2006-10-11 16:20:57 +08:00
|
|
|
/*
|
2008-04-30 06:13:32 +08:00
|
|
|
* ext4_jbd2.h
|
2006-10-11 16:20:57 +08:00
|
|
|
*
|
|
|
|
* 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.
|
|
|
|
*/
|
|
|
|
|
2008-04-30 06:13:32 +08:00
|
|
|
#ifndef _EXT4_JBD2_H
|
|
|
|
#define _EXT4_JBD2_H
|
2006-10-11 16:20:57 +08:00
|
|
|
|
|
|
|
#include <linux/fs.h>
|
2006-10-11 16:20:59 +08:00
|
|
|
#include <linux/jbd2.h>
|
2008-04-30 06:13:32 +08:00
|
|
|
#include "ext4.h"
|
2006-10-11 16:20:57 +08:00
|
|
|
|
|
|
|
#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
|
2006-10-11 16:21:03 +08:00
|
|
|
* block to complete the transaction.
|
|
|
|
*
|
2006-10-11 16:21:07 +08:00
|
|
|
* For extents-enabled fs we may have to allocate and modify up to
|
2013-04-10 00:39:26 +08:00
|
|
|
* 5 levels of tree, data block (for each of these we need bitmap + group
|
|
|
|
* summaries), root which is stored in the inode, sb
|
|
|
|
*/
|
2006-10-11 16:20:57 +08:00
|
|
|
|
2006-10-11 16:21:03 +08:00
|
|
|
#define EXT4_SINGLEDATA_TRANS_BLOCKS(sb) \
|
2015-10-18 04:18:43 +08:00
|
|
|
(ext4_has_feature_extents(sb) ? 20U : 8U)
|
2006-10-11 16:20:57 +08:00
|
|
|
|
|
|
|
/* 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. */
|
|
|
|
|
2006-10-11 16:21:03 +08:00
|
|
|
#define EXT4_DATA_TRANS_BLOCKS(sb) (EXT4_SINGLEDATA_TRANS_BLOCKS(sb) + \
|
2006-10-11 16:20:57 +08:00
|
|
|
EXT4_XATTR_TRANS_BLOCKS - 2 + \
|
2009-12-09 11:42:15 +08:00
|
|
|
EXT4_MAXQUOTAS_TRANS_BLOCKS(sb))
|
2006-10-11 16:20:57 +08:00
|
|
|
|
ext4: journal credits calulation cleanup and fix for non-extent writepage
When considering how many journal credits are needed for modifying a
chunk of data, we need to account for the super block, inode block,
quota blocks and xattr block, indirect/index blocks, also, group bitmap
and group descriptor blocks for new allocation (including data and
indirect/index blocks). There are many places in ext4 do the calculation
on their own and often missed one or two meta blocks, and often they
assume single block allocation, and did not considering the multile
chunk of allocation case.
This patch is trying to cleanup current journal credit code, provides
some common helper funtion to calculate the journal credits, to be used
for writepage, writepages, DIO, fallocate, migration, defrag, and for
both nonextent and extent files.
This patch modified the writepage/write_begin credit caculation for
nonextent files, to use the new helper function. It also fixed the
problem that writepage on nonextent files did not consider the case
blocksize <pagesize, thus could possibelly need multiple block
allocation in a single transaction.
Signed-off-by: Mingming Cao <cmm@us.ibm.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2008-08-20 10:16:07 +08:00
|
|
|
/*
|
|
|
|
* 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 + \
|
2009-12-09 11:42:15 +08:00
|
|
|
EXT4_MAXQUOTAS_TRANS_BLOCKS(sb))
|
ext4: journal credits calulation cleanup and fix for non-extent writepage
When considering how many journal credits are needed for modifying a
chunk of data, we need to account for the super block, inode block,
quota blocks and xattr block, indirect/index blocks, also, group bitmap
and group descriptor blocks for new allocation (including data and
indirect/index blocks). There are many places in ext4 do the calculation
on their own and often missed one or two meta blocks, and often they
assume single block allocation, and did not considering the multile
chunk of allocation case.
This patch is trying to cleanup current journal credit code, provides
some common helper funtion to calculate the journal credits, to be used
for writepage, writepages, DIO, fallocate, migration, defrag, and for
both nonextent and extent files.
This patch modified the writepage/write_begin credit caculation for
nonextent files, to use the new helper function. It also fixed the
problem that writepage on nonextent files did not consider the case
blocksize <pagesize, thus could possibelly need multiple block
allocation in a single transaction.
Signed-off-by: Mingming Cao <cmm@us.ibm.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2008-08-20 10:16:07 +08:00
|
|
|
|
2006-10-11 16:20:57 +08:00
|
|
|
/* 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
|
|
|
|
|
2017-06-22 09:09:57 +08:00
|
|
|
/*
|
|
|
|
* Number of credits needed if we need to insert an entry into a
|
|
|
|
* directory. For each new index block, we need 4 blocks (old index
|
|
|
|
* block, new index block, bitmap block, bg summary). For normal
|
|
|
|
* htree directories there are 2 levels; if the largedir feature
|
|
|
|
* enabled it's 3 levels.
|
|
|
|
*/
|
|
|
|
#define EXT4_INDEX_EXTRA_TRANS_BLOCKS 12U
|
2006-10-11 16:20:57 +08:00
|
|
|
|
|
|
|
#ifdef CONFIG_QUOTA
|
|
|
|
/* Amount of blocks needed for quota update - we know that the structure was
|
2011-04-05 03:33:39 +08:00
|
|
|
* allocated so we need to update only data block */
|
ext4: make quota as first class supported feature
This patch adds support for quotas as a first class feature in ext4;
which is to say, the quota files are stored in hidden inodes as file
system metadata, instead of as separate files visible in the file system
directory hierarchy.
It is based on the proposal at:
https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4
This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA
which, when turned on, enables quota accounting at mount time
iteself. Also, the quota inodes are stored in two additional superblock
fields. Some changes introduced by this patch that should be pointed
out are:
1) Two new ext4-superblock fields - s_usr_quota_inum and
s_grp_quota_inum for storing the quota inodes in use.
2) Default quota inodes are: inode#3 for tracking userquota and inode#4
for tracking group quota. The superblock fields can be set to use
other inodes as well.
3) If the QUOTA feature and corresponding quota inodes are set in
superblock, the quota usage tracking is turned on at mount time. On
'quotaon' ioctl, the quota limits enforcement is turned
on. 'quotaoff' ioctl turns off only the limits enforcement in this
case.
4) When QUOTA feature is in use, the quota mount options 'quota',
'usrquota', 'grpquota' are ignored by the kernel.
5) mke2fs or tune2fs can be used to set the QUOTA feature and initialize
quota inodes. The default reserved inodes will not be visible to user
as regular files.
6) The quota-tools will need to be modified to support hidden quota
files on ext4. E2fsprogs will also include support for creating and
fixing quota files.
7) Support is only for the new V2 quota file format.
Tested-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Johann Lombardi <johann@whamcloud.com>
Signed-off-by: Aditya Kali <adityakali@google.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2012-07-23 08:21:31 +08:00
|
|
|
#define EXT4_QUOTA_TRANS_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\
|
2015-10-18 04:18:43 +08:00
|
|
|
ext4_has_feature_quota(sb)) ? 1 : 0)
|
2006-10-11 16:20:57 +08:00
|
|
|
/* Amount of blocks needed for quota insert/delete - we do some block writes
|
|
|
|
* but inode, sb and group updates are done only once */
|
ext4: make quota as first class supported feature
This patch adds support for quotas as a first class feature in ext4;
which is to say, the quota files are stored in hidden inodes as file
system metadata, instead of as separate files visible in the file system
directory hierarchy.
It is based on the proposal at:
https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4
This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA
which, when turned on, enables quota accounting at mount time
iteself. Also, the quota inodes are stored in two additional superblock
fields. Some changes introduced by this patch that should be pointed
out are:
1) Two new ext4-superblock fields - s_usr_quota_inum and
s_grp_quota_inum for storing the quota inodes in use.
2) Default quota inodes are: inode#3 for tracking userquota and inode#4
for tracking group quota. The superblock fields can be set to use
other inodes as well.
3) If the QUOTA feature and corresponding quota inodes are set in
superblock, the quota usage tracking is turned on at mount time. On
'quotaon' ioctl, the quota limits enforcement is turned
on. 'quotaoff' ioctl turns off only the limits enforcement in this
case.
4) When QUOTA feature is in use, the quota mount options 'quota',
'usrquota', 'grpquota' are ignored by the kernel.
5) mke2fs or tune2fs can be used to set the QUOTA feature and initialize
quota inodes. The default reserved inodes will not be visible to user
as regular files.
6) The quota-tools will need to be modified to support hidden quota
files on ext4. E2fsprogs will also include support for creating and
fixing quota files.
7) Support is only for the new V2 quota file format.
Tested-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Johann Lombardi <johann@whamcloud.com>
Signed-off-by: Aditya Kali <adityakali@google.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2012-07-23 08:21:31 +08:00
|
|
|
#define EXT4_QUOTA_INIT_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\
|
2015-10-18 04:18:43 +08:00
|
|
|
ext4_has_feature_quota(sb)) ?\
|
ext4: make quota as first class supported feature
This patch adds support for quotas as a first class feature in ext4;
which is to say, the quota files are stored in hidden inodes as file
system metadata, instead of as separate files visible in the file system
directory hierarchy.
It is based on the proposal at:
https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4
This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA
which, when turned on, enables quota accounting at mount time
iteself. Also, the quota inodes are stored in two additional superblock
fields. Some changes introduced by this patch that should be pointed
out are:
1) Two new ext4-superblock fields - s_usr_quota_inum and
s_grp_quota_inum for storing the quota inodes in use.
2) Default quota inodes are: inode#3 for tracking userquota and inode#4
for tracking group quota. The superblock fields can be set to use
other inodes as well.
3) If the QUOTA feature and corresponding quota inodes are set in
superblock, the quota usage tracking is turned on at mount time. On
'quotaon' ioctl, the quota limits enforcement is turned
on. 'quotaoff' ioctl turns off only the limits enforcement in this
case.
4) When QUOTA feature is in use, the quota mount options 'quota',
'usrquota', 'grpquota' are ignored by the kernel.
5) mke2fs or tune2fs can be used to set the QUOTA feature and initialize
quota inodes. The default reserved inodes will not be visible to user
as regular files.
6) The quota-tools will need to be modified to support hidden quota
files on ext4. E2fsprogs will also include support for creating and
fixing quota files.
7) Support is only for the new V2 quota file format.
Tested-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Johann Lombardi <johann@whamcloud.com>
Signed-off-by: Aditya Kali <adityakali@google.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2012-07-23 08:21:31 +08:00
|
|
|
(DQUOT_INIT_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\
|
|
|
|
+3+DQUOT_INIT_REWRITE) : 0)
|
|
|
|
|
|
|
|
#define EXT4_QUOTA_DEL_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\
|
2015-10-18 04:18:43 +08:00
|
|
|
ext4_has_feature_quota(sb)) ?\
|
ext4: make quota as first class supported feature
This patch adds support for quotas as a first class feature in ext4;
which is to say, the quota files are stored in hidden inodes as file
system metadata, instead of as separate files visible in the file system
directory hierarchy.
It is based on the proposal at:
https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4
This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA
which, when turned on, enables quota accounting at mount time
iteself. Also, the quota inodes are stored in two additional superblock
fields. Some changes introduced by this patch that should be pointed
out are:
1) Two new ext4-superblock fields - s_usr_quota_inum and
s_grp_quota_inum for storing the quota inodes in use.
2) Default quota inodes are: inode#3 for tracking userquota and inode#4
for tracking group quota. The superblock fields can be set to use
other inodes as well.
3) If the QUOTA feature and corresponding quota inodes are set in
superblock, the quota usage tracking is turned on at mount time. On
'quotaon' ioctl, the quota limits enforcement is turned
on. 'quotaoff' ioctl turns off only the limits enforcement in this
case.
4) When QUOTA feature is in use, the quota mount options 'quota',
'usrquota', 'grpquota' are ignored by the kernel.
5) mke2fs or tune2fs can be used to set the QUOTA feature and initialize
quota inodes. The default reserved inodes will not be visible to user
as regular files.
6) The quota-tools will need to be modified to support hidden quota
files on ext4. E2fsprogs will also include support for creating and
fixing quota files.
7) Support is only for the new V2 quota file format.
Tested-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Johann Lombardi <johann@whamcloud.com>
Signed-off-by: Aditya Kali <adityakali@google.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2012-07-23 08:21:31 +08:00
|
|
|
(DQUOT_DEL_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\
|
|
|
|
+3+DQUOT_DEL_REWRITE) : 0)
|
2006-10-11 16:20:57 +08:00
|
|
|
#else
|
|
|
|
#define EXT4_QUOTA_TRANS_BLOCKS(sb) 0
|
|
|
|
#define EXT4_QUOTA_INIT_BLOCKS(sb) 0
|
|
|
|
#define EXT4_QUOTA_DEL_BLOCKS(sb) 0
|
|
|
|
#endif
|
2014-09-11 23:15:15 +08:00
|
|
|
#define EXT4_MAXQUOTAS_TRANS_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_TRANS_BLOCKS(sb))
|
|
|
|
#define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb))
|
|
|
|
#define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb))
|
2006-10-11 16:20:57 +08:00
|
|
|
|
2013-02-09 10:59:22 +08:00
|
|
|
/*
|
|
|
|
* Ext4 handle operation types -- for logging purposes
|
|
|
|
*/
|
|
|
|
#define EXT4_HT_MISC 0
|
|
|
|
#define EXT4_HT_INODE 1
|
|
|
|
#define EXT4_HT_WRITE_PAGE 2
|
|
|
|
#define EXT4_HT_MAP_BLOCKS 3
|
|
|
|
#define EXT4_HT_DIR 4
|
|
|
|
#define EXT4_HT_TRUNCATE 5
|
|
|
|
#define EXT4_HT_QUOTA 6
|
|
|
|
#define EXT4_HT_RESIZE 7
|
|
|
|
#define EXT4_HT_MIGRATE 8
|
|
|
|
#define EXT4_HT_MOVE_EXTENTS 9
|
|
|
|
#define EXT4_HT_XATTR 10
|
2013-06-05 01:21:11 +08:00
|
|
|
#define EXT4_HT_EXT_CONVERT 11
|
|
|
|
#define EXT4_HT_MAX 12
|
2013-02-09 10:59:22 +08:00
|
|
|
|
2012-02-21 06:53:02 +08:00
|
|
|
/**
|
|
|
|
* struct ext4_journal_cb_entry - Base structure for callback information.
|
|
|
|
*
|
|
|
|
* This struct is a 'seed' structure for a using with your own callback
|
|
|
|
* structs. If you are using callbacks you must allocate one of these
|
|
|
|
* or another struct of your own definition which has this struct
|
|
|
|
* as it's first element and pass it to ext4_journal_callback_add().
|
|
|
|
*/
|
|
|
|
struct ext4_journal_cb_entry {
|
|
|
|
/* list information for other callbacks attached to the same handle */
|
|
|
|
struct list_head jce_list;
|
|
|
|
|
|
|
|
/* Function to call with this callback structure */
|
|
|
|
void (*jce_func)(struct super_block *sb,
|
|
|
|
struct ext4_journal_cb_entry *jce, int error);
|
|
|
|
|
|
|
|
/* user data goes here */
|
|
|
|
};
|
|
|
|
|
|
|
|
/**
|
|
|
|
* ext4_journal_callback_add: add a function to call after transaction commit
|
|
|
|
* @handle: active journal transaction handle to register callback on
|
|
|
|
* @func: callback function to call after the transaction has committed:
|
|
|
|
* @sb: superblock of current filesystem for transaction
|
|
|
|
* @jce: returned journal callback data
|
|
|
|
* @rc: journal state at commit (0 = transaction committed properly)
|
|
|
|
* @jce: journal callback data (internal and function private data struct)
|
|
|
|
*
|
|
|
|
* The registered function will be called in the context of the journal thread
|
|
|
|
* after the transaction for which the handle was created has completed.
|
|
|
|
*
|
|
|
|
* No locks are held when the callback function is called, so it is safe to
|
|
|
|
* call blocking functions from within the callback, but the callback should
|
|
|
|
* not block or run for too long, or the filesystem will be blocked waiting for
|
|
|
|
* the next transaction to commit. No journaling functions can be used, or
|
|
|
|
* there is a risk of deadlock.
|
|
|
|
*
|
|
|
|
* There is no guaranteed calling order of multiple registered callbacks on
|
|
|
|
* the same transaction.
|
|
|
|
*/
|
2016-06-27 06:24:01 +08:00
|
|
|
static inline void _ext4_journal_callback_add(handle_t *handle,
|
|
|
|
struct ext4_journal_cb_entry *jce)
|
|
|
|
{
|
|
|
|
/* Add the jce to transaction's private list */
|
|
|
|
list_add_tail(&jce->jce_list, &handle->h_transaction->t_private_list);
|
|
|
|
}
|
|
|
|
|
2012-02-21 06:53:02 +08:00
|
|
|
static inline void ext4_journal_callback_add(handle_t *handle,
|
|
|
|
void (*func)(struct super_block *sb,
|
|
|
|
struct ext4_journal_cb_entry *jce,
|
|
|
|
int rc),
|
|
|
|
struct ext4_journal_cb_entry *jce)
|
|
|
|
{
|
|
|
|
struct ext4_sb_info *sbi =
|
|
|
|
EXT4_SB(handle->h_transaction->t_journal->j_private);
|
|
|
|
|
|
|
|
/* Add the jce to transaction's private list */
|
|
|
|
jce->jce_func = func;
|
|
|
|
spin_lock(&sbi->s_md_lock);
|
2016-06-27 06:24:01 +08:00
|
|
|
_ext4_journal_callback_add(handle, jce);
|
2012-02-21 06:53:02 +08:00
|
|
|
spin_unlock(&sbi->s_md_lock);
|
|
|
|
}
|
|
|
|
|
2016-06-27 06:24:01 +08:00
|
|
|
|
2012-02-21 06:53:02 +08:00
|
|
|
/**
|
|
|
|
* ext4_journal_callback_del: delete a registered callback
|
|
|
|
* @handle: active journal transaction handle on which callback was registered
|
|
|
|
* @jce: registered journal callback entry to unregister
|
2013-08-29 02:40:12 +08:00
|
|
|
* Return true if object was successfully removed
|
2012-02-21 06:53:02 +08:00
|
|
|
*/
|
2013-04-04 10:08:52 +08:00
|
|
|
static inline bool ext4_journal_callback_try_del(handle_t *handle,
|
2012-02-21 06:53:02 +08:00
|
|
|
struct ext4_journal_cb_entry *jce)
|
|
|
|
{
|
2013-04-04 10:08:52 +08:00
|
|
|
bool deleted;
|
2012-02-21 06:53:02 +08:00
|
|
|
struct ext4_sb_info *sbi =
|
|
|
|
EXT4_SB(handle->h_transaction->t_journal->j_private);
|
|
|
|
|
|
|
|
spin_lock(&sbi->s_md_lock);
|
2013-04-04 10:08:52 +08:00
|
|
|
deleted = !list_empty(&jce->jce_list);
|
2012-02-21 06:53:02 +08:00
|
|
|
list_del_init(&jce->jce_list);
|
|
|
|
spin_unlock(&sbi->s_md_lock);
|
2013-04-04 10:08:52 +08:00
|
|
|
return deleted;
|
2012-02-21 06:53:02 +08:00
|
|
|
}
|
|
|
|
|
2006-10-11 16:20:57 +08:00
|
|
|
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);
|
|
|
|
|
2017-08-06 13:00:49 +08:00
|
|
|
int ext4_expand_extra_isize(struct inode *inode,
|
|
|
|
unsigned int new_extra_isize,
|
|
|
|
struct ext4_iloc *iloc);
|
2006-10-11 16:20:57 +08:00
|
|
|
/*
|
2009-11-25 00:05:59 +08:00
|
|
|
* Wrapper functions with which ext4 calls into JBD.
|
2006-10-11 16:20:57 +08:00
|
|
|
*/
|
2010-06-30 02:53:24 +08:00
|
|
|
int __ext4_journal_get_write_access(const char *where, unsigned int line,
|
|
|
|
handle_t *handle, struct buffer_head *bh);
|
2006-10-11 16:20:57 +08:00
|
|
|
|
2010-06-30 02:53:24 +08:00
|
|
|
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);
|
2009-11-23 09:52:12 +08:00
|
|
|
|
2010-06-30 02:53:24 +08:00
|
|
|
int __ext4_journal_get_create_access(const char *where, unsigned int line,
|
2006-12-07 12:37:15 +08:00
|
|
|
handle_t *handle, struct buffer_head *bh);
|
2006-10-11 16:20:57 +08:00
|
|
|
|
2010-06-30 02:53:24 +08:00
|
|
|
int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
|
|
|
|
handle_t *handle, struct inode *inode,
|
|
|
|
struct buffer_head *bh);
|
2006-10-11 16:20:57 +08:00
|
|
|
|
2010-06-30 02:53:24 +08:00
|
|
|
int __ext4_handle_dirty_super(const char *where, unsigned int line,
|
2012-07-23 08:37:31 +08:00
|
|
|
handle_t *handle, struct super_block *sb);
|
2010-06-12 11:14:04 +08:00
|
|
|
|
2006-10-11 16:20:57 +08:00
|
|
|
#define ext4_journal_get_write_access(handle, bh) \
|
2010-06-30 02:53:24 +08:00
|
|
|
__ext4_journal_get_write_access(__func__, __LINE__, (handle), (bh))
|
2009-11-23 09:52:12 +08:00
|
|
|
#define ext4_forget(handle, is_metadata, inode, bh, block_nr) \
|
2010-06-30 02:53:24 +08:00
|
|
|
__ext4_forget(__func__, __LINE__, (handle), (is_metadata), (inode), \
|
|
|
|
(bh), (block_nr))
|
2006-10-11 16:20:57 +08:00
|
|
|
#define ext4_journal_get_create_access(handle, bh) \
|
2010-06-30 02:53:24 +08:00
|
|
|
__ext4_journal_get_create_access(__func__, __LINE__, (handle), (bh))
|
2009-01-07 13:06:22 +08:00
|
|
|
#define ext4_handle_dirty_metadata(handle, inode, bh) \
|
2010-06-30 02:53:24 +08:00
|
|
|
__ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \
|
|
|
|
(bh))
|
2010-06-12 11:14:04 +08:00
|
|
|
#define ext4_handle_dirty_super(handle, sb) \
|
2012-07-23 08:37:31 +08:00
|
|
|
__ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb))
|
2006-10-11 16:20:57 +08:00
|
|
|
|
2013-02-09 10:59:22 +08:00
|
|
|
handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line,
|
2013-06-05 00:37:50 +08:00
|
|
|
int type, int blocks, int rsv_blocks);
|
2010-07-27 23:56:40 +08:00
|
|
|
int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle);
|
2006-10-11 16:20:57 +08:00
|
|
|
|
2009-09-29 23:01:03 +08:00
|
|
|
#define EXT4_NOJOURNAL_MAX_REF_COUNT ((unsigned long) 4096)
|
2009-01-07 13:06:22 +08:00
|
|
|
|
2009-09-29 23:01:03 +08:00
|
|
|
/* Note: Do not use this for NULL handles. This is only to determine if
|
|
|
|
* a properly allocated handle is using a journal or not. */
|
2009-01-07 13:06:22 +08:00
|
|
|
static inline int ext4_handle_valid(handle_t *handle)
|
|
|
|
{
|
2009-09-29 23:01:03 +08:00
|
|
|
if ((unsigned long)handle < EXT4_NOJOURNAL_MAX_REF_COUNT)
|
2009-01-07 13:06:22 +08:00
|
|
|
return 0;
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void ext4_handle_sync(handle_t *handle)
|
|
|
|
{
|
|
|
|
if (ext4_handle_valid(handle))
|
|
|
|
handle->h_sync = 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2013-02-09 10:59:22 +08:00
|
|
|
#define ext4_journal_start_sb(sb, type, nblocks) \
|
2013-06-05 00:37:50 +08:00
|
|
|
__ext4_journal_start_sb((sb), __LINE__, (type), (nblocks), 0)
|
2013-02-09 10:59:22 +08:00
|
|
|
|
|
|
|
#define ext4_journal_start(inode, type, nblocks) \
|
2013-06-05 00:37:50 +08:00
|
|
|
__ext4_journal_start((inode), __LINE__, (type), (nblocks), 0)
|
|
|
|
|
|
|
|
#define ext4_journal_start_with_reserve(inode, type, blocks, rsv_blocks) \
|
|
|
|
__ext4_journal_start((inode), __LINE__, (type), (blocks), (rsv_blocks))
|
2013-02-09 10:59:22 +08:00
|
|
|
|
|
|
|
static inline handle_t *__ext4_journal_start(struct inode *inode,
|
|
|
|
unsigned int line, int type,
|
2013-06-05 00:37:50 +08:00
|
|
|
int blocks, int rsv_blocks)
|
2006-10-11 16:20:57 +08:00
|
|
|
{
|
2013-06-05 00:37:50 +08:00
|
|
|
return __ext4_journal_start_sb(inode->i_sb, line, type, blocks,
|
|
|
|
rsv_blocks);
|
2006-10-11 16:20:57 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
#define ext4_journal_stop(handle) \
|
2010-07-27 23:56:40 +08:00
|
|
|
__ext4_journal_stop(__func__, __LINE__, (handle))
|
2006-10-11 16:20:57 +08:00
|
|
|
|
2013-06-05 01:21:11 +08:00
|
|
|
#define ext4_journal_start_reserved(handle, type) \
|
2013-06-05 00:37:50 +08:00
|
|
|
__ext4_journal_start_reserved((handle), __LINE__, (type))
|
|
|
|
|
|
|
|
handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line,
|
|
|
|
int type);
|
|
|
|
|
|
|
|
static inline void ext4_journal_free_reserved(handle_t *handle)
|
|
|
|
{
|
|
|
|
if (ext4_handle_valid(handle))
|
|
|
|
jbd2_journal_free_reserved(handle);
|
|
|
|
}
|
|
|
|
|
2006-10-11 16:20:57 +08:00
|
|
|
static inline handle_t *ext4_journal_current_handle(void)
|
|
|
|
{
|
|
|
|
return journal_current_handle();
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline int ext4_journal_extend(handle_t *handle, int nblocks)
|
|
|
|
{
|
2009-01-07 13:06:22 +08:00
|
|
|
if (ext4_handle_valid(handle))
|
|
|
|
return jbd2_journal_extend(handle, nblocks);
|
|
|
|
return 0;
|
2006-10-11 16:20:57 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline int ext4_journal_restart(handle_t *handle, int nblocks)
|
|
|
|
{
|
2009-01-07 13:06:22 +08:00
|
|
|
if (ext4_handle_valid(handle))
|
|
|
|
return jbd2_journal_restart(handle, nblocks);
|
|
|
|
return 0;
|
2006-10-11 16:20:57 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline int ext4_journal_blocks_per_page(struct inode *inode)
|
|
|
|
{
|
2009-01-07 13:06:22 +08:00
|
|
|
if (EXT4_JOURNAL(inode) != NULL)
|
|
|
|
return jbd2_journal_blocks_per_page(inode);
|
|
|
|
return 0;
|
2006-10-11 16:20:57 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline int ext4_journal_force_commit(journal_t *journal)
|
|
|
|
{
|
2009-01-07 13:06:22 +08:00
|
|
|
if (journal)
|
|
|
|
return jbd2_journal_force_commit(journal);
|
|
|
|
return 0;
|
2006-10-11 16:20:57 +08:00
|
|
|
}
|
|
|
|
|
2016-04-24 12:56:08 +08:00
|
|
|
static inline int ext4_jbd2_inode_add_write(handle_t *handle,
|
|
|
|
struct inode *inode)
|
2008-07-12 07:27:31 +08:00
|
|
|
{
|
2009-01-07 13:06:22 +08:00
|
|
|
if (ext4_handle_valid(handle))
|
2016-04-24 12:56:07 +08:00
|
|
|
return jbd2_journal_inode_add_write(handle,
|
|
|
|
EXT4_I(inode)->jinode);
|
2009-01-07 13:06:22 +08:00
|
|
|
return 0;
|
2008-07-12 07:27:31 +08:00
|
|
|
}
|
|
|
|
|
2016-04-24 12:56:08 +08:00
|
|
|
static inline int ext4_jbd2_inode_add_wait(handle_t *handle,
|
|
|
|
struct inode *inode)
|
|
|
|
{
|
|
|
|
if (ext4_handle_valid(handle))
|
|
|
|
return jbd2_journal_inode_add_wait(handle,
|
|
|
|
EXT4_I(inode)->jinode);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2009-12-09 12:51:10 +08:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2006-10-11 16:20:57 +08:00
|
|
|
/* super.c */
|
|
|
|
int ext4_force_commit(struct super_block *sb);
|
|
|
|
|
2012-02-21 06:53:00 +08:00
|
|
|
/*
|
|
|
|
* Ext4 inode journal modes
|
|
|
|
*/
|
|
|
|
#define EXT4_INODE_JOURNAL_DATA_MODE 0x01 /* journal data mode */
|
|
|
|
#define EXT4_INODE_ORDERED_DATA_MODE 0x02 /* ordered data mode */
|
|
|
|
#define EXT4_INODE_WRITEBACK_DATA_MODE 0x04 /* writeback data mode */
|
|
|
|
|
|
|
|
static inline int ext4_inode_journal_mode(struct inode *inode)
|
2006-10-11 16:20:57 +08:00
|
|
|
{
|
2009-01-07 13:06:22 +08:00
|
|
|
if (EXT4_JOURNAL(inode) == NULL)
|
2012-02-21 06:53:00 +08:00
|
|
|
return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */
|
|
|
|
/* We do not support data journalling with delayed allocation */
|
|
|
|
if (!S_ISREG(inode->i_mode) ||
|
ext4: do not perform data journaling when data is encrypted
Currently data journalling is incompatible with encryption: enabling both
at the same time has never been supported by design, and would result in
unpredictable behavior. However, users are not precluded from turning on
both features simultaneously. This change programmatically replaces data
journaling for encrypted regular files with ordered data journaling mode.
Background:
Journaling encrypted data has not been supported because it operates on
buffer heads of the page in the page cache. Namely, when the commit
happens, which could be up to five seconds after caching, the commit
thread uses the buffer heads attached to the page to copy the contents of
the page to the journal. With encryption, it would have been required to
keep the bounce buffer with ciphertext for up to the aforementioned five
seconds, since the page cache can only hold plaintext and could not be
used for journaling. Alternatively, it would be required to setup the
journal to initiate a callback at the commit time to perform deferred
encryption - in this case, not only would the data have to be written
twice, but it would also have to be encrypted twice. This level of
complexity was not justified for a mode that in practice is very rarely
used because of the overhead from the data journalling.
Solution:
If data=journaled has been set as a mount option for a filesystem, or if
journaling is enabled on a regular file, do not perform journaling if the
file is also encrypted, instead fall back to the data=ordered mode for the
file.
Rationale:
The intent is to allow seamless and proper filesystem operation when
journaling and encryption have both been enabled, and have these two
conflicting features gracefully resolved by the filesystem.
Fixes: 4461471107b7
Signed-off-by: Sergey Karamov <skaramov@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@vger.kernel.org
2016-12-11 06:54:58 +08:00
|
|
|
test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
|
|
|
|
(ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
|
|
|
|
!test_opt(inode->i_sb, DELALLOC))) {
|
|
|
|
/* We do not support data journalling for encrypted data */
|
|
|
|
if (S_ISREG(inode->i_mode) && ext4_encrypted_inode(inode))
|
|
|
|
return EXT4_INODE_ORDERED_DATA_MODE; /* ordered */
|
2012-02-21 06:53:00 +08:00
|
|
|
return EXT4_INODE_JOURNAL_DATA_MODE; /* journal data */
|
ext4: do not perform data journaling when data is encrypted
Currently data journalling is incompatible with encryption: enabling both
at the same time has never been supported by design, and would result in
unpredictable behavior. However, users are not precluded from turning on
both features simultaneously. This change programmatically replaces data
journaling for encrypted regular files with ordered data journaling mode.
Background:
Journaling encrypted data has not been supported because it operates on
buffer heads of the page in the page cache. Namely, when the commit
happens, which could be up to five seconds after caching, the commit
thread uses the buffer heads attached to the page to copy the contents of
the page to the journal. With encryption, it would have been required to
keep the bounce buffer with ciphertext for up to the aforementioned five
seconds, since the page cache can only hold plaintext and could not be
used for journaling. Alternatively, it would be required to setup the
journal to initiate a callback at the commit time to perform deferred
encryption - in this case, not only would the data have to be written
twice, but it would also have to be encrypted twice. This level of
complexity was not justified for a mode that in practice is very rarely
used because of the overhead from the data journalling.
Solution:
If data=journaled has been set as a mount option for a filesystem, or if
journaling is enabled on a regular file, do not perform journaling if the
file is also encrypted, instead fall back to the data=ordered mode for the
file.
Rationale:
The intent is to allow seamless and proper filesystem operation when
journaling and encryption have both been enabled, and have these two
conflicting features gracefully resolved by the filesystem.
Fixes: 4461471107b7
Signed-off-by: Sergey Karamov <skaramov@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@vger.kernel.org
2016-12-11 06:54:58 +08:00
|
|
|
}
|
2012-02-21 06:53:00 +08:00
|
|
|
if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
|
|
|
|
return EXT4_INODE_ORDERED_DATA_MODE; /* ordered */
|
|
|
|
if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
|
|
|
|
return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */
|
ext4: do not perform data journaling when data is encrypted
Currently data journalling is incompatible with encryption: enabling both
at the same time has never been supported by design, and would result in
unpredictable behavior. However, users are not precluded from turning on
both features simultaneously. This change programmatically replaces data
journaling for encrypted regular files with ordered data journaling mode.
Background:
Journaling encrypted data has not been supported because it operates on
buffer heads of the page in the page cache. Namely, when the commit
happens, which could be up to five seconds after caching, the commit
thread uses the buffer heads attached to the page to copy the contents of
the page to the journal. With encryption, it would have been required to
keep the bounce buffer with ciphertext for up to the aforementioned five
seconds, since the page cache can only hold plaintext and could not be
used for journaling. Alternatively, it would be required to setup the
journal to initiate a callback at the commit time to perform deferred
encryption - in this case, not only would the data have to be written
twice, but it would also have to be encrypted twice. This level of
complexity was not justified for a mode that in practice is very rarely
used because of the overhead from the data journalling.
Solution:
If data=journaled has been set as a mount option for a filesystem, or if
journaling is enabled on a regular file, do not perform journaling if the
file is also encrypted, instead fall back to the data=ordered mode for the
file.
Rationale:
The intent is to allow seamless and proper filesystem operation when
journaling and encryption have both been enabled, and have these two
conflicting features gracefully resolved by the filesystem.
Fixes: 4461471107b7
Signed-off-by: Sergey Karamov <skaramov@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@vger.kernel.org
2016-12-11 06:54:58 +08:00
|
|
|
BUG();
|
2012-02-21 06:53:00 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline int ext4_should_journal_data(struct inode *inode)
|
|
|
|
{
|
|
|
|
return ext4_inode_journal_mode(inode) & EXT4_INODE_JOURNAL_DATA_MODE;
|
2006-10-11 16:20:57 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline int ext4_should_order_data(struct inode *inode)
|
|
|
|
{
|
2012-02-21 06:53:00 +08:00
|
|
|
return ext4_inode_journal_mode(inode) & EXT4_INODE_ORDERED_DATA_MODE;
|
2006-10-11 16:20:57 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline int ext4_should_writeback_data(struct inode *inode)
|
|
|
|
{
|
2012-02-21 06:53:00 +08:00
|
|
|
return ext4_inode_journal_mode(inode) & EXT4_INODE_WRITEBACK_DATA_MODE;
|
2006-10-11 16:20:57 +08:00
|
|
|
}
|
|
|
|
|
2010-03-05 05:14:02 +08:00
|
|
|
/*
|
|
|
|
* 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
|
2010-06-15 02:42:49 +08:00
|
|
|
* 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.
|
2010-03-05 05:14:02 +08:00
|
|
|
*/
|
|
|
|
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;
|
2010-05-17 10:00:00 +08:00
|
|
|
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
|
2010-03-05 05:14:02 +08:00
|
|
|
return 0;
|
|
|
|
if (ext4_should_journal_data(inode))
|
|
|
|
return 0;
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2008-04-30 06:13:32 +08:00
|
|
|
#endif /* _EXT4_JBD2_H */
|