mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-12-23 11:04:44 +08:00
441c850857
ext4_should_writeback_data() had an incorrect sequence of
tests to determine if it should return 0 or 1: in
particular, even in no-journal mode, 0 was being returned
for a non-regular-file inode.
This meant that, in non-journal mode, we would use
ext4_journalled_aops for directories, symlinks, and other
non-regular files. However, calling journalled aop
callbacks when there is no valid handle, can cause problems.
This would cause a kernel crash with Jan Kara's commit
2d859db3e4
("ext4: fix data corruption in inodes with
journalled data"), because we now dereference 'handle' in
ext4_journalled_write_end().
I also added BUG_ONs to check for a valid handle in the
obviously journal-only aops callbacks.
I tested this running xfstests with a scratch device in
these modes:
- no-journal
- data=ordered
- data=writeback
- data=journal
All work fine; the data=journal run has many failures and a
crash in xfstests 074, but this is no different from a
vanilla kernel.
Signed-off-by: Curt Wohlgemuth <curtw@google.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Cc: stable@kernel.org
326 lines
10 KiB
C
326 lines
10 KiB
C
/*
|
|
* ext4_jbd2.h
|
|
*
|
|
* Written by Stephen C. Tweedie <sct@redhat.com>, 1999
|
|
*
|
|
* Copyright 1998--1999 Red Hat corp --- All Rights Reserved
|
|
*
|
|
* This file is part of the Linux kernel and is made available under
|
|
* the terms of the GNU General Public License, version 2, or at your
|
|
* option, any later version, incorporated herein by reference.
|
|
*
|
|
* Ext4-specific journaling extensions.
|
|
*/
|
|
|
|
#ifndef _EXT4_JBD2_H
|
|
#define _EXT4_JBD2_H
|
|
|
|
#include <linux/fs.h>
|
|
#include <linux/jbd2.h>
|
|
#include "ext4.h"
|
|
|
|
#define EXT4_JOURNAL(inode) (EXT4_SB((inode)->i_sb)->s_journal)
|
|
|
|
/* Define the number of blocks we need to account to a transaction to
|
|
* modify one block of data.
|
|
*
|
|
* We may have to touch one inode, one bitmap buffer, up to three
|
|
* indirection blocks, the group and superblock summaries, and the data
|
|
* block to complete the transaction.
|
|
*
|
|
* For extents-enabled fs we may have to allocate and modify up to
|
|
* 5 levels of tree + root which are stored in the inode. */
|
|
|
|
#define EXT4_SINGLEDATA_TRANS_BLOCKS(sb) \
|
|
(EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS) \
|
|
? 27U : 8U)
|
|
|
|
/* Extended attribute operations touch at most two data buffers,
|
|
* two bitmap buffers, and two group summaries, in addition to the inode
|
|
* and the superblock, which are already accounted for. */
|
|
|
|
#define EXT4_XATTR_TRANS_BLOCKS 6U
|
|
|
|
/* Define the minimum size for a transaction which modifies data. This
|
|
* needs to take into account the fact that we may end up modifying two
|
|
* quota files too (one for the group, one for the user quota). The
|
|
* superblock only gets updated once, of course, so don't bother
|
|
* counting that again for the quota updates. */
|
|
|
|
#define EXT4_DATA_TRANS_BLOCKS(sb) (EXT4_SINGLEDATA_TRANS_BLOCKS(sb) + \
|
|
EXT4_XATTR_TRANS_BLOCKS - 2 + \
|
|
EXT4_MAXQUOTAS_TRANS_BLOCKS(sb))
|
|
|
|
/*
|
|
* Define the number of metadata blocks we need to account to modify data.
|
|
*
|
|
* This include super block, inode block, quota blocks and xattr blocks
|
|
*/
|
|
#define EXT4_META_TRANS_BLOCKS(sb) (EXT4_XATTR_TRANS_BLOCKS + \
|
|
EXT4_MAXQUOTAS_TRANS_BLOCKS(sb))
|
|
|
|
/* Delete operations potentially hit one directory's namespace plus an
|
|
* entire inode, plus arbitrary amounts of bitmap/indirection data. Be
|
|
* generous. We can grow the delete transaction later if necessary. */
|
|
|
|
#define EXT4_DELETE_TRANS_BLOCKS(sb) (2 * EXT4_DATA_TRANS_BLOCKS(sb) + 64)
|
|
|
|
/* Define an arbitrary limit for the amount of data we will anticipate
|
|
* writing to any given transaction. For unbounded transactions such as
|
|
* write(2) and truncate(2) we can write more than this, but we always
|
|
* start off at the maximum transaction size and grow the transaction
|
|
* optimistically as we go. */
|
|
|
|
#define EXT4_MAX_TRANS_DATA 64U
|
|
|
|
/* We break up a large truncate or write transaction once the handle's
|
|
* buffer credits gets this low, we need either to extend the
|
|
* transaction or to start a new one. Reserve enough space here for
|
|
* inode, bitmap, superblock, group and indirection updates for at least
|
|
* one block, plus two quota updates. Quota allocations are not
|
|
* needed. */
|
|
|
|
#define EXT4_RESERVE_TRANS_BLOCKS 12U
|
|
|
|
#define EXT4_INDEX_EXTRA_TRANS_BLOCKS 8
|
|
|
|
#ifdef CONFIG_QUOTA
|
|
/* Amount of blocks needed for quota update - we know that the structure was
|
|
* allocated so we need to update only data block */
|
|
#define EXT4_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 1 : 0)
|
|
/* Amount of blocks needed for quota insert/delete - we do some block writes
|
|
* but inode, sb and group updates are done only once */
|
|
#define EXT4_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\
|
|
(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_INIT_REWRITE) : 0)
|
|
|
|
#define EXT4_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\
|
|
(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_DEL_REWRITE) : 0)
|
|
#else
|
|
#define EXT4_QUOTA_TRANS_BLOCKS(sb) 0
|
|
#define EXT4_QUOTA_INIT_BLOCKS(sb) 0
|
|
#define EXT4_QUOTA_DEL_BLOCKS(sb) 0
|
|
#endif
|
|
#define EXT4_MAXQUOTAS_TRANS_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_TRANS_BLOCKS(sb))
|
|
#define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb))
|
|
#define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb))
|
|
|
|
int
|
|
ext4_mark_iloc_dirty(handle_t *handle,
|
|
struct inode *inode,
|
|
struct ext4_iloc *iloc);
|
|
|
|
/*
|
|
* On success, We end up with an outstanding reference count against
|
|
* iloc->bh. This _must_ be cleaned up later.
|
|
*/
|
|
|
|
int ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
|
|
struct ext4_iloc *iloc);
|
|
|
|
int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode);
|
|
|
|
/*
|
|
* Wrapper functions with which ext4 calls into JBD.
|
|
*/
|
|
void ext4_journal_abort_handle(const char *caller, unsigned int line,
|
|
const char *err_fn,
|
|
struct buffer_head *bh, handle_t *handle, int err);
|
|
|
|
int __ext4_journal_get_write_access(const char *where, unsigned int line,
|
|
handle_t *handle, struct buffer_head *bh);
|
|
|
|
int __ext4_forget(const char *where, unsigned int line, handle_t *handle,
|
|
int is_metadata, struct inode *inode,
|
|
struct buffer_head *bh, ext4_fsblk_t blocknr);
|
|
|
|
int __ext4_journal_get_create_access(const char *where, unsigned int line,
|
|
handle_t *handle, struct buffer_head *bh);
|
|
|
|
int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
|
|
handle_t *handle, struct inode *inode,
|
|
struct buffer_head *bh);
|
|
|
|
int __ext4_handle_dirty_super(const char *where, unsigned int line,
|
|
handle_t *handle, struct super_block *sb);
|
|
|
|
#define ext4_journal_get_write_access(handle, bh) \
|
|
__ext4_journal_get_write_access(__func__, __LINE__, (handle), (bh))
|
|
#define ext4_forget(handle, is_metadata, inode, bh, block_nr) \
|
|
__ext4_forget(__func__, __LINE__, (handle), (is_metadata), (inode), \
|
|
(bh), (block_nr))
|
|
#define ext4_journal_get_create_access(handle, bh) \
|
|
__ext4_journal_get_create_access(__func__, __LINE__, (handle), (bh))
|
|
#define ext4_handle_dirty_metadata(handle, inode, bh) \
|
|
__ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \
|
|
(bh))
|
|
#define ext4_handle_dirty_super(handle, sb) \
|
|
__ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb))
|
|
|
|
handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks);
|
|
int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle);
|
|
|
|
#define EXT4_NOJOURNAL_MAX_REF_COUNT ((unsigned long) 4096)
|
|
|
|
/* Note: Do not use this for NULL handles. This is only to determine if
|
|
* a properly allocated handle is using a journal or not. */
|
|
static inline int ext4_handle_valid(handle_t *handle)
|
|
{
|
|
if ((unsigned long)handle < EXT4_NOJOURNAL_MAX_REF_COUNT)
|
|
return 0;
|
|
return 1;
|
|
}
|
|
|
|
static inline void ext4_handle_sync(handle_t *handle)
|
|
{
|
|
if (ext4_handle_valid(handle))
|
|
handle->h_sync = 1;
|
|
}
|
|
|
|
static inline void ext4_handle_release_buffer(handle_t *handle,
|
|
struct buffer_head *bh)
|
|
{
|
|
if (ext4_handle_valid(handle))
|
|
jbd2_journal_release_buffer(handle, bh);
|
|
}
|
|
|
|
static inline int ext4_handle_is_aborted(handle_t *handle)
|
|
{
|
|
if (ext4_handle_valid(handle))
|
|
return is_handle_aborted(handle);
|
|
return 0;
|
|
}
|
|
|
|
static inline int ext4_handle_has_enough_credits(handle_t *handle, int needed)
|
|
{
|
|
if (ext4_handle_valid(handle) && handle->h_buffer_credits < needed)
|
|
return 0;
|
|
return 1;
|
|
}
|
|
|
|
static inline handle_t *ext4_journal_start(struct inode *inode, int nblocks)
|
|
{
|
|
return ext4_journal_start_sb(inode->i_sb, nblocks);
|
|
}
|
|
|
|
#define ext4_journal_stop(handle) \
|
|
__ext4_journal_stop(__func__, __LINE__, (handle))
|
|
|
|
static inline handle_t *ext4_journal_current_handle(void)
|
|
{
|
|
return journal_current_handle();
|
|
}
|
|
|
|
static inline int ext4_journal_extend(handle_t *handle, int nblocks)
|
|
{
|
|
if (ext4_handle_valid(handle))
|
|
return jbd2_journal_extend(handle, nblocks);
|
|
return 0;
|
|
}
|
|
|
|
static inline int ext4_journal_restart(handle_t *handle, int nblocks)
|
|
{
|
|
if (ext4_handle_valid(handle))
|
|
return jbd2_journal_restart(handle, nblocks);
|
|
return 0;
|
|
}
|
|
|
|
static inline int ext4_journal_blocks_per_page(struct inode *inode)
|
|
{
|
|
if (EXT4_JOURNAL(inode) != NULL)
|
|
return jbd2_journal_blocks_per_page(inode);
|
|
return 0;
|
|
}
|
|
|
|
static inline int ext4_journal_force_commit(journal_t *journal)
|
|
{
|
|
if (journal)
|
|
return jbd2_journal_force_commit(journal);
|
|
return 0;
|
|
}
|
|
|
|
static inline int ext4_jbd2_file_inode(handle_t *handle, struct inode *inode)
|
|
{
|
|
if (ext4_handle_valid(handle))
|
|
return jbd2_journal_file_inode(handle, EXT4_I(inode)->jinode);
|
|
return 0;
|
|
}
|
|
|
|
static inline void ext4_update_inode_fsync_trans(handle_t *handle,
|
|
struct inode *inode,
|
|
int datasync)
|
|
{
|
|
struct ext4_inode_info *ei = EXT4_I(inode);
|
|
|
|
if (ext4_handle_valid(handle)) {
|
|
ei->i_sync_tid = handle->h_transaction->t_tid;
|
|
if (datasync)
|
|
ei->i_datasync_tid = handle->h_transaction->t_tid;
|
|
}
|
|
}
|
|
|
|
/* super.c */
|
|
int ext4_force_commit(struct super_block *sb);
|
|
|
|
static inline int ext4_should_journal_data(struct inode *inode)
|
|
{
|
|
if (EXT4_JOURNAL(inode) == NULL)
|
|
return 0;
|
|
if (!S_ISREG(inode->i_mode))
|
|
return 1;
|
|
if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
|
|
return 1;
|
|
if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
|
|
return 1;
|
|
return 0;
|
|
}
|
|
|
|
static inline int ext4_should_order_data(struct inode *inode)
|
|
{
|
|
if (EXT4_JOURNAL(inode) == NULL)
|
|
return 0;
|
|
if (!S_ISREG(inode->i_mode))
|
|
return 0;
|
|
if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
|
|
return 0;
|
|
if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
|
|
return 1;
|
|
return 0;
|
|
}
|
|
|
|
static inline int ext4_should_writeback_data(struct inode *inode)
|
|
{
|
|
if (EXT4_JOURNAL(inode) == NULL)
|
|
return 1;
|
|
if (!S_ISREG(inode->i_mode))
|
|
return 0;
|
|
if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
|
|
return 0;
|
|
if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
|
|
return 1;
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* This function controls whether or not we should try to go down the
|
|
* dioread_nolock code paths, which makes it safe to avoid taking
|
|
* i_mutex for direct I/O reads. This only works for extent-based
|
|
* files, and it doesn't work if data journaling is enabled, since the
|
|
* dioread_nolock code uses b_private to pass information back to the
|
|
* I/O completion handler, and this conflicts with the jbd's use of
|
|
* b_private.
|
|
*/
|
|
static inline int ext4_should_dioread_nolock(struct inode *inode)
|
|
{
|
|
if (!test_opt(inode->i_sb, DIOREAD_NOLOCK))
|
|
return 0;
|
|
if (!S_ISREG(inode->i_mode))
|
|
return 0;
|
|
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
|
|
return 0;
|
|
if (ext4_should_journal_data(inode))
|
|
return 0;
|
|
return 1;
|
|
}
|
|
|
|
#endif /* _EXT4_JBD2_H */
|