
|
|
ctx->logging_conflict_inodes = false;
|
|
}
|
|
|
|
static inline void btrfs_release_log_ctx_extents(struct btrfs_log_ctx *ctx)
|
|
{
|
|
struct btrfs_ordered_extent *ordered;
|
|
struct btrfs_ordered_extent *tmp;
|
|
|
|
ASSERT(inode_is_locked(ctx->inode));
|
|
|
|
list_for_each_entry_safe(ordered, tmp, &ctx->ordered_extents, log_list) {
|
|
list_del_init(&ordered->log_list);
|
|
btrfs_put_ordered_extent(ordered);
|
|
}
|
|
}
|
|
|
|
static inline void btrfs_set_log_full_commit(struct btrfs_trans_handle *trans)
|
|
{
|
|
WRITE_ONCE(trans->fs_info->last_trans_log_full_commit, trans->transid);
|
|
}
|
|
|
|
static inline int btrfs_need_log_full_commit(struct btrfs_trans_handle *trans)
|
|
{
|
|
return READ_ONCE(trans->fs_info->last_trans_log_full_commit) ==
|
|
trans->transid;
|
|
}
|
|
|
|
int btrfs_sync_log(struct btrfs_trans_handle *trans,
|
|
struct btrfs_root *root, struct btrfs_log_ctx *ctx);
|
|
int btrfs_free_log(struct btrfs_trans_handle *trans, struct btrfs_root *root);
|
|
int btrfs_free_log_root_tree(struct btrfs_trans_handle *trans,
|
|
struct btrfs_fs_info *fs_info);
|
|
int btrfs_recover_log_trees(struct btrfs_root *tree_root);
|
|
int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans,
|
|
struct dentry *dentry,
|
|
struct btrfs_log_ctx *ctx);
|
|
void btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans,
|
|
struct btrfs_root *root,
|
|
const char *name, int name_len,
|
|
struct btrfs_inode *dir, u64 index);
|
|
void btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans,
|
|
struct btrfs_root *root,
|
|
const char *name, int name_len,
|
|
struct btrfs_inode *inode, u64 dirid);
|
|
void btrfs_end_log_trans(struct btrfs_root *root);
|
|
void btrfs_pin_log_trans(struct btrfs_root *root);
|
|
void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans,
|
|
struct btrfs_inode *dir, struct btrfs_inode *inode,
|
|
int for_rename);
|
|
void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans,
|
|
struct btrfs_inode *dir);
|
|
void btrfs_log_new_name(struct btrfs_trans_handle *trans,
|
|
struct dentry *old_dentry, struct btrfs_inode *old_dir,
|
|
u64 old_dir_index, struct dentry *parent);
|
|
|
|
#endif
|