![Filipe Manana](/assets/img/avatar_default.png)
We can get into inconsistency between inodes and directory entries after fsyncing a directory. The issue is that while a directory gets the new dentries persisted in the fsync log and replayed at mount time, the link count of the inode that directory entries point to doesn't get updated, staying with an incorrect link count (smaller then the correct value). This later leads to stale file handle errors when accessing (including attempt to delete) some of the links if all the other ones are removed, which also implies impossibility to delete the parent directories, since the dentries can not be removed. Another issue is that (unlike ext3/4, xfs, f2fs, reiserfs, nilfs2), when fsyncing a directory, new files aren't logged (their metadata and dentries) nor any child directories. So this patch fixes this issue too, since it has the same resolution as the incorrect inode link count issue mentioned before. This is very easy to reproduce, and the following excerpt from my test case for xfstests shows how: _scratch_mkfs >> $seqres.full 2>&1 _init_flakey _mount_flakey # Create our main test file and directory. $XFS_IO_PROG -f -c "pwrite -S 0xaa 0 8K" $SCRATCH_MNT/foo | _filter_xfs_io mkdir $SCRATCH_MNT/mydir # Make sure all metadata and data are durably persisted. sync # Add a hard link to 'foo' inside our test directory and fsync only the # directory. The btrfs fsync implementation had a bug that caused the new # directory entry to be visible after the fsync log replay but, the inode # of our file remained with a link count of 1. ln $SCRATCH_MNT/foo $SCRATCH_MNT/mydir/foo_2 # Add a few more links and new files. # This is just to verify nothing breaks or gives incorrect results after the # fsync log is replayed. ln $SCRATCH_MNT/foo $SCRATCH_MNT/mydir/foo_3 $XFS_IO_PROG -f -c "pwrite -S 0xff 0 64K" $SCRATCH_MNT/hello | _filter_xfs_io ln $SCRATCH_MNT/hello $SCRATCH_MNT/mydir/hello_2 # Add some subdirectories and new files and links to them. This is to verify # that after fsyncing our top level directory 'mydir', all the subdirectories # and their files/links are registered in the fsync log and exist after the # fsync log is replayed. mkdir -p $SCRATCH_MNT/mydir/x/y/z ln $SCRATCH_MNT/foo $SCRATCH_MNT/mydir/x/y/foo_y_link ln $SCRATCH_MNT/foo $SCRATCH_MNT/mydir/x/y/z/foo_z_link touch $SCRATCH_MNT/mydir/x/y/z/qwerty # Now fsync only our top directory. $XFS_IO_PROG -c "fsync" $SCRATCH_MNT/mydir # And fsync now our new file named 'hello', just to verify later that it has # the expected content and that the previous fsync on the directory 'mydir' had # no bad influence on this fsync. $XFS_IO_PROG -c "fsync" $SCRATCH_MNT/hello # Simulate a crash/power loss. _load_flakey_table $FLAKEY_DROP_WRITES _unmount_flakey _load_flakey_table $FLAKEY_ALLOW_WRITES _mount_flakey # Verify the content of our file 'foo' remains the same as before, 8192 bytes, # all with the value 0xaa. echo "File 'foo' content after log replay:" od -t x1 $SCRATCH_MNT/foo # Remove the first name of our inode. Because of the directory fsync bug, the # inode's link count was 1 instead of 5, so removing the 'foo' name ended up # deleting the inode and the other names became stale directory entries (still # visible to applications). Attempting to remove or access the remaining # dentries pointing to that inode resulted in stale file handle errors and # made it impossible to remove the parent directories since it was impossible # for them to become empty. echo "file 'foo' link count after log replay: $(stat -c %h $SCRATCH_MNT/foo)" rm -f $SCRATCH_MNT/foo # Now verify that all files, links and directories created before fsyncing our # directory exist after the fsync log was replayed. [ -f $SCRATCH_MNT/mydir/foo_2 ] || echo "Link mydir/foo_2 is missing" [ -f $SCRATCH_MNT/mydir/foo_3 ] || echo "Link mydir/foo_3 is missing" [ -f $SCRATCH_MNT/hello ] || echo "File hello is missing" [ -f $SCRATCH_MNT/mydir/hello_2 ] || echo "Link mydir/hello_2 is missing" [ -f $SCRATCH_MNT/mydir/x/y/foo_y_link ] || \ echo "Link mydir/x/y/foo_y_link is missing" [ -f $SCRATCH_MNT/mydir/x/y/z/foo_z_link ] || \ echo "Link mydir/x/y/z/foo_z_link is missing" [ -f $SCRATCH_MNT/mydir/x/y/z/qwerty ] || \ echo "File mydir/x/y/z/qwerty is missing" # We expect our file here to have a size of 64Kb and all the bytes having the # value 0xff. echo "file 'hello' content after log replay:" od -t x1 $SCRATCH_MNT/hello # Now remove all files/links, under our test directory 'mydir', and verify we # can remove all the directories. rm -f $SCRATCH_MNT/mydir/x/y/z/* rmdir $SCRATCH_MNT/mydir/x/y/z rm -f $SCRATCH_MNT/mydir/x/y/* rmdir $SCRATCH_MNT/mydir/x/y rmdir $SCRATCH_MNT/mydir/x rm -f $SCRATCH_MNT/mydir/* rmdir $SCRATCH_MNT/mydir # An fsck, run by the fstests framework everytime a test finishes, also detected # the inconsistency and printed the following error message: # # root 5 inode 257 errors 2001, no inode item, link count wrong # unresolved ref dir 258 index 2 namelen 5 name foo_2 filetype 1 errors 4, no inode ref # unresolved ref dir 258 index 3 namelen 5 name foo_3 filetype 1 errors 4, no inode ref status=0 exit The expected golden output for the test is: wrote 8192/8192 bytes at offset 0 XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) wrote 65536/65536 bytes at offset 0 XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) File 'foo' content after log replay: 0000000 aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa * 0020000 file 'foo' link count after log replay: 5 file 'hello' content after log replay: 0000000 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff * 0200000 Which is the output after this patch and when running the test against ext3/4, xfs, f2fs, reiserfs or nilfs2. Without this patch, the test's output is: wrote 8192/8192 bytes at offset 0 XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) wrote 65536/65536 bytes at offset 0 XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) File 'foo' content after log replay: 0000000 aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa * 0020000 file 'foo' link count after log replay: 1 Link mydir/foo_2 is missing Link mydir/foo_3 is missing Link mydir/x/y/foo_y_link is missing Link mydir/x/y/z/foo_z_link is missing File mydir/x/y/z/qwerty is missing file 'hello' content after log replay: 0000000 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff * 0200000 rmdir: failed to remove '/home/fdmanana/btrfs-tests/scratch_1/mydir/x/y/z': No such file or directory rmdir: failed to remove '/home/fdmanana/btrfs-tests/scratch_1/mydir/x/y': No such file or directory rmdir: failed to remove '/home/fdmanana/btrfs-tests/scratch_1/mydir/x': No such file or directory rm: cannot remove '/home/fdmanana/btrfs-tests/scratch_1/mydir/foo_2': Stale file handle rm: cannot remove '/home/fdmanana/btrfs-tests/scratch_1/mydir/foo_3': Stale file handle rmdir: failed to remove '/home/fdmanana/btrfs-tests/scratch_1/mydir': Directory not empty Fsck, without this fix, also complains about the wrong link count: root 5 inode 257 errors 2001, no inode item, link count wrong unresolved ref dir 258 index 2 namelen 5 name foo_2 filetype 1 errors 4, no inode ref unresolved ref dir 258 index 3 namelen 5 name foo_3 filetype 1 errors 4, no inode ref So fix this by logging the inodes that the dentries point to when fsyncing a directory. A test case for xfstests follows. Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
329 lines
8.7 KiB
C
329 lines
8.7 KiB
C
/*
|
|
* Copyright (C) 2007 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.
|
|
*/
|
|
|
|
#ifndef __BTRFS_I__
|
|
#define __BTRFS_I__
|
|
|
|
#include <linux/hash.h>
|
|
#include "extent_map.h"
|
|
#include "extent_io.h"
|
|
#include "ordered-data.h"
|
|
#include "delayed-inode.h"
|
|
|
|
/*
|
|
* ordered_data_close is set by truncate when a file that used
|
|
* to have good data has been truncated to zero. When it is set
|
|
* the btrfs file release call will add this inode to the
|
|
* ordered operations list so that we make sure to flush out any
|
|
* new data the application may have written before commit.
|
|
*/
|
|
#define BTRFS_INODE_ORDERED_DATA_CLOSE 0
|
|
#define BTRFS_INODE_ORPHAN_META_RESERVED 1
|
|
#define BTRFS_INODE_DUMMY 2
|
|
#define BTRFS_INODE_IN_DEFRAG 3
|
|
#define BTRFS_INODE_DELALLOC_META_RESERVED 4
|
|
#define BTRFS_INODE_HAS_ORPHAN_ITEM 5
|
|
#define BTRFS_INODE_HAS_ASYNC_EXTENT 6
|
|
#define BTRFS_INODE_NEEDS_FULL_SYNC 7
|
|
#define BTRFS_INODE_COPY_EVERYTHING 8
|
|
#define BTRFS_INODE_IN_DELALLOC_LIST 9
|
|
#define BTRFS_INODE_READDIO_NEED_LOCK 10
|
|
#define BTRFS_INODE_HAS_PROPS 11
|
|
/*
|
|
* The following 3 bits are meant only for the btree inode.
|
|
* When any of them is set, it means an error happened while writing an
|
|
* extent buffer belonging to:
|
|
* 1) a non-log btree
|
|
* 2) a log btree and first log sub-transaction
|
|
* 3) a log btree and second log sub-transaction
|
|
*/
|
|
#define BTRFS_INODE_BTREE_ERR 12
|
|
#define BTRFS_INODE_BTREE_LOG1_ERR 13
|
|
#define BTRFS_INODE_BTREE_LOG2_ERR 14
|
|
|
|
/* in memory btrfs inode */
|
|
struct btrfs_inode {
|
|
/* which subvolume this inode belongs to */
|
|
struct btrfs_root *root;
|
|
|
|
/* key used to find this inode on disk. This is used by the code
|
|
* to read in roots of subvolumes
|
|
*/
|
|
struct btrfs_key location;
|
|
|
|
/*
|
|
* Lock for counters and all fields used to determine if the inode is in
|
|
* the log or not (last_trans, last_sub_trans, last_log_commit,
|
|
* logged_trans).
|
|
*/
|
|
spinlock_t lock;
|
|
|
|
/* the extent_tree has caches of all the extent mappings to disk */
|
|
struct extent_map_tree extent_tree;
|
|
|
|
/* the io_tree does range state (DIRTY, LOCKED etc) */
|
|
struct extent_io_tree io_tree;
|
|
|
|
/* special utility tree used to record which mirrors have already been
|
|
* tried when checksums fail for a given block
|
|
*/
|
|
struct extent_io_tree io_failure_tree;
|
|
|
|
/* held while logging the inode in tree-log.c */
|
|
struct mutex log_mutex;
|
|
|
|
/* held while doing delalloc reservations */
|
|
struct mutex delalloc_mutex;
|
|
|
|
/* used to order data wrt metadata */
|
|
struct btrfs_ordered_inode_tree ordered_tree;
|
|
|
|
/* list of all the delalloc inodes in the FS. There are times we need
|
|
* to write all the delalloc pages to disk, and this list is used
|
|
* to walk them all.
|
|
*/
|
|
struct list_head delalloc_inodes;
|
|
|
|
/* node for the red-black tree that links inodes in subvolume root */
|
|
struct rb_node rb_node;
|
|
|
|
unsigned long runtime_flags;
|
|
|
|
/* Keep track of who's O_SYNC/fsyncing currently */
|
|
atomic_t sync_writers;
|
|
|
|
/* full 64 bit generation number, struct vfs_inode doesn't have a big
|
|
* enough field for this.
|
|
*/
|
|
u64 generation;
|
|
|
|
/*
|
|
* transid of the trans_handle that last modified this inode
|
|
*/
|
|
u64 last_trans;
|
|
|
|
/*
|
|
* transid that last logged this inode
|
|
*/
|
|
u64 logged_trans;
|
|
|
|
/*
|
|
* log transid when this inode was last modified
|
|
*/
|
|
int last_sub_trans;
|
|
|
|
/* a local copy of root's last_log_commit */
|
|
int last_log_commit;
|
|
|
|
/* total number of bytes pending delalloc, used by stat to calc the
|
|
* real block usage of the file
|
|
*/
|
|
u64 delalloc_bytes;
|
|
|
|
/*
|
|
* total number of bytes pending defrag, used by stat to check whether
|
|
* it needs COW.
|
|
*/
|
|
u64 defrag_bytes;
|
|
|
|
/*
|
|
* the size of the file stored in the metadata on disk. data=ordered
|
|
* means the in-memory i_size might be larger than the size on disk
|
|
* because not all the blocks are written yet.
|
|
*/
|
|
u64 disk_i_size;
|
|
|
|
/*
|
|
* if this is a directory then index_cnt is the counter for the index
|
|
* number for new files that are created
|
|
*/
|
|
u64 index_cnt;
|
|
|
|
/* Cache the directory index number to speed the dir/file remove */
|
|
u64 dir_index;
|
|
|
|
/* the fsync log has some corner cases that mean we have to check
|
|
* directories to see if any unlinks have been done before
|
|
* the directory was logged. See tree-log.c for all the
|
|
* details
|
|
*/
|
|
u64 last_unlink_trans;
|
|
|
|
/*
|
|
* Number of bytes outstanding that are going to need csums. This is
|
|
* used in ENOSPC accounting.
|
|
*/
|
|
u64 csum_bytes;
|
|
|
|
/* flags field from the on disk inode */
|
|
u32 flags;
|
|
|
|
/*
|
|
* Counters to keep track of the number of extent item's we may use due
|
|
* to delalloc and such. outstanding_extents is the number of extent
|
|
* items we think we'll end up using, and reserved_extents is the number
|
|
* of extent items we've reserved metadata for.
|
|
*/
|
|
unsigned outstanding_extents;
|
|
unsigned reserved_extents;
|
|
|
|
/*
|
|
* always compress this one file
|
|
*/
|
|
unsigned force_compress;
|
|
|
|
struct btrfs_delayed_node *delayed_node;
|
|
|
|
/* File creation time. */
|
|
struct timespec i_otime;
|
|
|
|
struct inode vfs_inode;
|
|
};
|
|
|
|
extern unsigned char btrfs_filetype_table[];
|
|
|
|
static inline struct btrfs_inode *BTRFS_I(struct inode *inode)
|
|
{
|
|
return container_of(inode, struct btrfs_inode, vfs_inode);
|
|
}
|
|
|
|
static inline unsigned long btrfs_inode_hash(u64 objectid,
|
|
const struct btrfs_root *root)
|
|
{
|
|
u64 h = objectid ^ (root->objectid * GOLDEN_RATIO_PRIME);
|
|
|
|
#if BITS_PER_LONG == 32
|
|
h = (h >> 32) ^ (h & 0xffffffff);
|
|
#endif
|
|
|
|
return (unsigned long)h;
|
|
}
|
|
|
|
static inline void btrfs_insert_inode_hash(struct inode *inode)
|
|
{
|
|
unsigned long h = btrfs_inode_hash(inode->i_ino, BTRFS_I(inode)->root);
|
|
|
|
__insert_inode_hash(inode, h);
|
|
}
|
|
|
|
static inline u64 btrfs_ino(struct inode *inode)
|
|
{
|
|
u64 ino = BTRFS_I(inode)->location.objectid;
|
|
|
|
/*
|
|
* !ino: btree_inode
|
|
* type == BTRFS_ROOT_ITEM_KEY: subvol dir
|
|
*/
|
|
if (!ino || BTRFS_I(inode)->location.type == BTRFS_ROOT_ITEM_KEY)
|
|
ino = inode->i_ino;
|
|
return ino;
|
|
}
|
|
|
|
static inline void btrfs_i_size_write(struct inode *inode, u64 size)
|
|
{
|
|
i_size_write(inode, size);
|
|
BTRFS_I(inode)->disk_i_size = size;
|
|
}
|
|
|
|
static inline bool btrfs_is_free_space_inode(struct inode *inode)
|
|
{
|
|
struct btrfs_root *root = BTRFS_I(inode)->root;
|
|
|
|
if (root == root->fs_info->tree_root &&
|
|
btrfs_ino(inode) != BTRFS_BTREE_INODE_OBJECTID)
|
|
return true;
|
|
if (BTRFS_I(inode)->location.objectid == BTRFS_FREE_INO_OBJECTID)
|
|
return true;
|
|
return false;
|
|
}
|
|
|
|
static inline int btrfs_inode_in_log(struct inode *inode, u64 generation)
|
|
{
|
|
int ret = 0;
|
|
|
|
spin_lock(&BTRFS_I(inode)->lock);
|
|
if (BTRFS_I(inode)->logged_trans == generation &&
|
|
BTRFS_I(inode)->last_sub_trans <=
|
|
BTRFS_I(inode)->last_log_commit &&
|
|
BTRFS_I(inode)->last_sub_trans <=
|
|
BTRFS_I(inode)->root->last_log_commit) {
|
|
/*
|
|
* After a ranged fsync we might have left some extent maps
|
|
* (that fall outside the fsync's range). So return false
|
|
* here if the list isn't empty, to make sure btrfs_log_inode()
|
|
* will be called and process those extent maps.
|
|
*/
|
|
smp_mb();
|
|
if (list_empty(&BTRFS_I(inode)->extent_tree.modified_extents))
|
|
ret = 1;
|
|
}
|
|
spin_unlock(&BTRFS_I(inode)->lock);
|
|
return ret;
|
|
}
|
|
|
|
#define BTRFS_DIO_ORIG_BIO_SUBMITTED 0x1
|
|
|
|
struct btrfs_dio_private {
|
|
struct inode *inode;
|
|
unsigned long flags;
|
|
u64 logical_offset;
|
|
u64 disk_bytenr;
|
|
u64 bytes;
|
|
void *private;
|
|
|
|
/* number of bios pending for this dio */
|
|
atomic_t pending_bios;
|
|
|
|
/* IO errors */
|
|
int errors;
|
|
|
|
/* orig_bio is our btrfs_io_bio */
|
|
struct bio *orig_bio;
|
|
|
|
/* dio_bio came from fs/direct-io.c */
|
|
struct bio *dio_bio;
|
|
|
|
/*
|
|
* The original bio may be splited to several sub-bios, this is
|
|
* done during endio of sub-bios
|
|
*/
|
|
int (*subio_endio)(struct inode *, struct btrfs_io_bio *, int);
|
|
};
|
|
|
|
/*
|
|
* Disable DIO read nolock optimization, so new dio readers will be forced
|
|
* to grab i_mutex. It is used to avoid the endless truncate due to
|
|
* nonlocked dio read.
|
|
*/
|
|
static inline void btrfs_inode_block_unlocked_dio(struct inode *inode)
|
|
{
|
|
set_bit(BTRFS_INODE_READDIO_NEED_LOCK, &BTRFS_I(inode)->runtime_flags);
|
|
smp_mb();
|
|
}
|
|
|
|
static inline void btrfs_inode_resume_unlocked_dio(struct inode *inode)
|
|
{
|
|
smp_mb__before_atomic();
|
|
clear_bit(BTRFS_INODE_READDIO_NEED_LOCK,
|
|
&BTRFS_I(inode)->runtime_flags);
|
|
}
|
|
|
|
bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end);
|
|
|
|
#endif
|