2017-12-18 03:00:59 +00:00
|
|
|
// SPDX-License-Identifier: GPL-2.0+
|
2006-10-11 08:20:57 +00:00
|
|
|
/*
|
2006-10-11 08:20:59 +00:00
|
|
|
* linux/fs/jbd2/journal.c
|
2006-10-11 08:20:57 +00:00
|
|
|
*
|
|
|
|
* Written by Stephen C. Tweedie <sct@redhat.com>, 1998
|
|
|
|
*
|
|
|
|
* Copyright 1998 Red Hat corp --- All Rights Reserved
|
|
|
|
*
|
|
|
|
* Generic filesystem journal-writing code; part of the ext2fs
|
|
|
|
* journaling system.
|
|
|
|
*
|
|
|
|
* This file manages journals: areas of disk reserved for logging
|
|
|
|
* transactional updates. This includes the kernel journaling thread
|
|
|
|
* which is responsible for scheduling updates to the log.
|
|
|
|
*
|
|
|
|
* We do not actually manage the physical storage of the journal in this
|
|
|
|
* file: that is left to a per-journal policy function, which allows us
|
|
|
|
* to store the journal within a filesystem-specified area for ext2
|
|
|
|
* journaling (ext2 can use a reserved inode for storing the log).
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/time.h>
|
|
|
|
#include <linux/fs.h>
|
2006-10-11 08:20:59 +00:00
|
|
|
#include <linux/jbd2.h>
|
2006-10-11 08:20:57 +00:00
|
|
|
#include <linux/errno.h>
|
|
|
|
#include <linux/slab.h>
|
|
|
|
#include <linux/init.h>
|
|
|
|
#include <linux/mm.h>
|
2006-12-07 04:34:23 +00:00
|
|
|
#include <linux/freezer.h>
|
2006-10-11 08:20:57 +00:00
|
|
|
#include <linux/pagemap.h>
|
|
|
|
#include <linux/kthread.h>
|
|
|
|
#include <linux/poison.h>
|
|
|
|
#include <linux/proc_fs.h>
|
2008-01-29 04:58:27 +00:00
|
|
|
#include <linux/seq_file.h>
|
2009-01-12 03:34:01 +00:00
|
|
|
#include <linux/math64.h>
|
2009-06-17 15:47:48 +00:00
|
|
|
#include <linux/hash.h>
|
2009-12-07 15:36:20 +00:00
|
|
|
#include <linux/log2.h>
|
|
|
|
#include <linux/vmalloc.h>
|
2010-07-27 15:56:05 +00:00
|
|
|
#include <linux/backing-dev.h>
|
2010-10-28 01:25:12 +00:00
|
|
|
#include <linux/bitops.h>
|
2010-12-17 15:44:16 +00:00
|
|
|
#include <linux/ratelimit.h>
|
2017-05-03 21:53:26 +00:00
|
|
|
#include <linux/sched/mm.h>
|
2009-06-17 15:47:48 +00:00
|
|
|
|
|
|
|
#define CREATE_TRACE_POINTS
|
|
|
|
#include <trace/events/jbd2.h>
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2016-12-24 19:46:01 +00:00
|
|
|
#include <linux/uaccess.h>
|
2006-10-11 08:20:57 +00:00
|
|
|
#include <asm/page.h>
|
|
|
|
|
2013-02-09 21:29:20 +00:00
|
|
|
#ifdef CONFIG_JBD2_DEBUG
|
2022-06-08 11:23:49 +00:00
|
|
|
static ushort jbd2_journal_enable_debug __read_mostly;
|
2013-02-09 21:29:20 +00:00
|
|
|
|
|
|
|
module_param_named(jbd2_debug, jbd2_journal_enable_debug, ushort, 0644);
|
|
|
|
MODULE_PARM_DESC(jbd2_debug, "Debugging level for jbd2");
|
|
|
|
#endif
|
|
|
|
|
2006-10-11 08:20:59 +00:00
|
|
|
EXPORT_SYMBOL(jbd2_journal_extend);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_stop);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_lock_updates);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_unlock_updates);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_get_write_access);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_get_create_access);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_get_undo_access);
|
2008-09-11 22:35:47 +00:00
|
|
|
EXPORT_SYMBOL(jbd2_journal_set_triggers);
|
2006-10-11 08:20:59 +00:00
|
|
|
EXPORT_SYMBOL(jbd2_journal_dirty_metadata);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_forget);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_flush);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_revoke);
|
|
|
|
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_init_dev);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_init_inode);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_check_used_features);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_check_available_features);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_set_features);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_load);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_destroy);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_abort);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_errno);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_ack_err);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_clear_err);
|
|
|
|
EXPORT_SYMBOL(jbd2_log_wait_commit);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_start_commit);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_force_commit_nested);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_wipe);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_blocks_per_page);
|
2022-02-09 20:21:43 +00:00
|
|
|
EXPORT_SYMBOL(jbd2_journal_invalidate_folio);
|
2006-10-11 08:20:59 +00:00
|
|
|
EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_force_commit);
|
2019-06-20 21:24:56 +00:00
|
|
|
EXPORT_SYMBOL(jbd2_journal_inode_ranged_write);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_inode_ranged_wait);
|
2020-10-06 00:48:38 +00:00
|
|
|
EXPORT_SYMBOL(jbd2_journal_finish_inode_data_buffers);
|
2008-07-11 23:27:31 +00:00
|
|
|
EXPORT_SYMBOL(jbd2_journal_init_jbd_inode);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_release_jbd_inode);
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate);
|
2011-01-10 17:29:43 +00:00
|
|
|
EXPORT_SYMBOL(jbd2_inode_cache);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2009-12-07 15:36:20 +00:00
|
|
|
static int jbd2_journal_create_slab(size_t slab_size);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
jbd2: use a single printk for jbd_debug()
Since the jbd_debug() is implemented with two separate printk()
calls, it can lead to corrupted and misleading debug output like
the following (see lines marked with "*"):
[ 290.339362] (fs/jbd2/journal.c, 203): kjournald2: kjournald2 wakes
[ 290.339365] (fs/jbd2/journal.c, 155): kjournald2: commit_sequence=42103, commit_request=42104
[ 290.339369] (fs/jbd2/journal.c, 158): kjournald2: OK, requests differ
[* 290.339376] (fs/jbd2/journal.c, 648): jbd2_log_wait_commit:
[* 290.339379] (fs/jbd2/commit.c, 370): jbd2_journal_commit_transaction: JBD2: want 42104, j_commit_sequence=42103
[* 290.339382] JBD2: starting commit of transaction 42104
[ 290.339410] (fs/jbd2/revoke.c, 566): jbd2_journal_write_revoke_records: Wrote 0 revoke records
[ 290.376555] (fs/jbd2/commit.c, 1088): jbd2_journal_commit_transaction: JBD2: commit 42104 complete, head 42079
i.e. the debug output from log_wait_commit and journal_commit_transaction
have become interleaved. The output should have been:
(fs/jbd2/journal.c, 648): jbd2_log_wait_commit: JBD2: want 42104, j_commit_sequence=42103
(fs/jbd2/commit.c, 370): jbd2_journal_commit_transaction: JBD2: starting commit of transaction 42104
It is expected that this is not easy to replicate -- I was only able
to cause it on preempt-rt kernels, and even then only under heavy
I/O load.
Reported-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Suggested-by: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2013-06-13 03:04:04 +00:00
|
|
|
#ifdef CONFIG_JBD2_DEBUG
|
|
|
|
void __jbd2_debug(int level, const char *file, const char *func,
|
|
|
|
unsigned int line, const char *fmt, ...)
|
|
|
|
{
|
|
|
|
struct va_format vaf;
|
|
|
|
va_list args;
|
|
|
|
|
|
|
|
if (level > jbd2_journal_enable_debug)
|
|
|
|
return;
|
|
|
|
va_start(args, fmt);
|
|
|
|
vaf.fmt = fmt;
|
|
|
|
vaf.va = &args;
|
jbd2: remove bunch of empty lines with jbd2 debug
See following dmesg output with jbd2 debug enabled:
...(start_this_handle, 313): New handle 00000000c88d6ceb going live.
...(start_this_handle, 383): Handle 00000000c88d6ceb given 53 credits (total 53, free 32681)
...(do_get_write_access, 838): journal_head 0000000002856fc0, force_copy 0
...(jbd2_journal_cancel_revoke, 421): journal_head 0000000002856fc0, cancelling revoke
We have an extra line with every messages, this is a waste of buffer,
we can fix it by removing "\n" in the caller or remove it in
the __jbd2_debug(), i checked every jbd2_debug() passed '\n' explicitly.
To avoid more lines, let's remove it inside __jbd2_debug().
Signed-off-by: Wang Shilong <wshilong@ddn.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Reviewed-by: Jan Kara <jack@suse.cz>
2018-05-21 02:14:29 +00:00
|
|
|
printk(KERN_DEBUG "%s: (%s, %u): %pV", file, func, line, &vaf);
|
jbd2: use a single printk for jbd_debug()
Since the jbd_debug() is implemented with two separate printk()
calls, it can lead to corrupted and misleading debug output like
the following (see lines marked with "*"):
[ 290.339362] (fs/jbd2/journal.c, 203): kjournald2: kjournald2 wakes
[ 290.339365] (fs/jbd2/journal.c, 155): kjournald2: commit_sequence=42103, commit_request=42104
[ 290.339369] (fs/jbd2/journal.c, 158): kjournald2: OK, requests differ
[* 290.339376] (fs/jbd2/journal.c, 648): jbd2_log_wait_commit:
[* 290.339379] (fs/jbd2/commit.c, 370): jbd2_journal_commit_transaction: JBD2: want 42104, j_commit_sequence=42103
[* 290.339382] JBD2: starting commit of transaction 42104
[ 290.339410] (fs/jbd2/revoke.c, 566): jbd2_journal_write_revoke_records: Wrote 0 revoke records
[ 290.376555] (fs/jbd2/commit.c, 1088): jbd2_journal_commit_transaction: JBD2: commit 42104 complete, head 42079
i.e. the debug output from log_wait_commit and journal_commit_transaction
have become interleaved. The output should have been:
(fs/jbd2/journal.c, 648): jbd2_log_wait_commit: JBD2: want 42104, j_commit_sequence=42103
(fs/jbd2/commit.c, 370): jbd2_journal_commit_transaction: JBD2: starting commit of transaction 42104
It is expected that this is not easy to replicate -- I was only able
to cause it on preempt-rt kernels, and even then only under heavy
I/O load.
Reported-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Suggested-by: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2013-06-13 03:04:04 +00:00
|
|
|
va_end(args);
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2012-05-27 11:48:56 +00:00
|
|
|
/* Checksumming functions */
|
2013-08-28 18:59:58 +00:00
|
|
|
static __be32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb)
|
2012-05-27 12:08:22 +00:00
|
|
|
{
|
2013-08-28 18:59:58 +00:00
|
|
|
__u32 csum;
|
|
|
|
__be32 old_csum;
|
2012-05-27 12:08:22 +00:00
|
|
|
|
|
|
|
old_csum = sb->s_checksum;
|
|
|
|
sb->s_checksum = 0;
|
|
|
|
csum = jbd2_chksum(j, ~0, (char *)sb, sizeof(journal_superblock_t));
|
|
|
|
sb->s_checksum = old_csum;
|
|
|
|
|
|
|
|
return cpu_to_be32(csum);
|
|
|
|
}
|
|
|
|
|
2006-10-11 08:20:57 +00:00
|
|
|
/*
|
|
|
|
* Helper function used to manage commit timeouts
|
|
|
|
*/
|
|
|
|
|
2017-10-18 16:40:28 +00:00
|
|
|
static void commit_timeout(struct timer_list *t)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
2017-10-18 16:40:28 +00:00
|
|
|
journal_t *journal = from_timer(journal, t, j_commit_timer);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2017-10-18 16:40:28 +00:00
|
|
|
wake_up_process(journal->j_task);
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2006-10-11 08:20:59 +00:00
|
|
|
* kjournald2: The main thread function used to manage a logging device
|
2006-10-11 08:20:57 +00:00
|
|
|
* journal.
|
|
|
|
*
|
|
|
|
* This kernel thread is responsible for two things:
|
|
|
|
*
|
|
|
|
* 1) COMMIT: Every so often we need to commit the current state of the
|
|
|
|
* filesystem to disk. The journal thread is responsible for writing
|
2020-10-15 20:37:56 +00:00
|
|
|
* all of the metadata buffers to disk. If a fast commit is ongoing
|
|
|
|
* journal thread waits until it's done and then continues from
|
|
|
|
* there on.
|
2006-10-11 08:20:57 +00:00
|
|
|
*
|
|
|
|
* 2) CHECKPOINT: We cannot reuse a used section of the log file until all
|
|
|
|
* of the data in that part of the log has been rewritten elsewhere on
|
|
|
|
* the disk. Flushing these old buffers to reclaim space in the log is
|
|
|
|
* known as checkpointing, and this thread is responsible for that job.
|
|
|
|
*/
|
|
|
|
|
2006-10-11 08:20:59 +00:00
|
|
|
static int kjournald2(void *arg)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
|
|
|
journal_t *journal = arg;
|
|
|
|
transaction_t *transaction;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Set up an interval timer which can be used to trigger a commit wakeup
|
|
|
|
* after the commit interval expires
|
|
|
|
*/
|
2017-10-18 16:40:28 +00:00
|
|
|
timer_setup(&journal->j_commit_timer, commit_timeout, 0);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2012-02-03 08:59:41 +00:00
|
|
|
set_freezable();
|
|
|
|
|
2006-10-11 08:20:57 +00:00
|
|
|
/* Record that the journal thread is running */
|
|
|
|
journal->j_task = current;
|
|
|
|
wake_up(&journal->j_wait_done_commit);
|
|
|
|
|
2017-05-03 21:53:26 +00:00
|
|
|
/*
|
|
|
|
* Make sure that no allocations from this kernel thread will ever
|
|
|
|
* recurse to the fs layer because we are responsible for the
|
|
|
|
* transaction commit and any fs involvement might get stuck waiting for
|
|
|
|
* the trasn. commit.
|
|
|
|
*/
|
|
|
|
memalloc_nofs_save();
|
|
|
|
|
2006-10-11 08:20:57 +00:00
|
|
|
/*
|
|
|
|
* And now, wait forever for commit wakeup events.
|
|
|
|
*/
|
2010-08-04 01:35:12 +00:00
|
|
|
write_lock(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
loop:
|
2006-10-11 08:20:59 +00:00
|
|
|
if (journal->j_flags & JBD2_UNMOUNT)
|
2006-10-11 08:20:57 +00:00
|
|
|
goto end_loop;
|
|
|
|
|
2022-06-08 11:23:48 +00:00
|
|
|
jbd2_debug(1, "commit_sequence=%u, commit_request=%u\n",
|
2006-10-11 08:20:57 +00:00
|
|
|
journal->j_commit_sequence, journal->j_commit_request);
|
|
|
|
|
|
|
|
if (journal->j_commit_sequence != journal->j_commit_request) {
|
2022-06-08 11:23:48 +00:00
|
|
|
jbd2_debug(1, "OK, requests differ\n");
|
2010-08-04 01:35:12 +00:00
|
|
|
write_unlock(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
del_timer_sync(&journal->j_commit_timer);
|
2006-10-11 08:20:59 +00:00
|
|
|
jbd2_journal_commit_transaction(journal);
|
2010-08-04 01:35:12 +00:00
|
|
|
write_lock(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
goto loop;
|
|
|
|
}
|
|
|
|
|
|
|
|
wake_up(&journal->j_wait_done_commit);
|
|
|
|
if (freezing(current)) {
|
|
|
|
/*
|
|
|
|
* The simpler the better. Flushing journal isn't a
|
|
|
|
* good idea, because that depends on threads that may
|
|
|
|
* be already stopped.
|
|
|
|
*/
|
2022-06-08 11:23:48 +00:00
|
|
|
jbd2_debug(1, "Now suspending kjournald2\n");
|
2010-08-04 01:35:12 +00:00
|
|
|
write_unlock(&journal->j_state_lock);
|
2011-11-21 20:32:22 +00:00
|
|
|
try_to_freeze();
|
2010-08-04 01:35:12 +00:00
|
|
|
write_lock(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
} else {
|
|
|
|
/*
|
|
|
|
* We assume on resume that commits are already there,
|
|
|
|
* so we don't sleep
|
|
|
|
*/
|
|
|
|
DEFINE_WAIT(wait);
|
|
|
|
|
|
|
|
prepare_to_wait(&journal->j_wait_commit, &wait,
|
|
|
|
TASK_INTERRUPTIBLE);
|
|
|
|
transaction = journal->j_running_transaction;
|
2024-05-14 11:24:38 +00:00
|
|
|
if (transaction == NULL ||
|
|
|
|
time_before(jiffies, transaction->t_expires)) {
|
2010-08-04 01:35:12 +00:00
|
|
|
write_unlock(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
schedule();
|
2010-08-04 01:35:12 +00:00
|
|
|
write_lock(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
finish_wait(&journal->j_wait_commit, &wait);
|
|
|
|
}
|
|
|
|
|
2022-06-08 11:23:48 +00:00
|
|
|
jbd2_debug(1, "kjournald2 wakes\n");
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Were we woken up by a commit wakeup event?
|
|
|
|
*/
|
|
|
|
transaction = journal->j_running_transaction;
|
|
|
|
if (transaction && time_after_eq(jiffies, transaction->t_expires)) {
|
|
|
|
journal->j_commit_request = transaction->t_tid;
|
2022-06-08 11:23:48 +00:00
|
|
|
jbd2_debug(1, "woke because of timeout\n");
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
goto loop;
|
|
|
|
|
|
|
|
end_loop:
|
|
|
|
del_timer_sync(&journal->j_commit_timer);
|
|
|
|
journal->j_task = NULL;
|
|
|
|
wake_up(&journal->j_wait_done_commit);
|
2022-06-08 11:23:48 +00:00
|
|
|
jbd2_debug(1, "Journal thread exiting.\n");
|
2017-02-02 01:49:35 +00:00
|
|
|
write_unlock(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2007-05-08 07:30:42 +00:00
|
|
|
static int jbd2_journal_start_thread(journal_t *journal)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
2007-05-08 07:30:42 +00:00
|
|
|
struct task_struct *t;
|
|
|
|
|
2009-09-29 19:51:30 +00:00
|
|
|
t = kthread_run(kjournald2, journal, "jbd2/%s",
|
|
|
|
journal->j_devname);
|
2007-05-08 07:30:42 +00:00
|
|
|
if (IS_ERR(t))
|
|
|
|
return PTR_ERR(t);
|
|
|
|
|
2008-03-29 03:07:18 +00:00
|
|
|
wait_event(journal->j_wait_done_commit, journal->j_task != NULL);
|
2007-05-08 07:30:42 +00:00
|
|
|
return 0;
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static void journal_kill_thread(journal_t *journal)
|
|
|
|
{
|
2010-08-04 01:35:12 +00:00
|
|
|
write_lock(&journal->j_state_lock);
|
2006-10-11 08:20:59 +00:00
|
|
|
journal->j_flags |= JBD2_UNMOUNT;
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
while (journal->j_task) {
|
2010-08-04 01:35:12 +00:00
|
|
|
write_unlock(&journal->j_state_lock);
|
2014-03-09 00:11:36 +00:00
|
|
|
wake_up(&journal->j_wait_commit);
|
2008-03-29 03:07:18 +00:00
|
|
|
wait_event(journal->j_wait_done_commit, journal->j_task == NULL);
|
2010-08-04 01:35:12 +00:00
|
|
|
write_lock(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
2010-08-04 01:35:12 +00:00
|
|
|
write_unlock(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2006-10-11 08:20:59 +00:00
|
|
|
* jbd2_journal_write_metadata_buffer: write a metadata buffer to the journal.
|
2006-10-11 08:20:57 +00:00
|
|
|
*
|
|
|
|
* Writes a metadata buffer to a given disk block. The actual IO is not
|
|
|
|
* performed but a new buffer_head is constructed which labels the data
|
|
|
|
* to be written with the correct destination disk block.
|
|
|
|
*
|
|
|
|
* Any magic-number escaping which needs to be done will cause a
|
|
|
|
* copy-out here. If the buffer happens to start with the
|
2006-10-11 08:20:59 +00:00
|
|
|
* JBD2_MAGIC_NUMBER, then we can't write it to the log directly: the
|
2006-10-11 08:20:57 +00:00
|
|
|
* magic number is only written to the log for descripter blocks. In
|
|
|
|
* this case, we copy the data and replace the first word with 0, and we
|
|
|
|
* return a result code which indicates that this buffer needs to be
|
|
|
|
* marked as an escaped buffer in the corresponding log descriptor
|
|
|
|
* block. The missing word can then be restored when the block is read
|
|
|
|
* during recovery.
|
|
|
|
*
|
|
|
|
* If the source buffer has already been modified by a new transaction
|
|
|
|
* since we took the last commit snapshot, we use the frozen copy of
|
2013-06-04 16:01:45 +00:00
|
|
|
* that data for IO. If we end up using the existing buffer_head's data
|
|
|
|
* for the write, then we have to make sure nobody modifies it while the
|
|
|
|
* IO is in progress. do_get_write_access() handles this.
|
2006-10-11 08:20:57 +00:00
|
|
|
*
|
2013-06-04 16:01:45 +00:00
|
|
|
* The function returns a pointer to the buffer_head to be used for IO.
|
2019-05-30 19:08:34 +00:00
|
|
|
*
|
2006-10-11 08:20:57 +00:00
|
|
|
*
|
|
|
|
* Return value:
|
|
|
|
* <0: Error
|
2024-05-14 11:24:31 +00:00
|
|
|
* =0: Finished OK without escape
|
|
|
|
* =1: Finished OK with escape
|
2006-10-11 08:20:57 +00:00
|
|
|
*/
|
|
|
|
|
2006-10-11 08:20:59 +00:00
|
|
|
int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
|
2006-10-11 08:20:57 +00:00
|
|
|
struct journal_head *jh_in,
|
2013-06-04 16:01:45 +00:00
|
|
|
struct buffer_head **bh_out,
|
|
|
|
sector_t blocknr)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
|
|
|
int done_copy_out = 0;
|
|
|
|
int do_escape = 0;
|
|
|
|
char *mapped_data;
|
|
|
|
struct buffer_head *new_bh;
|
2023-07-13 03:55:11 +00:00
|
|
|
struct folio *new_folio;
|
2006-10-11 08:20:57 +00:00
|
|
|
unsigned int new_offset;
|
|
|
|
struct buffer_head *bh_in = jh2bh(jh_in);
|
2009-07-13 21:55:35 +00:00
|
|
|
journal_t *journal = transaction->t_journal;
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* The buffer really shouldn't be locked: only the current committing
|
|
|
|
* transaction is allowed to write it, so nobody else is allowed
|
|
|
|
* to do any IO.
|
|
|
|
*
|
|
|
|
* akpm: except if we're journalling data, and write() output is
|
|
|
|
* also part of a shared mapping, and another thread has
|
|
|
|
* decided to launch a writepage() against this buffer.
|
|
|
|
*/
|
|
|
|
J_ASSERT_BH(bh_in, buffer_jbddirty(bh_in));
|
|
|
|
|
2015-06-08 14:53:10 +00:00
|
|
|
new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL);
|
2010-07-27 15:56:05 +00:00
|
|
|
|
2009-07-13 21:55:35 +00:00
|
|
|
/* keep subsequent assertions sane */
|
|
|
|
atomic_set(&new_bh->b_count, 1);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2019-08-09 12:42:32 +00:00
|
|
|
spin_lock(&jh_in->b_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
/*
|
|
|
|
* If a new transaction has already done a buffer copy-out, then
|
|
|
|
* we use that version of the data for the commit.
|
|
|
|
*/
|
|
|
|
if (jh_in->b_frozen_data) {
|
|
|
|
done_copy_out = 1;
|
2023-07-13 03:55:11 +00:00
|
|
|
new_folio = virt_to_folio(jh_in->b_frozen_data);
|
|
|
|
new_offset = offset_in_folio(new_folio, jh_in->b_frozen_data);
|
2006-10-11 08:20:57 +00:00
|
|
|
} else {
|
2024-05-14 11:24:35 +00:00
|
|
|
new_folio = bh_in->b_folio;
|
|
|
|
new_offset = offset_in_folio(new_folio, bh_in->b_data);
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
2023-07-13 03:55:11 +00:00
|
|
|
mapped_data = kmap_local_folio(new_folio, new_offset);
|
2008-09-11 22:35:47 +00:00
|
|
|
/*
|
2010-07-14 05:56:33 +00:00
|
|
|
* Fire data frozen trigger if data already wasn't frozen. Do this
|
|
|
|
* before checking for escaping, as the trigger may modify the magic
|
|
|
|
* offset. If a copy-out happens afterwards, it will have the correct
|
|
|
|
* data in the buffer.
|
2008-09-11 22:35:47 +00:00
|
|
|
*/
|
2010-07-14 05:56:33 +00:00
|
|
|
if (!done_copy_out)
|
2023-07-13 03:55:11 +00:00
|
|
|
jbd2_buffer_frozen_trigger(jh_in, mapped_data,
|
2010-07-14 05:56:33 +00:00
|
|
|
jh_in->b_triggers);
|
2008-09-11 22:35:47 +00:00
|
|
|
|
2006-10-11 08:20:57 +00:00
|
|
|
/*
|
|
|
|
* Check for escaping
|
|
|
|
*/
|
2024-05-14 11:24:32 +00:00
|
|
|
if (*((__be32 *)mapped_data) == cpu_to_be32(JBD2_MAGIC_NUMBER))
|
2006-10-11 08:20:57 +00:00
|
|
|
do_escape = 1;
|
2023-07-13 03:55:11 +00:00
|
|
|
kunmap_local(mapped_data);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Do we need to do a data copy?
|
|
|
|
*/
|
2024-05-14 11:24:32 +00:00
|
|
|
if (do_escape && !done_copy_out) {
|
2006-10-11 08:20:57 +00:00
|
|
|
char *tmp;
|
|
|
|
|
2019-08-09 12:42:32 +00:00
|
|
|
spin_unlock(&jh_in->b_state_lock);
|
2007-10-16 22:38:25 +00:00
|
|
|
tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS);
|
2009-12-01 14:04:42 +00:00
|
|
|
if (!tmp) {
|
2013-06-04 16:01:45 +00:00
|
|
|
brelse(new_bh);
|
2024-05-14 11:24:30 +00:00
|
|
|
free_buffer_head(new_bh);
|
2009-12-01 14:04:42 +00:00
|
|
|
return -ENOMEM;
|
|
|
|
}
|
2019-08-09 12:42:32 +00:00
|
|
|
spin_lock(&jh_in->b_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
if (jh_in->b_frozen_data) {
|
2007-10-16 22:38:25 +00:00
|
|
|
jbd2_free(tmp, bh_in->b_size);
|
2024-05-14 11:24:33 +00:00
|
|
|
goto copy_done;
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
jh_in->b_frozen_data = tmp;
|
2023-07-13 03:55:11 +00:00
|
|
|
memcpy_from_folio(tmp, new_folio, new_offset, bh_in->b_size);
|
2008-09-11 22:35:47 +00:00
|
|
|
/*
|
|
|
|
* This isn't strictly necessary, as we're using frozen
|
|
|
|
* data for the escaping, but it keeps consistency with
|
|
|
|
* b_frozen_data usage.
|
|
|
|
*/
|
|
|
|
jh_in->b_frozen_triggers = jh_in->b_triggers;
|
2024-05-14 11:24:33 +00:00
|
|
|
|
|
|
|
copy_done:
|
|
|
|
new_folio = virt_to_folio(jh_in->b_frozen_data);
|
|
|
|
new_offset = offset_in_folio(new_folio, jh_in->b_frozen_data);
|
|
|
|
done_copy_out = 1;
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Did we need to do an escaping? Now we've done all the
|
|
|
|
* copying, we can finally do so.
|
2024-05-14 11:24:34 +00:00
|
|
|
* b_frozen_data is from jbd2_alloc() which always provides an
|
|
|
|
* address from the direct kernels mapping.
|
2006-10-11 08:20:57 +00:00
|
|
|
*/
|
2024-05-14 11:24:34 +00:00
|
|
|
if (do_escape)
|
|
|
|
*((unsigned int *)jh_in->b_frozen_data) = 0;
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2023-07-13 03:55:11 +00:00
|
|
|
folio_set_bh(new_bh, new_folio, new_offset);
|
2013-06-04 16:01:45 +00:00
|
|
|
new_bh->b_size = bh_in->b_size;
|
|
|
|
new_bh->b_bdev = journal->j_dev;
|
2006-10-11 08:20:57 +00:00
|
|
|
new_bh->b_blocknr = blocknr;
|
2013-06-04 16:08:56 +00:00
|
|
|
new_bh->b_private = bh_in;
|
2006-10-11 08:20:57 +00:00
|
|
|
set_buffer_mapped(new_bh);
|
|
|
|
set_buffer_dirty(new_bh);
|
|
|
|
|
2013-06-04 16:01:45 +00:00
|
|
|
*bh_out = new_bh;
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* The to-be-written buffer needs to get moved to the io queue,
|
|
|
|
* and the original buffer whose contents we are shadowing or
|
|
|
|
* copying is moved to the transaction's shadow queue.
|
|
|
|
*/
|
|
|
|
JBUFFER_TRACE(jh_in, "file as BJ_Shadow");
|
2009-07-13 21:55:35 +00:00
|
|
|
spin_lock(&journal->j_list_lock);
|
|
|
|
__jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow);
|
|
|
|
spin_unlock(&journal->j_list_lock);
|
2013-06-04 16:08:56 +00:00
|
|
|
set_buffer_shadow(bh_in);
|
2019-08-09 12:42:32 +00:00
|
|
|
spin_unlock(&jh_in->b_state_lock);
|
2009-07-13 21:55:35 +00:00
|
|
|
|
2024-05-14 11:24:31 +00:00
|
|
|
return do_escape;
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Allocation code for the journal file. Manage the space left in the
|
|
|
|
* journal, so that we can begin checkpointing when appropriate.
|
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
2011-02-12 13:18:24 +00:00
|
|
|
* Called with j_state_lock locked for writing.
|
|
|
|
* Returns true if a transaction commit was started.
|
2006-10-11 08:20:57 +00:00
|
|
|
*/
|
2022-06-08 11:23:50 +00:00
|
|
|
static int __jbd2_log_start_commit(journal_t *journal, tid_t target)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
2013-01-30 05:39:28 +00:00
|
|
|
/* Return if the txn has already requested to be committed */
|
|
|
|
if (journal->j_commit_request == target)
|
|
|
|
return 0;
|
|
|
|
|
2006-10-11 08:20:57 +00:00
|
|
|
/*
|
2011-05-01 22:16:26 +00:00
|
|
|
* The only transaction we can possibly wait upon is the
|
|
|
|
* currently running transaction (if it exists). Otherwise,
|
|
|
|
* the target tid must be an old one.
|
2006-10-11 08:20:57 +00:00
|
|
|
*/
|
2011-05-01 22:16:26 +00:00
|
|
|
if (journal->j_running_transaction &&
|
|
|
|
journal->j_running_transaction->t_tid == target) {
|
2006-10-11 08:20:57 +00:00
|
|
|
/*
|
2010-10-16 13:19:14 +00:00
|
|
|
* We want a new commit: OK, mark the request and wakeup the
|
2006-10-11 08:20:57 +00:00
|
|
|
* commit thread. We do _not_ do the commit ourselves.
|
|
|
|
*/
|
|
|
|
|
|
|
|
journal->j_commit_request = target;
|
2022-06-08 11:23:48 +00:00
|
|
|
jbd2_debug(1, "JBD2: requesting commit %u/%u\n",
|
2006-10-11 08:20:57 +00:00
|
|
|
journal->j_commit_request,
|
|
|
|
journal->j_commit_sequence);
|
2013-02-07 03:30:23 +00:00
|
|
|
journal->j_running_transaction->t_requested = jiffies;
|
2006-10-11 08:20:57 +00:00
|
|
|
wake_up(&journal->j_wait_commit);
|
|
|
|
return 1;
|
2011-05-01 22:16:26 +00:00
|
|
|
} else if (!tid_geq(journal->j_commit_request, target))
|
|
|
|
/* This should never happen, but if it does, preserve
|
|
|
|
the evidence before kjournald goes into a loop and
|
|
|
|
increments j_commit_sequence beyond all recognition. */
|
2011-11-01 23:09:18 +00:00
|
|
|
WARN_ONCE(1, "JBD2: bad log_start_commit: %u %u %u %u\n",
|
2011-05-08 23:37:54 +00:00
|
|
|
journal->j_commit_request,
|
|
|
|
journal->j_commit_sequence,
|
2019-05-30 19:08:34 +00:00
|
|
|
target, journal->j_running_transaction ?
|
2011-05-08 23:37:54 +00:00
|
|
|
journal->j_running_transaction->t_tid : 0);
|
2006-10-11 08:20:57 +00:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2006-10-11 08:20:59 +00:00
|
|
|
int jbd2_log_start_commit(journal_t *journal, tid_t tid)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
|
2010-08-04 01:35:12 +00:00
|
|
|
write_lock(&journal->j_state_lock);
|
2006-10-11 08:20:59 +00:00
|
|
|
ret = __jbd2_log_start_commit(journal, tid);
|
2010-08-04 01:35:12 +00:00
|
|
|
write_unlock(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2013-06-13 02:24:07 +00:00
|
|
|
* Force and wait any uncommitted transactions. We can only force the running
|
|
|
|
* transaction if we don't have an active handle, otherwise, we will deadlock.
|
|
|
|
* Returns: <0 in case of error,
|
|
|
|
* 0 if nothing to commit,
|
|
|
|
* 1 if transaction was successfully committed.
|
2006-10-11 08:20:57 +00:00
|
|
|
*/
|
2013-06-13 02:24:07 +00:00
|
|
|
static int __jbd2_journal_force_commit(journal_t *journal)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
|
|
|
transaction_t *transaction = NULL;
|
|
|
|
tid_t tid;
|
2013-06-13 02:24:07 +00:00
|
|
|
int need_to_start = 0, ret = 0;
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2010-08-04 01:35:12 +00:00
|
|
|
read_lock(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
if (journal->j_running_transaction && !current->journal_info) {
|
|
|
|
transaction = journal->j_running_transaction;
|
2011-02-12 13:18:24 +00:00
|
|
|
if (!tid_geq(journal->j_commit_request, transaction->t_tid))
|
|
|
|
need_to_start = 1;
|
2006-10-11 08:20:57 +00:00
|
|
|
} else if (journal->j_committing_transaction)
|
|
|
|
transaction = journal->j_committing_transaction;
|
|
|
|
|
|
|
|
if (!transaction) {
|
2013-06-13 02:24:07 +00:00
|
|
|
/* Nothing to commit */
|
2010-08-04 01:35:12 +00:00
|
|
|
read_unlock(&journal->j_state_lock);
|
2013-06-13 02:24:07 +00:00
|
|
|
return 0;
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
tid = transaction->t_tid;
|
2010-08-04 01:35:12 +00:00
|
|
|
read_unlock(&journal->j_state_lock);
|
2011-02-12 13:18:24 +00:00
|
|
|
if (need_to_start)
|
|
|
|
jbd2_log_start_commit(journal, tid);
|
2013-06-13 02:24:07 +00:00
|
|
|
ret = jbd2_log_wait_commit(journal, tid);
|
|
|
|
if (!ret)
|
|
|
|
ret = 1;
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
2020-11-16 10:18:08 +00:00
|
|
|
* jbd2_journal_force_commit_nested - Force and wait upon a commit if the
|
|
|
|
* calling process is not within transaction.
|
2013-06-13 02:24:07 +00:00
|
|
|
*
|
|
|
|
* @journal: journal to force
|
|
|
|
* Returns true if progress was made.
|
2020-11-16 10:18:08 +00:00
|
|
|
*
|
|
|
|
* This is used for forcing out undo-protected data which contains
|
|
|
|
* bitmaps, when the fs is running out of space.
|
2013-06-13 02:24:07 +00:00
|
|
|
*/
|
|
|
|
int jbd2_journal_force_commit_nested(journal_t *journal)
|
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
ret = __jbd2_journal_force_commit(journal);
|
|
|
|
return ret > 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
2020-11-16 10:18:08 +00:00
|
|
|
* jbd2_journal_force_commit() - force any uncommitted transactions
|
2013-06-13 02:24:07 +00:00
|
|
|
* @journal: journal to force
|
|
|
|
*
|
|
|
|
* Caller want unconditional commit. We can only force the running transaction
|
|
|
|
* if we don't have an active handle, otherwise, we will deadlock.
|
|
|
|
*/
|
|
|
|
int jbd2_journal_force_commit(journal_t *journal)
|
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
J_ASSERT(!current->journal_info);
|
|
|
|
ret = __jbd2_journal_force_commit(journal);
|
|
|
|
if (ret > 0)
|
|
|
|
ret = 0;
|
|
|
|
return ret;
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Start a commit of the current running transaction (if any). Returns true
|
2009-02-10 16:27:46 +00:00
|
|
|
* if a transaction is going to be committed (or is currently already
|
|
|
|
* committing), and fills its tid in at *ptid
|
2006-10-11 08:20:57 +00:00
|
|
|
*/
|
2006-10-11 08:20:59 +00:00
|
|
|
int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
|
2010-08-04 01:35:12 +00:00
|
|
|
write_lock(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
if (journal->j_running_transaction) {
|
|
|
|
tid_t tid = journal->j_running_transaction->t_tid;
|
|
|
|
|
2009-02-10 16:27:46 +00:00
|
|
|
__jbd2_log_start_commit(journal, tid);
|
|
|
|
/* There's a running transaction and we've just made sure
|
|
|
|
* it's commit has been scheduled. */
|
|
|
|
if (ptid)
|
2006-10-11 08:20:57 +00:00
|
|
|
*ptid = tid;
|
2009-02-10 16:27:46 +00:00
|
|
|
ret = 1;
|
|
|
|
} else if (journal->j_committing_transaction) {
|
2006-10-11 08:20:57 +00:00
|
|
|
/*
|
2012-07-25 15:12:07 +00:00
|
|
|
* If commit has been started, then we have to wait for
|
|
|
|
* completion of that transaction.
|
2006-10-11 08:20:57 +00:00
|
|
|
*/
|
2009-02-10 16:27:46 +00:00
|
|
|
if (ptid)
|
|
|
|
*ptid = journal->j_committing_transaction->t_tid;
|
2006-10-11 08:20:57 +00:00
|
|
|
ret = 1;
|
|
|
|
}
|
2010-08-04 01:35:12 +00:00
|
|
|
write_unlock(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2011-05-24 15:59:18 +00:00
|
|
|
/*
|
|
|
|
* Return 1 if a given transaction has not yet sent barrier request
|
|
|
|
* connected with a transaction commit. If 0 is returned, transaction
|
|
|
|
* may or may not have sent the barrier. Used to avoid sending barrier
|
|
|
|
* twice in common cases.
|
|
|
|
*/
|
|
|
|
int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid)
|
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
transaction_t *commit_trans;
|
|
|
|
|
|
|
|
if (!(journal->j_flags & JBD2_BARRIER))
|
|
|
|
return 0;
|
|
|
|
read_lock(&journal->j_state_lock);
|
|
|
|
/* Transaction already committed? */
|
|
|
|
if (tid_geq(journal->j_commit_sequence, tid))
|
|
|
|
goto out;
|
|
|
|
commit_trans = journal->j_committing_transaction;
|
|
|
|
if (!commit_trans || commit_trans->t_tid != tid) {
|
|
|
|
ret = 1;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* Transaction is being committed and we already proceeded to
|
|
|
|
* submitting a flush to fs partition?
|
|
|
|
*/
|
|
|
|
if (journal->j_fs_dev != journal->j_dev) {
|
|
|
|
if (!commit_trans->t_need_data_flush ||
|
|
|
|
commit_trans->t_state >= T_COMMIT_DFLUSH)
|
|
|
|
goto out;
|
|
|
|
} else {
|
|
|
|
if (commit_trans->t_state >= T_COMMIT_JFLUSH)
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
ret = 1;
|
|
|
|
out:
|
|
|
|
read_unlock(&journal->j_state_lock);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(jbd2_trans_will_send_data_barrier);
|
|
|
|
|
2006-10-11 08:20:57 +00:00
|
|
|
/*
|
|
|
|
* Wait for a specified commit to complete.
|
|
|
|
* The caller may not hold the journal lock.
|
|
|
|
*/
|
2006-10-11 08:20:59 +00:00
|
|
|
int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
|
|
|
int err = 0;
|
|
|
|
|
2010-08-04 01:35:12 +00:00
|
|
|
read_lock(&journal->j_state_lock);
|
2017-04-30 00:12:16 +00:00
|
|
|
#ifdef CONFIG_PROVE_LOCKING
|
|
|
|
/*
|
|
|
|
* Some callers make sure transaction is already committing and in that
|
|
|
|
* case we cannot block on open handles anymore. So don't warn in that
|
|
|
|
* case.
|
|
|
|
*/
|
|
|
|
if (tid_gt(tid, journal->j_commit_sequence) &&
|
|
|
|
(!journal->j_committing_transaction ||
|
|
|
|
journal->j_committing_transaction->t_tid != tid)) {
|
|
|
|
read_unlock(&journal->j_state_lock);
|
|
|
|
jbd2_might_wait_for_commit(journal);
|
|
|
|
read_lock(&journal->j_state_lock);
|
|
|
|
}
|
|
|
|
#endif
|
2007-07-18 12:57:06 +00:00
|
|
|
#ifdef CONFIG_JBD2_DEBUG
|
2006-10-11 08:20:57 +00:00
|
|
|
if (!tid_geq(journal->j_commit_request, tid)) {
|
2013-12-09 02:13:59 +00:00
|
|
|
printk(KERN_ERR
|
2019-05-30 19:08:34 +00:00
|
|
|
"%s: error: j_commit_request=%u, tid=%u\n",
|
2008-04-17 14:38:59 +00:00
|
|
|
__func__, journal->j_commit_request, tid);
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
#endif
|
|
|
|
while (tid_gt(tid, journal->j_commit_sequence)) {
|
2022-06-08 11:23:48 +00:00
|
|
|
jbd2_debug(1, "JBD2: want %u, j_commit_sequence=%u\n",
|
2006-10-11 08:20:57 +00:00
|
|
|
tid, journal->j_commit_sequence);
|
2010-08-04 01:35:12 +00:00
|
|
|
read_unlock(&journal->j_state_lock);
|
2014-03-09 00:11:36 +00:00
|
|
|
wake_up(&journal->j_wait_commit);
|
2006-10-11 08:20:57 +00:00
|
|
|
wait_event(journal->j_wait_done_commit,
|
|
|
|
!tid_gt(tid, journal->j_commit_sequence));
|
2010-08-04 01:35:12 +00:00
|
|
|
read_lock(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
2010-08-04 01:35:12 +00:00
|
|
|
read_unlock(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2013-12-09 02:13:59 +00:00
|
|
|
if (unlikely(is_journal_aborted(journal)))
|
2006-10-11 08:20:57 +00:00
|
|
|
err = -EIO;
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2020-10-15 20:37:56 +00:00
|
|
|
/*
|
|
|
|
* Start a fast commit. If there's an ongoing fast or full commit wait for
|
|
|
|
* it to complete. Returns 0 if a new fast commit was started. Returns -EALREADY
|
|
|
|
* if a fast commit is not needed, either because there's an already a commit
|
|
|
|
* going on or this tid has already been committed. Returns -EINVAL if no jbd2
|
|
|
|
* commit has yet been performed.
|
|
|
|
*/
|
|
|
|
int jbd2_fc_begin_commit(journal_t *journal, tid_t tid)
|
|
|
|
{
|
2020-11-06 03:59:10 +00:00
|
|
|
if (unlikely(is_journal_aborted(journal)))
|
|
|
|
return -EIO;
|
2020-10-15 20:37:56 +00:00
|
|
|
/*
|
|
|
|
* Fast commits only allowed if at least one full commit has
|
|
|
|
* been processed.
|
|
|
|
*/
|
|
|
|
if (!journal->j_stats.ts_tid)
|
|
|
|
return -EINVAL;
|
|
|
|
|
2020-11-06 03:59:01 +00:00
|
|
|
write_lock(&journal->j_state_lock);
|
|
|
|
if (tid <= journal->j_commit_sequence) {
|
|
|
|
write_unlock(&journal->j_state_lock);
|
2020-10-15 20:37:56 +00:00
|
|
|
return -EALREADY;
|
2020-11-06 03:59:01 +00:00
|
|
|
}
|
2020-10-15 20:37:56 +00:00
|
|
|
|
|
|
|
if (journal->j_flags & JBD2_FULL_COMMIT_ONGOING ||
|
|
|
|
(journal->j_flags & JBD2_FAST_COMMIT_ONGOING)) {
|
|
|
|
DEFINE_WAIT(wait);
|
|
|
|
|
|
|
|
prepare_to_wait(&journal->j_fc_wait, &wait,
|
|
|
|
TASK_UNINTERRUPTIBLE);
|
|
|
|
write_unlock(&journal->j_state_lock);
|
|
|
|
schedule();
|
|
|
|
finish_wait(&journal->j_fc_wait, &wait);
|
|
|
|
return -EALREADY;
|
|
|
|
}
|
|
|
|
journal->j_flags |= JBD2_FAST_COMMIT_ONGOING;
|
|
|
|
write_unlock(&journal->j_state_lock);
|
2021-12-23 20:21:37 +00:00
|
|
|
jbd2_journal_lock_updates(journal);
|
2020-10-15 20:37:56 +00:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(jbd2_fc_begin_commit);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Stop a fast commit. If fallback is set, this function starts commit of
|
|
|
|
* TID tid before any other fast commit can start.
|
|
|
|
*/
|
|
|
|
static int __jbd2_fc_end_commit(journal_t *journal, tid_t tid, bool fallback)
|
|
|
|
{
|
2021-12-23 20:21:37 +00:00
|
|
|
jbd2_journal_unlock_updates(journal);
|
2020-10-15 20:37:56 +00:00
|
|
|
if (journal->j_fc_cleanup_callback)
|
2022-01-17 09:36:54 +00:00
|
|
|
journal->j_fc_cleanup_callback(journal, 0, tid);
|
2020-10-15 20:37:56 +00:00
|
|
|
write_lock(&journal->j_state_lock);
|
|
|
|
journal->j_flags &= ~JBD2_FAST_COMMIT_ONGOING;
|
|
|
|
if (fallback)
|
|
|
|
journal->j_flags |= JBD2_FULL_COMMIT_ONGOING;
|
|
|
|
write_unlock(&journal->j_state_lock);
|
|
|
|
wake_up(&journal->j_fc_wait);
|
|
|
|
if (fallback)
|
|
|
|
return jbd2_complete_transaction(journal, tid);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
int jbd2_fc_end_commit(journal_t *journal)
|
|
|
|
{
|
2020-11-06 03:58:58 +00:00
|
|
|
return __jbd2_fc_end_commit(journal, 0, false);
|
2020-10-15 20:37:56 +00:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(jbd2_fc_end_commit);
|
|
|
|
|
2020-11-06 03:58:58 +00:00
|
|
|
int jbd2_fc_end_commit_fallback(journal_t *journal)
|
2020-10-15 20:37:56 +00:00
|
|
|
{
|
2020-11-06 03:58:58 +00:00
|
|
|
tid_t tid;
|
|
|
|
|
|
|
|
read_lock(&journal->j_state_lock);
|
|
|
|
tid = journal->j_running_transaction ?
|
|
|
|
journal->j_running_transaction->t_tid : 0;
|
|
|
|
read_unlock(&journal->j_state_lock);
|
|
|
|
return __jbd2_fc_end_commit(journal, tid, true);
|
2020-10-15 20:37:56 +00:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(jbd2_fc_end_commit_fallback);
|
|
|
|
|
2017-11-01 15:36:45 +00:00
|
|
|
/* Return 1 when transaction with given tid has already committed. */
|
|
|
|
int jbd2_transaction_committed(journal_t *journal, tid_t tid)
|
|
|
|
{
|
jbd2: speed up jbd2_transaction_committed()
jbd2_transaction_committed() is used to check whether a transaction with
the given tid has already committed, it holds j_state_lock in read mode
and check the tid of current running transaction and committing
transaction, but holding the j_state_lock is expensive.
We have already stored the sequence number of the most recently
committed transaction in journal t->j_commit_sequence, we could do this
check by comparing it with the given tid instead. If the given tid isn't
smaller than j_commit_sequence, we can ensure that the given transaction
has been committed. That way we could drop the expensive lock and
achieve about 10% ~ 20% performance gains in concurrent DIOs on may
virtual machine with 100G ramdisk.
fio -filename=/mnt/foo -direct=1 -iodepth=10 -rw=$rw -ioengine=libaio \
-bs=4k -size=10G -numjobs=10 -runtime=60 -overwrite=1 -name=test \
-group_reporting
Before:
overwrite IOPS=88.2k, BW=344MiB/s
read IOPS=95.7k, BW=374MiB/s
rand overwrite IOPS=98.7k, BW=386MiB/s
randread IOPS=102k, BW=397MiB/s
After:
overwrite IOPS=105k, BW=410MiB/s
read IOPS=112k, BW=436MiB/s
rand overwrite IOPS=104k, BW=404MiB/s
randread IOPS=111k, BW=432MiB/s
CC: Dave Chinner <david@fromorbit.com>
Suggested-by: Dave Chinner <david@fromorbit.com>
Link: https://lore.kernel.org/linux-ext4/ZjILCPNZRHeazSqV@dread.disaster.area/
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Link: https://patch.msgid.link/20240520131831.2910790-1-yi.zhang@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2024-05-20 13:18:31 +00:00
|
|
|
return tid_geq(READ_ONCE(journal->j_commit_sequence), tid);
|
2017-11-01 15:36:45 +00:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(jbd2_transaction_committed);
|
|
|
|
|
ext4/jbd2: don't wait (forever) for stale tid caused by wraparound
In the case where an inode has a very stale transaction id (tid) in
i_datasync_tid or i_sync_tid, it's possible that after a very large
(2**31) number of transactions, that the tid number space might wrap,
causing tid_geq()'s calculations to fail.
Commit deeeaf13 "jbd2: fix fsync() tid wraparound bug", later modified
by commit e7b04ac0 "jbd2: don't wake kjournald unnecessarily",
attempted to fix this problem, but it only avoided kjournald spinning
forever by fixing the logic in jbd2_log_start_commit().
Unfortunately, in the codepaths in fs/ext4/fsync.c and fs/ext4/inode.c
that might call jbd2_log_start_commit() with a stale tid, those
functions will subsequently call jbd2_log_wait_commit() with the same
stale tid, and then wait for a very long time. To fix this, we
replace the calls to jbd2_log_start_commit() and
jbd2_log_wait_commit() with a call to a new function,
jbd2_complete_transaction(), which will correctly handle stale tid's.
As a bonus, jbd2_complete_transaction() will avoid locking
j_state_lock for writing unless a commit needs to be started. This
should have a small (but probably not measurable) improvement for
ext4's scalability.
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Reported-by: Ben Hutchings <ben@decadent.org.uk>
Reported-by: George Barnett <gbarnett@atlassian.com>
Cc: stable@vger.kernel.org
2013-04-04 02:02:52 +00:00
|
|
|
/*
|
|
|
|
* When this function returns the transaction corresponding to tid
|
|
|
|
* will be completed. If the transaction has currently running, start
|
|
|
|
* committing that transaction before waiting for it to complete. If
|
|
|
|
* the transaction id is stale, it is by definition already completed,
|
|
|
|
* so just return SUCCESS.
|
|
|
|
*/
|
|
|
|
int jbd2_complete_transaction(journal_t *journal, tid_t tid)
|
|
|
|
{
|
|
|
|
int need_to_wait = 1;
|
|
|
|
|
|
|
|
read_lock(&journal->j_state_lock);
|
|
|
|
if (journal->j_running_transaction &&
|
|
|
|
journal->j_running_transaction->t_tid == tid) {
|
|
|
|
if (journal->j_commit_request != tid) {
|
|
|
|
/* transaction not yet started, so request it */
|
|
|
|
read_unlock(&journal->j_state_lock);
|
|
|
|
jbd2_log_start_commit(journal, tid);
|
|
|
|
goto wait_commit;
|
|
|
|
}
|
|
|
|
} else if (!(journal->j_committing_transaction &&
|
|
|
|
journal->j_committing_transaction->t_tid == tid))
|
|
|
|
need_to_wait = 0;
|
|
|
|
read_unlock(&journal->j_state_lock);
|
|
|
|
if (!need_to_wait)
|
|
|
|
return 0;
|
|
|
|
wait_commit:
|
|
|
|
return jbd2_log_wait_commit(journal, tid);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(jbd2_complete_transaction);
|
|
|
|
|
2006-10-11 08:20:57 +00:00
|
|
|
/*
|
|
|
|
* Log buffer allocation routines:
|
|
|
|
*/
|
|
|
|
|
2006-10-11 08:21:13 +00:00
|
|
|
int jbd2_journal_next_log_block(journal_t *journal, unsigned long long *retp)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
|
|
|
unsigned long blocknr;
|
|
|
|
|
2010-08-04 01:35:12 +00:00
|
|
|
write_lock(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
J_ASSERT(journal->j_free > 1);
|
|
|
|
|
|
|
|
blocknr = journal->j_head;
|
|
|
|
journal->j_head++;
|
|
|
|
journal->j_free--;
|
|
|
|
if (journal->j_head == journal->j_last)
|
|
|
|
journal->j_head = journal->j_first;
|
2010-08-04 01:35:12 +00:00
|
|
|
write_unlock(&journal->j_state_lock);
|
2006-10-11 08:20:59 +00:00
|
|
|
return jbd2_journal_bmap(journal, blocknr, retp);
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
2020-10-15 20:37:56 +00:00
|
|
|
/* Map one fast commit buffer for use by the file system */
|
|
|
|
int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out)
|
|
|
|
{
|
|
|
|
unsigned long long pblock;
|
|
|
|
unsigned long blocknr;
|
|
|
|
int ret = 0;
|
|
|
|
struct buffer_head *bh;
|
|
|
|
int fc_off;
|
|
|
|
|
|
|
|
*bh_out = NULL;
|
|
|
|
|
|
|
|
if (journal->j_fc_off + journal->j_fc_first < journal->j_fc_last) {
|
|
|
|
fc_off = journal->j_fc_off;
|
|
|
|
blocknr = journal->j_fc_first + fc_off;
|
|
|
|
journal->j_fc_off++;
|
|
|
|
} else {
|
|
|
|
ret = -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
ret = jbd2_journal_bmap(journal, blocknr, &pblock);
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
bh = __getblk(journal->j_dev, pblock, journal->j_blocksize);
|
|
|
|
if (!bh)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
|
|
|
|
journal->j_fc_wbuf[fc_off] = bh;
|
|
|
|
|
|
|
|
*bh_out = bh;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(jbd2_fc_get_buf);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Wait on fast commit buffers that were allocated by jbd2_fc_get_buf
|
|
|
|
* for completion.
|
|
|
|
*/
|
|
|
|
int jbd2_fc_wait_bufs(journal_t *journal, int num_blks)
|
|
|
|
{
|
|
|
|
struct buffer_head *bh;
|
|
|
|
int i, j_fc_off;
|
|
|
|
|
|
|
|
j_fc_off = journal->j_fc_off;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Wait in reverse order to minimize chances of us being woken up before
|
|
|
|
* all IOs have completed
|
|
|
|
*/
|
|
|
|
for (i = j_fc_off - 1; i >= j_fc_off - num_blks; i--) {
|
|
|
|
bh = journal->j_fc_wbuf[i];
|
|
|
|
wait_on_buffer(bh);
|
2022-09-14 10:08:11 +00:00
|
|
|
/*
|
|
|
|
* Update j_fc_off so jbd2_fc_release_bufs can release remain
|
|
|
|
* buffer head.
|
|
|
|
*/
|
|
|
|
if (unlikely(!buffer_uptodate(bh))) {
|
2022-09-14 10:08:12 +00:00
|
|
|
journal->j_fc_off = i + 1;
|
2020-10-15 20:37:56 +00:00
|
|
|
return -EIO;
|
2022-09-14 10:08:11 +00:00
|
|
|
}
|
2022-09-14 10:08:12 +00:00
|
|
|
put_bh(bh);
|
|
|
|
journal->j_fc_wbuf[i] = NULL;
|
2020-10-15 20:37:56 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(jbd2_fc_wait_bufs);
|
|
|
|
|
|
|
|
int jbd2_fc_release_bufs(journal_t *journal)
|
|
|
|
{
|
|
|
|
struct buffer_head *bh;
|
|
|
|
int i, j_fc_off;
|
|
|
|
|
|
|
|
j_fc_off = journal->j_fc_off;
|
|
|
|
|
|
|
|
for (i = j_fc_off - 1; i >= 0; i--) {
|
|
|
|
bh = journal->j_fc_wbuf[i];
|
|
|
|
if (!bh)
|
|
|
|
break;
|
|
|
|
put_bh(bh);
|
|
|
|
journal->j_fc_wbuf[i] = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(jbd2_fc_release_bufs);
|
|
|
|
|
2006-10-11 08:20:57 +00:00
|
|
|
/*
|
|
|
|
* Conversion of logical to physical block numbers for the journal
|
|
|
|
*
|
|
|
|
* On external journals the journal blocks are identity-mapped, so
|
|
|
|
* this is a no-op. If needed, we can use j_blk_offset - everything is
|
|
|
|
* ready.
|
|
|
|
*/
|
2006-10-11 08:20:59 +00:00
|
|
|
int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr,
|
2006-10-11 08:21:13 +00:00
|
|
|
unsigned long long *retp)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
|
|
|
int err = 0;
|
2006-10-11 08:21:13 +00:00
|
|
|
unsigned long long ret;
|
2023-03-08 04:15:49 +00:00
|
|
|
sector_t block = blocknr;
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2023-03-08 04:15:49 +00:00
|
|
|
if (journal->j_bmap) {
|
|
|
|
err = journal->j_bmap(journal, &block);
|
|
|
|
if (err == 0)
|
|
|
|
*retp = block;
|
|
|
|
} else if (journal->j_inode) {
|
2020-01-09 13:30:41 +00:00
|
|
|
ret = bmap(journal->j_inode, &block);
|
|
|
|
|
|
|
|
if (ret || !block) {
|
2006-10-11 08:20:57 +00:00
|
|
|
printk(KERN_ALERT "%s: journal block not found "
|
|
|
|
"at offset %lu on %s\n",
|
2008-09-16 18:36:17 +00:00
|
|
|
__func__, blocknr, journal->j_devname);
|
2006-10-11 08:20:57 +00:00
|
|
|
err = -EIO;
|
2019-12-04 12:46:14 +00:00
|
|
|
jbd2_journal_abort(journal, err);
|
2020-01-09 13:30:41 +00:00
|
|
|
} else {
|
|
|
|
*retp = block;
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
2020-01-09 13:30:41 +00:00
|
|
|
|
2006-10-11 08:20:57 +00:00
|
|
|
} else {
|
|
|
|
*retp = blocknr; /* +journal->j_blk_offset */
|
|
|
|
}
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We play buffer_head aliasing tricks to write data/metadata blocks to
|
|
|
|
* the journal without copying their contents, but for journal
|
|
|
|
* descriptor blocks we do need to generate bona fide buffers.
|
|
|
|
*
|
2006-10-11 08:20:59 +00:00
|
|
|
* After the caller of jbd2_journal_get_descriptor_buffer() has finished modifying
|
2006-10-11 08:20:57 +00:00
|
|
|
* the buffer's contents they really should run flush_dcache_page(bh->b_page).
|
|
|
|
* But we don't bother doing that, so there will be coherency problems with
|
|
|
|
* mmaps of blockdevs which hold live JBD-controlled filesystems.
|
|
|
|
*/
|
2016-02-23 04:17:15 +00:00
|
|
|
struct buffer_head *
|
|
|
|
jbd2_journal_get_descriptor_buffer(transaction_t *transaction, int type)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
2016-02-23 04:17:15 +00:00
|
|
|
journal_t *journal = transaction->t_journal;
|
2006-10-11 08:20:57 +00:00
|
|
|
struct buffer_head *bh;
|
2006-10-11 08:21:13 +00:00
|
|
|
unsigned long long blocknr;
|
2016-02-23 04:17:15 +00:00
|
|
|
journal_header_t *header;
|
2006-10-11 08:20:57 +00:00
|
|
|
int err;
|
|
|
|
|
2006-10-11 08:20:59 +00:00
|
|
|
err = jbd2_journal_next_log_block(journal, &blocknr);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
if (err)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
|
2009-01-06 19:53:35 +00:00
|
|
|
if (!bh)
|
|
|
|
return NULL;
|
2019-11-05 16:44:24 +00:00
|
|
|
atomic_dec(&transaction->t_outstanding_credits);
|
2006-10-11 08:20:57 +00:00
|
|
|
lock_buffer(bh);
|
|
|
|
memset(bh->b_data, 0, journal->j_blocksize);
|
2016-02-23 04:17:15 +00:00
|
|
|
header = (journal_header_t *)bh->b_data;
|
|
|
|
header->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
|
|
|
|
header->h_blocktype = cpu_to_be32(type);
|
|
|
|
header->h_sequence = cpu_to_be32(transaction->t_tid);
|
2006-10-11 08:20:57 +00:00
|
|
|
set_buffer_uptodate(bh);
|
|
|
|
unlock_buffer(bh);
|
|
|
|
BUFFER_TRACE(bh, "return this buffer");
|
2013-06-04 16:06:01 +00:00
|
|
|
return bh;
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
2016-02-23 04:19:09 +00:00
|
|
|
void jbd2_descriptor_block_csum_set(journal_t *j, struct buffer_head *bh)
|
|
|
|
{
|
|
|
|
struct jbd2_journal_block_tail *tail;
|
|
|
|
__u32 csum;
|
|
|
|
|
|
|
|
if (!jbd2_journal_has_csum_v2or3(j))
|
|
|
|
return;
|
|
|
|
|
|
|
|
tail = (struct jbd2_journal_block_tail *)(bh->b_data + j->j_blocksize -
|
|
|
|
sizeof(struct jbd2_journal_block_tail));
|
|
|
|
tail->t_checksum = 0;
|
|
|
|
csum = jbd2_chksum(j, j->j_csum_seed, bh->b_data, j->j_blocksize);
|
|
|
|
tail->t_checksum = cpu_to_be32(csum);
|
|
|
|
}
|
|
|
|
|
2012-03-14 02:22:54 +00:00
|
|
|
/*
|
|
|
|
* Return tid of the oldest transaction in the journal and block in the journal
|
|
|
|
* where the transaction starts.
|
|
|
|
*
|
|
|
|
* If the journal is now empty, return which will be the next transaction ID
|
|
|
|
* we will write and where will that transaction start.
|
|
|
|
*
|
|
|
|
* The return value is 0 if journal tail cannot be pushed any further, 1 if
|
|
|
|
* it can.
|
|
|
|
*/
|
|
|
|
int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid,
|
|
|
|
unsigned long *block)
|
|
|
|
{
|
|
|
|
transaction_t *transaction;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
read_lock(&journal->j_state_lock);
|
|
|
|
spin_lock(&journal->j_list_lock);
|
|
|
|
transaction = journal->j_checkpoint_transactions;
|
|
|
|
if (transaction) {
|
|
|
|
*tid = transaction->t_tid;
|
|
|
|
*block = transaction->t_log_start;
|
|
|
|
} else if ((transaction = journal->j_committing_transaction) != NULL) {
|
|
|
|
*tid = transaction->t_tid;
|
|
|
|
*block = transaction->t_log_start;
|
|
|
|
} else if ((transaction = journal->j_running_transaction) != NULL) {
|
|
|
|
*tid = transaction->t_tid;
|
|
|
|
*block = journal->j_head;
|
|
|
|
} else {
|
|
|
|
*tid = journal->j_transaction_sequence;
|
|
|
|
*block = journal->j_head;
|
|
|
|
}
|
|
|
|
ret = tid_gt(*tid, journal->j_tail_sequence);
|
|
|
|
spin_unlock(&journal->j_list_lock);
|
|
|
|
read_unlock(&journal->j_state_lock);
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Update information in journal structure and in on disk journal superblock
|
|
|
|
* about log tail. This function does not check whether information passed in
|
|
|
|
* really pushes log tail further. It's responsibility of the caller to make
|
|
|
|
* sure provided log tail information is valid (e.g. by holding
|
|
|
|
* j_checkpoint_mutex all the time between computing log tail and calling this
|
|
|
|
* function as is the case with jbd2_cleanup_journal_tail()).
|
|
|
|
*
|
|
|
|
* Requires j_checkpoint_mutex
|
|
|
|
*/
|
2015-06-15 18:36:01 +00:00
|
|
|
int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block)
|
2012-03-14 02:22:54 +00:00
|
|
|
{
|
|
|
|
unsigned long freed;
|
2015-06-15 18:36:01 +00:00
|
|
|
int ret;
|
2012-03-14 02:22:54 +00:00
|
|
|
|
|
|
|
BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We cannot afford for write to remain in drive's caches since as
|
|
|
|
* soon as we update j_tail, next transaction can start reusing journal
|
|
|
|
* space and if we lose sb update during power failure we'd replay
|
|
|
|
* old transaction with possibly newly overwritten data.
|
|
|
|
*/
|
2023-11-29 11:47:40 +00:00
|
|
|
ret = jbd2_journal_update_sb_log_tail(journal, tid, block, REQ_FUA);
|
2015-06-15 18:36:01 +00:00
|
|
|
if (ret)
|
|
|
|
goto out;
|
|
|
|
|
2012-03-14 02:22:54 +00:00
|
|
|
write_lock(&journal->j_state_lock);
|
|
|
|
freed = block - journal->j_tail;
|
|
|
|
if (block < journal->j_tail)
|
|
|
|
freed += journal->j_last - journal->j_first;
|
|
|
|
|
|
|
|
trace_jbd2_update_log_tail(journal, tid, block, freed);
|
2022-06-08 11:23:48 +00:00
|
|
|
jbd2_debug(1,
|
2019-05-30 19:08:34 +00:00
|
|
|
"Cleaning journal tail from %u to %u (offset %lu), "
|
2012-03-14 02:22:54 +00:00
|
|
|
"freeing %lu\n",
|
|
|
|
journal->j_tail_sequence, tid, block, freed);
|
|
|
|
|
|
|
|
journal->j_free += freed;
|
|
|
|
journal->j_tail_sequence = tid;
|
|
|
|
journal->j_tail = block;
|
|
|
|
write_unlock(&journal->j_state_lock);
|
2015-06-15 18:36:01 +00:00
|
|
|
|
|
|
|
out:
|
|
|
|
return ret;
|
2012-03-14 02:22:54 +00:00
|
|
|
}
|
|
|
|
|
2012-03-14 02:45:38 +00:00
|
|
|
/*
|
2018-02-19 17:22:53 +00:00
|
|
|
* This is a variation of __jbd2_update_log_tail which checks for validity of
|
2012-03-14 02:45:38 +00:00
|
|
|
* provided log tail and locks j_checkpoint_mutex. So it is safe against races
|
|
|
|
* with other threads updating log tail.
|
|
|
|
*/
|
|
|
|
void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block)
|
|
|
|
{
|
2016-10-28 16:58:12 +00:00
|
|
|
mutex_lock_io(&journal->j_checkpoint_mutex);
|
2012-03-14 02:45:38 +00:00
|
|
|
if (tid_gt(tid, journal->j_tail_sequence))
|
|
|
|
__jbd2_update_log_tail(journal, tid, block);
|
|
|
|
mutex_unlock(&journal->j_checkpoint_mutex);
|
|
|
|
}
|
|
|
|
|
2008-01-29 04:58:27 +00:00
|
|
|
struct jbd2_stats_proc_session {
|
|
|
|
journal_t *journal;
|
|
|
|
struct transaction_stats_s *stats;
|
|
|
|
int start;
|
|
|
|
int max;
|
|
|
|
};
|
|
|
|
|
|
|
|
static void *jbd2_seq_info_start(struct seq_file *seq, loff_t *pos)
|
|
|
|
{
|
|
|
|
return *pos ? NULL : SEQ_START_TOKEN;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void *jbd2_seq_info_next(struct seq_file *seq, void *v, loff_t *pos)
|
|
|
|
{
|
2020-01-23 09:05:10 +00:00
|
|
|
(*pos)++;
|
2008-01-29 04:58:27 +00:00
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int jbd2_seq_info_show(struct seq_file *seq, void *v)
|
|
|
|
{
|
|
|
|
struct jbd2_stats_proc_session *s = seq->private;
|
|
|
|
|
|
|
|
if (v != SEQ_START_TOKEN)
|
|
|
|
return 0;
|
2013-02-07 03:30:23 +00:00
|
|
|
seq_printf(seq, "%lu transactions (%lu requested), "
|
|
|
|
"each up to %u blocks\n",
|
|
|
|
s->stats->ts_tid, s->stats->ts_requested,
|
|
|
|
s->journal->j_max_transaction_buffers);
|
2008-01-29 04:58:27 +00:00
|
|
|
if (s->stats->ts_tid == 0)
|
|
|
|
return 0;
|
|
|
|
seq_printf(seq, "average: \n %ums waiting for transaction\n",
|
2009-09-30 04:32:06 +00:00
|
|
|
jiffies_to_msecs(s->stats->run.rs_wait / s->stats->ts_tid));
|
2013-02-07 03:30:23 +00:00
|
|
|
seq_printf(seq, " %ums request delay\n",
|
|
|
|
(s->stats->ts_requested == 0) ? 0 :
|
|
|
|
jiffies_to_msecs(s->stats->run.rs_request_delay /
|
|
|
|
s->stats->ts_requested));
|
2008-01-29 04:58:27 +00:00
|
|
|
seq_printf(seq, " %ums running transaction\n",
|
2009-09-30 04:32:06 +00:00
|
|
|
jiffies_to_msecs(s->stats->run.rs_running / s->stats->ts_tid));
|
2008-01-29 04:58:27 +00:00
|
|
|
seq_printf(seq, " %ums transaction was being locked\n",
|
2009-09-30 04:32:06 +00:00
|
|
|
jiffies_to_msecs(s->stats->run.rs_locked / s->stats->ts_tid));
|
2008-01-29 04:58:27 +00:00
|
|
|
seq_printf(seq, " %ums flushing data (in ordered mode)\n",
|
2009-09-30 04:32:06 +00:00
|
|
|
jiffies_to_msecs(s->stats->run.rs_flushing / s->stats->ts_tid));
|
2008-01-29 04:58:27 +00:00
|
|
|
seq_printf(seq, " %ums logging transaction\n",
|
2009-09-30 04:32:06 +00:00
|
|
|
jiffies_to_msecs(s->stats->run.rs_logging / s->stats->ts_tid));
|
2009-01-12 03:34:01 +00:00
|
|
|
seq_printf(seq, " %lluus average transaction commit time\n",
|
|
|
|
div_u64(s->journal->j_average_commit_time, 1000));
|
2008-01-29 04:58:27 +00:00
|
|
|
seq_printf(seq, " %lu handles per transaction\n",
|
2009-09-30 04:32:06 +00:00
|
|
|
s->stats->run.rs_handle_count / s->stats->ts_tid);
|
2008-01-29 04:58:27 +00:00
|
|
|
seq_printf(seq, " %lu blocks per transaction\n",
|
2009-09-30 04:32:06 +00:00
|
|
|
s->stats->run.rs_blocks / s->stats->ts_tid);
|
2008-01-29 04:58:27 +00:00
|
|
|
seq_printf(seq, " %lu logged blocks per transaction\n",
|
2009-09-30 04:32:06 +00:00
|
|
|
s->stats->run.rs_blocks_logged / s->stats->ts_tid);
|
2008-01-29 04:58:27 +00:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void jbd2_seq_info_stop(struct seq_file *seq, void *v)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2009-09-22 23:43:43 +00:00
|
|
|
static const struct seq_operations jbd2_seq_info_ops = {
|
2008-01-29 04:58:27 +00:00
|
|
|
.start = jbd2_seq_info_start,
|
|
|
|
.next = jbd2_seq_info_next,
|
|
|
|
.stop = jbd2_seq_info_stop,
|
|
|
|
.show = jbd2_seq_info_show,
|
|
|
|
};
|
|
|
|
|
|
|
|
static int jbd2_seq_info_open(struct inode *inode, struct file *file)
|
|
|
|
{
|
2022-01-22 06:14:23 +00:00
|
|
|
journal_t *journal = pde_data(inode);
|
2008-01-29 04:58:27 +00:00
|
|
|
struct jbd2_stats_proc_session *s;
|
|
|
|
int rc, size;
|
|
|
|
|
|
|
|
s = kmalloc(sizeof(*s), GFP_KERNEL);
|
|
|
|
if (s == NULL)
|
|
|
|
return -ENOMEM;
|
|
|
|
size = sizeof(struct transaction_stats_s);
|
|
|
|
s->stats = kmalloc(size, GFP_KERNEL);
|
|
|
|
if (s->stats == NULL) {
|
|
|
|
kfree(s);
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
spin_lock(&journal->j_history_lock);
|
|
|
|
memcpy(s->stats, &journal->j_stats, size);
|
|
|
|
s->journal = journal;
|
|
|
|
spin_unlock(&journal->j_history_lock);
|
|
|
|
|
|
|
|
rc = seq_open(file, &jbd2_seq_info_ops);
|
|
|
|
if (rc == 0) {
|
|
|
|
struct seq_file *m = file->private_data;
|
|
|
|
m->private = s;
|
|
|
|
} else {
|
|
|
|
kfree(s->stats);
|
|
|
|
kfree(s);
|
|
|
|
}
|
|
|
|
return rc;
|
|
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
static int jbd2_seq_info_release(struct inode *inode, struct file *file)
|
|
|
|
{
|
|
|
|
struct seq_file *seq = file->private_data;
|
|
|
|
struct jbd2_stats_proc_session *s = seq->private;
|
|
|
|
kfree(s->stats);
|
|
|
|
kfree(s);
|
|
|
|
return seq_release(inode, file);
|
|
|
|
}
|
|
|
|
|
2020-02-04 01:37:17 +00:00
|
|
|
static const struct proc_ops jbd2_info_proc_ops = {
|
|
|
|
.proc_open = jbd2_seq_info_open,
|
|
|
|
.proc_read = seq_read,
|
|
|
|
.proc_lseek = seq_lseek,
|
|
|
|
.proc_release = jbd2_seq_info_release,
|
2008-01-29 04:58:27 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
static struct proc_dir_entry *proc_jbd2_stats;
|
|
|
|
|
|
|
|
static void jbd2_stats_proc_init(journal_t *journal)
|
|
|
|
{
|
2008-09-16 18:36:17 +00:00
|
|
|
journal->j_proc_entry = proc_mkdir(journal->j_devname, proc_jbd2_stats);
|
2008-01-29 04:58:27 +00:00
|
|
|
if (journal->j_proc_entry) {
|
2008-04-29 08:02:11 +00:00
|
|
|
proc_create_data("info", S_IRUGO, journal->j_proc_entry,
|
2020-02-04 01:37:17 +00:00
|
|
|
&jbd2_info_proc_ops, journal);
|
2008-01-29 04:58:27 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static void jbd2_stats_proc_exit(journal_t *journal)
|
|
|
|
{
|
|
|
|
remove_proc_entry("info", journal->j_proc_entry);
|
2008-09-16 18:36:17 +00:00
|
|
|
remove_proc_entry(journal->j_devname, proc_jbd2_stats);
|
2008-01-29 04:58:27 +00:00
|
|
|
}
|
|
|
|
|
2019-11-05 16:44:09 +00:00
|
|
|
/* Minimum size of descriptor tag */
|
|
|
|
static int jbd2_min_tag_size(void)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* Tag with 32-bit block numbers does not use last four bytes of the
|
|
|
|
* structure
|
|
|
|
*/
|
|
|
|
return sizeof(journal_block_tag_t) - 4;
|
|
|
|
}
|
|
|
|
|
2021-07-02 22:05:03 +00:00
|
|
|
/**
|
|
|
|
* jbd2_journal_shrink_scan()
|
2022-01-10 13:28:41 +00:00
|
|
|
* @shrink: shrinker to work on
|
|
|
|
* @sc: reclaim request to process
|
2021-07-02 22:05:03 +00:00
|
|
|
*
|
|
|
|
* Scan the checkpointed buffer on the checkpoint list and release the
|
|
|
|
* journal_head.
|
|
|
|
*/
|
|
|
|
static unsigned long jbd2_journal_shrink_scan(struct shrinker *shrink,
|
|
|
|
struct shrink_control *sc)
|
|
|
|
{
|
2023-09-11 09:44:30 +00:00
|
|
|
journal_t *journal = shrink->private_data;
|
2021-07-02 22:05:03 +00:00
|
|
|
unsigned long nr_to_scan = sc->nr_to_scan;
|
|
|
|
unsigned long nr_shrunk;
|
|
|
|
unsigned long count;
|
|
|
|
|
|
|
|
count = percpu_counter_read_positive(&journal->j_checkpoint_jh_count);
|
|
|
|
trace_jbd2_shrink_scan_enter(journal, sc->nr_to_scan, count);
|
|
|
|
|
|
|
|
nr_shrunk = jbd2_journal_shrink_checkpoint_list(journal, &nr_to_scan);
|
|
|
|
|
|
|
|
count = percpu_counter_read_positive(&journal->j_checkpoint_jh_count);
|
|
|
|
trace_jbd2_shrink_scan_exit(journal, nr_to_scan, nr_shrunk, count);
|
|
|
|
|
|
|
|
return nr_shrunk;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* jbd2_journal_shrink_count()
|
2022-01-10 13:28:41 +00:00
|
|
|
* @shrink: shrinker to work on
|
|
|
|
* @sc: reclaim request to process
|
2021-07-02 22:05:03 +00:00
|
|
|
*
|
|
|
|
* Count the number of checkpoint buffers on the checkpoint list.
|
|
|
|
*/
|
|
|
|
static unsigned long jbd2_journal_shrink_count(struct shrinker *shrink,
|
|
|
|
struct shrink_control *sc)
|
|
|
|
{
|
2023-09-11 09:44:30 +00:00
|
|
|
journal_t *journal = shrink->private_data;
|
2021-07-02 22:05:03 +00:00
|
|
|
unsigned long count;
|
|
|
|
|
|
|
|
count = percpu_counter_read_positive(&journal->j_checkpoint_jh_count);
|
|
|
|
trace_jbd2_shrink_count(journal, sc->nr_to_scan, count);
|
|
|
|
|
|
|
|
return count;
|
|
|
|
}
|
|
|
|
|
2023-08-11 06:35:59 +00:00
|
|
|
/*
|
|
|
|
* If the journal init or create aborts, we need to mark the journal
|
|
|
|
* superblock as being NULL to prevent the journal destroy from writing
|
|
|
|
* back a bogus superblock.
|
|
|
|
*/
|
|
|
|
static void journal_fail_superblock(journal_t *journal)
|
|
|
|
{
|
|
|
|
struct buffer_head *bh = journal->j_sb_buffer;
|
|
|
|
brelse(bh);
|
|
|
|
journal->j_sb_buffer = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2023-08-11 06:36:04 +00:00
|
|
|
* Check the superblock for a given journal, performing initial
|
2023-08-11 06:35:59 +00:00
|
|
|
* validation of the format.
|
|
|
|
*/
|
2023-08-11 06:36:04 +00:00
|
|
|
static int journal_check_superblock(journal_t *journal)
|
2023-08-11 06:35:59 +00:00
|
|
|
{
|
2023-08-11 06:36:04 +00:00
|
|
|
journal_superblock_t *sb = journal->j_superblock;
|
2023-08-11 06:36:05 +00:00
|
|
|
int num_fc_blks;
|
2023-08-11 06:36:04 +00:00
|
|
|
int err = -EINVAL;
|
2023-08-11 06:35:59 +00:00
|
|
|
|
|
|
|
if (sb->s_header.h_magic != cpu_to_be32(JBD2_MAGIC_NUMBER) ||
|
|
|
|
sb->s_blocksize != cpu_to_be32(journal->j_blocksize)) {
|
|
|
|
printk(KERN_WARNING "JBD2: no valid journal superblock found\n");
|
2023-08-11 06:36:04 +00:00
|
|
|
return err;
|
2023-08-11 06:35:59 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
if (be32_to_cpu(sb->s_header.h_blocktype) != JBD2_SUPERBLOCK_V1 &&
|
|
|
|
be32_to_cpu(sb->s_header.h_blocktype) != JBD2_SUPERBLOCK_V2) {
|
|
|
|
printk(KERN_WARNING "JBD2: unrecognised superblock format ID\n");
|
2023-08-11 06:36:04 +00:00
|
|
|
return err;
|
2023-08-11 06:35:59 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
if (be32_to_cpu(sb->s_maxlen) > journal->j_total_len) {
|
|
|
|
printk(KERN_WARNING "JBD2: journal file too short\n");
|
2023-08-11 06:36:04 +00:00
|
|
|
return err;
|
2023-08-11 06:35:59 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
if (be32_to_cpu(sb->s_first) == 0 ||
|
|
|
|
be32_to_cpu(sb->s_first) >= journal->j_total_len) {
|
|
|
|
printk(KERN_WARNING
|
|
|
|
"JBD2: Invalid start block of journal: %u\n",
|
|
|
|
be32_to_cpu(sb->s_first));
|
2023-08-11 06:36:04 +00:00
|
|
|
return err;
|
2023-08-11 06:35:59 +00:00
|
|
|
}
|
|
|
|
|
2023-08-11 06:36:02 +00:00
|
|
|
/*
|
|
|
|
* If this is a V2 superblock, then we have to check the
|
|
|
|
* features flags on it.
|
|
|
|
*/
|
|
|
|
if (!jbd2_format_support_feature(journal))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
if ((sb->s_feature_ro_compat &
|
|
|
|
~cpu_to_be32(JBD2_KNOWN_ROCOMPAT_FEATURES)) ||
|
|
|
|
(sb->s_feature_incompat &
|
|
|
|
~cpu_to_be32(JBD2_KNOWN_INCOMPAT_FEATURES))) {
|
|
|
|
printk(KERN_WARNING "JBD2: Unrecognised features on journal\n");
|
2023-08-11 06:36:04 +00:00
|
|
|
return err;
|
2023-08-11 06:36:02 +00:00
|
|
|
}
|
|
|
|
|
2023-08-11 06:36:05 +00:00
|
|
|
num_fc_blks = jbd2_has_feature_fast_commit(journal) ?
|
|
|
|
jbd2_journal_get_num_fc_blks(sb) : 0;
|
|
|
|
if (be32_to_cpu(sb->s_maxlen) < JBD2_MIN_JOURNAL_BLOCKS ||
|
|
|
|
be32_to_cpu(sb->s_maxlen) - JBD2_MIN_JOURNAL_BLOCKS < num_fc_blks) {
|
|
|
|
printk(KERN_ERR "JBD2: journal file too short %u,%d\n",
|
|
|
|
be32_to_cpu(sb->s_maxlen), num_fc_blks);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2023-08-11 06:35:59 +00:00
|
|
|
if (jbd2_has_feature_csum2(journal) &&
|
|
|
|
jbd2_has_feature_csum3(journal)) {
|
|
|
|
/* Can't have checksum v2 and v3 at the same time! */
|
|
|
|
printk(KERN_ERR "JBD2: Can't enable checksumming v2 and v3 "
|
|
|
|
"at the same time!\n");
|
2023-08-11 06:36:04 +00:00
|
|
|
return err;
|
2023-08-11 06:35:59 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
if (jbd2_journal_has_csum_v2or3_feature(journal) &&
|
|
|
|
jbd2_has_feature_checksum(journal)) {
|
|
|
|
/* Can't have checksum v1 and v2 on at the same time! */
|
|
|
|
printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2/3 "
|
|
|
|
"at the same time!\n");
|
2023-08-11 06:36:04 +00:00
|
|
|
return err;
|
2023-08-11 06:35:59 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Load the checksum driver */
|
|
|
|
if (jbd2_journal_has_csum_v2or3_feature(journal)) {
|
2023-08-11 06:36:03 +00:00
|
|
|
if (sb->s_checksum_type != JBD2_CRC32C_CHKSUM) {
|
|
|
|
printk(KERN_ERR "JBD2: Unknown checksum type\n");
|
2023-08-11 06:36:04 +00:00
|
|
|
return err;
|
2023-08-11 06:36:03 +00:00
|
|
|
}
|
|
|
|
|
2023-08-11 06:35:59 +00:00
|
|
|
journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0);
|
|
|
|
if (IS_ERR(journal->j_chksum_driver)) {
|
|
|
|
printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n");
|
|
|
|
err = PTR_ERR(journal->j_chksum_driver);
|
|
|
|
journal->j_chksum_driver = NULL;
|
2023-08-11 06:36:04 +00:00
|
|
|
return err;
|
2023-08-11 06:35:59 +00:00
|
|
|
}
|
|
|
|
/* Check superblock checksum */
|
|
|
|
if (sb->s_checksum != jbd2_superblock_csum(journal, sb)) {
|
|
|
|
printk(KERN_ERR "JBD2: journal checksum error\n");
|
|
|
|
err = -EFSBADCRC;
|
2023-08-11 06:36:04 +00:00
|
|
|
return err;
|
2023-08-11 06:35:59 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2023-08-11 06:36:04 +00:00
|
|
|
return 0;
|
2023-08-11 06:35:59 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static int journal_revoke_records_per_block(journal_t *journal)
|
|
|
|
{
|
|
|
|
int record_size;
|
|
|
|
int space = journal->j_blocksize - sizeof(jbd2_journal_revoke_header_t);
|
|
|
|
|
|
|
|
if (jbd2_has_feature_64bit(journal))
|
|
|
|
record_size = 8;
|
|
|
|
else
|
|
|
|
record_size = 4;
|
|
|
|
|
|
|
|
if (jbd2_journal_has_csum_v2or3(journal))
|
|
|
|
space -= sizeof(struct jbd2_journal_block_tail);
|
|
|
|
return space / record_size;
|
|
|
|
}
|
|
|
|
|
2024-06-24 17:01:18 +00:00
|
|
|
static int jbd2_journal_get_max_txn_bufs(journal_t *journal)
|
|
|
|
{
|
|
|
|
return (journal->j_total_len - journal->j_fc_wbufsize) / 4;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Base amount of descriptor blocks we reserve for each transaction.
|
|
|
|
*/
|
|
|
|
static int jbd2_descriptor_blocks_per_trans(journal_t *journal)
|
|
|
|
{
|
|
|
|
int tag_space = journal->j_blocksize - sizeof(journal_header_t);
|
|
|
|
int tags_per_block;
|
|
|
|
|
|
|
|
/* Subtract UUID */
|
|
|
|
tag_space -= 16;
|
|
|
|
if (jbd2_journal_has_csum_v2or3(journal))
|
|
|
|
tag_space -= sizeof(struct jbd2_journal_block_tail);
|
|
|
|
/* Commit code leaves a slack space of 16 bytes at the end of block */
|
|
|
|
tags_per_block = (tag_space - 16) / journal_tag_bytes(journal);
|
|
|
|
/*
|
|
|
|
* Revoke descriptors are accounted separately so we need to reserve
|
|
|
|
* space for commit block and normal transaction descriptor blocks.
|
|
|
|
*/
|
|
|
|
return 1 + DIV_ROUND_UP(jbd2_journal_get_max_txn_bufs(journal),
|
|
|
|
tags_per_block);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Initialize number of blocks each transaction reserves for its bookkeeping
|
|
|
|
* and maximum number of blocks a transaction can use. This needs to be called
|
|
|
|
* after the journal size and the fastcommit area size are initialized.
|
|
|
|
*/
|
|
|
|
static void jbd2_journal_init_transaction_limits(journal_t *journal)
|
|
|
|
{
|
|
|
|
journal->j_revoke_records_per_block =
|
|
|
|
journal_revoke_records_per_block(journal);
|
|
|
|
journal->j_transaction_overhead_buffers =
|
|
|
|
jbd2_descriptor_blocks_per_trans(journal);
|
|
|
|
journal->j_max_transaction_buffers =
|
|
|
|
jbd2_journal_get_max_txn_bufs(journal);
|
|
|
|
}
|
|
|
|
|
2023-08-11 06:35:59 +00:00
|
|
|
/*
|
|
|
|
* Load the on-disk journal superblock and read the key fields into the
|
|
|
|
* journal_t.
|
|
|
|
*/
|
2023-08-11 06:36:04 +00:00
|
|
|
static int journal_load_superblock(journal_t *journal)
|
2023-08-11 06:35:59 +00:00
|
|
|
{
|
|
|
|
int err;
|
2023-08-11 06:36:04 +00:00
|
|
|
struct buffer_head *bh;
|
2023-08-11 06:35:59 +00:00
|
|
|
journal_superblock_t *sb;
|
|
|
|
|
2023-08-11 06:36:04 +00:00
|
|
|
bh = getblk_unmovable(journal->j_dev, journal->j_blk_offset,
|
|
|
|
journal->j_blocksize);
|
|
|
|
if (bh)
|
|
|
|
err = bh_read(bh, 0);
|
|
|
|
if (!bh || err < 0) {
|
|
|
|
pr_err("%s: Cannot read journal superblock\n", __func__);
|
|
|
|
brelse(bh);
|
|
|
|
return -EIO;
|
|
|
|
}
|
2023-08-11 06:35:59 +00:00
|
|
|
|
2023-08-11 06:36:04 +00:00
|
|
|
journal->j_sb_buffer = bh;
|
|
|
|
sb = (journal_superblock_t *)bh->b_data;
|
|
|
|
journal->j_superblock = sb;
|
|
|
|
err = journal_check_superblock(journal);
|
|
|
|
if (err) {
|
|
|
|
journal_fail_superblock(journal);
|
|
|
|
return err;
|
|
|
|
}
|
2023-08-11 06:35:59 +00:00
|
|
|
|
|
|
|
journal->j_tail_sequence = be32_to_cpu(sb->s_sequence);
|
|
|
|
journal->j_tail = be32_to_cpu(sb->s_start);
|
|
|
|
journal->j_first = be32_to_cpu(sb->s_first);
|
|
|
|
journal->j_errno = be32_to_cpu(sb->s_errno);
|
|
|
|
journal->j_last = be32_to_cpu(sb->s_maxlen);
|
|
|
|
|
|
|
|
if (be32_to_cpu(sb->s_maxlen) < journal->j_total_len)
|
|
|
|
journal->j_total_len = be32_to_cpu(sb->s_maxlen);
|
|
|
|
/* Precompute checksum seed for all metadata */
|
|
|
|
if (jbd2_journal_has_csum_v2or3(journal))
|
|
|
|
journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid,
|
|
|
|
sizeof(sb->s_uuid));
|
2024-06-24 17:01:18 +00:00
|
|
|
/* After journal features are set, we can compute transaction limits */
|
|
|
|
jbd2_journal_init_transaction_limits(journal);
|
2023-08-11 06:35:59 +00:00
|
|
|
|
|
|
|
if (jbd2_has_feature_fast_commit(journal)) {
|
|
|
|
journal->j_fc_last = be32_to_cpu(sb->s_maxlen);
|
2023-08-11 06:36:05 +00:00
|
|
|
journal->j_last = journal->j_fc_last -
|
|
|
|
jbd2_journal_get_num_fc_blks(sb);
|
2023-08-11 06:35:59 +00:00
|
|
|
journal->j_fc_first = journal->j_last + 1;
|
|
|
|
journal->j_fc_off = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2006-10-11 08:20:57 +00:00
|
|
|
/*
|
|
|
|
* Management for journal control blocks: functions to create and
|
|
|
|
* destroy journal_t structures, and to initialise and read existing
|
|
|
|
* journal blocks from disk. */
|
|
|
|
|
|
|
|
/* First: create and setup a journal_t object in memory. We initialise
|
|
|
|
* very few fields yet: that has to wait until we have created the
|
|
|
|
* journal structures from from scratch, or loaded them from disk. */
|
|
|
|
|
2016-09-15 16:02:32 +00:00
|
|
|
static journal_t *journal_init_common(struct block_device *bdev,
|
|
|
|
struct block_device *fs_dev,
|
|
|
|
unsigned long long start, int len, int blocksize)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
2016-06-30 15:39:38 +00:00
|
|
|
static struct lock_class_key jbd2_trans_commit_key;
|
2006-10-11 08:20:57 +00:00
|
|
|
journal_t *journal;
|
|
|
|
int err;
|
2016-09-15 16:02:32 +00:00
|
|
|
int n;
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2009-12-23 13:05:15 +00:00
|
|
|
journal = kzalloc(sizeof(*journal), GFP_KERNEL);
|
2006-10-11 08:20:57 +00:00
|
|
|
if (!journal)
|
2023-08-11 06:36:08 +00:00
|
|
|
return ERR_PTR(-ENOMEM);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2023-08-11 06:36:06 +00:00
|
|
|
journal->j_blocksize = blocksize;
|
|
|
|
journal->j_dev = bdev;
|
|
|
|
journal->j_fs_dev = fs_dev;
|
|
|
|
journal->j_blk_offset = start;
|
|
|
|
journal->j_total_len = len;
|
2023-12-13 01:32:20 +00:00
|
|
|
jbd2_init_fs_dev_write_error(journal);
|
2023-08-11 06:36:06 +00:00
|
|
|
|
|
|
|
err = journal_load_superblock(journal);
|
|
|
|
if (err)
|
|
|
|
goto err_cleanup;
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
init_waitqueue_head(&journal->j_wait_transaction_locked);
|
|
|
|
init_waitqueue_head(&journal->j_wait_done_commit);
|
|
|
|
init_waitqueue_head(&journal->j_wait_commit);
|
|
|
|
init_waitqueue_head(&journal->j_wait_updates);
|
2013-06-04 16:35:11 +00:00
|
|
|
init_waitqueue_head(&journal->j_wait_reserved);
|
2020-10-15 20:37:56 +00:00
|
|
|
init_waitqueue_head(&journal->j_fc_wait);
|
2020-06-09 07:35:40 +00:00
|
|
|
mutex_init(&journal->j_abort_mutex);
|
2006-10-11 08:20:57 +00:00
|
|
|
mutex_init(&journal->j_barrier);
|
|
|
|
mutex_init(&journal->j_checkpoint_mutex);
|
|
|
|
spin_lock_init(&journal->j_revoke_lock);
|
|
|
|
spin_lock_init(&journal->j_list_lock);
|
2023-08-11 06:36:06 +00:00
|
|
|
spin_lock_init(&journal->j_history_lock);
|
2010-08-04 01:35:12 +00:00
|
|
|
rwlock_init(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2007-10-16 22:38:25 +00:00
|
|
|
journal->j_commit_interval = (HZ * JBD2_DEFAULT_MAX_COMMIT_AGE);
|
2009-01-04 01:27:38 +00:00
|
|
|
journal->j_min_batch_time = 0;
|
|
|
|
journal->j_max_batch_time = 15000; /* 15ms */
|
2013-06-04 16:35:11 +00:00
|
|
|
atomic_set(&journal->j_reserved_credits, 0);
|
2023-08-11 06:36:06 +00:00
|
|
|
lockdep_init_map(&journal->j_trans_commit_map, "jbd2_handle",
|
|
|
|
&jbd2_trans_commit_key, 0);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
/* The journal is marked for error until we succeed with recovery! */
|
2006-10-11 08:20:59 +00:00
|
|
|
journal->j_flags = JBD2_ABORT;
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
/* Set up a default-sized revoke table for the new mount. */
|
2006-10-11 08:20:59 +00:00
|
|
|
err = jbd2_journal_init_revoke(journal, JOURNAL_REVOKE_DEFAULT_HASH);
|
2017-03-15 19:08:48 +00:00
|
|
|
if (err)
|
|
|
|
goto err_cleanup;
|
2008-01-29 04:58:27 +00:00
|
|
|
|
2023-08-11 06:36:06 +00:00
|
|
|
/*
|
|
|
|
* journal descriptor can store up to n blocks, we need enough
|
|
|
|
* buffers to write out full descriptor block.
|
|
|
|
*/
|
2023-08-11 06:36:08 +00:00
|
|
|
err = -ENOMEM;
|
2019-11-05 16:44:09 +00:00
|
|
|
n = journal->j_blocksize / jbd2_min_tag_size();
|
2016-09-15 16:02:32 +00:00
|
|
|
journal->j_wbufsize = n;
|
2020-11-06 03:58:55 +00:00
|
|
|
journal->j_fc_wbuf = NULL;
|
2016-09-15 16:02:32 +00:00
|
|
|
journal->j_wbuf = kmalloc_array(n, sizeof(struct buffer_head *),
|
|
|
|
GFP_KERNEL);
|
2017-03-15 19:08:48 +00:00
|
|
|
if (!journal->j_wbuf)
|
|
|
|
goto err_cleanup;
|
2016-09-15 16:02:32 +00:00
|
|
|
|
2023-08-11 06:36:06 +00:00
|
|
|
err = percpu_counter_init(&journal->j_checkpoint_jh_count, 0,
|
|
|
|
GFP_KERNEL);
|
2023-08-11 06:36:00 +00:00
|
|
|
if (err)
|
2017-03-15 19:08:48 +00:00
|
|
|
goto err_cleanup;
|
2016-09-15 16:02:32 +00:00
|
|
|
|
2021-07-02 22:05:03 +00:00
|
|
|
journal->j_shrink_transaction = NULL;
|
2023-09-11 09:44:30 +00:00
|
|
|
|
|
|
|
journal->j_shrinker = shrinker_alloc(0, "jbd2-journal:(%u:%u)",
|
|
|
|
MAJOR(bdev->bd_dev),
|
|
|
|
MINOR(bdev->bd_dev));
|
|
|
|
if (!journal->j_shrinker) {
|
|
|
|
err = -ENOMEM;
|
2021-07-02 22:05:03 +00:00
|
|
|
goto err_cleanup;
|
2023-09-11 09:44:30 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
journal->j_shrinker->scan_objects = jbd2_journal_shrink_scan;
|
|
|
|
journal->j_shrinker->count_objects = jbd2_journal_shrink_count;
|
|
|
|
journal->j_shrinker->private_data = journal;
|
|
|
|
|
|
|
|
shrinker_register(journal->j_shrinker);
|
2021-07-02 22:05:03 +00:00
|
|
|
|
2006-10-11 08:20:57 +00:00
|
|
|
return journal;
|
2017-03-15 19:08:48 +00:00
|
|
|
|
|
|
|
err_cleanup:
|
2023-08-11 06:36:06 +00:00
|
|
|
percpu_counter_destroy(&journal->j_checkpoint_jh_count);
|
2023-09-11 02:51:38 +00:00
|
|
|
if (journal->j_chksum_driver)
|
|
|
|
crypto_free_shash(journal->j_chksum_driver);
|
2017-03-15 19:08:48 +00:00
|
|
|
kfree(journal->j_wbuf);
|
|
|
|
jbd2_journal_destroy_revoke(journal);
|
2023-08-11 06:36:06 +00:00
|
|
|
journal_fail_superblock(journal);
|
2017-03-15 19:08:48 +00:00
|
|
|
kfree(journal);
|
2023-08-11 06:36:08 +00:00
|
|
|
return ERR_PTR(err);
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
2006-10-11 08:20:59 +00:00
|
|
|
/* jbd2_journal_init_dev and jbd2_journal_init_inode:
|
2006-10-11 08:20:57 +00:00
|
|
|
*
|
|
|
|
* Create a journal structure assigned some fixed set of disk blocks to
|
|
|
|
* the journal. We don't actually touch those disk blocks yet, but we
|
|
|
|
* need to set up all of the mapping information to tell the journaling
|
|
|
|
* system where the journal blocks are.
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
|
|
|
/**
|
2008-04-17 14:38:59 +00:00
|
|
|
* journal_t * jbd2_journal_init_dev() - creates and initialises a journal structure
|
2006-10-11 08:20:57 +00:00
|
|
|
* @bdev: Block device on which to create the journal
|
|
|
|
* @fs_dev: Device which hold journalled filesystem for this journal.
|
|
|
|
* @start: Block nr Start of journal.
|
|
|
|
* @len: Length of the journal in blocks.
|
|
|
|
* @blocksize: blocksize of journalling device
|
2008-04-17 14:38:59 +00:00
|
|
|
*
|
|
|
|
* Returns: a newly created journal_t *
|
2006-10-11 08:20:57 +00:00
|
|
|
*
|
2006-10-11 08:20:59 +00:00
|
|
|
* jbd2_journal_init_dev creates a journal which maps a fixed contiguous
|
2006-10-11 08:20:57 +00:00
|
|
|
* range of blocks on an arbitrary block device.
|
|
|
|
*
|
|
|
|
*/
|
2016-09-15 16:02:32 +00:00
|
|
|
journal_t *jbd2_journal_init_dev(struct block_device *bdev,
|
2006-10-11 08:20:57 +00:00
|
|
|
struct block_device *fs_dev,
|
2006-10-11 08:21:13 +00:00
|
|
|
unsigned long long start, int len, int blocksize)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
2016-09-15 16:02:32 +00:00
|
|
|
journal_t *journal;
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2016-09-15 16:02:32 +00:00
|
|
|
journal = journal_init_common(bdev, fs_dev, start, len, blocksize);
|
2023-08-11 06:36:08 +00:00
|
|
|
if (IS_ERR(journal))
|
|
|
|
return ERR_CAST(journal);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2022-07-13 05:53:17 +00:00
|
|
|
snprintf(journal->j_devname, sizeof(journal->j_devname),
|
|
|
|
"%pg", journal->j_dev);
|
2015-06-25 22:02:38 +00:00
|
|
|
strreplace(journal->j_devname, '/', '!');
|
2009-01-06 19:53:35 +00:00
|
|
|
jbd2_stats_proc_init(journal);
|
|
|
|
|
2006-10-11 08:20:57 +00:00
|
|
|
return journal;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
2006-10-11 08:20:59 +00:00
|
|
|
* journal_t * jbd2_journal_init_inode () - creates a journal which maps to a inode.
|
2006-10-11 08:20:57 +00:00
|
|
|
* @inode: An inode to create the journal in
|
|
|
|
*
|
2006-10-11 08:20:59 +00:00
|
|
|
* jbd2_journal_init_inode creates a journal which maps an on-disk inode as
|
2006-10-11 08:20:57 +00:00
|
|
|
* the journal. The inode must exist already, must support bmap() and
|
|
|
|
* must have all data blocks preallocated.
|
|
|
|
*/
|
2016-09-15 16:02:32 +00:00
|
|
|
journal_t *jbd2_journal_init_inode(struct inode *inode)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
2016-09-15 16:02:32 +00:00
|
|
|
journal_t *journal;
|
2020-01-09 13:30:41 +00:00
|
|
|
sector_t blocknr;
|
|
|
|
int err = 0;
|
|
|
|
|
|
|
|
blocknr = 0;
|
|
|
|
err = bmap(inode, &blocknr);
|
|
|
|
if (err || !blocknr) {
|
2023-08-11 06:36:08 +00:00
|
|
|
pr_err("%s: Cannot locate journal superblock\n", __func__);
|
|
|
|
return err ? ERR_PTR(err) : ERR_PTR(-EINVAL);
|
2016-09-15 16:02:32 +00:00
|
|
|
}
|
|
|
|
|
2022-06-08 11:23:48 +00:00
|
|
|
jbd2_debug(1, "JBD2: inode %s/%ld, size %lld, bits %d, blksize %ld\n",
|
2016-09-15 16:02:32 +00:00
|
|
|
inode->i_sb->s_id, inode->i_ino, (long long) inode->i_size,
|
|
|
|
inode->i_sb->s_blocksize_bits, inode->i_sb->s_blocksize);
|
|
|
|
|
|
|
|
journal = journal_init_common(inode->i_sb->s_bdev, inode->i_sb->s_bdev,
|
|
|
|
blocknr, inode->i_size >> inode->i_sb->s_blocksize_bits,
|
|
|
|
inode->i_sb->s_blocksize);
|
2023-08-11 06:36:08 +00:00
|
|
|
if (IS_ERR(journal))
|
|
|
|
return ERR_CAST(journal);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
journal->j_inode = inode;
|
2022-07-13 05:53:17 +00:00
|
|
|
snprintf(journal->j_devname, sizeof(journal->j_devname),
|
2023-06-05 17:05:51 +00:00
|
|
|
"%pg-%lu", journal->j_dev, journal->j_inode->i_ino);
|
|
|
|
strreplace(journal->j_devname, '/', '!');
|
2008-01-29 04:58:27 +00:00
|
|
|
jbd2_stats_proc_init(journal);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
return journal;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Given a journal_t structure, initialise the various fields for
|
|
|
|
* startup of a new journaling session. We use this both when creating
|
|
|
|
* a journal, and after recovering an old journal to reset it for
|
|
|
|
* subsequent use.
|
|
|
|
*/
|
|
|
|
|
|
|
|
static int journal_reset(journal_t *journal)
|
|
|
|
{
|
|
|
|
journal_superblock_t *sb = journal->j_superblock;
|
2006-10-11 08:21:13 +00:00
|
|
|
unsigned long long first, last;
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
first = be32_to_cpu(sb->s_first);
|
|
|
|
last = be32_to_cpu(sb->s_maxlen);
|
2009-07-17 14:40:01 +00:00
|
|
|
if (first + JBD2_MIN_JOURNAL_BLOCKS > last + 1) {
|
2011-11-01 23:09:18 +00:00
|
|
|
printk(KERN_ERR "JBD2: Journal too short (blocks %llu-%llu).\n",
|
2009-07-17 14:40:01 +00:00
|
|
|
first, last);
|
|
|
|
journal_fail_superblock(journal);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
journal->j_first = first;
|
2020-11-06 03:58:55 +00:00
|
|
|
journal->j_last = last;
|
2020-10-15 20:37:55 +00:00
|
|
|
|
jbd2: continue to record log between each mount
For a newly mounted file system, the journal committing thread always
record new transactions from the start of the journal area, no matter
whether the journal was clean or just has been recovered. So the logdump
code in debugfs cannot dump continuous logs between each mount, it is
disadvantageous to analysis corrupted file system image and locate the
file system inconsistency bugs.
If we get a corrupted file system in the running products and want to
find out what has happened, besides lookup the system log, one effective
way is to backtrack the journal log. But we may not always run e2fsck
before each mount and the default fsck -a mode also cannot always
checkout all inconsistencies, so it could left over some inconsistencies
into the next mount until we detect it. Finally, transactions in the
journal may probably discontinuous and some relatively new transactions
has been covered, it becomes hard to analyse. If we could record
transactions continuously between each mount, we could acquire more
useful info from the journal. Like this:
|Previous mount checkpointed/recovered logs|Current mount logs |
|{------}{---}{--------} ... {------}| ... |{======}{========}...000000|
And yes the journal area is limited and cannot record everything, the
problematic transaction may also be covered even if we do this, but
this is still useful for fuzzy tests and short-running products.
This patch save the head blocknr in the superblock after flushing the
journal or unmounting the file system, let the next mount could continue
to record new transaction behind it. This change is backward compatible
because the old kernel does not care about the head blocknr of the
journal. It is also fine if we mount a clean old image without valid
head blocknr, we fail back to set it to s_first just like before.
Finally, for the case of mount an unclean file system, we could also get
the journal head easily after scanning/replaying the journal, it will
continue to record new transaction after the recovered transactions.
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20230322013353.1843306-2-yi.zhang@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2023-03-22 01:33:51 +00:00
|
|
|
if (journal->j_head != 0 && journal->j_flags & JBD2_CYCLE_RECORD) {
|
|
|
|
/*
|
|
|
|
* Disable the cycled recording mode if the journal head block
|
|
|
|
* number is not correct.
|
|
|
|
*/
|
|
|
|
if (journal->j_head < first || journal->j_head >= last) {
|
|
|
|
printk(KERN_WARNING "JBD2: Incorrect Journal head block %lu, "
|
|
|
|
"disable journal_cycle_record\n",
|
|
|
|
journal->j_head);
|
|
|
|
journal->j_head = journal->j_first;
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
journal->j_head = journal->j_first;
|
|
|
|
}
|
|
|
|
journal->j_tail = journal->j_head;
|
2020-10-15 20:37:55 +00:00
|
|
|
journal->j_free = journal->j_last - journal->j_first;
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
journal->j_tail_sequence = journal->j_transaction_sequence;
|
|
|
|
journal->j_commit_sequence = journal->j_transaction_sequence - 1;
|
|
|
|
journal->j_commit_request = journal->j_commit_sequence;
|
|
|
|
|
2020-11-06 03:58:55 +00:00
|
|
|
/*
|
|
|
|
* Now that journal recovery is done, turn fast commits off here. This
|
|
|
|
* way, if fast commit was enabled before the crash but if now FS has
|
|
|
|
* disabled it, we don't enable fast commits.
|
|
|
|
*/
|
|
|
|
jbd2_clear_feature_fast_commit(journal);
|
|
|
|
|
2006-10-11 08:20:57 +00:00
|
|
|
/*
|
|
|
|
* As a special case, if the on-disk copy is already marked as needing
|
2012-03-13 19:41:04 +00:00
|
|
|
* no recovery (s_start == 0), then we can safely defer the superblock
|
|
|
|
* update until the next commit by setting JBD2_FLUSHED. This avoids
|
2006-10-11 08:20:57 +00:00
|
|
|
* attempting a write to a potential-readonly device.
|
|
|
|
*/
|
2012-03-13 19:41:04 +00:00
|
|
|
if (sb->s_start == 0) {
|
2022-06-08 11:23:48 +00:00
|
|
|
jbd2_debug(1, "JBD2: Skipping superblock update on recovered sb "
|
2019-05-30 19:08:34 +00:00
|
|
|
"(start %ld, seq %u, errno %d)\n",
|
2006-10-11 08:20:57 +00:00
|
|
|
journal->j_tail, journal->j_tail_sequence,
|
|
|
|
journal->j_errno);
|
2012-03-13 19:41:04 +00:00
|
|
|
journal->j_flags |= JBD2_FLUSHED;
|
|
|
|
} else {
|
2012-03-13 19:43:04 +00:00
|
|
|
/* Lock here to make assertions happy... */
|
2016-10-28 16:58:12 +00:00
|
|
|
mutex_lock_io(&journal->j_checkpoint_mutex);
|
2012-03-14 02:22:54 +00:00
|
|
|
/*
|
2016-11-01 13:40:10 +00:00
|
|
|
* Update log tail information. We use REQ_FUA since new
|
2012-03-14 02:22:54 +00:00
|
|
|
* transaction will start reusing journal space and so we
|
|
|
|
* must make sure information about current log tail is on
|
|
|
|
* disk before that.
|
|
|
|
*/
|
|
|
|
jbd2_journal_update_sb_log_tail(journal,
|
|
|
|
journal->j_tail_sequence,
|
2023-11-29 11:47:40 +00:00
|
|
|
journal->j_tail, REQ_FUA);
|
2012-03-13 19:43:04 +00:00
|
|
|
mutex_unlock(&journal->j_checkpoint_mutex);
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
2012-03-13 19:41:04 +00:00
|
|
|
return jbd2_journal_start_thread(journal);
|
|
|
|
}
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2019-02-14 21:27:14 +00:00
|
|
|
/*
|
|
|
|
* This function expects that the caller will have locked the journal
|
|
|
|
* buffer head, and will return with it unlocked
|
|
|
|
*/
|
2022-07-14 18:07:22 +00:00
|
|
|
static int jbd2_write_superblock(journal_t *journal, blk_opf_t write_flags)
|
2012-03-13 19:41:04 +00:00
|
|
|
{
|
|
|
|
struct buffer_head *bh = journal->j_sb_buffer;
|
2013-07-01 12:12:38 +00:00
|
|
|
journal_superblock_t *sb = journal->j_superblock;
|
2022-08-18 05:04:37 +00:00
|
|
|
int ret = 0;
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2019-04-06 22:57:40 +00:00
|
|
|
/* Buffer got discarded which means block device got invalidated */
|
2020-06-20 06:19:48 +00:00
|
|
|
if (!buffer_mapped(bh)) {
|
|
|
|
unlock_buffer(bh);
|
2019-04-06 22:57:40 +00:00
|
|
|
return -EIO;
|
2020-06-20 06:19:48 +00:00
|
|
|
}
|
2019-04-06 22:57:40 +00:00
|
|
|
|
2023-11-29 11:47:40 +00:00
|
|
|
/*
|
|
|
|
* Always set high priority flags to exempt from block layer's
|
|
|
|
* QOS policies, e.g. writeback throttle.
|
|
|
|
*/
|
|
|
|
write_flags |= JBD2_JOURNAL_REQ_FLAGS;
|
2012-03-14 02:22:54 +00:00
|
|
|
if (!(journal->j_flags & JBD2_BARRIER))
|
2016-06-05 19:32:25 +00:00
|
|
|
write_flags &= ~(REQ_FUA | REQ_PREFLUSH);
|
2023-11-29 11:47:39 +00:00
|
|
|
|
|
|
|
trace_jbd2_write_superblock(journal, write_flags);
|
|
|
|
|
2008-10-07 01:35:40 +00:00
|
|
|
if (buffer_write_io_error(bh)) {
|
|
|
|
/*
|
|
|
|
* Oh, dear. A previous attempt to write the journal
|
|
|
|
* superblock failed. This could happen because the
|
|
|
|
* USB device was yanked out. Or it could happen to
|
|
|
|
* be a transient write error and maybe the block will
|
|
|
|
* be remapped. Nothing we can do but to retry the
|
|
|
|
* write and hope for the best.
|
|
|
|
*/
|
|
|
|
printk(KERN_ERR "JBD2: previous I/O error detected "
|
|
|
|
"for journal superblock update for %s.\n",
|
|
|
|
journal->j_devname);
|
|
|
|
clear_buffer_write_io_error(bh);
|
|
|
|
set_buffer_uptodate(bh);
|
|
|
|
}
|
2019-02-14 21:28:14 +00:00
|
|
|
if (jbd2_journal_has_csum_v2or3(journal))
|
|
|
|
sb->s_checksum = jbd2_superblock_csum(journal, sb);
|
2012-03-14 02:22:54 +00:00
|
|
|
get_bh(bh);
|
|
|
|
bh->b_end_io = end_buffer_write_sync;
|
2022-08-18 05:04:37 +00:00
|
|
|
submit_bh(REQ_OP_WRITE | write_flags, bh);
|
2012-03-14 02:22:54 +00:00
|
|
|
wait_on_buffer(bh);
|
2012-03-13 19:41:04 +00:00
|
|
|
if (buffer_write_io_error(bh)) {
|
|
|
|
clear_buffer_write_io_error(bh);
|
|
|
|
set_buffer_uptodate(bh);
|
2012-03-14 02:22:54 +00:00
|
|
|
ret = -EIO;
|
|
|
|
}
|
|
|
|
if (ret) {
|
2022-08-18 05:04:37 +00:00
|
|
|
printk(KERN_ERR "JBD2: I/O error when updating journal superblock for %s.\n",
|
|
|
|
journal->j_devname);
|
2020-06-09 07:35:40 +00:00
|
|
|
if (!is_journal_aborted(journal))
|
|
|
|
jbd2_journal_abort(journal, ret);
|
2012-03-13 19:41:04 +00:00
|
|
|
}
|
2015-06-15 18:36:01 +00:00
|
|
|
|
|
|
|
return ret;
|
2012-03-13 19:41:04 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* jbd2_journal_update_sb_log_tail() - Update log tail in journal sb on disk.
|
|
|
|
* @journal: The journal to update.
|
2012-03-14 02:22:54 +00:00
|
|
|
* @tail_tid: TID of the new transaction at the tail of the log
|
|
|
|
* @tail_block: The first block of the transaction at the tail of the log
|
2022-07-14 18:07:22 +00:00
|
|
|
* @write_flags: Flags for the journal sb write operation
|
2012-03-13 19:41:04 +00:00
|
|
|
*
|
|
|
|
* Update a journal's superblock information about log tail and write it to
|
|
|
|
* disk, waiting for the IO to complete.
|
|
|
|
*/
|
2015-06-15 18:36:01 +00:00
|
|
|
int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid,
|
2022-07-14 18:07:22 +00:00
|
|
|
unsigned long tail_block,
|
|
|
|
blk_opf_t write_flags)
|
2012-03-13 19:41:04 +00:00
|
|
|
{
|
|
|
|
journal_superblock_t *sb = journal->j_superblock;
|
2015-06-15 18:36:01 +00:00
|
|
|
int ret;
|
2012-03-13 19:41:04 +00:00
|
|
|
|
2018-02-19 17:22:53 +00:00
|
|
|
if (is_journal_aborted(journal))
|
|
|
|
return -EIO;
|
2023-12-13 01:32:21 +00:00
|
|
|
if (jbd2_check_fs_dev_write_error(journal)) {
|
2021-06-10 11:24:34 +00:00
|
|
|
jbd2_journal_abort(journal, -EIO);
|
|
|
|
return -EIO;
|
|
|
|
}
|
2018-02-19 17:22:53 +00:00
|
|
|
|
2012-03-13 19:43:04 +00:00
|
|
|
BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
|
2022-06-08 11:23:48 +00:00
|
|
|
jbd2_debug(1, "JBD2: updating superblock (start %lu, seq %u)\n",
|
2012-03-14 02:22:54 +00:00
|
|
|
tail_block, tail_tid);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2019-02-14 21:27:14 +00:00
|
|
|
lock_buffer(journal->j_sb_buffer);
|
2012-03-14 02:22:54 +00:00
|
|
|
sb->s_sequence = cpu_to_be32(tail_tid);
|
|
|
|
sb->s_start = cpu_to_be32(tail_block);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2022-07-14 18:07:22 +00:00
|
|
|
ret = jbd2_write_superblock(journal, write_flags);
|
2015-06-15 18:36:01 +00:00
|
|
|
if (ret)
|
|
|
|
goto out;
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2012-03-13 19:41:04 +00:00
|
|
|
/* Log is no longer empty */
|
|
|
|
write_lock(&journal->j_state_lock);
|
|
|
|
WARN_ON(!sb->s_sequence);
|
|
|
|
journal->j_flags &= ~JBD2_FLUSHED;
|
|
|
|
write_unlock(&journal->j_state_lock);
|
2015-06-15 18:36:01 +00:00
|
|
|
|
|
|
|
out:
|
|
|
|
return ret;
|
2012-03-13 19:41:04 +00:00
|
|
|
}
|
2012-02-20 22:53:01 +00:00
|
|
|
|
2012-03-13 19:41:04 +00:00
|
|
|
/**
|
|
|
|
* jbd2_mark_journal_empty() - Mark on disk journal as empty.
|
|
|
|
* @journal: The journal to update.
|
2022-07-14 18:07:22 +00:00
|
|
|
* @write_flags: Flags for the journal sb write operation
|
2012-03-13 19:41:04 +00:00
|
|
|
*
|
|
|
|
* Update a journal's dynamic superblock fields to show that journal is empty.
|
|
|
|
* Write updated superblock to disk waiting for IO to complete.
|
|
|
|
*/
|
2022-07-14 18:07:22 +00:00
|
|
|
static void jbd2_mark_journal_empty(journal_t *journal, blk_opf_t write_flags)
|
2012-03-13 19:41:04 +00:00
|
|
|
{
|
|
|
|
journal_superblock_t *sb = journal->j_superblock;
|
2020-10-15 20:37:56 +00:00
|
|
|
bool had_fast_commit = false;
|
2008-10-07 01:35:40 +00:00
|
|
|
|
2012-03-13 19:43:04 +00:00
|
|
|
BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
|
2019-02-14 21:27:14 +00:00
|
|
|
lock_buffer(journal->j_sb_buffer);
|
|
|
|
if (sb->s_start == 0) { /* Is it already empty? */
|
|
|
|
unlock_buffer(journal->j_sb_buffer);
|
2012-08-19 02:29:40 +00:00
|
|
|
return;
|
|
|
|
}
|
2019-02-14 21:27:14 +00:00
|
|
|
|
2022-06-08 11:23:48 +00:00
|
|
|
jbd2_debug(1, "JBD2: Marking journal as empty (seq %u)\n",
|
2012-03-13 19:41:04 +00:00
|
|
|
journal->j_tail_sequence);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
sb->s_sequence = cpu_to_be32(journal->j_tail_sequence);
|
2012-03-13 19:41:04 +00:00
|
|
|
sb->s_start = cpu_to_be32(0);
|
jbd2: continue to record log between each mount
For a newly mounted file system, the journal committing thread always
record new transactions from the start of the journal area, no matter
whether the journal was clean or just has been recovered. So the logdump
code in debugfs cannot dump continuous logs between each mount, it is
disadvantageous to analysis corrupted file system image and locate the
file system inconsistency bugs.
If we get a corrupted file system in the running products and want to
find out what has happened, besides lookup the system log, one effective
way is to backtrack the journal log. But we may not always run e2fsck
before each mount and the default fsck -a mode also cannot always
checkout all inconsistencies, so it could left over some inconsistencies
into the next mount until we detect it. Finally, transactions in the
journal may probably discontinuous and some relatively new transactions
has been covered, it becomes hard to analyse. If we could record
transactions continuously between each mount, we could acquire more
useful info from the journal. Like this:
|Previous mount checkpointed/recovered logs|Current mount logs |
|{------}{---}{--------} ... {------}| ... |{======}{========}...000000|
And yes the journal area is limited and cannot record everything, the
problematic transaction may also be covered even if we do this, but
this is still useful for fuzzy tests and short-running products.
This patch save the head blocknr in the superblock after flushing the
journal or unmounting the file system, let the next mount could continue
to record new transaction behind it. This change is backward compatible
because the old kernel does not care about the head blocknr of the
journal. It is also fine if we mount a clean old image without valid
head blocknr, we fail back to set it to s_first just like before.
Finally, for the case of mount an unclean file system, we could also get
the journal head easily after scanning/replaying the journal, it will
continue to record new transaction after the recovered transactions.
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20230322013353.1843306-2-yi.zhang@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2023-03-22 01:33:51 +00:00
|
|
|
sb->s_head = cpu_to_be32(journal->j_head);
|
2020-10-15 20:37:56 +00:00
|
|
|
if (jbd2_has_feature_fast_commit(journal)) {
|
|
|
|
/*
|
|
|
|
* When journal is clean, no need to commit fast commit flag and
|
|
|
|
* make file system incompatible with older kernels.
|
|
|
|
*/
|
|
|
|
jbd2_clear_feature_fast_commit(journal);
|
|
|
|
had_fast_commit = true;
|
|
|
|
}
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2022-07-14 18:07:22 +00:00
|
|
|
jbd2_write_superblock(journal, write_flags);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2020-10-15 20:37:56 +00:00
|
|
|
if (had_fast_commit)
|
|
|
|
jbd2_set_feature_fast_commit(journal);
|
|
|
|
|
2012-03-13 19:41:04 +00:00
|
|
|
/* Log is no longer empty */
|
2010-08-04 01:35:12 +00:00
|
|
|
write_lock(&journal->j_state_lock);
|
2012-03-13 19:41:04 +00:00
|
|
|
journal->j_flags |= JBD2_FLUSHED;
|
2010-08-04 01:35:12 +00:00
|
|
|
write_unlock(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
2021-05-18 15:13:25 +00:00
|
|
|
/**
|
|
|
|
* __jbd2_journal_erase() - Discard or zeroout journal blocks (excluding superblock)
|
|
|
|
* @journal: The journal to erase.
|
|
|
|
* @flags: A discard/zeroout request is sent for each physically contigous
|
|
|
|
* region of the journal. Either JBD2_JOURNAL_FLUSH_DISCARD or
|
|
|
|
* JBD2_JOURNAL_FLUSH_ZEROOUT must be set to determine which operation
|
|
|
|
* to perform.
|
|
|
|
*
|
|
|
|
* Note: JBD2_JOURNAL_FLUSH_ZEROOUT attempts to use hardware offload. Zeroes
|
|
|
|
* will be explicitly written if no hardware offload is available, see
|
|
|
|
* blkdev_issue_zeroout for more details.
|
|
|
|
*/
|
|
|
|
static int __jbd2_journal_erase(journal_t *journal, unsigned int flags)
|
|
|
|
{
|
|
|
|
int err = 0;
|
|
|
|
unsigned long block, log_offset; /* logical */
|
|
|
|
unsigned long long phys_block, block_start, block_stop; /* physical */
|
|
|
|
loff_t byte_start, byte_stop, byte_count;
|
|
|
|
|
|
|
|
/* flags must be set to either discard or zeroout */
|
|
|
|
if ((flags & ~JBD2_JOURNAL_FLUSH_VALID) || !flags ||
|
|
|
|
((flags & JBD2_JOURNAL_FLUSH_DISCARD) &&
|
|
|
|
(flags & JBD2_JOURNAL_FLUSH_ZEROOUT)))
|
|
|
|
return -EINVAL;
|
|
|
|
|
2022-04-15 04:52:55 +00:00
|
|
|
if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) &&
|
|
|
|
!bdev_max_discard_sectors(journal->j_dev))
|
2021-05-18 15:13:25 +00:00
|
|
|
return -EOPNOTSUPP;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* lookup block mapping and issue discard/zeroout for each
|
|
|
|
* contiguous region
|
|
|
|
*/
|
|
|
|
log_offset = be32_to_cpu(journal->j_superblock->s_first);
|
|
|
|
block_start = ~0ULL;
|
|
|
|
for (block = log_offset; block < journal->j_total_len; block++) {
|
|
|
|
err = jbd2_journal_bmap(journal, block, &phys_block);
|
|
|
|
if (err) {
|
|
|
|
pr_err("JBD2: bad block at offset %lu", block);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (block_start == ~0ULL) {
|
|
|
|
block_start = phys_block;
|
|
|
|
block_stop = block_start - 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* last block not contiguous with current block,
|
|
|
|
* process last contiguous region and return to this block on
|
|
|
|
* next loop
|
|
|
|
*/
|
|
|
|
if (phys_block != block_stop + 1) {
|
|
|
|
block--;
|
|
|
|
} else {
|
|
|
|
block_stop++;
|
|
|
|
/*
|
|
|
|
* if this isn't the last block of journal,
|
|
|
|
* no need to process now because next block may also
|
|
|
|
* be part of this contiguous region
|
|
|
|
*/
|
|
|
|
if (block != journal->j_total_len - 1)
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* end of contiguous region or this is last block of journal,
|
|
|
|
* take care of the region
|
|
|
|
*/
|
|
|
|
byte_start = block_start * journal->j_blocksize;
|
|
|
|
byte_stop = block_stop * journal->j_blocksize;
|
|
|
|
byte_count = (block_stop - block_start + 1) *
|
|
|
|
journal->j_blocksize;
|
|
|
|
|
2024-04-11 14:53:37 +00:00
|
|
|
truncate_inode_pages_range(journal->j_dev->bd_mapping,
|
2021-05-18 15:13:25 +00:00
|
|
|
byte_start, byte_stop);
|
|
|
|
|
|
|
|
if (flags & JBD2_JOURNAL_FLUSH_DISCARD) {
|
|
|
|
err = blkdev_issue_discard(journal->j_dev,
|
|
|
|
byte_start >> SECTOR_SHIFT,
|
|
|
|
byte_count >> SECTOR_SHIFT,
|
2022-04-15 04:52:57 +00:00
|
|
|
GFP_NOFS);
|
2021-05-18 15:13:25 +00:00
|
|
|
} else if (flags & JBD2_JOURNAL_FLUSH_ZEROOUT) {
|
|
|
|
err = blkdev_issue_zeroout(journal->j_dev,
|
|
|
|
byte_start >> SECTOR_SHIFT,
|
|
|
|
byte_count >> SECTOR_SHIFT,
|
|
|
|
GFP_NOFS, 0);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (unlikely(err != 0)) {
|
|
|
|
pr_err("JBD2: (error %d) unable to wipe journal at physical blocks %llu - %llu",
|
|
|
|
err, block_start, block_stop);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* reset start and stop after processing a region */
|
|
|
|
block_start = ~0ULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
return blkdev_issue_flush(journal->j_dev);
|
|
|
|
}
|
2012-03-13 19:41:04 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* jbd2_journal_update_sb_errno() - Update error in the journal.
|
|
|
|
* @journal: The journal to update.
|
|
|
|
*
|
|
|
|
* Update a journal's errno. Write updated superblock to disk waiting for IO
|
|
|
|
* to complete.
|
|
|
|
*/
|
2012-08-05 23:04:57 +00:00
|
|
|
void jbd2_journal_update_sb_errno(journal_t *journal)
|
2012-03-13 19:41:04 +00:00
|
|
|
{
|
|
|
|
journal_superblock_t *sb = journal->j_superblock;
|
2018-02-19 04:45:18 +00:00
|
|
|
int errcode;
|
2012-03-13 19:41:04 +00:00
|
|
|
|
2019-02-14 21:27:14 +00:00
|
|
|
lock_buffer(journal->j_sb_buffer);
|
2018-02-19 04:45:18 +00:00
|
|
|
errcode = journal->j_errno;
|
|
|
|
if (errcode == -ESHUTDOWN)
|
|
|
|
errcode = 0;
|
2022-06-08 11:23:48 +00:00
|
|
|
jbd2_debug(1, "JBD2: updating superblock error (errno %d)\n", errcode);
|
2018-02-19 04:45:18 +00:00
|
|
|
sb->s_errno = cpu_to_be32(errcode);
|
2012-03-13 19:41:04 +00:00
|
|
|
|
2023-11-29 11:47:40 +00:00
|
|
|
jbd2_write_superblock(journal, REQ_FUA);
|
2012-03-13 19:41:04 +00:00
|
|
|
}
|
2012-08-05 23:04:57 +00:00
|
|
|
EXPORT_SYMBOL(jbd2_journal_update_sb_errno);
|
2012-03-13 19:41:04 +00:00
|
|
|
|
2006-10-11 08:20:57 +00:00
|
|
|
/**
|
2020-11-16 10:18:08 +00:00
|
|
|
* jbd2_journal_load() - Read journal from disk.
|
2006-10-11 08:20:57 +00:00
|
|
|
* @journal: Journal to act on.
|
|
|
|
*
|
|
|
|
* Given a journal_t structure which tells us which disk blocks contain
|
|
|
|
* a journal, read the journal from disk to initialise the in-memory
|
|
|
|
* structures.
|
|
|
|
*/
|
2006-10-11 08:20:59 +00:00
|
|
|
int jbd2_journal_load(journal_t *journal)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
|
|
|
int err;
|
2023-08-11 06:36:00 +00:00
|
|
|
journal_superblock_t *sb = journal->j_superblock;
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2009-12-07 15:36:20 +00:00
|
|
|
/*
|
|
|
|
* Create a slab for this blocksize
|
|
|
|
*/
|
|
|
|
err = jbd2_journal_create_slab(be32_to_cpu(sb->s_blocksize));
|
|
|
|
if (err)
|
|
|
|
return err;
|
|
|
|
|
2006-10-11 08:20:57 +00:00
|
|
|
/* Let the recovery code check whether it needs to recover any
|
|
|
|
* data from the journal. */
|
2023-04-13 09:57:39 +00:00
|
|
|
err = jbd2_journal_recover(journal);
|
|
|
|
if (err) {
|
|
|
|
pr_warn("JBD2: journal recovery failed\n");
|
|
|
|
return err;
|
|
|
|
}
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2009-11-15 20:31:37 +00:00
|
|
|
if (journal->j_failed_commit) {
|
|
|
|
printk(KERN_ERR "JBD2: journal transaction %u on %s "
|
|
|
|
"is corrupt.\n", journal->j_failed_commit,
|
|
|
|
journal->j_devname);
|
2015-10-17 20:16:04 +00:00
|
|
|
return -EFSCORRUPTED;
|
2009-11-15 20:31:37 +00:00
|
|
|
}
|
2020-01-11 02:25:42 +00:00
|
|
|
/*
|
|
|
|
* clear JBD2_ABORT flag initialized in journal_init_common
|
|
|
|
* here to update log tail information with the newest seq.
|
|
|
|
*/
|
|
|
|
journal->j_flags &= ~JBD2_ABORT;
|
2009-11-15 20:31:37 +00:00
|
|
|
|
2006-10-11 08:20:57 +00:00
|
|
|
/* OK, we've finished with the dynamic journal bits:
|
|
|
|
* reinitialise the dynamic contents of the superblock in memory
|
|
|
|
* and reset them on disk. */
|
2023-04-13 09:57:39 +00:00
|
|
|
err = journal_reset(journal);
|
|
|
|
if (err) {
|
|
|
|
pr_warn("JBD2: journal reset failed\n");
|
|
|
|
return err;
|
|
|
|
}
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2006-10-11 08:20:59 +00:00
|
|
|
journal->j_flags |= JBD2_LOADED;
|
2006-10-11 08:20:57 +00:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
2020-11-16 10:18:08 +00:00
|
|
|
* jbd2_journal_destroy() - Release a journal_t structure.
|
2006-10-11 08:20:57 +00:00
|
|
|
* @journal: Journal to act on.
|
|
|
|
*
|
|
|
|
* Release a journal_t structure once it is no longer in use by the
|
|
|
|
* journaled object.
|
2008-10-11 00:29:13 +00:00
|
|
|
* Return <0 if we couldn't clean up the journal.
|
2006-10-11 08:20:57 +00:00
|
|
|
*/
|
2008-10-11 00:29:13 +00:00
|
|
|
int jbd2_journal_destroy(journal_t *journal)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
2008-10-11 00:29:13 +00:00
|
|
|
int err = 0;
|
|
|
|
|
2006-10-11 08:20:57 +00:00
|
|
|
/* Wait for the commit thread to wake up and die. */
|
|
|
|
journal_kill_thread(journal);
|
|
|
|
|
|
|
|
/* Force a final log commit */
|
|
|
|
if (journal->j_running_transaction)
|
2006-10-11 08:20:59 +00:00
|
|
|
jbd2_journal_commit_transaction(journal);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
/* Force any old transactions to disk */
|
|
|
|
|
|
|
|
/* Totally anal locking here... */
|
|
|
|
spin_lock(&journal->j_list_lock);
|
|
|
|
while (journal->j_checkpoint_transactions != NULL) {
|
|
|
|
spin_unlock(&journal->j_list_lock);
|
2016-10-28 16:58:12 +00:00
|
|
|
mutex_lock_io(&journal->j_checkpoint_mutex);
|
2015-07-28 18:57:14 +00:00
|
|
|
err = jbd2_log_do_checkpoint(journal);
|
2008-11-05 05:09:22 +00:00
|
|
|
mutex_unlock(&journal->j_checkpoint_mutex);
|
2015-07-28 18:57:14 +00:00
|
|
|
/*
|
|
|
|
* If checkpointing failed, just free the buffers to avoid
|
|
|
|
* looping forever
|
|
|
|
*/
|
|
|
|
if (err) {
|
|
|
|
jbd2_journal_destroy_checkpoint(journal);
|
|
|
|
spin_lock(&journal->j_list_lock);
|
|
|
|
break;
|
|
|
|
}
|
2006-10-11 08:20:57 +00:00
|
|
|
spin_lock(&journal->j_list_lock);
|
|
|
|
}
|
|
|
|
|
|
|
|
J_ASSERT(journal->j_running_transaction == NULL);
|
|
|
|
J_ASSERT(journal->j_committing_transaction == NULL);
|
|
|
|
J_ASSERT(journal->j_checkpoint_transactions == NULL);
|
|
|
|
spin_unlock(&journal->j_list_lock);
|
|
|
|
|
2021-06-10 11:24:34 +00:00
|
|
|
/*
|
|
|
|
* OK, all checkpoint transactions have been checked, now check the
|
2023-12-13 01:32:21 +00:00
|
|
|
* writeback errseq of fs dev and abort the journal if some buffer
|
|
|
|
* failed to write back to the original location, otherwise the
|
|
|
|
* filesystem may become inconsistent.
|
2021-06-10 11:24:34 +00:00
|
|
|
*/
|
|
|
|
if (!is_journal_aborted(journal) &&
|
2023-12-13 01:32:21 +00:00
|
|
|
jbd2_check_fs_dev_write_error(journal))
|
2021-06-10 11:24:34 +00:00
|
|
|
jbd2_journal_abort(journal, -EIO);
|
|
|
|
|
2006-10-11 08:20:57 +00:00
|
|
|
if (journal->j_sb_buffer) {
|
2008-10-11 00:29:13 +00:00
|
|
|
if (!is_journal_aborted(journal)) {
|
2016-10-28 16:58:12 +00:00
|
|
|
mutex_lock_io(&journal->j_checkpoint_mutex);
|
jbd2: fix FS corruption possibility in jbd2_journal_destroy() on umount path
On umount path, jbd2_journal_destroy() writes latest transaction ID
(->j_tail_sequence) to be used at next mount.
The bug is that ->j_tail_sequence is not holding latest transaction ID
in some cases. So, at next mount, there is chance to conflict with
remaining (not overwritten yet) transactions.
mount (id=10)
write transaction (id=11)
write transaction (id=12)
umount (id=10) <= the bug doesn't write latest ID
mount (id=10)
write transaction (id=11)
crash
mount
[recovery process]
transaction (id=11)
transaction (id=12) <= valid transaction ID, but old commit
must not replay
Like above, this bug become the cause of recovery failure, or FS
corruption.
So why ->j_tail_sequence doesn't point latest ID?
Because if checkpoint transactions was reclaimed by memory pressure
(i.e. bdev_try_to_free_page()), then ->j_tail_sequence is not updated.
(And another case is, __jbd2_journal_clean_checkpoint_list() is called
with empty transaction.)
So in above cases, ->j_tail_sequence is not pointing latest
transaction ID at umount path. Plus, REQ_FLUSH for checkpoint is not
done too.
So, to fix this problem with minimum changes, this patch updates
->j_tail_sequence, and issue REQ_FLUSH. (With more complex changes,
some optimizations would be possible to avoid unnecessary REQ_FLUSH
for example though.)
BTW,
journal->j_tail_sequence =
++journal->j_transaction_sequence;
Increment of ->j_transaction_sequence seems to be unnecessary, but
ext3 does this.
Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@vger.kernel.org
2016-03-10 04:47:25 +00:00
|
|
|
|
|
|
|
write_lock(&journal->j_state_lock);
|
|
|
|
journal->j_tail_sequence =
|
|
|
|
++journal->j_transaction_sequence;
|
|
|
|
write_unlock(&journal->j_state_lock);
|
|
|
|
|
2023-11-29 11:47:40 +00:00
|
|
|
jbd2_mark_journal_empty(journal, REQ_PREFLUSH | REQ_FUA);
|
2012-03-13 19:43:04 +00:00
|
|
|
mutex_unlock(&journal->j_checkpoint_mutex);
|
|
|
|
} else
|
2008-10-11 00:29:13 +00:00
|
|
|
err = -EIO;
|
2006-10-11 08:20:57 +00:00
|
|
|
brelse(journal->j_sb_buffer);
|
|
|
|
}
|
|
|
|
|
2023-09-11 09:44:30 +00:00
|
|
|
if (journal->j_shrinker) {
|
2021-07-02 22:05:03 +00:00
|
|
|
percpu_counter_destroy(&journal->j_checkpoint_jh_count);
|
2023-09-11 09:44:30 +00:00
|
|
|
shrinker_free(journal->j_shrinker);
|
2021-07-02 22:05:03 +00:00
|
|
|
}
|
2008-01-29 04:58:27 +00:00
|
|
|
if (journal->j_proc_entry)
|
|
|
|
jbd2_stats_proc_exit(journal);
|
2014-11-26 01:02:37 +00:00
|
|
|
iput(journal->j_inode);
|
2006-10-11 08:20:57 +00:00
|
|
|
if (journal->j_revoke)
|
2006-10-11 08:20:59 +00:00
|
|
|
jbd2_journal_destroy_revoke(journal);
|
2012-05-27 11:50:56 +00:00
|
|
|
if (journal->j_chksum_driver)
|
|
|
|
crypto_free_shash(journal->j_chksum_driver);
|
2020-11-06 03:58:55 +00:00
|
|
|
kfree(journal->j_fc_wbuf);
|
2006-10-11 08:20:57 +00:00
|
|
|
kfree(journal->j_wbuf);
|
|
|
|
kfree(journal);
|
2008-10-11 00:29:13 +00:00
|
|
|
|
|
|
|
return err;
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/**
|
2020-11-16 10:18:08 +00:00
|
|
|
* jbd2_journal_check_used_features() - Check if features specified are used.
|
2006-10-11 08:20:57 +00:00
|
|
|
* @journal: Journal to check.
|
|
|
|
* @compat: bitmask of compatible features
|
|
|
|
* @ro: bitmask of features that force read-only mount
|
|
|
|
* @incompat: bitmask of incompatible features
|
|
|
|
*
|
|
|
|
* Check whether the journal uses all of a given set of
|
|
|
|
* features. Return true (non-zero) if it does.
|
|
|
|
**/
|
|
|
|
|
2020-07-18 12:57:37 +00:00
|
|
|
int jbd2_journal_check_used_features(journal_t *journal, unsigned long compat,
|
2006-10-11 08:20:57 +00:00
|
|
|
unsigned long ro, unsigned long incompat)
|
|
|
|
{
|
|
|
|
journal_superblock_t *sb;
|
|
|
|
|
|
|
|
if (!compat && !ro && !incompat)
|
|
|
|
return 1;
|
2023-03-15 01:31:26 +00:00
|
|
|
if (!jbd2_format_support_feature(journal))
|
2006-10-11 08:20:57 +00:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
sb = journal->j_superblock;
|
|
|
|
|
|
|
|
if (((be32_to_cpu(sb->s_feature_compat) & compat) == compat) &&
|
|
|
|
((be32_to_cpu(sb->s_feature_ro_compat) & ro) == ro) &&
|
|
|
|
((be32_to_cpu(sb->s_feature_incompat) & incompat) == incompat))
|
|
|
|
return 1;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
2020-11-16 10:18:08 +00:00
|
|
|
* jbd2_journal_check_available_features() - Check feature set in journalling layer
|
2006-10-11 08:20:57 +00:00
|
|
|
* @journal: Journal to check.
|
|
|
|
* @compat: bitmask of compatible features
|
|
|
|
* @ro: bitmask of features that force read-only mount
|
|
|
|
* @incompat: bitmask of incompatible features
|
|
|
|
*
|
|
|
|
* Check whether the journaling code supports the use of
|
|
|
|
* all of a given set of features on this journal. Return true
|
|
|
|
* (non-zero) if it can. */
|
|
|
|
|
2020-07-18 12:57:37 +00:00
|
|
|
int jbd2_journal_check_available_features(journal_t *journal, unsigned long compat,
|
2006-10-11 08:20:57 +00:00
|
|
|
unsigned long ro, unsigned long incompat)
|
|
|
|
{
|
|
|
|
if (!compat && !ro && !incompat)
|
|
|
|
return 1;
|
|
|
|
|
2023-03-15 01:31:26 +00:00
|
|
|
if (!jbd2_format_support_feature(journal))
|
2006-10-11 08:20:57 +00:00
|
|
|
return 0;
|
|
|
|
|
2006-10-11 08:20:59 +00:00
|
|
|
if ((compat & JBD2_KNOWN_COMPAT_FEATURES) == compat &&
|
|
|
|
(ro & JBD2_KNOWN_ROCOMPAT_FEATURES) == ro &&
|
|
|
|
(incompat & JBD2_KNOWN_INCOMPAT_FEATURES) == incompat)
|
2006-10-11 08:20:57 +00:00
|
|
|
return 1;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2020-11-06 03:58:55 +00:00
|
|
|
static int
|
|
|
|
jbd2_journal_initialize_fast_commit(journal_t *journal)
|
|
|
|
{
|
|
|
|
journal_superblock_t *sb = journal->j_superblock;
|
|
|
|
unsigned long long num_fc_blks;
|
|
|
|
|
2020-11-20 20:22:32 +00:00
|
|
|
num_fc_blks = jbd2_journal_get_num_fc_blks(sb);
|
2020-11-06 03:58:55 +00:00
|
|
|
if (journal->j_last - num_fc_blks < JBD2_MIN_JOURNAL_BLOCKS)
|
|
|
|
return -ENOSPC;
|
|
|
|
|
|
|
|
/* Are we called twice? */
|
|
|
|
WARN_ON(journal->j_fc_wbuf != NULL);
|
|
|
|
journal->j_fc_wbuf = kmalloc_array(num_fc_blks,
|
|
|
|
sizeof(struct buffer_head *), GFP_KERNEL);
|
|
|
|
if (!journal->j_fc_wbuf)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
journal->j_fc_wbufsize = num_fc_blks;
|
|
|
|
journal->j_fc_last = journal->j_last;
|
|
|
|
journal->j_last = journal->j_fc_last - num_fc_blks;
|
|
|
|
journal->j_fc_first = journal->j_last + 1;
|
|
|
|
journal->j_fc_off = 0;
|
|
|
|
journal->j_free = journal->j_last - journal->j_first;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2006-10-11 08:20:57 +00:00
|
|
|
/**
|
2020-11-16 10:18:08 +00:00
|
|
|
* jbd2_journal_set_features() - Mark a given journal feature in the superblock
|
2006-10-11 08:20:57 +00:00
|
|
|
* @journal: Journal to act on.
|
|
|
|
* @compat: bitmask of compatible features
|
|
|
|
* @ro: bitmask of features that force read-only mount
|
|
|
|
* @incompat: bitmask of incompatible features
|
|
|
|
*
|
|
|
|
* Mark a given journal feature as present on the
|
|
|
|
* superblock. Returns true if the requested features could be set.
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
2020-07-18 12:57:37 +00:00
|
|
|
int jbd2_journal_set_features(journal_t *journal, unsigned long compat,
|
2006-10-11 08:20:57 +00:00
|
|
|
unsigned long ro, unsigned long incompat)
|
|
|
|
{
|
2012-05-27 11:48:56 +00:00
|
|
|
#define INCOMPAT_FEATURE_ON(f) \
|
|
|
|
((incompat & (f)) && !(sb->s_feature_incompat & cpu_to_be32(f)))
|
|
|
|
#define COMPAT_FEATURE_ON(f) \
|
|
|
|
((compat & (f)) && !(sb->s_feature_compat & cpu_to_be32(f)))
|
2006-10-11 08:20:57 +00:00
|
|
|
journal_superblock_t *sb;
|
|
|
|
|
2006-10-11 08:20:59 +00:00
|
|
|
if (jbd2_journal_check_used_features(journal, compat, ro, incompat))
|
2006-10-11 08:20:57 +00:00
|
|
|
return 1;
|
|
|
|
|
2006-10-11 08:20:59 +00:00
|
|
|
if (!jbd2_journal_check_available_features(journal, compat, ro, incompat))
|
2006-10-11 08:20:57 +00:00
|
|
|
return 0;
|
|
|
|
|
2014-08-27 22:40:07 +00:00
|
|
|
/* If enabling v2 checksums, turn on v3 instead */
|
|
|
|
if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V2) {
|
|
|
|
incompat &= ~JBD2_FEATURE_INCOMPAT_CSUM_V2;
|
|
|
|
incompat |= JBD2_FEATURE_INCOMPAT_CSUM_V3;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Asking for checksumming v3 and v1? Only give them v3. */
|
|
|
|
if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V3 &&
|
2012-05-27 11:48:56 +00:00
|
|
|
compat & JBD2_FEATURE_COMPAT_CHECKSUM)
|
|
|
|
compat &= ~JBD2_FEATURE_COMPAT_CHECKSUM;
|
|
|
|
|
2022-06-08 11:23:48 +00:00
|
|
|
jbd2_debug(1, "Setting new features 0x%lx/0x%lx/0x%lx\n",
|
2006-10-11 08:20:57 +00:00
|
|
|
compat, ro, incompat);
|
|
|
|
|
|
|
|
sb = journal->j_superblock;
|
|
|
|
|
2020-11-06 03:58:55 +00:00
|
|
|
if (incompat & JBD2_FEATURE_INCOMPAT_FAST_COMMIT) {
|
|
|
|
if (jbd2_journal_initialize_fast_commit(journal)) {
|
|
|
|
pr_err("JBD2: Cannot enable fast commits.\n");
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2019-02-14 21:27:14 +00:00
|
|
|
/* Load the checksum driver if necessary */
|
|
|
|
if ((journal->j_chksum_driver == NULL) &&
|
|
|
|
INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
|
|
|
|
journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0);
|
|
|
|
if (IS_ERR(journal->j_chksum_driver)) {
|
|
|
|
printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n");
|
|
|
|
journal->j_chksum_driver = NULL;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
/* Precompute checksum seed for all metadata */
|
|
|
|
journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid,
|
|
|
|
sizeof(sb->s_uuid));
|
|
|
|
}
|
|
|
|
|
|
|
|
lock_buffer(journal->j_sb_buffer);
|
|
|
|
|
2014-08-27 22:40:07 +00:00
|
|
|
/* If enabling v3 checksums, update superblock */
|
|
|
|
if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
|
2012-05-27 11:48:56 +00:00
|
|
|
sb->s_checksum_type = JBD2_CRC32C_CHKSUM;
|
|
|
|
sb->s_feature_compat &=
|
|
|
|
~cpu_to_be32(JBD2_FEATURE_COMPAT_CHECKSUM);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* If enabling v1 checksums, downgrade superblock */
|
|
|
|
if (COMPAT_FEATURE_ON(JBD2_FEATURE_COMPAT_CHECKSUM))
|
|
|
|
sb->s_feature_incompat &=
|
2014-08-27 22:40:07 +00:00
|
|
|
~cpu_to_be32(JBD2_FEATURE_INCOMPAT_CSUM_V2 |
|
|
|
|
JBD2_FEATURE_INCOMPAT_CSUM_V3);
|
2012-05-27 11:48:56 +00:00
|
|
|
|
2006-10-11 08:20:57 +00:00
|
|
|
sb->s_feature_compat |= cpu_to_be32(compat);
|
|
|
|
sb->s_feature_ro_compat |= cpu_to_be32(ro);
|
|
|
|
sb->s_feature_incompat |= cpu_to_be32(incompat);
|
2019-02-14 21:27:14 +00:00
|
|
|
unlock_buffer(journal->j_sb_buffer);
|
2024-06-24 17:01:18 +00:00
|
|
|
jbd2_journal_init_transaction_limits(journal);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
return 1;
|
2012-05-27 11:48:56 +00:00
|
|
|
#undef COMPAT_FEATURE_ON
|
|
|
|
#undef INCOMPAT_FEATURE_ON
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
2008-01-29 04:58:27 +00:00
|
|
|
/*
|
2020-11-16 10:18:08 +00:00
|
|
|
* jbd2_journal_clear_features() - Clear a given journal feature in the
|
2008-01-29 04:58:27 +00:00
|
|
|
* superblock
|
|
|
|
* @journal: Journal to act on.
|
|
|
|
* @compat: bitmask of compatible features
|
|
|
|
* @ro: bitmask of features that force read-only mount
|
|
|
|
* @incompat: bitmask of incompatible features
|
|
|
|
*
|
|
|
|
* Clear a given journal feature as present on the
|
|
|
|
* superblock.
|
|
|
|
*/
|
|
|
|
void jbd2_journal_clear_features(journal_t *journal, unsigned long compat,
|
|
|
|
unsigned long ro, unsigned long incompat)
|
|
|
|
{
|
|
|
|
journal_superblock_t *sb;
|
|
|
|
|
2022-06-08 11:23:48 +00:00
|
|
|
jbd2_debug(1, "Clear features 0x%lx/0x%lx/0x%lx\n",
|
2008-01-29 04:58:27 +00:00
|
|
|
compat, ro, incompat);
|
|
|
|
|
|
|
|
sb = journal->j_superblock;
|
|
|
|
|
|
|
|
sb->s_feature_compat &= ~cpu_to_be32(compat);
|
|
|
|
sb->s_feature_ro_compat &= ~cpu_to_be32(ro);
|
|
|
|
sb->s_feature_incompat &= ~cpu_to_be32(incompat);
|
2024-06-24 17:01:18 +00:00
|
|
|
jbd2_journal_init_transaction_limits(journal);
|
2008-01-29 04:58:27 +00:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(jbd2_journal_clear_features);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
/**
|
2020-11-16 10:18:08 +00:00
|
|
|
* jbd2_journal_flush() - Flush journal
|
2006-10-11 08:20:57 +00:00
|
|
|
* @journal: Journal to act on.
|
2021-05-18 15:13:25 +00:00
|
|
|
* @flags: optional operation on the journal blocks after the flush (see below)
|
2006-10-11 08:20:57 +00:00
|
|
|
*
|
|
|
|
* Flush all data for a given journal to disk and empty the journal.
|
|
|
|
* Filesystems can use this when remounting readonly to ensure that
|
2021-05-18 15:13:25 +00:00
|
|
|
* recovery does not need to happen on remount. Optionally, a discard or zeroout
|
|
|
|
* can be issued on the journal blocks after flushing.
|
|
|
|
*
|
|
|
|
* flags:
|
|
|
|
* JBD2_JOURNAL_FLUSH_DISCARD: issues discards for the journal blocks
|
|
|
|
* JBD2_JOURNAL_FLUSH_ZEROOUT: issues zeroouts for the journal blocks
|
2006-10-11 08:20:57 +00:00
|
|
|
*/
|
2021-05-18 15:13:25 +00:00
|
|
|
int jbd2_journal_flush(journal_t *journal, unsigned int flags)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
|
|
|
int err = 0;
|
|
|
|
transaction_t *transaction = NULL;
|
|
|
|
|
2010-08-04 01:35:12 +00:00
|
|
|
write_lock(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
/* Force everything buffered to the log... */
|
|
|
|
if (journal->j_running_transaction) {
|
|
|
|
transaction = journal->j_running_transaction;
|
2006-10-11 08:20:59 +00:00
|
|
|
__jbd2_log_start_commit(journal, transaction->t_tid);
|
2006-10-11 08:20:57 +00:00
|
|
|
} else if (journal->j_committing_transaction)
|
|
|
|
transaction = journal->j_committing_transaction;
|
|
|
|
|
|
|
|
/* Wait for the log commit to complete... */
|
|
|
|
if (transaction) {
|
|
|
|
tid_t tid = transaction->t_tid;
|
|
|
|
|
2010-08-04 01:35:12 +00:00
|
|
|
write_unlock(&journal->j_state_lock);
|
2006-10-11 08:20:59 +00:00
|
|
|
jbd2_log_wait_commit(journal, tid);
|
2006-10-11 08:20:57 +00:00
|
|
|
} else {
|
2010-08-04 01:35:12 +00:00
|
|
|
write_unlock(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/* ...and flush everything in the log out to disk. */
|
|
|
|
spin_lock(&journal->j_list_lock);
|
|
|
|
while (!err && journal->j_checkpoint_transactions != NULL) {
|
|
|
|
spin_unlock(&journal->j_list_lock);
|
2016-10-28 16:58:12 +00:00
|
|
|
mutex_lock_io(&journal->j_checkpoint_mutex);
|
2006-10-11 08:20:59 +00:00
|
|
|
err = jbd2_log_do_checkpoint(journal);
|
2008-10-11 00:29:13 +00:00
|
|
|
mutex_unlock(&journal->j_checkpoint_mutex);
|
2006-10-11 08:20:57 +00:00
|
|
|
spin_lock(&journal->j_list_lock);
|
|
|
|
}
|
|
|
|
spin_unlock(&journal->j_list_lock);
|
2008-10-11 00:29:13 +00:00
|
|
|
|
|
|
|
if (is_journal_aborted(journal))
|
|
|
|
return -EIO;
|
|
|
|
|
2016-10-28 16:58:12 +00:00
|
|
|
mutex_lock_io(&journal->j_checkpoint_mutex);
|
2015-06-15 18:36:01 +00:00
|
|
|
if (!err) {
|
|
|
|
err = jbd2_cleanup_journal_tail(journal);
|
|
|
|
if (err < 0) {
|
|
|
|
mutex_unlock(&journal->j_checkpoint_mutex);
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
err = 0;
|
|
|
|
}
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
/* Finally, mark the journal as really needing no recovery.
|
|
|
|
* This sets s_start==0 in the underlying superblock, which is
|
|
|
|
* the magic code for a fully-recovered superblock. Any future
|
|
|
|
* commits of data to the journal will restore the current
|
|
|
|
* s_start value. */
|
2023-11-29 11:47:40 +00:00
|
|
|
jbd2_mark_journal_empty(journal, REQ_FUA);
|
2021-05-18 15:13:25 +00:00
|
|
|
|
|
|
|
if (flags)
|
|
|
|
err = __jbd2_journal_erase(journal, flags);
|
|
|
|
|
2012-03-13 19:43:04 +00:00
|
|
|
mutex_unlock(&journal->j_checkpoint_mutex);
|
2010-08-04 01:35:12 +00:00
|
|
|
write_lock(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
J_ASSERT(!journal->j_running_transaction);
|
|
|
|
J_ASSERT(!journal->j_committing_transaction);
|
|
|
|
J_ASSERT(!journal->j_checkpoint_transactions);
|
|
|
|
J_ASSERT(journal->j_head == journal->j_tail);
|
|
|
|
J_ASSERT(journal->j_tail_sequence == journal->j_transaction_sequence);
|
2010-08-04 01:35:12 +00:00
|
|
|
write_unlock(&journal->j_state_lock);
|
2015-06-15 18:36:01 +00:00
|
|
|
out:
|
|
|
|
return err;
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
2020-11-16 10:18:08 +00:00
|
|
|
* jbd2_journal_wipe() - Wipe journal contents
|
2006-10-11 08:20:57 +00:00
|
|
|
* @journal: Journal to act on.
|
|
|
|
* @write: flag (see below)
|
|
|
|
*
|
|
|
|
* Wipe out all of the contents of a journal, safely. This will produce
|
|
|
|
* a warning if the journal contains any valid recovery information.
|
2006-10-11 08:20:59 +00:00
|
|
|
* Must be called between journal_init_*() and jbd2_journal_load().
|
2006-10-11 08:20:57 +00:00
|
|
|
*
|
|
|
|
* If 'write' is non-zero, then we wipe out the journal on disk; otherwise
|
|
|
|
* we merely suppress recovery.
|
|
|
|
*/
|
|
|
|
|
2006-10-11 08:20:59 +00:00
|
|
|
int jbd2_journal_wipe(journal_t *journal, int write)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
2023-08-11 06:36:07 +00:00
|
|
|
int err;
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2006-10-11 08:20:59 +00:00
|
|
|
J_ASSERT (!(journal->j_flags & JBD2_LOADED));
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
if (!journal->j_tail)
|
2023-08-11 06:36:07 +00:00
|
|
|
return 0;
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2011-11-01 23:09:18 +00:00
|
|
|
printk(KERN_WARNING "JBD2: %s recovery information on journal\n",
|
2006-10-11 08:20:57 +00:00
|
|
|
write ? "Clearing" : "Ignoring");
|
|
|
|
|
2006-10-11 08:20:59 +00:00
|
|
|
err = jbd2_journal_skip_recovery(journal);
|
2012-03-13 19:43:04 +00:00
|
|
|
if (write) {
|
|
|
|
/* Lock to make assertions happy... */
|
2019-02-01 04:42:11 +00:00
|
|
|
mutex_lock_io(&journal->j_checkpoint_mutex);
|
2023-11-29 11:47:40 +00:00
|
|
|
jbd2_mark_journal_empty(journal, REQ_FUA);
|
2012-03-13 19:43:04 +00:00
|
|
|
mutex_unlock(&journal->j_checkpoint_mutex);
|
|
|
|
}
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
2020-11-16 10:18:08 +00:00
|
|
|
* jbd2_journal_abort () - Shutdown the journal immediately.
|
2006-10-11 08:20:57 +00:00
|
|
|
* @journal: the journal to shutdown.
|
|
|
|
* @errno: an error number to record in the journal indicating
|
|
|
|
* the reason for the shutdown.
|
|
|
|
*
|
|
|
|
* Perform a complete, immediate shutdown of the ENTIRE
|
|
|
|
* journal (not of a single transaction). This operation cannot be
|
|
|
|
* undone without closing and reopening the journal.
|
|
|
|
*
|
2006-10-11 08:20:59 +00:00
|
|
|
* The jbd2_journal_abort function is intended to support higher level error
|
2006-10-11 08:20:57 +00:00
|
|
|
* recovery mechanisms such as the ext2/ext3 remount-readonly error
|
|
|
|
* mode.
|
|
|
|
*
|
|
|
|
* Journal abort has very specific semantics. Any existing dirty,
|
|
|
|
* unjournaled buffers in the main filesystem will still be written to
|
|
|
|
* disk by bdflush, but the journaling mechanism will be suspended
|
|
|
|
* immediately and no further transaction commits will be honoured.
|
|
|
|
*
|
|
|
|
* Any dirty, journaled buffers will be written back to disk without
|
|
|
|
* hitting the journal. Atomicity cannot be guaranteed on an aborted
|
|
|
|
* filesystem, but we _do_ attempt to leave as much data as possible
|
|
|
|
* behind for fsck to use for cleanup.
|
|
|
|
*
|
|
|
|
* Any attempt to get a new transaction handle on a journal which is in
|
|
|
|
* ABORT state will just result in an -EROFS error return. A
|
2006-10-11 08:20:59 +00:00
|
|
|
* jbd2_journal_stop on an existing handle will return -EIO if we have
|
2006-10-11 08:20:57 +00:00
|
|
|
* entered abort state during the update.
|
|
|
|
*
|
|
|
|
* Recursive transactions are not disturbed by journal abort until the
|
2006-10-11 08:20:59 +00:00
|
|
|
* final jbd2_journal_stop, which will receive the -EIO error.
|
2006-10-11 08:20:57 +00:00
|
|
|
*
|
2006-10-11 08:20:59 +00:00
|
|
|
* Finally, the jbd2_journal_abort call allows the caller to supply an errno
|
2006-10-11 08:20:57 +00:00
|
|
|
* which will be recorded (if possible) in the journal superblock. This
|
|
|
|
* allows a client to record failure conditions in the middle of a
|
|
|
|
* transaction without having to complete the transaction to record the
|
|
|
|
* failure to disk. ext3_error, for example, now uses this
|
|
|
|
* functionality.
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
2006-10-11 08:20:59 +00:00
|
|
|
void jbd2_journal_abort(journal_t *journal, int errno)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
2019-12-04 12:46:14 +00:00
|
|
|
transaction_t *transaction;
|
|
|
|
|
2020-06-09 07:35:40 +00:00
|
|
|
/*
|
|
|
|
* Lock the aborting procedure until everything is done, this avoid
|
|
|
|
* races between filesystem's error handling flow (e.g. ext4_abort()),
|
|
|
|
* ensure panic after the error info is written into journal's
|
|
|
|
* superblock.
|
|
|
|
*/
|
|
|
|
mutex_lock(&journal->j_abort_mutex);
|
2019-12-04 12:46:14 +00:00
|
|
|
/*
|
|
|
|
* ESHUTDOWN always takes precedence because a file system check
|
|
|
|
* caused by any other journal abort error is not required after
|
|
|
|
* a shutdown triggered.
|
|
|
|
*/
|
|
|
|
write_lock(&journal->j_state_lock);
|
|
|
|
if (journal->j_flags & JBD2_ABORT) {
|
|
|
|
int old_errno = journal->j_errno;
|
|
|
|
|
|
|
|
write_unlock(&journal->j_state_lock);
|
|
|
|
if (old_errno != -ESHUTDOWN && errno == -ESHUTDOWN) {
|
|
|
|
journal->j_errno = errno;
|
|
|
|
jbd2_journal_update_sb_errno(journal);
|
|
|
|
}
|
2020-06-09 07:35:40 +00:00
|
|
|
mutex_unlock(&journal->j_abort_mutex);
|
2019-12-04 12:46:14 +00:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Mark the abort as occurred and start current running transaction
|
|
|
|
* to release all journaled buffer.
|
|
|
|
*/
|
|
|
|
pr_err("Aborting journal on device %s.\n", journal->j_devname);
|
|
|
|
|
|
|
|
journal->j_flags |= JBD2_ABORT;
|
|
|
|
journal->j_errno = errno;
|
|
|
|
transaction = journal->j_running_transaction;
|
|
|
|
if (transaction)
|
|
|
|
__jbd2_log_start_commit(journal, transaction->t_tid);
|
|
|
|
write_unlock(&journal->j_state_lock);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Record errno to the journal super block, so that fsck and jbd2
|
|
|
|
* layer could realise that a filesystem check is needed.
|
|
|
|
*/
|
|
|
|
jbd2_journal_update_sb_errno(journal);
|
2020-06-09 07:35:40 +00:00
|
|
|
mutex_unlock(&journal->j_abort_mutex);
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
2020-11-16 10:18:08 +00:00
|
|
|
* jbd2_journal_errno() - returns the journal's error state.
|
2006-10-11 08:20:57 +00:00
|
|
|
* @journal: journal to examine.
|
|
|
|
*
|
2009-06-09 04:06:20 +00:00
|
|
|
* This is the errno number set with jbd2_journal_abort(), the last
|
2006-10-11 08:20:57 +00:00
|
|
|
* time the journal was mounted - if the journal was stopped
|
|
|
|
* without calling abort this will be 0.
|
|
|
|
*
|
|
|
|
* If the journal has been aborted on this mount time -EROFS will
|
|
|
|
* be returned.
|
|
|
|
*/
|
2006-10-11 08:20:59 +00:00
|
|
|
int jbd2_journal_errno(journal_t *journal)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
|
|
|
int err;
|
|
|
|
|
2010-08-04 01:35:12 +00:00
|
|
|
read_lock(&journal->j_state_lock);
|
2006-10-11 08:20:59 +00:00
|
|
|
if (journal->j_flags & JBD2_ABORT)
|
2006-10-11 08:20:57 +00:00
|
|
|
err = -EROFS;
|
|
|
|
else
|
|
|
|
err = journal->j_errno;
|
2010-08-04 01:35:12 +00:00
|
|
|
read_unlock(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
2020-11-16 10:18:08 +00:00
|
|
|
* jbd2_journal_clear_err() - clears the journal's error state
|
2006-10-11 08:20:57 +00:00
|
|
|
* @journal: journal to act on.
|
|
|
|
*
|
2009-06-09 04:06:20 +00:00
|
|
|
* An error must be cleared or acked to take a FS out of readonly
|
2006-10-11 08:20:57 +00:00
|
|
|
* mode.
|
|
|
|
*/
|
2006-10-11 08:20:59 +00:00
|
|
|
int jbd2_journal_clear_err(journal_t *journal)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
|
|
|
int err = 0;
|
|
|
|
|
2010-08-04 01:35:12 +00:00
|
|
|
write_lock(&journal->j_state_lock);
|
2006-10-11 08:20:59 +00:00
|
|
|
if (journal->j_flags & JBD2_ABORT)
|
2006-10-11 08:20:57 +00:00
|
|
|
err = -EROFS;
|
|
|
|
else
|
|
|
|
journal->j_errno = 0;
|
2010-08-04 01:35:12 +00:00
|
|
|
write_unlock(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
2020-11-16 10:18:08 +00:00
|
|
|
* jbd2_journal_ack_err() - Ack journal err.
|
2006-10-11 08:20:57 +00:00
|
|
|
* @journal: journal to act on.
|
|
|
|
*
|
2009-06-09 04:06:20 +00:00
|
|
|
* An error must be cleared or acked to take a FS out of readonly
|
2006-10-11 08:20:57 +00:00
|
|
|
* mode.
|
|
|
|
*/
|
2006-10-11 08:20:59 +00:00
|
|
|
void jbd2_journal_ack_err(journal_t *journal)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
2010-08-04 01:35:12 +00:00
|
|
|
write_lock(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
if (journal->j_errno)
|
2006-10-11 08:20:59 +00:00
|
|
|
journal->j_flags |= JBD2_ACK_ERR;
|
2010-08-04 01:35:12 +00:00
|
|
|
write_unlock(&journal->j_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
2006-10-11 08:20:59 +00:00
|
|
|
int jbd2_journal_blocks_per_page(struct inode *inode)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 12:29:47 +00:00
|
|
|
return 1 << (PAGE_SHIFT - inode->i_sb->s_blocksize_bits);
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
2006-10-11 08:21:08 +00:00
|
|
|
/*
|
|
|
|
* helper functions to deal with 32 or 64bit block numbers.
|
|
|
|
*/
|
|
|
|
size_t journal_tag_bytes(journal_t *journal)
|
|
|
|
{
|
2014-08-27 22:40:07 +00:00
|
|
|
size_t sz;
|
|
|
|
|
2015-10-17 20:18:45 +00:00
|
|
|
if (jbd2_has_feature_csum3(journal))
|
2014-08-27 22:40:07 +00:00
|
|
|
return sizeof(journal_block_tag3_t);
|
|
|
|
|
|
|
|
sz = sizeof(journal_block_tag_t);
|
2012-05-27 12:12:12 +00:00
|
|
|
|
2015-10-17 20:18:45 +00:00
|
|
|
if (jbd2_has_feature_csum2(journal))
|
2014-08-27 22:40:07 +00:00
|
|
|
sz += sizeof(__u16);
|
2012-05-27 12:12:12 +00:00
|
|
|
|
2015-10-17 20:18:45 +00:00
|
|
|
if (jbd2_has_feature_64bit(journal))
|
2014-08-27 22:40:07 +00:00
|
|
|
return sz;
|
2006-10-11 08:21:08 +00:00
|
|
|
else
|
2014-08-27 22:40:07 +00:00
|
|
|
return sz - sizeof(__u32);
|
2006-10-11 08:21:08 +00:00
|
|
|
}
|
|
|
|
|
2009-12-07 15:36:20 +00:00
|
|
|
/*
|
|
|
|
* JBD memory management
|
|
|
|
*
|
|
|
|
* These functions are used to allocate block-sized chunks of memory
|
|
|
|
* used for making copies of buffer_head data. Very often it will be
|
|
|
|
* page-sized chunks of data, but sometimes it will be in
|
|
|
|
* sub-page-size chunks. (For example, 16k pages on Power systems
|
|
|
|
* with a 4k block file system.) For blocks smaller than a page, we
|
|
|
|
* use a SLAB allocator. There are slab caches for each block size,
|
|
|
|
* which are allocated at mount time, if necessary, and we only free
|
|
|
|
* (all of) the slab caches when/if the jbd2 module is unloaded. For
|
|
|
|
* this reason we don't need to a mutex to protect access to
|
|
|
|
* jbd2_slab[] allocating or releasing memory; only in
|
|
|
|
* jbd2_journal_create_slab().
|
|
|
|
*/
|
|
|
|
#define JBD2_MAX_SLABS 8
|
|
|
|
static struct kmem_cache *jbd2_slab[JBD2_MAX_SLABS];
|
|
|
|
|
|
|
|
static const char *jbd2_slab_names[JBD2_MAX_SLABS] = {
|
|
|
|
"jbd2_1k", "jbd2_2k", "jbd2_4k", "jbd2_8k",
|
|
|
|
"jbd2_16k", "jbd2_32k", "jbd2_64k", "jbd2_128k"
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
|
|
static void jbd2_journal_destroy_slabs(void)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for (i = 0; i < JBD2_MAX_SLABS; i++) {
|
2018-05-21 02:38:26 +00:00
|
|
|
kmem_cache_destroy(jbd2_slab[i]);
|
2009-12-07 15:36:20 +00:00
|
|
|
jbd2_slab[i] = NULL;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static int jbd2_journal_create_slab(size_t size)
|
|
|
|
{
|
2010-10-16 20:34:39 +00:00
|
|
|
static DEFINE_MUTEX(jbd2_slab_create_mutex);
|
2009-12-07 15:36:20 +00:00
|
|
|
int i = order_base_2(size) - 10;
|
|
|
|
size_t slab_size;
|
|
|
|
|
|
|
|
if (size == PAGE_SIZE)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
if (i >= JBD2_MAX_SLABS)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if (unlikely(i < 0))
|
|
|
|
i = 0;
|
2010-10-16 20:34:39 +00:00
|
|
|
mutex_lock(&jbd2_slab_create_mutex);
|
2009-12-07 15:36:20 +00:00
|
|
|
if (jbd2_slab[i]) {
|
2010-10-16 20:34:39 +00:00
|
|
|
mutex_unlock(&jbd2_slab_create_mutex);
|
2009-12-07 15:36:20 +00:00
|
|
|
return 0; /* Already created */
|
|
|
|
}
|
|
|
|
|
|
|
|
slab_size = 1 << (i+10);
|
|
|
|
jbd2_slab[i] = kmem_cache_create(jbd2_slab_names[i], slab_size,
|
|
|
|
slab_size, 0, NULL);
|
2010-10-16 20:34:39 +00:00
|
|
|
mutex_unlock(&jbd2_slab_create_mutex);
|
2009-12-07 15:36:20 +00:00
|
|
|
if (!jbd2_slab[i]) {
|
|
|
|
printk(KERN_EMERG "JBD2: no memory for jbd2_slab cache\n");
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct kmem_cache *get_slab(size_t size)
|
|
|
|
{
|
|
|
|
int i = order_base_2(size) - 10;
|
|
|
|
|
|
|
|
BUG_ON(i >= JBD2_MAX_SLABS);
|
|
|
|
if (unlikely(i < 0))
|
|
|
|
i = 0;
|
2010-04-30 13:34:31 +00:00
|
|
|
BUG_ON(jbd2_slab[i] == NULL);
|
2009-12-07 15:36:20 +00:00
|
|
|
return jbd2_slab[i];
|
|
|
|
}
|
|
|
|
|
|
|
|
void *jbd2_alloc(size_t size, gfp_t flags)
|
|
|
|
{
|
|
|
|
void *ptr;
|
|
|
|
|
|
|
|
BUG_ON(size & (size-1)); /* Must be a power of 2 */
|
|
|
|
|
2016-06-24 21:49:28 +00:00
|
|
|
if (size < PAGE_SIZE)
|
2009-12-07 15:36:20 +00:00
|
|
|
ptr = kmem_cache_alloc(get_slab(size), flags);
|
2016-06-24 21:49:28 +00:00
|
|
|
else
|
|
|
|
ptr = (void *)__get_free_pages(flags, get_order(size));
|
2009-12-07 15:36:20 +00:00
|
|
|
|
|
|
|
/* Check alignment; SLUB has gotten this wrong in the past,
|
|
|
|
* and this can lead to user data corruption! */
|
|
|
|
BUG_ON(((unsigned long) ptr) & (size-1));
|
|
|
|
|
|
|
|
return ptr;
|
|
|
|
}
|
|
|
|
|
|
|
|
void jbd2_free(void *ptr, size_t size)
|
|
|
|
{
|
2016-06-24 21:49:28 +00:00
|
|
|
if (size < PAGE_SIZE)
|
|
|
|
kmem_cache_free(get_slab(size), ptr);
|
|
|
|
else
|
|
|
|
free_pages((unsigned long)ptr, get_order(size));
|
2009-12-07 15:36:20 +00:00
|
|
|
};
|
|
|
|
|
2006-10-11 08:20:57 +00:00
|
|
|
/*
|
|
|
|
* Journal_head storage management
|
|
|
|
*/
|
2006-12-07 04:33:20 +00:00
|
|
|
static struct kmem_cache *jbd2_journal_head_cache;
|
2007-07-18 12:57:06 +00:00
|
|
|
#ifdef CONFIG_JBD2_DEBUG
|
2006-10-11 08:20:57 +00:00
|
|
|
static atomic_t nr_journal_heads = ATOMIC_INIT(0);
|
|
|
|
#endif
|
|
|
|
|
2019-05-11 01:15:47 +00:00
|
|
|
static int __init jbd2_journal_init_journal_head_cache(void)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
2019-05-11 01:15:47 +00:00
|
|
|
J_ASSERT(!jbd2_journal_head_cache);
|
2006-10-11 08:21:00 +00:00
|
|
|
jbd2_journal_head_cache = kmem_cache_create("jbd2_journal_head",
|
2006-10-11 08:20:57 +00:00
|
|
|
sizeof(struct journal_head),
|
|
|
|
0, /* offset */
|
2017-01-18 10:53:44 +00:00
|
|
|
SLAB_TEMPORARY | SLAB_TYPESAFE_BY_RCU,
|
2007-07-20 01:11:58 +00:00
|
|
|
NULL); /* ctor */
|
2008-03-29 03:07:18 +00:00
|
|
|
if (!jbd2_journal_head_cache) {
|
2011-11-01 23:09:18 +00:00
|
|
|
printk(KERN_EMERG "JBD2: no memory for journal_head cache\n");
|
2019-05-11 01:15:47 +00:00
|
|
|
return -ENOMEM;
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
2019-05-11 01:15:47 +00:00
|
|
|
return 0;
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
2012-02-20 22:53:03 +00:00
|
|
|
static void jbd2_journal_destroy_journal_head_cache(void)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
2018-05-21 02:38:26 +00:00
|
|
|
kmem_cache_destroy(jbd2_journal_head_cache);
|
|
|
|
jbd2_journal_head_cache = NULL;
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* journal_head splicing and dicing
|
|
|
|
*/
|
|
|
|
static struct journal_head *journal_alloc_journal_head(void)
|
|
|
|
{
|
|
|
|
struct journal_head *ret;
|
|
|
|
|
2007-07-18 12:57:06 +00:00
|
|
|
#ifdef CONFIG_JBD2_DEBUG
|
2006-10-11 08:20:57 +00:00
|
|
|
atomic_inc(&nr_journal_heads);
|
|
|
|
#endif
|
2013-05-28 11:27:11 +00:00
|
|
|
ret = kmem_cache_zalloc(jbd2_journal_head_cache, GFP_NOFS);
|
2008-03-29 03:07:18 +00:00
|
|
|
if (!ret) {
|
2022-06-08 11:23:48 +00:00
|
|
|
jbd2_debug(1, "out of memory for journal_head\n");
|
2010-12-17 15:44:16 +00:00
|
|
|
pr_notice_ratelimited("ENOMEM in %s, retrying.\n", __func__);
|
2015-06-15 19:45:58 +00:00
|
|
|
ret = kmem_cache_zalloc(jbd2_journal_head_cache,
|
|
|
|
GFP_NOFS | __GFP_NOFAIL);
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
2019-08-09 12:42:32 +00:00
|
|
|
if (ret)
|
|
|
|
spin_lock_init(&ret->b_state_lock);
|
2006-10-11 08:20:57 +00:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void journal_free_journal_head(struct journal_head *jh)
|
|
|
|
{
|
2007-07-18 12:57:06 +00:00
|
|
|
#ifdef CONFIG_JBD2_DEBUG
|
2006-10-11 08:20:57 +00:00
|
|
|
atomic_dec(&nr_journal_heads);
|
2007-10-16 22:38:25 +00:00
|
|
|
memset(jh, JBD2_POISON_FREE, sizeof(*jh));
|
2006-10-11 08:20:57 +00:00
|
|
|
#endif
|
2006-10-11 08:20:59 +00:00
|
|
|
kmem_cache_free(jbd2_journal_head_cache, jh);
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* A journal_head is attached to a buffer_head whenever JBD has an
|
|
|
|
* interest in the buffer.
|
|
|
|
*
|
|
|
|
* Whenever a buffer has an attached journal_head, its ->b_state:BH_JBD bit
|
|
|
|
* is set. This bit is tested in core kernel code where we need to take
|
|
|
|
* JBD-specific actions. Testing the zeroness of ->b_private is not reliable
|
|
|
|
* there.
|
|
|
|
*
|
|
|
|
* When a buffer has its BH_JBD bit set, its ->b_count is elevated by one.
|
|
|
|
*
|
|
|
|
* When a buffer has its BH_JBD bit set it is immune from being released by
|
|
|
|
* core kernel code, mainly via ->b_count.
|
|
|
|
*
|
2011-06-13 19:38:22 +00:00
|
|
|
* A journal_head is detached from its buffer_head when the journal_head's
|
|
|
|
* b_jcount reaches zero. Running transaction (b_transaction) and checkpoint
|
|
|
|
* transaction (b_cp_transaction) hold their references to b_jcount.
|
2006-10-11 08:20:57 +00:00
|
|
|
*
|
|
|
|
* Various places in the kernel want to attach a journal_head to a buffer_head
|
|
|
|
* _before_ attaching the journal_head to a transaction. To protect the
|
2006-10-11 08:20:59 +00:00
|
|
|
* journal_head in this situation, jbd2_journal_add_journal_head elevates the
|
2006-10-11 08:20:57 +00:00
|
|
|
* journal_head's b_jcount refcount by one. The caller must call
|
2006-10-11 08:20:59 +00:00
|
|
|
* jbd2_journal_put_journal_head() to undo this.
|
2006-10-11 08:20:57 +00:00
|
|
|
*
|
|
|
|
* So the typical usage would be:
|
|
|
|
*
|
|
|
|
* (Attach a journal_head if needed. Increments b_jcount)
|
2006-10-11 08:20:59 +00:00
|
|
|
* struct journal_head *jh = jbd2_journal_add_journal_head(bh);
|
2006-10-11 08:20:57 +00:00
|
|
|
* ...
|
2011-06-13 19:38:22 +00:00
|
|
|
* (Get another reference for transaction)
|
|
|
|
* jbd2_journal_grab_journal_head(bh);
|
2006-10-11 08:20:57 +00:00
|
|
|
* jh->b_transaction = xxx;
|
2011-06-13 19:38:22 +00:00
|
|
|
* (Put original reference)
|
2006-10-11 08:20:59 +00:00
|
|
|
* jbd2_journal_put_journal_head(jh);
|
2006-10-11 08:20:57 +00:00
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Give a buffer_head a journal_head.
|
|
|
|
*
|
|
|
|
* May sleep.
|
|
|
|
*/
|
2006-10-11 08:20:59 +00:00
|
|
|
struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
|
|
|
struct journal_head *jh;
|
|
|
|
struct journal_head *new_jh = NULL;
|
|
|
|
|
|
|
|
repeat:
|
2013-05-28 11:27:11 +00:00
|
|
|
if (!buffer_jbd(bh))
|
2006-10-11 08:20:57 +00:00
|
|
|
new_jh = journal_alloc_journal_head();
|
|
|
|
|
|
|
|
jbd_lock_bh_journal_head(bh);
|
|
|
|
if (buffer_jbd(bh)) {
|
|
|
|
jh = bh2jh(bh);
|
|
|
|
} else {
|
|
|
|
J_ASSERT_BH(bh,
|
|
|
|
(atomic_read(&bh->b_count) > 0) ||
|
2022-12-15 21:43:59 +00:00
|
|
|
(bh->b_folio && bh->b_folio->mapping));
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
if (!new_jh) {
|
|
|
|
jbd_unlock_bh_journal_head(bh);
|
|
|
|
goto repeat;
|
|
|
|
}
|
|
|
|
|
|
|
|
jh = new_jh;
|
|
|
|
new_jh = NULL; /* We consumed it */
|
|
|
|
set_buffer_jbd(bh);
|
|
|
|
bh->b_private = jh;
|
|
|
|
jh->b_bh = bh;
|
|
|
|
get_bh(bh);
|
|
|
|
BUFFER_TRACE(bh, "added journal_head");
|
|
|
|
}
|
|
|
|
jh->b_jcount++;
|
|
|
|
jbd_unlock_bh_journal_head(bh);
|
|
|
|
if (new_jh)
|
|
|
|
journal_free_journal_head(new_jh);
|
|
|
|
return bh->b_private;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Grab a ref against this buffer_head's journal_head. If it ended up not
|
|
|
|
* having a journal_head, return NULL
|
|
|
|
*/
|
2006-10-11 08:20:59 +00:00
|
|
|
struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
|
|
|
struct journal_head *jh = NULL;
|
|
|
|
|
|
|
|
jbd_lock_bh_journal_head(bh);
|
|
|
|
if (buffer_jbd(bh)) {
|
|
|
|
jh = bh2jh(bh);
|
|
|
|
jh->b_jcount++;
|
|
|
|
}
|
|
|
|
jbd_unlock_bh_journal_head(bh);
|
|
|
|
return jh;
|
|
|
|
}
|
2022-01-29 21:41:23 +00:00
|
|
|
EXPORT_SYMBOL(jbd2_journal_grab_journal_head);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
|
|
|
static void __journal_remove_journal_head(struct buffer_head *bh)
|
|
|
|
{
|
|
|
|
struct journal_head *jh = bh2jh(bh);
|
|
|
|
|
2011-06-13 19:38:22 +00:00
|
|
|
J_ASSERT_JH(jh, jh->b_transaction == NULL);
|
|
|
|
J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
|
|
|
|
J_ASSERT_JH(jh, jh->b_cp_transaction == NULL);
|
|
|
|
J_ASSERT_JH(jh, jh->b_jlist == BJ_None);
|
|
|
|
J_ASSERT_BH(bh, buffer_jbd(bh));
|
|
|
|
J_ASSERT_BH(bh, jh2bh(jh) == bh);
|
|
|
|
BUFFER_TRACE(bh, "remove journal_head");
|
2019-08-09 12:42:33 +00:00
|
|
|
|
|
|
|
/* Unlink before dropping the lock */
|
|
|
|
bh->b_private = NULL;
|
|
|
|
jh->b_bh = NULL; /* debug, really */
|
|
|
|
clear_buffer_jbd(bh);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void journal_release_journal_head(struct journal_head *jh, size_t b_size)
|
|
|
|
{
|
2011-06-13 19:38:22 +00:00
|
|
|
if (jh->b_frozen_data) {
|
|
|
|
printk(KERN_WARNING "%s: freeing b_frozen_data\n", __func__);
|
2019-08-09 12:42:33 +00:00
|
|
|
jbd2_free(jh->b_frozen_data, b_size);
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
2011-06-13 19:38:22 +00:00
|
|
|
if (jh->b_committed_data) {
|
|
|
|
printk(KERN_WARNING "%s: freeing b_committed_data\n", __func__);
|
2019-08-09 12:42:33 +00:00
|
|
|
jbd2_free(jh->b_committed_data, b_size);
|
2011-06-13 19:38:22 +00:00
|
|
|
}
|
|
|
|
journal_free_journal_head(jh);
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2011-06-13 19:38:22 +00:00
|
|
|
* Drop a reference on the passed journal_head. If it fell to zero then
|
2006-10-11 08:20:57 +00:00
|
|
|
* release the journal_head from the buffer_head.
|
|
|
|
*/
|
2006-10-11 08:20:59 +00:00
|
|
|
void jbd2_journal_put_journal_head(struct journal_head *jh)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
|
|
|
struct buffer_head *bh = jh2bh(jh);
|
|
|
|
|
|
|
|
jbd_lock_bh_journal_head(bh);
|
|
|
|
J_ASSERT_JH(jh, jh->b_jcount > 0);
|
|
|
|
--jh->b_jcount;
|
2011-06-13 19:38:22 +00:00
|
|
|
if (!jh->b_jcount) {
|
2006-10-11 08:20:57 +00:00
|
|
|
__journal_remove_journal_head(bh);
|
2011-06-13 19:38:22 +00:00
|
|
|
jbd_unlock_bh_journal_head(bh);
|
2019-08-09 12:42:33 +00:00
|
|
|
journal_release_journal_head(jh, bh->b_size);
|
2006-10-11 08:20:57 +00:00
|
|
|
__brelse(bh);
|
2019-08-09 12:42:33 +00:00
|
|
|
} else {
|
2011-06-13 19:38:22 +00:00
|
|
|
jbd_unlock_bh_journal_head(bh);
|
2019-08-09 12:42:33 +00:00
|
|
|
}
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
2022-01-29 21:41:23 +00:00
|
|
|
EXPORT_SYMBOL(jbd2_journal_put_journal_head);
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2008-07-11 23:27:31 +00:00
|
|
|
/*
|
|
|
|
* Initialize jbd inode head
|
|
|
|
*/
|
|
|
|
void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode)
|
|
|
|
{
|
|
|
|
jinode->i_transaction = NULL;
|
|
|
|
jinode->i_next_transaction = NULL;
|
|
|
|
jinode->i_vfs_inode = inode;
|
|
|
|
jinode->i_flags = 0;
|
2019-06-20 21:24:56 +00:00
|
|
|
jinode->i_dirty_start = 0;
|
|
|
|
jinode->i_dirty_end = 0;
|
2008-07-11 23:27:31 +00:00
|
|
|
INIT_LIST_HEAD(&jinode->i_list);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Function to be called before we start removing inode from memory (i.e.,
|
|
|
|
* clear_inode() is a fine place to be called from). It removes inode from
|
|
|
|
* transaction's lists.
|
|
|
|
*/
|
|
|
|
void jbd2_journal_release_jbd_inode(journal_t *journal,
|
|
|
|
struct jbd2_inode *jinode)
|
|
|
|
{
|
|
|
|
if (!journal)
|
|
|
|
return;
|
|
|
|
restart:
|
|
|
|
spin_lock(&journal->j_list_lock);
|
|
|
|
/* Is commit writing out inode - we have to wait */
|
2016-02-23 04:20:30 +00:00
|
|
|
if (jinode->i_flags & JI_COMMIT_RUNNING) {
|
2008-07-11 23:27:31 +00:00
|
|
|
wait_queue_head_t *wq;
|
|
|
|
DEFINE_WAIT_BIT(wait, &jinode->i_flags, __JI_COMMIT_RUNNING);
|
|
|
|
wq = bit_waitqueue(&jinode->i_flags, __JI_COMMIT_RUNNING);
|
2017-03-05 10:25:39 +00:00
|
|
|
prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
|
2008-07-11 23:27:31 +00:00
|
|
|
spin_unlock(&journal->j_list_lock);
|
|
|
|
schedule();
|
2017-03-05 10:25:39 +00:00
|
|
|
finish_wait(wq, &wait.wq_entry);
|
2008-07-11 23:27:31 +00:00
|
|
|
goto restart;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (jinode->i_transaction) {
|
|
|
|
list_del(&jinode->i_list);
|
|
|
|
jinode->i_transaction = NULL;
|
|
|
|
}
|
|
|
|
spin_unlock(&journal->j_list_lock);
|
|
|
|
}
|
|
|
|
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2008-01-29 04:58:27 +00:00
|
|
|
#ifdef CONFIG_PROC_FS
|
|
|
|
|
|
|
|
#define JBD2_STATS_PROC_NAME "fs/jbd2"
|
|
|
|
|
|
|
|
static void __init jbd2_create_jbd_stats_proc_entry(void)
|
|
|
|
{
|
|
|
|
proc_jbd2_stats = proc_mkdir(JBD2_STATS_PROC_NAME, NULL);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void __exit jbd2_remove_jbd_stats_proc_entry(void)
|
|
|
|
{
|
|
|
|
if (proc_jbd2_stats)
|
|
|
|
remove_proc_entry(JBD2_STATS_PROC_NAME, NULL);
|
|
|
|
}
|
|
|
|
|
|
|
|
#else
|
|
|
|
|
|
|
|
#define jbd2_create_jbd_stats_proc_entry() do {} while (0)
|
|
|
|
#define jbd2_remove_jbd_stats_proc_entry() do {} while (0)
|
|
|
|
|
|
|
|
#endif
|
|
|
|
|
2011-01-10 17:29:43 +00:00
|
|
|
struct kmem_cache *jbd2_handle_cache, *jbd2_inode_cache;
|
2006-10-11 08:20:57 +00:00
|
|
|
|
2019-05-11 01:15:47 +00:00
|
|
|
static int __init jbd2_journal_init_inode_cache(void)
|
|
|
|
{
|
|
|
|
J_ASSERT(!jbd2_inode_cache);
|
|
|
|
jbd2_inode_cache = KMEM_CACHE(jbd2_inode, 0);
|
|
|
|
if (!jbd2_inode_cache) {
|
|
|
|
pr_emerg("JBD2: failed to create inode cache\n");
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2012-02-20 22:53:03 +00:00
|
|
|
static int __init jbd2_journal_init_handle_cache(void)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
2019-05-11 01:15:47 +00:00
|
|
|
J_ASSERT(!jbd2_handle_cache);
|
2011-01-10 17:29:43 +00:00
|
|
|
jbd2_handle_cache = KMEM_CACHE(jbd2_journal_handle, SLAB_TEMPORARY);
|
2019-05-11 01:15:47 +00:00
|
|
|
if (!jbd2_handle_cache) {
|
2011-01-10 17:29:43 +00:00
|
|
|
printk(KERN_EMERG "JBD2: failed to create handle cache\n");
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
2006-10-11 08:20:57 +00:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2019-05-11 01:15:47 +00:00
|
|
|
static void jbd2_journal_destroy_inode_cache(void)
|
|
|
|
{
|
|
|
|
kmem_cache_destroy(jbd2_inode_cache);
|
|
|
|
jbd2_inode_cache = NULL;
|
|
|
|
}
|
|
|
|
|
2006-10-11 08:20:59 +00:00
|
|
|
static void jbd2_journal_destroy_handle_cache(void)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
2018-05-21 02:38:26 +00:00
|
|
|
kmem_cache_destroy(jbd2_handle_cache);
|
|
|
|
jbd2_handle_cache = NULL;
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Module startup and shutdown
|
|
|
|
*/
|
|
|
|
|
|
|
|
static int __init journal_init_caches(void)
|
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
|
2019-05-11 01:15:47 +00:00
|
|
|
ret = jbd2_journal_init_revoke_record_cache();
|
|
|
|
if (ret == 0)
|
|
|
|
ret = jbd2_journal_init_revoke_table_cache();
|
2006-10-11 08:20:57 +00:00
|
|
|
if (ret == 0)
|
2012-02-20 22:53:03 +00:00
|
|
|
ret = jbd2_journal_init_journal_head_cache();
|
2006-10-11 08:20:57 +00:00
|
|
|
if (ret == 0)
|
2012-02-20 22:53:03 +00:00
|
|
|
ret = jbd2_journal_init_handle_cache();
|
2019-05-11 01:15:47 +00:00
|
|
|
if (ret == 0)
|
|
|
|
ret = jbd2_journal_init_inode_cache();
|
2006-10-11 08:20:57 +00:00
|
|
|
if (ret == 0)
|
2012-02-20 22:53:02 +00:00
|
|
|
ret = jbd2_journal_init_transaction_cache();
|
2006-10-11 08:20:57 +00:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2006-10-11 08:20:59 +00:00
|
|
|
static void jbd2_journal_destroy_caches(void)
|
2006-10-11 08:20:57 +00:00
|
|
|
{
|
2019-05-11 01:15:47 +00:00
|
|
|
jbd2_journal_destroy_revoke_record_cache();
|
|
|
|
jbd2_journal_destroy_revoke_table_cache();
|
2012-02-20 22:53:03 +00:00
|
|
|
jbd2_journal_destroy_journal_head_cache();
|
2006-10-11 08:20:59 +00:00
|
|
|
jbd2_journal_destroy_handle_cache();
|
2019-05-11 01:15:47 +00:00
|
|
|
jbd2_journal_destroy_inode_cache();
|
2012-02-20 22:53:02 +00:00
|
|
|
jbd2_journal_destroy_transaction_cache();
|
2009-12-07 15:36:20 +00:00
|
|
|
jbd2_journal_destroy_slabs();
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static int __init journal_init(void)
|
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
BUILD_BUG_ON(sizeof(struct journal_superblock_s) != 1024);
|
|
|
|
|
|
|
|
ret = journal_init_caches();
|
2008-04-30 02:02:47 +00:00
|
|
|
if (ret == 0) {
|
|
|
|
jbd2_create_jbd_stats_proc_entry();
|
|
|
|
} else {
|
2006-10-11 08:20:59 +00:00
|
|
|
jbd2_journal_destroy_caches();
|
2008-04-30 02:02:47 +00:00
|
|
|
}
|
2006-10-11 08:20:57 +00:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void __exit journal_exit(void)
|
|
|
|
{
|
2007-07-18 12:57:06 +00:00
|
|
|
#ifdef CONFIG_JBD2_DEBUG
|
2006-10-11 08:20:57 +00:00
|
|
|
int n = atomic_read(&nr_journal_heads);
|
|
|
|
if (n)
|
2013-12-09 02:13:59 +00:00
|
|
|
printk(KERN_ERR "JBD2: leaked %d journal_heads!\n", n);
|
2006-10-11 08:20:57 +00:00
|
|
|
#endif
|
2008-01-29 04:58:27 +00:00
|
|
|
jbd2_remove_jbd_stats_proc_entry();
|
2006-10-11 08:20:59 +00:00
|
|
|
jbd2_journal_destroy_caches();
|
2006-10-11 08:20:57 +00:00
|
|
|
}
|
|
|
|
|
2024-05-26 18:53:49 +00:00
|
|
|
MODULE_DESCRIPTION("Generic filesystem journal-writing module");
|
2006-10-11 08:20:57 +00:00
|
|
|
MODULE_LICENSE("GPL");
|
|
|
|
module_init(journal_init);
|
|
|
|
module_exit(journal_exit);
|
|
|
|
|